# Event-Based Machine Vision for Edge AI Computing

## TL;DR

This paper introduces a new event-based machine vision framework that improves speed and efficiency for edge AI tasks like human detection and pose estimation.

## Contribution

A timestamp-based recency encoding method and task-specific network optimizations for sparse event images are introduced.

## Key findings

- The proposed method achieves an 11× speed-up for human detection and pose estimation.
- Event-based sensing reduces data volume by 30× compared to conventional CMOS video.
- A compact CNN achieves high accuracy for hand posture recognition with low latency.

## Abstract

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 11× speed-up for human detection and pose estimation.

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 11× 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.

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.

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 × 480), the raw DVS stream is about 30× smaller than conventional CMOS video and remains about 5× 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 11× 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.