Relationships of image classification accuracy and variation of landscape statistics

CSpace

	Relationships of image classification accuracy and variation of landscape statistics
	Shao, G ; Liu, D ; Zhao, G
	2001-02-01
发表期刊	CANADIAN JOURNAL OF REMOTE SENSING
ISSN	0703-8992
卷号	27 期号:1 页码:35-45
摘要	Multiple classifications of a Landsat Thematic Mapper (TM) image resulted in 23 thematic maps for an area of 31,660 ha in central Indiana in the United States. Each map consists of four land use and land cover types (classes): urban, agricultural land, forest, and water A common set of reference data was randomly sampled from the image and was used to evaluate the classification accuracy of each of the 23 maps. The classification accuracy of these maps was between 77.6 to 89.2%. Landscape index values for nine landscape-level indices and nine class-level indices were derived from the 23 maps. Although the majority of the thematic maps were not significantly, different in overall accuracy, the landscape index values showed high variation among the maps. The results suggested that the variation of landscape index values is inversely, proportional to classification accuracy. Therefore, when classification accuracy is lower, the uncertainties of landscape characterization become higher Unfortunately, such uncertainties are not readily, predictable because landscape index values can be altered by the magnitude and spatial distribution of classification errors. Classification accuracy alone is not sufficient to ensure the accuracy of landscape characterization.
语种	英语
WOS研究方向	Remote Sensing
WOS类目	Remote Sensing
WOS记录号	WOS:000172767800005
出版者	CANADIAN AERONAUTICS SPACE INST
引用统计
文献类型	期刊论文
条目标识符	http://ir.amss.ac.cn/handle/2S8OKBNM/16873
专题	中国科学院数学与系统科学研究院
通讯作者	Shao, G
作者单位	1.Purdue Univ, Dept Forestry & Nat Resources, W Lafayette, IN 47907 USA 2.Chinese Acad Sci, Inst Appl Math, Beijing 100080, Peoples R China 3.S Carolina Dept Hlth & Environm Control, Div Biostat, Columbia, SC 29201 USA
推荐引用方式 GB/T 7714	Shao, G,Liu, D,Zhao, G. Relationships of image classification accuracy and variation of landscape statistics[J]. CANADIAN JOURNAL OF REMOTE SENSING,2001,27(1):35-45.
APA	Shao, G,Liu, D,&Zhao, G.(2001).Relationships of image classification accuracy and variation of landscape statistics.CANADIAN JOURNAL OF REMOTE SENSING,27(1),35-45.
MLA	Shao, G,et al."Relationships of image classification accuracy and variation of landscape statistics".CANADIAN JOURNAL OF REMOTE SENSING 27.1(2001):35-45.