Land-cover classification with high-resolution remote sensing images using transferable deep models

• Published in: Remote sensing of environment Vol. 237; p. 111322
• Main Authors: Tong, Xin-Yi, Xia, Gui-Song, Lu, Qikai, Shen, Huanfeng, Li, Shengyang, You, Shucheng, Zhang, Liangpei
• Format: Journal Article
• Language: English
• Published: New York Elsevier Inc 01.02.2020; Elsevier BV
• Subjects: Artificial neural networks; Classification; Datasets; Deep learning; Detection; Gaofen-2 satellite images; High resolution; High-resolution remote sensing; Image acquisition; Image classification; Image resolution; Image segmentation; Internet; Labels; Land cover; land-cover classification; Mapping; Neural networks; Remote sensing; Satellite imagery; Spatial data; Spatial resolution; Target recognition; Deep learning; High-resolution remote sensing; land-cover classification; Gaofen-2 satellite images
• ISSN: 0034-4257; 1879-0704
• DOI: 10.1016/j.rse.2019.111322

In recent years, large amount of high spatial-resolution remote sensing (HRRS) images are available for land-cover mapping. However, due to the complex information brought by the increased spatial resolution and the data disturbances caused by different conditions of image acquisition, it is often difficult to find an efficient method for achieving accurate land-cover classification with high-resolution and heterogeneous remote sensing images. In this paper, we propose a scheme to apply deep model obtained from labeled land-cover dataset to classify unlabeled HRRS images. The main idea is to rely on deep neural networks for presenting the contextual information contained in different types of land-covers and propose a pseudo-labeling and sample selection scheme for improving the transferability of deep models. More precisely, a deep Convolutional Neural Networks (CNNs) is first pre-trained with a well-annotated land-cover dataset, referred to as the source data. Then, given a target image with no labels, the pre-trained CNN model is utilized to classify the image in a patch-wise manner. The patches with high confidence are assigned with pseudo-labels and employed as the queries to retrieve related samples from the source data. The pseudo-labels confirmed with the retrieved results are regarded as supervised information for fine-tuning the pre-trained deep model. To obtain a pixel-wise land-cover classification with the target image, we rely on the fine-tuned CNN and develop a hybrid classification by combining patch-wise classification and hierarchical segmentation. In addition, we create a large-scale land-cover dataset containing 150 Gaofen-2 satellite images for CNN pre-training. Experiments on multi-source HRRS images, including Gaofen-2, Gaofen-1, Jilin-1, Ziyuan-3, Sentinel-2A, and Google Earth platform data, show encouraging results and demonstrate the applicability of the proposed scheme to land-cover classification with multi-source HRRS images. •A method to learn transferable deep model for 5-class land-cover (LC) classification.•A labeled dataset consisting of 150 Gaofen-2 images for LC classification.•It improves LC classification performance about 20% using multi-source RS images.•The method shows good transferability on different sensors and geolocations.