基于无人机多光谱的沼泽植被识别方法

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (6481 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract This paper established machine learning models to classify swamp vegetation communities based on high-resolution UAV multispectral images. In Honghe National Nature Reserve, typical sample areas were selected in the core area, buffer zone and experimental area and ortho-images of these areas were acquired using low-altitude UAVs with RGB and multispectral cameras. Multidimensional datasets were then derived from multiresolution segmentation of ortho-images, and established four classification scenarios. The object-based random forest (RF) algorithm was used to classify vegetation communities after feature selection and parameters (mtry and ntree) optimization and tuning. This algorithm also could rank the importance of each feature in multidimensional datasets and eliminat data redundancy accordingly. The results showed that:The optimized object-based RF algorithm had a high recognition ability for swamp vegetation. The scenario 4 (combination of spectral bands, texture features, geometric features, location features, surface elevation information and vegetation indexes) in the core area obtained the highest overall accuracy (87.12%), and the kappa value was 0.850 at the 95% confidence interval, which was 12.27% higher than scenario 2 (combining spectral bands, geometric features and location features), and the kappa value improved 0.140; For an identification accuracy of typical swamp vegetation, the classification of the reed achieved the highest user's accuracy of above 88%, and its producer's accuracy was higher than 90%. The classification of Calamagrostis angustifolia also achieved over 85% of producer's accuracy, but its user's accuracy (78%) was lower in the core area. This method can be used as an effective method to identify swamp vegetation communities and provide more accurate data support for studying dynamic changes of wetland ecological environment.

Key words： UAV multi-spectral data random forest algorithm multidimensional data set variable selection parameter tuning

Received: 30 September 2020

PACS:

X171

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	ZUO Ping-ping
	FU Bo-lin
	LAN Fei-wu
	XIE Shu-yu
	HE Hong-chang
	FAN Dong-lin
	LOU Pei-qing

Cite this article:

ZUO Ping-ping,FU Bo-lin,LAN Fei-wu等. Classification method of swamp vegetation using UAV multispectral data[J]. CHINA ENVIRONMENTAL SCIENCECE, 2021, 41(5): 2399-2410.

URL:

http://www.zghjkx.com.cn/EN/ OR http://www.zghjkx.com.cn/EN/Y2021/V41/I5/2399

[1]	Mitsch W J. Restoration of our lakes and rivers with wetlands-an important application of ecological engineering[J]. Water Science and Technology, 1995,31(8):167-177.
[2]	Guo M, Li J, Sheng C, et al. A review of wetland remote sensing[J]. Sensors, 2017,17(4):777.
[3]	Kokaly R F, Despain D G, Clark R N, et al. Mapping vegetation in Yellowstone National Park using spectral feature analysis of AVIRIS data[J]. Remote sensing of environment, 2003,84(3):437-456.
[4]	Yuan L, Zhang L. Identification of the spectral characteristics of submerged plant Vallisneria spiralis[J]. Acta Ecologica Sinica, 2006,26(4):1005-1010.
[5]	Dennison W C, Orth R J, Moore K A, et al. Assessing water quality with submersed aquatic vegetation[J]. BioScience, 1993,43(2):86-94.
[6]	张磊,宫兆宁,王启为,等. Sentinel-2影像多特征优选的黄河三角洲湿地信息提取[J]. 遥感学报, 2019,23(2):313-326. Zhang L, Gong Z N, Wang Q W, et al. Extraction of Yellow River Delta wetland information based on multi-feature optimization of Sentinel-2 image[J]. Journal of Remote Sensing, 2019,23(2):313-326.
[7]	程琳琳,董雪梅,詹佳琪,等.基于面向对象的GF-1遥感影像采煤沉陷区湿地分类[J]. 农业工程学报, 2018,34(9):240-247. Cheng L L, Dong X M, Zhan J Q, et al. Wetland classification based on object-oriented GF-1remote sensing images in coal mining subsidence area[J]. Transactions of the Chinese Society of Agricultural Engineering, 2018,34(9):240-247.
[8]	李恒凯,吴娇,王秀丽.基于GF-1影像的东江流域面向对象土地利用分类[J]. 农业工程学报, 2018,34(10):245-252. Li H K, Wu J, Wang X L. Object-oriented land use classification of Dongjiang basin based on GF-1 image[J]. Transactions of the Chinese Society of Agricultural Engineering, 2018,34(10):245-252.
[9]	王猛,张新长,王家耀,等.结合随机森林面向对象的森林资源分类[J]. 测绘学报, 2020,49(2):235-244. Wang M, Zhang X C, Wang J Y, et al. Object-oriented classification of forest resources with random forest[J]. Journal of Surveying and Mapping, 2020,49(2):235-244.
[10]	Lou P Q, Fu B L, He H C, et al. An optimized object-based random forest algorithm for marsh vegetation mapping using high-spatial-resolution GF-1and ZY-3data[J]. Remote Sensing, 2020,12(8):1270.
[11]	Mahdavi S, Salehi B, Amani M, et al. A dynamic classification scheme for mapping spectrally similar classes:Application to wetland classification[J]. International Journal of Applied Earth Observation and Geoinformation, 2019,83:101914.
[12]	Böhler J E, Schaepman M E, Kneubühler M. Crop classification in a heterogeneous arable landscape using uncalibrated UAV data[J]. Remote Sensing, 2018,10(8):1282.
[13]	Pajares G. Overview and current status of remote sensing applications based on unmanned aerial vehicles (UAVs)[J]. Photogrammetric Engineering & Remote Sensing, 2015,81(4):281-330.
[14]	Shahbazi M, Théau J, Ménard P. Recent applications of unmanned aerial imagery in natural resource management[J]. GIScience & Remote Sensing, 2014,51(4):339-365.
[15]	Latif M A. An agricultural perspective on flying sensors:State of the art, challenges, and future directions[J]. IEEE Geoscience and Remote Sensing Magazine, 2018,6(4):10-22.
[16]	Pande-Chhetri R, Abd-Elrahman A, Liu T, et al. Object-based classification of wetland vegetation using very high-resolution unmanned air system imagery[J]. European Journal of Remote Sensing, 2017,50(1):564-576.
[17]	De Giglio M, Greggio N, Goffo F, et al. Comparison of pixel-and object-based classification methods of unmanned aerial vehicle data applied to coastal dune vegetation communities:Casal borsetti case study[J]. Remote Sensing, 2019,11(12):1416.
[18]	Wu Q, Zhong R, Zhao W, et al. A comparison of pixel-based decision tree and object-based Support Vector Machine methods for land-cover classification based on aerial images and airborne lidar data[J]. International Journal of Remote Sensing, 2017,38(23):7176-7195.
[19]	肖武,任河,吕雪娇,等.基于无人机遥感的高潜水位采煤沉陷湿地植被分类[J]. 农业机械学报, 2019,50(2):177-186. Xiao W, Ren H, Lu X J, et al. Vegetation classification of subsided wetlands in coal mining at high phreatic level based on remote sensing by drones[J]. Transactions of the Chinese Society of Agricultural Machinery, 2019,50(2):177-186.
[20]	娄佩卿,陈晓雨,王疏桐,等.基于无人机影像的喀斯特农耕区地物识别——以桂林市为例[J]. 国土资源遥感, 2020,32(1):216-223. Lou P Q, Chen X Y, Wang S T, et al. Feature recognition in karst farming areas based on UAV images:Taking Guilin as an example[J]. Remote Sensing for Land and Resources, 2020,32(1):216-223.
[21]	刘舒,朱航.基于超高空间分辩率无人机影像的面向对象土地利用分类方法[J]. 农业工程学报, 2020,36(2):87-94. Liu S, Zhu H. Object-oriented land use classification method based on ultra-high spatial resolution UAV images[J]. Transactions of the Chinese Society of Agricultural Engineering, 2020,36(2):87-94.
[22]	耿仁方,付波霖,蔡江涛,等.基于无人机影像和面向对象随机森林算法的岩溶湿地植被识别方法研究[J]. 地球信息科学学报, 2019, 21(8):1295-1306. Geng R F, Fu B L, Cai J T, et al. Research on karst wetland vegetation identification method based on UAV image and object-oriented random forest algorithm[J]. Journal of Geo-Information Science, 2019,21(8):12951306.
[23]	朱宝光,董树斌,朱丽萍,等.洪河国家级自然保护区湿地功能区保育与湿地补偿研究[J]. 湿地科学与管理, 2006,(3):25-28. Zhu B G, Dong S B, Zhu L P, et al. Research on wetland function area conservation and wetland compensation in Honghe National Nature Reserve[J]. Wetland Science and Management, 2006,(3):25-28.
[24]	Dragut L, Tiede D, Levick S R. ESP:a tool to estimate scale parameter for multiresolution image segmentation of remotely sensed data[J]. International Journal of Geographical Information Science, 2010,24(6):859-871.
[25]	Dronova I. Object-based image analysis in wetland research:A review[J]. Remote Sensing, 2015,7(5):6380-6413.
[26]	魏鹏飞,徐新刚,李中元,等.基于无人机多光谱影像的夏玉米叶片氮含量遥感估测[J]. 农业工程学报, 2019,35(8):126-133,335. Wei P F, Xu X G, Li Z Y, et al. Remote sensing estimation of nitrogen content in summer maize leaves based on UAV multispectral images[J]. Transactions of the Chinese Society of Agricultural Engineering, 2019,35(8):126-133,335.
[27]	Villoslada M, Bergamo T F, Ward R D, et al. Fine scale plant community assessment in coastal meadows using UAV based multispectral data[J]. Ecological Indicators, 2020,111:105979.
[28]	Suo C, McGovern E, Gilmer A. Coastal dune vegetation mapping using a multispectral sensor mounted on an UAS[J]. Remote Sensing, 2019,11(15):1814.
[29]	Breiman L. Random forests[J]. Machine learning, 2001,45(1):5-32.
[30]	Phiri D, Morgenroth J, Xu C. Four decades of land cover and forest connectivity study in Zambia-An object-based image analysis approach[J]. International Journal of Applied Earth Observation and Geoinformation, 2019,79:97-109.
[31]	Nguyen U, Glenn E P, Dang T D, et al. Mapping vegetation types in semi-arid riparian regions using random forest and object-based image approach:A case study of the Colorado River Ecosystem, Grand Canyon, Arizona[J]. Ecological Informatics, 2019,50:43-50.