Quantitative evaluation of matching methods and validity measures for stereo vision
Data(s) |
01/07/2001
|
---|---|
Resumo |
The authors present a qualitative and quantitative comparison of various similarity measures that form the kernel of common area-based stereo-matching systems. The authors compare classical difference and correlation measures as well as nonparametric measures based on the rank and census transforms for a number of outdoor images. For robotic applications, important considerations include robustness to image defects such as intensity variation and noise, the number of false matches, and computational complexity. In the absence of ground truth data, the authors compare the matching techniques based on the percentage of matches that pass the left-right consistency test. The authors also evaluate the discriminatory power of several match validity measures that are reported in the literature for eliminating false matches and for estimating match confidence. For guidance applications, it is essential to have and estimate of confidence in the three-dimensional points generated by stereo vision. Finally, a new validity measure, the rank constraint, is introduced that is capable of resolving ambiguous matches for rank transform-based matching. |
Identificador | |
Publicador |
Sage Publications Ltd. |
Relação |
DOI:10.1177/02783640122067525 Banks, Jasmine & Corke, Peter (2001) Quantitative evaluation of matching methods and validity measures for stereo vision. The International Journal of Robotics Research, 20(7), pp. 512-532. |
Fonte |
School of Electrical Engineering & Computer Science; Science & Engineering Faculty |
Palavras-Chave | #080104 Computer Vision #080106 Image Processing #stereo vision #image matching #area-based matching #rank transform #census transform #match constraints |
Tipo |
Journal Article |