IET Intelligent Transport Systems · 2009 · 13 citations · 19 references
ComputingComputer ScienceComputer VisionMachine VisionRobot VisionDepth EstimationObject DetectionObject RecognitionObstacle DetectionScene UnderstandingStereo VisionCamera-based Obstacle DetectionMonocular Obstacle DetectionMotion SegmentationMotion-based Obstacle DetectionObstacle AnalysisPedestrian DetectionSegmentation By Motion
A car-mounted single monochrome camera-based pedestrian detection algorithm is discussed. The detection range is divided into two sub-regions, that is, the near distance range and the far distance range. Two different detection algorithms are applied in the two regions. For the near distance range, where the direction of the motion of the detected obstacle is important, a motion segmentation approach using interest points is utilised. For the far distance range where the motion of the detected obstacle is not as important, a robust and computationally efficient modified inverse perspective mapping-based obstacle detection is utilised. Finally, a low-level pedestrian-oriented segmentation algorithm, which is aimed at the depth information of the detected pedestrian candidate, is also presented.
19
A Trainable System for Object Detection
Tomaso Poggio · International Journal of Computer Vision · 2000 · 1.3K citations