Acquisition of three-dimensional information of a real-world scene from two-dimensional images has been one of the most important issues in computer vision and image understanding in the last two decades. Noncontact range acquisition techniques can be essentially classified into two classes: Passive and active. This paper concentrates on passive depth extraction techniques which have the advantage that 3-D information can be obtained without affecting the scene. Passive range sensing techniques are often referred to as shape-from-x, where x is one of visual cues such as shading, texture, contour, focus, stereo, and motion. These techniques produce 2.5-D representations of visible surfaces. This survey discusses aspects of this research field and reviews some recent advances including video-rate range imaging sensors as well as emerging themes and applications.

This paper proposes robust algorithms for linebased pose enumeration from a single view, and it reports on their evaluations by simulations. The proposed algorithms incorporate two major refinements into the algorithms originally proposed by Shakunaga [1]. The first refinement, introduction of zone-crossing detection to the 1-d search remarkably decreases the rate of overlooking a correct pose. The second refinement, adaptive selection of a PAT pair considerably reduces the average estimation error. Simulation results show that pose estimation precision depends primarily on the precision of line detection. Although the refinements are widely effective, they are more effective for more precise line detection. For 99% of rigid body samples, the algorithm can estimate rotation with an error of less than 2 degrees, and for 99.9% of the samples, the error is less than 10 degrees. Simulation experiments for articulated objects show similar results by using the second algorithm. The effectiveness of the algorithms is verified in an alignment approach by simulations.

The present paper reports a robust projection onto eigenspace that is based on iterative projection. The fundamental method proposed in Shakunaga and Sakaue and involves iterative analysis of relative residual and projection. The present paper refines the projection method by solving linear equations while taking noise ratio into account. The refinement improves both the efficiency and robustness of the projection. Experimental results indicate that the proposed method works well for various kinds of noise, including shadows, reflections and occlusions. The proposed method can be applied to a wide variety of computer vision problems, which include object/face recognition and image-based rendering.