摘要
针对现有滑坡体检测精度低的现实问题,提出了一种基于深度学习的滑坡体检测框架。该框架包含数据采集与处理、特征选择、检测模型三个部分,可融合多源数据有效提高对滑坡体检测能力。提出了多模态的KlA-lexNet模型,可实现像素级分割预测,有效地融合空间特征。实验结果表明,所提KlAlexNet模型具备高精度的滑坡体检测能力。与U-Net、U-Net++、FC_DenseNet、YOLOv9-seg等方法相比具备优势。实验结果验证了所提方法的有效性和实用性,该方法具有广阔的应用前景。
In response to the current issue of low precision in landslide detection,a deep learning-based landslide detection framework was proposed.This framework includeed three parts:data collection and processing,feature selection,and detection model,which can effectively improve the detection capability of landslides by integrating multi-source data.A multimodal KlAlexNet model was proposed,which could achieve pixel-level segmentation prediction and effectively fuse spatial features.Experimental results indicate that the proposed KlAlexNet model has high precision in landslide detection.Compared with methods such as U-Net,U-Net++,FC_DenseNet,and YOLOv9-seg,it demonstrates advantages.The experimental results validate the effectiveness and practicality of the proposed method,indicating its broad application prospects.
作者
陈龙
葛澄
戴颖超
王宏宇
刘维维
CHEN Long;GE Cheng;DAI Yingchao;WANG Hongyu;LIU Weiwei(Chengdu Big Data Industry Technology Research Institute Co.,Ltd.,Chengdu 610095,China;Innovative Equipment Research Institute of Beijing Institute of Technology in Sichuan Tianfu New Area,Chengdu 610299,China;School of Automation,Chongqing University,Chongqing 400044,China;Beijing Institute of Tech-nology,Beijing 100081,China)
出处
《华南地震》
2025年第2期66-74,共9页
South China Journal of Seismology
基金
基于天空地一体化的滑坡监测评估与应急系统研发与应用(2023-CY02-00002-GX)。
关键词
深度学习
滑坡检测
卷积神经网络
特征提取
损失函数
Deep learning
Landslide detection
Convolutional neural networks
Feature extraction
Loss func⁃tion
