MRIM: Enabling Mixed-Resolution Imaging for low-power pervasive vision tasks

• Main Authors: WU, Jiyan, SUBASHARAN, Vithurson, TRAN, Tuan, MISRA, Archan
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: Mixed resolution; imaging tasks; energy consumption; Graphics and Human Computer Interfaces; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/7165; https://ink.library.smu.edu.sg/context/sis_research/article/8167/viewcontent/a5_wu_final_MRIM.pdf
• Institution: Singapore Management University

While many pervasive computing applications increasingly utilize real-time context extracted from a vision sensing infrastructure, the high energy overhead of DNN-based vision sensing pipelines remains a challenge for sustainable in-the-wild deployment. One common approach to reducing such energy overheads is the capture and transmission of lower-resolution images to an edge node (where the DNN inferencing task is executed), but this results in an accuracy-vs-energy tradeoff, as the DNN inference accuracy typically degrades with a drop in resolution. In this work, we introduce MRIM, a simple but effective framework to tackle this tradeoff. Under MRIM, the vision sensor platform first executes a lightweight preprocessing step to determine the saliency of different sub-regions within a single captured image frame, and then performs a saliency-aware non-uniform downscaling of individual sub-regions to produce a “mixed-resolution” image. We describe two novel low-complexity algorithms that the sensor platform can use to quickly compute suitable resolution choices for different regions under different energy/accuracy constraints. Experimental studies, involving object detection tasks evaluated traces from two benchmark urban monitoring datasets as well as a prototype Raspberry Pi-based MRIM implementation, demonstrate MRIM’s efficacy: even with unoptimized embedded platform, MRIM can provide system energy savings of 35+% or increase task accuracy by 8+%, over conventional baselines of uniform resolution downscaling or image encoding, while supporting high throughput.