Efficient and accurate recognition of human interactions is crucial for numerous service applications, including security surveillance and public safety. However, achieving real-time interaction recognition on resource-constrained edge devices poses significant computational challenges. In this paper, we propose a lightweight methodology for detecting human activity and interactions in video streams, specifically tailored for edge computing environments. Our approach utilizes distance estimation and interaction detection based on pose estimation techniques, enabling rapid analysis of video data while conserving computational resources. By leveraging a distance grid for proximity analysis and TensorFlow's MoveNet for pose estimation, our method achieves promising results in interaction recognition. We demonstrate the feasibility of our approach through empirical evaluation and discuss its potential implications for real-world deployment on edge devices.
Tài liệu tham khảo
Azimi, S., De Sio, C., & Sterpone, L. (2023). Enhanced Video Surveillance Systems for “Signal for Help” Detection on Edge Devices. 2023 IEEE International Symposium on Technology and Society (ISTAS), 1–4. https://doi.org/10.1109/ISTAS57930.2023.10305989
Deng, Y., Han, T., & Ansari, N. (2020). FedVision: Federated Video Analytics With Edge Computing. IEEE Open Journal of the Computer Society, 1, 62–72. https://doi.org/10.1109/OJCS.2020.2996184
Ezzat, M. A., Abd El Ghany, M. A., Almotairi, S., & Salem, M. A.-M. (2021). Horizontal Review on Video Surveillance for Smart Cities: Edge Devices, Applications, Datasets, and Future Trends. Sensors, 21(9), 3222. https://doi.org/10.3390/s21093222
Guo, Y., Zou, B., Ren, J., Liu, Q., Zhang, D., & Zhang, Y. (2019). Distributed and Efficient Object Detection via Interactions Among Devices, Edge, and Cloud. IEEE Transactions on Multimedia, 21(11), 2903–2915. https://doi.org/10.1109/TMM.2019.2912703
Huang, Y., Zhao, H., Qiao, X., Tang, J., & Liu, L. (2021). Towards Video Streaming Analysis and Sharing for Multi-Device Interaction with Lightweight DNNs. IEEE INFOCOM 2021 - IEEE Conference on Computer Communications, 1–10. https://doi.org/10.1109/INFOCOM42981.2021.9488846
Kim, J.-H., Kim, N., & Won, C. S. (2021). Deep Edge Computing for Videos. IEEE Access, 9, 123348–123357. https://doi.org/10.1109/ACCESS.2021.3109904
Nikouei, S. Y., Chen, Y., Aved, A. J., & Blasch, E. (2021). I-ViSE: Interactive Video Surveillance as an Edge Service Using Unsupervised Feature Queries. IEEE Internet of Things Journal, 8(21), 16181–16190. https://doi.org/10.1109/JIOT.2020.3016825
Patrikar, D. R., & Parate, M. R. (2022). Anomaly detection using edge computing in video surveillance system: Review. International Journal of Multimedia Information Retrieval, 11(2), 85–110. https://doi.org/10.1007/s13735-022-00227-8
Wang, F., Zhang, M., Wang, X., Ma, X., & Liu, J. (2020). Deep Learning for Edge Computing Applications: A State-of-the-Art Survey. IEEE Access, 8, 58322–58336. https://doi.org/10.1109/ACCESS.2020.2982411
Wang, Q., Fang, W., & Xiong, N. N. (2024). TLEE: Temporal-Wise and Layer-Wise Early Exiting Network for Efficient Video Recognition on Edge Devices. IEEE Internet of Things Journal, 11(2), 2842–2854. https://doi.org/10.1109/JIOT.2023.3293506
Wang, Y., Zhu, A., Ma, H., Ai, L., Song, W., & Zhang, S. (2023). 3D-ShuffleViT: An Efficient Video Action Recognition Network with Deep Integration of Self-Attention and Convolution. Mathematics, 11(18), 3848. https://doi.org/10.3390/math11183848.
