Abstract: "Sensing 3-D shape and motion is an important problem in autonomous navigation and manipulation. Stereo vision is an attractive approach to this problem in several domains. We address fundamental components of this problem by using stereo vision to estimate the 3-D structure or '...

Ausführliche Beschreibung

Bibliographische Detailangaben

1. Verfasser:	Matthies, Larry (VerfasserIn)
Format:	Buch
Sprache:	English
Veröffentlicht:	Pittsburgh, Pa. 1989
Schriftenreihe:	Carnegie-Mellon University <Pittsburgh, Pa.> / Computer Science Department: CMU-CS 89,195
Schlagworte:	Robot vision Hochschulschrift
Zusammenfassung:	Abstract: "Sensing 3-D shape and motion is an important problem in autonomous navigation and manipulation. Stereo vision is an attractive approach to this problem in several domains. We address fundamental components of this problem by using stereo vision to estimate the 3-D structure or 'depth' of objects visible to a robot, as well as to estimate the motion of the robot as it travels through an unknown environment. We begin by using cameras on-board a robot vehicle to estimate the motion of the vehicle by tracking 3-D feature-points or 'landmarks'. We formulate this task as a statistical estimation problem, develop sequential methods for estimating the vehicle motion and updating the landmark model, and implement a system that successfully tracks landmarks through stereo image sequences In laboratory experiments, this system has achieved an accuracy of 2% of distance over 5.5 meters and 55 stereo image pairs. These results establish the importance of statistical modelling in this problem and demonstrate the feasibility of visual motion estimation in unknown environments. This work embodies a successful paradigm for feature-based depth and motion estimation, but the feature-based approach results in a very limited 3-D model of the environment. To extend this aspect of the system, we address the problem of estimating 'depth maps' from stereo images. Depth maps specify scene depth for each pixel in the image. We propose a system architecture in which exploratory camera motion is used to acquire a narrow-baseline image pair by moving one camera of the stereo system Depth estimates obtained from this image pair are used to 'bootstrap' matching of a wide-baseline image pair acquired with both cameras of the stereo system. We formulate the bootstrap operation statistically by modelling depth maps as random fields and developing Bayesian matching algorithms in which depth information from the narrow-baseline image pair forms the prior density for matching the wide baseline image pair. This leads to efficient, area-based matching algorithms that are applied independently for each pixel or each scanline of the image. Experimental results with scale models of complex, outdoor scenes demonstrate the power of the approach.
Beschreibung:	Pittsburgh, Pa., Carnegie-Mellon Univ., Diss.
Beschreibung:	VII, 161 S. Ill., graph. Darst.