Experimental Combination of Intensity and Stereo Edges for Improved Snake Segmentation

By Danijela Markovic and Margrit Gelautz

Abstract

In this paper, we present an algorithm to combine edge information from stereo-derived depth maps with edges from the original intensity/color image to improve the contour detection in images of natural scenes. After computing the disparity map, we generate a so-called "Edge Combination image", which relies on those edges of the original image that are also present in the stereo map. We describe an algorithm to identify corresponding intensity and depth edges, which are usually not perfectly aligned due to errors in the stereo reconstruction. Our experiments show that proposed Edge Combination approach can improve significantly the segmentation results of an Active Contour algorithm.

Reference

D. Markovic, M. Gelautz: "Experimental Combination of Intensity and Stereo Edges for Improved Snake Segmentation"; in: "7th International Conference on PATTERN RECOGNITION and IMAGE ANALYSIS: NEW INFORMATION TECHNOLOGIES", Association for Pattern Recognition and Image Analysis of the Russian Federation, 2004, 310 - 313.

BibTeX

@incollection{TUW-138922,     author = {Markovic, Danijela and Gelautz, Margrit},     title = {Experimental Combination of Intensity and Stereo Edges for Improved Snake Segmentation},     booktitle = {7th International Conference on PATTERN RECOGNITION and IMAGE ANALYSIS: NEW INFORMATION TECHNOLOGIES},     year = {2004},     pages = {310--313},     publisher = {Association for Pattern Recognition and Image Analysis of the Russian Federation},     url = {http://www.ims.tuwien.ac.at/media/documents/publications/ECL_PRIA_2004.doc} } Click into the text area and press Ctrl+A/Ctrl+C or ⌘+A/⌘+C to copy the BibTeX into your clipboard… or download the BibTeX.