Robust Approach for Disparity Map Estimation Based on Multilevel Decomposition

A novel approach for dense disparity map (DM) estimation is designed. The proposed frameworks include together processing of stereo pairs using the following blocks: CIEL∗a∗b∗ color space conversion, stereo matching via multilevel scheme, employing Normalized Cross-Correlation or Structural Similarity Index Measure, color segmentation by k-means on a∗b∗ color plane, and adaptive post-filtering. The Bad Matching Pixels and Structural Similarity Index Measure criteria are applied in order to compare the performance of the proposed approach against state-of-the-art techniques. Two designed frameworks appear outperform existing state-of-the-art techniques in terms of objective criteria as well as in subjective visual perception.