Probabilistic regularisation and symmetry in binocular dynamic programming stereo
Pattern Recognition Letters - In memory of Professor E.S. Gelsema
Stereo Matching Using Belief Propagation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hi-index | 0.00 |
Digital photogrammetric processing of aerial and space stereo images acquired with CCD-line scanners is widely used in today's remote sensing, surveying, and mapping of the Earth's surface. Because of considerable geometric distortions due to movements of a scanner platform, the acquired images have to be corrected before processing. A conventional approach consists of sequential correction and terrain reconstruction stages. Its main drawback is that the former stage loses calibration information for restoring terrain model in a world co-ordinate frame, so that an extra processing is necessary to restore this information. We propose a more flexible approach iteratively combining both the stages. Experiments confirm that such processing holds much promise for photogrammetric processing of the line scanner stereo images.