Landslide Detection and Segmentation Using Mask R-CNN with Simulated Hard Samples

JIANG Wandong; XI Jiangbo; LI Zhenhong; DING Mingtao; YANG Ligong; XIE Dashuai

doi:10.13203/j.whugis20200692

Volume 48 Issue 12

Dec. 2023

Turn off MathJax

Article Contents

Abstract

References

Geomatics and Information Science of Wuhan University > 2023 > 48(12): 1931-1942. > DOI: 10.13203/j.whugis20200692

JIANG Wandong, XI Jiangbo, LI Zhenhong, DING Mingtao, YANG Ligong, XIE Dashuai. Landslide Detection and Segmentation Using Mask R-CNN with Simulated Hard Samples[J]. Geomatics and Information Science of Wuhan University, 2023, 48(12): 1931-1942. DOI: 10.13203/j.whugis20200692

Citation:

PDF (6437 KB)

Landslide Detection and Segmentation Using Mask R-CNN with Simulated Hard Samples

JIANG Wandong^{1, 2,},
XI Jiangbo^{1, 2, 3, ,},
LI Zhenhong^{1, 2, 3},
DING Mingtao^{1, 2, 3},
YANG Ligong¹,
XIE Dashuai^{1, 2}

1.
College of Geological Engineering and Geomantics, Chang'an University, Xi'an 710054, China
2.
Big Data Center for Geosciences and Satellites, Chang'an University, Xi'an 710054, China
3.
Key Laboratory of Western China's Mineral Resources and Geological Engineering, Ministry of Education, Xi'an 710054, China

More Information

Received Date: August 08, 2021
Available Online: November 29, 2023

Graphical Abstract

Abstract

Abstract

Objectives
With the advance in artificial intelligence, using high-resolution images to detect geological hazards has gradually become a research hotspot. Visual interpretation of landslides heavily relies on expert experience, and conventional automatic landslide detection approaches are sensitive to the presence of bare land, roads and other ground objects.
Methods
To address these, a mask region-based convolutional neural network(Mask R-CNN) with simulated hard samples is presented for landslide detection and segmentation. Based on existing landslide samples, hard landslide samples are simulated by utilizing the shapes, colors, textures, and other characteristics of landslides to make each of the samples with a more complicated background. The original imagery and simulated hard samples are then fed into the Mask R-CNN for landslide detection and segmentation. Since the number of landslides is often limited in reality, small sample learning in the frequency domain is also presented to reduce the number of input samples while ensuring the accuracy of detection and segmentation.
Results
The experimental results in Bijie City, Guizhou Province, show that the detection and the average pixel segmentation accuracies of the proposed Mask R-CNN method with simulated hard samples are 94.0% and 90.3%, respectively. It is seen that the proposed method has high performance on landslide detection and segmentation with low false alarm rates. In addition, the performance of the proposed small-sample-based learning method in frequency domain can be improved even with a half of the data input.
Conclusions
The effectiveness of the proposed Mask R-CNN method is further proved by the successful detection of Tianshui landslides in Gansu Province, China.
- deep learning,
- landslide detection,
- Mask R-CNN,
- hard samples,
- frequency domain

FullText(HTML)

References (42)

References

[1]	李振洪, 宋闯, 余琛, 等. 卫星雷达遥感在滑坡灾害探测和监测中的应用: 挑战与对策[J]. 武汉大学学报(信息科学版), 2019, 44(7): 967-979. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201907003.htm Li Zhenhong, Song Chuang, Yu Chen, et al. Application of Satellite Radar Remote Sensing to Landslide Detection and Monitoring: Challenges and Solutions[J]. Geomatics and Information Science of Wuhan University, 2019, 44(7): 967-979. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201907003.htm
[2]	Dai K R, Li Z H, Xu Q, et al. Entering the Era of Earth Observation-Based Landslide Warning Systems: A Novel and Exciting Framework[J]. IEEE Geoscience and Remote Sensing Magazine, 2020, 8(1): 136-153. doi: 10.1109/MGRS.2019.2954395
[3]	陆会燕, 李为乐, 许强, 等. 光学遥感与InSAR结合的金沙江白格滑坡上下游滑坡隐患早期识别[J]. 武汉大学学报(信息科学版), 2019, 44(9): 1342-1354. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201909011.htm Lu Huiyan, Li Weile, Xu Qiang, et al. Early Detection of Landslides in the Upstream and Downstream Areas of the Baige Landslide, the Jinsha River Based on Optical Remote Sensing and InSAR Technologies[J]. Geomatics and Information Science of Wuhan University, 2019, 44(9): 1342-1354. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201909011.htm
[4]	杜源, 王纯, 张勤, 等. 顾及黄土滑坡灾害状态特征的实时GNSS滤波算法[J]. 武汉大学学报(信息科学版), 2023, 48(7): 1216-1222. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH202307020.htm Du Yuan, Wang Chun, Zhang Qin, et al. Real-Time GNSS Filtering Algorithm Considering State Characteristics of Loess Landslide Hazards[J]. Geomatics and Information Science of Wuhan University, 2023, 48(7): 1216-1222. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH202307020.htm
[5]	Bovenga F, Nitti D O, Fornaro G, et al. Using C/X-band SAR Interferometry and GNSS Measurements for the Assisi Landslide Analysis[J]. International Journal of Remote Sensing, 2013, 34(11): 4083-4104. doi: 10.1080/01431161.2013.772310
[6]	Qiu D W, Wang L Y, Luo D A, et al. Landslide Monitoring Analysis of Single-Frequency BDS/GPS Combined Positioning with Constraints on Deformation Characteristics[J]. Survey Review, 2019, 51(367): 364-372. doi: 10.1080/00396265.2018.1467075
[7]	Jaboyedoff M, Oppikofer T, Abellán A, et al. Use of LiDAR in Landslide Investigations: A Review[J]. Natural Hazards, 2012, 61(1): 5-28. doi: 10.1007/s11069-010-9634-2
[8]	McKean J, Roering J. Objective Landslide Detection and Surface Morphology Mapping Using High-Resolution Airborne Laser Altimetry[J]. Geomorphology, 2004, 57(3/4): 331-351.
[9]	许强, 董秀军, 李为乐. 基于天-空-地一体化的重大地质灾害隐患早期识别与监测预警[J]. 武汉大学学报(信息科学版), 2019, 44(7): 957-966. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201907002.htm Xu Qiang, Dong Xiujun, Li Weile. Integrated Space-Air-Ground Early Detection, Monitoring and Warning System for Potential Catastrophic Geohazards[J]. Geomatics and Information Science of Wuhan University, 2019, 44(7): 957-966. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201907002.htm
[10]	葛大庆, 戴可人, 郭兆成, 等. 重大地质灾害隐患早期识别中综合遥感应用的思考与建议[J]. 武汉大学学报(信息科学版), 2019, 44(7): 949-956. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201907001.htm Ge Daqing, Dai Keren, Guo Zhaocheng, et al. Early Identification of Serious Geological Hazards with Integrated Remote Sensing Technologies: Thoughts and Recommendations[J]. Geomatics and Information Science of Wuhan University, 2019, 44(7): 949-956. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201907001.htm
[11]	许强, 陆会燕, 李为乐, 等. 滑坡隐患类型与对应识别方法[J]. 武汉大学学报(信息科学版), 2022, 47(3): 377-387. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH202203007.htm Xu Qiang, Lu Huiyan, Li Weile, et al. Types of Potential Landslide and Corresponding Identification Technologies[J]. Geomatics and Information Science of Wuhan University, 2022, 47(3): 377-387. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH202203007.htm
[12]	何朝阳, 许强, 巨能攀, 等. 滑坡实时监测预警模型调度算法优化研究[J]. 武汉大学学报(信息科学版), 2021, 46(7): 970-982. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH202107002.htm He Chaoyang, Xu Qiang, Ju Nengpan, et al. Optimization of Model Scheduling Algorithm in Real-Time Monitoring and Early Warning of Landslide[J]. Geomatics and Information Science of Wuhan University, 2021, 46(7): 970-982. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH202107002.htm
[13]	Sato H P, Hasegawa H, Fujiwara S, et al. Interpretation of Landslide Distribution Triggered by the 2005 Northern Pakistan Earthquake Using SPOT5 Imagery[J]. Landslides, 2007, 4(2): 113-122. doi: 10.1007/s10346-006-0069-5
[14]	Đurić U, Marjanović M, Radić Z, et al. Machine Learning Based Landslide Assessment of the Belgrade Metropolitan Area: Pixel Resolution Effects and a Cross-Scaling Concept[J]. Engineering Geology, 2019, 256: 23-38. doi: 10.1016/j.enggeo.2019.05.007
[15]	Lu P, Qin Y Y, Li Z B, et al. Landslide Mapping from Multi-sensor Data Through Improved Change Detection-Based Markov Random Field[J]. Remote Sensing of Environment, 2019, 231: 111235. doi: 10.1016/j.rse.2019.111235
[16]	Pawłuszek K, Marczak S, Borkowski A, et al. Multi-aspect Analysis of Object-Oriented Landslide Detection Based on an Extended Set of LiDAR-Derived Terrain Features[J]. ISPRS International Journal of Geo-Information, 2019, 8(8): 321. doi: 10.3390/ijgi8080321
[17]	Bacha A S, Van Der Werff H, Shafique M, et al. Transferability of Object-Based Image Analysis Approaches for Landslide Detection in the Himalaya Mountains of Northern Pakistan[J]. International Journal of Remote Sensing, 2020, 41(9): 3390-3410. doi: 10.1080/01431161.2019.1701725
[18]	李麒崙, 张万昌, 易亚宁. 地震滑坡信息提取方法研究: 以2017年九寨沟地震为例[J]. 中国科学院大学学报, 2020, 37(1): 93-102. https://www.cnki.com.cn/Article/CJFDTOTAL-ZKYB202001010.htm Li Qilun, Zhang Wanchang, Yi Yaning. An Information Extraction Method of Earthquake-Induced Landslide: A Case Study of the Jiuzhaigou Earthquake in 2017[J]. Journal of University of Chinese Academy of Sciences, 2020, 37(1): 93-102. https://www.cnki.com.cn/Article/CJFDTOTAL-ZKYB202001010.htm
[19]	Petschko H, Bell R, Glade T. Effectiveness of Visually Analyzing LiDAR DTM Derivatives for Earth and Debris Slide Inventory Mapping for Statistical Susceptibility Modeling[J]. Landslides, 2016, 13(5): 857-872. doi: 10.1007/s10346-015-0622-1
[20]	许冲, 戴福初, 陈剑, 等. 汶川Ms8.0地震重灾区次生地质灾害遥感精细解译[J]. 遥感学报, 2009, 13(4): 754-762. https://www.cnki.com.cn/Article/CJFDTOTAL-YGXB200904031.htm Xu Chong, Dai Fuchu, Chen Jian, et al. Fine Remote Sensing Interpretation of Secondary Geological Disasters in the Hardest Hit Areas of Wenchuan Earthquake (Ms 8.0)[J]. Journal of Remote Sensing, 2009, 13(4): 754-762. https://www.cnki.com.cn/Article/CJFDTOTAL-YGXB200904031.htm
[21]	Danneels G, Pirard E, Havenith H B. Automatic Landslide Detection from Remote Sensing Images Using Supervised Classification Methods[C]// IEEE International Geoscience and Remote Sensing Symposium. Barcelona, Spain, Barcelona, Spain, 2007.
[22]	Perotto-Baldiviezo H, Thurow T, Smith C, et al. GIS-Based Spatial Analysis and Modeling for Landslide Hazard Assessment in Steeplands, Southern Honduras[J]. Agriculture, Ecosystems and Environment, 2004, 103(1): 165-176.
[23]	Cao Y, Yin K L, Zhou C, et al. Establishment of Landslide Groundwater Level Prediction Model Based on GA-SVM and Influencing Factor Analysis[J]. Sensors, 2020, 20(3): 845.
[24]	Zhu C H, Hu G D. Time Series Prediction of Landslide Displacement Using SVM Model: Application to Baishuihe Landslide in Three Gorges Reservoir Area, China[J]. Applied Mechanics and Materials, 2012, 239/240: 1413-1420.
[25]	Zhang K X, Wu X L, Niu R Q, et al. The Assessment of Landslide Susceptibility Mapping Using Random Forest and Decision Tree Methods in the Three Gorges Reservoir Area, China[J]. Environmental Earth Sciences, 2017, 76(11): 405.
[26]	Stumpf A, Kerle N. Object-Oriented Mapping of Landslides Using Random Forests[J]. Remote Sensing of Environment, 2011, 115(10): 2564-2577.
[27]	Mezaal M, Pradhan B, Rizeei H. Improving Landslide Detection from Airborne Laser Scanning Data Using Optimized Dempster-Shafer[J]. Remote Sensing, 2018, 10(7): 1029.
[28]	Wang F, Jiang M Q, Qian C, et al. Residual Attention Network for Image Classification[C]// IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017.
[29]	Zhao Z Q, Zheng P, Xu S T, et al. Object Detection with Deep Learning: A Review[J]. IEEE Transactions on Neural Networks and Learning Systems, 2019, 30(11): 3212-3232.
[30]	Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation[C]//International Conference on Medical Image Computing and Computer-assisted Intervention, Marrakesh, Morocco, 2015.
[31]	Shi W Z, Zhang M, Ke H F, et al. Landslide Recognition by Deep Convolutional Neural Network and Change Detection[J]. IEEE Transactions on Geoscien- ce and Remote Sensing, 2021, 59(6): 4654-4672.
[32]	Ghorbanzadeh O, Blaschke T, Gholamnia K, et al. Evaluation of Different Machine Learning Methods and Deep-Learning Convolutional Neural Networks for Landslide Detection[J]. Remote Sensing, 2019, 11(2): 196.
[33]	Yu B, Chen F, Xu C. Landslide Detection Based on Contour-Based Deep Learning Framework in Case of National Scale of Nepal in 2015[J]. Computers and Geosciences, 2020, 135: 104388.
[34]	Wang H J, Zhang L M, Yin K S, et al. Landslide Identification Using Machine Learning[J]. Geoscien- ce Frontiers, 2021, 12(1): 351-364.
[35]	Liu P, Wei Y M, Wang Q J, et al. Research on Post-Earthquake Landslide Extraction Algorithm Based on Improved U-Net Model[J]. Remote Sensing, 2020, 12(5): 894.
[36]	Fukushima K, Miyake S, Ito T. Neocognitron: A Neural Network Model for a Mechanism of Visual Pattern Recognition[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1983, SMC-13(5): 826-834.
[37]	Girshick R, Donahue J, Darrell T, et al. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition, Columbus, USA, 2014.
[38]	Girshick R. Fast R-CNN[C]//IEEE International Conference on Computer Vision, Santiago, Chile, 2015.
[39]	Ren S Q, He K M, Girshick R, et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.
[40]	He K M, Gkioxari G, Dollar P, et al. Mask R-CNN[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(2): 386-397.
[41]	Bochkovskiy A, Wang C Y, Liao H Y M. YOLOv4: Optimal Speed and Accuracy of Object Detection[C]//Computer Vision and Pattern Recognition, Seattle, WA, USA, 2020.
[42]	Ji S P, Yu D W, Shen C Y, et al. Landslide Detection from an Open Satellite Imagery and Digital Elevation Model Dataset Using Attention Boosted Convolutional Neural Networks[J]. Landslides, 2020, 17: 1337–1352.

[1]	WEI Erhu, LIU Xuexi, WANG Lingxuan, LIU Jingnan. Analysis and Assessment of BDS/GPS Combined Precise Point Positioning Accuracy[J]. Geomatics and Information Science of Wuhan University, 2018, 43(11): 1654-1660. DOI: 10.13203/j.whugis20160568
[2]	SHU Bao, LIU Hui, ZHANG Jinsheng, PAN Guofu, JIANG Jun. Performance Assessment of Partial Ambiguity Resolution Based on BDS/GPS Combined Positioning[J]. Geomatics and Information Science of Wuhan University, 2017, 42(7): 989-994, 1001. DOI: 10.13203/j.whugis20150017
[3]	ZHANG Rui, YANG Yuanxi, ZHANG Qin, HUANG Guanwen, WANG Le, YAN Xingyuan, QU Wei. Contribution Analysis of BDS/GPS Combined Orbit Determination[J]. Geomatics and Information Science of Wuhan University, 2017, 42(5): 600-608. DOI: 10.13203/j.whugis20150081
[4]	SUI Xin, SHI Chuang, LI Min, XU Zongqiu, XU Aigong. Impact Analysis of GPS/BDS Combined Positioning on Ambiguity Search Region for Short Baseline[J]. Geomatics and Information Science of Wuhan University, 2016, 41(10): 1372-1378. DOI: 10.13203/j.whugis20150479
[5]	GAO Xiao, DAI Wujiao, LI Shijia. Interior Performance Test of High Precision GPS/BDS Compatible Receivers[J]. Geomatics and Information Science of Wuhan University, 2015, 40(6): 795-799. DOI: 10.13203/j.whugis20130459
[6]	Dongmei, XU Houze. Determination of Geoid Using GPS Leveling and Gravity Data[J]. Geomatics and Information Science of Wuhan University, 2011, 36(5): 621-624.
[7]	LI Yihe, SHEN Yunzhong. Impact of Temporal Correlation of GPS Observations on Baseline Solution[J]. Geomatics and Information Science of Wuhan University, 2011, 36(4): 427-430.
[8]	XIONG Yongliang, HUANG Dingfa, XU Shaoguang, LIAO Hua. Long Distance Kinematic GPS Data Processing and Kinematic Crustal Deformation Features Analysis of Wenchuan Earthquake[J]. Geomatics and Information Science of Wuhan University, 2010, 35(3): 265-269.
[9]	ZENG Xuping. GPS Data Processing of Landslide Vertical Deformation Monitoring[J]. Geomatics and Information Science of Wuhan University, 2004, 29(3): 201-204.
[10]	JIANG Weiping, LIU Jingnan, YE Shirong. The Systematical Error Analysis of Baseline Processing in GPS Network[J]. Geomatics and Information Science of Wuhan University, 2001, 26(3): 196-199,238.

Cited By

Cited by

Periodical cited type(8)

1.	翟高鹏，李文彬，薛新春，何杰. 空间直角坐标分量中误差转换到相邻点基线分量中误差的算法设计与实现. 测绘与空间地理信息. 2024(02): 204-206+210 .
2.	张亮亮，李亚泽，熊磊，杨鹏飞，闵恒良. “北斗云”——电力时空大数据云平台技术与应用研究. 西部资源. 2023(02): 189-192 .
3.	伏明星，李仲勤，张瑞鹏. 宝兰高铁某标段CPI复测数据处理与稳定性分析. 测绘地理信息. 2021(06): 40-45 .
4.	刘洋洋，党亚民，许长辉. 基于GAMIT对国家GNSS基准站进行的北斗基线解算分析. 测绘工程. 2019(03): 25-29 .
5.	张波. 北斗卫星导航系统用于高精度工程控制网建立的可行性分析. 北京测绘. 2019(07): 792-796 .
6.	白正伟，张勤，黄观文，景策，王家兴. “轻终端+行业云”的实时北斗滑坡监测技术. 测绘学报. 2019(11): 1424-1429 .
7.	闫子耀. 基于北斗系统的船舶导航系统定位精度研究. 中国水运(下半月). 2018(07): 49-50 .
8.	闫子耀. 基于北斗系统的船舶导航系统定位精度研究. 中国水运(下半月). 2018(14): 49-50 .

Other cited types(1)

Get Citation

PDF

XML

Article views (2249) PDF downloads (244) Cited by(9)

Landslide Detection and Segmentation Using Mask R-CNN with Simulated Hard Samples

Abstract

References

Related Articles

Cited by

Periodical cited type(8)

Other cited types(1)

Catalog

Related

Landslide Detection and Segmentation Using Mask R-CNN with Simulated Hard Samples

Abstract

References

Related Articles

Cited by

Periodical cited type(8)

Other cited types(1)

Catalog

Related

Export File

Citation

Format

Content