Search

Pedestrian detection is a critical task in computer vision; however, mainstream algorithms often struggle to achieve high detection accuracy in complex scenarios, particularly due to target occlusion and the presence of small objects. This paper introduces a novel pedestrian detection algorithm, YOLO-ESL, based on the YOLOv7 framework. YOLO-ESL integrates the ELAN-SA module, designed to enhance feature extraction, with the LGA module, which improves feature fusion. The ELAN-SA module optimizes the flexibility and efficiency of small object feature extraction, while the LGA module effectively integrates multi-scale features through local and global attention mechanisms. Additionally, the CIOUNMS algorithm addresses the issue of target loss in cases of high overlap, improving boundary box filtering. Evaluated on the VOC2012 pedestrian dataset, YOLO-ESL achieved an accuracy of 93.7%, surpassing the baseline model by 3.0%. Compared to existing methods, this model not only demonstrates strong performance in handling occluded and small object detection but also remarkable robustness and efficiency. [ABSTRACT FROM AUTHOR]

The advancements in deep learning have significantly enhanced the accuracy and robustness of pedestrian detection. However, recent studies reveal that adversarial attacks can exploit the vulnerabilities of deep learning models to mislead detection systems. These attacks are effective not only in digital environments but also pose significant threats to the reliability of pedestrian detection systems in the physical world. Existing adversarial attacks targeting pedestrian detection primarily focus on daytime scenarios and are easily noticeable by road observers. In this paper, we propose a novel adversarial attack method against vehicle–pedestrian detection systems at night. Our approach utilizes reflective optical materials that can effectively reflect light back to its source. We optimize the placement of these reflective patches using the particle swarm optimization (PSO) algorithm and deploy patches that blend with the color of pedestrian clothing in real-world scenarios. These patches remain inconspicuous during the day or under low-light conditions, but at night, the reflected light from vehicle headlights effectively disrupts the vehicle's pedestrian detection systems. Considering that real-world detection models are often black-box systems, we propose a "symmetry" strategy, which involves using the behavior of an alternative model to simulate the response of the target model to adversarial patches. We generate adversarial examples using YOLOv5 and apply our attack to various types of pedestrian detection models. Experiments demonstrate that our approach is both effective and broadly applicable. [ABSTRACT FROM AUTHOR]

Occlusion presents a major obstacle in the development of pedestrian detection technologies utilizing computer vision. This challenge includes both inter-class occlusion caused by environmental objects obscuring pedestrians, and intra-class occlusion resulting from interactions between pedestrians. In complex and variable urban settings, these compounded occlusion patterns critically limit the efficacy of both one-stage and two-stage pedestrian detectors, leading to suboptimal detection performance. To address this, we introduce a novel architecture termed the Attention-Guided Feature Enhancement Network (AGFEN), designed within the deep convolutional neural network framework. AGFEN improves the semantic information of high-level features by mapping it onto low-level feature details through sampling, creating an effect comparable to mask modulation. This technique enhances both channel-level and spatial-level features concurrently without incurring additional annotation costs. Furthermore, we transition from a traditional one-to-one correspondence between proposals and predictions to a one-to-multiple paradigm, facilitating non-maximum suppression using the prediction set as the fundamental unit. Additionally, we integrate these methodologies by aggregating local features between regions of interest (RoI) through the reuse of classification weights, effectively mitigating false positives. Our experimental evaluations on three widely used datasets demonstrate that AGFEN achieves a 2.38% improvement over the baseline detector on the CrowdHuman dataset, underscoring its effectiveness and potential for advancing pedestrian detection technologies. [ABSTRACT FROM AUTHOR]

The incidence of right-turning pedestrian accidents is increasing in South Korea. Most of the accidents occur when a large vehicle is turning right, and the main cause of the accidents was found to be the driver's limited field of vision. After these accidents, the government implemented a series of institutional measures with the objective of preventing such accidents. However, despite the institutional arrangements in place, pedestrian accidents continue to occur. We focused on the many limitations that autonomous vehicles, like humans, can face in such situations. To address this issue, we propose a right-turn pedestrian collision avoidance system by installing a LiDAR sensor in the center of the intersection to facilitate pedestrian detection. Furthermore, the urban road environment is considered, as this provides the optimal conditions for the model to perform at its best. During this research, we collected data on right-turn accidents using the CARLA simulator and ROS interface and demonstrated the effectiveness of our approach in preventing such incidents. Our results suggest that the implementation of this method can effectively reduce the incidence of right-turn accidents in autonomous vehicles. [ABSTRACT FROM AUTHOR]

Owing to the low detection accuracy of camera-based object detection models, various fusion techniques with Light Detection and Ranging (LiDAR) have been attempted. This has resulted in improved detection of objects that are difficult to detect due to partial occlusion by obstacles or unclear silhouettes. However, the detection performance remains limited in low-light environments where small pedestrians are located far from the sensor or pedestrians have difficult-to-estimate shapes. This study proposes an object detection model that employs a Gaussian–Sobel filter. This filter combines Gaussian blurring, which suppresses the effects of noise, and a Sobel mask, which accentuates object features, to effectively utilize depth maps generated by LiDAR for object detection. The model performs independent pedestrian detection using the real-time object detection model You Only Look Once v4, based on RGB images obtained using a camera and depth maps preprocessed by the Gaussian–Sobel filter, and estimates the optimal pedestrian location using non-maximum suppression. This enables accurate pedestrian detection while maintaining a high detection accuracy even in low-light or external-noise environments, where object features and contours are not well defined. The test evaluation results demonstrated that the proposed method achieved at least 1–7% higher average precision than the state-of-the-art models under various environments. [ABSTRACT FROM AUTHOR]

Pedestrian detection has recently attracted widespread attention as a challenging problem in computer vision. The accuracy of pedestrian detection is affected by differences in gestures, background clutter, local occlusion, differences in scales, pixel blur, and other factors occurring in real scenes. These problems lead to false and missed detections. In view of these visual description deficiencies, we leveraged pedestrian pose information as a supplementary resource to address the occlusion challenges that arise in pedestrian detection. An attention mechanism was integrated into the visual information as a supplement to the pose information, because the acquisition of pose information was limited by the pose estimation algorithm. We developed a pedestrian detection method that integrated an attention mechanism with visual and pose information, including pedestrian region generation and pedestrian recognition networks, effectively addressing occlusion and false detection issues. The pedestrian region proposal network was used to generate a series of candidate regions with possible pedestrian targets from the original image. Then, the pedestrian recognition network was used to judge whether each candidate region contained pedestrian targets. The pedestrian recognition network was composed of four parts: visual features, pedestrian poses, pedestrian attention, and classification modules. The visual feature module was responsible for extracting the visual feature descriptions of candidate regions. The pedestrian pose module was used to extract pose feature descriptions. The pedestrian attention module was used to extract attention information, and the classification module was responsible for fusing visual features and pedestrian pose descriptions with the attention mechanism. The experimental results on the Caltech and CityPersons datasets demonstrated that the proposed method could substantially more accurately identify pedestrians than current state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Connected cooperative and automated (CAM) vehicles and self-driving cars need to achieve robust and accurate environment understanding. With this aim, they are usually equipped with sensors and adopt multiple sensing strategies, also fused among them to exploit their complementary properties. In recent years, artificial intelligence such as machine learning- and deep learning-based approaches have been applied for object and pedestrian detection and prediction reliability quantification. This paper proposes a procedure based on the YOLOv8 (You Only Look Once) method to discover objects on the roads such as cars, traffic lights, pedestrians and street signs in foggy weather conditions. In particular, YOLOv8 is a recent release of YOLO, a popular neural network model used for object detection and image classification. The obtained model is applied to a dataset including about 4000 foggy road images and the object detection accuracy is improved by changing hyperparameters such as epochs, batch size and augmentation methods. To achieve good accuracy and few errors in detecting objects in the images, the hyperparameters are optimized by four different methods, and different metrics are considered, namely accuracy factor, precision, recall, precision–recall and loss. [ABSTRACT FROM AUTHOR]

Aiming at the YOLOv4 model's difficulty in dealing with occluded pedestrians in real scenarios, this paper made improvements in ensuring the real-time performance of the YOLOv4 model and applied the YOLOv4 model to pedestrian detection. In order to improve the model's ability to detect occluded pedestrians, the model adopted the K-means ++ clustering algorithm to re-design the priori frames applicable to the pedestrian target sizes, and introduced the exclusion loss function term to maximise the distance between the candidate frames and the neighbouring real frames of non-mate-hing targets, and minimise the overlap ratio between the candidate frames and the real frames of other targets. The improved model was experimented on the challenging datasets CrowdHuman and Caltech, and the experimental results verified the effectiveness of it. Finally the model has been applied to video pedestrian detection in real scenarios, which also verified the effectiveness of the improvements in this paper. [ABSTRACT FROM AUTHOR]

In order to achieve the protection of personal privacy, the author proposes research on sports data privacy protection and information security management. The author used the two-dimensional fractional Fourier transform (2D-FRFT) method to encrypt the detected human body parts, which can be decrypted when needed for viewing. Compared to traditional Fourier transform, Fractional Fourier Transform (FRFT) can better express the time-frequency characteristics of signals and is very sensitive to the order of the transform. It is widely used in image encryption systems. 2D-FRFT increases the range of keys, further enhancing the security of the system. The author achieved encryption by extracting the detected human body parts and then performing a certain order of FRFT in the x and y directions respectively; When decrypting, use the same order of encryption to perform inverse fractional Fourier transform. Finally, based on research on pedestrian detection and encryption technology, the author designed a human-machine interaction interface that integrates the functions of detection and encryption interfaces, making the entire operation more intuitive and concise. [ABSTRACT FROM AUTHOR]

Although pedestrian detection techniques are improving, this task is still challenging due to the problems of target occlusion, small targets, and complex pedestrian backgrounds in images of different scenes. As a result, the You Only Look Once algorithm exhibits lower detection accuracy. In this paper, a multisensor (MS) module that utilizes multiple dilated convolutions is proposed to sample feature images, avoiding information loss caused by repeated sampling, to improve the feature extraction and target detection performance of the algorithm. In addition, a lightweight shuffle-based efficient channel attention mechanism is introduced to conduct grouping in the channel dimension and perform parallel processing for each subfeature map channel. A new branch is introduced to enrich the channel feature information for multiscale feature representation. Finally, a distance intersection over union-based nonmaximum suppression (DIoU-NMS) method is introduced to minimize the occurrence of missed targets due to occlusion by taking the prediction box and ground truth box centroid locations information into account without increasing the computational cost over that of normal NMS. Our method is extensively evaluated on several challenging pedestrian detection datasets, achieving 87.73%, 34.7%, 93.96% and 95.23% mean average precision values on PASCAL VOC, MS COCO, Caltech Pedestrian and INRIA Person, which are respectively. The experimental results demonstrate the effectiveness of the method. [ABSTRACT FROM AUTHOR]

The increasing availability of ubiquitous sensor data on the built environment holds great potential for a new generation of travel and mobility research. Bluetooth technology, for example, is already vastly used in vehicular transportation management solutions and services. Current studies discuss the potential of this emerging technology for pedestrian mobility research, but it has yet to be examined in a large urban setting. One of the main problems is detecting pedestrians from Bluetooth records since their behavior and movement patterns share similarities with other urban transportation modes. This study aims to accurately detect pedestrians using a network of 65 Bluetooth detectors located in Tel-Aviv, Israel, which record on average over 60,000 unique daily Bluetooth Media-Access-Control addresses. We propose a detection methodology that includes system calibration, effective travel time calculation, and classification by velocity that takes into consideration the probability of vehicular traffic jams. An evaluation of the proposed methodology presents a promising pedestrian detection accuracy rate of 89%. We showcase the results of pedestrian traffic analysis, together with a discussion on the data analysis challenges and limitations. To the best of our knowledge, this work is the first to analyze pedestrian records detection from a Bluetooth network employed in a dynamic urban environment setting.

With the rapid promotion of autonomous driving technology, it is extremely important to scientifically anticipate the related technologies and analyze their possible impact on urban road systems. The accuracy of detection and localization of traffic elements of autonomous driving is closely related to the ability of autonomous driving devices to make control decisions and the safety of autonomous driving. The study designs a new high-speed road driving scheme based on autonomous driving by analyzing the challenges related to urban traffic that may be brought about by unmanned driving. On the basis of the faster R-CNN algorithm, the context information around the target is introduced to locate and detect small-scale traffic signs. A new pedestrian detection model is designed, which is based on the feature pyramid network and introduces the SE module to highlight the features of the visible part of the pedestrian and reduce the missed detection rate caused by inter-class occlusion. The improved traffic sign detection framework improves the detection accuracy by 18.91% compared to the original faster R-CNN, while the enhanced pedestrian inspection method improves the detection accuracy by 14.00%. For both traffic sign detection and pedestrian detection accuracy and speed are improved compared to the original method. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

To eliminate the defects of incomplete detection and high false detection rate caused by insignificant pedestrian target features, dense small targets and complex background in infrared images, this paper proposes an infrared pedestrian target detection algorithm based on improved YOLOv7. Firstly, the original Spatial Pyramid Pooling (SPP) module is replaced by the Channel Attention based Spatial Pyramid Pooling (CASPP) module based on the YOLOv7-tiny model, so that the model could pay more attention to the extraction of pedestrian features; then, the convolution module CBM based on the Meta-ACON activation function is introduced, which further suppressed the background noise and preserved the details of the pedestrians; finally, an alpha fusion data enhancement method is proposed to enrich the diversity of samples and improve the stability of the model in complex environments. The validation based on the FLIR dataset shows that the proposed method improves the accuracy by 3% and reduces the computation by 38% compared with the YOLOv7-tiny algorithm, which is more suitable for infrared pedestrian target detection scenarios. [ABSTRACT FROM AUTHOR]

In response to the complex and diverse nature of the road traffic environment, where vehicle and pedestrian detection is prone to false and missed detections, this paper proposes a vehicle and pedestrian target detection algorithm YOLOv8-RC based on multi-scale feature fusion. Initially, the RCS-OSA module is introduced within the structure of the base network YOLOv8 to replace the original module, thereby enhancing and integrating the extracted feature information. Additionally, a lightweight Context-Aware Adaptive Feature Reorganization (CARAFE) is employed to replace the original upsampling operator, enhancing the network s capability for global multi-scale information fusion. Subsequently, a detection dataset consisting of 6 000 images of vehicle and pedestrian targets is constructed through public datasets and network collection. The algorithm s detection performance is quantitatively evaluated using accuracy, recall rate, mean Average Precision at a 50% intersection over union threshold (mAP50), and mAP50-95. Compared to YOLOv8-N, YOLOv8-RC demonstrates an improvement of 1.7 percentage in accuracy, 1.2 percentage in recall rate, 0.9 percentage in mAP50, and 0.5 percentage in mAP50-95, thus validating the algorithm's effectiveness. [ABSTRACT FROM AUTHOR]

In response to the problems of complex model networks, low detection accuracy, and the detection of small targets prone to false detections and omissions in pedestrian detection, this paper proposes FedsNet, a pedestrian detection network based on RT-DETR. By constructing a new lightweight backbone network, ResFastNet, the number of parameters and computation of the model are reduced to accelerate the detection speed of pedestrian detection. Integrating the Efficient Multi-scale Attention(EMA) mechanism with the backbone network creates a new ResBlock module for improved detection of small targets. The more effective DySample has been adopted as the upsampling operator to improve the accuracy and robustness of pedestrian detection. SIoU is used as the loss function to improve the accuracy of pedestrian recognition and speed up model convergence. Experimental evaluations conducted on a self-built pedestrian detection dataset demonstrate that the average accuracy value of the FedsNet model is 91 % , which is a 1.7 % improvement over the RT-DETR model. The parameters and model volume are reduced by 15.1 % and 14.5 % , respectively. When tested on the public dataset WiderPerson, FedsNet achieved the average accuracy value of 71.3 % , an improvement of 1.1 % over the original model. In addition, the detection speed of the FedsNet network reaches 109.5 FPS and 100.3 FPS, respectively, meeting the real-time requirements of pedestrian detection. [ABSTRACT FROM AUTHOR]

In crowded pedestrian detection, occlusion situations are common challenges that seriously impact detection performance. These occlusions are usually classified into pedestrian-to-pedestrian occlusions and object-to-pedestrian occlusions which result in false detection and missed detection. In this paper, we propose a novel model to address the crowded pedestrian detections in the cases of occlusions, which can generate an optimal bounding box containing the pedestrian instance with accurate position information. Firstly, Distance-Intersection over Union loss is introduced in Region Proposal Networks module for network training to generate proposal boxes, considering both the position and area of the region where the pedestrian is occluded. Secondly, a refinement module is added in Region Convolutional Neural Network to eliminate false positive proposal boxes, Earth Mover's Distance Loss is used to re-predict the pedestrian in these boxes. Finally, Relocation Non-Maximum Suppression is employed to select the optimal bounding box. Considering the parts of the pedestrian contained by its adjacent proposal boxes, the optimal bounding box is located in order to achieve the complete pedestrian instance. The proposed model is evaluated on CrowdHuman and CityPersons datasets respectively. On CrowdHuman dataset, the proposed model improves AP by 5.6% and JI by 5.2%, while reducing MR−2 by 3.8% compared to the baseline. Compared to the state-of-the-art model, the proposed model reduces 0.4% on MR−2, which shows its effectiveness for pedestrian detection in crowded scenes. On CityPersons dataset, the proposed model obtains the AP with 96.8% among all the evaluated models, which indicates its generalization for pedestrian detections in various crowded scenes. [ABSTRACT FROM AUTHOR]

In large public places such as railway stations and airports, dense pedestrian detection is important for safety and security. Deep learning methods provide relatively effective solutions but still face problems such as feature extraction difficulties, image multi-scale variations, and high leakage detection rates, which bring great challenges to the research in this field. In this paper, we propose an improved dense pedestrian detection algorithm GR-yolo based on Yolov8. GR-yolo introduces the repc3 module to optimize the backbone network, which enhances the ability of feature extraction, adopts the aggregation–distribution mechanism to reconstruct the yolov8 neck structure, fuses multi-level information, achieves a more efficient exchange of information, and enhances the detection ability of the model. Meanwhile, the Giou loss calculation is used to help GR-yolo converge better, improve the detection accuracy of the target position, and reduce missed detection. Experiments show that GR-yolo has improved detection performance over yolov8, with a 3.1% improvement in detection means accuracy on the wider people dataset, 7.2% on the crowd human dataset, and 11.7% on the people detection images dataset. Therefore, the proposed GR-yolo algorithm is suitable for dense, multi-scale, and scene-variable pedestrian detection, and the improvement also provides a new idea to solve dense pedestrian detection in real scenes. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Zhengzhou University (Natural Science Edition) is the property of Journal of Zhengzhou University (Natural Science Edition) Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

To provide drivers with real-time and accurate pedestrian information and reduce traffic accidents, the detection of enhanced YOLOv3-tiny (DOEYT) pedestrian detection algorithm was proposed. The robust feature extraction network was established, and the asymmetric max-pooling was used for down sampling to prevent the loss of lateral pedestrian features due to the increased receptive field. Hardswish was employed as activation function for the convolutional layers to optimize network performance, and the global context (GC) self-attention mechanism was used to capture holistic feature information. In the classification and regression network, the three-scale detection strategy was adopted to improve the accuracy of small-scale pedestrian target detection. The k-means++ algorithm was used to regenerate dataset anchor boxes for enhancing network convergence speed. The pedestrian detection dataset was constructed and divided into training and testing sets to evaluate DOEYT performance. The results show that by the asymmetric max-pooling, Hardswish function and GC self-attention mechanism, AP values are increased by 14.4%, 7.9% and 10.8%, respectively. On the testing set, DOEYT achieves average precision of 91.2% and detection speed of 103 frames per second, which demonstrates that the proposed algorithm can quickly and accurately detect pedestrians for reducing the risk of traffic accidents. [ABSTRACT FROM AUTHOR]

Aiming at the high false negative rate and low accuracy in crowded scenes, a pedestrian detection network based on multi-scale features and mutual supervision is proposed. To effectively extract pedestrian feature information in complex scenes, a network combining PANet pyramid network and mixed dilated convolutions is used to extract feature information. Then, a mutual supervision detection network for head-body detection is designed, which utilizes the mutual supervision of head bounding boxes and full-body bounding boxes to obtain more accurate pedestrian detection results. The proposed network achieves 13.5% MR-2 performance on CrowdHuman dataset, with an improvement of 3.6% compared to the YOLOv5 network, and a simultaneous improvement of 3.5% in average precision (AP). On CityPersons dataset, it achieves 48.2% MR-2 performance, with 2.3% improvement compared to the YOLOv5 network, and a simultaneous improvement of 2.8% in AP. The results indicate that the proposed network demonstrates good detection performance in densely crowded scenes. [ABSTRACT FROM AUTHOR]

YOLOv7 is one of the most effective algorithms for one‐stage detectors. However, when it is applied to pedestrian detection tasks in the industrial scene, it is still challenging for complex environments and multi‐scale changes of pedestrians. This paper proposes a new pedestrian detector for the industrial scene based on improved YOLOv7‐tiny and named as GP‐YOLO. First, the neck of YOLOv7‐tiny is replaced by RepGFPN structure, make full use of multi‐scale features to enhance the detection accuracy of objects with large‐scale changes. Second, a new gnconv branch is added to the feature fusion module, and the high‐order spatial interaction capability is introduced to further enhance the target detection accuracy. Finally, a lightweight method based on PModule is proposed, on this basis, a PConv bottleneck is designed to reduce the FLOPs and enhance the feature extraction. Experiments on a self‐made Industrial Pedestrian Data set show that before lightweight, the proposed algorithm achieves a 3.2% improvement in mAP@0.5:0.95 and a 3.7% improvement in Recall compared to the baseline YOLOv7‐tiny. After lightweight GP‐YOLO, compared to non‐lightweight, parameters and FLOPs are decreased by 26% and 23%, respectively, the mAP@0.5:0.95 is decreased by only 1.1% and the Recall is decreased by only 1.3%, which remains at a high level. Compared with baseline YOLOv7‐tiny, the lightweight GP‐YOLO has similar parameters and FLOPs, but the mAP@0.5:0.95 is increased by 2.1%, and the Recall is increased by 2.4%. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

Research on autonomous vehicles has been at a peak recently. One of the most researched aspects is the performance degradation of sensors in harsh weather conditions such as rain, snow, fog, and hail. This work addresses this performance degradation by fusing multiple sensor modalities inside the neural network used for detection. The proposed fusion method removes the pre-process fusion stage. It directly produces detection boxes from numerous images. It reduces the computation cost by providing detection and fusion simultaneously. By separating the network during the initial layers, the network can easily be modified for new sensors. Intra-network fusion improves robustness to missing inputs and applies to all compatible types of inputs while reducing the peak computing cost by using a valley-fill algorithm. Our experiments demonstrate that adopting a parallel multimodal network to fuse thermal images in the network improves object detection during difficult weather conditions such as harsh winters by up to 5% mAP while reducing dataset bias during complicated weather conditions. It also happens with around 50% fewer parameters than late-fusion approaches, which duplicate the whole network instead of the first section of the feature extractor. [ABSTRACT FROM AUTHOR]

In this study, we propose YOLOv5s-PGD algorithm for dense pedestrian detection, which can improve the recall and reduce the number of parameters compared with YOLOv5s. First, a minimum scale detection layer has been added to deepen the pyramid's depth and enhance detection accuracy. Second, ghost convolution has been employed to replace standard convolution to increase real-time performance of the algorithm. Finally, depth separable convolution has been used to address issues of high parameters and large computational complexity that lower the efficiency of the algorithm. Experiment results demonstrate that the detection accuracy of the YOLOv5s-PGD algorithm on the CrowdHuman public dataset is up to 85.1%, which is 2.2% higher than that of YOLOv5s. Furthermore, the number of parameters has decreased by 19.7%, and the calculation burden has decreased by 2.5%. Consequently, the proposed YOLOv5s-PGD algorithm better satisfies the requirements of real-time detection, model optimization, and terminal deployment in dense pedestrian scenarios. [ABSTRACT FROM AUTHOR]

Pedestrian detection in densely populated scenes, particularly in the presence of occlusions, remains a challenging issue in computer vision. Existing approaches often address detection leakage by enhancing model architectures or incorporating attention mechanisms; However, small-scale pedestrians have fewer features and are easily overfitted to the dataset and these approaches still face challenges in accurately detecting pedestrians with small target sizes. To tackle this issue, this research rethinks the occlusion region through small-scale pedestrian detection and proposes the You Only Look Once model for efficient pedestrian detection(YOLO-EPD). Firstly, we find that Standard Convolution and Dilated Convolution do not fit well with pedestrian targets with different scales due to a single receptive field, and we propose the Selective Content Aware Downsampling (SCAD) module, which is integrated into the backbone to attain enhanced feature extraction. In addition, to address the issue of missed detections resulting from insufficient feature extraction for small-scale pedestrian detection, we propose the Crowded Multi-Head Attention (CMHA) module, which makes full use of multi-layer information. Finally, for the challenge of optimizing the performance and effectiveness of small-object detection, we design Unified Channel-Task Distillation (UCTD) with channel attention and a Lightweight head (Lhead) using parameter sharing to keep it lightweight. Experimental results validate the superiority of YOLO-EPD, achieving a remarkable 91.1% Average Precision (AP) on the Widerperson dataset, while concurrently reducing parameters and computational overhead by 40%. The experimental findings demonstrate that YOLO-EPD greatly accelerates the convergence of model training and achieves better real-time performance in real-world dense scenarios. [ABSTRACT FROM AUTHOR]

Pedestrian monitoring in crowded areas like train stations has an important impact in the overall operation and management of those public spaces. An organized distribution of the different elements located inside a station will contribute not only to the safety of all passengers but will also allow for a more efficient process of the regular activities including entering/leaving the station, boarding/alighting from trains, and waiting. This improved distribution only comes by obtaining sufficiently accurate information on passengers' positions, and their derivatives like speeds, densities, traffic flow. The work described here addresses this need by using an artificial intelligence approach based on computational vision and convolutional neural networks. From the available videos taken regularly at subways stations, two methods are tested. One is based on tracking each person's bounding box from which filtered 3D kinematics are derived, including position, velocity and density. Another infers the pose and activity that a person has by analyzing its main body key points. Measurements of these quantities would enable a sensible and efficient design of inner spaces in places like railway and subway stations. [ABSTRACT FROM AUTHOR]

In largescale crowded places, abnormal crowd gathering occurs from time to time, which brings certain challenges to the dense pedestrian detection technology involved in application scenarios such as autonomous driving and largescale public place crowd monitoring systems. The new generation of dense pedestrian detection technology requires higher accuracy, smaller computing overhead, faster detection speed and more convenient deployment. In view of the above requirements, a lightweight dense pedestrian detection algorithm MER-YOLO based on YOLOv8 is proposed, which first uses Mobile ViT as the backbone network to improve the overall feature extraction ability of the model in pedestrian gathering areas. The EMA attention mechanism module is introduced to encode the global information, further aggregate pixel level features through dimensional interaction, and strengthen the detection ability of small targets by combining the detection head with 160×160 scale. The use of Repulsion Loss as the bounding box loss function reduces the missed detection and misdetection of small target pedestrians under dense crowds. The experimental results show that compared with YOLOv8n, the mAP@0. 5 of the MERYOLO pedestrian detection algorithm is improved by 4. 5%on the Crowd Human dataset and 2. 1%on the Wider Person dataset, while only 3. 1x106 parameters and 9. 8 GFLOPs, which meet the deployment requirements of low computing power and high precision. [ABSTRACT FROM AUTHOR]

The pedestrian detection technology of automated driving is also facing some challenges. Aiming at the problem of specific target deblurring in the image, this research built a pedestrian detection deblurring model in view of Generative adversarial network and multi-scale convolution. First, it designs an image deblurring algorithm in view of Generative adversarial network. Then, on the basis of image deblurring, a pedestrian deblurring algorithm in view of multi-scale convolution is designed to focus on deblurring the pedestrians in the image. The outcomes showcase that the peak signal to noise ratio and structural similarity index of the image deblurring algorithm in view of the Generative adversarial network are the highest, which are 29.7 dB and 0.943 dB respectively, and the operation time is the shortest, which is 0.50 s. The pedestrian deblurring algorithm in view of multi-scale convolution has the highest peak signal-tonoise ratio (PSNR) and structural similarity indicators in the HIDE test set and GoPro dataset, with 29.4 dB and 0.925 dB, 40.45 dB and 0.992 dB, respectively. The resulting restored image is the clearest and possesses the best visual effect. The enlarged part of the face can reveal more detailed information, and it is the closest to a real clear image. The deblurring effect is not limited to the size of the pedestrians in the image. In summary, the model constructed in this study has good application effects in image deblurring and pedestrian detection, and has a certain promoting effect on the development of autonomous driving technology. [ABSTRACT FROM AUTHOR]

In the field of pedestrian detection in overhead scenes, widely-used deep learning algorithms often underperform due to insufficient pedestrian feature information. To address this issue, we propose an efficient algorithm called Unsupervised Overhead Dark Polar (UODP). This algorithm is specifically designed for scenes with a near 90-degree overhead angle, low pedestrian pixel resolution leading to significant loss of semantic information. It predicts the pedestrian positions by extracting prominent intensity peaks in grayscale image and utilizes polar coordinates to analyze pedestrian bounding boxes based on the top-down view characteristics. Additionally, its prominent advantage lies in unsupervised learning, which allows adaptation to various overhead scenes by adjusting intuitive parameters without training. In terms of performance, UODP has been evaluated on diverse datasets, including our open-source Southeast University overhead pedestrain dataset and several representative public datasets. Compared to cutting-edge deep learning algorithms such as DINO, RTMDet and DAB-DETR, UODP demonstrates higher accuracy and speed with lower computational requirements. The sensitivity analysis of some important parameters further reveals the mechanisms of the algorithm. Therefore, we recommend using UODP for pedestrian detection tasks that align with its design scenarios. [ABSTRACT FROM AUTHOR]

Fisheye camera is an important sensor in on-board systems and surveillance systems. However, the current fisheye image pedestrian detection still exists problems such as large distortions are difficult to detect, sparse datasets, and poor real-time performance. We propose an adversarial pedestrian detection model based on virtual fisheye image training. The fisheye transformation model is proposed to generate virtual image dataset, which provides a complete data base for network training. The DEMO-YOLO network is used to ensure real-time performance while improving accuracy, and the spatial transformation network is introduced to convert the features extracted from the backbone network into hard examples. In the process of training, adversarial learning is used so that the network is able to deal with objects with large deformations. The model is trained on the fisheye-transformed CityPersons and Kitti datasets and tested on the real fisheye dataset Woodscape. The experimental results show that compared with the traditional detection methods, the accuracy of the proposed model is improved by 18.45% and the real-time performance reaches an average of 318 frames/s. Therefore, the model can be applied to fisheye cameras. [ABSTRACT FROM AUTHOR]

In this paper, we present a pedestrian detection and avoidance scheme utilizing multi-sensor data collection and machine learning for intelligent transportation systems (ITSs). The system integrates a video camera, an infrared (IR) camera, and a micro-Doppler radar for data acquisition and training. A deep convolutional neural network (DCNN) is employed to process RGB and IR images. The RGB dataset comprises 1200 images (600 with pedestrians and 600 without), while the IR dataset includes 1000 images (500 with pedestrians and 500 without), 85% of which were captured at night. Two distinct DCNNs were trained using these datasets, achieving a validation accuracy of 99.6% with the RGB camera and 97.3% with the IR camera. The radar sensor determines the pedestrian's range and direction of travel. Experimental evaluations conducted in a vehicle demonstrated that the multi-sensor detection scheme effectively triggers a warning signal to a vibrating motor on the steering wheel and displays a warning message on the passenger's touchscreen computer when a pedestrian is detected in potential danger. This system operates efficiently both during the day and at night. [ABSTRACT FROM AUTHOR]

In the realm of intelligent transportation, pedestrian detection has witnessed significant advancements. However, it continues to grapple with challenging issues, notably the detection of pedestrians in complex lighting scenarios. Conventional visible light mode imaging is profoundly affected by varying lighting conditions. Under optimal daytime lighting, visibility is enhanced, leading to superior pedestrian detection outcomes. Conversely, under low-light conditions, visible light mode imaging falters due to the inadequate provision of pedestrian target information, resulting in a marked decline in detection efficacy. In this context, infrared light mode imaging emerges as a valuable supplement, bolstering pedestrian information provision. This paper delves into pedestrian detection and tracking algorithms within a multi-modal image framework grounded in deep learning methodologies. Leveraging the YOLOv4 algorithm as a foundation, augmented by a channel stack fusion module, a novel multi-modal pedestrian detection algorithm tailored for intelligent transportation is proposed. This algorithm capitalizes on the fusion of visible and infrared light mode image features to enhance pedestrian detection performance amidst complex road environments. Experimental findings demonstrate that compared to the Visible-YOLOv4 algorithm, renowned for its high performance, the proposed Double-YOLOv4-CSE algorithm exhibits a notable improvement, boasting a 5.0% accuracy rate enhancement and a 6.9% reduction in logarithmic average missing rate. This research's goal is to ensure that the algorithm can run smoothly even on a low configuration 1080 Ti GPU and to improve the algorithm's coverage at the application layer, making it affordable and practical for both urban and rural areas. This addresses the broader research problem within the scope of smart cities and remote ends with limited computational power. [ABSTRACT FROM AUTHOR]

Existing research has primarily focused on the accuracy of automated pedestrian detection systems, overlooking the consequential environmental impacts arising from false or missed pedestrian detections. To fill these research gaps, this study investigates the emissions and fuel consumption resulting from incorrect pedestrian detection at signalized intersections in microsimulation. To carry out experiments, the authors employ Vissim microsimulation software and the Comprehensive Modal Emission Model (CMEM). For the first time in the literature, missed and false calls are modeled in microsimulation and their environmental impacts are accurately measured. The research highlights the limitations of current automated pedestrian (video) detection systems (APVDSs) technologies in reducing emissions and fuel consumption effectively. While APVDSs offer potential benefits for traffic management, their inability to accurately detect pedestrians undermines their environmental efficacy. This study emphasizes the importance of considering environmental impacts of APVDSs, and challenges the belief that pedestrian recall treatment is the least eco-friendly. Also, the study showed that coupling APVDS or push-button treatments with pedestrian recycle features increases fuel consumption and CO2 by 10% at the intersections with higher pedestrian demand. By understanding the emissions and fuel consumption associated with incorrect detections, transportation agencies can make more informed decisions regarding the implementation and improvement of APVDS technologies. [ABSTRACT FROM AUTHOR]