IEEE Intelligent Vehicles Symposium · 2007 · 51 citations · 12 references
ComputingComputer ScienceRobotics EngineeringComputer VisionMachine VisionRobot VisionObject DetectionObstacle AvoidanceObstacle DetectionStereo VisionVehicle PerceptionVisual SlamDisparity ComputationObstacle Detection SystemsReal-time Obstacle DetectionReal-time ProcessingReal-time Stereo VisionStereo CorrespondenceStereo MatchingStereo Vision Obstacle Detection
A fast and robust stereo algorithm for on-board obstacle detection systems is proposed. The proposed method finds the optimum road-obstacle boundary which provides the most consistent interpretation of the input stereo image pair. Global optimization combined with a robust matching measure enables stable detection of obstacles under various circumstances, such as heavy rain and severe lighting conditions. The processing time for VGA size image pair is about 15msec on a 3.6GHz pentium IV processor, which is fast enough for real-time applications.
12