DocumentCode :
1436516
Title :
A Quantitative Evaluation of Confidence Measures for Stereo Vision
Author :
Xiaoyan Hu ; Mordohai, P.
Author_Institution :
Dept. of Comput. Sci., Stevens Inst. of Technol., Hoboken, NJ, USA
Volume :
34
Issue :
11
fYear :
2012
Firstpage :
2121
Lastpage :
2133
Abstract :
We present an extensive evaluation of 17 confidence measures for stereo matching that compares the most widely used measures as well as several novel techniques proposed here. We begin by categorizing these methods according to which aspects of stereo cost estimation they take into account and then assess their strengths and weaknesses. The evaluation is conducted using a winner-take-all framework on binocular and multibaseline datasets with ground truth. It measures the capability of each confidence method to rank depth estimates according to their likelihood for being correct, to detect occluded pixels, and to generate low-error depth maps by selecting among multiple hypotheses for each pixel. Our work was motivated by the observation that such an evaluation is missing from the rapidly maturing stereo literature and that our findings would be helpful to researchers in binocular and multiview stereo.
Keywords :
costing; image matching; stereo image processing; binocular stereo; confidence measures; low-error depth maps; multiview stereo; quantitative evaluation; stereo cost estimation; stereo literature; stereo matching; stereo vision; Benchmark testing; Cost function; Error analysis; Estimation; Pattern matching; Reliability; Stereo image processing; 3D reconstruction; Stereo vision; confidence; correspondence; distinctiveness; Algorithms; Artificial Intelligence; Image Enhancement; Image Interpretation, Computer-Assisted; Imaging, Three-Dimensional; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity; Subtraction Technique;
fLanguage :
English
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publisher :
ieee
ISSN :
0162-8828
Type :
jour
DOI :
10.1109/TPAMI.2012.46
Filename :
6143951
Link To Document :
بازگشت