基于无人机高光谱影像的薇甘菊分布提取研究——以云南德宏州为例
作者:
基金项目:

云南省产业技术领军人才计划项目;林业公益性行业科研专项经费(201504305)资助


Distribution Extraction of Mikania micrantha Based on UAV Hyperspectral Image: A Case Study in Dehong, Yunnan Province, China
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [33]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    为有效控制薇甘菊入侵,及时掌握其空间分布和动态变化,基于无人机高光谱数据,通过深度学习(DL)、支持向量机(SVM)、随机森林(RF)等方法提取云南省德宏州微甘菊分布情况。结果表明,DL、SVM和RF等3种方法均有效实现了薇甘菊的分布提取,以DL方法的提取效果最佳,制图精度和用户精度分别为96.61%和95.00%;其次为RF方法,制图精度和用户精度分别为94.83%和91.67%;SVM方法的制图精度和用户精度分别为92.45%和81.67%。这3种方法均能很好提取薇甘菊集中分布区域,且DL和RF方法对零散分布薇甘菊的识别效果优于SVM。因此,无人机高光谱影像为薇甘菊的监测、预警和精准防治提供了支撑和依据,对保护当地生态系统安全具有重要意义。

    Abstract:

    As a highly dangerous alien species, Mikania micrantha has become a serious threat to the ecosystem health and biodiversity of invasive sites. In order to effectively control its invasion, and grasp its spatial distribution and dynamic change, its distribution in Dehong Prefecture, Yunnan Province was extracted by deep learning (DL), support vector machine (SVM) and random forest (RF) methods based on UAV hyperspectral data. The results showed that three methods could effectively extract the distribution of M. micrantha, in which DL method had the best extraction effect with mapping accuracy and user accuracy of 96.61% and 95.00%, respectively, followed by the RF method with those of 94.83% and 91.67%, and the SVM method with those of 92.45% and 81.67%. All three methods could well extract the concentrated distribution areas of M. micrantha, the methods of DL and RF were better than SVM in identification of fragmented distribution of M. micrantha. Therefore, UAV hyperspectral images would provide supports and basis for the monitoring, early warning and precise control of M. micrantha invasion, which was of great significance to protect the security of local ecosystems.

    参考文献
    [1] HOLM L G, PLUCKNETT D L, PANCHO J V, et al. The World's Worst Weeds:Distribution and Biology[M]. Honolulu, USA:University Press of Hawaii, 1977:320.
    [2] TAI H K, GU Z L, XU Y C, et al. Recent advance in quarantinable weed Mikania micrantha H. B. K.[J]. J Agric Catastrophol, 2011, 1(2):59-62. doi:10.19383/j.cnki.nyzhyj.2011.02.016.太红坤, 顾中量, 徐云川, 等. 检疫性杂草薇甘菊的研究进展[J]. 农业灾害研究, 2011, 1(2):59-62. doi:10.19383/j.cnki.nyzhyj.2011. 02.016.
    [3] LOWE S, BROWNE M, BOUDJELAS S, et al. 100 of the World's Worst Invasive Alien Species[M]. Auckland, New Zealand:IUCN/SSC Invasive Species Specialist Group (ISSG), 2000:1-12.
    [4] DAY M D, KAWI A, KURIKA K, et al. Mikania micrantha Kunth (Asteraceae) (Mile-a-Minute):Its distribution and physical and socioeconomic impacts in Papua New Guinea[J]. Pacif Sci, 2012, 66(2):213-223. doi:10.2984/66.2.8.
    [5] QIU L, YANG Z G, CHEN W, et al. Forecasting analysis potential space distribution of Mikania micrantha in Guangzhou[J]. J CS Univ For Technol, 2010, 30(5):128-133. doi:10.14067/j.cnki.1673-923x. 2010.05.016.邱罗, 杨志高, 陈伟, 等. 广州薇甘菊潜在空间分布预测分析[J]. 中南林业科技大学学报, 2010, 30(5):128-133. doi:10.14067/j.cnki. 1673-923x.2010.05.016.
    [6] LI Y Q, JI M, LIU L, et al. Progress in prevention and control of Mikania micrantha in Yunnan forestland[J]. J Biosafety, 2019, 28(1):1-6.李云琴, 季梅, 刘凌, 等. 云南省林地薇甘菊防控研究进展[J]. 生物安全学报, 2019, 28(1):1-6.
    [7] ZAN Q J, WANG Y J, WANG B S, et al. The distribution and harm of the exotic weed Mikania micrantha[J]. Chin J Ecol, 2000, 19(6):5861,77. doi:10.13292/j.1000-4890.2000.0095.昝启杰, 王勇军, 王伯荪, 等. 外来杂草薇甘菊的分布及危害[J]. 生态学杂志, 2000, 19(6):58-61,77. doi:10.13292/j.1000-4890.2000.0095.
    [8] ZHONG X Q, HUANG Z, SI H, et al. Analysis of ecological-economic loss caused by weed Mikania micrantha on Neilingding Island, Shenzhen, China[J]. J Trop Subtrop Bot, 2004, 12(2):167-170. doi:10. 3969/j.issn.1005-3395.2004.02.012.钟晓青, 黄卓, 司寰, 等. 深圳内伶仃岛薇甘菊危害的生态经济损失分析[J]. 热带亚热带植物学报, 2004, 12(2):167-170. doi:10. 3969/j.issn.1005-3395.2004.02.012.
    [9] HE D B, KE S X, ZHOU P Y, et al. Research on distribution pattern and control policies of Mikania micrantha Kunth in Dehong Prefecture[J]. CS For Invent Plan, 2016, 35(4):35-41. doi:10.16166/j.cnki.cn431095.2016.04.008.贺东北, 柯善新, 周平阳, 等. 德宏州薇甘菊分布规律与防控策略研究[J]. 中南林业调查规划, 2016, 35(4):35-41. doi:10.16166/j. cnki.cn43-1095.2016.04.008.
    [10] XU X W, ZE S Z, YANG B, et al. Research status of Mikania micrantha biological control and resource utilization[J]. Chin J Trop Agric, 2014, 34(12):75-84. doi:10.3969/j.issn.1009-2196.2014.12.019.徐小伟, 泽桑梓, 杨斌, 等. 薇甘菊的分布危害、生物防治及资源化利用研究现状与展望[J]. 热带农业科学, 2014, 34(12):75-84. doi:10.3969/j.issn.1009-2196.2014.12.019.
    [11] ZE S Z, JI M, YAN Z L, et al. Preliminary report of Mikania micrantha jeopardize status on Burma Road[J]. For Invent Plan, 2012, 37(5):67-70,74. doi:10.3969/j.issn.1671-3168.2012.05.017.泽桑梓, 季梅, 闫争亮, 等. 滇缅公路薇甘菊危害状况调查初报[J]. 林业调查规划, 2012, 37(5):67-70,74. doi:10.3969/j.issn.1671-3168. 2012.05.017.
    [12] HU J, LIN H, SUN H, et al. Precise extraction of Mikania micrantha information based on WorldView-2 data[J]. J CS Univ For Technol, 2015, 35(1):42-49. doi:10.14067/j.cnki.1673-923x.2015.01.009.胡佳, 林辉, 孙华, 等. 基于WorldView-2的薇甘菊信息精细提取[J]. 中南林业科技大学学报, 2015, 35(1):42-49. doi:10.14067/j.cnki. 1673-923x.2015.01.009.
    [13] LIU S, LIN H, SUN H, et al. Information extraction of Mikania micrantha based on Pleiades-1 data[J]. J CS Univ For Technol, 2014, 34(11):116-119. doi:10.3969/j.issn.1673-923X.2014.11.023.柳帅, 林辉, 孙华, 等. 基于Pleiades-1卫星数据薇甘菊信息提取[J]. 中南林业科技大学学报, 2014, 34(11):116-119. doi:10.3969/j. issn.1673-923X.2014.11.023.
    [14] BRADLEY B A. Remote detection of invasive plants:A review of spectral, textural and phenological approaches[J]. Biol Invasions, 2014, 16(7):1411-1425. doi:10.1007/s10530-013-0578-9.
    [15] ALVAREZ-TABOADA F, PAREDES C, JULIÁN-PELAZ J. Mapping of the invasive species Hakea sericea using unmanned aerial vehicle (UAV) and WorldView-2 imagery and an object-oriented approach[J]. Remote Sens, 2017, 9(9):913. doi:10.3390/rs9090913.
    [16] CHEN L, LIN H, SUN H. Remote sensing of a Mikania micrantha invasion in alien species with WordView-2 images[J]. J Zhejiang Agric For Univ, 2014, 31(2):185-189. doi:10.11833/j.issn.2095-0756.2014. 02.004.陈利, 林辉, 孙华. 基于WorldView-2影像的外来物种薇甘菊入侵遥感监测[J]. 浙江农林大学学报, 2014, 31(2):185-189. doi:10. 11833/j.issn.2095-0756.2014.02.004.
    [17] LIU Z W, LIU S Q, XIE J J. Research on refinement terrain surface features classification based on hyperspectral image of UAV[J]. Mod Inform Technol, 2020, 4(10):1-4,7. doi:10.19850/j.cnki.2096-4706. 2020.10.001.柳宗伟, 刘胜前, 谢佳君. 基于无人机高光谱影像的精细地物分类的研究[J]. 现代信息科技, 2020, 4(10):1-4,7. doi:10.19850/j.cnki. 2096-4706.2020.10.001.
    [18] LIU Y J, ZHANG G, WANG X, et al. Classification study of Mikania micrantha Kunth. from UAV hyperspectral image band selection[J]. Bull Surv Map, 2020(4):34-39,52. doi:10.13474/j.cnki.11-2246.2020. 0108.刘彦君, 张贵, 王潇, 等. 基于无人机高光谱影像波段选择的薇甘菊分类[J]. 测绘通报, 2020(4):34-39,52. doi:10.13474/j.cnki.112246.2020.0108.
    [19] GUO C C. Research on the classification method of land use type based on UAV remote sensing in irrigation district[D]. Yangling:Northwest Agricultrual & Forestry University, 2016:2-5.郭聪聪. 基于无人机遥感的灌区土地利用类型分类方法研究[D]. 杨凌:西北农林科技大学, 2016:2-5.
    [20] SUN Z Y, JING W L, QIAO X, et al. Identification and monitoring of blooming Mikania micrantha outbreak points based on UAV remote sensing[J]. Trop Geo, 2019, 39(4):482-491. doi:10.13284/j.cnki.rddl. 003153.孙中宇, 荆文龙, 乔曦, 等. 基于无人机遥感的盛花期薇甘菊爆发点识别与监测[J]. 热带地理, 2019, 39(4):482-491. doi:10.13284/j. cnki.rddl.003153.
    [21] FU X Y, ZE S Z, ZHOU X, et al. Study on potential suitable area of Mikania micrantha in Yunnan Province based on GIS[J]. J W China For Sci, 2015, 44(1):98-102. doi:10.16473/j.cnki.xblykx1972.2015.01.010.付小勇, 泽桑梓, 周晓, 等. 基于GIS的云南省薇甘菊潜在适生区研究[J]. 西部林业科学, 2015, 44(1):98-102. doi:10.16473/j.cnki. xblykx1972.2015.01.010.
    [22] ZHANG G Y, YANG J H, BI S B, et al. Invasive weed Mikania micrantha monitoring and risk analysis in Dehong[J]. Chin Agric Sci Bull, 2015, 31(15):187-192.张国云, 杨俊华, 毕生斌, 等. 德宏州入侵杂草薇甘菊调查监测及风险分析[J]. 中国农学通报, 2015, 31(15):187-192.
    [23] GAO L, YANG G J, WANG B S, et al. Soybean leaf area index retrieval with UAV (unmanned aerial vehicle) remote sensing imagery[J]. Chin J Eco-Agric, 2015, 23(7):868-876. doi:10.13930/j.cnki.cjea.150018.高林, 杨贵军, 王宝山, 等. 基于无人机遥感影像的大豆叶面积指数反演研究[J]. 中国生态农业学报, 2015, 23(7):868-876. doi:10. 13930/j.cnki.cjea.150018.
    [24] BOONPOOK W, TAN Y M, YE Y H, et al. A deep learning approach on building detection from unmanned aerial vehicle-based images in riverbank monitoring[J]. Sensors, 2018, 18(11):3921. doi:10.3390/s 18113921.
    [25] TAYLOR M A P. Critical transport infrastructure in urban areas:Impacts of traffic incidents assessed using accessibility-based network vulnerability analysis[J]. Growth Change, 2008, 39(4):593-616. doi:10.1111/j.1468-2257.2008.00448.x.
    [26] HU M Y. The study of tree species identification based on deeping learning method[D]. Lin'an:Zhejiang Agriculture & Forestry University, 2019:24.胡明越. 基于深度学习的树种识别算法研究[D]. 临安:浙江农林大学, 2019:24.
    [27] ZHANG R, MA J W. State of the art on remotely sensed data classification based on support vector machines[J]. Adv Earth Sci, 2009, 24(5):555-562. doi:10.3321/j.issn:1001-8166.2009.05.012.张睿, 马建文. 支持向量机在遥感数据分类中的应用新进展[J]. 地球科学进展, 2009, 24(5):555-562. doi:10.3321/j.issn:1001-8166. 2009.05.012.
    [28] ZANG S Y, ZHANG C, ZHANG L J, et al. Wetland remote sensing classification using support vector machine optimized with genetic algorithm:A case study in Honghe nature national reserve[J]. Sci Geol Sin, 2012, 32(4):434-441. doi:10.13249/j.cnki.sgs.2012.04.006.臧淑英, 张策, 张丽娟, 等. 遗传算法优化的支持向量机湿地遥感分类——以洪河国家级自然保护区为例[J]. 地理科学, 2012, 32(4):434-441. doi:10.13249/j.cnki.sgs.2012.04.006.
    [29] ZHOU Z L, SHA J M, FAN Y X, et al. Remote sensing land usage classification and landscape pattern analysis based on random forest[J]. Comput Syst Appl, 2020, 29(2):40-48. doi:10.15888/j.cnki.csa.007228.周正龙, 沙晋明, 范跃新, 等. 基于随机森林的遥感土地利用分类及景观格局分析[J]. 计算机系统应用, 2020, 29(2):40-48. doi:10. 15888/j.cnki.csa.007228.
    [30] VAN DER LINDEN S, RABE A, HELD M, et al. The EnMAP-box:A toolbox and application programming interface for EnMAP data processing[J]. Remote Sens, 2015, 7(9):11249-11266. doi:10.3390/rs 70911249.
    [31] LI Y Z, PAN Y Z, ZHU X F, et al. Comparison analysis on land cover area estimators:Confusion matrix calibration and regression[J]. Trans Chin Soc Agric Eng, 2013, 29(11):115-123. doi:10.3969/j.issn.10026819.2013.11.015.李宜展, 潘耀忠, 朱秀芳, 等. 土地覆盖类别面积混淆矩阵校正与回归遥感估算方法对比[J]. 农业工程学报, 2013, 29(11):115-123. doi:10.3969/j.issn.1002-6819.2013.11.015.
    [32] QI L, ZHAO C J, LI C J, et al. Accuracy of winter wheat identification based on multi-temporal CBERS-02 images[J]. Chin J Appl Ecol, 2008, 19(10):2201-2208.齐腊, 赵春江, 李存军, 等. 基于多时相中巴资源卫星影像的冬小麦分类精度[J]. 应用生态学报, 2008, 19(10):2201-2208.
    [33] TENG W X, WEN X R, WANG N, et al. Tree species classification and mapping based on deep transfer learning with unmanned aerial vehicle high resolution images[J]. Laser Optoelectr Prog, 2019, 56(7):072801.滕文秀, 温小荣, 王妮, 等. 基于深度迁移学习的无人机高分影像树种分类与制图[J]. 激光与光电子学进展, 2019, 56(7):072801.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

刘雪莲,石雷,李宇宸,刘梦盈,姚俊,马云强,杨绪兵.基于无人机高光谱影像的薇甘菊分布提取研究——以云南德宏州为例[J].热带亚热带植物学报,2021,29(6):579~588

复制
分享
文章指标
  • 点击次数:403
  • 下载次数: 537
  • HTML阅读次数: 879
  • 引用次数: 0
历史
  • 收稿日期:2021-01-21
  • 最后修改日期:2021-04-16
  • 在线发布日期: 2021-12-02
文章二维码