Abstract
Moving object detection is a crucial task in computer vision. Event-based cameras are bio-inspired cameras that work by mimicking the working of the human eye. These cameras have multiple advantages over conventional frame-based cameras, like reduced latency, HDR, reduced motion blur during high motion, low power consumption, etc. However, these advantages come at a high cost, as event-based cameras are noise sensitive and have low resolution. Moreover, the task of moving object detection in these cameras is difficult, as event-based sensors capture only the binary changes in brightness of a scene, lacking useful visual features like texture and color. In this paper, we investigate the application of the k-means clustering technique in detecting moving objects in event-based data. Experimental results in publicly available datasets using k-means show significant improvement in performance over the state-of-the-art methods.
Abstract (translated)
URL
https://arxiv.org/abs/2109.01879
