3D Velocity Filters for Improved Object Detection in Automotive Applications

Vision-based object detection is a core part of many automotive collision warning systems. Especially due to the extensive information an image can hold and the decreasing costs of computational power, it has attracted more and more interest in the last decade. This paper proposes a motion-based approach to simplify the detection of moving objects. In contrast to most of the existing approaches we interpret the image sequence containing the moving object (e.g. a vehicle or a crossing pedestrian) as a three-dimensional signal, not just as an image matrix. Thus, we can benefit from the advanced theoretical knowledge on system description and handling from the field of signal processing. More precisely, we use three-dimensional velocity filters to oppress every object in the image that is not moving in a certain direction at a certain velocity. We present basic considerations on motion in the spatio-temporal and spectral domain as well as transfer function design. Finally, examples from pedestrian detection are given and ideal filter results are compared to results obtained using a wave digital filter (WDF) implementation thereof.