Application of Multi-Channel Hough Transform to Stereo Vision

摘要

A major issue in any stereo vision system is the correspondence problem. In this report a feature-based stereo vision technique is described where curve-segments are used as the feature primitives in the matching process. The local characteristics of the curve-segments are extracted by the Generalized Hough Transform (R-table) representation of the curve-segment. The left image and the right image are first filtered by using several Laplacian of a Gaussian operator of different widths (channels). Curve-segments are extracted by a tracking algorithm and their centroids are obtained. At each channel the Generalized Hough Transform of each curve-segment in the left and the right image is evaluated. This is done by calculating the R-table representation of each curve-segment using the centroid of the curve-segment as the reference point. The R-table, is used as a local feature vector in representing the distinctive characteristics of the curve-segment. Initial node assignments are formed between the left curve-segments and the right curve-segments if they satisfy the epipolar constraint and their R-tables satisfy a similarity measure. The epipolar constraint on the centroids of the curve-segment and the channel size is used to limit the searching space in the right image. (RH)