Polarimetric SAR Image Classification Using Deep Convolutional Neural Networks

• Published in: IEEE geoscience and remote sensing letters Vol. 13; no. 12; pp. 1935 - 1939
• Main Authors: Zhou, Yu, Wang, Haipeng, Xu, Feng, Jin, Ya-Qiu
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.12.2016; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Computer vision; Convolution; Data mining; Deep convolutional neural network; Deep water; Feature extraction; Image classification; Machine learning; Neural networks; Polarimetric radar; polarimetric synthetic aperture radar (POLSAR); Polarography; Radar imaging; Radar polarimetry; Remote sensing; SAR (radar); supervised classification; Synthetic aperture radar; Training; Vectors; Vegetation; Netherlands, Flevoland; USA, Calfornia, San Francisco; San Francisco California; Netherlands; United States > US
• ISSN: 1545-598X; 1558-0571
• DOI: 10.1109/LGRS.2016.2618840

Deep convolutional neural networks have achieved great success in computer vision and many other areas. They automatically extract translational-invariant spatial features and integrate with neural network-based classifier. This letter investigates the suitability and potential of deep convolutional neural network in supervised classification of polarimetric synthetic aperture radar (POLSAR) images. The multilooked POLSAR data in the format of coherency or covariance matrix is first converted into a normalized 6-D real feature vector. The six-channel real image is then fed into a four-layer convolutional neural network tailored for POLSAR classification. With two cascaded convolutional layers, the designed deep neural network can automatically learn hierarchical polarimetric spatial features from the data. Two experiments are presented using the AIRSAR data of San Francisco, CA, and Flevoland, The Netherlands. Classification result of the San Francisco case shows that slant built-up areas, which are conventionally mixed with vegetated area in polarimetric feature space, can now be successfully distinguished after taking into account spatial features. Quantitative analysis with respect to ground truth information available for the Flevoland test site shows that the proposed method achieves an accuracy of 92.46% in classifying the considered 15 classes. Such results are comparable with the state of the art.