Title :
Modeling object classes in aerial images using texture motifs
Author :
Bhagavathy, Sitaram ; Newsam, Shawn ; Manjunath, B.S.
Author_Institution :
Dept. of Electr. & Comput. Eng., California Univ., Santa Barbara, CA, USA
Abstract :
We propose a canonical model for object classes in aerial images. This model is motivated by the observation that geographic regions of interest are characterized by collections of texture motifs corresponding to the geographic processes that generate them. We show that this model is effective in learning the common texture themes, or motifs, of the object classes.
Keywords :
Gaussian distribution; image classification; image retrieval; image texture; object recognition; terrain mapping; aerial images; canonical model; common texture themes; geographic regions of interest; image feature distributions; mixed Gaussian distributions; object class modeling; remotely sensed imagery; texture motifs; Airports; Character generation; Content based retrieval; Gaussian distribution; Gaussian processes; Image analysis; Image retrieval; Image segmentation; Image texture analysis; Information retrieval;
Conference_Titel :
Pattern Recognition, 2002. Proceedings. 16th International Conference on
Print_ISBN :
0-7695-1695-X
DOI :
10.1109/ICPR.2002.1048470