Can Motion Segmentation Improve Patch-based Object Recognition?

Adrian Ulges; Thomas Breuel

In: Proceedings of the 20th International Conference on Pattern Recognition. International Conference on Pattern Recognition (ICPR-10), August 23-26, Istanbul, Turkey, IEEE, 2010.


Patch-based methods, which constitute the state of the art in object recognition, are often applied to video data, where motion information provides a valuable clue for separating objects of interest from the background. We show that such motion-based segmentation improves the robustness of patch-based recognition with respect to clutter. Our approach ­ which employs segmentation information to rule out incorrect correspondences between training and test views ­ is demonstrated to distinctly outperform baselines operating on unsegmented images. Relative improvements reach 50% for the recognition of specific objects, and 33% for object category retrieval.


paper.pdf (pdf, 441 KB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence