Smart City Gnosys
Smart city article details
| Title | Split Computing Video Analytics Performance Enhancement With Auction-Based Resource Management |
|---|---|
| ID_Doc | 52771 |
| Authors | Fu K.-J.; Yang Y.-T.; Wei H.-Y. |
| Year | 2022 |
| Published | IEEE Access, 10 |
| DOI | http://dx.doi.org/10.1109/ACCESS.2022.3211984 |
| Abstract | Recently, computer vision applications based on deep neural networks (DNN) have developed rapidly. They are expected to be used in Internet-of-Things (IoT) systems such as smart cities, factories of the future, and security surveillance cameras. However, resource-limited IoT devices cannot execute such computationally intensive inference tasks locally within a reasonable time. Edge computing and the split computing technique provide such systems with a solution that reduces the inference latency and improves the system performance by enabling collaborative inference between the devices and the nearby edge server and alleviating the large uplink transmission with the split point carefully selected. This article proposes an incentive-compatible mechanism to configure the frame rate and the input resolution of the camera network for video analytics using layer-level split computing. Specifically, we evaluate the performance of the system at the video level, where the frame rate and the input resolution are both configuration knobs that contribute to accuracy. We also address the joint resource allocation and the split point decision problem for split computing that underlies the configuration. We show that the proposed mechanism achieves optimal configuration and guarantees truthfulness, individual rationality, and weak budget balance. © 2013 IEEE. |
| Author Keywords | deep learning; Edge computing; game theory; split computing; video analytics |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
14727  | 0.865 | 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) |
| 31076 | 0.86 | Lin L.; Lin J.; Xiong J.; Li P.; Lin J.; Wang X.; Lin L. | Incentivizing Resource Contribution For Video Analytics In Computing Power Networking: A Dual-Layer Stackelberg Game Approach | IEEE Internet of Things Journal, 12, 14 (2025) |
| 21748 | 0.859 | Yang Y.-T.; Wei H.-Y. | Edge Computing And Networking Resource Management For Decomposable Deep Learning: An Auction-Based Approach | 2021 22nd Asia-Pacific Network Operations and Management Symposium, APNOMS 2021 (2021) |
| 3217 | 0.855 | Mendieta M.; Neff C.; Lingerfelt D.; Beam C.; George A.; Rogers S.; Ravindran A.; Tabkhi H. | A Novel Application/Infrastructure Co-Design Approach For Real-Time Edge Video Analytics | Conference Proceedings - IEEE SOUTHEASTCON, 2019-April (2019) |