Please wait a minute...
img

官方微信

遥感技术与应用  2021, Vol. 36 Issue (3): 533-543    DOI: 10.11873/j.issn.1004-0323.2021.3.0533
森林遥感专栏     
基于无人机遥感技术的台风灾害倒伏绿化树木检测
廖鸿燕(),周小成(),黄洪宇
福州大学地理空间信息技术国家地方联合工程研究中心
空间数据挖掘与信息共享教育部重点实验室,福建 福州 350116
Detection of Lodging Landscape Trees in Typhoon Disaster based on Unmanned Aerial Vehicle Remote Sensing
Hongyan Liao(),Xiaocheng Zhou(),Hongyu Huang
Key Laboratory of Spatial Data Mining &Information Sharing of Ministry of Education,National Engineering Research Centre of Geospatial Information Technology,Fuzhou University,Fuzhou 350116,China
 全文: PDF(3067 KB)   HTML
摘要:

以福州大学为试验区,提出一种基于无人机遥感影像的台风灾害倒伏绿化树木的快速提取方法,为园林部门进行台风灾害损失评估、灾后重建提供参考。首先利用无人机遥感技术获取高于10 cm分辨率的台风过境前后影像,经过处理得到数字正射影像(Digital Orthophoto Map,DOM)和数字表面模型(Digital Surface Model,DSM);其次采用高斯高通滤波算法突出树干的边缘信息;然后采用对比过滤分割算法结合互信息最大化特征选择算法(maximum Relevance Minimum Redundancy,mRMR)选择最佳特征子集,再分别根据阈值和随机森林(Random Forest,RF)分类方法检测出树干与非树干;最后使用骨架化算法将倒下的树干简化为骨架线,采用八邻域追踪法对单棵树干进行精细提取。结果表明:基于单期无人机影像使用阈值分类方法在试验区中共检测出了71棵倒伏木,准确率达76.06%;而基于RF分类方法倒伏木提取准确率虽提高了12.73%,但漏检率达25.39%;为了比较基于单期和两期影像两种数据源倒伏木的检测效率,结合两期DSM差值,分别采用阈值分类和RF分类两种方法,准确率分别为89.66%和87.30%,漏检率为17.46%和12.70%。研究认为,通过单时相影像特征基本能够检测出倒伏木,多时相影像分析可以有效提高倒伏木的检测精度,为不同数据源情况下的倒伏木检测提供了一种新途径。基于无人机遥感技术可以较好地实现台风灾后倒伏木数量的快速估算。

关键词: 无人机遥感台风灾害倒伏木特征选择灾害评估    
Abstract:

Fuzhou University was taken as an experimental area, this paper presented a fast extraction method of lodging landscape trees in typhoon disaster based on unmanned aerial vehicle remote sensing image, which can provide reference for the assessment of typhoon disaster losses and post-disaster reconstruction of the landscape department. Firstly, unmanned aerial vehicle remote sensing technology was used to obtain Pre and Post images during typhoon passing with a resolution higher than 10cm. After processing, Digital Orthophoto Map(DOM)and Digital Surface Model(DSM)were obtained. Then gaussian high pass filtering algorithm was used to highlight the edge information of tree trunk. And the best feature subset was selected by contrast filtering segmentation algorithm combined with maximum Relevance Minimum Redundancy(mRMR)feature selection algorithm. In addition, the tree trunk and non-tree trunk were detected according to the threshold value and Random Forest(RF)classification method respectively. At last, the tree trunk of lodging tree was simplified into skeleton line by using skeletonization algorithm, and the single tree trunk was extracted by using octo-neighborhood tracking method. The results show that a total of 71 lodging trees were detected using threshold classification based on single-phase UVA images, with an accuracy of 76.06% in the experimental area. However, the accuracy of lodging tree extraction improved by 12.73% based on RF classification,and the missed detection reached 25.39%. In order to compare the detection efficiency of lodging trees based on single-phase and two-phase images, combined the difference value of DSM in the two phases, threshold and RF classification were used respectively, with an accuracy of 89.66% and 87.30%, a commission of 17.46% and 12.70%.Research suggests that the single-phase image features can basically detect the lodging trees, and the multi-phase images analysis can effectively improve the detection accuracy of the lodging trees, providing an effective reference for the detection of the lodging trees under different data sources. According to the research, the UAV remote sensing technology can realize the rapid estimation of the number of lodging trees after typhoon.

Key words: UAV Remote Sensing    Typhoon disaster    Lodging tree    Feature selection    Hazard assessment
收稿日期: 2020-02-20 出版日期: 2021-07-22
ZTFLH:  TP79  
基金资助: 国家重点研发计划项目(2017YFB0504202);中央引导地方科技发展专项(2017L3012)
通讯作者: 周小成     E-mail: 2224524324@qq.com;zhouxc@fzu.edu.cn
作者简介: 廖鸿燕(1994-),男,福建宁德人,硕士研究生,主要从事资源与环境遥感研究。E?mail:2224524324@qq.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
廖鸿燕
周小成
黄洪宇

引用本文:

廖鸿燕,周小成,黄洪宇. 基于无人机遥感技术的台风灾害倒伏绿化树木检测[J]. 遥感技术与应用, 2021, 36(3): 533-543.

Hongyan Liao,Xiaocheng Zhou,Hongyu Huang. Detection of Lodging Landscape Trees in Typhoon Disaster based on Unmanned Aerial Vehicle Remote Sensing. Remote Sensing Technology and Application, 2021, 36(3): 533-543.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2021.3.0533        http://www.rsta.ac.cn/CN/Y2021/V36/I3/533

图1  台风过境前后影像对比图
图2  台风倒伏木提取技术路线图
图3  两期DSM差值图
特征名称定义式备注

可见光植被指数

VDVI

(2·G-R-B)(2·G+R+B)、B为可见光影像各波段均值,其值为[-1,1]
边界指数bv2(lv+wv)其中,bv为对象边界长度、lv为对象长度、wv为对象宽度,其值为 [1,+∞]
非对称性1/4VarX+VarY+VarXY2-VarX·VarY2(VarX+VarY)其中,VarX,VarY分别为x、y方向上的方差,其值为[0,1]
密度#Pv1+VarX+VarY其中,#Pv为内接椭圆的直径、VarX+VarY为内接椭圆的直径,其值为[0,+∞]
紧密度lv+wv#Pv其中,#Pv为对象包含的总像元数,其值为[0,+∞]

归一化表面模型

nDSM

DSM-DEM其中,DSM为数字表面高程模型、DEM为数字高程模型,其值为[-∞,+∞]
两期DSM差值DSM1-DSM2其中DSM1、DSM2为台风过境前后的DSM
椭圆拟合性2#x,yPv:εv(x,y)1#Pv-1其中,εv(x,y)为一个对象的椭圆直径,其值为[0,1]
主方向180°πtan-1VarXY,λ1-VarY+90°其中,λ1为分割后对象重心方向的特征向量的特征值,其值为[0,180]

波段比率

Ratio R/G/B

cˉk(v)k=1n1cˉk(v)其中,cˉk(v)为对象的平均值,其值为[0,1]
圆度εvmax-εvmin其中,εvmax内接椭圆的短半径、εvmin内接椭圆的长半径,其值为[0,+∞]
长度#Pvγv其中,γv为分割对象的长宽比,其值为[0,+∞]
形状指数bv/(4#Pv)表示对象的边界长度与面积的比值,其值为[0,+∞]
表1  最优特征子集汇总表
图4  控制点实测高程值与提取高程值关系图
图5  实测树高与对应点DSM差值关系图
图6  实测胸径与提取胸径关系图
图7  单时相与多时相提取结果图
数据源方法

提取

株数/棵

正提

株数/棵

遗漏

株数/棵

误判

株数/棵

OA/%PC/%OE/%CE/%
单时相阈值分类715491763.3876.0614.2826.99
RF分类534716658.4988.7925.399.52
多时相阈值分类585211670.6989.6617.469.52
RF分类63558874.6087.3012.7012.70
表2  精度评价结果表
1 Yin Chengtuan, Zhang Jinshan, Xiong Mengjie, et al. Trend Analysis of Typhoon and Strom Surge Disaster on the South China Sea Coast of China[J]. Journal of Tropical Oceanography,2019,38(1):35-42.
1 殷成团, 张金善, 熊梦婕,等. 我国南海沿海台风及暴潮灾害趋势分析[J]. 热带海洋学报, 2019,38(1):35-42.
2 Thompson B K, Escobedo F J, Staudhammer C L, et al. Modeling Hurricane-caused Urban Forest Debris in Houston, Texas[J]. Landscape and Urban Planning, 2011,101(3):286-297. doi:10.1016/j.landurbplan.2011.02.034.
doi: 10.1016/j.landurbplan.2011.02.034
3 Staudhammer C, Escobedo F, Lawrence A, et al. Rapid Assessment of Change and Hurricane Impacts to Houston's Urban Forest Structure[J]. Arboriculture &Amp; Urban Forestry, 2011,37(2):60-66.
4 Szantoi Z, Malone S, Escobedo F, et al. A Tool for Rapid Post-hurricane Urban Tree Debris Estimates Using High Resolution Aerial Imagery[J]. International Journal of Applied Earth Observation and Geoinformation,2012,18:548-556. doi:10.1016/j.jag.2011.10.009.
doi: 10.1016/j.jag.2011.10.009
5 Büyüksalih I, Bayburt S, Schardt M, et al. Forest Stem Volume Calculation Using Airborne LiDAR Data[J]. ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2017,XLII-1/W1:265-270. doi:10.5194/isprs-archives-XLII-1-W1-265-2017.
doi: 10.5194/isprs-archives-XLII-1-W1-265-2017
6 Goodbody T R H, Coops N C, Tompalski P, et al. Updating Residual Stem Volume Estimates Using ALS- and UAV-Acquired Stereo-Photogrammetric Point Clouds[J]. International Journal of Remote Sensing, 2017,38(8-10):2938-2953. doi: 10.1080/01431161.2016.1219425.
doi: 10.1080/01431161.2016.1219425
7 Liang Xiaojun, Pang Yong, Chen Bowei, et al. Accurate Measurement of Individual Tree Position based on DBH Extraction of Terrestrial Laser Scanning, 2020,33(4):67-74.[梁晓军, 庞勇, 陈博伟. 基于地基激光雷达胸径提取的单木位置精确测量[J]. 林业科学研究, 2020,33(4):67-74.]
8 Geng Lin, Li Mingze, Fan Wenyi, et al. Individual Tree Structure Parameters and Effective Crown of the Stand Extraction base on Airborn LiDAR Data[J]. Scientia Silvae Sinicae, 2018,54(7): 62-72.
8 耿林, 李明泽, 范文仪,等. 基于机载LiDAR的单木结构参数及林分有效冠的提取[J]. 林业科学, 2018,54(7):62-72.
9 Eamer J B R, Walker I J. Quantifying Sand Storage Capacity of Large Woody Debris on Beaches Using LiDAR[J]. Geomorphology, 2010,118(1-2):33-47. doi: 10.1016/j.geomorph.2009.12.006.
doi: 10.1016/j.geomorph.2009.12.006
10 Lindberg E, Hollaus M, Mücke W, et al. Detection of Lying Tree Stems from Airborne Laser Scanning Data Using a Line Template Matching Algorithm[J]. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, 2013,II-5/W2:169-174.doi:10.5194/isprsannals-II-5-W2-169-2013.
doi: 10.5194/isprsannals-II-5-W2-169-2013
11 Nyström M, Holmgren J, Fransson J E S, et al. Detection of Windthrown Trees Using Airborne Laser Scanning[J]. International Journal of Applied Earth Observation and Geoinformation, 2014,30:21-29.doi: 10.1016/j.jag.2014.01.012
doi: 10.1016/j.jag.2014.01.012
12 Díaz-Varela R, De La Rosa R, León L, et al. High-resolution Airborne UAV Imagery to Assess Olive Tree Crown Parameters Using 3D Photo Reconstruction: Application in Breeding Trials[J]. Remote Sensing, 2015,7(4):4213-4232.doi: 10.3390/rs70404213.
doi: 10.3390/rs70404213
13 Guerra-Hernandez J, Gonzalez-Ferreiro E, Sarmento A, et al. Short Communication. Using High Resolution UAV Imagery to Estimate Tree Variables in Pinus Pinea Plantation in Portugal[J]. Forest Systems, 2016,25(2):C9.doi: 10.5424/fs/2016252-08895.
doi: 10.5424/fs/2016252-08895
14 Xia Yan,Huang Liang,Wang Xiaoxuan,et al. Fine Extraction of Tobacco based on UAV Images[J].Remote Sensing Technology and Application,2020,35(5):1158-1166.
14 夏炎,黄亮,王枭轩,等.基于无人机影像的烟草精细提取[J].遥感技术与应用,2020,35(5):1158-1166.
15 Zarco-Tejada P J, Diaz-Varela R, Angileri V, et al. Tree Height Quantification Using Very High Resolution Imagery Acquired from an Unmanned Aerial Vehicle (UAV) and Automatic 3D Photo-Reconstruction Methods[J]. European Journal of Agronomy,2014,55:89-99.doi:10.1016/j.eja.2014. 01.004.
doi: 10.1016/j.eja.2014. 01.004
16 Windrim L, Bryson M, Mclean M, et al. Automated Mapping of Woody Debris over Harvested Forest Plantations Using UAVs, High-Resolution Imagery, and Machine Learning[J]. Remote Sensing,2019,11(6):733.doi:10.3390/rs1106 0733.
doi: 10.3390/rs1106 0733
17 Duan F, Wan Y, Deng L. A Novel Approach for Coarse-to-Fine Windthrown Tree Extraction based on Unmanned Aerial Vehicle Images[J]. Remote Sensing, 2017,9(4):306.doi:10.3390/rs9040306.
doi: 10.3390/rs9040306
18 Tang Jianxiong, Xu Lilai, Li Yanmin, et al. Assessing The Damage Caused by Urban Green Space Ecosystem Service based on UAV Remote Sensing[J]. Journalist of Natural Disasters, 2018,27(3): 153-161.
18 汤剑雄, 徐礼来, 李彦旻,等. 基于无人机遥感的台风对城市树木生态系统服务的损失评估[J]. 自然灾害学报, 2018,27(3):153-161.
19 Li Zhixue, Yan Zike, Zhang Xi. Discussion on Key Technology and Application of UAV Survey Data Processing[J]. Bulletin of Surveying and Mapping, 2017,(S1):42-46[李志学, 颜紫科, 张曦. 无人机测绘数据处理关键技术及应用探究[J]. 测绘通报, 2017,():42-46.]
20 Zhang Yali, Li Yunfeng, Chen Hongtao. Palmprint Recognition based on Highpass Filter and Principle Components Character of LBP[J]. Techniques of Automation and Application, 2010,29(4): 16-19,26.
20 张亚莉, 李云峰, 陈红涛. 基于高通滤波及LBP主成分特征的一种掌纹识别方法[J]. 模式识别与仿真, 2010,29(4):16-19, 26.
21 Yan Hongping, Yu Bing. The Principal Component Analysis for RS Image Processing[J]. Resources Environment & Engineering, 2006,20(2): 168-170.
21 严红萍, 俞兵. 主成分分析在遥感图像处理中的应用[J]. 资源环境与工程, 2006,20(2): 168-170.
22 Wu Bo, Zhu Qindong, Gao Haiyan, et al. Feature Selection based on Maximal Mutual Information Criterion in Object-Oriented Classification[J]. Remote Sensing for Land&Resources, 2009,81(3):30-34.
22 吴波, 朱勤东, 高海燕,等. 面向对象影像分类中基于最大化互信息的特征选择[J]. 国土资源遥感, 2009,81(3):30-34.
23 Dong Zhanjie, Mao Zhengyuan. Methodological Research on Road Extraction based on Characteristics of Road Greenbelts in Remotely Sensed Imagery[J]. Remote Sensing for Land&Resources, 2011,83(2):43-46.
23 董占杰, 毛政元. 基于道路绿地特征的遥感影像道路信息提取方法研究[J]. 国土资源遥感, 2011,83(2):43-46.
24 Bao Wenxia, Yu Guofen, Zhu Ming, et al. Image Matching Algorithm based on Elliptic Metric Spectral Feature[J]. Journal of Southeast University (Natural Science Edition), 2018, 48(3):11-16.
24 鲍文霞, 余国芬, 朱明,等. 基于椭圆形度量谱特征的图像匹配算法[J]. 东南大学学报(自然科学版), 2018, 48(3):11-16.
25 Du Peijun, Chen Yunhao, Fang Tao, et al. Study on the Extraction and Applications of Spectral Feature in Hyperspectral Remote Sensing[J].Journal of China University of Mining & Technology, 2003,18(5):34-38.
25 杜培军, 陈云浩, 方涛,等. 高光谱遥感数据光谱特征的提取与应用[J]. 中国矿业大学学报, 2003,18(5):34-38.
26 Wang Xiaoqin,Wang Miaomiao,Wang Shaoqiang,et al. Extraction of Vegetation Information from Visible Unmanned Aerial Vehicle Images[J]. Transactions of the Chinese Society of Agricultural Engineering, 2015,31(5): 152-157.
26 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): 152-157.
27 Sathya P, Kayalvizhi R. Optimal Segmentation of Brain MRI based on Adaptive Bacterial Foraging Algorithm[J]. Neurocomputing, 2011, 74(14-15):2299-2313. doi:10.1016/j.neucom.2011.03.010.
doi: 10.1016/j.neucom.2011.03.010
28 Song Rongjie, Ning Jifeng, Chang Qingrui, et al. Kiwifruit Orchard Mapping based on Wavelet Textures and Random Forest[J]. Journal of Agricultural Machinery, 2018,49(4): 222-231.
28 宋荣杰, 宁纪锋, 常庆瑞,等. 基于小波纹理和随机森林的猕猴桃果园遥感提取[J]. 农业机械学报, 2018,49(4): 222-231.
29 He Yi, Zhou Xiaocheng, Huang Hongyu, et al. Counting Tree Number in Subtropical Districts based on UAV Remote Sensing Image[J]. Remote Sensing Technology and Application, 2018,33(1): 168-176.
29 何艺, 周小成, 黄洪宇,等. 基于无人机遥感的亚热带森林林分株数提取[J]. 遥感技术与应用, 2018,33(1): 168-176.
30 Sun Yuanhui,Xu Zhiyong,Zhang Jianlin,et al.Feature Enhan-cement Algorithm for Single Shot Detector based on Deep Learning[J]. Semiconductor Optoelectronics, 2019, 40(1): 108-111.
30 孙元辉,徐智勇,张建林,等.基于深度学习的单步目标检测器特征增强算法[J].半导体光电,2019,40(1):108-111.
[1] 帅艳民,杨健,吴昊,邵聪颖,徐辛超,刘明岳,刘涛,梁继. 基于无人机观测的水稻冠层样方多角度反射特点分析[J]. 遥感技术与应用, 2021, 36(2): 342-352.
[2] 张少伟,惠刚盈,韩宗涛,孙珊珊,田昕. 基于光学多光谱与SAR遥感特征快速优化的大区域森林地上生物量估测[J]. 遥感技术与应用, 2019, 34(5): 925-938.
[3] 何艺,周小成,黄洪宇,许雪琴. 基于无人机遥感的亚热带森林林分株数提取[J]. 遥感技术与应用, 2018, 33(1): 168-176.
[4] 刘慧珺,苏红军,赵-波. 基于改进萤火虫算法的高光谱遥感多特征优化方法[J]. 遥感技术与应用, 2018, 33(1): 110-118.
[5] 吴健生,林 倩,李卫锋,刘建政,彭 建. 基于特征选择的土地整理地物识别规则的动态提取[J]. 遥感技术与应用, 2013, 28(5): 799-806.
[6] 高利鹏,赵华亮,刘明翔,张华. 基于遥感影像不透水层估算的震后城区损坏面积评估[J]. 遥感技术与应用, 2013, 28(4): 582-587.
[7] 于 欢,孔 博. 无人机遥感影像自动无缝拼接技术研究[J]. 遥感技术与应用, 2012, 27(3): 347-352.
[8] 苏红军, 杜培军. 高光谱数据特征选择与特征提取研究[J]. 遥感技术与应用, 2006, 21(4): 288-293.