Real time obstacle detection in stereovision on non flat road geometry through "v-disparity" representation

By R. Labayrade, Didier Aubert, Jean-Philippe Tarel. Intelligent Vehicle Symposium, 2002. IEEE, 2002

728 citations recorded by the source corpus.

Presents a road obstacle detection method able to cope with uphill and downhill gradients and dynamic pitching of the vehicle. Our approach is based on the construction and investigation of the "v-disparity" image which provides a good representation of the geometric content of the road scene. The advantage of this image is that it provides semi-global matching and is able to perform robust obstacle detection even in the case of partial occlusion or errors committed during the matching process. Furthermore, this detection is performed without any explicit extraction of coherent structures. This paper explains the construction of the "v-disparity" image, its main properties, and the obstacle detection method. The longitudinal profile of the road is estimated and the objects located above the road surface are then extracted as potential obstacles; subsequently, the accurate detection of road obstacles, in particular the position of tyre-road contact points is computed in a precise manner. The whole process is performed at frame rate with a current-day PC. Our experimental findings and comparisons with the results obtained using a flat geometry hypothesis show the benefits of our approach.

Subfields: Automotive Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/8063db75bd3dab8efc5a33f59dfb03f2fb92e270

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Automotive Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Fast shape-based road sign detection for a driver assistance system (2004, background): “By modelling the road [ 17 ], it may be possible to dictate parts of the image where a sign cannot appear, but road modelling has its own computational expense, and, as discussed previously, colour-based methods are not robust.”
Self-Supervised Drivable Area and Road Anomaly Segmentation Using RGB-D Data For Robotic Wheelchairs (2019, methodology): “As derived in [8], for an RGB-D camera consisting of two cameras, the projection of the real world point P with coordinates of ( X, Y, Z ) on the image coordinates ( U, V ) can be computed by (1)–(3): where b is the distance between the optical centers of two cameras; f is the focal length; ( u 0 ,…”
Human fall detection on embedded platform using depth maps and wireless accelerometer (2014, methodology): “In [24] a method based on v-disparity maps between two stereo images has been proposed to achieve reliable obstacle detection.”
Hobbit, a care robot supporting independent living at home: First prototype and lessons learned (2016, methodology): “We apply a ‘‘v-disparity’’based approach [25] to the disparity images provided by the camera in order to detect and remove the floor.”
Survey of Pedestrian Detection for Advanced Driver Assistance Systems (2010, background): “Regarding stereo-based pose estimation, Labayrade et al. introduced v-disparity space [24], which consists of accumulating stereo disparity along the image y-axis in order to 1) compute the slope of the road (which is related to the horizon line) and 2) point out the existence of vertical objects…”
Research Advances and Challenges of Autonomous and Connected Ground Vehicles (2019, methodology): “ods, like v-disparity for ground surface modeling [152], [153], u-disparity for computing free space [154], [155] and depth map for clustering [155]– [158], are frequently utilized for initial scene segmentation not for direct vehicle detection.”