Evaluation of disparity maps
Main Article Content
A disparity map is the output of a stereo correspondence algorithm. It is estimated in an intermediate step of a 3D information recovery process, from two or more images. A performance assessment of stereo correspondence algorithms may be addressed by a quantitative comparison of estimated disparity maps against ground-truth data. This assessment requires of the use of a methodology, which involves several evaluation elements and methods. Some elements and methods have been discussed with more attention than others in the literature. In the one hand, the quantity of used images and their relation to the application domain are topics rising large debate. On the other hand, there exist few publications on evaluation measures and error criteria. In practice, contradictory evaluation results may be obtained if different error measures are used, even on a same test-bed. In this paper, an evaluation methodology for stereo correspondence algorithms is presented. In contrast to conventional methodologies, it allows an interactive selection of multiple evaluation elements and methods. Moreover, it is based on a formal definition of error criteria based on set partitions. Experimental evaluation results showed that the proposed methodology allows a better understanding and analysis of algorithms performance than the Middlebury methodology. Final remarks highlights the relevance of discussing on the different elements and methods involved in an evaluation process.
- María Trujillo, An overview on the standard of digital video broadcasting – terrestrial , Ingeniería y Competitividad: Vol. 15 No. 1 (2013): Ingeniería y Competitividad
- Marta Millán, Maria Trujillo, Daniel Valencia, An architecture for semantic integration of data and medical images , Ingeniería y Competitividad: Vol. 16 No. 2 (2014)
Authors grant the journal and Universidad del Valle the economic rights over accepted manuscripts, but may make any reuse they deem appropriate for professional, educational, academic or scientific reasons, in accordance with the terms of the license granted by the journal to all its articles.
Articles will be published under the Creative Commons 4.0 BY-NC-SA licence (Attribution-NonCommercial-ShareAlike).