一种基于多摄像头的行人追踪和重识别方案
A Multi-Camera-Based Pedestrian Tracking and Re-Identification Solution
DOI: 10.12677/csa.2025.159220, PDF,    科研立项经费支持
作者: 谭丽欢, 郭萍, 罗 颂*:警务物联网应用技术公安部重点实验室,北京;重庆理工大学计算机科学与工程学院,重庆;宋鹃伲:成都市公安局锦江区分局信息通信科,四川 成都;周俊豪:重庆理工大学两江国际学院,重庆
关键词: 行人定位行人追踪计算机视觉人工智能行人重识别Pedestrian Localization Pedestrian Tracking Computer Vision Artificial Intelligence Pedestrian Re-Identification
摘要: 随着城市交通管理、安保和智慧城市建设的需求日益增长,研究高效、准确、实时的行人定位和追踪系统具有重要的研究意义和实用价值。本文针对目前计算机视觉和人工智能领域的行人检测和跟踪技术,提出了一个基于视觉的行人定位和追踪系统。系统采用YOLOv5算法进行行人检测,DeepSORT算法进行多目标跟踪,并使用ResNet50模型实现行人重识别。此外,系统还支持目标运动轨迹绘制、行人数量统计等功能。实验结果表明,该系统在公开数据集(例如Market-1501数据集)和现实场景数据上具有良好的性能表现,可为城市交通管理、安保和智慧城市建设等领域提供有力支持。未来,将继续优化算法和模型结构,提高系统的准确性和实时性,为计算机视觉和人工智能领域的研究和应用带来更多创新。
Abstract: With the growing demand for urban traffic management, security, and smart city development, researching efficient, accurate, real-time pedestrian localization and tracking systems holds significant research significance and practical value. This paper proposes a vision-based pedestrian localization and tracking system targeting current pedestrian detection and tracking technologies in the fields of computer vision and artificial intelligence. The system employs the YOLOv5 algorithm for pedestrian detection, the DeepSORT algorithm for multi-object tracking, and the ResNet50 model for pedestrian re-identification. Additionally, the system supports functions such as target motion trajectory mapping and pedestrian counting. Experimental results demonstrate that the system exhibits excellent performance on both public datasets (e.g., the Market-1501 dataset) and real-world scenario data, providing robust support for urban traffic management, security, and smart city development. In the future, further optimization of algorithms and model structures will be pursued to enhance the system’s accuracy and real-time performance, driving innovation in both research and applications within the fields of computer vision and artificial intelligence.
文章引用:谭丽欢, 宋鹃伲, 周俊豪, 郭萍, 罗颂. 一种基于多摄像头的行人追踪和重识别方案[J]. 计算机科学与应用, 2025, 15(9): 16-30. https://doi.org/10.12677/csa.2025.159220

参考文献

[1] 国务院第七次全国人口普查领导小组办公室. 第七次全国人口普查公报(第二号) [EB/OL]. 2021-05-11.
http://www.stats.gov.cn/tjsj/zxfb/202105/t20210510_1817178.html, 2022-06-05.
[2] 孙明军. 无人驾驶中的行人检测与重识别算法研究[D]: [硕士学位论文]. 武汉: 武汉理工大学, 2018.
[3] Redmon, J., Divvala, S., Girshick, R. and Farhadi, A. (2016) You Only Look Once: Unified, Real-Time Object Detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 779-788. [Google Scholar] [CrossRef
[4] Wojke, N., Bewley, A. and Paulus, D. (2017) Simple Online and Realtime Tracking with a Deep Association Metric. 2017 IEEE International Conference on Image Processing (ICIP), Beijing, 17-20 September 2017, 3645-3649. [Google Scholar] [CrossRef
[5] He, K.M., Zhang, X.Y., Ren, S.Q. and Sun, J. (2016) Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 770-778. [Google Scholar] [CrossRef
[6] Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J. and Tian, Q. (2015) Scalable Person Re-Identification: A Benchmark. 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, 7-13 December 2015, 1116-1124. [Google Scholar] [CrossRef
[7] Wang, C.Y., Liao, H.Y.M., Wu, Y.H., Chen, P.Y., et al. (2020) CSPNet: A New Backbone That Can Enhance Learning Capability of CNN. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPR Workshop), Seattle, 14-19 June 2020, 1571-1580.
[8] Liu, S., Qi, L., Qin, H., Shi, J. and Jia, J. (2018) Path Aggregation Network for Instance Segmentation. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 8759-8768. [Google Scholar] [CrossRef
[9] He, K., Zhang, X., Ren, S. and Sun, J. (2015) Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37, 1904-1916. [Google Scholar] [CrossRef] [PubMed]
[10] Bewley, A., Ge, Z., Ott, L., Ramos, F. and Upcroft, B. (2016) Simple Online and Realtime Tracking. 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, 25-28 September 2016, 3464-3468. [Google Scholar] [CrossRef
[11] 罗浩, 姜伟, 范星, 张思朋. 基于深度学习的行人重识别研究进展[J]. 自动化学报, 2019, 45(11): 2032-2049.
[12] Hermans, A., Beyer, L. and Leibe, B. (2017) In Defense of the Triplet Loss for Person Re-Identification. [Google Scholar] [CrossRef
[13] Chen, W.H., Chen, X.T., Zhang, J.G. and Huang, K.Q. (2017) Beyond Triplet Loss: A Deep Quadruplet Network for Person Re-Identification. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 21-26 July 2017, 1320-1329. [Google Scholar] [CrossRef
[14] Guo, J., Yuan, Y., Huang, L., Zhang, C., Yao, J. and Han, K. (2019) Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, 27 October-2 November 2019, 3641-3650. [Google Scholar] [CrossRef
[15] Chen, H., Wang, Y., Lagadec, B., Dantcheva, A. and Bremond, F. (2021) Joint Generative and Contrastive Learning for Unsupervised Person Re-Identification. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 20-25 June 2021, 2004-2013. [Google Scholar] [CrossRef
[16] Fu, Y., Wang, X., Wei, Y. and Huang, T. (2019) STA: Spatial-Temporal Attention for Large-Scale Video-Based Person Re-Identification. Proceedings of the AAAI Conference on Artificial Intelligence, 33, 8287-8294. [Google Scholar] [CrossRef
[17] Zhang, Y., Sun, P., Jiang, Y., Yu, D., Weng, F., Yuan, Z., et al. (2021) ByteTrack: Multi-Object Tracking by Associating Every Detection Box. In: Lecture Notes in Computer Science, Springer, 1-21. [Google Scholar] [CrossRef