期刊
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
卷 59, 期 6, 页码 4654-4672出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2020.3015826
关键词
Terrain factors; Feature extraction; Training; Data mining; Image recognition; Convolutional neural networks; Remote sensing; Change detection; convolutional neural network (CNN); landslide; remotely sensed (RS) images
类别
资金
- Ministry of Science and Technology of the People's Republic of China [2017YFB0503604]
- Hong Kong Polytechnic University Projects through the Landslip Prevention and Mitigation Programme, 2017 [CE 49/2017 (GE)]
This article proposes a novel integrated approach combining deep learning and change detection for automatic landslide recognition from RS images. The method achieves high accuracy and speed at landslide-prone locations by building CNN based on historical landslide training data and optimizing post-processing methods.
It is a technological challenge to recognize landslides from remotely sensed (RS) images automatically and at high speeds, which is fundamentally important for preventing and controlling natural landslide hazards. Many methods have been developed, but there remains room for improvement for stable, higher accuracy, and high-speed landslide recognition for large areas with complex land cover. In this article, a novel integrated approach combining a deep convolutional neural network (CNN) and change detection is proposed for landslide recognition from RS images. Logically, it comprises the following four parts. First, a CNN for landslide recognition is built based on training data sets from RS images with historical landslides. Second, the object-oriented change detection CNN (CDCNN) with a fully connected conditional random field (CRF) is implemented based on the trained CNN. Third, the preliminary CDCNN is optimized by the proposed postprocessing methods. Finally, the results are further enhanced by a set of information extraction methods, including trail extraction, source point extraction, and attribute extraction. Furthermore, in the implementation of the proposed approach, image block processing and parallel processing strategies are adopted. As a result, the speed has been improved significantly, which is extremely important for RS images covering large areas. The effectiveness of the proposed approach has been examined using two landslide-prone sites, Lantau Island and Sharp Peak, Hong Kong, with a total area of more than 70 km(2). Besides its high speed, the proposed approach has an accuracy exceeding 80%, and the experiments demonstrate its high practicability.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据