caa a22 4500 467914311 CHVBK 20180406152857.0 cr unu---uuuuu 170328e20060901xx s 000 0 eng 10.1007/s11263-006-7067-x doi (NATIONALLICENCE)springer-10.1007/s11263-006-7067-x Robust Tracking Using Foreground-Background Texture Discrimination [Elektronische Daten] [Hieu Nguyen, Arnold Smeulders] This paper conceives of tracking as the developing distinction of a foreground against the background. In this manner, fast changes in the object or background appearance can be dealt with. When modelling the target alone (and not its distinction from the background), changes of lighting or changes of viewpoint can invalidate the internal target model. As the main contribution, we propose a new model for the detection of the target using foreground/background texture discrimination. The background is represented as a set of texture patterns. During tracking, the algorithm maintains a set of discriminant functions each distinguishing one pattern in the object region from background patterns in the neighborhood of the object. The idea is to train the foreground/background discrimination dynamically, that is while the tracking develops. In our case, the discriminant functions are efficiently trained online using a differential version of Linear Discriminant Analysis (LDA). Object detection is performed by maximizing the sum of all discriminant functions. The method employs two complementary sources of information: it searches for the image region similar to the target object, and simultaneously it seeks to avoid background patterns seen before. The detection result is therefore less sensitive to sudden changes in the appearance of the object than in methods relying solely on similarity to the target. The experiments show robust performance under severe changes of viewpoint or abrupt changes of lighting. Springer Science + Business Media, LLC, 2006 visual tracking nationallicence foreground/background discrimination nationallicence texture nationallicence linear discriminant analysis nationallicence Nguyen Hieu Department of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute, 12180, NY, USA aut Smeulders Arnold Department of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute, 12180, NY, USA aut International Journal of Computer Vision Kluwer Academic Publishers 69/3(2006-09-01), 277-293 0920-5691 69:3<277 2006 69 11263 https://doi.org/10.1007/s11263-006-7067-x text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s11263-006-7067-x text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Nguyen Hieu Department of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute, 12180, NY, USA aut NATIONALLICENCE 700 1- Smeulders Arnold Department of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute, 12180, NY, USA aut NATIONALLICENCE 773 0- International Journal of Computer Vision Kluwer Academic Publishers 69/3(2006-09-01), 277-293 0920-5691 69:3<277 2006 69 11263 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer