Stereo matching algorithm based on the combination of matching costs
| Autor: | Zhu Yalong, Li Yijun, Wang Ende, Peng Liangyu, Wu Tianyao |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Matching (statistics)
Pixel Computer science ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 020207 software engineering 02 engineering and technology Absolute difference Function (mathematics) Computer Science::Computer Vision and Pattern Recognition Pattern recognition (psychology) 0202 electrical engineering electronic engineering information engineering Range (statistics) 020201 artificial intelligence & image processing Sensitivity (control systems) Algorithm Blossom algorithm ComputingMethodologies_COMPUTERGRAPHICS |
| Zdroj: | 2017 IEEE 7th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER). |
| DOI: | 10.1109/cyber.2017.8446444 |
| Popis: | Aiming at solving the problem of low accuracy of weak texture region and disparity discontinuous region and sensitivity to illumination caused by existing local stereo matching algorithm, a new stereo matching algorithm based on the combination of Sum of Absolute Difference algorithm and Absolute Difference of Gradient algorithm is presented here. Using the average of the pixels in the disparity range to apply adaptive weight to the SAD part. The new algorithm can adaptively adjust each part of the cost function in the proportion of the total cost function according to the different texture, illumination characteristics of image. Moreover, we use the semiglobal matching algorithm to calculate the cost of 8 directions, to carry out optimized processing on disparity image, finally a dense disparity map is obtained. The experimental results shows that the proposed method not only improve accuracy of stereo matching, but also has well results in weak texture region and disparity discontinuous region. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|