Smart City Gnosys
Smart city article details
| Title | E2Ec: Edge-To-Edge Collaboration For Efficient Real-Time Video Surveillance Inference |
|---|---|
| ID_Doc | 21552 |
| Authors | Li G.; Zeng J.; Peng Z.; Liang Y.; Zheng X.; Wang T. |
| Year | 2025 |
| Published | IEEE Transactions on Mobile Computing |
| DOI | http://dx.doi.org/10.1109/TMC.2025.3559919 |
| Abstract | In smart cities, Multi-Camera Multi-Target pedestrian tracking and Re-identification (MCMT-ReID) is essential for effective surveillance, particularly in real-time scenarios, as it demands significant computational resources. Current edgecloud collaboration methods encounter issues such as high latency and potential data leakage due to the physical distance between cloud servers and cameras. To address these issues, we propose a novel Edge-to-Edge Collaboration (E2EC) system that fully utilizes collaboration between heterogeneous edge devices. E2EC partitions the MCMT-ReID task into two modular applications: Tracking and Re-identification (ReID), and employs a customized Kafka communication protocol to optimize data exchange efficiency. Moreover, E2EC dynamically orchestrates intermediate inference flows and transmits features instead of pedestrian detection frames to avoid data leakage. To enhance ReID accuracy, we introduce a real-time ReID Loop Confirmation (ReLC) algorithm, which continuously validates identities to boost reliability and accuracy. E2EC has been deployed and tested in a real-world campus environment to validate its effectiveness. Experimental results demonstrate that E2EC enhances the Rank-1 accuracy and mAP of pedestrian ReID by 36.88% and 46.00%, respectively. Furthermore, it achieves an increase of about 6.35%-12.66% in throughput and reduces latency by 35.01%-57.83% compared to baselines, ensuring realtime performance under dynamic workloads. © 2002-2012 IEEE. |
| Author Keywords | Collaborative inference; Edge computing; Edge intelligence; Video surveillance |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
14727  | 0.86 | Pasandi H.B.; Nadeem T. | Collaborative Intelligent Cross-Camera Video Analytics At Edge: Opportunities And Challenges | AIChallengeIoT 2019 - Proceedings of the 2019 International Workshop on Challenges in Artificial Intelligence and Machine Learning for Internet of Things (2019) |
| 61474 | 0.857 | Dong Z.; Lu Y.; Tong G.; Shu Y.; Wang S.; Shi W. | Watchdog: Real-Time Vehicle Tracking On Geo-Distributed Edge Nodes | ACM Transactions on Internet of Things, 4, 1 (2023) |
| 21393 | 0.857 | Khochare A.; Sheshadri K.R.; Shriram R.; Simmhan Y. | Dynamic Scaling Of Video Analytics For Wide-Area Tracking In Urban Spaces | Proceedings - 19th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGrid 2019 (2019) |
| 14737 | 0.855 | Sun H.; Chen Y.; Aved A.; Blasch E. | Collaborative Multi-Object Tracking As An Edge Service Using Transfer Learning | Proceedings - 2020 IEEE 22nd International Conference on High Performance Computing and Communications, IEEE 18th International Conference on Smart City and IEEE 6th International Conference on Data Science and Systems, HPCC-SmartCity-DSS 2020 (2020) |
| 20701 | 0.854 | Chen Y.-Y.; Lin Y.-H.; Hu Y.-C.; Hsia C.-H.; Lian Y.-A.; Jhong S.-Y. | Distributed Real-Time Object Detection Based On Edge-Cloud Collaboration For Smart Video Surveillance Applications | IEEE Access, 10 (2022) |