Matching Deformable Features Based on Oriented Multi-scale Filter Banks
This paper presents a technique to enable deformable objects to be matched throughout video sequences based on the information provided by multi-scale Gaussian derivative filter banks. We show that this technique is robust enough for viewpoint changes, lighting changes, large motions of the matched object and small changes in rotation and scale. Unlike other well-known color-based techniques, this technique only uses the gray level values of the image. The proposed algorithm is mainly based on the definition of a particular multi-scale template model and a similarity measure for template matching. The matching approach has been tested on video sequences acquired with a conventional webcam showing a promising behavior with this kind of low-quality images.
KeywordsVideo Sequence Object Recognition Target Image Deformable Object Yellow Circle
Unable to display preview. Download preview PDF.
- 1.Agarwal, S., Awan, A., Roth, D.: Learning to detect objects in images via a sparse, part-based representation. IEEE PAMI 26(11), 1475–1490 (2004)Google Scholar
- 2.Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: IEEE CVPR 2003, February 2003, vol. 2, pp. 264–271 (2003)Google Scholar
- 6.Leibe, B.: Interleaved Object Categorization and Segmentation. PhD thesis, ETH Zurich (October 2004)Google Scholar
- 11.Serre, T., Wolf, L., Poggio, T.: Object recognition with features inspired by visual cortex. In: IEEE CSC on CVPR (June 2005)Google Scholar
- 13.Varma, M., Zisserman, A.: Unifying statistical texture classification frameworks. Image and Vision Computing 22(14), 1175–1183 (2005)Google Scholar
- 14.Yokono, J.J., Poggio, T.: Oriented filters for object recognition: an empirical study. In: Proc. of the Sixth IEEE FGR (May 2004)Google Scholar