Euphrates: Algorithm-SoC Co-Design for Low-Power Mobile Continuous Vision
arXiv:1803.11232
Abstract
Continuous computer vision (CV) tasks increasingly rely on convolutional neural networks (CNN). However, CNNs have massive compute demands that far exceed the performance and energy constraints of mobile devices. In this paper, we propose and develop an algorithm-architecture co-designed system, Euphrates, that simultaneously improves the energy-efficiency and performance of continuous vision tasks. Our key observation is that changes in pixel data between consecutive frames represents visual motion. We first propose an algorithm that leverages this motion information to relax the number of expensive CNN inferences required by continuous vision applications. We co-design a mobile System-on-a-Chip (SoC) architecture to maximize the efficiency of the new algorithm. The key to our architectural augmentation is to co-optimize different SoC IP blocks in the vision pipeline collectively. Specifically, we propose to expose the motion data that is naturally generated by the Image Signal Processor (ISP) early in the vision pipeline to the CNN engine. Measurement and synthesis results show that Euphrates achieves up to 66% SoC-level energy savings (4 times for the vision computations), with only 1% accuracy loss.
References in corpus (7)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- High-Speed Tracking with Kernelized Correlation Filters
- YOLO9000: Better, Faster, Stronger
- Learning Multi-Domain Convolutional Neural Networks for Visual Tracking
- Fast YOLO: A Fast You Only Look Once System for Real-time Embedded Object Detection in Video
- Real-time Action Recognition with Enhanced Motion Vector CNNs
- Need for Speed: A Benchmark for Higher Frame Rate Object Tracking