Global Correlation Based Ground Plane Estimation Using V-Disparity Image

This paper presents the estimation of the position of the ground plane for navigation of on-road or off-road vehicles, in particular for obstacle detection using stereo vision. Ground plane estimation plays an important role in stereo vision based obstacle detection tasks. V-disparity image is widely used for ground plane estimation. However, it heavily relies on distinct road features which may not exist. In here, we introduce a global correlation method to extract the position of the ground plane in V-disparity image even without distinct road features.

Authors

• Jun Zhao
• Jay Katupitiya
• James Ward

Keywords

• Roads
• Cameras
• Mobile robots
• Stereo vision
• Image segmentation
• Navigation
• Robot sensing systems
• Remotely operated vehicles
• Correlation
• Data mining
• Ground Plane
• Ground Plane Estimation
• Obstacle Avoidance
• Stereopsis
• Road Characteristics
• Acquisition Time
• Slope Of Line
• Image Plane
• Image Pairs
• Line Segment
• Depth Map
• Tilt Angle
• Road Conditions
• Pitch Angle
• Line Positions
• Hough Transform
• Pitch Variation
• Stereo Matching
• 3D World
• Lane Markings
• Matching Cost
• Disparity Map
• Candidate Lines
• Plane Fitting
• Calibration Stage
• Straight Line
• Bottom Image
• V-disparity image