Occlusion detection is an important problem in 3D computer vision which uses multiple views, such as stereo vision. The presence of occlusion complicates the problem of vergence and the subsequent stereo matching in the generation of 3D data. This paper presents an approach which detects the presence of occlusion concurrently during the vergence process. The main limitation of the approach where the maximum correlation coefficient can be very high even when a significant amount of occlusions is present in the stereo images is shown. This paper presents an adaptive method of adjusting the correlation threshold with respect to the contrast-levels of the image being analyzed to alleviate this limitation. The proposed adaptive threshold method ensures that the sensitivity of detecting mismatches is less dependent upon the contrast-levels of the image being analyzed. The computational advantage of the proposed adaptive threshold method over the fixed threshold method is also presented. Experimental results which show the strengths of the proposed adaptive threshold method over the fixed threshold method on real scenes are given.

The authors describe an exploratory vergence method which has the ability to detect occlusion and specular highlights using information that is inherent in the vergence process. They propose an active exploratory vergence method based on concurrent cross-correlation of multi-scale stereo images. This method is capable of detecting occlusion and specular highlights concurrently during the vergence process. It not only improves computational efficiency but also leads to the exploration of a better viewing direction and position that overcome the problem created by occlusion and specular highlights. An efficient parallel implementation of the multi-scale cross-correlation algorithm is also described. The robustness of the proposed method against occlusion and specular highlights is demonstrated.>