Realtime On-Road Vehicle Detection with Optical Flows and Haar-Like Feature Detectors

An autonomous vehicle is a demanding application for our daily life. Such vehicle requires to detect other vehicles on the road. Given the sequences of images, the algorithms need to find other vehicles in realtime. There two types of on-road vehicles, traveling in the same direction or traveling in the opposite direction. Due to the distinct features of two types of vehicles, different approaches are necessary to detect vehicles in different directions. Here, we use ‘optical flow‘ to detect vehicles in the opposite direction because the coming traffics shows salient motions. We use ‘Haar-like feature detection‘ for vehicles in the same direction because the traffics represent relatively stable shape (car rear) and little motion. We verify the detected region with estimating 3D geometry. If the detector fail to find the vehicles, we interpolate the region from the previous frames. Then, the detected vehicles are projected into the 3D space. Our system detects vehicles with high accuracy in realtime for 11 frames/sec.