| Title |
Semantics-Driven Cloud-Edge Collaborative Inference A Case Study Of License Plate Detection |
| ID_Doc |
48288 |
| Authors |
Gao Y.; Zhang B. |
| Year |
2023 |
| Published |
2023 International Conference on Image Processing, Computer Vision and Machine Learning, ICICML 2023 |
| DOI |
http://dx.doi.org/10.1109/ICICML60161.2023.10424826 |
| Abstract |
With the proliferation of video data in smart city applications like intelligent transportation, efficient video analytics has become crucial but also challenging. This paper proposes a semantics-driven cloud-edge collaborative approach for accelerating video inference, using license plate recognition as a case study. The method separates semantics extraction and recognition, allowing edge servers to only extract visual semantics (license plate patches) from video frames and offload computation-intensive recognition to the cloud or neighboring edges based on load. This segmented processing coupled with a load-aware work distribution strategy aims to reduce end-to-end latency and improve throughput. Experiments demonstrate significant improvements in end-to-end inference speed (up to 5x faster), throughput (up to 9 FPS), and reduced traffic volumes (50% less) compared to cloud-only or edge-only processing, validating the efficiency of the proposed approach. The cloud-edge collaborative framework with semantics-driven work partitioning provides a promising solution for scaling video analytics in smart cities. © 2023 IEEE. |
| Author Keywords |
cloud computing; edge computing; license plate recognition; smart cities; video analytics |
