[1]闻馨,贾明明,李晓燕,等.基于无人机可见光影像的红树林冠层群落识别[J].森林与环境学报,2020,40(05):486-496.[doi:10.13324/j.cnki.jfcf.2020.05.005]
 WEN Xin,JIA Mingming,LI Xiaoyan,et al.Identification of mangrove canopy species based on visible unmanned aerial vehicle images[J].,2020,40(05):486-496.[doi:10.13324/j.cnki.jfcf.2020.05.005]
点击复制

基于无人机可见光影像的红树林冠层群落识别()
分享到:

《森林与环境学报》[ISSN:2096-0018/CN:35-1327/S]

卷:
40
期数:
2020年05期
页码:
486-496
栏目:
出版日期:
2020-09-15

文章信息/Info

Title:
Identification of mangrove canopy species based on visible unmanned aerial vehicle images
作者:
闻馨12 贾明明2 李晓燕1 王宗明23 钟才荣4 冯尔辉4
1. 吉林大学地球科学学院, 吉林 长春 130061;
2. 中国科学院东北地理与农业生态研究所湿地生态与环境重点实验室, 吉林 长春 130102;
3. 国家地球系统科学数据中心, 北京 100101;
4. 海南东寨港国家级自然保护区管理局, 海南 海口 571129
Author(s):
WEN Xin12 JIA Mingming2 LI Xiaoyan1 WANG Zongming23 ZHONG Cairong4 FENG Erhui4
1. College of Earth Science, Jilin University, Changchun, Jilin 130061, China;
2. Key Laboratory of Wetland Ecology and Environment, Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun, Jilin 130102, China;
3. National Earth System Science Data Center, Beijing 100101, China;
4. Hainan Dongzhaigang National Nature Reserve Administration Bureau, Haikou, Hainan 571129, China
关键词:
无人机可见光影像红树林冠层群落随机森林分类最优分割尺度
Keywords:
unmanned aerial vehiclevisible imagerymangrove canopy speciesrandom forest classificationoptimal segmentation scale
分类号:
P901
DOI:
10.13324/j.cnki.jfcf.2020.05.005
摘要:
为快速准确地监测红树林群落类型和分布,获得无人机影像在高精度红树林群落制图中的应用方法,使用无人机获取海南省澄迈县富力湾红树林国家级湿地公园的高空间分辨率(5 cm)可见光影像,应用面向对象分类和最优分割算法提取红树林冠层边界,使用可见光波段差异植被指数和随机森林分类算法识别红树林冠层群落。研究结果表明:面向对象的随机森林红树林群落分类中,选用最优分割尺度和适宜的随机森林算法特征和参数能够提高红树林群落分类精度,最终分类结果总体精度达89.09%,Kappa系数为0.87。该方法适合高精度、小尺度的红树林群落制图,能够及时、准确地监测红树林群落变化。因此,无人机可见光影像在红树林的监测与管理中有广阔的应用前景。
Abstract:
China’s Fuliwan National Mangrove Park, which is located in Chengmai County, Hainan Province, was selected to study methods for the regular and accurate monitoring of mangrove community species and distribution: unmanned aerial vehicle(UAV) imagery with high-spatial resolution was applied to achieve precise mangrove community mapping. A UAV capable of providing high-spatial resolution(5 cm), multispectral images(red,green,and blue bands) was used in this study. First, an object-oriented classification method and an optimal segmentation scale model were used to segment the mangrove canopies. Thereafter, the visible-band difference vegetation index(VDVI) and random forest classifier were applied to identify different mangrove canopy species. The results demonstrated that using optimal segmentation scale with the most suitable parameters and features in the random forest model facilitated accurate mangrove species classification.The overall accuracy and Kappa index of the classification results were 89.09% and 0.87, respectively, suggesting that this method is useful for small-scale, high-precision mapping of mangrove species while regularly and precisely monitoring changes. According to the results and discussion of this study, visible unmanned aerial vehicle imagery has enormous potential for managing mangrove ecosystems.

参考文献/References:

[1] 王文卿,王瑁.中国红树林[M].北京:科学出版社,2007:1,95-108.
[2] 贾明明.1973-2013年中国红树林动态变化遥感分析[D].长春:中国科学院东北地理与农业生态研究所,2014.
[3] 路春燕,高弋斌,陈远丽,等.基于RS/GIS的泉州湾红树林湿地时空动态变化分析[J].森林与环境学报,2019,39(2):143-152.
[4] 何斌源,范航清,王瑁,等.中国红树林湿地物种多样性及其形成[J].生态学报,2007,27(11):4859-4870.
[5] WANG L,SOUSA W P,GONG P,et al.Comparison of Ikonos and Quickbird images for mapping mangrove species on the Caribbean coast of Panama[J].Remote Sensing of Environment,2004,91(3/4):432-440.
[6] 陶艳成,葛文标,刘文爱,等.基于高分辨率卫星影像的广西红树林面积监测与群落调查[J].自然资源学报,2017,32(9):1602-1614.
[7] 唐焕丽,刘凯,朱远辉,等.基于WorldView-2数据和支持向量机的红树林群落分类研究[J].中山大学学报(自然科学版),2015,54(4):102-111.
[8] 林志玮,丁启禄,涂伟豪,等.基于多元HoG及无人机航拍图像的植被类型识别[J].森林与环境学报,2018,38(4):444-450.
[9] 汪小钦,王苗苗,王绍强,等.基于可见光波段无人机遥感的植被信息提取[J].农业工程学报,2015,31(5):152-158.
[10] 冯家莉, 刘凯, 朱远辉, 等.无人机遥感在红树林资源调查中的应用[J].热带地理,2015,35(1):35-42.
[11] 刘凯,龚辉,曹晶晶等.基于多类型无人机数据的红树林遥感分类对比[J].热带地理,2019,39(4):492-501.
[12] 雷鸣,田卫新,任东,等.基于对象分类的遥感影像森林变化检测方法[J].森林与环境学报,2019,39(6):641-646.
[13] 陈远丽,路春燕,刘金福,等.漳江口湿地变化的遥感监测[J].森林与环境学报,2019,39(1):61-69.
[14] JOHNSON B,XIE Z X.Unsupervised image segmentation evaluation and refinement using a multi-scale approach[J].ISPRS Journal of Photogrammetry and Remote Sensing,2011,66(4):473-483.
[15] 殷瑞娟,施润和,李镜尧.一种高分辨率遥感影像的最优分割尺度自动选取方法[J].地球信息科学学报,2013,15(6):902-910.
[16] 齐雁冰,王茵茵,陈洋,等.基于遥感与随机森林算法的陕西省土壤有机质空间预测[J].自然资源学报,2017,32(6):1074-1086.
[17] 孙傲,赵礼峰.基于信息增益和基尼不纯度的k近邻算法[J].计算机技术与发展,2019,29(9):51-54,116.
[18] 李欣海.随机森林模型在分类与回归分析中的应用[J].应用昆虫学报,2013,50(4):1190-1197.
[19] WAN L M,ZHANG H S,WANG T,et al.Mangrove species discrimination from very high resolution imagery using Gaussian Markov Random Field model[J].Wetlands,2018,38(5):861-874.

相似文献/References:

[1]樊仲谋,周成军,周新年,等.无人机航测技术在森林资源调查中的应用[J].森林与环境学报,2018,38(03):297.[doi:10.13324/j.cnki.jfcf.2018.03.007]
 FAN Zhongmou,ZHOU Chengjun,ZHOU Xinnian,et al.Application of unmanned aerial vehicle aerial survey technology in forest inventory[J].,2018,38(05):297.[doi:10.13324/j.cnki.jfcf.2018.03.007]
[2]林志玮,丁启禄,涂伟豪,等.基于多元HoG及无人机航拍图像的植被类型识别[J].森林与环境学报,2018,38(04):444.[doi:10.13324/j.cnki.jfcf.2018.04.010]
 LIN Zhiwei,DING Qilu,TU Weihao,et al.Vegetation type recognition based on multivariate HoG and aerial image captured by UAV[J].,2018,38(05):444.[doi:10.13324/j.cnki.jfcf.2018.04.010]

备注/Memo

备注/Memo:
收稿日期:2020-04-28;改回日期:2020-08-10。
基金项目:国家科技部基础资源调查专项(2017FY100706);吉林省自然科学基金项目(20200201048JC)。
作者简介:闻馨(1994-),女,硕士研究生,从事滨海湿地植物群落研究。Email:wenxin18@mails.jlu.edu.cn。
通讯作者:李晓燕(1975-),教授,从事资源遥感与土地信息系统研究。Email:lxyan@jlu.edu.cn。
更新日期/Last Update: 1900-01-01