基于遥感影像的滑坡图像检测方法的研究
Research on Landslide Image Detection Method Based on Remote Sensing Images
DOI: 10.12677/CSA.2023.1311204, PDF,    科研立项经费支持
作者: 侯梦媛, 李明亮, 吕梅洁：河北地质大学信息工程学院，河北 石家庄;智能传感物联网技术河北省工程研究中心，河北 石家庄
关键词: 滑坡检测；遥感影像；Faster RCNN；卷积神经网络；目标检测；Landslide Detection； Remote Sensing Images； Faster RCNN； Convolutional Neural Network； Object Detection
摘要: 滑坡是全球主要的自然灾害之一，危害极大，其影响不可忽视。深度学习进行滑坡检测的进程不断发展，Faster RCNN有较大的贡献，但仍存在检测速率慢和精度低的问题。对Faster RCNN模型进行改进，首先，在Faster RCNN模型中增加inception模块，增加网络的宽度及深度，使模型能充分提取遥感影像的特征；再次，在Faster RCNN模型中增加残差注意力网络，加深网络，提高图像检测精度，从而优化算法检测效果。采用毕节市公开的滑坡数据集进行测试，结果表明，对于同一测试数据，改进的Faster RCNN算法模型与现有的Faster RCNN、VGG16、inception v3模型相比，在精度、召回率、准确率等方面有2%~5%的提升。由此可得出，改进后的算法模型能够准确有效地对遥感影像中的滑坡区域进行检测。
Abstract: Landslide is one of the major natural disasters worldwide, with great harm and its impact cannot be ignored. The process of deep learning for landslide detection is constantly developing, and Faster RCNN has made significant contributions, but there are still problems with slow detection speed and low accuracy. To improve the Faster RCNN model, firstly, an insertion module is added to the Faster RCNN model to increase the width and depth of the net-work, enabling the model to fully extract features from remote sensing images; once again, add residual attention networks to the Faster RCNN model, deepen the network, improve image detection accuracy, and optimize the algorithm’s detection performance. The test was conducted using the publicly available landslide dataset in Bijie City, and the results showed that for the same test data, the improved Faster RCNN algorithm model showed a 2% to 5% improvement in accuracy, recall, and accuracy compared to the existing Faster RCNN, VGG16, and inception v3 models. From this, it can be concluded that the improved algorithm model can accurately and effectively detect land-slide areas in remote sensing images.
文章引用：侯梦媛, 李明亮, 吕梅洁. 基于遥感影像的滑坡图像检测方法的研究[J]. 计算机科学与应用, 2023, 13(11): 2051-2061. https://doi.org/10.12677/CSA.2023.1311204

参考文献

[1] 李郎平, 兰恒星. 滑坡运动路径复杂度研究: 综述与展望[J]. 地球科学, 2022, 47(12): 4663-4680.
[2] 自然资源部地质灾害技术指导中心. 全国地质灾害通报(2021年) [R]. 北京: 中国地质环境监测院, 2022.
[3] 杨成生, 董继红, 朱赛楠, 等. 金沙江结合带巴塘段滑坡群InSAR探测识别与形变特征[J]. 地球科学与环境学报, 2021, 43(2): 398-408.
[4] 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.
[5] 姚纪华, 吕慧珠, 赵文刚, 等. 基于遥感与地质耦合法的水库滑坡群特性解译研究[J]. 工程勘察, 2021, 49(1): 47-53.
[6] 虎振兴, 徐泓, 汪超亮, 等. 基于时间序列遥感影像的滑坡检测方法[J]. 航天返回与遥感, 2018, 39(2): 104-114.
[7] 张毅, 谭龙, 陈冠, 等. 基于面向对象分类法的高分辨率遥感滑坡信息提取[J]. 兰州大学学报(自然科学版), 2014, 50(5): 745-750.
[8] 张福浩, 朱月月, 赵习枝, 等. 地理因子支持下的滑坡隐患点空间分布特征及识别研究[J]. 武汉大学学报(信息科学版), 2020, 45(8): 1233-1244.
[9] Yi, Y., Zhang, Z., Zhang, W., et al. (2019) Comparison of Different Machine Learning Models for Landslide Susceptibility Mapping. 2019 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Yokohama, 28 July-2 August 2019, 9318-9321. [Google Scholar] [CrossRef] 
[10] Ghorbanzadeh, O., Blaschke, T., Gholamnia, K., et al. (2019) Evaluation of Different Machine Learning Methods and Deep-Learning Convolutional Neural Networks for Landslide Detection. Remote Sensing, 11, Article 196. [Google Scholar] [CrossRef] 
[11] Wang, H.J., Zhang, L.M., Yin, K.S., Luo, H.Y. and Li, J.H. (2021) Land-slide Identification Using Machine Learning. Geoscience Frontiers, 12, 351-364. [Google Scholar] [CrossRef] 
[12] Mohan, A., Singh, A.K., Kumar, B. and Dwivedi, R. (2020) Review on Remote Sensing Methods for Landslide Detection Using Machine and Deep Learning. Transactions on Emerging Telecommunications Technologies, 32, e3998. [Google Scholar] [CrossRef] 
[13] 周俊宇, 赵艳明. 卷积神经网络在图像分类和目标检测应用综述[J]. 计算机工程与应用, 2017, 53(13): 34-41.
[14] 巨袁臻, 许强, 金时超, 等. 使用深度学习方法实现黄土滑坡自动识别[J]. 武汉大学学报(信息科学版), 2020, 45(11): 1747-1755.
[15] Ju, Y.Z., Xu, Q., Jin, S.C., et al. (2022) Loess Landslide Detection Using Object Detection Algorithms in Northwest China. Remote Sensing, 14, Article 1182. [Google Scholar] [CrossRef] 
[16] 李准. 基于深度学习的林芝地区滑坡图像检测方法的研究[D]: [硕士学位论文]. 拉萨: 西藏大学, 2021.
[17] Cheng, L.B., Li, J., Duan, P. and Wang, M.G. (2021) A Small Attentional YOLO Model for Landslide Detection from Satellite Remote Sensing Images. Landslides, 18, 2751-2765. [Google Scholar] [CrossRef] 
[18] 张康, 黑保琴, 周壮, 等. 变异系数降维的CNN高光谱遥感图像分类[J]. 遥感学报, 2018, 22(1): 87-96.
[19] Bui, T.A., Lee, P.J., Lum, K.Y., Loh, C. and Tan, K. (2020) Deep Learning for Landslide Recognition in Satellite Architecture. IEEE Access, 8, 143665-143678. [Google Scholar] [CrossRef] 
[20] Xu, W.J., Xu, Q., Liu, G.Y. and Xu, H.Y. (2021) A Novel Parameter Inversion Method for an Improved DEM Simulation of a River Damming Process by a Large-Scale Landslide. Engineering Geology, 293, Article ID: 106282. [Google Scholar] [CrossRef] 
[21] Romero, A., Gatta, C. and Camps-Valls, G. (2015) Unsuper-vised Deep Feature Extraction for Remote Sensing Image Classification. IEEE Transactions on Geoscience and Remote Sensing, 54, 1349-1362. [Google Scholar] [CrossRef] 
[22] Can, R., Kocaman, S. and Gokceoglu, C. (2019) A Convolu-tional Neural Network Architecture for Auto-Detection of Landslide Photographs to Assess Citizen Science and Volun-teered Geographic Information Data Quality. International Journal of Geo-Information, 8, Article 300. [Google Scholar] [CrossRef] 
[23] Jiao, L.C., et al. (2019) A Survey of Deep Learning-Based Object Detec-tion. IEEE Access, 7, 128837-128868. [Google Scholar] [CrossRef] 
[24] Zou, Z.X., Shi, Z.W., Guo, Y.H., et al. (2019) Object Detec-tion in 20 Years: A Survey. Proceedings of the IEEE, 111, 257-276. [Google Scholar] [CrossRef] 
[25] Redmon, J., Divvala, S., Girshick, R. and Farhadi, A. (2016) You Only Look Once: Unified, Real-Time Object Detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 779-788. [Google Scholar] [CrossRef] 
[26] Liu, W., Anguelov, D., Erhan, D., et al. (2016) SSD: Single Shot Multibox Detector. In: Leibe, B., Matas, J., Sebe, N. and Well-ing, M., Eds., Computer Vision—ECCV 2016, Springer, Cham, 21-37. [Google Scholar] [CrossRef] 
[27] Girshick, R., Donahue, J., Darrell, T. and Malik, J. (2013) Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. 2014 IEEE Conference on Computer Vi-sion and Pattern Recognition, Columbus, 23-28 June 2014, 580-587. [Google Scholar] [CrossRef] 
[28] Girshick, R. (2015) Fast R-CNN. 2015 IEEE International Confer-ence on Computer Vision (ICCV), Santiago, 7-13 December 2015, 1440-1448. [Google Scholar] [CrossRef] 
[29] Ren, S., He, K., Girshick, R. and Sun, J. (2017) Faster R-CNN: To-wards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Ma-chine Intelligence, 39, 1137-1149. [Google Scholar] [CrossRef] 
[30] Ji, S.P., Yu, D.W., Shen, C.Y., Li, W.L. and Xu, Q. (2020) Landslide Detection from an Open Satellite Imagery and Digital Elevation Model Dataset Using Attention Boosted Con-volutional Neural Networks. Landslides, 17, 1337-1352. [Google Scholar] [CrossRef]