zbMATH — the first resource for mathematics

Simultaneous object recognition and segmentation by image exploration. (English) Zbl 1098.68761
Pajdla, Tomáš (ed.) et al., Computer vision – ECCV 2004. 8th European conference on computer vision, Prague, Czech Republic, May 11–14, 2004. Proceedings, Part I. Berlin: Springer (ISBN 3-540-21984-6/pbk). Lecture Notes in Computer Science 3021, 40-54 (2004).
Summary: Methods based on local, viewpoint invariant features have proven capable of recognizing objects in spite of viewpoint changes, occlusion and clutter. However, these approaches fail when these factors are too strong, due to the limited repeatability and discriminative power of the features. As additional shortcomings, the objects need to be rigid and only their approximate location is found. We present a novel Object Recognition approach which overcomes these limitations. An initial set of feature correspondences is first generated. The method anchors on it and then gradually explores the surrounding area, trying to construct more and more matching features, increasingly farther from the initial ones. The resulting process covers the object with matches, and simultaneously separates the correct matches from the wrong ones. Hence, recognition and segmentation are achieved at the same time. Only very few correct initial matches suffice for reliable recognition. The experimental results demonstrate the stronger power of the presented method in dealing with extensive clutter, dominant occlusion, large scale and viewpoint changes. Moreover non-rigid deformations are explicitly taken into account, and the approximative contours of the object are produced. The approach can extend any viewpoint invariant feature extractor.
Online-only supplementary material: A few pages with all model images of our object database.
For the entire collection see [Zbl 1094.68003].

68T45 Machine vision and scene understanding
Full Text: DOI