A Fast Stereo Vision Algorithm With Improved Performance at Object Borders

Conventional correlation based stereo vision algorithms have poor performance at object borders due to occlusion. This paper analyzes image characteristics at depth discontinuities to improve the performance. It uses a new window scheme, especially to handle occlusion. The results show dramatically improved performance at depth discontinuities

Authors

• Jun Zhao
• Jay Katupitiya

Keywords

• Stereo vision
• Pixel
• Optimization methods
• Intelligent robots
• Manufacturing
• Australia
• Image analysis
• Performance analysis
• Minimization methods
• Performance evaluation
• Fast Algorithm
• Stereopsis
• Object Borders
• South Wales State Government
• Window Size
• Image Pixels
• Depth Map
• Left Image
• Normalization Strategy
• Matching Strategy
• Phase Matching
• Correct Matches
• Left Border
• Plyometric
• New Left
• Left View
• Smoothness Constraint
• Sum Of Absolute Differences
• Matching Error
• Matching Cost
• Incorrect Matches
• Small Disparity
• Unique Constraints
• Pixel Intensity
• Pixel Of Interest
• Object Surface
• Grayscale
• Line Scan
• Occlusion
• SMP
• correlation