EA: An Event Autoencoder for High-Speed Vision Sensing

TL;DR

This paper introduces an event autoencoder for high-speed vision sensing that compresses and reconstructs event data efficiently, enabling real-time, low-power applications with high accuracy and significantly fewer parameters.

Contribution

It presents a novel event autoencoder architecture with adaptive thresholding and lightweight classification, achieving high recognition accuracy with fewer parameters and faster processing on embedded devices.

Findings

Achieves comparable accuracy to YOLO-v4 with 35.5x fewer parameters.

Runs at 8 to 44.8 FPS on embedded platforms.

Classifier improves FPS by up to 87.84x over state-of-the-art.

Abstract

High-speed vision sensing is essential for real-time perception in applications such as robotics, autonomous vehicles, and industrial automation. Traditional frame-based vision systems suffer from motion blur, high latency, and redundant data processing, limiting their performance in dynamic environments. Event cameras, which capture asynchronous brightness changes at the pixel level, offer a promising alternative but pose challenges in object detection due to sparse and noisy event streams. To address this, we propose an event autoencoder architecture that efficiently compresses and reconstructs event data while preserving critical spatial and temporal features. The proposed model employs convolutional encoding and incorporates adaptive threshold selection and a lightweight classifier to enhance recognition accuracy while reducing computational complexity. Experimental results on the existing Smart Event Face Dataset (SEFD) demonstrate that our approach achieves comparable accuracy to the YOLO-v4 model while utilizing up to $35.5\times$ fewer parameters. Implementations on embedded platforms, including Raspberry Pi 4B and NVIDIA Jetson Nano, show high frame rates ranging from 8 FPS up to 44.8 FPS. The proposed classifier exhibits up to 87.84x better FPS than the state-of-the-art and significantly improves event-based vision performance, making it ideal for low-power, high-speed applications in real-time edge computing.