饶绪黎,冯晨,黄炎和

• 1:福州职业技术学院信息工程学院

• 2:福建农林大学机电工程学院

• 
  

摘要(Abstract)：

总结近年来遥感分析技术、机器学习及深度学习的传统方法，分析人工智能中深度学习算法应用于滑坡、崩岗信息提取与识别的优势；通过方案对比与实验分析发现，样本采集数量、数据标注质量、崩岗特征提取方式等极大地限制了崩岗智能识别的精度与泛化性。未来将进一步探究多源数据融合与特征提取优化方法；探索基于迁移学习的崩岗多任务识别方法；并结合遥感影像的崩岗变化检测技术，实现对崩岗的准确识别和动态分析。

关键词(KeyWords)： 智能识别;深度学习;滑坡影像;崩岗影像;目标检测

基金项目(Foundation): 2023年福建省财政厅科技项目“福建省典型地质灾害智能防控研究”（LX-2024-HX-011）

作者(Author): 饶绪黎,冯晨,黄炎和

DOI: 10.19473/j.cnki.1008-4940.2024.02.002

参考文献(References)：

• [1] KEYPORT R N, OOMMEN T, MARTHA T R, et al. A comparative analysis of pixel-and object-based detection of landslides from very high-resolution images[J]. International Journal of Applied Earth Observation and Geoinformation,2018, 64:1-11.

• [2] LARY D J, ALAVI A H, GANDOMI A H, et al. Machine learning in geosciences and remote sensing[J]. Geoscience Frontiers, 2016, 7(1):3-10.

• [3] ZHU M, HE Y N, HE Q Y. A review of researches on deep learning in remote sensing application[J]. Scientific Journal of Earth Science, 2019, 10(1):1-11.

• [4] KRIZHEVSKY A, SUTSKEVER I, HINTON G E.ImageNet classification with deep convolutional neural n e t w o r ks[C]//P r o c e e d i n g s o f t h e 2 5 t h I n t e r n a t i o n a l Conference on Neural Information Processing Systems.Lake Tahoe:Curran Associates, 2012:1097-1105.

• [5] CHEN C Y, LIU M Y, TUZEL O, et al. R-CNN for small object detection[C]. Taiwan:13th Asian Conference on Computer Vision, 2017.

• [6] 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.

• [7] HUANG Z, HUANG L, GONG Y, et al. Mask scoring R-C N N[C]. P r o c e e d i n g s o f t h e I E E E C o n f e r e n c e o n Computer Vision and Pattern Recognition. 2019:6409-6418.

• [8] JIANG P Y, ERGU D, LIU F Y, et al. A review of Yolo algorithm developments[J]. Procedia Computer Science,2022, 199:1066-1073.

• [9] LIU W, ANGUELOV D, ERHAN D, et al. Ssd:single shot multibox detector[C]. Amsterdam:European Conference on Computer Vision, 2016.

• [10] LONG J, SHELHAMER E, Darrell T. Fully convolutional networks f or semantic segmentation[C]. Boston:2015I E E E C o n f e r e n c e o n C o m p u t e r Vi s i o n a n d P a t t e r n Recognition(CVPR), 2015.

• [11] SIDDIQUE N, PAHEDING S, ELKIN C P, et al. U-net and its variants for medical image segmentation:a review of theory and applications[J]. Ieee Access, 2021, 9:82031-82057.

• [12] SI H F, SHI Z, HU X L, et al. Image semantic segmentation based on improved DeepLab V3 model[J]. International Journal of Modelling, Identification and Control, 2020,36(2):116-125.

• [13]付饶,何敬,刘刚.基于改进YOLOv4的2021年海地7.2级地震震后滑坡识别[J].地震研究,2023,46(2):300-307.

• [14] WANG T, LIU M, ZHANG H,et al. Landslide detection based on improved YOLOv5 and satellite images[C].Chongqing:2021 4th International Conference on Pattern Recognition and Artificial Intelligence(PRAI), 2021.

• [15] ZHANG D F, ZHANG S P, WANG H H, et al. Research on landslide detection in remote sensing image based on improved Faster-RCNN[C]. Shanghai:2022 2nd International Conference on Computer, Control and Robotics(ICCCR),2022.

• [16]王曦，于鸣，任洪娥. UNET与FPN相结合的遥感图像语义分割[J].液晶与显示,2021,36(3):475-483.

• [17] LEI T, ZHANG Y X, LV Z, et al. Landslide inventory mapping from bitemporal images using deep convolutional neural networks[J]. IEEE Geoscience and Remote Sensing Letters, 2019, 16(6):982-986.

• [18]毛佳琪，何敬，刘刚，等.基于改进的DeepLabV3+算法滑坡识别[J].自然灾害学报,2023,32(2):227-234.

• [19]黄雯珂,滕飞,王子丹,等.基于深度学习的图像分割综述[J].计算机科学,2024,51(2):107-116.

• [20] MEENA S R, SOARES L P, GROHMANN C H, et al.Landslide detection in the Himalayas using machine learning algorithms and U-Net[J]. Landslides, 2022, 19:1209-1229.

• [21] LIU P, WEI Y M, WANG Q J, et al. Research on postea r t hq ua k e la ndslid e ex t r act ion a lgor it h m based on improved U-Net model[J]. Remote Sensing, 2020, 12(5):894-907.

• [22] GHORBANZADEH O, CRIVELLARI A, GHAMISI P, et al. A comprehensive transferability evaluation of U-Net and ResU-Net for landslide detection from Sentinel-2 data(case study areas from Taiwan, China, and Japan)[J]. Scientific Reports, 2021, 11(1):14629-14649.

• [23] QI W, WEI M, YANG W, et al. Automatic mapping of landslides by the ResU-Net[J]. Remote Sensing, 2020,12(15):2487.

• [24]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.

• [25]师芸，石龙龙，牛敏杰,等.基于单阶段实例分割网络的黄土滑坡多任务自动识别[J].测绘通报,2022(4):26-31.

• [26]李昊洁，谢浩，胥闻博，等．遥感影像的空间分辨率对提取崩岗精度的影响[J].安徽农业科学,2016,44(30):227-229,246.

• [27]林敬兰，黄炎和，林金石，等．福建省崩岗侵蚀的地质地貌背景分析[J].亚热带水土保持,2014,26(4):1-5.

• [28]林敬兰，陈志明，黄炎和，等.安溪县崩岗侵蚀空间分布特征探讨[J].水土保持研究,2009,16(6):63-68.

• [29]张铁洋，陈峰云，邓羽松，等.基于CORS-RTK结合GIS的崩岗侵蚀调查方法及应用[J].中国水土保持,2019(2):47-49,69.

• [30]梁钊雄，周红艺，吴国威，等.基于无人机影像的崩岗空间分布特征研究[J].江苏农业科学,2018,46(4):220-224.

• [31]沈盛彧，赵元凌，程冬兵，等.基于无人机遥感技术的崩岗快速调查方法[J].长江科学院院报,2018,35(4):43-47,53.

• [32]江学顶，梁钊雄，周红艺，等.基于无人机倾斜摄影技术的崩岗动态变化监测[J].热带地理,2019,39(4):597-603.

• [33] LIAO K T, SONG Y J, XIE S H, et al. Monitoring of Benggang erosion based on UAV photogrammetry t e c h n o l o g y[J].I O P C o n f e r e n c e S e r i e s:E a r t h a n d Environmental Science, 2019, 330(5):052003.

• [34]周小荃，余宏亮，魏玉杰，等.无人机倾斜航空摄影监测崩岗侵蚀量变化的方法[J].农业工程学报,2019,35(21):51-59.

• [35]刘洁，廖凯涛，宋月君，等.基于GF-2号卫星数据的崩岗提取研究[J].地理空间信息, 2021, 19(11):85-87,107,8.

• [36]刘洁，廖凯涛，宋月君，等.南方崩岗区Pleiades影像融合评价及自动识别[J].江西水利科技,2020,46(4):235-239.

• [37]沈盛彧，张彤，程冬兵，等.融合无人机高分辨率DOM和DSM数据语义的崩岗识别[J].农业工程学报,2020,36(12):69-79.