Object detection by global contour shape

8 years 9 months ago
Object detection by global contour shape
We present a method for object class detection in images based on global shape. A distance measure for elastic shape matching is derived, which is invariant to scale and rotation, and robust against non-parametric deformations. Starting from an over-segmentation of the image, the space of potential object boundaries is explored to find boundaries, which have high similarity with the shape template of the object class to be detected. An extensive experimental evaluation is presented. The approach achieves a remarkable detection rate of 83%-91% at 0.2 false positives per image on three challenging data sets. Key words: object category detection, contour matching, probabilistic shape distance, region grouping
Konrad Schindler, David Suter
Added 28 Dec 2010
Updated 28 Dec 2010
Type Journal
Year 2008
Where PR
Authors Konrad Schindler, David Suter
Comments (0)