Abstract
The geological conditions along Sichuan–Tibet Railway are complex, and frequently-occurred landslides have brought severe challenges to the railway construction. Therefore, a complete and accurate landslide perception can provide references for railway route selection and landslide risk governance. In this study, we utilized change vector analysis, principal component analysis, and independent component analysis (ICA) for change detection images generation, and then adopted the multithreshold method to produce the training sample templates for landslides and nonlandslides, respectively. The Markov random field (MRF) algorithm was further used to extract the optimal landslide objects. In particular, we tested the performance of the proposed approach using the Sentinel-2 datasets in a rapid perception of the coseismic landslides for the Nyingchi event that occurred on 18 November 2017 and affected the railway construction. We further calculated completeness, correctness, accuracy, F1-score, and Kappa coefficient, for a quantitative evaluation of landslide perception results. We found that the ICA-based change detection in MRF can extract landslides more completely and accurately. This study set up with the aim to assess the effectiveness and applicability of the proposed method in mapping landslide migration areas under complex geological conditions along the Sichuan–Tibet Railway, which offers a comprehensively intelligent approach to supporting the hazard mitigation for a safe railway construction and operation.
Highlights
Sichuan-Tibet Railway, which connects Chengdu (Sichuan Province) and Lhasa (Tibet Province), is an epic project that is currently under construction in China
To fill the gap of lacking application under complex geological conditions, we developed change detection-based Markov Random Field (MRF) for intelligent perception of landslide migration areas along Sichuan-Tibet Railway
Compared with the ground truths, it clearly demonstrates that the proposed method for landslide perception with independent component analysis (ICA) (Fig. 6h) can produce less misclassified pixels, which shows better performance than the results from principal component analysis (PCA) (Fig. 6f) and change vector analysis (CVA) (Fig. 6g)
Summary
Sichuan-Tibet Railway, which connects Chengdu (Sichuan Province) and Lhasa (Tibet Province), is an epic project that is currently under construction in China. The visual interpretation method cannot accurately analyze landslide disasters in time to provide reference for engineering construction. There are two basic approaches usually adopted in practice for landslide mapping [10], [11], namely, pixel-based and object-oriented method. The pixel-based method is effective in extracting information from low- and medium-resolution remote sensing images. For high-resolution remote sensing images, the pixel-based method may have difficulty in effectively extracting the landslide information from images due to the salt and pepper noises, resulting in poor classification accuracy [12], [13]. The object-oriented method uses the spectral, spatial and morphometric information of pixel groups as basic units for information extraction, thereby improving the performance of image classification. Chen et al [17] integrated random
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
