A measure for accuracy disparity maps evaluation
CIARP'11 Proceedings of the 16th Iberoamerican Congress conference on Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications
| Hi-index | 0.00 |
In this paper, we present a novel objective approach to evaluate the disparity map quality. The two indices which are disparity gradient and disparity acceleration are first proposed for the evaluation of the disparity map. These two indices are under the assumption that the disparity map should be smooth in the natural scene. The joint application of the two indices guarantees the effective and reliable evaluation. The experimental results demonstrate the perfect performance of the proposed approach especially under certain noise levels.