检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:潘燕萍 洪宇 刘金福[2,3] 赵婧雯 朱建琴 PAN Yanping;HONG Yu;LIU Jinfu;ZHAO Jingwen;ZHU Jianqin(College of Computer and Information,Fujian Agriculture and Forestry University,Fuzhou 350002,Fujian,China;College of Forestry,Fujian Agriculture and Forestry University,Fuzhou 350002,Fujian,China;Key Laboratory of Ecology and Resource Statistics of Fujian Universities and Colleges,Fuzhou 350002,Fujian,China;Wuyi Mountain National Park Scientific Research and Monitoring Center,Nanping 354300,Fujian,China)
机构地区:[1]福建农林大学计算机与信息学院,福建福州350002 [2]福建农林大学林学院,福建福州350002 [3]生态与资源统计福建省高校重点实验室,福建福州350002 [4]武夷山国家公园科研监测中心,福建南平354300
出 处:《福建林业科技》2025年第1期64-73,共10页Journal of Fujian Forestry Science and Technology
基 金:福建省林业科技项目(2022FKJ02,2022FKJ26)。
摘 要:以福建省武夷山国家公园为研究区域、以马尾松、杉木和阔叶树混交林等3种天然林为研究对象,提出一种基于深度学习、结合协调注意力机制的树冠自动提取方法CA-Net,探讨基于CA-Net网络的无人机影像天然林树冠分割效果。结果表明:①在天然林数据集上,分水岭算法适用性差;而与U-Net相比,CA-Net的mIoU、mPA和Accuracy分别提升4.75%、3.27%和2.84%。②背景类别上,CA-Net的IoU、Recall和Precision分别达到69.58%、84.17%和80.06%;而树冠类别上,CA-Net的IoU、Recall和Precision分别为83.85%、90.11%和92.35%。③杉木-阔叶树混交林上CA-Net分割精度最高;与U-Net相比,马尾松-杉木混交林、马尾松-杉木-阔叶树混交林中分割精度mIoU分别提升1.83%、3.12%,mPA分别增加6.93%、2.95%,Accuracy分别提高3.57%、1.83%。可见,CA-Net在复杂天然林背景下能有效克服背景干扰和精细特征提取困难等问题,提高树冠分割精度和效率。Taking Wuyi Mountain National Park in Fujian Province as the study area and three types of natural forests,including Pinus massoniana,Fir and broadleaf mixed forests,CA-Net,an automatic canopy extraction method based on deep learning combined with coordinated attention mechanism was proposed.The results show that:①the Watershed algorithm was poorly applicable in the natural forest dataset,whereas the mIoU,mPA and Accuracy of CA-Net is improved compared with U-Net,improved by 4.75%,3.27%and 2.84%,respectively.②On the background category,CA-Net′s IoU,Recall,and Precision reached 69.58%,84.17%and 80.06%,respectively;whereas on the canopy category,CA-Net′s IoU,Recall and Precision were 83.85%,90.11%and 92.35%,respectively.③CA-Net had the highest segmentation accuracy on mixed fir-broadleaf forests,and the segmentation accuracy mIoU increased by 1.83%and 3.12%,mPA increased by 6.93%and 2.95%,Accuracy increased by 3.57%and 1.83%,respectively,compared with that of U-Net for mixed Masson pine-fir forests,and mixed Masson pine-fir-broadleaf forests.It can be seen that CA-Net can effectively overcome the problems of background interference and difficulties in fine feature extraction to improve the accuracy and efficiency of canopy segmentation in complex natural forests.
关 键 词:卷积神经网络 注意力机制 无人机影像 树冠分割 武夷山国家公园
分 类 号:S757.2[农业科学—森林经理学] TP751[农业科学—林学]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.13