Compact Deep Color Features for Remote Sensing Scene Classification
Open Access
- 27 February 2021
- journal article
- research article
- Published by Springer Nature in Neural Processing Letters
- Vol. 53 (2) , 1523-1544
Abstract
Aerial scene classification is a challenging problem in understanding high-resolution remote sensing images. Most recent aerial scene classification approaches are based on Convolutional Neural Networks (CNNs). These CNN models are trained on a large amount of labeled data and the de facto practice is to use RGB patches as input to the networks. However, the importance of color within the deep learning framework is yet to be investigated for aerial scene classification. In this work, we investigate the fusion of several deep color models, trained using color representations, for aerial scene classification. We show that combining several deep color models significantly improves the recognition performance compared to using the RGB network alone. This improvement in classification performance is, however, achieved at the cost of a high-dimensional final image representation. We propose to use an information theoretic compression approach to counter this issue, leading to a compact deep color feature set without any significant loss in accuracy. Comprehensive experiments are performed on five remote sensing scene classification benchmarks: UC-Merced with 21 scene classes, WHU-RS19 with 19 scene types, RSSCN7 with 7 categories, AID with 30 aerial scene classes, and NWPU-RESISC45 with 45 categories. Our results clearly demonstrate that the fusion of deep color features always improves the overall classification performance compared to the standard RGB deep features. On the large-scale NWPU-RESISC45 dataset, our deep color features provide a significant absolute gain of 4.3% over the standard RGB deep features.Keywords
Funding Information
- Aalto University
This publication has 45 references indexed in Scilit:
- Image Super-Resolution Using Deep Convolutional NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Compact color–texture description for texture classificationPattern Recognition Letters, 2015
- Features, Color Spaces, and Boosting: New Insights on Semantic Classification of Remote Sensing ImagesIEEE Transactions on Geoscience and Remote Sensing, 2014
- Evaluation of second-order visual features for land-use classification2014
- Return of the Devil in the Details: Delving Deep into Convolutional Nets2014
- A Hierarchical Scheme of Multiple Feature Fusion for High-Resolution Satellite Scene Categorization2013
- Modulating Shape Features by Color Attention for Object RecognitionInternational Journal of Computer Vision, 2011
- Learning Photometric Invariance for Object DetectionInternational Journal of Computer Vision, 2010
- Group Theoretical Structure of Spectral SpacesJournal of Mathematical Imaging and Vision, 2005
- Color invarianceIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001