Search

Due to deep learning's accurate cognition of the street environment, the convolutional neural network has achieved dramatic development in the application of street scenes. Considering the needs of autonomous driving and assisted driving, in a general way, computer vision technology is used to find obstacles to avoid collisions, which has made semantic segmentation a research priority in recent years. However, semantic segmentation has been constantly facing new challenges for quite a long time. Complex network depth information, large datasets, real-time requirements, etc., are typical problems that need to be solved urgently in the realization of autonomous driving technology. In order to address these problems, we propose an improved lightweight real-time semantic segmentation network, which is based on an efficient image cascading network (ICNet) architecture, using multi-scale branches and a cascaded feature fusion unit to extract rich multi-level features. In this paper, a spatial information network is designed to transmit more prior knowledge of spatial location and edge information. During the course of the training phase, we append an external loss function to enhance the learning process of the deep learning network system as well. This lightweight network can quickly perceive obstacles and detect roads in the drivable area from images to satisfy autonomous driving characteristics. The proposed model shows substantial performance on the Cityscapes dataset. With the premise of ensuring real-time performance, several sets of experimental comparisons illustrate that SP-ICNet enhances the accuracy of road obstacle detection and provides nearly ideal prediction outputs. Compared to the current popular semantic segmentation network, this study also demonstrates the effectiveness of our lightweight network for road obstacle detection in autonomous driving. [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]

Unmanned Aerial Vehicles (UAVs) have been very effective in collecting aerial images data for various Internet-of-Things (IoT)/smart cities applications such as search and rescue, surveillance, vehicle detection, counting, intelligent transportation systems, to name a few. However, the real-time processing of collected data on edge in the context of the Internet-of-Drones remains an open challenge because UAVs have limited energy capabilities, while computer vision techniquesconsume excessive energy and require abundant resources. This fact is even more critical when deep learning algorithms, such as convolutional neural networks (CNNs), are used for classification and detection. In this paper, we first propose a system architecture of computation offloading for Internet-connected drones. Then, we conduct a comprehensive experimental study to evaluate the performance in terms of energy, bandwidth, and delay of the cloud computation offloading approach versus the edge computing approach of deep learning applications in the context of UAVs. In particular, we investigate the tradeoff between the communication cost and the computation of the two candidate approaches experimentally. The main results demonstrate that the computation offloading approach allows us to provide much higher throughput (i.e., frames per second) as compared to the edge computing approach, despite the larger communication delays. [ABSTRACT FROM AUTHOR]

Real time crowd analysis represents an active area of research within the computer vision community in general and scene analysis in particular. Over the last 10 years, various methods for crowd management in real time scenario have received immense attention due to large scale applications in people counting, public events management, disaster management, safety monitoring an so on. Although many sophisticated algorithms have been developed to address the task; crowd management in real time conditions is still a challenging problem being completely solved, particularly in wild and unconstrained conditions. In the proposed paper, we present a detailed review of crowd analysis and management, focusing on state-of-the-art methods for both controlled and unconstrained conditions. The paper illustrates both the advantages and disadvantages of state-of-the-art methods. The methods presented comprise the seminal research works on crowd management, and monitoring and then culminating state-of-the-art methods of the newly introduced deep learning methods. Comparison of the previous methods is presented, with a detailed discussion of the direction for future research work. We believe this review article will contribute to various application domains and will also augment the knowledge of the crowd analysis within the research community. [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]

In this paper, a complete system based on computer vision and deep learning is proposed for surface inspection of the armatures in a vibration motor with miniature volume. A device for imaging and positioning was designed in order to obtain the images of the surface of the armatures. The images obtained by the device were divided into a training set and a test set. With continuous experimental exploration and improvement, the most efficient deep-network model was designed. The results show that the model leads to high accuracy on both the training set and the test set. In addition, we proposed a training method to make the network designed by us perform better. To guarantee the quality of the motor, a double-branch discrimination mechanism was also proposed. In order to verify the reliability of the system, experimental verification was conducted on the production line, and a satisfactory discrimination performance was reached. The results indicate that the proposed detection system for the armatures based on computer vision and deep learning is stable and reliable for armature production lines. [ABSTRACT FROM AUTHOR]

Automation of agricultural processes requires systems that can accurately detect and classify produce in real industrial environments that include variation in fruit appearance due to illumination, occlusion, seasons, weather conditions, etc. In this paper we combine a visual processing approach inspired by colour-opponent theory in humans with recent advancements in one-stage deep learning networks to accurately, rapidly and robustly detect ripe soft fruits (strawberries) in real industrial settings and using standard (RGB) camera input. The resultant system was tested on an existent data-set captured in controlled conditions as well our new real-world data-set captured on a real strawberry farm over two months. We utilise F 1 score, the harmonic mean of precision and recall, to show our system matches the state-of-the-art detection accuracy ( F 1 : 0.793 vs. 0.799) in controlled conditions; has greater generalisation and robustness to variation of spatial parameters (camera viewpoint) in the real-world data-set ( F 1 : 0.744); and at a fraction of the computational cost allowing classification at almost 30fps. We propose that the L*a*b*Fruits system addresses some of the most pressing limitations of current fruit detection systems and is well-suited to application in areas such as yield forecasting and harvesting. Beyond the target application in agriculture this work also provides a proof-of-principle whereby increased performance is achieved through analysis of the domain data, capturing features at the input level rather than simply increasing model complexity. [ABSTRACT FROM AUTHOR]

Rapid and accurate industrial inspection to ensure the highest quality standards at a competitive price is one of the biggest challenges in the manufacturing industry. This paper shows an application of how a Deep Learning soft sensor application can be combined with a high-resolution optical quality control camera to increase the accuracy and reduce the cost of an industrial visual inspection process in the Printing Industry 4.0. During the process of producing gravure cylinders, mistakes like holes in the printing cylinder are inevitable. In order to improve the defect detection performance and reduce quality inspection costs by process automation, this paper proposes a deep neural network (DNN) soft sensor that compares the scanned surface to the used engraving file and performs an automatic quality control process by learning features through exposure to training data. The DNN sensor developed achieved a fully automated classification accuracy rate of 98.4%. Further research aims to use these results to three ends. Firstly, to predict the amount of errors a cylinder has, to further support the human operation by showing the error probability to the operator, and finally to decide autonomously about product quality without human involvement. [ABSTRACT FROM AUTHOR]

Transfer learning is a pervasive technology in computer vision and natural language processing fields, yielding exponential performance improvements by leveraging prior knowledge gained from data with different distributions. However, while recent works seek to mature machine learning and deep learning techniques in applications related to wireless communications, a field loosely termed radio frequency machine learning, few have demonstrated the use of transfer learning techniques for yielding performance gains, improved generalization, or to address concerns of training data costs. With modifications to existing transfer learning taxonomies constructed to support transfer learning in other modalities, this paper presents a tailored taxonomy for radio frequency applications, yielding a consistent framework that can be used to compare and contrast existing and future works. This work offers such a taxonomy, discusses the small body of existing works in transfer learning for radio frequency machine learning, and outlines directions where future research is needed to mature the field. [ABSTRACT FROM AUTHOR]

Complex hand gesture interactions among dynamic sign words may lead to misclassification, which affects the recognition accuracy of the ubiquitous sign language recognition system. This paper proposes to augment the feature vector of dynamic sign words with knowledge of hand dynamics as a proxy and classify dynamic sign words using motion patterns based on the extracted feature vector. In this method, some double-hand dynamic sign words have ambiguous or similar features across a hand motion trajectory, which leads to classification errors. Thus, the similar/ambiguous hand motion trajectory is determined based on the approximation of a probability density function over a time frame. Then, the extracted features are enhanced by transformation using maximal information correlation. These enhanced features of 3D skeletal videos captured by a leap motion controller are fed as a state transition pattern to a classifier for sign word classification. To evaluate the performance of the proposed method, an experiment is performed with 10 participants on 40 double hands dynamic ASL words, which reveals 97.98% accuracy. The method is further developed on challenging ASL, SHREC, and LMDHG data sets and outperforms conventional methods by 1.47%, 1.56%, and 0.37%, respectively. [ABSTRACT FROM AUTHOR]

The intelligent crack detection method is an important guarantee for the realization of intelligent operation and maintenance, and it is of great significance to traffic safety. In recent years, the recognition of road pavement cracks based on computer vision has attracted increasing attention. With the technological breakthroughs of general deep learning algorithms in recent years, detection algorithms based on deep learning and convolutional neural networks have achieved better results in the field of crack recognition. In this paper, deep learning is investigated to intelligently detect road cracks, and Faster R-CNN and Mask R-CNN are compared and analyzed. The results show that the joint training strategy is very effective, and we are able to ensure that both Faster R-CNN and Mask R-CNN complete the crack detection task when trained with only 130+ images and can outperform YOLOv3. However, the joint training strategy causes a degradation in the effectiveness of the bounding box detected by Mask R-CNN. [ABSTRACT FROM AUTHOR]

This paper presents a method to classify flow regime and vapor quality in vertical two-phase (vapor-liquid) flow, using a video of the flow as the input; this represents the first high-performing and entirely camera image-based method for the classification of a vertical flow regime (which is effective across a wide range of regimes) and the first image-based tool for estimating vapor quality. The approach makes use of computer vision techniques and deep learning to train a convolutional neural network (CNN), which is used for individual frame classification and image feature extraction, and a deep long short-term memory (LSTM) network, used to capture temporal information present in a sequence of image feature sets and to make a final vapor quality or flow regime classification. This novel architecture for two-phase flow studies achieves accurate flow regime and vapor quality classifications in a practical application to two-phase CO2 flow in vertical tubes, based on offline data and an online prototype implementation, developed as a proof of concept for the use of these models within a feedback control loop. The use of automatically selected image features, produced by a CNN architecture in three distinct tasks comprising flow-image classification, flow-regime classification, and vapor quality prediction, confirms that these features are robust and useful, and offer a viable alternative to manually extracting image features for image-based flow studies. The successful application of the LSTM network reveals the significance of temporal information for image-based studies of two-phase flow. [ABSTRACT FROM AUTHOR]

Manufacturing is an imperfect process that requires frequent checks and verifications to ensure products are being produced properly. In many cases, such as visual inspection, these checks can be automated to a certain degree. Incorporating advanced inspection techniques (i.e., via deep learning) into real-world inspection pipelines requires different mechanical, machine vision, and process-level considerations. In this work, we present an approach that builds upon prior work at an automotive gear facility located in Guelph, Ontario, which is looking to expand its defect detection capabilities. We outline a set of inspection-cell changes, which has led to full-gear surface scanning and inspection at a rate of every 7.5 s, and which is currently able to detect three common types of surface-level defects. [ABSTRACT FROM AUTHOR]

One of the key challenges in laser powder bed fusion (LPBF) additive manufacturing of metals is the appearance of microscopic pores in 3D-printed metallic structures. Quality control in LPBF can be accomplished with non-destructive imaging of the actual 3D-printed structures. Thermal tomography (TT) is a promising non-contact, non-destructive imaging method, which allows for the visualization of subsurface defects in arbitrary-sized metallic structures. However, because imaging is based on heat diffusion, TT images suffer from blurring, which increases with depth. We have been investigating the enhancement of TT imaging capability using machine learning. In this work, we introduce a novel multi-task learning (MTL) approach, which simultaneously performs the classification of synthetic TT images, and segmentation of experimental scanning electron microscopy (SEM) images. Synthetic TT images are obtained from computer simulations of metallic structures with subsurface elliptical-shaped defects, while experimental SEM images are obtained from imaging of LPBF-printed stainless-steel coupons. MTL network is implemented as a shared U-net encoder between the classification and the segmentation tasks. Results of this study show that the MTL network performs better in both the classification of synthetic TT images and the segmentation of SEM images tasks, as compared to the conventional approach when the individual tasks are performed independently of each other. [ABSTRACT FROM AUTHOR]

Regarding the interpretable techniques in the field of image recognition, Grad-CAM is widely used for feature localization in images to reflect the logical decision-making information behind the neural network due to its high applicability. However, extensive experimentation on a customized dataset revealed that the deep convolutional neural network (CNN) model based on Gradient-weighted Class Activation Mapping (Grad-CAM) technology cannot effectively resist the interference of large-scale noise. In this article, an optimization of the deep CNN model was proposed by incorporating the Dropkey and Dropout (as a comparison) algorithm. Compared with Grad-CAM, the improved Grad-CAM based on Dropkey applies an attention mechanism to the feature map before calculating the gradient, which can introduce randomness and eliminate some areas by applying a mask to the attention score. Experimental results show that the optimized Grad-CAM deep CNN model based on the Dropkey algorithm can effectively resist large-scale noise interference and achieve accurate localization of image features. For instance, under the interference of a noise variance of 0.6, the Dropkey-enhanced ResNet50 model achieves a confidence level of 0.878 in predicting results, while the other two models exhibit confidence levels of 0.766 and 0.481, respectively. Moreover, it exhibits excellent performance in visualizing tasks related to image features such as distortion, low contrast, and small object characteristics. Furthermore, it has promising prospects in practical computer vision applications. For instance, in the field of autonomous driving, it can assist in verifying whether deep learning models accurately understand and process crucial objects, road signs, pedestrians, or other elements in the environment. [ABSTRACT FROM AUTHOR]

This work investigates the application of Computer Vision to the problem of the automated counting and measuring of crabs and lobsters onboard fishing boats. The aim is to provide catch count and measurement data for these key commercial crustacean species. This can provide vital input data for stock assessment models, to enable the sustainable management of these species. The hardware system is required to be low-cost, have low-power usage, be waterproof, available (given current chip shortages), and able to avoid over-heating. The selected hardware is based on a Raspberry Pi 3A+ contained in a custom waterproof housing. This hardware places challenging limitations on the options for processing the incoming video, with many popular deep learning frameworks (even light-weight versions) unable to load or run given the limited computational resources. The problem can be broken into several steps: (1) Identifying the portions of the video that contain each individual animal; (2) Selecting a set of representative frames for each animal, e.g, lobsters must be viewed from the top and underside; (3) Detecting the animal within the frame so that the image can be cropped to the region of interest; (4) Detecting keypoints on each animal; and (5) Inferring measurements from the keypoint data. In this work, we develop a pipeline that addresses these steps, including a key novel solution to frame selection in video streams that uses classification, temporal segmentation, smoothing techniques and frame quality estimation. The developed pipeline is able to operate on the target low-power hardware and the experiments show that, given sufficient training data, reasonable performance is achieved. [ABSTRACT FROM AUTHOR]

Hand gesture recognition is a vital means of communication to convey information between humans and machines. We propose a novel model for hand gesture recognition based on computer vision methods and compare results based on images with complex scenes. While extracting skin color information is an efficient method to determine hand regions, complicated image backgrounds adversely affect recognizing the exact area of the hand shape. Some valuable features like saliency maps, histogram of oriented gradients (HOG), Canny edge detection, and skin color help us maximize the accuracy of hand shape recognition. Considering these features, we proposed an efficient hand posture detection model that improves the test accuracy results to over 99% on the NUS Hand Posture Dataset II and more than 97% on the hand gesture dataset with different challenging backgrounds. In addition, we added noise to around 60% of our datasets. Replicating our experiment, we achieved more than 98% and nearly 97% accuracy on NUS and hand gesture datasets, respectively. Experiments illustrate that the saliency method with HOG has stable performance for a wide range of images with complex backgrounds having varied hand colors and sizes. [ABSTRACT FROM AUTHOR]

Too often, the testing and evaluation of object detection, as well as the classification techniques for high-resolution remote sensing imagery, are confined to clean, discretely partitioned datasets, i.e., the closed-world model. In recent years, the performance on a number of benchmark datasets has exceeded 99% when evaluated using cross-validation techniques. However, real-world remote sensing data are truly big data, which often exceed billions of pixels. Therefore, one of the greatest challenges regarding the evaluation of machine learning models taken out of the clean laboratory setting and into the real world is the difficulty of measuring performance. It is necessary to evaluate these models on a grander scale, namely, tens of thousands of square kilometers, where it is intractable to the ground truth and the ever-changing anthropogenic surface of Earth. The ultimate goal of computer vision model development for automated analysis and broad area search and discovery is to augment and assist humans, specifically human–machine teaming for real-world tasks. In this research, various models have been trained using object classes from benchmark datasets such as UC Merced, PatternNet, RESISC-45, and MDSv2. We detail techniques to scan broad swaths of the Earth with deep convolutional neural networks. We present algorithms for localizing object detection results, as well as a methodology for the evaluation of the results of broad-area scans. Our research explores the challenges of transitioning these models out of the training–validation laboratory setting and into the real-world application domain. We show a scalable approach to leverage state-of-the-art deep convolutional neural networks for the search, detection, and annotation of objects within large swaths of imagery, with the ultimate goal of providing a methodology for evaluating object detection machine learning models in real-world scenarios. [ABSTRACT FROM AUTHOR]

Due to the precautions put in place during the COVID-19 pandemic, utilization of telemedicine has increased quickly for patient care and clinical trials. Unfortunately, teleconsultation is closer to a video conference than a medical consultation, with the current solutions setting the patient and doctor into an evaluation that relies entirely on a two-dimensional view of each other. We are developing a patented telehealth platform that assists with diagnostic testing of ocular manifestations of myasthenia gravis. We present a hybrid algorithm combining deep learning with computer vision to give quantitative metrics of ptosis and ocular muscle fatigue leading to eyelid droop and diplopia. The method works both on a fixed image and frame by frame of the video in real-time, allowing capture of dynamic muscular weakness during the examination. We then use signal processing and filtering to derive robust metrics of ptosis and l ocular misalignment. In our construction, we have prioritized the robustness of the method versus accuracy obtained in controlled conditions in order to provide a method that can operate in standard telehealth conditions. The approach is general and can be applied to many disorders of ocular motility and ptosis. [ABSTRACT FROM AUTHOR]

Human pose estimation is an important Computer Vision problem, whose goal is to estimate the human body through joints. Currently, methods that employ deep learning techniques excel in the task of 2D human pose estimation. However, the use of 3D poses can bring more accurate and robust results. Since 3D pose labels can only be acquired in restricted scenarios, fully convolutional methods tend to perform poorly on the task. One strategy to solve this problem is to use 2D pose estimators, to estimate 3D poses in two steps using 2D pose inputs. Due to database acquisition constraints, the performance improvement of this strategy can only be observed in controlled environments, therefore domain adaptation techniques can be used to increase the generalization capability of the system by inserting information from synthetic domains. In this work, we propose a novel method called Domain Unified approach, aimed at solving pose misalignment problems on a cross-dataset scenario, through a combination of three modules on top of the pose estimator: pose converter, uncertainty estimator, and domain classifier. Our method led to a 44.1mm (29.24%) error reduction, when training with the SURREAL synthetic dataset and evaluating with Human3.6M over a no-adaption scenario, achieving state-of-the-art performance. [ABSTRACT FROM AUTHOR]

Edge detection is a crucial step in many computer vision tasks, and in recent years, models based on deep convolutional neural networks (CNNs) have achieved human-level performance in edge detection. However, we have observed that CNN-based methods rely on pre-trained backbone networks and generate edge images with unwanted background details. We propose four new fusion difference convolution (FDC) structures that integrate traditional gradient operators into modern CNNs. At the same time, we have also added a channel spatial attention module (CSAM) and an up-sampling module (US). These structures allow the model to better recognize the semantic and edge information in the images. Our model is trained from scratch on the BIPED dataset without any pre-trained weights and achieves promising results. Moreover, it generalizes well to other datasets without fine-tuning. [ABSTRACT FROM AUTHOR]

One of the primary causes of fires at construction sites is welding sparks. Fire detection systems utilizing computer vision technology offer a unique opportunity to monitor fires in construction sites. However, little effort has been made to date in regard to real-time tracking of small sparks that can lead to major fires at construction sites. In this study, a novel method is proposed to detect welding sparks in real-time contour detection with deep learning parameter tuning. An automatic parameter tuning algorithm employing a convolutional neural network was developed to identify the optimum hue saturation value. Additional filtering methods regarding the non-welding zone and a contour area-based filter were also newly developed to enhance the accuracy of welding spark prediction. The method was evaluated using 230 welding spark images and 104 videos. The results obtained from the welding images indicate that the suggested model for detecting welding sparks achieves a precision of 74.45% and a recall of 63.50% when noise images, such as flashing and reflection light, were removed from the dataset. Furthermore, our findings demonstrate that the proposed model is effective in capturing the number of welding sparks in the video dataset, with a 95.2% accuracy in detecting the moment when the number of welding sparks reaches its peak. These results highlight the potential of automated welding spark detection to enhance fire surveillance at construction sites. [ABSTRACT FROM AUTHOR]

A continuing trend in precision apiculture is to use computer vision methods to quantify characteristics of bee traffic in managed colonies at the hive's entrance. Since traffic at the hive's entrance is a contributing factor to the hive's productivity and health, we assessed the potential of three open-source convolutional network models, YOLOv3, YOLOv4-tiny, and YOLOv7-tiny, to quantify omnidirectional traffic in videos from on-hive video loggers on regular, unmodified one- and two-super Langstroth hives and compared their accuracies, energy efficacies, and operational energy footprints. We trained and tested the models with a 70/30 split on a dataset of 23,173 flying bees manually labeled in 5819 images from 10 randomly selected videos and manually evaluated the trained models on 3600 images from 120 randomly selected videos from different apiaries, years, and queen races. We designed a new energy efficacy metric as a ratio of performance units per energy unit required to make a model operational in a continuous hive monitoring data pipeline. In terms of accuracy, YOLOv3 was first, YOLOv7-tiny—second, and YOLOv4-tiny—third. All models underestimated the true amount of traffic due to false negatives. YOLOv3 was the only model with no false positives, but had the lowest energy efficacy and highest operational energy footprint in a deployed hive monitoring data pipeline. YOLOv7-tiny had the highest energy efficacy and the lowest operational energy footprint in the same pipeline. Consequently, YOLOv7-tiny is a model worth considering for training on larger bee datasets if a primary objective is the discovery of non-invasive computer vision models of traffic quantification with higher energy efficacies and lower operational energy footprints. [ABSTRACT FROM AUTHOR]

Corals play a crucial role as the primary habitat-building organisms within reef ecosystems, forming expansive structures that extend over vast distances, akin to the way tall buildings define a city's skyline. However, coral reefs are vulnerable to damage and destruction due to their inherent fragility and exposure to various threats, including the impacts of climate change. Similar to successful city management, the utilization of advanced underwater videography, photogrammetric computer vision, and machine learning can facilitate precise 3D modeling and the semantic mapping of coral reefs, aiding in their careful management and conservation to ensure their survival. This study focuses on generating detailed 3D mesh models, digital surface models, and orthomosaics of coral habitats by utilizing underwater coral images and control points. Furthermore, an innovative multi-modal deep neural network is designed to perform the pixel-wise semantic segmentation of orthomosaics, enabling the projection of resulting semantic maps onto a 3D space. Notably, this study achieves a significant milestone by accomplishing semantic fine-grained 3D modeling and rugosity evaluation of coral reefs with millimeter-level accuracy, providing a potent means to understand coral reef variations under climate change with high spatial and temporal resolution. [ABSTRACT FROM AUTHOR]

Machine learning (ML) and especially deep learning (DL) with neural networks have demonstrated an amazing success in all sorts of AI problems, from computer vision to game playing, from natural language processing to speech and image recognition. In many ways, the approach of ML toward solving a class of problems is fundamentally different than the one followed in classical engineering, or with ontologies. While the latter rely on detailed domain knowledge and almost exhaustive search by means of static inference rules, ML adopts the view of collecting large datasets and processes this massive information through a generic learning algorithm that builds up tentative solutions. Combining the capabilities of ontology-based recommendation and ML-based techniques in a hybrid system is thus a natural and promising method to enhance semantic knowledge with statistical models. This merge could alleviate the burden of creating large, narrowly focused ontologies for complicated domains, by using probabilistic or generative models to enhance the predictions without attempting to provide a semantic support for them. In this paper, we present a novel hybrid recommendation system that blends a single architecture of classical knowledge-driven recommendations arising from a tailored ontology with recommendations generated by a data-driven approach, specifically with classifiers and a neural collaborative filtering. We show that bringing together these knowledge-driven and data-driven worlds provides some measurable improvement, enabling the transfer of semantic information to ML and, in the opposite direction, statistical knowledge to the ontology. Moreover, the novel proposed system enables the extraction of the reasoning recommendation results after updating the standard ontology with the new products and user behaviors, thus capturing the dynamic behavior of the environment of our interest. [ABSTRACT FROM AUTHOR]

A real-time Bangla Sign Language interpreter can enable more than 200 k hearing and speech-impaired people to the mainstream workforce in Bangladesh. Bangla Sign Language (BdSL) recognition and detection is a challenging topic in computer vision and deep learning research because sign language recognition accuracy may vary on the skin tone, hand orientation, and background. This research has used deep machine learning models for accurate and reliable BdSL Alphabets and Numerals using two well-suited and robust datasets. The dataset prepared in this study comprises of the largest image database for BdSL Alphabets and Numerals in order to reduce inter-class similarity while dealing with diverse image data, which comprises various backgrounds and skin tones. The papers compared classification with and without background images to determine the best working model for BdSL Alphabets and Numerals interpretation. The CNN model trained with the images that had a background was found to be more effective than without background. The hand detection portion in the segmentation approach must be more accurate in the hand detection process to boost the overall accuracy in the sign recognition. It was found that ResNet18 performed best with 99.99% accuracy, precision, F1 score, sensitivity, and 100% specificity, which outperforms the works in the literature for BdSL Alphabets and Numerals recognition. This dataset is made publicly available for researchers to support and encourage further research on Bangla Sign Language Interpretation so that the hearing and speech-impaired individuals can benefit from this research. [ABSTRACT FROM AUTHOR]

For facing of the problems caused by the YOLOv4 algorithm's insensitivity to small objects and low detection precision in traffic light detection and recognition, the Improved YOLOv4 algorithm is investigated in the paper using the shallow feature enhancement mechanism and the bounding box uncertainty prediction mechanism. The shallow feature enhancement mechanism is used to extract features from the network and improve the network's ability to locate small objects and color resolution by merging two shallow features at different stages with the high-level semantic features obtained after two rounds of upsampling. Uncertainty is introduced in the bounding box prediction mechanism to improve the reliability of the prediction of the bounding box by modeling the output coordinates of the prediction bounding box and adding the Gaussian model to calculate the uncertainty of the coordinate information. The LISA traffic light data set is used to perform detection and recognition experiments separately. The Improved YOLOv4 algorithm is shown to have a high effectiveness in enhancing the detection and recognition precision of traffic lights. In the detection experiment, the area under the PR curve value of the Improved YOLOv4 algorithm is found to be 97.58%, which represents an increase of 7.09% in comparison to the 90.49% score gained in the Vision for Intelligent Vehicles and Applications Challenge Competition. In the recognition experiment, the mean average precision of the Improved YOLOv4 algorithm is 82.15%, which is 2.86% higher than that of the original YOLOv4 algorithm. The Improved YOLOv4 algorithm shows remarkable advantages as a robust and practical method for use in the real-time detection and recognition of traffic signal lights. [ABSTRACT FROM AUTHOR]

This paper focuses on improving the performance of scientific instrumentation that uses glass spray chambers for sample introduction, such as spectrometers, which are widely used in analytical chemistry, by detecting incidents using deep convolutional models. The performance of these instruments can be affected by the quality of the introduction of the sample into the spray chamber. Among the indicators of poor quality sample introduction are two primary incidents: The formation of liquid beads on the surface of the spray chamber, and flooding at the bottom of the spray chamber. Detecting such events autonomously as they occur can assist with improving the overall operational accuracy and efficacy of the chemical analysis, and avoid severe incidents such as malfunction and instrument damage. In contrast to objects commonly seen in the real world, beading and flooding detection are more challenging since they are of significantly small size and transparent. Furthermore, the non-rigid property increases the difficulty of the detection of these incidents, as such that existing deep-learning-based object detection frameworks are prone to fail for this task. There is no former work that uses computer vision to detect these incidents in the chemistry industry. In this work, we propose two frameworks for the detection task of these two incidents, which not only leverage the modern deep learning architectures but also integrate with expert knowledge of the problems. Specifically, the proposed networks first localize the regions of interest where the incidents are most likely generated and then refine these incident outputs. The use of data augmentation and synthesis, and choice of negative sampling in training, allows for a large increase in accuracy while remaining a real-time system for inference. In the data collected from our laboratory, our method surpasses widely used object detection baselines and can correctly detect 95% of the beads and 98% of the flooding. At the same time, out method can process four frames per second and is able to be implemented in real time. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNN) have proven to be efficient in computer vision and data classification with an increasing number of successful applications. Time series classification (TSC) has been one of the challenging problems in data mining in the last decade, and significant research has been proposed with various solutions, including algorithm-based approaches as well as machine and deep learning approaches. This paper focuses on combining the two well-known deep learning techniques, namely the Inception module and the Fully Convolutional Network. The proposed method proved to be more efficient than the previous state-of-the-art InceptionTime method. We tested our model on the univariate TSC benchmark (the UCR/UEA archive), which includes 85 time-series datasets, and proved that our network outperforms the InceptionTime in terms of the training time and overall accuracy on the UCR archive. [ABSTRACT FROM AUTHOR]

The existing classification methods for Panax notoginseng taproots suffer from low accuracy, low efficiency, and poor stability. In this study, a classification model based on image feature fusion is established for Panax notoginseng taproots. The images of Panax notoginseng taproots collected in the experiment are preprocessed by Gaussian filtering, binarization, and morphological methods. Then, a total of 40 features are extracted, including size and shape features, HSV and RGB color features, and texture features. Through BP neural network, extreme learning machine (ELM), and support vector machine (SVM) models, the importance of color, texture, and fusion features for the classification of the main roots of Panax notoginseng is verified. Among the three models, the SVM model performs the best, achieving an accuracy of 92.037% on the prediction set. Next, iterative retaining information variables (IRIVs), variable iterative space shrinkage approach (VISSA), and stepwise regression analysis (SRA) are used to reduce the dimension of all the features. Finally, a traditional machine learning SVM model based on feature selection and a deep learning model based on semantic segmentation are established. With the model size of only 125 kb and the training time of 3.4 s, the IRIV-SVM model achieves an accuracy of 95.370% on the test set, so IRIV-SVM is selected as the main root classification model for Panax notoginseng. After being optimized by the gray wolf optimizer, the IRIV-GWO-SVM model achieves the highest classification accuracy of 98.704% on the test set. The study results of this paper provide a basis for developing online classification methods of Panax notoginseng with different grades in actual production. [ABSTRACT FROM AUTHOR]

Submarines are considered extremely strategic for any naval army due to their stealth capability. Periscopes are crucial sensors for these vessels, and emerging to the surface or periscope depth is required to identify visual contacts through this device. This maneuver has many procedures and usually has to be fast and agile to avoid exposure. This paper presents and implements a novel architecture for real submarine periscopes developed for future Brazilian naval fleet operations. Our system consists of a probe that is connected to the craft and carries a 360 camera. We project and take the images inside the vessel using traditional VR/XR devices. We also propose and implement an efficient computer vision-based MR technique to estimate and display detected vessels effectively and precisely. The vessel detection model is trained using synthetic images. So, we built and made available a dataset composed of 99,000 images. Finally, we also estimate distances of the classified elements, showing all the information in an AR-based interface. Although the probe is wired-connected, it allows for the vessel to stand in deep positions, reducing its exposure and introducing a new way for submarine maneuvers and operations. We validate our proposal through a user experience experiment using 19 experts in periscope operations. [ABSTRACT FROM AUTHOR]

Underwater video surveys play a significant role in marine benthic research. Usually, surveys are filmed in transects, which are stitched into 2D mosaic maps for further analysis. Due to the massive amount of video data and time-consuming analysis, the need for automatic image segmentation and quantitative evaluation arises. This paper investigates such techniques on annotated mosaic maps containing hundreds of instances of brittle stars. By harnessing a deep convolutional neural network with pre-trained weights and post-processing results with a common blob detection technique, we investigate the effectiveness and potential of such segment-and-count approach by assessing the segmentation and counting success. Discs could be recommended instead of full shape masks for brittle stars due to faster annotation among marker variants tested. Underwater image enhancement techniques could not improve segmentation results noticeably, but some might be useful for augmentation purposes. [ABSTRACT FROM AUTHOR]

Pedestrian trajectory prediction is one of the main concerns of computer vision problems in the automotive industry, especially in the field of advanced driver assistance systems. The ability to anticipate the next movements of pedestrians on the street is a key task in many areas, e.g., self-driving auto vehicles, mobile robots or advanced surveillance systems, and they still represent a technological challenge. The performance of state-of-the-art pedestrian trajectory prediction methods currently benefits from the advancements in sensors and associated signal processing technologies. The current paper reviews the most recent deep learning-based solutions for the problem of pedestrian trajectory prediction along with employed sensors and afferent processing methodologies, and it performs an overview of the available datasets, performance metrics used in the evaluation process, and practical applications. Finally, the current work exposes the research gaps from the literature and outlines potential new research directions. [ABSTRACT FROM AUTHOR]

Video-based person re-identification is an important task with the challenges of lighting variation, low-resolution images, background clutter, occlusion, and human appearance similarity in the multi-camera visual sensor networks. In this paper, we propose a video-based person re-identification method called the end-to-end learning architecture with hybrid deep appearance-temporal feature. It can learn the appearance features of pivotal frames, the temporal features, and the independent distance metric of different features. This architecture consists of two-stream deep feature structure and two Siamese networks. For the first-stream structure, we propose the Two-branch Appearance Feature (TAF) sub-structure to obtain the appearance information of persons, and used one of the two Siamese networks to learn the similarity of appearance features of a pairwise person. To utilize the temporal information, we designed the second-stream structure that consisting of the Optical flow Temporal Feature (OTF) sub-structure and another Siamese network, to learn the person's temporal features and the distances of pairwise features. In addition, we select the pivotal frames of video as inputs to the Inception-V3 network on the Two-branch Appearance Feature sub-structure, and employ the salience-learning fusion layer to fuse the learned global and local appearance features. Extensive experimental results on the PRID2011, iLIDS-VID, and Motion Analysis and Re-identification Set (MARS) datasets showed that the respective proposed architectures reached 79%, 59% and 72% at Rank-1 and had advantages over state-of-the-art algorithms. Meanwhile, it also improved the feature representation ability of persons. [ABSTRACT FROM AUTHOR]

This paper's core objective is to develop and validate a new neurocomputing model to classify document images in particularly demanding hard conditions such as image distortions, image size variance and scale, a huge number of classes, etc. Document classification is a special machine vision task in which document images are categorized according to their likelihood. Document classification is by itself an important topic for the digital office and it has several usages. Additionally, different methods for solving this problem have been presented in various studies; their respectively reached performance is however not yet good enough. This task is very tough and challenging. Thus, a novel, more accurate and precise model is needed. Although the related works do reach acceptable accuracy values for less hard conditions, they generally fully fail in the face of those above-mentioned hard, real-world conditions, including, amongst others, distortions such as noise, blur, low contrast, and shadows. In this paper, a novel deep CNN model is developed, validated and benchmarked with a selection of the most relevant recent document classification models. Additionally, the model's sensitivity was significantly improved by injecting different artifacts during the training process. In the benchmarking, it does clearly outperform all others by at least 4%, thus reaching more than 96% accuracy. [ABSTRACT FROM AUTHOR]

Video analytics and computer vision applications face challenges when using video sequences with low visibility. The visibility of a video sequence is degraded when the sequence is affected by atmospheric interference like rain. Many approaches have been proposed to remove rain streaks from video sequences. Some approaches are based on physical features, and some are based on data-driven (i.e., deep-learning) models. Although the physical features-based approaches have better rain interpretability, the challenges are extracting the appropriate features and fusing them for meaningful rain removal, as the rain streaks and moving objects have dynamic physical characteristics and are difficult to distinguish. Additionally, the outcome of the data-driven models mostly depends on variations relating to the training dataset. It is difficult to include datasets with all possible variations in model training. This paper addresses both issues and proposes a novel hybrid technique where we extract novel physical features and data-driven features and then combine them to create an effective rain-streak removal strategy. The performance of the proposed algorithm has been tested in comparison to several relevant and contemporary methods using benchmark datasets. The experimental result shows that the proposed method outperforms the other methods in terms of subjective, objective, and object detection comparisons for both synthetic and real rain scenarios by removing rain streaks and retaining the moving objects more effectively. [ABSTRACT FROM AUTHOR]

In turning, the wear control of a cutting tool benefits product quality enhancement, tool-related costs' optimisation, and assists in avoiding undesired events. In small series and individual production, the machine operator is the one who determines when to change a cutting tool, based upon their experience. Bad decisions can often lead to greater costs, production downtime, and scrap. In this paper, a Tool Condition Monitoring (TCM) system is presented that automatically classifies tool wear of turning tools into four classes (no, low, medium, high wear). A cutting tool was monitored with infrared (IR) camera immediately after the cut and in the following 60 s. The Convolutional Neural Network Inception V3 was used to analyse and classify the thermographic images, which were divided into different groups depending on the time of acquisition. Based on classification result, one gets information about the cutting capability of the tool for further machining. The proposed model, combining Infrared Thermography, Computer Vision, and Deep Learning, proved to be a suitable method with results of more than 96% accuracy. The most appropriate time of image acquisition is 6–12 s after the cut is finished. While existing temperature based TCM systems focus on measuring a cutting tool absolute temperature, the proposed system analyses a temperature distribution (relative temperatures) on the whole image based on image features. [ABSTRACT FROM AUTHOR]

The automatic detection of the thread roll's margin is one of the kernel problems in the textile field. As the traditional detection method based on the thread's tension has the disadvantages of high cost and low reliability, this paper proposes a technology that installs a camera on a mobile robot and uses computer vision to detect the thread roll's margin. Before starting, we define a thread roll's margin as follows: The difference between the thread roll's radius and the bobbin's radius. Firstly, we capture images of the thread roll's end surface. Secondly, we obtain the bobbin's image coordinates by calculating the image's convolutions with a Circle Gradient Operator. Thirdly, we fit the thread roll and bobbin's contours into ellipses, and then delete false detections according to the bobbin's image coordinates. Finally, we restore every sub-image of the thread roll by a perspective transformation method, and establish the conversion relationship between the actual size and pixel size. The difference value of the two concentric circles' radii is the thread roll's margin. However, there are false detections and these errors may be more than 19.4 mm when the margin is small. In order to improve the precision and delete false detections, we use deep learning to detect thread roll and bobbin's radii and then can calculate the thread roll's margin. After that, we fuse the two results. However, the deep learning method also has some false detections. As such, in order to eliminate the false detections completely, we estimate the thread roll's margin according to thread consumption speed. Lastly, we use a Kalman Filter to fuse the measured value and estimated value; the average error is less than 5.7 mm. [ABSTRACT FROM AUTHOR]

With the rapid development of deep learning, computer vision has assisted in solving a variety of problems in engineering construction. However, very few computer vision-based approaches have been proposed on work productivity's evaluation. Therefore, taking a super high-rise project as a research case, using the detected object information obtained by a deep learning algorithm, a computer vision-based method for evaluating the productivity of assembling reinforcement is proposed. Firstly, a detector that can accurately distinguish various entities related to assembling reinforcement based on CenterNet is established. DLA34 is selected as the backbone. The mAP reaches 0.9682, and the speed of detecting a single image can be as low as 0.076 s. Secondly, the trained detector is used to detect the video frames, and images with detected boxes and documents with coordinates can be obtained. The position relationship between the detected work objects and detected workers is used to determine how many workers (N) have participated in the task. The time (T) to perform the process can be obtained from the change of coordinates of the work object. Finally, the productivity is evaluated according to N and T. The authors use four actual construction videos for validation, and the results show that the productivity evaluation is generally consistent with the actual conditions. The contribution of this research to construction management is twofold: On the one hand, without affecting the normal behavior of workers, a connection between construction individuals and work object is established, and the work productivity evaluation is realized. On the other hand, the proposed method has a positive effect on improving the efficiency of construction management. [ABSTRACT FROM AUTHOR]

The paper describes the process of designing a simple fiducial marker. The marker is meant for use in augmented reality applications. Unlike other systems, it does not encode any information, but it can be used for obtaining the position, rotation, relative size, and projective transformation. Also, the system works well with motion blur and is resistant to the marker's imperfections, which could theoretically be drawn only by hand. Previous systems put constraints on colors that need to be used to form the marker. The proposed system works with any saturated color, leading to better blending with the surrounding environment. The marker's final shape is a rectangular area of a solid color with three lines of a different color going from the center to three corners of the rectangle. Precise detection can be achieved using neural networks, given that the training set is very varied and well designed. A detailed literature review was performed, and no such system was found. Therefore, the proposed design is novel for localization in the spatial scene. The testing proved that the system works well both indoor and outdoor, and the detections are precise. [ABSTRACT FROM AUTHOR]

Human action recognition has attracted considerable research attention in the field of computer vision, especially for classroom environments. However, most relevant studies have focused on one specific behavior of students. Therefore, this paper proposes a student behavior recognition system based on skeleton pose estimation and person detection. First, consecutive frames captured with a classroom camera were used as the input images of the proposed system. Then, skeleton data were collected using the OpenPose framework. An error correction scheme was proposed based on the pose estimation and person detection techniques to decrease incorrect connections in the skeleton data. The preprocessed skeleton data were subsequently used to eliminate several joints that had a weak effect on behavior classification. Second, feature extraction was performed to generate feature vectors that represent human postures. The adopted features included normalized joint locations, joint distances, and bone angles. Finally, behavior classification was conducted to recognize student behaviors. A deep neural network was constructed to classify actions, and the proposed system was able to identify the number of students in a classroom. Moreover, a system prototype was implemented to verify the feasibility of the proposed system. The experimental results indicated that the proposed scheme outperformed the skeleton-based scheme in complex situations. The proposed system had a 15.15% higher average precision and 12.15% higher average recall than the skeleton-based scheme did. [ABSTRACT FROM AUTHOR]

Automated pavement distress recognition is a key step in smart infrastructure assessment. Advances in deep learning and computer vision have improved the automated recognition of pavement distresses in road surface images. This task remains challenging due to the high variation of defects in shapes and sizes, demanding a better incorporation of contextual information into deep networks. In this paper, we show that an attention-based multi-scale convolutional neural network (A+MCNN) improves the automated classification of common distress and non-distress objects in pavement images by (i) encoding contextual information through multi-scale input tiles and (ii) employing a mid-fusion approach with an attention module for heterogeneous image contexts from different input scales. A+MCNN is trained and tested with four distress classes (crack, crack seal, patch, pothole), five non-distress classes (joint, marker, manhole cover, curbing, shoulder), and two pavement classes (asphalt, concrete). A+MCNN is compared with four deep classifiers that are widely used in transportation applications and a generic CNN classifier (as the control model). The results show that A+MCNN consistently outperforms the baselines by 1∼26% on average in terms of the F-score. A comprehensive discussion is also presented regarding how these classifiers perform differently on different road objects, which has been rarely addressed in the existing literature. [ABSTRACT FROM AUTHOR]

Ensuring the quality of color contact lenses is vital, particularly in detecting defects during their production since they are directly worn on the eyes. One significant defect is the "center deviation (CD) defect", where the colored area (CA) deviates from the center point. Measuring the extent of deviation of the CA from the center point is necessary to detect these CD defects. In this study, we propose a method that utilizes image processing and analysis techniques for detecting such defects. Our approach involves employing semantic segmentation to simplify the image and reduce noise interference and utilizing the Hough circle transform algorithm to measure the deviation of the center point of the CA in color contact lenses. Experimental results demonstrated that our proposed method achieved a 71.2% reduction in error compared with existing research methods. [ABSTRACT FROM AUTHOR]

Improving soybean (Glycine max L. (Merr.)) yield is crucial for strengthening national food security. Predicting soybean yield is essential to maximize the potential of crop varieties. Non-destructive methods are needed to estimate yield before crop maturity. Various approaches, including the pod-count method, have been used to predict soybean yield, but they often face issues with the crop background color. To address this challenge, we explored the application of a depth camera to real-time filtering of RGB images, aiming to enhance the performance of the pod-counting classification model. Additionally, this study aimed to compare object detection models (YOLOV7 and YOLOv7-E6E) and select the most suitable deep learning (DL) model for counting soybean pods. After identifying the best architecture, we conducted a comparative analysis of the model's performance by training the DL model with and without background removal from images. Results demonstrated that removing the background using a depth camera improved YOLOv7's pod detection performance by 10.2% precision, 16.4% recall, 13.8% mAP@50, and 17.7% mAP@0.5:0.95 score compared to when the background was present. Using a depth camera and the YOLOv7 algorithm for pod detection and counting yielded a mAP@0.5 of 93.4% and mAP@0.5:0.95 of 83.9%. These results indicated a significant improvement in the DL model's performance when the background was segmented, and a reasonably larger dataset was used to train YOLOv7. [ABSTRACT FROM AUTHOR]

Pellet fuels are nowadays commonly used as a heat source for food preparation. Unfortunately, they may contain intrusions which might be harmful for humans and the environment. The intrusions can be identified precisely using immersed microscopy analysis. The aim of this study is to investigate the possibility of autonomous identification of selected classes of intrusions using relatively simple deep learning models. The semantic segmentation was chosen as a method for impurity identification in the microscopic image. Three architectures of deep networks based on UNet architecture were examined. The networks contained the same depth as UNet but with a successively limited number of filters. The input image influence on the segmentation results was also examined. The efficiency of the network was assessed using the intersection over union index. The results showed an easily observable impact of the filter used on segmentation efficiency. The influence of the input image resolution is not so clear, and even the lowest (256 × 256 pixels) resolution used gave satisfactory results. The biggest (but still smaller than originally proposed UNet) network yielded segmentation quality good enough for practical applications. The simpler one was also applicable, although the quality of the segmentation decreased considerably. The simplest network gave poor results and is not suitable in applications. The two proposed networks can be used as a support for domain experts in practical applications. [ABSTRACT FROM AUTHOR]

Drowsy driving can significantly affect driving performance and overall road safety. Statistically, the main causes are decreased alertness and attention of the drivers. The combination of deep learning and computer-vision algorithm applications has been proven to be one of the most effective approaches for the detection of drowsiness. Robust and accurate drowsiness detection systems can be developed by leveraging deep learning to learn complex coordinate patterns using visual data. Deep learning algorithms have emerged as powerful techniques for drowsiness detection because of their ability to learn automatically from given inputs and feature extractions from raw data. Eye-blinking-based drowsiness detection was applied in this study, which utilized the analysis of eye-blink patterns. In this study, we used custom data for model training and experimental results were obtained for different candidates. The blinking of the eye and mouth region coordinates were obtained by applying landmarks. The rate of eye-blinking and changes in the shape of the mouth were analyzed using computer-vision techniques by measuring eye landmarks with real-time fluctuation representations. An experimental analysis was performed in real time and the results proved the existence of a correlation between yawning and closed eyes, classified as drowsy. The overall performance of the drowsiness detection model was 95.8% accuracy for drowsy-eye detection, 97% for open-eye detection, 0.84% for yawning detection, 0.98% for right-sided falling, and 100% for left-sided falling. Furthermore, the proposed method allowed a real-time eye rate analysis, where the threshold served as a separator of the eye into two classes, the "Open" and "Closed" states. [ABSTRACT FROM AUTHOR]

The development of an accurate and efficient method for detecting missing bolts in engineering structures is crucial. To this end, a missing bolt detection method that leveraged machine vision and deep learning was developed. First, a comprehensive dataset of bolt images captured under natural conditions was constructed, which improved the generality and recognition accuracy of the trained bolt target detection model. Second, three deep learning network models, namely, YOLOv4, YOLOv5s, and YOLOXs, were compared, and YOLOv5s was selected as the bolt target detection model. With YOLOv5s as the target recognition model, the bolt head and bolt nut had average precisions of 0.93 and 0.903, respectively. Third, a missing bolt detection method based on perspective transformation and IoU was presented and validated under laboratory conditions. Finally, the proposed method was applied to an actual footbridge structure to test its feasibility and effectiveness in real engineering scenarios. The experimental results showed that the proposed method could accurately identify bolt targets with a confidence level of over 80% and detect missing bolts under different image distances, perspective angles, light intensities, and image resolutions. Moreover, the experimental results on a footbridge demonstrated that the proposed method could reliably detect the missing bolt even at a shooting distance of 1 m. The proposed method provided a low-cost, efficient, and automated technical solution for the safety management of bolted connection components in engineering structures. [ABSTRACT FROM AUTHOR]

Allocentric semantic 3D maps are highly useful for a variety of human–machine interaction related tasks since egocentric viewpoints can be derived by the machine for the human partner. Class labels and map interpretations, however, may differ or could be missing for the participants due to the different perspectives. Particularly, when considering the viewpoint of a small robot, which significantly differs from the viewpoint of a human. In order to overcome this issue, and to establish common ground, we extend an existing real-time 3D semantic reconstruction pipeline with semantic matching across human and robot viewpoints. We use deep recognition networks, which usually perform well from higher (i.e., human) viewpoints but are inferior from lower viewpoints, such as that of a small robot. We propose several approaches for acquiring semantic labels for images taken from unusual perspectives. We start with a partial 3D semantic reconstruction from the human perspective that we transfer and adapt to the small robot's perspective using superpixel segmentation and the geometry of the surroundings. The quality of the reconstruction is evaluated in the Habitat simulator and a real environment using a robot car with an RGBD camera. We show that the proposed approach provides high-quality semantic segmentation from the robot's perspective, with accuracy comparable to the original one. In addition, we exploit the gained information and improve the recognition performance of the deep network for the lower viewpoints and show that the small robot alone is capable of generating high-quality semantic maps for the human partner. The computations are close to real-time, so the approach enables interactive applications. [ABSTRACT FROM AUTHOR]

In the realm of computer vision, semantic segmentation is the task of recognizing objects in images at the pixel level. This is done by performing a classification of each pixel. The task is complex and requires sophisticated skills and knowledge about the context to identify objects' boundaries. The importance of semantic segmentation in many domains is undisputed. In medical diagnostics, it simplifies the early detection of pathologies, thus mitigating the possible consequences. In this work, we provide a review of the literature on deep ensemble learning models for polyp segmentation and develop new ensembles based on convolutional neural networks and transformers. The development of an effective ensemble entails ensuring diversity between its components. To this end, we combined different models (HarDNet-MSEG, Polyp-PVT, and HSNet) trained with different data augmentation techniques, optimization methods, and learning rates, which we experimentally demonstrate to be useful to form a better ensemble. Most importantly, we introduce a new method to obtain the segmentation mask by averaging intermediate masks after the sigmoid layer. In our extensive experimental evaluation, the average performance of the proposed ensembles over five prominent datasets beat any other solution that we know of. Furthermore, the ensembles also performed better than the state-of-the-art on two of the five datasets, when individually considered, without having been specifically trained for them. [ABSTRACT FROM AUTHOR]

Hundreds of people are injured or killed in road accidents. These accidents are caused by several intrinsic and extrinsic factors, including the attentiveness of the driver towards the road and its associated features. These features include approaching vehicles, pedestrians, and static fixtures, such as road lanes and traffic signs. If a driver is made aware of these features in a timely manner, a huge chunk of these accidents can be avoided. This study proposes a computer vision-based solution for detecting and recognizing traffic types and signs to help drivers pave the door for self-driving cars. A real-world roadside dataset was collected under varying lighting and road conditions, and individual frames were annotated. Two deep learning models, YOLOv7 and Faster RCNN, were trained on this custom-collected dataset to detect the aforementioned road features. The models produced mean Average Precision (mAP) scores of 87.20% and 75.64%, respectively, along with class accuracies of over 98.80%; all of these were state-of-the-art. The proposed model provides an excellent benchmark to build on to help improve traffic situations and enable future technological advances, such as Advance Driver Assistance System (ADAS) and self-driving cars. [ABSTRACT FROM AUTHOR]