MOSAIC: Spatially-Multiplexed Edge AI Optimization over Multiple Concurrent Video Sensing Streams
PROCEEDINGS OF THE 2023 PROCEEDINGS OF THE 14TH ACM MULTIMEDIA SYSTEMS CONFERENCE, MMSYS 2023(2023)
摘要
Sustaining high fidelity and high throughput of perception tasks over vision sensor streams on edge devices remains a formidable challenge, especially given the continuing increase in image sizes (e.g., generated by 4K cameras) and complexity of DNN models. One promising approach involves criticality-aware processing, where the computation is directed selectively to "critical" portions of individual image frames. We introduce MOSAIC, a novel system for such criticality-aware concurrent processing of multiple vision sensing streams that provides a multiplicative increase in the achievable throughput with negligible loss in perception fidelity. MOSAIC determines critical regions from images received from multiple vision sensors and spatially bin-packs these regions using a novel multi-scale Mosaic Across Scales (MoS) tiling strategy into a single 'canvas frame', sized such that the edge device can retain sufficiently high processing throughput. Experimental studies using benchmark datasets for two tasks, Automatic License Plate Recognition and Drone-based Pedestrian Detection, shows that MOSAIC, executing on a Jetson TX2 edge device, can provide dramatic gains in the throughput vs. fidelity tradeoff. For instance, for drone-based pedestrian detection, for a batch size of 4, MOSAIC can pack input frames from 6 cameras to achieve (a) 4.75x (475%) higher throughput (23 FPS per camera, cumulatively 138FPS) with = 1% accuracy loss, compared to a First Come First Serve (FCFS) processing paradigm.
更多查看译文
关键词
Edge AI,Machine Perception,Canvas-based Processing
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要