Event Data Stream Compression Based on Point Cloud Representation

The Dynamic Vision System (DVS) is a novel image acquisition system that works only when there is a brightness change in a pixel, resulting in a stream of events including timestamps, spatial coordinates and the sign of the brightness change (increase or decrease). Although DVS's output data size is much smaller than conventional image systems, it still requires further compression, as the main applications of DVS are embedded systems with limited transmission and storage resources. In this paper, we propose a new method for lossless compression of event data streams based on point cloud representations. The event data stream is organized into a 3D point cloud to which a compression algorithm is applied. In addition, different generation strategies are devised in order to compare the compression performance of the proposed approach. Experimental results show an improved compression ratio of about 22% under lossless conditions.