21 July 2017 Deep feature extraction and combination for remote sensing image classification based on pre-trained CNN models
Author Affiliations +
Proceedings Volume 10420, Ninth International Conference on Digital Image Processing (ICDIP 2017); 104203D (2017) https://doi.org/10.1117/12.2281755
Event: Ninth International Conference on Digital Image Processing (ICDIP 2017), 2017, Hong Kong, China
Abstract
Understanding a scene provided by Very High Resolution (VHR) satellite imagery has become a more and more challenging problem. In this paper, we propose a new method for scene classification based on different pre-trained Deep Features Learning Models (DFLMs). DFLMs are applied simultaneously to extract deep features from the VHR image scene, and then different basic operators are applied for features combination extracted with different pre-trained Convolutional Neural Networks (CNN) models. We conduct experiments on the public UC Merced benchmark dataset, which contains 21 different areal categories with sub-meter resolution. Experimental results demonstrate the effectiveness of the proposed method, as compared to several state-of-the-art methods.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Souleyman Chaib, Souleyman Chaib, Hongxun Yao, Hongxun Yao, Yanfeng Gu, Yanfeng Gu, Moussa Amrani, Moussa Amrani, } "Deep feature extraction and combination for remote sensing image classification based on pre-trained CNN models", Proc. SPIE 10420, Ninth International Conference on Digital Image Processing (ICDIP 2017), 104203D (21 July 2017); doi: 10.1117/12.2281755; https://doi.org/10.1117/12.2281755
PROCEEDINGS
5 PAGES


SHARE
Back to Top