A new method of identifying occlusion and specular highlights using active vision

Occlusion and specular highlights are two fundamental problems in 3D computer vision. Their presence complicates the process of camera vergence, stereo matching and 3D reconstruction. The paper presents a new method of identifying occlusion and specular highlights using active vision. In the method, active camera movement is employed not in solving stereo correspondences, but to help in the identification of occlusion and specular highlights during vergence. The early identification facilitates the acquisition of well-posed stereo images and hence simplifies the subsequent task of stereo correspondences and the recovery of 3D scene information