Smart City Gnosys

Smart city article details

Title	A Multi-Object Tracking Algorithm Based On Yolov5-Concise Network
ID_Doc	2819
Authors	Cheng B.; Huang Y.; Xie X.; Du J.
Year	2022
Published	Proceedings of SPIE - The International Society for Optical Engineering, 12246
DOI	http://dx.doi.org/10.1117/12.2643719
Abstract	As the basis of pedestrian and traffic statistics, multi-object tracking (MOT) is widely used in smart cities and smart shops. Due to the high cost of cloud analysis, MOT algorithm is mainly deployed on the end-side device. However, limited by computing resources and capital cost, it is difficult to deploy large models in end-side device. As tracking based on detection has become the most effective MOT method, a lightweight detection network model YOLOv5-Concise with only 0.302M parameters is proposed for end-side deployment in this paper. Then, the application of knowledge distillation technology based on outputs and feature relation in object detection is studied. By knowledge distillation, the YOLOv5-Concise model's detection precision mAP0.5 is increased by 7.26%, mAP0.5:0.95 is increased by 16%, and the detection speed remained unchanged. Finally, on the camera equipped with T40 chip, the detection speed of the model is measured to 28 FPS, and the accuracy rate of 98.1% is obtained in the pedestrian statistics test. © 2022 SPIE.
Author Keywords	End-side; Knowledge Distillation; Multi-object Tracking; Object detection; Pedestrian statistics

Similar Articles

Id	Similarity	Authors	Title	Published
23868	0.865	Tseng Y.-S.; Su Y.-F.; Lin D.-T.	Enhancing Multi-Target Multi-Camera Vehicle Tracking With Yolov9 And Attention Mechanisms For Smart City Traffic Monitoring	Multimedia Tools and Applications (2025)
17814	0.86	Wang X.; Sun Z.; Chehri A.; Jeon G.; Song Y.	Deep Learning And Multi-Modal Fusion For Real-Time Multi-Object Tracking: Algorithms, Challenges, Datasets, And Comparative Study	Information Fusion, 105 (2024)
62125	0.859	Song F.; Li P.	Yolov5-Ms: Real-Time Multi-Surveillance Pedestrian Target Detection Model For Smart Cities	Biomimetics, 8, 6 (2023)
50560	0.858	Baiat Z.E.; Baydere S.	Smart City Traffic Monitoring:Yolov7 Transfer Learning Approach For Real-Time Vehicle Detection	2023 International Conference on Smart Applications, Communications and Networking, SmartNets 2023 (2023)
25460	0.856	Zhao Q.; Ma W.; Zheng C.; Li L.	Exploration Of Vehicle Target Detection Method Based On Lightweight Yolov5 Fusion Background Modeling	Applied Sciences (Switzerland), 13, 7 (2023)
23647	0.853	Bhonde T.; Temare H.; Dadwhal Y.S.	Enhanced Object Detection Using Yolov8: Identifying Vehicles And Pedestrians In Urban Environments	2024 IEEE Pune Section International Conference, PuneCon 2024 (2024)
56151	0.852	Feng Z.; You F.	The Object Detection Method For Pedestrian Video Based On Improved Yolov3	ACM International Conference Proceeding Series (2021)
30766	0.851	Li H.; Yin K.; Ji X.; Liu Y.; Huang T.; Yin G.	Improved Yolov3 Surveillance Device Object Detection Method Based On Federated Learning	2022 4th International Conference on Data-Driven Optimization of Complex Systems, DOCS 2022 (2022)
3990	0.851	Wang L.; Liu T.	A Real-Time Tracking Approach For Moving Objects Based On An Integrated Algorithm Of Yolov7 And Sort	Journal of Circuits, Systems and Computers, 34, 4 (2025)