Multi-view scheduling of onboard live video analytics to minimize frame processing latency

• Main Authors: LIU, Shengzhong, WANG, Tianshi, GUO, Hongpeng, FU, Xinzhe, DAVID, Philip, WIGNESS, Maggie, MISRA, Archan, ABDELZAHER, Tarek
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: Edge Computing; Live Video Analytics; Collaborative Sensing; Data Science; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/7888; https://ink.library.smu.edu.sg/context/sis_research/article/8890/viewcontent/717700a503.pdf
• Institution: Singapore Management University

This paper presents a real-time multi-view scheduling framework for DNN-based live video analytics at the edge to minimize frame processing latency. The work is motivated by applications where a higher frame rate is important, not to miss actions of interest. Examples include defense, border security, and intruder detection applications where sensors (in this paper, cameras) are deployed to monitor key roads, chokepoints, or passageways to identify events of interest (and intervene in real-time). Supporting a higher frame rate entails lowering frame processing latency. We assume that multiple cameras are deployed with partially overlapping views. Each camera has access to limited onboard computing capacity. Many targets cross the field of view of these cameras (but the great majority do not require action). We take advantage of the spatial-temporal correlations among multi-camera video streams to perform target-to-camera assignment such that the maximum frame processing time across cameras is minimized. Specifically, we use a data-driven approach to identify objects seen by multiple cameras, and propose a batch-aware latency-balanced (BALB) scheduling algorithm to drive the object-to-camera assignment. We empirically evaluate the proposed system with a real-world surveillance dataset on a testbed consisting of multiple NVIDIA Jetson boards. The results show that our system substantially improves the video processing speed, attaining multiplicative speedups of 2.45× to 6.85×, and consistently outperforms the competitive static region partitioning strategy.