New algorithms from reconstruction of a 3-D depth map from one or more images

Algorithms are developed to recover the depth and orientation maps of a surface from its image intensities. They combine the advantages of stereo vision and shape-from-shading (SFS) methods. These algorithms generate dense surface depth and orientation maps accurately and unambiguously. Previous SFS algorithms can not be directly extended to combine stereo images because the recovery of surface depth and that of orientation are separated in these formulations. A novel SFS algorithm is proposed to couple the generation of the depth and orientation maps. The formulation also ensures that the reconstructed surface depth and its orientation are consistent. The SFS algorithm for a single image is next extended to utilize stereo images. The correspondence over stereo images is established simultaneously with the generation of surface depth and orientation. An alternative approach is also suggested from combining stereo and SFS techniques. The use of embedding techniques to combine sparse depth measurements is discussed