Study of the Automatic Recognition of Landslides by Using InSAR Images and the Improved Mask R-CNN Model in the Eastern Tibet Plateau
The development of landslide hazards is spatially scattered, temporally random, and poorly characterized. Given the advantages of the large spatial scale and high sensitivity of InSAR observations, InSAR is becoming one of the main techniques for active landslide identification. The difficult proble...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/14/3362 |
| _version_ | 1797444063037751296 |
|---|---|
| author | Yang Liu Xin Yao Zhenkui Gu Zhenkai Zhou Xinghong Liu Xingming Chen Shangfei Wei |
| author_facet | Yang Liu Xin Yao Zhenkui Gu Zhenkai Zhou Xinghong Liu Xingming Chen Shangfei Wei |
| author_sort | Yang Liu |
| collection | DOAJ |
| description | The development of landslide hazards is spatially scattered, temporally random, and poorly characterized. Given the advantages of the large spatial scale and high sensitivity of InSAR observations, InSAR is becoming one of the main techniques for active landslide identification. The difficult problem is how to quickly extract landslide information from extensive InSAR image data. Since the instance segmentation model (Mask R-CNN) in deep learning can provide highly robust target recognition, we select the landslide-prone eastern edge of the Tibetan Plateau as a specific test area. Introducing and optimizing this model achieves high-speed and accurate recognition of InSAR observations. First, the InSAR patch landslide instance segmentation dataset (SLD) is established by developing a common object in context (COCO) annotation format conversion code based on InSAR observations. The Mask R-CNN+++ is found by adding three functions of the ResNext module to increase the fineness of the network segmentation results and enhance the noise resistance of the model, the DCB (deformable convolutional block) to improve the feature extraction ability of the network for geometric morphological changes of landslide patches, and an attention mechanism to selectively enhance usefully and suppress features less valuable to the native Mask R-CNN network. The model achieves 92.94% accuracy on the test set, and the active landslide recognition speed based on this model under ordinary computer hardware conditions is 72.3 km<sup>2</sup>/s. The overall characteristics of the results of this study show that the optimized model effectively enhances the perceptibility of image morphological changes, thereby resulting in smoother recognition boundaries and further improvement of the generalization ability of segmentation detection. This result is expected to serve to identify and monitor active landslides in complex surface conditions on a large spatial scale. Moreover, active landslides of different geometric features, motion patterns, and intensities are expected to be further segmented. |
| first_indexed | 2024-03-09T13:06:10Z |
| format | Article |
| id | doaj.art-e5a0a660e7864a2f92c43d889d5caa59 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T13:06:10Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-e5a0a660e7864a2f92c43d889d5caa592023-11-30T21:48:59ZengMDPI AGRemote Sensing2072-42922022-07-011414336210.3390/rs14143362Study of the Automatic Recognition of Landslides by Using InSAR Images and the Improved Mask R-CNN Model in the Eastern Tibet PlateauYang Liu0Xin Yao1Zhenkui Gu2Zhenkai Zhou3Xinghong Liu4Xingming Chen5Shangfei Wei6Institute of Geomechanics, Chinese Academy of Geological Sciences, Beijing 100081, ChinaInstitute of Geomechanics, Chinese Academy of Geological Sciences, Beijing 100081, ChinaInstitute of Geomechanics, Chinese Academy of Geological Sciences, Beijing 100081, ChinaInstitute of Geomechanics, Chinese Academy of Geological Sciences, Beijing 100081, ChinaInstitute of Geomechanics, Chinese Academy of Geological Sciences, Beijing 100081, ChinaInstitute of Geomechanics, Chinese Academy of Geological Sciences, Beijing 100081, ChinaDepartment of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen 361005, ChinaThe development of landslide hazards is spatially scattered, temporally random, and poorly characterized. Given the advantages of the large spatial scale and high sensitivity of InSAR observations, InSAR is becoming one of the main techniques for active landslide identification. The difficult problem is how to quickly extract landslide information from extensive InSAR image data. Since the instance segmentation model (Mask R-CNN) in deep learning can provide highly robust target recognition, we select the landslide-prone eastern edge of the Tibetan Plateau as a specific test area. Introducing and optimizing this model achieves high-speed and accurate recognition of InSAR observations. First, the InSAR patch landslide instance segmentation dataset (SLD) is established by developing a common object in context (COCO) annotation format conversion code based on InSAR observations. The Mask R-CNN+++ is found by adding three functions of the ResNext module to increase the fineness of the network segmentation results and enhance the noise resistance of the model, the DCB (deformable convolutional block) to improve the feature extraction ability of the network for geometric morphological changes of landslide patches, and an attention mechanism to selectively enhance usefully and suppress features less valuable to the native Mask R-CNN network. The model achieves 92.94% accuracy on the test set, and the active landslide recognition speed based on this model under ordinary computer hardware conditions is 72.3 km<sup>2</sup>/s. The overall characteristics of the results of this study show that the optimized model effectively enhances the perceptibility of image morphological changes, thereby resulting in smoother recognition boundaries and further improvement of the generalization ability of segmentation detection. This result is expected to serve to identify and monitor active landslides in complex surface conditions on a large spatial scale. Moreover, active landslides of different geometric features, motion patterns, and intensities are expected to be further segmented.https://www.mdpi.com/2072-4292/14/14/3362landslideMask R-CNNInSARdeep learninginstance segmentation |
| spellingShingle | Yang Liu Xin Yao Zhenkui Gu Zhenkai Zhou Xinghong Liu Xingming Chen Shangfei Wei Study of the Automatic Recognition of Landslides by Using InSAR Images and the Improved Mask R-CNN Model in the Eastern Tibet Plateau Remote Sensing landslide Mask R-CNN InSAR deep learning instance segmentation |
| title | Study of the Automatic Recognition of Landslides by Using InSAR Images and the Improved Mask R-CNN Model in the Eastern Tibet Plateau |
| title_full | Study of the Automatic Recognition of Landslides by Using InSAR Images and the Improved Mask R-CNN Model in the Eastern Tibet Plateau |
| title_fullStr | Study of the Automatic Recognition of Landslides by Using InSAR Images and the Improved Mask R-CNN Model in the Eastern Tibet Plateau |
| title_full_unstemmed | Study of the Automatic Recognition of Landslides by Using InSAR Images and the Improved Mask R-CNN Model in the Eastern Tibet Plateau |
| title_short | Study of the Automatic Recognition of Landslides by Using InSAR Images and the Improved Mask R-CNN Model in the Eastern Tibet Plateau |
| title_sort | study of the automatic recognition of landslides by using insar images and the improved mask r cnn model in the eastern tibet plateau |
| topic | landslide Mask R-CNN InSAR deep learning instance segmentation |
| url | https://www.mdpi.com/2072-4292/14/14/3362 |
| work_keys_str_mv | AT yangliu studyoftheautomaticrecognitionoflandslidesbyusinginsarimagesandtheimprovedmaskrcnnmodelintheeasterntibetplateau AT xinyao studyoftheautomaticrecognitionoflandslidesbyusinginsarimagesandtheimprovedmaskrcnnmodelintheeasterntibetplateau AT zhenkuigu studyoftheautomaticrecognitionoflandslidesbyusinginsarimagesandtheimprovedmaskrcnnmodelintheeasterntibetplateau AT zhenkaizhou studyoftheautomaticrecognitionoflandslidesbyusinginsarimagesandtheimprovedmaskrcnnmodelintheeasterntibetplateau AT xinghongliu studyoftheautomaticrecognitionoflandslidesbyusinginsarimagesandtheimprovedmaskrcnnmodelintheeasterntibetplateau AT xingmingchen studyoftheautomaticrecognitionoflandslidesbyusinginsarimagesandtheimprovedmaskrcnnmodelintheeasterntibetplateau AT shangfeiwei studyoftheautomaticrecognitionoflandslidesbyusinginsarimagesandtheimprovedmaskrcnnmodelintheeasterntibetplateau |