Adaptive descriptor-based robust stereo matching under radiometric changes

• An effective matching scheme for robust stereo matching under various radiometric changes.
• A content adaptive descriptor-based approach to effectively reflect image contents.
• Entropy-based energy function guiding for weighting the elements of the descriptor.
• Outperforming the state-of-art algorithms by improving around 16.5% bad pixel displacements.
• It is robust to radiometric changes and can be applicable to outdoor applications.

In a real stereo vision system, the acquired stereo images suffer from varying radiometric changes due to illumination and camera parameter changes. Therefore, we propose an effective matching scheme created by building a content adaptive descriptor. Specifically, the descriptor reflects image contents and its element are adaptively weighted and applied to estimate the correct corresponding pixels based on the entropy energy function even under radiometric changes. For the performance evaluation, the proposed scheme is compared with the state-of-art algorithm using Middlebury and KITTI Vision stereo datasets that have radiometric changes. Specifically, 24 of 71 indoor image pairs in the Middlebury and 3 of 7 outdoor pairs are selected, respectively. Experimental result shows that the proposed method reports 6.23% bad pixel matching on average, but it outperforms state-of-the-art algorithms by reducing around 2% bad pixel matching error, which achieves about 16.5% performance improvement.