干旱区生态环境知识资源中心(Arid): A Novel Desert Vegetation Extraction and Shadow Separation Method Based on Visible Light Images from Unmanned Aerial Vehicles

Arid

DOI	10.3390/su15042954
	A Novel Desert Vegetation Extraction and Shadow Separation Method Based on Visible Light Images from Unmanned Aerial Vehicles
	Lu, Yuefeng; Song, Zhenqi; Li, Yuqing; An, Zhichao; Zhao, Lan; Zan, Guosheng; Lu, Miao
通讯作者	Lu, M
来源期刊	SUSTAINABILITY
EISSN	2071-1050
出版年	2023
卷号	15 期号:4
英文摘要	Owing to factors such as climate change and human activities, ecological and environmental problems of land desertification have emerged in many regions around the world, among which the problem of land desertification in northwestern China is particularly serious. To grasp the trend of land desertification and the degree of natural vegetation degradation in northwest China is a basic prerequisite for managing the fragile ecological environment there. Visible light remote sensing images taken by a UAV can monitor the vegetation cover in desert areas on a large scale and with high time efficiency. However, as there are many low shrubs in desert areas, the shadows cast by them are darker, and the traditional RGB color-space-based vegetation index is affected by the shadow texture when extracting vegetation, so it is difficult to achieve high accuracy. For this reason, this paper proposes the Lab color-space-based vegetation index L2AVI (L-a-a vegetation index) to solve this problem. The EXG (excess green index), NGRDI (normalized green-red difference index), VDVI (visible band difference vegetation index), MGRVI (modified green-red vegetation index), and RGBVI (red-green-blue vegetation index) constructed based on RGB color space were used as control experiments in the three selected study areas. The results show that, although the extraction accuracies of the vegetation indices constructed based on RGB color space all reach more than 70%, these vegetation indices are all affected by the shadow texture to different degrees, and there are many problems of misdetection and omission. However, the accuracy of the L2AVI index can reach 99.20%, 99.73%, and 99.69%, respectively, avoiding the problem of omission due to vegetation shading and having a high extraction accuracy. Therefore, the L2AVI index can provide technical support and a decision basis for the protection and control of land desertification in northwest China.
英文关键词	land desertification UAV visible remote sensing imagery vegetation index shadow texture color space
类型	Article
语种	英语
开放获取类型	gold
收录类别	SCI-E ; SSCI
WOS记录号	WOS:000942058800001
WOS关键词	IDENTIFICATION ; INDEXES
WOS类目	Green & Sustainable Science & Technology ; Environmental Sciences ; Environmental Studies
WOS研究方向	Science & Technology - Other Topics ; Environmental Sciences & Ecology
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/398763
推荐引用方式 GB/T 7714	Lu, Yuefeng,Song, Zhenqi,Li, Yuqing,et al. A Novel Desert Vegetation Extraction and Shadow Separation Method Based on Visible Light Images from Unmanned Aerial Vehicles[J],2023,15(4).
APA	Lu, Yuefeng.,Song, Zhenqi.,Li, Yuqing.,An, Zhichao.,Zhao, Lan.,...&Lu, Miao.(2023).A Novel Desert Vegetation Extraction and Shadow Separation Method Based on Visible Light Images from Unmanned Aerial Vehicles.SUSTAINABILITY,15(4).
MLA	Lu, Yuefeng,et al."A Novel Desert Vegetation Extraction and Shadow Separation Method Based on Visible Light Images from Unmanned Aerial Vehicles".SUSTAINABILITY 15.4(2023).