Abstract
Loess landslides are widely distributed in Northern China and pose a significant threat to human life, natural resources, and infrastructure in mountainous regions. Accurate segmentation and measurement of loess landslides is crucial to documenting their occurrence and extent and investigating the distribution, types, and patterns of slope failures. The measurement of landslides also assists in assessing their susceptibility and risk. Herein, a novel loess landslide segmentation and measurement framework based on deep learning is proposed. Multiple experts label the ground-truth landslide regions, and simultaneous truth and performance level estimation (STAPLE) masks are generated. The U-Net segmentation algorithm is trained using a supervised approach to segment the loess landslide region. The fully connected conditional random field is integrated into the U-Net to further optimize the segmentation quality. In the final step, the predicted landslide boundaries are visualized, and the diameters (e.g., length and width) of the segmentation outcome are computed simultaneously. Four state-of-the-art segmentation algorithms are selected for the comparative analysis. The computational results demonstrate that the proposed framework outperforms all the other algorithms tested in terms of segmentation accuracy and boundary errors. The results verify the advantages of using STAPLE and U-Net integrated with a conditional random field.
Similar content being viewed by others
References
Aboelenein NM, Songhao P, Koubaa A, Noor A, Afifi A (2020) HTTU-Net: Hybrid Two Track U-Net for automatic brain tumor segmentation. IEEE Access 8:101406–101415
Amankwah SO, Wang G, Gnyawali K, Hagan DF, Sarfo I, Zhen D, Nooni IK, Ullah W, Duan Z (2022) Landslide detection from bitemporal satellite imagery using attention-based deep neural networks. Landslides, 1–13
Bekaert D, Handwerger AL, Agram P, Kirschbaum DB (2020) Insar-based detection method for mapping and monitoring slow-moving landslides in remote regions with steep and mountainous terrain: an application to nepal. Remote Sens Environ 249:111983
Bragagnolo L, Rezende LR, da Silva RV, Grzybowski JMV (2021) Convolutional neural networks applied to semantic segmentation of landslide scars. Catena 201:105189
Chen LC, Papandreou G, Schroff F, Adam H (2017) Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587
Cheng Z, Gong W, Tang H, Juang CH, Deng Q, Chen J, Ye X (2021) UAV photogrammetry-based remote sensing and preliminary assessment of the behavior of a landslide in Guizhou. China Eng Geol 289:106172
Cherny A, Engl T, Flach S (2019) Non-Gibbs states on a Bose-Hubbard lattice. Phys Rev A 99(2):023603
Chidester B, Ton TV, Tran MT, Ma J, Do MN (2019) Enhanced rotation-equivariant u-net for nuclear segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (pp. 0–0)
Du B, Zhao Z, Hu X, Wu G, Han L, Sun L, Gao Q (2021) Landslide susceptibility prediction based on image semantic segmentation. Comput Geosci 104860
Gautam A, Raman B (2019) Segmentation of ischemic stroke lesion from 3d mr images using random forest. Multimed Tools Apps 78(6):6559–6579
Ghorbanzadeh O, Blaschke T, Gholamnia K, Meena SR, Tiede D, Aryal J (2019) Evaluation of different machine learning methods and deep-learning convolutional neural networks for landslide detection. Remote Sens 11(2):196
Ghorbanzadeh O, Shahabi H, Crivellari A, Homayouni S, Blaschke T, Ghamisi P (2022) Landslide detection using deep learning and object-based image analysis. Landslides 19(4):929–939
Ivanov V, Longoni L, Ferrario M, Brunero M, Arosio D, Papini M (2021) Applicability of an interferometric optical fibre sensor for shallow landslide monitoring-Experimental tests. Eng Geol 288:106128
Ji S, Yu D, Shen C, Li W, Xu Q (2020) Landslide detection from an open satellite imagery and digital elevation model dataset using attention boosted convolutional neural networks. Landslides 17(6):1337–1352
Jin YW, Jia S, Ashraf AB, Hu P (2020) Integrative data augmentation with U-Net segmentation masks improves detection of lymph node metastases in breast cancer patients. Cancers 12(10):2934
Kats E, Goldberger J, Greenspan H (2019) A soft STAPLE algorithm combined with anatomical knowledge. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 510–517). Springer, Cham
Krähenbühl P, Koltun V (2011) Efficient inference in fully connected crfs with gaussian edge potentials. Adv Neural Inf Process Syst 24:109–117
Li H, He Y, Xu Q et al (2022) Detection and segmentation of loess landslides via satellite images: a two-phase framework. Landslides. https://doi.org/10.1007/s10346-021-01789-0
Li H, Xu Q, He Y, Fan X, Li S (2020) Modeling and predicting reservoir landslide displacement with deep belief network and EWMA control charts: a case study in Three Gorges Reservoir. Landslides 17(3):693–707
Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3431–3440)
Meena SR, Soares LP, Grohmann CH, van Westen C, Bhuyan K, Singh RP, Catani F (2022) Landslide detection in the Himalayas using machine learning algorithms and U-Net. Landslides 19(5):1209–1229
Nishio M, Noguchi S, Fujimoto K (2020) Automatic pancreas segmentation using coarse-scaled 2d model of deep learning: usefulness of data augmentation and deep U-net. Appl Sci 10(10):3360
Peng C, Zhang X, Yu G, Luo G, Sun J (2017) Large kernel matters-improve semantic segmentation by global convolutional network. In Proceedings of the IEEE conference on computer vision and pattern recognition. 4353–4361
Peng D, Xu Q, Liu F, He Y, Zhang S, Qi X, Zhang X (2018a) Distribution and failure modes of the landslides in Heitai terrace, China. Eng Geol 236:97–110
Peng J, Fan Z, Wu D, Zhuang J, Dai F, Chen W, Zhao C (2015) Heavy rainfall triggered loess–mudstone landslide and subsequent debris flow in Tianshui, China. Eng Geol 186:79–90
Peng J, Sun P, Igwe O (2018b) Loess caves, a special kind of geo-hazard on loess plateau, northwestern China. Eng Geol 236:79–88
Perlaki G, Horvath R, Nagy SA, Bogner P, Doczi T, Janszky J, Orsi G (2017) Comparison of accuracy between FSL’s FIRST and Freesurfer for caudate nucleus and putamen segmentation. Sci Rep 7(1):1–9
Prakash N, Manconi A, Loew S (2021) A new strategy to map landslides with a generalized convolutional neural network. Sci Rep 11(1):1–15
Qi X, Xu Q, Liu F (2018) Analysis of retrogressive loess flowslides in Heifangtai, China. Eng Geol 236:119–128
Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention (pp. 234–241). Springer, Cham
Shapiro LG (1996) Connected component labeling and adjacency graph construction. In Machine intelligence and pattern recognition (Vol. 19, pp. 1–30). North-Holland
Shen N, Chen L, Wang L, Hu H, Lu X, Qian C, Chen R (2021) Short-term landslide displacement detection based on GNSS real-time kinematic positioning. IEEE Trans Instrum Meas 70:1–14
Shirmard H, Farahbakhsh E, Muller D, Chandra R (2022) A review of machine learning in processing remote sensing data for mineral exploration. Remote Sens Environ 268:112750
Soares LP, Dias HC, Grohmann CH (2020) Landslide segmentation with u-net: Evaluating different sampling methods and patch sizes. arXiv preprint arXiv:2007.06672
Tayyebi SM, Pastor M, Stickle MM, Yagüe Á, Manzanal D, Molinos M, Navas P (2021) Two-phase SPH modelling of a real debris avalanche and analysis of its impact on bottom drainage screens. Landslides, 1–15
Warfield SK, Zou KH, Wells WM (2004) Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation. IEEE Trans Med Imaging 23(7):903–921
Wang H, Zhang L, Yin K, Luo H, Li J (2021) Landslide identification using machine learning. Geosci Front 12(1):351–364
Xu Q, Li H, He Y, Liu F, Peng D (2019) Comparison of data-driven models of loess landslide runout distance estimation. Bull Eng Geol Env 78(2):1281–1294
Yang H, Huang C, Wang L, Luo X (2020) An improved encoder–decoder network for ore image segmentation. IEEE Sens J 21(10):11469–11475
Yi Y, Zhang W (2020) A new deep-learning-based approach for earthquake-triggered landslide detection from single-temporal RapidEye satellite imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 13:6166–6176
Yin J, Zhou Z, Xu S, Yang R, Liu K (2022) A 3D grouped convolutional network fused with conditional random field and its application in image multi-target fine segmentation. Int J Comput Intell Syst 15(1):1–14
Yu H, Gong H, Chen B, Liu K, Gao M (2020) Analysis of the influence of groundwater on land subsidence in beijing based on the geographical weighted regression (gwr) model. Sci Total Environ 738:139405
Zhong Z, Kim Y, Plichta K, Allen BG, Zhou L, Buatti J, Wu X (2019) Simultaneous co-segmentation of tumors in PET-CT images using deep fully convolutional networks. Med Phys 46(2):619–633
Funding
This research is supported by the Science Fund for Creative Research Groups of the National Natural Science Foundation of China (Grant No. 41521002), the Major Program of the National Natural Science Foundation of China (Grant No. 41790445), the Opening fund of State Key Laboratory of Geohazard Prevention and Geoenvironment Protection (Chengdu University of Technology) (Grant No. SKLGP2021K014), the “Miaozi project” of scientific and technological innovation in Sichuan Province, China (Grant No. 2021090), the key research program of Sichuan Province, China (Grant: No. 22ZDYF2365), and the Project of remote sensing identification and monitoring of geological hazards in Sichuan province, CN (2020) (Grant No. 510201202076888).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Li, H., He, Y., Xu, Q. et al. Sematic segmentation of loess landslides with STAPLE mask and fully connected conditional random field. Landslides 20, 367–380 (2023). https://doi.org/10.1007/s10346-022-01983-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10346-022-01983-8