DocumentCode :
63593
Title :
Pyramid of Spatial Relatons for Scene-Level Land Use Classification
Author :
Shizhi Chen ; YingLi Tian
Author_Institution :
City Coll. of New York, City Univ. of New York, New York, NY, USA
Volume :
53
Issue :
4
fYear :
2015
fDate :
Apr-15
Firstpage :
1947
Lastpage :
1957
Abstract :
Local feature with bag-of-words (BOW) representation has become one of the most popular approaches in object classification and image retrieval applications in the computer vision community. The recent efforts in the remote sensing community have demonstrated that the BOW approach can also effectively apply to geographic images for the applications of classification and retrieval. However, the BOW representation discards spatial information, which is critical for the remotely sensed land use classification. Several algorithms have incorporated spatial information into the BOW representation by hard encoding coordinates of local features. Such rigid spatial encoding is not robust to translation and rotation variations, which are common characteristics of geographic images. To effectively incorporate spatial information into the BOW model for the land use classification, we propose a pyramid-of-spatial-relatons (PSR) model to capture both absolute and relative spatial relationships of local features. Unlike the conventional cooccurrence approach to describe pairwise spatial relationships between local features, the PSR model employs a novel concept of spatial relation to describe relative spatial relationship of a group of local features. As the result, the storage cost of the PSR model only linearly increases with the visual word codebook size instead of the quadratic relationship as in the cooccurrence approach. The PSR model is robust to translation and rotation variations and demonstrates excellent performance for the application of remotely sensed land use classification. On the Land Use and Land Cover image database, the PSR achieves 8% higher in the classification accuracy than the state of the art. If using only gray images, it outperforms the state of the art by more than 11%.
Keywords :
data structures; geophysical image processing; image classification; land use; remote sensing; BOW model; Land Use and Land Cover image database; absolute spatial relationships; bag of words representation; computer vision; geographic images; image classification; image retrieval applications; local features; object classification; pyramid of spatial relatons model; relative spatial relationships; remotely sensed land use classification; scene level land use classification; spatial information; visual word codebook size; Accuracy; Computational modeling; Computer vision; Encoding; Histograms; Remote sensing; Visualization; Bag of words (BOW); geographical image classification; land use classification; pyramid of spatial relatons (PSR); spatial pyramid matching (SPM);
fLanguage :
English
Journal_Title :
Geoscience and Remote Sensing, IEEE Transactions on
Publisher :
ieee
ISSN :
0196-2892
Type :
jour
DOI :
10.1109/TGRS.2014.2351395
Filename :
6895132
Link To Document :
بازگشت