Bio-Inspired Looming Object Detection Using Event-Based Cameras

A novel looming object detection method for event-based cameras is presented. Event-based cameras capture changes in a scene without generating redundant data compared to frame-based cameras. In this paper, a bio-inspired looming object detection algorithm for frame-based cameras was adapted for an event-based camera. The adapted algorithm was then used as part of a looming object detection algorithm that is fast and capable of detecting multiple looming objects in a scene. The new method is tested on the Davis Dynamic Vision Sensor event-based camera and it is fast and effective.