Landslide Inventory Mapping with Bitemporal Aerial Remote Sensing Images Based on the Dual-Path Fully Convolutional Network

Zhiyong Lv, Tongfei Liu, Xiang Bing Kong*, Cheng Shi, Jon Atli Benediktsson

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

4 Citations (Scopus)

Abstract

This article presents a novel dual-path full convolutional network (DP-FCN) model for constructing a landslide inventory map (LIM) with bitemporal very high-resolution (VHR) remote sensing images. Unlike traditional methods for drawing LIM, the proposed DP-FCN directly draws LIMs from the bitemporal aerial images with VHR through a trained deep neural network without generating the change magnitude map. Thus, the proposed approach can effectively reduce the effects of pseudo changes caused by phenological differences rather than landslide events. The proposed DP-FCN model contains two modules, namely, deep feature extraction, and joint feature learning networks. Deep feature extraction aims to reduce redundancy while extracting the high-level deep features from bitemporal images. Joint feature learning establishes the relationship between the deep features of bitemporal images and the ground reference map. Experiments on the real datasets of the landslide sites in Lantau Island of Hong Kong, China, demonstrate the feasibility and superiority of the proposed approach in drawing LIM with VHR remote sensing images. Moreover, compared with the results obtained by the state-of-the-art algorithms, the proposed DP-FCN method achieves the best performance in terms of accuracy for landslide inventory mapping.

Original languageEnglish
Article number9036919
Pages (from-to)4575-4584
Number of pages10
JournalIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Volume13
DOIs
Publication statusPublished - 2020

Bibliographical note

Funding Information:
Manuscript received January 15, 2020; revised February 27, 2020; accepted March 11, 2020. Date of publication March 16, 2020; date of current version August 24, 2020. This work was supported in part by the National Key Research and Development Program of China under Grant 2017YFC0504501, in part by the National Natural Science Foundation of China under Grants 61501200, 61701396, and 61902313, and in part by the Natural Science Foundation of Shaan Xi Province under Grant 2017JQ4006. (Corresponding author: Xiang-Bing Kong.) ZhiYong Lv, TongFei Liu, and Cheng Shi are with the School of Computer Science and Engineering, Xi’An University of Technology, Xi’An 710048, China (e-mail: [email protected]; [email protected]; [email protected]).

Publisher Copyright:
© 2008-2012 IEEE.

Other keywords

  • Change detection (CD)
  • landslide inventory map (LIM)
  • natural disaster
  • remote sensing images

Fingerprint

Dive into the research topics of 'Landslide Inventory Mapping with Bitemporal Aerial Remote Sensing Images Based on the Dual-Path Fully Convolutional Network'. Together they form a unique fingerprint.

Cite this