Vegetation extraction method based on color indices from UAV images

doi:10.6046/gtzyyg.2016.01.12

Download: PDF(11234 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

Vegetation extraction plays a key role in such aspects as agricultural monitoring, ecological and environmental function evaluation. Traditionally, it is a labor input task before remotely sensed images are involved. Yet it is difficult to deal with conditions when clouds exist. Therefore, scenes become hopeful when unmanned aerial vehicle(UAV) images emerge in vegetation extraction, and hence this means is a low-cost and flexible way with high spatial resolution. High efficiency methods are therefore required to extract vegetation area automatically using UAV images, preferentially with various color indices always involved. The problem is that there is no evaluation of the effects of vegetation extraction with different color indices. In this paper, Weishan County of Shandong Province was chosen as the study area and four color vegetation indices comprising normalized green-red difference (NGRDI), excess green (ExG), excess green minus excess red (ExG-ExR) and green leaf index (GLI) were selected to extract vegetation information from UAV images with OTSU threshold values. The results show that all the color indices are capable of extracting vegetation area with accuracies above 90%. ExG-ExR index could more likely generate higher accurate results than other indices. ExG and GLI indices generate relatively high accurate and stable results, and could also be used for effective vegetation extraction. For images with high RGB value contrast between vegetation and background, all the color indices work especially well. Further analysis has revealed that accuracies of vegetation extraction have positive relationship with the proportion of winter wheat in images, and exhibit negative relationship with the proportion of broadleaf trees, buildings and roads.

Keywords UAV aerial photography emergency mapping Photoscan Pro

TP751.1

Issue Date: 27 November 2015

	Service

	E-mail this article
	E-mail Alert
	RSS
	Articles by authors

	ZHAO Yunjing
	GONG Xucai
	DU Wenjun
	ZHOU Li

Cite this article:

ZHAO Yunjing,GONG Xucai,DU Wenjun, et al. Vegetation extraction method based on color indices from UAV images[J]. REMOTE SENSING FOR LAND & RESOURCES, 2016, 28(1): 78-86.

URL:

https://www.gtzyyg.com/EN/10.6046/gtzyyg.2016.01.12 OR https://www.gtzyyg.com/EN/Y2016/V28/I1/78

[1] Torres-Sánchez J,Peña-Barragán J M,Gómez-Candón D,et al.Imagery from Unmanned Aerial Vehicles for Early Site Specific Weed Management[M]//Precision Agriculture.The Netherlands:Wageningen Academic Publishers,2013:193-199.

[2] Motohka T,Nasahara K N,Oguma H,et al.Applicability of green-red vegetation index for remote sensing of vegetation phenology[J].Remote Sensing,2010,2(10):2369-2387.

[3] Woebbecke D M,Meyer G E,Bargen K V,et al.Color indices for weed identification under various soil,residue, and lighting conditions[J].Transactions of the ASABE,1995,38(1):259-269.

[4] 迟德霞,张伟,王洋.基于EXG因子的水稻秧苗图像分割[J].安徽农业科学,2012,40(36):17902-17903. Chi D X,Zhang W,Wang Y.Segmentation of rice seedling image based on EXG factor[J].Journal of Anhui Agricultural Sciences,2012,40(36):17902-17903.

[5] 胡健波,张璐,黄伟,等.基于数码照片的草地植被覆盖度快速提取方法[J].草业科学,2011,28(9):1661-1665. Hu J B,Zhang L,Huang W,et al.Quickly determining grassland cover using the digital image[J].Pratacultural Science,2011,28(9):1661-1665.

[6] 龙满生,何东健.玉米苗期杂草的计算机识别技术研究[J].农业工程学报,2007,23(7):139-144. Long M S,He D J.Weed identification from corn seedling based on computer vision[J].Transactions of the CSAE,2007,23(7):139-144.

[7] Meyer G E,Neto J C.Verification of color vegetation indices for automated crop imaging applications[J].Computers and Electronics in Agriculture,2008,63(2):282-293.

[8] Hunt E R Jr,Cavigelli M,Daughtry C S T,et al.Evaluation of digital photography from model aircraft for remote sensing of crop biomass and nitrogen status[J].Precision Agriculture,2005,6(4):359-378.

[9] Louhaichi M,Borman M M,Johnson D E.Spatially located platform and aerial photography for documentation of grazing impacts on wheat[J].Geocarto International,2001,16(1):65-70.

[10] Hunt E R Jr,Daughtry C S T,Eitel J U H,et al.Remote sensing leaf chlorophyll content using a visible band index[J].Agronomy Journal,2001,103(4):1090-1099.

[11] Hunt E R Jr,Doraiswamy P C,McMurtrey J E,et al.A visible band index for remote sensing leaf chlorophyll content at the canopy scale[J].International Journal of Applied Earth Observation and Geoinformation,2013,21:103-112.

[12] Shimada S,Matsumoto J,Sekiyama A,et al.A new spectral index to detect Poaceae grass abundance in Mongolian grasslands[J].Advances in Space Research,2012,50(9):1266-1273.

[13] Meyer G E,Neto J C,Jones D D,et al.Intensified fuzzy clusters for classifying plant,soil,and residue regions of interest from color images[J].Computers and Electronics in Agriculture,2004,42(3):161-180.

[14] Gonzalez R C,Woods R E. Digital Image Processing[M].3rd ed.Beijing:Publishing House of Electronics Industry,2010:479-483.