Pedestrian Detection Algorithm Research Articles

A lightweight algorithm for pedestrian detection in overhead images

A lightweight algorithm for pedestrian detection in overhead images

Research on Pedestrian Detection Algorithm in Industrial Scene Based on Improved YOLOv7‐Tiny

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. Published by Wiley Periodicals LLC.

Research on pedestrian object detection algorithm in urban road scenes based on improved YOLOv5

Pedestrians have random distribution and dynamic characteristics. Aiming to this problem, this paper proposes a pedestrian object detection method based on improved YOLOv5 in urban road scenes. Firstly, the last C3 module was replaced in the Backbone with the SE attention mechanism to enhance the network’s extraction of pedestrian object features and improve the detection accuracy of small-scale pedestrians. Secondly, the EIOU loss function was introduced to optimize the object detection performance of the detection network. To validate the effectiveness of the algorithm, experiments were conducted on a dataset composed of filtered Caltech pedestrian detection data and images taken by ourselves. The experiments showed that the improved algorithm has P-value, R-value, and mAP of 98.4%, 95.5%, and 98%, respectively. Compared to the YOLOv5 model, it has increased P-value by 1.4%, R-value by 2.7%, and mAP by 1.3%. The improved algorithm also boosts the detection speed. The detection speed is 0.8 ms faster than the YOLOv5 model. It is also faster than other mainstream algorithms including Faster R-CNN and SSD. The improved algorithm enhances the effectiveness of pedestrian detection significantly and has important application value.

Exploring visual techniques for indoor intrusion detection using detectron2 and Faster RCNN

As societal evolution marches forward, there's an escalating emphasis on indoor security concerns. Within the safety realm, indoor intrusion detection emerges as a pivotal challenge, given its direct implications on safeguarding human lives and assets. Leveraging visual methods for indoor intrusion detection holds promising potential, particularly due to its straightforward deployment advantages. This study zeroes in on surveillance video footage, a prevalent medium in the security domain, as its experimental muse. Post an initial preprocessing phase utilizing a video difference map, the research introduces a pedestrian detection algorithm hinged on the synergy of detectron2 and Faster R-CNN. Insights gleaned reveal that this combined algorithm, when augmented with the video difference map preprocessing, exhibits commendable accuracy, robustness, and real-time efficacy on surveillance footage, especially in scenarios bereft of significant target occlusion. Moreover, this algorithm showcases an adeptness at discerning diminutively sized targets, demonstrating resilience against varying light magnitudes and maintaining impeccable accuracy amidst intricate lighting conditions. By harnessing this methodology, the enhancement of indoor environment safety monitoring becomes feasible, thereby bolstering the provision of dependable protection for individuals.

YOLOv8-CB: Dense Pedestrian Detection Algorithm Based on In-Vehicle Camera

Recently, the field of vehicle-mounted visual intelligence technology has witnessed a surge of interest in pedestrian detection. Existing algorithms for dense pedestrian detection at intersections face challenges such as high computational weight, complex models that are difficult to deploy, and suboptimal detection accuracy for small targets and highly occluded pedestrians. To address these issues, this paper proposes an improved lightweight multi-scale pedestrian detection algorithm, YOLOv8-CB. The algorithm introduces a lightweight cascade fusion network, CFNet (cascade fusion network), and a CBAM attention module to improve the characterization of multi-scale feature semantics and location information, and it superimposes a bidirectional weighted feature fusion path BIFPN structure to fuse more effective features and improve pedestrian detection performance. It is experimentally verified that compared with the YOLOv8n algorithm, the accuracy of the improved model is increased by 2.4%, the number of model parameters is reduced by 6.45%, and the computational load is reduced by 6.74%. The inference time for a single image is 10.8 ms. The cascade fusion algorithm YOLOv8-CB has higher detection accuracy and is a lighter model for multi-scale pedestrian detection in complex scenes such as streets or intersections. This proposed algorithm presents a valuable approach for device-side pedestrian detection with limited computational resources.

Pedestrian Target Recognition Algorithm in Public Places Based on Representation Learning and Similarity Learning

To ensure public safety, the government has placed a lot of cameras in public places and used them to monitor key targets. In target detection, pedestrian target detection is undoubtedly a research hotspot. How to realize the high efficiency of pedestrian detection is the focus of this field. As a result, this research suggests an algorithm for pedestrian target detection in public spaces that is based on representation learning and similarity learning. The algorithm uses representation learning to extract pedestrian features and Singular Value Decomposition (SVD) to build a more trustworthy Feature Extraction Network (FEN). In addition, the improved Softmax function is used for similarity learning, and the K-Nearest Neighbor algorithm (KNN is applied for image retrieval to fgreatly increase the identification accuracy of pedestrians. The algorithm proposed in this study only needs two rounds of constraint training to achieve the best state. The mean absolute error and mean square error are 0.31 and 9.38, respectively. Its Relative Robustness (RR), Relative Generalization (RG) and Relative Scalability (RS) are excellent. In the final practical test, the model finally achieved 98.8% accuracy and 2.1% false positive rate. The proposed algorithm in this study has good application value in pedestrian target detection, and can better promote the development of social public safety

Low-light pedestrian detection and tracking algorithm based on autoencoder structure and improved Bytetrack

Low-light pedestrian detection and tracking algorithm based on autoencoder structure and improved Bytetrack

Research on a vehicle and pedestrian detection algorithm based on improved attention and feature fusion

<abstract> <p>With the widespread integration of deep learning in intelligent transportation and various industrial sectors, target detection technology is gradually becoming one of the key research areas. Accurately detecting road vehicles and pedestrians is of great significance for the development of autonomous driving technology. Road object detection faces problems such as complex backgrounds, significant scale changes, and occlusion. To accurately identify traffic targets in complex environments, this paper proposes a road target detection algorithm based on the enhanced YOLOv5s. This algorithm introduces the weighted enhanced polarization self attention (WEPSA) self-attention mechanism, which uses spatial attention and channel attention to strengthen the important features extracted by the feature extraction network and suppress insignificant background information. In the neck network, we designed a weighted feature fusion network (CBiFPN) to enhance neck feature representation and enrich semantic information. This strategic feature fusion not only boosts the algorithm's adaptability to intricate scenes, but also contributes to its robust performance. Then, the bounding box regression loss function uses EIoU to accelerate model convergence and reduce losses. Finally, a large number of experiments have shown that the improved YOLOv5s algorithm achieves mAP@0.5 scores of 92.8% and 53.5% on the open-source datasets KITTI and Cityscapes. On the self-built dataset, the mAP@0.5 reaches 88.7%, which is 1.7%, 3.8%, and 3.3% higher than YOLOv5s, respectively, ensuring real-time performance while improving detection accuracy. In addition, compared to the latest YOLOv7 and YOLOv8, the improved YOLOv5 shows good overall performance on the open-source datasets.</p> </abstract>

Pedestrian detection algorithm integrating large kernel attention and YOLOV5 lightweight model.

In the context of intelligent driving, pedestrian detection faces challenges related to low accuracy in target recognition and positioning. To address this issue, a pedestrian detection algorithm is proposed that integrates a large kernel attention mechanism with the YOLOV5 lightweight model. The algorithm aims to enhance long-term attention and dependence during image processing by fusing the large kernel attention module with the C3 module. Furthermore, it addresses the lack of long-distance relationship information in channel and spatial feature extraction and representation by introducing the Coordinate Attention mechanism. This mechanism effectively extracts local information and focused location details, thereby improving detection accuracy. To improve the positioning accuracy of obscured targets, the alpha CIOU bounding box regression loss function is employed. It helps mitigate the impact of occlusions and enhances the algorithm's ability to precisely localize pedestrians. To evaluate the effectiveness of trained model, experiments are conducted on the BDD100K pedestrian dataset as well as the Pascal VOC dataset. Experimental results demonstrate that the improved attention fusion YOLOV5 lightweight model achieves an average accuracy of 60.3%. Specifically, the detection accuracy improves by 1.1% compared to the original YOLOV5 algorithm, and the accuracy performance index reaches 73.0%. These findings strongly indicate the proposed algorithm in significantly enhancing the accuracy of pedestrian detection in road scenes.

Hold surrounding’s key-you only look once version 7: a real-time pedestrian and vehicle detection algorithm in the low-signal-to-noise ratio infrared image

Hold surrounding’s key-you only look once version 7: a real-time pedestrian and vehicle detection algorithm in the low-signal-to-noise ratio infrared image

Research on lightweight pedestrian detection based on improved YOLOv5

Aiming at the problems of low detection accuracy and the large size of the pedestrian detection algorithm, to improve the edge intelligent recognition capability of the terminal, this paper proposes a lightweight pedestrian detection scheme based on the improved YOLOv5. In this paper, the algorithm first takes the original YOLOv5 as the basic framework and uses the Ghost Bottleneck module to replace the C3 module in the original YOLOv5 network to reduce the number of parameters, eliminate redundant features, and obtain a more lightweight model. Then the attention mechanism CBAM module is added to improve the feature extraction capability and detection accuracy of the algorithm. After experimental verification, the improved lightweight YOLOv5 algorithm significantly reduces the model size and computational cost while guaranteeing accuracy, which is suitable for deployment in edge devices.

Review of pedestrian detection technology based on deep learning

Pedestrian detection is one of the main research problems in the field of computer vision. With the development of deep learning technology, pedestrian detection algorithms have made great progress and breakthroughs. Currently, pedestrian detection technology using deep learning has become mainstream. The first type of algorithm is called two-stage detection algorithms, which are based on Region of Interest (ROI) and single-stage detection algorithms adopt an end-to-end training method. So this paper conducts extensive research on the basis of classification and comparison, studies the characteristics and development of the above two detection algorithms, respectively, and finally puts forward suggestions for their future development, such as the fusion of image background and target state.

Qualification of the PAVIN Fog and Rain Platform and Its Digital Twin for the Evaluation of a Pedestrian Detector in Fog.

Vehicles featuring partially automated driving can now be certified within a guaranteed operational design domain. The verification in all kinds of scenarios, including fog, cannot be carried out in real conditions (risks or low occurrence). Simulation tools for adverse weather conditions (e.g., physical, numerical) must be implemented and validated. The aim of this study is, therefore, to verify what criteria need to be met to obtain sufficient data to test AI-based pedestrian detection algorithms. It presents both analyses on real and numerically simulated data. A novel method for the test environment evaluation, based on a reference detection algorithm, was set up. The following parameters are taken into account in this study: weather conditions, pedestrian variety, the distance of pedestrians to the camera, fog uncertainty, the number of frames, and artificial fog vs. numerically simulated fog. Across all examined elements, the disparity between results derived from real and simulated data is less than 10%. The results obtained provide a basis for validating and improving standards dedicated to the testing and approval of autonomous vehicles.

Towards Sustainable Cities: Utilizing Computer Vision and AI for Efficient Public Lighting and Energy Management

This study showcases the optimization of public lighting systems using computer vision with an emphasis on the YOLO algorithm for pedestrian detection, aiming to reduce energy expenses. In a time when the demand for electricity is escalating due to factors like taxes and urban expansion, it is imperative to explore strategies to cut costs. One pivotal area is public lighting management. Presently, governments are transitioning from sodium vapor lighting to LED lamps, which already contributes to decreasing consumption. In this scenario, computer vision systems, particularly using YOLO, have the potential to further reduce consumption by adjusting the power of LED lamps based on pedestrian traffic. Additionally, this paper employs fuzzy logic to calculate lamp power based on detected pedestrians and ambient lighting, ensuring compliance with the NBR 5101:2018 standard. Tests with public surveillance camera images and simulations validated the proposal. Upon implementing this project in practice, a 45% reduction in public lighting consumption was observed compared to conventional LED lighting.

An Improved Lightweight Dense Pedestrian Detection Algorithm

Due to the limited memory and computing resources in the real application of target detection, the method is challenging to implement on mobile and embedded devices. In order to achieve the balance between detection accuracy and speed in pedestrian-intensive scenes, an improved lightweight dense pedestrian detection algorithm GS-YOLOv5 (GhostNet GSConv- SIoU) is proposed in this paper. In the Backbone section, GhostNet is used to replace the original CSPDarknet53 network structure, reducing the number of parameters and computation. The CBL module is replaced with GSConv in the Head section, and the CSP module is replaced with VoV-GSCSP. The SloU loss function is used to replace the original IoU loss function to improve the prediction box overlap problem in dense scenes. The model parameters are reduced by 40% and the calculation amount is reduced by 64% without losing the average accuracy, and the detection accuracy is improved by 0.5%. The experimental results show that the GS-YOLOv5 can detect pedestrians more effectively under limited hardware conditions to cope with dense pedestrian scenes, and it is suitable for the online real-time detection of pedestrians.

Replacing the human driver: An objective benchmark for occluded pedestrian detection

Early detection of vulnerable road users is a crucial requirement for autonomous vehicles to meet and exceed the object detection capabilities of human drivers. One of the most complex outstanding challenges is that of partial occlusion where a target object is only partially available to the sensor due to obstruction by another foreground object. A number of leading pedestrian detection benchmarks provide annotation for partial occlusion, however each benchmark varies greatly in their definition of the occurrence and severity of occlusion. Research demonstrates that a high degree of subjectivity is used to classify occlusion level in these cases and occlusion is typically categorized into 2–3 broad categories such as “partially” and “heavily” occluded. In addition, many pedestrian instances are impacted by multiple inhibiting factors which contribute to non-detection such as object scale, distance from camera, lighting variations and adverse weather. This can lead to inaccurate or inconsistent reporting of detection performance for partially occluded pedestrians depending on which benchmark is used. This research introduces a novel, objective benchmark for partially occluded pedestrian detection to facilitate the objective characterization of pedestrian detection models. Characterization is carried out on seven popular pedestrian detection models for a range of occlusion levels from 0%–99% to demonstrate the impact of progressive levels of partial occlusion on pedestrian detectability. Results show that the proposed benchmark provides more objective, fine grained analysis of pedestrian detection algorithms than the current state of the art.

Multi-Attribute NMS: An Enhanced Non-Maximum Suppression Algorithm for Pedestrian Detection in Crowded Scenes

Removing duplicate proposals is a critical process in pedestrian detection, and is usually performed via Non-Maximum Suppression (NMS); however, in crowded scenes, the detection proposals of occluded pedestrians are hard to distinguish from duplicate proposals, making the detection results inaccurate. In order to address the above-mentioned problem, the authors of this paper propose a Multi-Attribute NMS (MA-NMS) algorithm, which combines density and count attributes in order to adaptively adjust suppression, effectively preserving the proposals of occluded pedestrians while removing duplicate proposals. In order to obtain the density and count attributes, an attribute branch (ATTB), which uses a context extraction module (CEM) to extract the context of pedestrians, and then, concatenates the context with the features of pedestrians in order to predict both the density and count attributes simultaneously, is also proposed. With the proposed ATTB, a pedestrian detector, based on MA-NMS, is constructed for pedestrian detection in crowded scenes. Extensive experiments are conducted using the CrowdHuman and CityPersons datasets, and the results show that the proposed method outperforms mainstream methods on AP (average precision), Recall, and MR−2 (log-average miss rate), sufficiently validating the effectiveness of the proposed MA-NMS algorithm.

Pedestrian Flows Characterization and Estimation with Computer Vision Techniques

This work describes a straightforward implementation of detecting and tracking pedestrian walking across a public square using computer vision. The methodology consists of the use of the well-known YOLOv3 algorithm over videos recorded during different days of the week. The chosen location was the Piazza Duca d’Aosta in the city of Milan, Italy, in front of the main Centrale railway station, an access point for the subway. Several analyses have been carried out to investigate macroscopic parameters of pedestrian dynamics such as densities, speeds, and main directions followed by pedestrians, as well as testing strengths and weaknesses of computer-vision algorithms for pedestrian detection. The developed system was able to represent spatial densities and speeds of pedestrians along temporal profiles. Considering the whole observation period, the mean value of the Voronoi density was about 0.035 person/m2 with a standard deviation of about 0.014 person/m2. On the other hand, two main speed clusters were identified during morning/evening hours. The largest number of pedestrians with an average speed of about 0.77 m/s was observed along the exit direction of the subway entrances during both morning and evening hours. The second relevant group of pedestrians was observed walking in the opposite direction with an average speed of about 0.65 m/s. The analyses generated initial insights into the future development of a decision-support system to help with the management and control of pedestrian dynamics.

Research on Human Behavior Feature Recognition and Intelligent Early Warning Methods in Safety Supervision Scene Video based on Yolov7

With the continuous improvement of infrastructure construction in China, the construction of various supporting power facilities is constantly followed up. A large number of ultra-high voltage or high-voltage power facilities, such as high-voltage transmission towers, transformers, or substations, are gradually emerging in populated areas, farmland, or fishponds where people still pass by sometimes. In such circumstances, people who do not have the qualification to contact power facilities at times approach, contact, or even climb these dangerous high-voltage transmission and distribution facilities illegally for various reasons, which not only poses a huge hidden peril or even threat to the safety of people’s lives and property but also cause a huge negative impact on the smooth operation of power infrastructure. To solve this intractable problem, this topic proposes a pedestrian detection and recognition algorithm, which can accurately distinguish between ordinary pedestrians and power grid maintenance inspectors based on YOLOv7, providing a reliable method for timely detection and early warning of pedestrians who may contact power facilities.

Research on Intelligent Disinfection-Vehicle System Design and Its Global Path Planning

We aimed to research the design and path-planning methods of an intelligent disinfection-vehicle system. A ROS (robot operating system) system was utilized as the control platform, and SLAM (simultaneous localization and mapping) technology was used to establish an indoor scene map. On this basis, a new path-planning method combining the A* algorithm and the Floyd algorithm is proposed to ensure the safety, efficiency, and stability of the path. Simulation results show that with the average shortest distance between obstacles and paths of 0.463, this algorithm reduces the average numbers of redundant nodes and turns in the path by 70.43% and 31.1%, respectively, compared to the traditional A* algorithm. The algorithm has superior performance in terms of safety distance, path length, and redundant nodes and turns. Additionally, a mask recognition and pedestrian detection algorithm is utilized to ensure public safety. The results of the study indicate that the method has satisfactory performance. The intelligent disinfection-vehicle system operates stably, meets the indoor mapping requirements, and can recognize pedestrians and masks.