Moving Object Detection for Event-based Vision using k-means Clustering

Abstract

Moving object detection is a crucial task in computer vision. Event-based cameras are bio-inspired cameras that mimic the working of the human eye. Unlike conventional frame-based cameras, these cameras pose multiple advantages, 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 sensitive to noise and have low resolution. Moreover, for the lack of useful visual features like texture and color, moving object detection in these cameras becomes more challenging. Our proposed method uses k-Means clustering for detecting moving objects in event-based data. We further compare the proposed method against state-of-the-art algorithms and show performance improvement over them.