Bio-inspired Event Based Motion Detection for Traffic Safety in a Close-Real Automotive Environment

In this paper a bio-inspired and automotive-compliant system for traffic safety is presented. This work is the first complete application of Address Event Representation (AER) techniques to a real world problem in an automotive environment. The main goal is to detect hands driver activity in the driving wheel area. Our system is based on AER, where the more relevant visual information in the image is first processed. Different pixel activity detection and AER event generation methods have been deeply evaluated. Obtained results are compared with a classical computer vision system based on JPEG transmission. It has been proved that for the scan AER event generation method the performance over JPEG is improved. As our work results show, AER technology could be an effective alternative to be considered in real world conditions. Promising results have been obtained in an automotive-compliant environment.