Event-to-Video Conversion for Overhead Object Detection

Abstract

Collecting overhead imagery using an event camera is desirable due to the energy efficiency of the image sensor compared to standard cameras. However, event cameras complicate downstream image processing, especially for complex tasks such as object detection. In this paper, we investigate the viability of event streams for overhead object detection. We demonstrate that across a number of standard modeling approaches, there is a significant gap in performance between dense event representations and corresponding RGB frames. We establish that this gap is, in part, due to a lack of overlap between the event representations and the pre-training data that the object detectors were initially trained on through a number of experiments. Then, apply an off-the-shelf event-to-video conversion tool that converts event streams into gray-scale video to close this gap. We demonstrate that this approach results in a large performance increase, outperforming even event-specific object detection techniques on our overhead target task. These results suggest that better aligning event representations with existing large pre-trained models may result in greater short-term performance gains compared to end-to-end event-specific architectural improvements.