Search

Industrial inspection is crucial for maintaining quality and safety in industrial processes. Deep learning models have recently demonstrated promising results in such tasks. This paper proposes YOLOX-Ray, an efficient new deep learning architecture tailored for industrial inspection. YOLOX-Ray is based on the You Only Look Once (YOLO) object detection algorithms and integrates the SimAM attention mechanism for improved feature extraction in the Feature Pyramid Network (FPN) and Path Aggregation Network (PAN). Moreover, it also employs the Alpha-IoU cost function for enhanced small-scale object detection. YOLOX-Ray's performance was assessed in three case studies: hotspot detection, infrastructure crack detection and corrosion detection. The architecture outperforms all other configurations, achieving m A P 50 values of 89%, 99.6% and 87.7%, respectively. For the most challenging metric, m A P 50 : 95 , the achieved values were 44.7%, 66.1% and 51.8%, respectively. A comparative analysis demonstrated the importance of combining the SimAM attention mechanism with Alpha-IoU loss function for optimal performance. In conclusion, YOLOX-Ray's ability to detect and to locate multi-scale objects in industrial environments presents new opportunities for effective, efficient and sustainable inspection processes across various industries, revolutionizing the field of industrial inspections. [ABSTRACT FROM AUTHOR]

Object detection is a fundamental task in computer vision. Over the past several years, convolutional neural network (CNN)-based object detection models have significantly improved detection accuracyin terms of average precision (AP). Furthermore, feature pyramid networks (FPNs) are essential modules for object detection models to consider various object scales. However, the AP for small objects is lower than the AP for medium and large objects. It is difficult to recognize small objects because they do not have sufficient information, and information is lost in deeper CNN layers. This paper proposes a new FPN model named ssFPN (scale sequence (S 2 ) feature-based feature pyramid network) to detect multi-scale objects, especially small objects. We propose a new scale sequence (S 2 ) feature that is extracted by 3D convolution on the level of the FPN. It is defined and extracted from the FPN to strengthen the information on small objects based on scale-space theory. Motivated by this theory, the FPN is regarded as a scale space and extracts a scale sequence (S 2 ) feature by three-dimensional convolution on the level axis of the FPN. The defined feature is basically scale-invariant and is built on a high-resolution pyramid feature map for small objects. Additionally, the deigned S 2 feature can be extended to most object detection models based on FPNs. We also designed a feature-level super-resolution approach to show the efficiency of the scale sequence (S 2 ) feature. We verified that the scale sequence (S 2 ) feature could improve the classification accuracy for low-resolution images by training a feature-level super-resolution model. To demonstrate the effect of the scale sequence (S 2 ) feature, experiments on the scale sequence (S 2 ) feature built-in object detection approach including both one-stage and two-stage models were conducted on the MS COCO dataset. For the two-stage object detection models Faster R-CNN and Mask R-CNN with the S 2 feature, AP improvements of up to 1.6% and 1.4%, respectively, were achieved. Additionally, the AP S of each model was improved by 1.2% and 1.1%, respectively. Furthermore, the one-stage object detection models in the YOLO series were improved. For YOLOv4-P5, YOLOv4-P6, YOLOR-P6, YOLOR-W6, and YOLOR-D6 with the S 2 feature, 0.9%, 0.5%, 0.5%, 0.1%, and 0.1% AP improvements were observed. For small object detection, the AP S increased by 1.1%, 1.1%, 0.9%, 0.4%, and 0.1%, respectively. Experiments using the feature-level super-resolution approach with the proposed scale sequence (S 2 ) feature were conducted on the CIFAR-100 dataset. By training the feature-level super-resolution model, we verified that ResNet-101 with the S 2 feature trained on LR images achieved a 55.2% classification accuracy, which was 1.6% higher than for ResNet-101 trained on HR images. [ABSTRACT FROM AUTHOR]

Blind people often encounter challenges in managing their clothing, specifically in identifying defects such as stains or holes. With the progress of the computer vision field, it is crucial to minimize these limitations as much as possible to assist blind people with selecting appropriate clothing. Therefore, the objective of this paper is to use object detection technology to categorize and detect stains on garments. The defect detection system proposed in this study relies on the You Only Look Once (YOLO) architecture, which is a single-stage object detector that is well-suited for automated inspection tasks. The authors collected a dataset of clothing with defects and used it to train and evaluate the proposed system. The methodology used for the optimization of the defect detection system was based on three main components: (i) increasing the dataset with new defects, illumination conditions, and backgrounds, (ii) introducing data augmentation, and (iii) introducing defect classification. The authors compared and evaluated three different YOLOv5 models. The results of this study demonstrate that the proposed approach is effective and suitable for different challenging defect detection conditions, showing high average precision (AP) values, and paving the way for a mobile application to be accessible for the blind community. [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]

Gaze estimation is an established research problem in computer vision. It has various applications in real life, from human–computer interactions to health care and virtual reality, making it more viable for the research community. Due to the significant success of deep learning techniques in other computer vision tasks—for example, image classification, object detection, object segmentation, and object tracking—deep learning-based gaze estimation has also received more attention in recent years. This paper uses a convolutional neural network (CNN) for person-specific gaze estimation. The person-specific gaze estimation utilizes a single model trained for one individual user, contrary to the commonly-used generalized models trained on multiple people's data. We utilized only low-quality images directly collected from a standard desktop webcam, so our method can be applied to any computer system equipped with such a camera without additional hardware requirements. First, we used the web camera to collect a dataset of face and eye images. Then, we tested different combinations of CNN parameters, including the learning and dropout rates. Our findings show that building a person-specific eye-tracking model produces better results with a selection of good hyperparameters when compared to universal models that are trained on multiple users' data. In particular, we achieved the best results for the left eye with 38.20 MAE (Mean Absolute Error) in pixels, the right eye with 36.01 MAE, both eyes combined with 51.18 MAE, and the whole face with 30.09 MAE, which is equivalent to approximately 1.45 degrees for the left eye, 1.37 degrees for the right eye, 1.98 degrees for both eyes combined, and 1.14 degrees for full-face images. [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]

The construction industry is increasingly adopting off-site and modular construction methods due to the advantages offered in terms of safety, quality, and productivity for construction projects. Despite the advantages promised by this method of construction, modular construction factories still rely on manually-intensive work, which can lead to highly variable cycle times. As a result, these factories experience bottlenecks in production that can reduce productivity and cause delays to modular integrated construction projects. To remedy this effect, computer vision-based methods have been proposed to monitor the progress of work in modular construction factories. However, these methods fail to account for changes in the appearance of the modular units during production, they are difficult to adapt to other stations and factories, and they require a significant amount of annotation effort. Due to these drawbacks, this paper proposes a computer vision-based progress monitoring method that is easy to adapt to different stations and factories and relies only on two image annotations per station. In doing so, the Scale-invariant feature transform (SIFT) method is used to identify the presence of modular units at workstations, and the Mask R-CNN deep learning-based method is used to identify active workstations. This information was synthesized using a near real-time data-driven bottleneck identification method suited for assembly lines in modular construction factories. This framework was successfully validated using 420 h of surveillance videos of a production line in a modular construction factory in the U.S., providing 96% accuracy in identifying the occupancy of the workstations and an F-1 Score of 89% in identifying the state of each station on the production line. The extracted active and inactive durations were successfully used via a data-driven bottleneck detection method to detect bottleneck stations inside a modular construction factory. The implementation of this method in factories can lead to continuous and comprehensive monitoring of the production line and prevent delays by timely identification of bottlenecks. [ABSTRACT FROM AUTHOR]

Fashion is one of the many fields of application that image captioning is being used in. For e-commerce websites holding tens of thousands of images of clothing, automated item descriptions are quite desirable. This paper addresses captioning images of clothing in the Arabic language using deep learning. Image captioning systems are based on Computer Vision and Natural Language Processing techniques because visual and textual understanding is needed for these systems. Many approaches have been proposed to build such systems. The most widely used methods are deep learning methods which use the image model to analyze the visual content of the image, and the language model to generate the caption. Generating the caption in the English language using deep learning algorithms received great attention from many researchers in their research, but there is still a gap in generating the caption in the Arabic language because public datasets are often not available in the Arabic language. In this work, we created an Arabic dataset for captioning images of clothing which we named "ArabicFashionData" because this model is the first model for captioning images of clothing in the Arabic language. Moreover, we classified the attributes of the images of clothing and used them as inputs to the decoder of our image captioning model to enhance Arabic caption quality. In addition, we used the attention mechanism. Our approach achieved a BLEU-1 score of 88.52. The experiment findings are encouraging and suggest that, with a bigger dataset, the attributes-based image captioning model can achieve excellent results for Arabic image captioning. [ABSTRACT FROM AUTHOR]

Person re-identification (Re-ID) is a method for identifying the same individual via several non-interfering cameras. Person Re-ID has been felicitously applied to an assortment of computer vision applications. Due to the emergence of deep learning algorithms, person Re-ID techniques, which often involve the attention module, have gained remarkable success. Moreover, people's traits are mostly similar, which makes distinguishing between them complicated. This paper presents a novel approach for person Re-ID, by introducing a multi-part feature network, that combines the position attention module (PAM) and the efficient channel attention (ECA). The goal is to enhance the accuracy and robustness of person Re-ID methods through the use of attention mechanisms. The proposed multi-part feature network employs the PAM to extract robust and discriminative features by utilizing channel, spatial, and temporal context information. The PAM learns the spatial interdependencies of features and extracts a greater variety of contextual information from local elements, hence enhancing their capacity for representation. The ECA captures local cross-channel interaction and reduces the model's complexity, while maintaining accuracy. Inclusive experiments were executed on three publicly available person Re-ID datasets: Market-1501, DukeMTMC, and CUHK-03. The outcomes reveal that the suggested method outperforms existing state-of-the-art methods, and the rank-1 accuracy can achieve 95.93%, 89.77%, and 73.21% in trials on the public datasets Market-1501, DukeMTMC-reID, and CUHK03, respectively, and can reach 96.41%, 94.08%, and 91.21% after re-ranking. The proposed method demonstrates a high generalization capability and improves both quantitative and qualitative performance. Finally, the proposed multi-part feature network, with the combination of PAM and ECA, offers a promising solution for person Re-ID, by combining the benefits of temporal, spatial, and channel information. The results of this study evidence the effectiveness and potential of the suggested method for person Re-ID in computer vision applications. [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]

Anomalous road manhole covers pose a potential risk to road safety in cities. In the development of smart cities, computer vision techniques use deep learning to automatically detect anomalous manhole covers to avoid these risks. One important problem is that a large amount of data are required to train a road anomaly manhole cover detection model. The number of anomalous manhole covers is usually small, which makes it a challenge to create training datasets quickly. To expand the dataset and improve the generalization of the model, researchers usually copy and paste samples from the original data to other data in order to achieve data augmentation. In this paper, we propose a new data augmentation method, which uses data that do not exist in the original dataset as samples to automatically select the pasting position of manhole cover samples and predict the transformation parameters via visual prior experience and perspective transformations, making it more accurately capture the actual shape of manhole covers on a road. Without using other data enhancement processes, our method raises the mean average precision (mAP) by at least 6.8 compared with the baseline model. [ABSTRACT FROM AUTHOR]

During flight, unmanned aerial vehicles (UAVs) need several sensors to follow a predefined path and reach a specific destination. To this aim, they generally exploit an inertial measurement unit (IMU) for pose estimation. Usually, in the UAV context, an IMU entails a three-axis accelerometer and a three-axis gyroscope. However, as happens for many physical devices, they can present some misalignment between the real value and the registered one. These systematic or occasional errors can derive from different sources and could be related to the sensor itself or to external noise due to the place where it is located. Hardware calibration requires special equipment, which is not always available. In any case, even if possible, it can be used to solve the physical problem and sometimes requires removing the sensor from its location, which is not always feasible. At the same time, solving the problem of external noise usually requires software procedures. Moreover, as reported in the literature, even two IMUs from the same brand and the same production chain could produce different measurements under identical conditions. This paper proposes a soft calibration procedure to reduce the misalignment created by systematic errors and noise based on the grayscale or RGB camera built-in on the drone. Based on the transformer neural network architecture trained in a supervised learning fashion on pairs of short videos shot by the UAV's camera and the correspondent UAV measurements, the strategy does not require any special equipment. It is easily reproducible and could be used to increase the trajectory accuracy of the UAV during the flight. [ABSTRACT FROM AUTHOR]

Video streaming-based real-time vehicle identification and license plate recognition systems are challenging to design and deploy in terms of real-time processing on edge, dealing with low image resolution, high noise, and identification. This paper addresses these issues by introducing a novel multi-stage, real-time, deep learning-based vehicle identification and license plate recognition system. The system is based on a set of algorithms that efficiently integrate two object detectors, an image classifier, and a multi-object tracker to recognize car models and license plates. The information redundancy of Saudi license plates' Arabic and English characters is leveraged to boost the license plate recognition accuracy while satisfying real-time inference performance. The system optimally achieves real-time performance on edge GPU devices and maximizes models' accuracy by taking advantage of the temporally redundant information of the video stream's frames. The edge device sends a notification of the detected vehicle and its license plate only once to the cloud after completing the processing. The system was experimentally evaluated on vehicles and license plates in real-world unconstrained environments at several parking entrance gates. It achieves 17.1 FPS on a Jetson Xavier AGX edge device with no delay. The comparison between the accuracy on the videos and on static images extracted from them shows that the processing of video streams using this proposed system enhances the relative accuracy of the car model and license plate recognition by 13% and 40%, respectively. This research work has won two awards in 2021 and 2022. [ABSTRACT FROM AUTHOR]

With the rapid advancement of deep learning theory and hardware device computing capacity, computer vision tasks, such as object detection and instance segmentation, have entered a revolutionary phase in recent years. As a result, extremely challenging integrated tasks, such as person search, might develop quickly. The majority of efficient network frameworks, such as Seq-Net, are based on Faster R-CNN. However, because of the parallel structure of Faster R-CNN, the performance of re-ID can be significantly impacted by the single-layer, low resolution, and occasionally overlooked check feature diagrams retrieved during pedestrian detection. To address these issues, this paper proposed a person search methodology based on an inception convolution and feature fusion module (IC-FFM) using Seq-Net (Sequential End-to-end Network) as the benchmark. First, we replaced the general convolution in ResNet-50 with the new inception convolution module (ICM), allowing the convolution operation to effectively and dynamically distribute various channels. Then, to improve the accuracy of information extraction, the feature fusion module (FFM) was created to combine multi-level information using various levels of convolution. Finally, Bounding Box regression was created using convolution and the double-head module (DHM), which considerably enhanced the accuracy of pedestrian retrieval by combining global and fine-grained information. Experiments on CHUK-SYSU and PRW datasets showed that our method has higher accuracy than Seq-Net. In addition, our method is simpler and can be easily integrated into existing two-stage frameworks. [ABSTRACT FROM AUTHOR]

Recently, the scientific community has placed great emphasis on the recognition of human activity, especially in the area of health and care for the elderly. There are already practical applications of activity recognition and unusual conditions that use body sensors such as wrist-worn devices or neck pendants. These relatively simple devices may be prone to errors, might be uncomfortable to wear, might be forgotten or not worn, and are unable to detect more subtle conditions such as incorrect postures. Therefore, other proposed methods are based on the use of images and videos to carry out human activity recognition, even in open spaces and with multiple people. However, the resulting increase in the size and complexity involved when using image data requires the use of the most recent advanced machine learning and deep learning techniques. This paper presents an approach based on deep learning with attention to the recognition of activities from multiple frames. Feature extraction is performed by estimating the pose of the human skeleton, and classification is performed using a neural network based on Bidirectional Encoder Representation of Transformers (BERT). This algorithm was trained with the UP-Fall public dataset, generating more balanced artificial data with a Generative Adversarial Neural network (GAN), and evaluated with real data, outperforming the results of other activity recognition methods using the same dataset. [ABSTRACT FROM AUTHOR]

The last paper of this Special Issue, entitled "3D Sensors for Sewer Inspection: A Quantitative Review and Analysis" [[13]], a study of different depth perception approaches - ToF, passive stereo, and active stereo - is conducted to identify the solution that is best-suited for sewer inspection. Time-of-Flight (ToF) sensors represent a popular choice among active depth sensors, and the Multi-Path Interference (MPI) effect is tackled in the third paper, "Deep Learning for Transient Image Reconstruction from ToF Data" [[5]]. The fourth paper, "Combining Augmented Reality and 3D Printing to Improve Surgical Workflows in Orthopedic Oncology: Smartphone Application and Clinical Evaluation" [[6]], explores the field of medical imaging and introduces an innovative solution for orthopedic oncological surgery, combining 3D printing and Augmented Reality (AR). Effective 3D perception of an observed scene greatly enriches the knowledge about the surrounding environment and is crucial to effectively develop high-level applications for various purposes. [Extracted from the article]

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]

It is important to estimate the exact depth from 2D images, and many studies have been conducted for a long period of time to solve depth estimation problems. Recently, as research on estimating depth from monocular camera images based on deep learning is progressing, research for estimating accurate depths using various techniques is being conducted. However, depth estimation from 2D images has been a problem in predicting the boundary between objects. In this paper, we aim to predict sophisticated depths by emphasizing the precise boundaries between objects. We propose a depth estimation network with encoder–decoder structures using the Laplacian pyramid and local planar guidance method. In the process of upsampling the learned features using the encoder, the purpose of this step is to obtain a clearer depth map by guiding a more sophisticated boundary of an object using the Laplacian pyramid and local planar guidance techniques. We train and test our models with KITTI and NYU Depth V2 datasets. The proposed network constructs a DNN using only convolution and uses the ConvNext networks as a backbone. A trained model shows the performance of the absolute relative error (Abs_rel) 0.054 and root mean square error (RMSE) 2.252 based on the KITTI dataset and absolute relative error (Abs_rel) 0.102 and root mean square error 0.355 based on the NYU Depth V2 dataset. On the state-of-the-art monocular depth estimation, our network performance shows the fifth-best performance based on the KITTI Eigen split and the eighth-best performance based on the NYU Depth V2. [ABSTRACT FROM AUTHOR]

There is great interest in automatically detecting road weather and understanding its impacts on the overall safety of the transport network. This can, for example, support road condition-based maintenance or even serve as detection systems that assist safe driving during adverse climate conditions. In computer vision, previous work has demonstrated the effectiveness of deep learning in predicting weather conditions from outdoor images. However, training deep learning models to accurately predict weather conditions using real-world road-facing images is difficult due to: (1) the simultaneous occurrence of multiple weather conditions; (2) imbalanced occurrence of weather conditions throughout the year; and (3) road idiosyncrasies, such as road layouts, illumination, and road objects, etc. In this paper, we explore the use of a focal loss function to force the learning process to focus on weather instances that are hard to learn with the objective of helping address data imbalances. In addition, we explore the attention mechanism for pixel-based dynamic weight adjustment to handle road idiosyncrasies using state-of-the-art vision transformer models. Experiments with a novel multi-label road weather dataset show that focal loss significantly increases the accuracy of computer vision approaches for imbalanced weather conditions. Furthermore, vision transformers outperform current state-of-the-art convolutional neural networks in predicting weather conditions with a validation accuracy of 92% and an F1-score of 81.22%, which is impressive considering the imbalanced nature of the dataset. [ABSTRACT FROM AUTHOR]

Understanding actions in videos remains a significant challenge in computer vision, which has been the subject of several pieces of research in the last decades. Convolutional neural networks (CNN) are a significant component of this topic and play a crucial role in the renown of Deep Learning. Inspired by the human vision system, CNN has been applied to visual data exploitation and has solved various challenges in various computer vision tasks and video/image analysis, including action recognition (AR). However, not long ago, along with the achievement of the transformer in natural language processing (NLP), it began to set new trends in vision tasks, which has created a discussion around whether the Vision Transformer models (ViT) will replace CNN in action recognition in video clips. This paper conducts this trending topic in detail, the study of CNN and Transformer for Action Recognition separately and a comparative study of the accuracy-complexity trade-off. Finally, based on the performance analysis's outcome, the question of whether CNN or Vision Transformers will win the race will be discussed. [ABSTRACT FROM AUTHOR]

Most facial recognition and face analysis systems start with facial detection. Early techniques, such as Haar cascades and histograms of directed gradients, mainly rely on features that had been manually developed from particular images. However, these techniques are unable to correctly synthesize images taken in untamed situations. However, deep learning's quick development in computer vision has also sped up the development of a number of deep learning-based face detection frameworks, many of which have significantly improved accuracy in recent years. When detecting faces in face detection software, the difficulty of detecting small, scale, position, occlusion, blurring, and partially occluded faces in uncontrolled conditions is one of the problems of face identification that has been explored for many years but has not yet been entirely resolved. In this paper, we propose Retina net baseline, a single-stage face detector, to handle the challenging face detection problem. We made network improvements that boosted detection speed and accuracy. In Experiments, we used two popular datasets, such as WIDER FACE and FDDB. Specifically, on the WIDER FACE benchmark, our proposed method achieves AP of 41.0 at speed of 11.8 FPS with a single-scale inference strategy and AP of 44.2 with multi-scale inference strategy, which are results among one-stage detectors. Then, we trained our model during the implementation using the PyTorch framework, which provided an accuracy of 95.6% for the faces, which are successfully detected. Visible experimental results show that our proposed model outperforms seamless detection and recognition results achieved using performance evaluation matrices. [ABSTRACT FROM AUTHOR]

Limited by computing resources of embedded devices, there are problems in the field of fabric defect detection, including small defect size, extremely unbalanced aspect ratio of defect size, and slow detection speed. To address these problems, a sliding window multihead self-attention mechanism is proposed for the detection of small targets, and the Swin Transformer module is introduced to replace the main module in the original YOLOv5 algorithm. First, to reduce the distance between several scales, the weighted bidirectional feature network is employed on embedded devices. In addition, it is helpful to improve the perception of small-target faults by incorporating a detection layer to achieve four-scale detection. At last, to improve the learning of positive sample instances and lower the missed detection rate, the generalized focal loss function is finally implemented on YOLOv5. Experimental results show that the accuracy of the improved algorithm on the fabric dataset reaches 85.6%, and the mAP is increased by 4.2% to 76.5%, which meets the requirements for real-time detection on embedded devices. [ABSTRACT FROM AUTHOR]

3D reconstruction is the computer vision task of reconstructing the 3D shape of an object from multiple 2D images. Most existing algorithms for this task are designed for offline settings, producing a single reconstruction from a batch of images taken from diverse viewpoints. Alongside reconstruction accuracy, additional considerations arise when 3D reconstructions are used in real-time processing pipelines for applications such as robot navigation or manipulation. In these cases, an accurate 3D reconstruction is already required while the data gathering is still in progress. In this paper, we demonstrate how existing batch-based reconstruction algorithms lead to suboptimal reconstruction quality when used for online, iterative 3D reconstruction and propose appropriate modifications to the existing Pix2Vox++ architecture. When additional viewpoints become available at a high rate, e.g., from a camera mounted on a drone, selecting the most informative viewpoints is important in order to mitigate long term memory loss and to reduce the computational footprint. We present qualitative and quantitative results on the optimal selection of viewpoints and show that state-of-the-art reconstruction quality is already obtained with elementary selection algorithms. [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]

There are physical Human–Robot Interaction (pHRI) applications where the robot has to grab the human body, such as rescue or assistive robotics. Being able to precisely estimate the grasping location when grabbing a human limb is crucial to perform a safe manipulation of the human. Computer vision methods provide pre-grasp information with strong constraints imposed by the field environments. Force-based compliant control, after grasping, limits the amount of applied strength. On the other hand, valuable tactile and proprioceptive information can be obtained from the pHRI gripper, which can be used to better know the features of the human and the contact state between the human and the robot. This paper presents a novel dataset of tactile and kinesthetic data obtained from a robot gripper that grabs a human forearm. The dataset is collected with a three-fingered gripper with two underactuated fingers and a fixed finger with a high-resolution tactile sensor. A palpation procedure is performed to record the shape of the forearm and to recognize the bones and muscles in different sections. Moreover, an application for the use of the database is included. In particular, a fusion approach is used to estimate the actual grasped forearm section using both kinesthetic and tactile information on a regression deep-learning neural network. First, tactile and kinesthetic data are trained separately with Long Short-Term Memory (LSTM) neural networks, considering the data are sequential. Then, the outputs are fed to a Fusion neural network to enhance the estimation. The experiments conducted show good results in training both sources separately, with superior performance when the fusion approach is considered. [ABSTRACT FROM AUTHOR]

With a large number of Local Binary Patterns (LBP) variants being currently used today, the significant and importance of visual descriptors in computer vision applications are prominent. This paper presents a novel visual descriptor, i.e., SIM-LBP. It employs a new matrix technique called the Symmetric Inline Matrix generator method, which acts as a new variant of LBP. The key feature that separates our variant from existing counterparts is that our variant is very efficient in extracting facial expression features like eyes, eye brows, nose and mouth in a wide range of lighting conditions. For testing our model, we applied SIM-LBP on the JAFFE dataset to convert all the images to its corresponding SIM-LBP transformed variant. These transformed images are then used to train a Convolution Neural Network (CNN) based deep learning model for facial expressions recognition (FER). Several performance evaluation metrics, i.e., recognition accuracy rate, precision, recall, and F1-score, were used to test mode efficiency in comparison with those using the traditional LBP descriptor and other LBP variants. Our model outperformed in all four matrices with the proposed SIM-LBP transformation on the input images against those of baseline methods. In comparison analysis with the other state-of-the-art methods, it shows the usefulness of the proposed SIM-LBP model. Our proposed SIM-LBP variant transformation can also be applied on facial images to identify a person's mental states and predict mood variations. [ABSTRACT FROM AUTHOR]

Object detection is a computer vision task that involves localisation and classification of objects in an image. Video data implicitly introduces several challenges, such as blur, occlusion and defocus, making video object detection more challenging in comparison to still image object detection, which is performed on individual and independent images. This paper tackles these challenges by proposing an attention-heavy framework for video object detection that aggregates the disentangled features extracted from individual frames. The proposed framework is a two-stage object detector based on the Faster R-CNN architecture. The disentanglement head integrates scale, spatial and task-aware attention and applies it to the features extracted by the backbone network across all the frames. Subsequently, the aggregation head incorporates temporal attention and improves detection in the target frame by aggregating the features of the support frames. These include the features extracted from the disentanglement network along with the temporal features. We evaluate the proposed framework using the ImageNet VID dataset and achieve a mean Average Precision (mAP) of 49.8 and 52.5 using the backbones of ResNet-50 and ResNet-101, respectively. The improvement in performance over the individual baseline methods validates the efficacy of the proposed approach. [ABSTRACT FROM AUTHOR]

Recent image-style transfer methods use the structure of a VGG feature network to encode and decode the feature map of the image. Since the network is designed for the general image-classification task, it has a number of channels and, accordingly, requires a huge amount of memory and high computational power, which is not mandatory for such a relatively simple task as image-style transfer. In this paper, we propose a new technique to size down the previously used style transfer network for eliminating the redundancy of the VGG feature network in memory consumption and computational cost. Our method automatically finds a number of consistently inactive convolution channels during the network training phase by using two new losses, i.e., channel loss and xor loss. The former maximizes the number of inactive channels and the latter fixes the positions of these inactive channels to be the same for the image. Our method improves the image generation speed to be up to 49% faster and reduces the number of parameters by 20% while maintaining style transferring performance. Additionally, our losses are also effective in pruning the VGG16 classifier network, i.e., parameter reduction by 26% and top-1 accuracy improvement by 0.16% on CIFAR-10. [ABSTRACT FROM AUTHOR]

Point clouds are one of the most widely used data formats produced by depth sensors. There is a lot of research into feature extraction from unordered and irregular point cloud data. Deep learning in computer vision achieves great performance for data classification and segmentation of 3D data points as point clouds. Various research has been conducted on point clouds and remote sensing tasks using deep learning (DL) methods. However, there is a research gap in providing a road map of existing work, including limitations and challenges. This paper focuses on introducing the state-of-the-art DL models, categorized by the structure of the data they consume. The models' performance is collected, and results are provided for benchmarking on the most used datasets. Additionally, we summarize the current benchmark 3D datasets publicly available for DL training and testing. In our comparative study, we can conclude that convolutional neural networks (CNNs) achieve the best performance in various remote-sensing applications while being light-weighted models, namely Dynamic Graph CNN (DGCNN) and ConvPoint. [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]

The development of the smartphone and computer vision technique provides customers with a convenient approach to identify tea species, as well as qualities. However, the prediction model may not behave robustly due to changes in illumination conditions. Fluorescence imaging can induce the fluorescence signal from typical components, and thus may improve the prediction accuracy. In this paper, a tea classification method based on fluorescence imaging and convolutional neural networks (CNN) is proposed. Ultra-violet (UV) LEDs with a central wavelength of 370 nm were utilized to induce the fluorescence of tea samples so that the fluorescence images could be captured. Five kinds of tea were included and pre-processed. Two CNN-based classification models, e.g., the VGG16 and ResNet-34, were utilized for model training. Images captured under the conventional fluorescent lamp were also tested for comparison. The results show that the accuracy of the classification model based on fluorescence images is better than those based on the white-light illumination images, and the performance of the VGG16 model is better than the ResNet-34 model in our case. The classification accuracy of fluorescence images reached 97.5%, which proves that the LED-induced fluorescence imaging technique is promising to use in our daily life. [ABSTRACT FROM AUTHOR]

The diffractive deep neural network (D2NN) can efficiently accomplish 2D object recognition based on rapid optical manipulation. Moreover, the multiple-view D2NN array (MDA) possesses the obvious advantage of being able to effectively achieve 3D object classification. At present, 3D target recognition should be performed in a high-speed and dynamic way. It should be invariant to the typical shifting, scaling, and rotating variance of targets in relatively complicated circumstances, which remains a shortcoming of optical neural network architectures. In order to efficiently recognize 3D targets based on the developed D2NN, a more robust MDA (mr-MDA) is proposed in this paper. Through utilizing a new training strategy to tackle several random disturbances introduced into the optical neural network system, a trained mr-MDA model constructed by us was numerically verified, demonstrating that the training strategy is able to dynamically recognize 3D objects in a relatively stable way. [ABSTRACT FROM AUTHOR]

The grading of cancer tissues is still one of the main challenges for pathologists. The development of enhanced analysis strategies hence becomes crucial to accurately identify and further deal with each individual case. Raman spectroscopy (RS) is a promising tool for the classification of tumor tissues as it allows us to obtain the biochemical maps of the tissues under analysis and to observe their evolution in terms of biomolecules, proteins, lipid structures, DNA, vitamins, and so on. However, its potential could be further improved by providing a classification system which would be able to recognize the sample tumor category by taking as input the raw Raman spectroscopy signal; this could provide more reliable responses in shorter time scales and could reduce or eliminate false-positive or -negative diagnoses. Deep Learning techniques have become ubiquitous in recent years, with models able to perform classification with high accuracy in most diverse fields of research, e.g., natural language processing, computer vision, medical imaging. However, deep models often rely on huge labeled datasets to produce reasonable accuracy, otherwise occurring in overfitting issues when the training data is insufficient. In this paper, we propose a chondrogenic tumor CLAssification through wavelet transform of RAman spectra (CLARA), which is able to classify with high accuracy Raman spectra obtained from bone tissues. CLARA recognizes and grades the tumors in the evaluated dataset with 97 % accuracy by exploiting a classification pipeline consisting of the division of the original task in two binary classification steps, where the first is performed on the original RS signals while the latter is accomplished through the use of a hybrid temporal-frequency 2D transform. [ABSTRACT FROM AUTHOR]

This paper introduces a new dataset of a surgical knot-tying task, and a multi-modal deep learning model that achieves comparable performance to expert human raters on this skill assessment task. Seventy-two surgical trainees and faculty were recruited for the knot-tying task, and were recorded using video, kinematic, and image data. Three expert human raters conducted the skills assessment using the Objective Structured Assessment of Technical Skill (OSATS) Global Rating Scale (GRS). We also designed and developed three deep learning models: a ResNet-based image model, a ResNet-LSTM kinematic model, and a multi-modal model leveraging the image and time-series kinematic data. All three models demonstrate performance comparable to the expert human raters on most GRS domains. The multi-modal model demonstrates the best overall performance, as measured using the mean squared error (MSE) and intraclass correlation coefficient (ICC). This work is significant since it demonstrates that multi-modal deep learning has the potential to replicate human raters on a challenging human-performed knot-tying task. The study demonstrates an algorithm with state-of-the-art performance in surgical skill assessment. As objective assessment of technical skill continues to be a growing, but resource-heavy, element of surgical education, this study is an important step towards automated surgical skill assessment, ultimately leading to reduced burden on training faculty and institutes. [ABSTRACT FROM AUTHOR]

The accurate intelligent identification and detection of road cracks is a key issue in road maintenance, and it has become popular to perform this task through the field of computer vision. In this paper, we proposed a deep learning-based crack detection method that initially uses the idea of image sparse representation and compressed sensing to preprocess the datasets. Only the pixels that represent the crack features remain, while most pixels of non-crack features are relatively sparse, which can significantly improve the accuracy and efficiency of crack identification. The proposed method achieved good results based on the limited datasets of crack images. Various algorithms were tested, namely, linear smooth, median filtering, Gaussian smooth, and grayscale threshold, where the optimal parameters of the various algorithms were analyzed and trained with faster regions with convolutional neural network features (faster R-CNN). The results of the experiments showed that the proposed method has good robustness, with higher detection efficiency in the presence of, for example, road markings, shallow cracks, multiple cracks, and blurring. The result shows that the improvement of mean average precision (mAP) can reach 5% compared with the original method. [ABSTRACT FROM AUTHOR]

The rapid development of technology has brought about a revolution in healthcare stimulating a wide range of smart and autonomous applications in homes, clinics, surgeries and hospitals. Smart healthcare opens the opportunity for a qualitative advance in the relations between healthcare providers and end-users for the provision of healthcare such as enabling doctors to diagnose remotely while optimizing the accuracy of the diagnosis and maximizing the benefits of treatment by enabling close patient monitoring. This paper presents a comprehensive review of non-invasive vital data acquisition and the Internet of Things in healthcare informatics and thus reports the challenges in healthcare informatics and suggests future work that would lead to solutions to address the open challenges in IoT and non-invasive vital data acquisition. In particular, the conducted review has revealed that there has been a daunting challenge in the development of multi-frequency vital IoT systems, and addressing this issue will help enable the vital IoT node to be reachable by the broker in multiple area ranges. Furthermore, the utilization of multi-camera systems has proven its high potential to increase the accuracy of vital data acquisition, but the implementation of such systems has not been fully developed with unfilled gaps to be bridged. Moreover, the application of deep learning to the real-time analysis of vital data on the node/edge side will enable optimal, instant offline decision making. Finally, the synergistic integration of reliable power management and energy harvesting systems into non-invasive data acquisition has been omitted so far, and the successful implementation of such systems will lead to a smart, robust, sustainable and self-powered healthcare system. [ABSTRACT FROM AUTHOR]

The paper presents a simple, yet robust computer vision system for robot arm tracking with the use of RGB-D cameras. Tracking means to measure in real time the robot state given by three angles and with known restrictions about the robot geometry. The tracking system consists of two parts: image preprocessing and machine learning. In the machine learning part, we compare two approaches: fitting the robot pose to the point cloud and fitting the convolutional neural network model to the sparse 3D depth images. The advantage of the presented approach is direct use of the point cloud transformed to the sparse image in the network input and use of sparse convolutional and pooling layers (sparse CNN). The experiments confirm that the robot tracking is performed in real time and with an accuracy comparable to the accuracy of the depth sensor. [ABSTRACT FROM AUTHOR]

Ergonomic risk assessment is vital for identifying work-related human postures that can be detrimental to the health of a worker. Traditionally, ergonomic risks are reported by human experts through time-consuming and error-prone procedures; however, automatic algorithmic methods have recently started to emerge. To further facilitate the automatic ergonomic risk assessment, this paper proposes a novel variational deep learning architecture to estimate the ergonomic risk of any work-related task by utilizing the Rapid Entire Body Assessment (REBA) framework. The proposed method relies on the processing of RGB images and the extraction of 3D skeletal information that is then fed to a novel deep network for accurate and robust estimation of REBA scores for both individual body parts and the entire body. Through a variational approach, the proposed method processes the skeletal information to construct a descriptive skeletal latent space that can accurately model human postures. Moreover, the proposed method distills knowledge from ground truth ergonomic risk scores and leverages it to further enhance the discrimination ability of the skeletal latent space, leading to improved accuracy. Experiments on two well-known datasets (i.e., University of Washington Indoor Object Manipulation (UW-IOM) and Technische Universität München (TUM) Kitchen) validate the ability of the proposed method to achieve accurate results, overcoming current state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The task of reconstructing 3D scenes based on visual data represents a longstanding problem in computer vision. Common reconstruction approaches rely on the use of multiple volumetric primitives to describe complex objects. Superquadrics (a class of volumetric primitives) have shown great promise due to their ability to describe various shapes with only a few parameters. Recent research has shown that deep learning methods can be used to accurately reconstruct random superquadrics from both 3D point cloud data and simple depth images. In this paper, we extended these reconstruction methods to intensity and color images. Specifically, we used a dedicated convolutional neural network (CNN) model to reconstruct a single superquadric from the given input image. We analyzed the results in a qualitative and quantitative manner, by visualizing reconstructed superquadrics as well as observing error and accuracy distributions of predictions. We showed that a CNN model designed around a simple ResNet backbone can be used to accurately reconstruct superquadrics from images containing one object, but only if one of the spatial parameters is fixed or if it can be determined from other image characteristics, e.g., shadows. Furthermore, we experimented with images of increasing complexity, for example, by adding textures, and observed that the results degraded only slightly. In addition, we show that our model outperforms the current state-of-the-art method on the studied task. Our final result is a highly accurate superquadric reconstruction model, which can also reconstruct superquadrics from real images of simple objects, without additional training. [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]

As an essential task in computer vision, video anomaly detection technology is used in video surveillance, scene understanding, road traffic analysis and other fields. However, the definition of anomaly, scene change and complex background present great challenges for video anomaly detection tasks. The insight that motivates this study is that the reconstruction error for normal samples would be lower since they are closer to the training data, while the anomalies could not be reconstructed well. In this paper, we proposed a Convolutional Recurrent AutoEncoder (CR-AE), which combines an attention-based Convolutional Long–Short-Term Memory (ConvLSTM) network and a Convolutional AutoEncoder. The ConvLSTM network and the Convolutional AutoEncoder could capture the irregularity of the temporal pattern and spatial irregularity, respectively. The attention mechanism was used to obtain the current output characteristics from the hidden state of each Covn-LSTM layer. Then, a convolutional decoder was utilized to reconstruct the input video clip and the testing video clip with higher reconstruction error, which were further judged to be anomalies. The proposed method was tested on two popular benchmarks (UCSD ped2 Dataset and Avenue Dataset), and the experimental results demonstrated that CR-AE achieved 95.6% and 73.1% frame-level AUC on two public datasets, respectively. [ABSTRACT FROM AUTHOR]

The development of recent image style transfer methods allows the quick transformation of an input content image into an arbitrary style. However, these methods have a limitation that the scale-across style pattern of a style image cannot be fully transferred into a content image. In this paper, we propose a new style transfer method, named total style transfer, that resolves this limitation by utilizing intra/inter-scale statistics of multi-scaled feature maps without losing the merits of the existing methods. First, we use a more general feature transform layer that employs intra/inter-scale statistics of multi-scaled feature maps and transforms the multi-scaled style of a content image into that of a style image. Secondly, we generate a multi-scaled stylized image by using only a single decoder network with skip-connections, in which multi-scaled features are merged. Finally, we optimize the style loss for the decoder network in the intra/inter-scale statistics of image style. Our improved total style transfer can generate a stylized image with a scale-across style pattern from a pair of content and style images in one forwarding pass. Our method achieved less memory consumption and faster feed-forwarding speed compared with the recent cascade scheme and the lowest style loss among the recent style transfer methods. [ABSTRACT FROM AUTHOR]

Age estimation from human faces is an important yet challenging task in computer vision because of the large differences between physical age and apparent age. Due to the differences including races, genders, and other factors, the performance of a learning method for this task strongly depends on the training data. Although many inspiring works have focused on the age estimation of a single human face through deep learning, the existing methods still have lower performance when dealing with faces in videos because of the differences in head pose between frames, which can lead to greatly different results. In this paper, a combined system of age estimation and head pose estimation is proposed to improve the performance of age estimation from faces in videos. We use deep regression forests (DRFs) to estimate the age of facial images, while a multiloss convolutional neural network is also utilized to estimate the head pose. Accordingly, we estimate the age of faces only for head poses within a set degree threshold to enable value refinement. First, we divided the images in the Cross-Age Celebrity Dataset (CACD) and the Asian Face Age Dataset (AFAD) according to the estimated head pose degrees and generated separate age estimates for images with different poses. The experimental results showed that the accuracy of age estimation from frontal facial images was better than that for faces at different angles, thus demonstrating the effect of head pose on age estimation. Further experiments were conducted on several videos to estimate the age of the same person with his or her face at different angles, and the results show that our proposed combined system can provide more precise and reliable age estimates than a system without head pose estimation. [ABSTRACT FROM AUTHOR]

In this paper, we propose an activity detection system using a 24 × 32 resolution infrared array sensor placed on the ceiling. We first collect the data at different resolutions (i.e., 24 × 32, 12 × 16, and 6 × 8) and apply the advanced deep learning (DL) techniques of Super-Resolution (SR) and denoising to enhance the quality of the images. We then classify the images/sequences of images depending on the activities the subject is performing using a hybrid deep learning model combining a Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM). We use data augmentation to improve the training of the neural networks by incorporating a wider variety of samples. The process of data augmentation is performed by a Conditional Generative Adversarial Network (CGAN). By enhancing the images using SR, removing the noise, and adding more training samples via data augmentation, our target is to improve the classification accuracy of the neural network. Through experiments, we show that employing these deep learning techniques to low-resolution noisy infrared images leads to a noticeable improvement in performance. The classification accuracy improved from 78.32% to 84.43% (for images with 6 × 8 resolution), and from 90.11% to 94.54% (for images with 12 × 16 resolution) when we used the CNN and CNN + LSTM networks, respectively. [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]

In recent years, due to the advancements in machine learning, object detection has become a mainstream task in the computer vision domain. The first phase of object detection is to find the regions where objects can exist. With the improvements in deep learning, traditional approaches, such as sliding windows and manual feature selection techniques, have been replaced with deep learning techniques. However, object detection algorithms face a problem when performed in low light, challenging weather, and crowded scenes, similar to any other task. Such an environment is termed a challenging environment. This paper exploits pixel-level information to improve detection under challenging situations. To this end, we exploit the recently proposed hybrid task cascade network. This network works collaboratively with detection and segmentation heads at different cascade levels. We evaluate the proposed methods on three complex datasets of ExDark, CURE-TSD, and RESIDE, and achieve a mAP of 0.71, 0.52, and 0.43, respectively. Our experimental results assert the efficacy of the proposed approach. [ABSTRACT FROM AUTHOR]

The safe in-field operation of autonomous agricultural vehicles requires detecting all objects that pose a risk of collision. Current vision-based algorithms for object detection and classification are unable to detect unknown classes of objects. In this paper, the problem is posed as anomaly detection instead, where convolutional autoencoders are applied to identify any objects deviating from the normal pattern. Training an autoencoder network to reconstruct normal patterns in agricultural fields makes it possible to detect unknown objects by high reconstruction error. Basic autoencoder (AE), vector-quantized variational autoencoder (VQ-VAE), denoising autoencoder (DAE) and semisupervised autoencoder (SSAE) with a max-margin-inspired loss function are investigated and compared with a baseline object detector based on YOLOv5. Results indicate that SSAE with an area under the curve for precision/recall (PR AUC) of 0.9353 outperforms other autoencoder models and is comparable to an object detector with a PR AUC of 0.9794. Qualitative results show that SSAE is capable of detecting unknown objects, whereas the object detector is unable to do so and fails to identify known classes of objects in specific cases. [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]

Intelligent video surveillance systems are rapidly being introduced to public places. The adoption of computer vision and machine learning techniques enables various applications for collected video features; one of the major is safety monitoring. The efficacy of violent event detection is measured by the efficiency and accuracy of violent event detection. In this paper, we present a novel architecture for violence detection from video surveillance cameras. Our proposed model is a spatial feature extracting a U-Net-like network that uses MobileNet V2 as an encoder followed by LSTM for temporal feature extraction and classification. The proposed model is computationally light and still achieves good results—experiments showed that an average accuracy is 0.82 ± 2% and average precision is 0.81 ± 3% using a complex real-world security camera footage dataset based on RWF-2000. [ABSTRACT FROM AUTHOR]

Public aquariums and similar institutions often use video as a method to monitor the behavior, health, and status of aquatic organisms in their environments. These video footages take up a sizeable amount of space and require the use of autoencoders to reduce their file size for efficient storage. The autoencoder neural network is an emerging technique which uses the extracted latent space from an input source to reduce the image size for storage, and then reconstructs the source within an acceptable loss range for use. To meet an aquarium's practical needs, the autoencoder must have easily maintainable codes, low power consumption, be easily adoptable, and not require a substantial amount of memory use or processing power. Conventional configurations of autoencoders often provide results that perform beyond an aquarium's needs at the cost of being too complex for their architecture to handle, while few take low-contrast sources into consideration. Thus, in this instance, "keeping it simple" would be the ideal approach to the autoencoder's model design. This paper proposes a practical approach catered to an aquarium's specific needs through the configuration of autoencoder parameters. It first explores the differences between the two of the most widely applied autoencoder approaches, Multilayer Perceptron (MLP) and Convolution Neural Networks (CNN), to identify the most appropriate approach. The paper concludes that while both approaches (with proper configurations and image preprocessing) can reduce the dimensionality and reduce visual noise of the low-contrast images gathered from aquatic video footage, the CNN approach is more suitable for an aquarium's architecture. As an unexpected finding of the experiments conducted, the paper also discovered that by manipulating the formula for the MLP approach, the autoencoder could generate a denoised differential image that contains sharper and more desirable visual information to an aquarium's operation. Lastly, the paper has found that proper image preprocessing prior to the application of the autoencoder led to better model convergence and prediction results, as demonstrated both visually and numerically in the experiment. The paper concludes that by combining the denoising effect of MLP, CNN's ability to manage memory consumption, and proper image preprocessing, the specific practical needs of an aquarium can be adeptly fulfilled. [ABSTRACT FROM AUTHOR]