Experiments with segment-based stereo using dynamic programmingFunded under: JRC-INDHAZ 2C
This paper addresses the problem of depth recovery using stereo analysis. The system described uses segments as features to be matched. A segment is defined as a group of connected edge points in the image, detected using the Marr-Hildreth technique. The identification of corresponding segments in the two images is obtained by a dynamic programming based algorithm. After the detection phase each edge is described symbolically in terms of a list of attributes. The symbolic descriptions of the stereo pair are used for computing a correspondence cost for each candidate pair analysed. Only a subset of all possible matches in the feature space is considered. The set of matched pairs making the solution is given by the minimal cost path in the feature space. The output of the program is a disparity map of the scene. The system has performed satisfactorily on a set of laboratory scenes. Experimental results are presented and discussed.
Bibliographic Reference: Paper presented: Primo Congresso della Associazione Italiana per l'Intelligenza Artificiale, Trento (IT), Nov. 8-10, 1989
Availability: Available from (1) as Paper EN 35033 ORA
Record Number: 198911219 / Last updated on: 1994-12-01
Original language: en
Available languages: en