Real-time vehicle and lane detection with embedded hardware

For autonomously acting robots and driver assistance systems powerful optical stereo sensor systems are required. Object positions and environmental conditions have to be acquired in real-time. In this paper an algorithm based on a hardware-software co-design is applied. A depth-map is generated with a hierarchical detection method. A depthhistogram is generated by using the density distribution of the disparity in the depth-map. It is used for object detection. The object clustering can be accomplished without calculation of 3-d-points, due to the almost identical mapping of the objects over the whole distance, within the histogram. A lane detection is applied by using a Hough Transform. The suitability at night and the detection of small objects like bikers is proven.