Event-Based Machine Vision for Edge AI Computing

초록

Highlights What are the main findings? We present an event image representation that preserves moving-edge structure while reducing data volume for downstream processing. The proposed event-based edge AI computing achieves an 11x speed-up for human detection and pose estimation. What are the implications of the main findings? The approach enables privacy-friendly, always-on home occupancy sensing under tight edge constraints. Combining event encoding with compact models is an effective deployment recipe for motion-centric edge AI tasks.Highlights What are the main findings? We present an event image representation that preserves moving-edge structure while reducing data volume for downstream processing. The proposed event-based edge AI computing achieves an 11x speed-up for human detection and pose estimation. What are the implications of the main findings? The approach enables privacy-friendly, always-on home occupancy sensing under tight edge constraints. Combining event encoding with compact models is an effective deployment recipe for motion-centric edge AI tasks.Abstract Event-based sensors provide sparse, motion-centric measurements that can reduce data bandwidth and enable always-on perception on resource-constrained edge devices. This paper presents an event-based machine vision framework for smart-home AIoT that couples a Dynamic Vision Sensor (DVS) with compute-efficient algorithms for (i) human/object detection, (ii) 2D human pose estimation, (iii) hand posture recognition for human-machine interfaces. The main methodological contributions are timestamp-based, polarity-agnostic recency encoding that preserves moving-edge structure while suppressing static background, and task-specific network optimizations (architectural reduction and mixed-bit quantization) tailored to sparse event images. With a fixed downstream network, the recency encoding improves action recognition accuracy over temporal accumulation (0.908 vs. 0.896). In a 24 h indoor monitoring experiment (640 x 480), the raw DVS stream is about 30x smaller than conventional CMOS video and remains about 5x smaller after standard compression. For human detection, the optimized event processing reduces computation from 5.8 G to 81 M FLOPs and runtime from 172 ms to 15 ms (more than 11x speed-up). For pose estimation, a pruned HRNet reduces model size from 127 MB to 19 MB and inference time from 70 ms to 6 ms on an NVIDIA Titan X while maintaining a comparable accuracy (mAP from 0.95 to 0.94) on MS COCO 2017 using synthetic event streams generated by an event simulator. For hand posture recognition, a compact CNN achieves 99.19% recall and 0.0926% FAR with 14.31 ms latency on a single i5-4590 CPU core using 10-frame sequence voting. These results indicate that event-based sensing combined with lightweight inference is a practical approach to privacy-friendly, real-time perception under strict edge constraints.

키워드