版权说明 操作指南
首页 > 成果 > 详情

YOLOv8-DBW: An Improved High-Accuracy Fast Landslide Detection Model

认领
导出
Link by DOI
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
Wang, Zhengqing;Chen, Yulin;Ding, Huadong;Liu, Zhongnan;Xie, Yanshi;...
通讯作者:
Ding, HD
作者机构:
[Ding, HD; Zhang, Dinghao; Feng, Peng; Liu, Rentian; Liu, Jiabin; Ding, Huadong; Meng, Lingjie; Xie, Yanshi; Wang, Zhengqing; Yu, Yan] Univ South China, Sch Resource & Environm & Safety Engn, Hengyang, Peoples R China.
[Chen, Yulin; Liu, Zhongnan] Geophys & Geochem Survey Inst Hunan Prov, Changsha, Peoples R China.
[Zhou, Kun] Hunan Green Min Engn & Construct Co, Changsha, Peoples R China.
[Li, Ce] Nat Resources & Planning Bur Hanyuan Cty, Yaan, Peoples R China.
通讯机构:
[Ding, HD ] U
Univ South China, Sch Resource & Environm & Safety Engn, Hengyang, Peoples R China.
语种:
英文
关键词:
BiFormer;deep learning;DySample;landslide detection;remote sensing;WIoU;YOLOv8
期刊:
Transactions in GIS
ISSN:
1361-1682
年:
2025
卷:
29
期:
1
页码:
e70021
基金类别:
This work was supported by the "Xinning 1:10,000 Geohazard High Precision Survey and Risk Prospecting Project Remote Sensing Interpretation and Other Comprehensive Research" fund from the Geophysical and Geochemical Survey Institute of Hunan Province, Gran; Hunan Provincial Department of Natural Resources
机构署名:
本校为第一且通讯机构
摘要:
Landslides can pose a significant threat and damage to life and property. Rapid and accurate determination of the location of landslides is critical to preventing and stopping geohazards. Currently, manual visual interpretation, semiautomatic interpretation, and traditional machine learning interpretation of landslides are less efficient and cannot meet the requirements of certain high-standard interpretation, while the object detection technology based on deep learning is developing rapidly, and its application in the field of intelligent interpretation of landslides is still immature. In thi...

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com