Search

Physical aggression is a serious and widespread problem in society, affecting people worldwide. It impacts nearly every aspect of life. While some studies explore the root causes of violent behavior, others focus on urban planning in high-crime areas. Real-time violence detection, powered by artificial intelligence, offers a direct and efficient solution, reducing the need for extensive human supervision and saving lives. This paper is a continuation of a systematic mapping study and its objective is to provide a comprehensive and up-to-date review of AI-based video violence detection, specifically in physical assaults. Regarding violence detection, the following have been grouped and categorized from the review of the selected papers: 21 challenges that remain to be solved, 28 datasets that have been created in recent years, 21 keyframe extraction methods, 16 types of algorithm inputs, as well as a wide variety of algorithm combinations and their corresponding accuracy results. Given the lack of recent reviews dealing with the detection of violence in video, this study is considered necessary and relevant. [ABSTRACT FROM AUTHOR]

Technological advancements have expanded the range of methods for capturing human body motion, including solutions involving inertial sensors (IMUs) and optical alternatives. However, the rising complexity and costs associated with commercial solutions have prompted the exploration of more cost-effective alternatives. This paper presents a markerless optical motion capture system using a RealSense depth camera and intelligent computer vision algorithms. It facilitates precise posture assessment, the real-time calculation of joint angles, and acquisition of subject-specific anthropometric data for gait analysis. The proposed system stands out for its simplicity and affordability in comparison to complex commercial solutions. The gathered data are stored in comma-separated value (CSV) files, simplifying subsequent analysis and data mining. Preliminary tests, conducted in controlled laboratory environments and employing a commercial MEMS-IMU system as a reference, revealed a maximum relative error of 7.6% in anthropometric measurements, with a maximum absolute error of 4.67 cm at average height. Stride length measurements showed a maximum relative error of 11.2%. Static joint angle tests had a maximum average error of 10.2%, while dynamic joint angle tests showed a maximum average error of 9.06%. The proposed optical system offers sufficient accuracy for potential application in areas such as rehabilitation, sports analysis, and entertainment. [ABSTRACT FROM AUTHOR]

High-pressure pipelines are critical for transporting hazardous materials over long distances, but they face threats from third-party interference activities. Preventive measures are implemented, but interference accidents can still occur, making the need for high-quality detection strategies vital. This paper proposes an end-to-end Artificial Intelligence of Things (AIoT) solution to detect potential interference threats in real time. The solution involves developing a smart visual sensor capable of processing images using state-of-the-art computer vision algorithms and transmitting alerts to pipeline operators in real time. The system's core is based on the object-detection model (e.g., You Only Look Once version 4 (YOLOv4) and DETR with Improved deNoising anchOr boxes (DINO)), trained on a custom Pipeline Visual Threat Assessment (Pipe-VisTA) dataset. Among the trained models, DINO was able to achieve the best Mean Average Precision (mAP) of 71.2% for the unseen test dataset. However, for the deployment on a limited computational-ability edge computer (i.e., the NVIDIA Jetson Nano), the simpler and TensorRT-optimized YOLOv4 model was used, which achieved a mAP of 61.8% for the test dataset. The developed AIoT device captures the image using a camera, processes on the edge using the trained YOLOv4 model to detect the potential threat, transmits the threat alert to a Fleet Portal via LoRaWAN, and hosts the alert on a dashboard via a satellite network. The device has been fully tested in the field to ensure its functionality prior to deployment for the SEA Gas use-case. The AIoT smart solution has been deployed across the 10km stretch of the SEA Gas pipeline across the Murray Bridge section. In total, 48 AIoT devices and three Fleet Portals are installed to ensure the line-of-sight communication between the devices and portals. [ABSTRACT FROM AUTHOR]

This paper presents a computer vision-based approach to chronic subdural hematoma segmentation that can be performed by one click. Chronic subdural hematoma is estimated to occur in 0.002–0.02% of the general population each year and the risk increases with age, with a high frequency of about 0.05–0.06% in people aged 70 years and above. In our research, we developed our own dataset, which includes 53 series of CT scans collected from 21 patients with one or two hematomas. Based on the dataset, we trained two neural network models based on U-Net architecture to automate the manual segmentation process. One of the models performed segmentation based only on the current frame, while the other additionally processed multiple adjacent images to provide context, a technique that is more similar to the behavior of a doctor. We used a 10-fold cross-validation technique to better estimate the developed models' efficiency. We used the Dice metric for segmentation accuracy estimation, which was 0.77. Also, for testing our approach, we used scans from five additional patients who did not form part of the dataset, and created a scenario in which three medical experts carried out a hematoma segmentation before we carried out segmentation using our best model. We developed the OsiriX DICOM Viewer plugin to implement our solution into the segmentation process. We compared the segmentation time, which was more than seven times faster using the one-click approach, and the experts agreed that the segmentation quality was acceptable for clinical usage. [ABSTRACT FROM AUTHOR]

Anomaly detection in video surveillance is a highly developed subject that is attracting increased attention from the research community. There is great demand for intelligent systems with the capacity to automatically detect anomalous events in streaming videos. Due to this, a wide variety of approaches have been proposed to build an effective model that would ensure public security. There has been a variety of surveys of anomaly detection, such as of network anomaly detection, financial fraud detection, human behavioral analysis, and many more. Deep learning has been successfully applied to many aspects of computer vision. In particular, the strong growth of generative models means that these are the main techniques used in the proposed methods. This paper aims to provide a comprehensive review of the deep learning-based techniques used in the field of video anomaly detection. Specifically, deep learning-based approaches have been categorized into different methods by their objectives and learning metrics. Additionally, preprocessing and feature engineering techniques are discussed thoroughly for the vision-based domain. This paper also describes the benchmark databases used in training and detecting abnormal human behavior. Finally, the common challenges in video surveillance are discussed, to offer some possible solutions and directions for future research. [ABSTRACT FROM AUTHOR]

In the realm of intelligent sensor systems, the dependence on Artificial Intelligence (AI) applications has heightened the importance of interpretability. This is particularly critical for opaque models such as Deep Neural Networks (DNN), as understanding their decisions is essential, not only for ethical and regulatory compliance, but also for fostering trust in AI-driven outcomes. This paper introduces the novel concept of a Computer Vision Interpretability Index (CVII). The CVII framework is designed to emulate human cognitive processes, specifically in tasks related to vision. It addresses the intricate challenge of quantifying interpretability, a task that is inherently subjective and varies across domains. The CVII is rigorously evaluated using a range of computer vision models applied to the COCO (Common Objects in Context) dataset, a widely recognized benchmark in the field. The findings established a robust correlation between image interpretability, model selection, and CVII scores. This research makes a substantial contribution to enhancing interpretability for human comprehension, as well as within intelligent sensor applications. By promoting transparency and reliability in AI-driven decision-making, the CVII framework empowers its stakeholders to effectively harness the full potential of AI technologies. [ABSTRACT FROM AUTHOR]

The presented paper investigates the problem of endoscopic bleeding detection in endoscopic videos in the form of a binary image classification task. A set of definitions of high-level visual features of endoscopic bleeding is introduced, which incorporates domain knowledge from the field. The high-level features are coupled with respective feature descriptors, enabling automatic capture of the features using image processing methods. Each of the proposed feature descriptors outputs a feature activation map in the form of a grayscale image. Acquired feature maps can be appended in a straightforward way to the original color channels of the input image and passed to the input of a convolutional neural network during the training and inference steps. An experimental evaluation is conducted to compare the classification ROC AUC of feature-extended convolutional neural network models with baseline models using regular color image inputs. The advantage of feature-extended models is demonstrated for the Resnet and VGG convolutional neural network architectures. [ABSTRACT FROM AUTHOR]

Recent studies indicate that food demand will increase by 35–56% over the period 2010–2050 due to population increase, economic development, and urbanization. Greenhouse systems allow for the sustainable intensification of food production with demonstrated high crop production per cultivation area. Breakthroughs in resource-efficient fresh food production merging horticultural and AI expertise take place with the international competition "Autonomous Greenhouse Challenge". This paper describes and analyzes the results of the third edition of this competition. The competition's goal is the realization of the highest net profit in fully autonomous lettuce production. Two cultivation cycles were conducted in six high-tech greenhouse compartments with operational greenhouse decision-making realized at a distance and individually by algorithms of international participating teams. Algorithms were developed based on time series sensor data of the greenhouse climate and crop images. High crop yield and quality, short growing cycles, and low use of resources such as energy for heating, electricity for artificial light, and CO2 were decisive in realizing the competition's goal. The results highlight the importance of plant spacing and the moment of harvest decisions in promoting high crop growth rates while optimizing greenhouse occupation and resource use. In this paper, images taken with depth cameras (RealSense) for each greenhouse were used by computer vision algorithms (Deepabv3+ implemented in detectron2 v0.6) in deciding optimum plant spacing and the moment of harvest. The resulting plant height and coverage could be accurately estimated with an R2 of 0.976, and a mIoU of 98.2, respectively. These two traits were used to develop a light loss and harvest indicator to support remote decision-making. The light loss indicator could be used as a decision tool for timely spacing. Several traits were combined for the harvest indicator, ultimately resulting in a fresh weight estimation with a mean absolute error of 22 g. The proposed non-invasively estimated indicators presented in this article are promising traits to be used towards full autonomation of a dynamic commercial lettuce growing environment. Computer vision algorithms act as a catalyst in remote and non-invasive sensing of crop parameters, decisive for automated, objective, standardized, and data-driven decision making. However, spectral indexes describing lettuces growth and larger datasets than the currently accessible are crucial to address existing shortcomings between academic and industrial production systems that have been encountered in this work. [ABSTRACT FROM AUTHOR]

Regular inspections during construction work ensure that the completed work aligns with the plans and specifications and that it is within the planned time and budget. This requires frequent physical site observations to independently measure and verify the completion percentage of the construction progress performed over periods of time. The current computer vision techniques for measuring as-built elements predominantly employ three-dimensional laser scanning or three-dimensional photogrammetry modeling to ascertain the geometric properties of as-built elements on construction sites. Both techniques require data acquisition from several positions and angles to generate sufficient information about the element's coordinates, making the deployment of these techniques on dynamic construction project sites challenging. This paper proposes a pipeline for automating the measurement of as-built components using artificial intelligence and computer vision techniques. The pipeline requires a single image obtained with a stereo camera system to measure the sizes of selected objects or as-built components. The results in this work were demonstrated by measuring the sizes of concrete walls and columns. The novelty of this work is attributed to the use of a single image and a single target for developing a fully automated computer vision-based method for measuring any given object. The proposed solution is suitable for use in measuring the sizes of as-built components in built assets. It has the potential to be further developed and integrated with building information modelling applications for use on construction projects for progress monitoring. [ABSTRACT FROM AUTHOR]

Background: The planetary rover is an essential platform for planetary exploration. Visual semantic segmentation is significant in the localization, perception, and path planning of the rover autonomy. Recent advances in computer vision and artificial intelligence brought about new opportunities. A systematic literature review (SLR) can help analyze existing solutions, discover available data, and identify potential gaps. Methods: A rigorous SLR has been conducted, and papers are selected from three databases (IEEE Xplore, Web of Science, and Scopus) from the start of records to May 2022. The 320 candidate studies were found by searching with keywords and bool operators, and they address the semantic terrain segmentation in the navigation vision of planetary rovers. Finally, after four rounds of screening, 30 papers were included with robust inclusion and exclusion criteria as well as quality assessment. Results: 30 studies were included for the review, and sub-research areas include navigation (16 studies), geological analysis (7 studies), exploration efficiency (10 studies), and others (3 studies) (overlaps exist). Five distributions are extendedly depicted (time, study type, geographical location, publisher, and experimental setting), which analyzes the included study from the view of community interests, development status, and reimplementation ability. One key research question and six sub-research questions are discussed to evaluate the current achievements and future gaps. Conclusions: Many promising achievements in accuracy, available data, and real-time performance have been promoted by computer vision and artificial intelligence. However, a solution that satisfies pixel-level segmentation, real-time inference time, and onboard hardware does not exist, and an open, pixel-level annotated, and the real-world data-based dataset is not found. As planetary exploration projects progress worldwide, more promising studies will be proposed, and deep learning will bring more opportunities and contributions to future studies. Contributions: This SLR identifies future gaps and challenges by proposing a methodical, replicable, and transparent survey, which is the first review (also the first SLR) for semantic terrain segmentation in the navigation vision of planetary rovers. [ABSTRACT FROM AUTHOR]

Artificial intelligence technologies such as computer vision (CV), machine learning, Internet of Things (IoT), and robotics have advanced rapidly in recent years. The new technologies provide non-contact measurements in three areas: indoor environmental monitoring, outdoor environ-mental monitoring, and equipment monitoring. This paper summarizes the specific applications of non-contact measurement based on infrared images and visible images in the areas of personnel skin temperature, position posture, the urban physical environment, building construction safety, and equipment operation status. At the same time, the challenges and opportunities associated with the application of CV technology are anticipated. [ABSTRACT FROM AUTHOR]

Defect inspection is important to ensure consistent quality and efficiency in industrial manufacturing. Recently, machine vision systems integrating artificial intelligence (AI)-based inspection algorithms have exhibited promising performance in various applications, but practically, they often suffer from data imbalance. This paper proposes a defect inspection method using a one-class classification (OCC) model to deal with imbalanced datasets. A two-stream network architecture consisting of global and local feature extractor networks is presented, which can alleviate the representation collapse problem of OCC. By combining an object-oriented invariant feature vector with a training-data-oriented local feature vector, the proposed two-stream network model prevents the decision boundary from collapsing to the training dataset and obtains an appropriate decision boundary. The performance of the proposed model is demonstrated in the practical application of automotive-airbag bracket-welding defect inspection. The effects of the classification layer and two-stream network architecture on the overall inspection accuracy were clarified by using image samples collected in a controlled laboratory environment and from a production site. The results are compared with those of a previous classification model, demonstrating that the proposed model can improve the accuracy, precision, and F1 score by up to 8.19%, 10.74%, and 4.02%, respectively. [ABSTRACT FROM AUTHOR]

Computer vision algorithms implementations, especially for real-time applications, are present in a variety of devices that we are currently using (from smartphones or automotive applications to monitoring/security applications) and pose specific challenges, memory bandwidth or energy consumption (e.g., for mobility) being the most notable ones. This paper aims at providing a solution to improve the overall quality of real-time object detection computer vision algorithms using a hybrid hardware–software implementation. To this end, we explore the methods for a proper allocation of algorithm components towards hardware (as IP Cores) and the interfacing between hardware and software. Addressing specific design constraints, the relationship between the above components allows embedded artificial intelligence to select the operating hardware blocks (IP cores)—in the configuration phase—and to dynamically change the parameters of the aggregated hardware resources—in the instantiation phase, similar to the concretization of a class into a software object. The conclusions show the benefits of using hybrid hardware–software implementations, as well as major gains from using IP Cores, managed by artificial intelligence, for an object detection use-case, implemented on a FPGA demonstrator built around a Xilinx Zynq-7000 SoC Mini-ITX sub-system. [ABSTRACT FROM AUTHOR]

Accurately identifying the location and depth of buried utility assets became a considerable challenge in the construction industry, for which accidental strikes can cause important economic losses and safety concerns. While the collection of as-built utility locations is becoming more accurate, there still exists an important need to be capable of accurately detecting buried utilities in order to eliminate risks associated with digging. Current practices typically involve the use of trained agents to survey and detect underground utilities at locations of interest, which is a costly and time-consuming process. With advances in artificial intelligence (AI), an opportunity arose in conducting virtual sensing of buried utilities by combining robotics (e.g., drones), knowledge, and logic. This paper reviewed methods that are based on AI in mapping underground infrastructure. In particular, the use of AI in aerial and terrestrial mapping of utility assets was reviewed, followed by a summary of AI techniques used in fusing multi-source data in creating underground infrastructure maps. Key observations from the consolidated literature were that (1) when leveraging computer vision methods, automatic mapping techniques vastly focus on manholes localized from aerial imagery; (2) when applied to non-intrusive sensing, AI methods vastly focus on empowering ground-penetrating radar (GPR)-produced data; and (3) data fusion techniques to produce utility maps should be extended to any utility assets/types. Based on these observations, a universal utility mapping model was proposed, one that could enable mapping of underground utilities using limited information available in the form of different sources of data and knowledge. [ABSTRACT FROM AUTHOR]

Underground mining operations present critical safety hazards due to limited visibility and blind areas, which can lead to collisions between mobile machines and vehicles or persons, causing accidents and fatalities. This paper aims to survey the existing literature on anti-collision systems based on computer vision for pedestrian detection in underground mines, categorize them based on the types of sensors used, and evaluate their effectiveness in deep underground environments. A systematic review of the literature was conducted following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines to identify relevant research work on anti-collision systems for underground mining. The selected studies were analyzed and categorized based on the types of sensors used and their advantages and limitations in deep underground environments. This study provides an overview of the anti-collision systems used in underground mining, including cameras and lidar sensors, and their effectiveness in detecting pedestrians in deep underground environments. Anti-collision systems based on computer vision are effective in reducing accidents and fatalities in underground mining operations. However, their performance is influenced by factors, such as lighting conditions, sensor placement, and sensor range. The findings of this study have significant implications for the mining industry and could help improve safety in underground mining operations. This review and analysis of existing anti-collision systems can guide mining companies in selecting the most suitable system for their specific needs, ultimately reducing the risk of accidents and fatalities. [ABSTRACT FROM AUTHOR]

Road condition monitoring (RCM) has been a demanding strategic research area in maintaining a large network of transport infrastructures. With advancements in computer vision and data mining techniques along with high computing resources, several innovative pavement distress evaluation systems have been developed in recent years. The majority of these technologies employ next-generation distributed sensors and vision-based artificial intelligence (AI) methodologies to evaluate, classify and localize pavement distresses using the measured data. This paper presents an exhaustive and systematic literature review of these technologies in RCM that have been published from 2017–2022 by utilizing next-generation sensors, including contact and noncontact measurements. The various methodologies and innovative contributions of the existing literature reviewed in this paper, together with their limitations, promise a futuristic insight for researchers and transport infrastructure owners. The decisive role played by smart sensors and data acquisition platforms, such as smartphones, drones, vehicles integrated with non-intrusive sensors, such as RGB, and thermal cameras, lasers and GPR sensors in the performance of the system are also highlighted. In addition to sensing, a discussion on the prevalent challenges in the development of AI technologies as well as potential areas for further exploration paves the way for an all-inclusive and well-directed futuristic research on RCM. [ABSTRACT FROM AUTHOR]

Background: Industry 4.0 technologies have been widely used in the railway industry, focusing mainly on maintenance and control tasks necessary in the railway infrastructure. Given the great potential that these technologies offer, the scientific community has come to use them in varied ways to solve a wide range of problems such as train failures, train station security, rail system control and communication in hard-to-reach areas, among others. For this reason, this paper aims to answer the following research questions: what are the main issues in the railway transport industry, what are the technologic strategies that are currently being used to solve these issues and what are the technologies from industry 4.0 that are used in the railway transport industry to solve the aforementioned issues? Methods: This study adopts a systematic literature review approach. We searched the Science Direct and Web of Science database inception from January 2017 to November 2021. Studies published in conferences or journals written in English or Spanish were included for initial process evaluation. The initial included papers were analyzed by authors and selected based on whether they helped answer the proposed research questions or not. Results: Of the recovered 515 articles, 109 were eligible, from which we could identify three main application domains in the railway industry: monitoring, decision and planification techniques, and communication and security. Regarding industry 4.0 technologies, we identified 9 different technologies applied in reviewed studies: Artificial Intelligence (AI), Internet of Things (IoT), Cloud Computing, Big Data, Cybersecurity, Modelling and Simulation, Smart Decision Support Systems (SDSS), Computer Vision and Virtual Reality (VR). This study is, to our knowledge, one of the first to show how industry 4.0 technologies are currently being used to tackle railway industry problems and current application trends in the scientific community, which is highly useful for the development of future studies and more advanced solutions. Funding: Colombian national organizations Minciencias and the Mining-Energy Planning Unit. [ABSTRACT FROM AUTHOR]

Using artificial intelligence (AI) and the IoT (Internet of Things) is a primary focus of applied engineering research to improve agricultural efficiency. This review paper summarizes the engagement of artificial intelligence models and IoT techniques in detecting, classifying, and counting cotton insect pests and corresponding beneficial insects. The effectiveness and limitations of AI and IoT techniques in various cotton agricultural settings were comprehensively reviewed. This review indicates that insects can be detected with an accuracy of between 70 and 98% using camera/microphone sensors and enhanced deep learning algorithms. However, despite the numerous pests and beneficial insects, only a few species were targeted for detection and classification by AI and IoT systems. Not surprisingly, due to the challenges of identifying immature and predatory insects, few studies have designed systems to detect and characterize them. The location of the insects, sufficient data size, concentrated insects on the image, and similarity in species appearance are major obstacles when implementing AI. Similarly, IoT is constrained by a lack of effective field distance between sensors when targeting insects according to their estimated population size. Based on this study, the number of pest species monitored by AI and IoT technologies should be increased while improving the system's detection accuracy. [ABSTRACT FROM AUTHOR]

It is considered that 1 in 10 adults worldwide have diabetes. Diabetic foot ulcers are some of the most common complications of diabetes, and they are associated with a high risk of lower-limb amputation and, as a result, reduced life expectancy. Timely detection and periodic ulcer monitoring can considerably decrease amputation rates. Recent research has demonstrated that computer vision can be used to identify foot ulcers and perform non-contact telemetry by using ulcer and tissue area segmentation. However, the applications are limited to controlled lighting conditions, and expert knowledge is required for dataset annotation. This paper reviews the latest publications on the use of artificial intelligence for ulcer area detection and segmentation. The PRISMA methodology was used to search for and select articles, and the selected articles were reviewed to collect quantitative and qualitative data. Qualitative data were used to describe the methodologies used in individual studies, while quantitative data were used for generalization in terms of dataset preparation and feature extraction. Publicly available datasets were accounted for, and methods for preprocessing, augmentation, and feature extraction were evaluated. It was concluded that public datasets can be used to form a bigger, more diverse datasets, and the prospects of wider image preprocessing and the adoption of augmentation require further research. [ABSTRACT FROM AUTHOR]

Computer vision in consideration of automated and robotic systems has come up as a steady and robust platform in sewer maintenance and cleaning tasks. The AI revolution has enhanced the ability of computer vision and is being used to detect problems with underground sewer pipes, such as blockages and damages. A large amount of appropriate, validated, and labeled imagery data is always a key requirement for learning AI-based detection models to generate the desired outcomes. In this paper, a new imagery dataset S-BIRD (Sewer-Blockages Imagery Recognition Dataset) is presented to draw attention to the predominant sewers' blockages issue caused by grease, plastic and tree roots. The need for the S-BIRD dataset and various parameters such as its strength, performance, consistency and feasibility have been considered and analyzed for real-time detection tasks. The YOLOX object detection model has been trained to prove the consistency and viability of the S-BIRD dataset. It also specified how the presented dataset will be used in an embedded vision-based robotic system to detect and remove sewer blockages in real-time. The outcomes of an individual survey conducted at a typical mid-size city in a developing country, Pune, India, give ground for the necessity of the presented work. [ABSTRACT FROM AUTHOR]

In this study, we used image recognition technology to explore different ways to improve the safety of construction workers. Three object recognition scenarios were designed for safety at a construction site, and a corresponding object recognition model was developed for each scenario. The first object recognition model checks whether there are construction workers at the site. The second object recognition model assesses the risk of falling (falling off a structure or falling down) when working at an elevated position. The third object recognition model determines whether the workers are appropriately wearing safety helmets and vests. These three models were newly created using the image data collected from the construction sites and synthetic image data collected from the virtual environment based on transfer learning. In particular, we verified an artificial intelligence model based on a virtual environment in this study. Thus, simulating and performing tests on worker falls and fall injuries, which are difficult to re-enact by humans, are efficient algorithm verification methods. The verification and synthesis data acquisition method based on a virtual environment is one of the main contributions of this study. This paper describes the overall application development approach, including the structure and method used to collect the construction site image data, structure of the training image dataset, image dataset augmentation method, and the artificial intelligence backbone model applied for transfer learning. [ABSTRACT FROM AUTHOR]

Because of the development of image processing using cameras and the subsequent development of artificial intelligence technology, various fields have begun to develop. However, it is difficult to implement an image processing algorithm that requires a lot of calculations on a light board. This paper proposes a method using real-time deep learning object recognition algorithms in lightweight embedded boards. We have developed an algorithm suitable for lightweight embedded boards by appropriately using two deep neural network architectures. The first architecture requires small computational volumes, although it provides low accuracy. The second architecture uses large computational volumes and provides high accuracy. The area is determined using the first architecture, which processes semantic segmentation with relatively little computation. After masking the area using the more accurate deep learning architecture, object detection is implemented with improved accuracy, as the image is filtered by segmentation and the cases that have not been recognized by various variables, such as differentiation from the background, are excluded. OpenCV (Open source Computer Vision) is used to process input images in Python, and images are processed using an efficient neural network (ENet) and You Only Look Once (YOLO). By running this algorithm, the average error can be reduced by approximately 2.4 times, allowing for more accurate object detection. In addition, object recognition can be performed in real time for lightweight embedded boards, as a rate of about 4 FPS (frames per second) is achieved. [ABSTRACT FROM AUTHOR]

The use of small, interconnected and intelligent tools within the broad framework of pervasive computing for analysis and assessments in sport and physical activity is not a trend in itself but defines a way for information to be handled, processed and utilised: everywhere, at any time. The demand for objective data to support decision making prompted the adoption of wearables that evolve to fulfil the aims of assessing athletes and practitioners as closely as possible with their performance environments. In the present paper, we mention and discuss the advancements in ubiquitous computing in sports and physical activity in the past 5 years. Thus, recent developments in wearable sensors, cloud computing and artificial intelligence tools have been the pillars for a major change in the ways sport-related analyses are performed. The focus of our analysis is wearable technology, computer vision solutions for markerless tracking and their major contribution to the process of acquiring more representative data from uninhibited actions in realistic ecological conditions. We selected relevant literature on the applications of such approaches in various areas of sports and physical activity while outlining some limitations of the present-day data acquisition and data processing practices and the resulting sensors' functionalities, as well as the limitations to the data-driven informed decision making in the current technological and scientific framework. Finally, we hypothesise that a continuous merger of measurement, processing and analysis will lead to the development of more reliable models utilising the advantages of open computing and unrestricted data access and allow for the development of personalised-medicine-type approaches to sport training and performance. [ABSTRACT FROM AUTHOR]

The increased global waste generation rates over the last few decades have made the waste management task a significant problem. One of the potential approaches adopted globally is to recycle a significant portion of generated waste. However, the contamination of recyclable waste has been a major problem in this context and causes almost 75% of recyclable waste to be unusable. For sustainable development, efficient management and recycling of waste are of huge importance. To reduce the waste contamination rates, conventionally, a manual bin-tagging approach is adopted; however, this is inefficient and requires huge labor effort. Within household waste contamination, plastic bags have been found to be one of the main contaminants. Towards automating the process of plastic-bag contamination detection, this paper proposes an edge-computing video analytics solution using the latest Artificial Intelligence (AI), Artificial Intelligence of Things (AIoT) and computer vision technologies. The proposed system is based on the idea of capturing video of waste from the truck hopper, processing it using edge-computing hardware to detect plastic-bag contamination and storing the contamination-related information for further analysis. Faster R-CNN and You Only Look Once version 4 (YOLOv4) deep learning model variants are trained using the Remondis Contamination Dataset (RCD) developed from Remondis manual tagging historical records. The overall system was evaluated in terms of software and hardware performance using standard evaluation measures (i.e., training performance, testing performance, Frames Per Second (FPS), system usage, power consumption). From the detailed analysis, YOLOv4 with CSPDarkNet_tiny was identified as a suitable candidate with a Mean Average Precision (mAP) of 63% and FPS of 24.8 with NVIDIA Jetson TX2 hardware. The data collected from the deployment of edge-computing hardware on waste collection trucks was used to retrain the models and improved performance in terms of mAP, False Positives (FPs), False Negatives (FNs) and True Positives (TPs) was achieved for the retrained YOLOv4 with CSPDarkNet_tiny backbone model. A detailed cost analysis of the proposed system is also provided for stakeholders and policy makers. [ABSTRACT FROM AUTHOR]

Object detection is a common application within the computer vision area. Its tasks include the classic challenges of object localization and classification. As a consequence, object detection is a challenging task. Furthermore, this technique is crucial for maritime applications since situational awareness can bring various benefits to surveillance systems. The literature presents various models to improve automatic target recognition and tracking capabilities that can be applied to and leverage maritime surveillance systems. Therefore, this paper reviews the available models focused on localization, classification, and detection. Moreover, it analyzes several works that apply the discussed models to the maritime surveillance scenario. Finally, it highlights the main opportunities and challenges, encouraging new research in this area. [ABSTRACT FROM AUTHOR]

Human pose estimation has long been a fundamental problem in computer vision and artificial intelligence. Prominent among the 2D human pose estimation (HPE) methods are the regression-based approaches, which have been proven to achieve excellent results. However, the ground-truth labels are usually inherently ambiguous in challenging cases such as motion blur, occlusions, and truncation, leading to poor performance measurement and lower levels of accuracy. In this paper, we propose Cofopose, which is a two-stage approach consisting of a person and keypoint detection transformers for 2D human pose estimation. Cofopose is composed of conditional cross-attention, a conditional DEtection TRansformer (conditional DETR), and an encoder-decoder in the transformer framework; this allows it to achieve person and keypoint detection. In a significant departure from other approaches, we use conditional cross-attention and fine-tune conditional DETR for our person detection, and encoder-decoders in the transformers for our keypoint detection. Cofopose was extensively evaluated using two benchmark datasets, MS COCO and MPII, achieving an improved performance with significant margins over the existing state-of-the-art frameworks. [ABSTRACT FROM AUTHOR]

This is a review focused on advances and current limitations of computer vision (CV) and how CV can help us obtain to more autonomous actions in surgery. It is a follow-up article to one that we previously published in Sensors entitled, "Artificial Intelligence Surgery: How Do We Get to Autonomous Actions in Surgery?" As opposed to that article that also discussed issues of machine learning, deep learning and natural language processing, this review will delve deeper into the field of CV. Additionally, non-visual forms of data that can aid computerized robots in the performance of more autonomous actions, such as instrument priors and audio haptics, will also be highlighted. Furthermore, the current existential crisis for surgeons, endoscopists and interventional radiologists regarding more autonomy during procedures will be discussed. In summary, this paper will discuss how to harness the power of CV to keep doctors who do interventions in the loop. [ABSTRACT FROM AUTHOR]

In the last few years, Augmented Reality, Virtual Reality, and Artificial Intelligence (AI) have been increasingly employed in different application domains. Among them, the retail market presents the opportunity to allow people to check the appearance of accessories, makeup, hairstyle, hair color, and clothes on themselves, exploiting virtual try-on applications. In this paper, we propose an eyewear virtual try-on experience based on a framework that leverages advanced deep learning-based computer vision techniques. The virtual try-on is performed on a 3D face reconstructed from a single input image. In designing our system, we started by studying the underlying architecture, components, and their interactions. Then, we assessed and compared existing face reconstruction approaches. To this end, we performed an extensive analysis and experiments for evaluating their design, complexity, geometry reconstruction errors, and reconstructed texture quality. The experiments allowed us to select the most suitable approach for our proposed try-on framework. Our system considers actual glasses and face sizes to provide a realistic fit estimation using a markerless approach. The user interacts with the system by using a web application optimized for desktop and mobile devices. Finally, we performed a usability study that showed an above-average score of our eyewear virtual try-on application. [ABSTRACT FROM AUTHOR]

With the development of artificial intelligence technology and the popularity of intelligent production projects, intelligent inspection systems have gradually become a hot topic in the industrial field. As a fundamental problem in the field of computer vision, how to achieve object detection in the industry while taking into account the accuracy and real-time detection is an important challenge in the development of intelligent detection systems. The detection of defects on steel surfaces is an important application of object detection in the industry. Correct and fast detection of surface defects can greatly improve productivity and product quality. To this end, this paper introduces the MSFT-YOLO model, which is improved based on the one-stage detector. The MSFT-YOLO model is proposed for the industrial scenario in which the image background interference is great, the defect category is easily confused, the defect scale changes a great deal, and the detection results of small defects are poor. By adding the TRANS module, which is designed based on Transformer, to the backbone and detection headers, the features can be combined with global information. The fusion of features at different scales by combining multi-scale feature fusion structures enhances the dynamic adjustment of the detector to objects at different scales. To further improve the performance of MSFT-YOLO, we also introduce plenty of effective strategies, such as data augmentation and multi-step training methods. The test results on the NEU-DET dataset show that MSPF-YOLO can achieve real-time detection, and the average detection accuracy of MSFT-YOLO is 75.2, improving about 7% compared to the baseline model (YOLOv5) and 18% compared to Faster R-CNN, which is advantageous and inspiring. [ABSTRACT FROM AUTHOR]

The development of a Social Intelligence System based on artificial intelligence is one of the cutting edge technologies in Assistive Robotics. Such systems need to create an empathic interaction with the users; therefore, it os required to include an Emotion Recognition (ER) framework which has to run, in near real-time, together with several other intelligent services. Most of the low-cost commercial robots, however, although more accessible by users and healthcare facilities, have to balance costs and effectiveness, resulting in under-performing hardware in terms of memory and processing unit. This aspect makes the design of the systems challenging, requiring a trade-off between the accuracy and the complexity of the adopted models. This paper proposes a compact and robust service for Assistive Robotics, called Lightweight EMotion recognitiON (LEMON), which uses image processing, Computer Vision and Deep Learning (DL) algorithms to recognize facial expressions. Specifically, the proposed DL model is based on Residual Convolutional Neural Networks with the combination of Dilated and Standard Convolution Layers. The first remarkable result is the few numbers (i.e., 1.6 Million) of parameters characterizing our model. In addition, Dilated Convolutions expand receptive fields exponentially with preserving resolution, less computation and memory cost to recognize the distinction among facial expressions by capturing the displacement of the pixels. Finally, to reduce the dying ReLU problem and improve the stability of the model, we apply an Exponential Linear Unit (ELU) activation function in the initial layers of the model. We have performed training and evaluation (via one- and five-fold cross validation) of the model with five datasets available in the community and one mixed dataset created by taking samples from all of them. With respect to the other approaches, our model achieves comparable results with a significant reduction in terms of the number of parameters. [ABSTRACT FROM AUTHOR]

Facial emotion recognition (FER) is an important topic in the fields of computer vision and artificial intelligence owing to its significant academic and commercial potential. Although FER can be conducted using multiple sensors, this review focuses on studies that exclusively use facial images, because visual expressions are one of the main information channels in interpersonal communication. This paper provides a brief review of researches in the field of FER conducted over the past decades. First, conventional FER approaches are described along with a summary of the representative categories of FER systems and their main algorithms. Deep-learning-based FER approaches using deep networks enabling “end-to-end” learning are then presented. This review also focuses on an up-to-date hybrid deep-learning approach combining a convolutional neural network (CNN) for the spatial features of an individual frame and long short-term memory (LSTM) for temporal features of consecutive frames. In the later part of this paper, a brief review of publicly available evaluation metrics is given, and a comparison with benchmark results, which are a standard for a quantitative comparison of FER researches, is described. This review can serve as a brief guidebook to newcomers in the field of FER, providing basic knowledge and a general understanding of the latest state-of-the-art studies, as well as to experienced researchers looking for productive directions for future work. [ABSTRACT FROM AUTHOR]

Embedded systems control and monitor a great deal of our reality. While some "classic" features are intrinsically necessary, such as low power consumption, rugged operating ranges, fast response and low cost, these systems have evolved in the last few years to emphasize connectivity functions, thus contributing to the Internet of Things paradigm. A myriad of sensing/computing devices are being attached to everyday objects, each able to send and receive data and to act as a unique node in the Internet. Apart from the obvious necessity to process at least some data at the edge (to increase security and reduce power consumption and latency), a major breakthrough will arguably come when such devices are endowed with some level of autonomous "intelligence". Intelligent computing aims to solve problems for which no efficient exact algorithm can exist or for which we cannot conceive an exact algorithm. Central to such intelligence is Computer Vision (CV), i.e., extracting meaning from images and video. While not everything needs CV, visual information is the richest source of information about the real world: people, places and things. The possibilities of embedded CV are endless if we consider new applications and technologies, such as deep learning, drones, home robotics, intelligent surveillance, intelligent toys, wearable cameras, etc. This paper describes the Eyes of Things (EoT) platform, a versatile computer vision platform tackling those challenges and opportunities. [ABSTRACT FROM AUTHOR]

Plant phenomics has been rapidly advancing over the past few years. This advancement is attributed to the increased innovation and availability of new technologies which can enable the high-throughput phenotyping of complex plant traits. The application of artificial intelligence in various domains of science has also grown exponentially in recent years. Notably, the computer vision, machine learning, and deep learning aspects of artificial intelligence have been successfully integrated into non-invasive imaging techniques. This integration is gradually improving the efficiency of data collection and analysis through the application of machine and deep learning for robust image analysis. In addition, artificial intelligence has fostered the development of software and tools applied in field phenotyping for data collection and management. These include open-source devices and tools which are enabling community driven research and data-sharing, thereby availing the large amounts of data required for the accurate study of phenotypes. This paper reviews more than one hundred current state-of-the-art papers concerning AI-applied plant phenotyping published between 2010 and 2020. It provides an overview of current phenotyping technologies and the ongoing integration of artificial intelligence into plant phenotyping. Lastly, the limitations of the current approaches/methods and future directions are discussed. [ABSTRACT FROM AUTHOR]

This paper provides a review of the literature on vision-based on-board obstacle detection and distance estimation in railways. Environment perception is crucial for autonomous detection of obstacles in a vehicle's surroundings. The use of on-board sensors for road vehicles for this purpose is well established, and advances in Artificial Intelligence and sensing technologies have motivated significant research and development in obstacle detection in the automotive field. However, research and development on obstacle detection in railways has been less extensive. To the best of our knowledge, this is the first comprehensive review of on-board obstacle detection methods for railway applications. This paper reviews currently used sensors, with particular focus on vision sensors due to their dominant use in the field. It then discusses and categorizes the methods based on vision sensors into methods based on traditional Computer Vision and methods based on Artificial Intelligence. [ABSTRACT FROM AUTHOR]

Multi-view action recognition has gained a great interest in video surveillance, human computer interaction, and multimedia retrieval, where multiple cameras of different types are deployed to provide a complementary field of views. Fusion of multiple camera views evidently leads to more robust decisions on both tracking multiple targets and analysing complex human activities, especially where there are occlusions. In this paper, we incorporate the marginalised stacked denoising autoencoders (mSDA) algorithm to further improve the bag of words (BoWs) representation in terms of robustness and usefulness for multi-view action recognition. The resulting representations are fed into three simple fusion strategies as well as a multiple kernel learning algorithm at the classification stage. Based on the internal evaluation, the codebook size of BoWs and the number of layers of mSDA may not significantly affect recognition performance. According to results on three multi-view benchmark datasets, the proposed framework improves recognition performance across all three datasets and outputs record recognition performance, beating the state-of-art algorithms in the literature. It is also capable of performing real-time action recognition at a frame rate ranging from 33 to 45, which could be further improved by using more powerful machines in future applications. [ABSTRACT FROM AUTHOR]

Providing high on-shelf availability (OSA) is a key factor to increase profits in grocery stores. Recently, there has been growing interest in computer vision approaches to monitor OSA. However, the largest and well-known computer vision datasets do not provide annotation for store products, and therefore, a huge effort is needed to manually label products on images. To tackle the annotation problem, this paper proposes a new method that combines two concepts "semi-supervised learning" and "on-shelf availability" (SOSA) for the first time. Moreover, it is the first time that "You Only Look Once" (YOLOv4) deep learning architecture is used to monitor OSA. Furthermore, this paper provides the first demonstration of explainable artificial intelligence (XAI) on OSA. It presents a new software application, called SOSA XAI, with its capabilities and advantages. In the experimental studies, the effectiveness of the proposed SOSA method was verified on image datasets, with different ratios of labeled samples varying from 20% to 80%. The experimental results show that the proposed approach outperforms the existing approaches (RetinaNet and YOLOv3) in terms of accuracy. [ABSTRACT FROM AUTHOR]

We propose an intelligent vision-based Automated Guided Vehicle (AGV) system using fiduciary markers. In this paper, we explore a low-cost, efficient vehicle guiding method using a consumer grade web camera and fiduciary markers. In the proposed method, the system uses fiduciary markers with a capital letter or triangle indicating direction in it. The markers are very easy to produce, manipulate, and maintain. The marker information is used to guide a vehicle. We use hue and saturation values in the image to extract marker candidates. When the known size fiduciary marker is detected by using a bird's eye view and Hough transform, the positional relation between the marker and the vehicle can be calculated. To recognize the character in the marker, a distance transform is used. The probability of feature matching was calculated by using a distance transform, and a feature having high probability is selected as a captured marker. Four directional signals and 10 alphabet features are defined and used as markers. A 98.87% recognition rate was achieved in the testing phase. The experimental results with the fiduciary marker show that the proposed method is a solution for an indoor AGV system. [ABSTRACT FROM AUTHOR]

The most effective methods of preventing COVID-19 infection include maintaining physical distancing and wearing a face mask while in close contact with people in public places. However, densely populated areas have a greater incidence of COVID-19 dissemination, which is caused by people who do not comply with standard operating procedures (SOPs). This paper presents a prototype called PADDIE-C19 (Physical Distancing Device with Edge Computing for COVID-19) to implement the physical distancing monitoring based on a low-cost edge computing device. The PADDIE-C19 provides real-time results and responses, as well as notifications and warnings to anyone who violates the 1-m physical distance rule. In addition, PADDIE-C19 includes temperature screening using an MLX90614 thermometer and ultrasonic sensors to restrict the number of people on specified premises. The Neural Network Processor (KPU) in Grove Artificial Intelligence Hardware Attached on Top (AI HAT), an edge computing unit, is used to accelerate the neural network model on person detection and achieve up to 18 frames per second (FPS). The results show that the accuracy of person detection with Grove AI HAT could achieve 74.65% and the average absolute error between measured and actual physical distance is 8.95 cm. Furthermore, the accuracy of the MLX90614 thermometer is guaranteed to have less than 0.5 °C value difference from the more common Fluke 59 thermometer. Experimental results also proved that when cloud computing is compared to edge computing, the Grove AI HAT achieves the average performance of 18 FPS for a person detector (kmodel) with an average 56 ms execution time in different networks, regardless of the network connection type or speed. [ABSTRACT FROM AUTHOR]

Recently, artificial intelligence has been successfully used in fields, such as computer vision, voice, and big data analysis. However, various problems, such as security, privacy, and ethics, also occur owing to the development of artificial intelligence. One such problem are deepfakes. Deepfake is a compound word for deep learning and fake. It refers to a fake video created using artificial intelligence technology or the production process itself. Deepfakes can be exploited for political abuse, pornography, and fake information. This paper proposes a method to determine integrity by analyzing the computer vision features of digital content. The proposed method extracts the rate of change in the computer vision features of adjacent frames and then checks whether the video is manipulated. The test demonstrated the highest detection rate of 97% compared to the existing method or machine learning method. It also maintained the highest detection rate of 96%, even for the test that manipulates the matrix of the image to avoid the convolutional neural network detection method. [ABSTRACT FROM AUTHOR]

This paper presents an innovative access control system, based on human detection and path analysis, to reduce false automatic door system actions while increasing the added values for security applications. The proposed system can first identify a person from the scene, and track his trajectory to predict his intention for accessing the entrance, and finally activate the door accordingly. The experimental results show that the proposed system has the advantages of high precision, safety, reliability, and can be responsive to demands, while preserving the benefits of being low cost and high added value. [ABSTRACT FROM AUTHOR]

When deploying a model for object detection, a confidence score threshold is chosen to filter out false positives and ensure that a predicted bounding box has a certain minimum score. To achieve state-of-the-art performance on benchmark datasets, most neural networks use a rather low threshold as a high number of false positives is not penalized by standard evaluation metrics. However, in scenarios of Artificial Intelligence (AI) applications that require high confidence scores (e.g., due to legal requirements or consequences of incorrect detections are severe) or a certain level of model robustness is required, it is unclear which base model to use since they were mainly optimized for benchmark scores. In this paper, we propose a method to find the optimum performance point of a model as a basis for fairer comparison and deeper insights into the trade-offs caused by selecting a confidence score threshold. [ABSTRACT FROM AUTHOR]

In recent years, we have assisted with an impressive advance in augmented reality systems and computer vision algorithms, based on image processing and artificial intelligence. Thanks to these technologies, mainstream smartphones are able to estimate their own motion in 3D space with high accuracy. In this paper, we exploit such technologies to support the autonomous mobility of people with visual disabilities, identifying pre-defined virtual paths and providing context information, reducing the distance between the digital and real worlds. In particular, we present ARIANNA+, an extension of ARIANNA, a system explicitly designed for visually impaired people for indoor and outdoor localization and navigation. While ARIANNA is based on the assumption that landmarks, such as QR codes, and physical paths (composed of colored tapes, painted lines, or tactile pavings) are deployed in the environment and recognized by the camera of a common smartphone, ARIANNA+ eliminates the need for any physical support thanks to the ARKit library, which we exploit to build a completely virtual path. Moreover, ARIANNA+ adds the possibility for the users to have enhanced interactions with the surrounding environment, through convolutional neural networks (CNNs) trained to recognize objects or buildings and enabling the possibility of accessing contents associated with them. By using a common smartphone as a mediation instrument with the environment, ARIANNA+ leverages augmented reality and machine learning for enhancing physical accessibility. The proposed system allows visually impaired people to easily navigate in indoor and outdoor scenarios simply by loading a previously recorded virtual path and providing automatic guidance along the route, through haptic, speech, and sound feedback. [ABSTRACT FROM AUTHOR]

New processing methods based on artificial intelligence (AI) and deep learning are replacing traditional computer vision algorithms. The more advanced systems can process huge amounts of data in large computing facilities. In contrast, this paper presents a smart video surveillance system executing AI algorithms in low power consumption embedded devices. The computer vision algorithm, typical for surveillance applications, aims to detect, count and track people's movements in the area. This application requires a distributed smart camera system. The proposed AI application allows detecting people in the surveillance area using a MobileNet-SSD architecture. In addition, using a robust Kalman filter bank, the algorithm can keep track of people in the video also providing people counting information. The detection results are excellent considering the constraints imposed on the process. The selected architecture for the edge node is based on a UpSquared2 device that includes a vision processor unit (VPU) capable of accelerating the AI CNN inference. The results section provides information about the image processing time when multiple video cameras are connected to the same edge node, people detection precision and recall curves, and the energy consumption of the system. The discussion of results shows the usefulness of deploying this smart camera node throughout a distributed surveillance system. [ABSTRACT FROM AUTHOR]

In recent years, the technology of artificial intelligence (AI) and robots is rapidly spreading to countries around the world. More and more scholars and industry experts have proposed AI deep learning models and methods to solve human life problems and improve work efficiency. Modern people's lives are very busy, which led us to investigate whether the demand for Bento buffet cafeterias has gradually increased in Taiwan. However, when eating at a buffet in a cafeteria, people often encounter two problems. The first problem is that customers need to queue up to check out after they have selected and filled their dishes from the buffet. However, it always takes too much time waiting, especially at lunch or dinner time. The second problem is sometimes customers question the charges calculated by cafeteria staff, claiming they are too expensive at the checkout counter. Therefore, it is necessary to develop an AI-enabled checkout system. The AI-enabled self-checkout system will help the Bento buffet cafeterias reduce long lineups without the need to add additional workers. In this paper, we used computer vision and deep-learning technology to design and implement an AI-enabled checkout system for Bento buffet cafeterias. The prototype contains an angle steel shelf, a Kinect camera, a light source, and a desktop computer. Six baseline convolutional neural networks were applied for comparison on food recognition. In our experiments, there were 22 different food categories in a Bento buffet cafeteria employed. Experimental results show that the inception_v4 model can achieve the highest average validation accuracy of 99.11% on food recognition, but it requires the most training and recognition time. AlexNet model achieves a 94.5% accuracy and requires the least training time and recognition time. We propose a hierarchical approach with two stages to achieve good performance in both the recognition accuracy rate and the required training and recognition time. The approach is designed to perform the first step of identification and the second step of recognizing similar food images, respectively. Experimental results show that the proposed approach can achieve a 96.3% accuracy rate on our test dataset and required very little recognition time for input images. In addition, food volumes could be estimated using the depth images captured by the Kinect camera, and a framework of visual checkout system was successfully built. [ABSTRACT FROM AUTHOR]

Deep learning techniques are being increasingly used in the scientific community as a consequence of the high computational capacity of current systems and the increase in the amount of data available as a result of the digitalisation of society in general and the industrial world in particular. In addition, the immersion of the field of edge computing, which focuses on integrating artificial intelligence as close as possible to the client, makes it possible to implement systems that act in real time without the need to transfer all of the data to centralised servers. The combination of these two concepts can lead to systems with the capacity to make correct decisions and act based on them immediately and in situ. Despite this, the low capacity of embedded systems greatly hinders this integration, so the possibility of being able to integrate them into a wide range of micro-controllers can be a great advantage. This paper contributes with the generation of an environment based on Mbed OS and TensorFlow Lite to be embedded in any general purpose embedded system, allowing the introduction of deep learning architectures. The experiments herein prove that the proposed system is competitive if compared to other commercial systems. [ABSTRACT FROM AUTHOR]

Visual question answering (VQA) is a multi-modal task involving natural language processing (NLP) and computer vision (CV), which requires models to understand of both visual information and textual information simultaneously to predict the correct answer for the input visual image and textual question, and has been widely used in smart and intelligent transport systems, smart city, and other fields. Today, advanced VQA approaches model dense interactions between image regions and question words by designing co-attention mechanisms to achieve better accuracy. However, modeling interactions between each image region and each question word will force the model to calculate irrelevant information, thus causing the model's attention to be distracted. In this paper, to solve this problem, we propose a novel model called Multi-modal Explicit Sparse Attention Networks (MESAN), which concentrates the model's attention by explicitly selecting the parts of the input features that are the most relevant to answering the input question. We consider that this method based on top-k selection can reduce the interference caused by irrelevant information and ultimately help the model to achieve better performance. The experimental results on the benchmark dataset VQA v2 demonstrate the effectiveness of our model. Our best single model delivers 70.71% and 71.08% overall accuracy on the test-dev and test-std sets, respectively. In addition, we also demonstrate that our model can obtain better attended features than other advanced models through attention visualization. Our work proves that the models with sparse attention mechanisms can also achieve competitive results on VQA datasets. We hope that it can promote the development of VQA models and the application of artificial intelligence (AI) technology related to VQA in various aspects. [ABSTRACT FROM AUTHOR]

Due to recent advancements in virtual reality (VR) and augmented reality (AR), the demand for high quality immersive contents is a primary concern for production companies and consumers. Similarly, the topical record-breaking performance of deep learning in various domains of artificial intelligence has extended the attention of researchers to contribute to different fields of computer vision. To ensure the quality of immersive media contents using these advanced deep learning technologies, several learning based Stitched Image Quality Assessment methods have been proposed with reasonable performances. However, these methods are unable to localize, segment, and extract the stitching errors in panoramic images. Further, these methods used computationally complex procedures for quality assessment of panoramic images. With these motivations, in this paper, we propose a novel three-fold Deep Learning based No-Reference Stitched Image Quality Assessment (DLNR-SIQA) approach to evaluate the quality of immersive contents. In the first fold, we fined-tuned the state-of-the-art Mask R-CNN (Regional Convolutional Neural Network) on manually annotated various stitching error-based cropped images from the two publicly available datasets. In the second fold, we segment and localize various stitching errors present in the immersive contents. Finally, based on the distorted regions present in the immersive contents, we measured the overall quality of the stitched images. Unlike existing methods that only measure the quality of the images using deep features, our proposed method can efficiently segment and localize stitching errors and estimate the image quality by investigating segmented regions. We also carried out extensive qualitative and quantitative comparison with full reference image quality assessment (FR-IQA) and no reference image quality assessment (NR-IQA) on two publicly available datasets, where the proposed system outperformed the existing state-of-the-art techniques. [ABSTRACT FROM AUTHOR]

Immediate assessment of structural integrity of important civil infrastructures, like bridges, hospitals, or dams, is of utmost importance after natural disasters. Currently, inspection is performed manually by engineers who look for local damages and their extent on significant locations of the structure to understand its implication on its global stability. However, the whole process is time-consuming and prone to human errors. Due to their size and extent, some regions of civil structures are hard to gain access for manual inspection. In such situations, a vision-based system of Unmanned Aerial Vehicles (UAVs) programmed with Artificial Intelligence algorithms may be an effective alternative to carry out a health assessment of civil infrastructures in a timely manner. This paper proposes a framework of achieving the above-mentioned goal using computer vision and deep learning algorithms for detection of cracks on the concrete surface from its image by carrying out image segmentation of pixels, i.e., classification of pixels in an image of the concrete surface and whether it belongs to cracks or not. The image segmentation or dense pixel level classification is carried out using a deep neural network architecture named U-Net. Further, morphological operations on the segmented images result in dense measurements of crack geometry, like length, width, area, and crack orientation for individual cracks present in the image. The efficacy and robustness of the proposed method as a viable real-life application was validated by carrying out a laboratory experiment of a four-point bending test on an 8-foot-long concrete beam of which the video is recorded using a camera mounted on a UAV-based, as well as a still ground-based, video camera. Detection, quantification, and localization of damage on a civil infrastructure using the proposed framework can directly be used in the prognosis of the structure's ability to withstand service loads. [ABSTRACT FROM AUTHOR]

For a safe market launch of automated vehicles, the risks of the overall system as well as the sub-components must be efficiently identified and evaluated. This also includes camera-based object detection using artificial intelligence algorithms. It is trivial and explainable that due to the principle of the camera, performance depends highly on the environmental conditions and can be poor, for example in heavy fog. However, there are other factors influencing the performance of camera-based object detection, which will be comprehensively investigated for the first time in this paper. Furthermore, a precise modeling of the detection performance and the explanation of individual detection results is not possible due to the artificial intelligence based algorithms used. Therefore, a modeling approach based on the investigated influence factors is proposed and the newly developed SHapley Additive exPlanations (SHAP) approach is adopted to analyze and explain the detection performance of different object detection algorithms. The results show that many influence factors such as the relative rotation of an object towards the camera or the position of an object on the image have basically the same influence on the detection performance regardless of the detection algorithm used. In particular, the revealed weaknesses of the tested object detectors can be used to derive challenging and critical scenarios for the testing and type approval of automated vehicles. [ABSTRACT FROM AUTHOR]

The rapid development of vision sensor based on artificial intelligence (AI) is reforming industries and making our world smarter. Among these trends, it is of great significance to adapt AI technologies into the intelligent agricultural management. In smart agricultural aviation spraying, the droplets' distribution and deposition are important indexes for estimating effectiveness in plant protection process. However, conventional approaches are problematic, they lack adaptivity to environmental changes, and consumes non-reusable test materials. One example is that the machine vision algorithms they employ can't guarantee that the division of adhesive droplets thereby disabling the accurate measurement of critical parameters. To alleviate these problems, we put forward an intelligent visual droplet detection node which can adapt to the environment illumination change. Then, we propose a modified marker controllable watershed segmentation algorithm to segment those adhesive droplets, and calculate their characteristic parameters on the basis of the segmentation results, including number, coverage, coverage density, etc. Finally, we use the intelligent node to detect droplets, and then expound the situation that the droplet region is effectively segmented and marked. The intelligent node has better adaptability and robustness even under the condition of illumination changing. The large-scale distributed detection result indicates that our approach has good consistency with the non-recyclable water-sensitive paper approach. Our approach provides an intelligent and environmental friendly way of tests for spraying techniques, especially for plant protection with Unmanned Aerial Vehicles. [ABSTRACT FROM AUTHOR]