The gradient - A powerful and robust cost function for stereo matching
Authors:
- 1 November 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Abstract
Using gradient information for a pixel-based cost function for stereo matching has lacked adequate attention in the literature. This paper provides experimental evidence to show that the gradient as a data descriptor outperforms other pixel-based functions such as absolute differences and the Birchfield and Tomasi cost functions. The cost functions are tested against stereo image datasets where ground truth data is available. Furthermore, analysing the effect of the cost functions when exposure and illumination settings are different between the left and right camera is analysed. Not only has the performance of the cost functions been analysed, but also analysis into “why” one cost function is better than another. The analysis tests the global and spacial optimality of the cost function, showing that the gradient information returns stronger minima than the other two. These results are aimed at future research towards the design of a new smoothness prior that also depends on the characteristics of the employed cost function. This paper shows that the gradient is a simple, yet powerful, data descriptor that shows robustness to illumination and exposure differences, but is often overlooked by the stereo community.Keywords
This publication has 14 references indexed in Scilit:
- Evaluation of stereo confidence indoors and outdoors2010
- Residual Images Remove Illumination Artifacts!Lecture Notes in Computer Science, 2009
- A Methodology for Evaluating Illumination Artifact Removal for Corresponding ImagesLecture Notes in Computer Science, 2009
- Evaluation of Stereo Matching Costs on Images with Radiometric DifferencesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- New Robust Matching Cost Functions for Stereo Vision2007
- Evaluation of Cost Functions for Stereo Matching2007
- Efficient Belief Propagation for Early VisionInternational Journal of Computer Vision, 2006
- Segment-Based Stereo Matching Using Belief Propagation and a Self-Adapting Dissimilarity Measure2006
- Accurate and Efficient Stereo Processing by Semi-Global Matching and Mutual Information2005
- Non-parametric local transforms for computing visual correspondence1994