5 January 1989 Local Parallel Models For Integration Of Stereo Matching Constraints And Intrinsic Image Combination
Author Affiliations +
Proceedings Volume 1003, Sensor Fusion: Spatial Reasoning and Scene Interpretation; (1989) https://doi.org/10.1117/12.948929
Event: 1988 Cambridge Symposium on Advances in Intelligent Robotics Systems, 1988, Boston, MA, United States
Parallel relaxation computations such as those of connectionist networks offer a useful model for constraint integration and intrinsic image combination in developing a general-purpose stereo matching algorithm. This paper describes such a stereo algorithm that incorporates hierarchical, surface structure and edge appearance constraints that are redefined and are integrated at the level of individual candidate matches. The algorithm produced a high percentage of correct decisions on a wide-variety of stereo pairs. Its few errors arose when the correlation measures defined by the constraints were either weakened, or ambiguous, as in the case of periodic patterns in the images. Two additional mechanisms are discussed for overcoming the remaining errors. First, an independent estimate of disparity, obtained through a depth-from-focus algorithm, can resolve the ambiguity in periodic regions. Second, a third image, taken from a position above the left image, is incorporated into matching. This is accomplished by defining matches between the new image and the left image, and relating the new and old matches through new constraints. Both of the new approaches are easily easily incorporated into the connectionist network computations of the original algorithm.
© (1989) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Charles V. Stewart, Charles V. Stewart, } "Local Parallel Models For Integration Of Stereo Matching Constraints And Intrinsic Image Combination", Proc. SPIE 1003, Sensor Fusion: Spatial Reasoning and Scene Interpretation, (5 January 1989); doi: 10.1117/12.948929; https://doi.org/10.1117/12.948929


Dynamic image fusion and general observer preference
Proceedings of SPIE (April 28 2010)
New Results in Automatic Focusing and a New Method for...
Proceedings of SPIE (February 28 1990)
Trinocular Stereo: Theoretical Advantages and a New Algorithm
Proceedings of SPIE (February 28 1990)
Optical flow techniques for moving target detection
Proceedings of SPIE (March 31 1991)
Multiresolution range-guided stereo matching
Proceedings of SPIE (March 31 1991)
Multilevel fusion using enhanced feature detection
Proceedings of SPIE (May 24 2005)

Back to Top