Scene Classification of Remote Sensing Image Based on Multi-scale Feature and Deep Neural Network

• Main Authors: XU Suhui, MU Xiaodong, ZHAO Peng, MA Ji
• Format: Article
• Language: zho
• Published: Surveying and Mapping Press 2016-07-01
• Series: Acta Geodaetica et Cartographica Sinica
• Subjects: remote sensing image; scene classification; deep convolutional neural network; nonsubsampled Contourlet transform; multiple-kernel support vector machine
• Online Access: http://html.rhhz.net/CHXB/html/2016-7-834.htm
• ISSN: 1001-1595; 1001-1595

Aiming at low precision of remote sensing image scene classification owing to small sample sizes, a new classification approach is proposed based on multi-scale deep convolutional neural network (MS-DCNN), which is composed of nonsubsampled Contourlet transform (NSCT), deep convolutional neural network (DCNN), and multiple-kernel support vector machine (MKSVM). Firstly, remote sensing image multi-scale decomposition is conducted via NSCT. Secondly, the decomposing high frequency and low frequency subbands are trained by DCNN to obtain image features in different scales. Finally, MKSVM is adopted to integrate multi-scale image features and implement remote sensing image scene classification. The experiment results in the standard image classification data sets indicate that the proposed approach obtains great classification effect due to combining the recognition superiority to different scenes of low frequency and high frequency subbands.