Event-based YOLO Object Detection: Proof of Concept for Forward Perception System
This is an incremental step towards building AI pipelines for advanced vehicular applications, specifically for roadside object detection using event cameras.
This study tackled object detection for fast-moving forward perception systems using neuromorphic event data, achieving a 0.85 mAP on the manually annotated event-simulated A2D2 dataset with YOLOv5 networks.
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.