Search

In this paper, stereo image reconstruction using regular- ized adaptive disparity estimation is proposed. That is, by adaptively predicting the mutual correlation between stereo images pair using the proposed algorithm, the bandwidth of stereo input images pair can be compressed to the level of a conventional 2D image and a predicted image also can be effectively reconstructed using a refer- ence image and disparity vectors. Especially, in the proposed algo- rithm, the first feature values are extracted from the input stereo images pair. Then, a matching window for stereo matching is adap- tively selected depending on the magnitude of these feature values. That is, for the region having larger feature values, a smaller match- ing window is selected, while, for the opposite case, a larger match- ing window is selected by comparing predetermined threshold val- ues. This approach is not only able to reduce a mismatching of disparity vectors, which occurs in the conventional dense disparity estimation with a small matching window, but is also able to reduce blocking effects that occur in the coarse disparity estimation with a large matching window. In addition, in this paper, a new regularized adaptive disparity estimation technique is proposed. That is, by regularizing the estimated disparity vector with the neighboring dis- parity vectors, problems of the conventional adaptive disparity esti- mation scheme might be solved, and the predicted stereo image can be more effectively reconstructed. From experiments using stereo sequences of "Man", "Fichier", "Manege", and "Tunnel", it is shown that the proposed algorithm improves the PSNRs of a reconstructed image to about 6.90 dB on average at ±30 search ranges as com- pared to those of conventional algorithms. Also, it is found that there is almost no difference between an original image and a recon- structed image through the proposed algorithm by comparison to that of conventional algorithms. © 2007 SPIE and