Event-based YOLO Object Detection: Proof of Concept for Forward Perception System

TL;DR

This paper demonstrates the feasibility of using neuromorphic event data with YOLOv5 networks for fast, efficient roadside object detection in forward perception systems, advancing autonomous vehicle technology.

Contribution

It introduces a novel approach combining neuromorphic event data with YOLOv5 for improved object detection in vehicular forward perception systems.

Findings

Event-based YOLO achieves promising detection accuracy.

Ensemble models improve robustness and inference results.

Proof of concept for neuromorphic event data in automotive perception.

Abstract

Neuromorphic vision or event vision is an advanced vision technology, where in contrast to the visible camera that outputs pixels, the event vision generates neuromorphic events every time there is a brightness change which exceeds a specific threshold in the field of view (FOV). This study focuses on leveraging neuromorphic event data for roadside object detection. This is a proof of concept towards building artificial intelligence (AI) based pipelines which can be used for forward perception systems for advanced vehicular applications. The focus is on building efficient state-of-the-art object detection networks with better inference results for fast-moving forward perception using an event camera. In this article, the event-simulated A2D2 dataset is manually annotated and trained on two different YOLOv5 networks (small and large variants). To further assess its robustness, single model testing and ensemble model testing are carried out.