DocumentCode :
3330292
Title :
Alignment by maximization of mutual information
Author :
Viola, Paul ; Wells, William M., III
Author_Institution :
Artificial Intelligence Lab., MIT, Cambridge, MA, USA
fYear :
1995
fDate :
20-23 Jun 1995
Firstpage :
16
Lastpage :
23
Abstract :
A new information-theoretic approach is presented for finding the pose of an object in an image. The technique does not require information about the surface properties of the object, besides its shape, and is robust with respect to variations of illumination. In our derivation, few assumptions are made about the nature of the imaging process. As a result, the algorithms are quite general and can foreseeably be used in a wide variety of imaging situations. Experiments are presented that demonstrate the approach in registering magnetic resonance images, aligning a complex 3D object model to real scenes including clutter and occlusion, tracking a human head in a video sequence and aligning a view-based 2D object model to real images. The method is based on a formulation of the mutual information between the model and the image. As applied in this paper, the technique is intensity-based, rather than feature-based. It works well in domains where edge or gradient-magnitude based methods have difficulty, yet it is more robust then traditional correlation. Additionally, it has an efficient implementation that is based on stochastic approximation
Keywords :
biomedical NMR; clutter; computer vision; image sequences; information theory; lighting; medical image processing; optimisation; tracking; clutter; complex 3D object model alignment; human head tracking; illumination variations; imaging process; information-theoretic approach; intensity-based technique; magnetic resonance image registration; mutual information maximization; object pose; occlusion; shape; stochastic approximation; video sequence; view-based 2D object model alignment; Humans; Layout; Lighting; Magnetic heads; Magnetic resonance; Magnetic resonance imaging; Mutual information; Robustness; Shape; Video sequences;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision, 1995. Proceedings., Fifth International Conference on
Conference_Location :
Cambridge, MA
Print_ISBN :
0-8186-7042-8
Type :
conf
DOI :
10.1109/ICCV.1995.466930
Filename :
466930
Link To Document :
بازگشت