A hybrid approach for stereo disparity computation
| Autor: | F. Valentinotti, S. Taraglio |
|---|---|
| Rok vydání: | 1999 |
| Předmět: |
Phase difference
business.industry Computation Pattern recognition Hybrid approach Computer Science Applications Stereopsis Test case Hardware and Architecture Robustness (computer science) Gravitational singularity Computer Vision and Pattern Recognition Artificial intelligence business Software Mathematics |
| Zdroj: | Machine Vision and Applications. 11:161-170 |
| ISSN: | 1432-1769 0932-8092 |
| DOI: | 10.1007/s001380050099 |
| Popis: | An alternative, hybrid approach for disparity estimation, based on the phase difference technique, is presented. The proposed technique combines the robustness of the matching method with the sub-pixel accuracy of the phase difference approach. A matching between the phases of the left and right signals is introduced in order to allow the phase difference method to work in a reduced disparity range. In this framework, a new criterion to detect signal singularities is proposed. The presented test cases show that the performance of the proposed technique in terms of accuracy and density of the disparity estimates has greatly improved. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink