Unsupervised Feature Learning for Aerial Scene Classification
- 7 March 2013
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 52 (1), 439-451
- https://doi.org/10.1109/tgrs.2013.2241444
Abstract
The rich data provided by high-resolution satellite imagery allow us to directly model aerial scenes by understanding their spatial and structural patterns. While pixel- and object-based classification approaches are widely used for satellite image analysis, often these approaches exploit the high-fidelity image data in a limited way. In this paper, we explore an unsupervised feature learning approach for scene classification. Dense low-level feature descriptors are extracted to characterize the local spatial patterns. These unlabeled feature measurements are exploited in a novel way to learn a set of basis functions. The low-level feature descriptors are encoded in terms of the basis functions to generate new sparse representation for the feature descriptors. We show that the statistics generated from the sparse features characterize the scene well producing excellent classification accuracy. We apply our technique to several challenging aerial scene data sets: ORNL-I data set consisting of 1-m spatial resolution satellite imagery with diverse sensor and scene characteristics representing five land-use categories, UCMERCED data set representing twenty one different aerial scene categories with sub-meter resolution, and ORNL-II data set for large-facility scene detection. Our results are highly promising and, on the UCMERCED data set we outperform the previous best results. We demonstrate that the proposed aerial scene classification method can be highly effective in developing a detection system that can be used to automatically scan large-scale high-resolution satellite imagery for detecting large facilities such as a shopping mall.Keywords
This publication has 25 references indexed in Scilit:
- Spatial pyramid co-occurrence for image classificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Unsupervised Semantic Labeling Framework for Identification of Complex Facilities in High-Resolution Remote Sensing ImagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- A Hierarchical and Contextual Model for Aerial Image ParsingInternational Journal of Computer Vision, 2009
- Semantic Annotation of Satellite Images Using Latent Dirichlet AllocationIEEE Geoscience and Remote Sensing Letters, 2009
- Classification and Extraction of Spatial Features in Urban Areas Using High-Resolution Multispectral ImageryIEEE Geoscience and Remote Sensing Letters, 2007
- A Multilevel Context-Based System for Classification of Very High Spatial Resolution ImagesIEEE Transactions on Geoscience and Remote Sensing, 2006
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene CategoriesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Classifying land development in high-resolution panchromatic satellite images using straight-line statisticsIEEE Transactions on Geoscience and Remote Sensing, 2004
- A comparison of methods for multiclass support vector machinesIEEE Transactions on Neural Networks, 2002
- Object recognition from local scale-invariant featuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999