摘要
为提高土地覆盖分类精度,本文应用SPOT.HRV卫星图象,将其空间信息(增强处理图象)叠加到光谱信息(原图象)上的方法编制土地覆盖类型图,并设立9个探讨项目,通过分类精度检验表明:用增强处理图象进行分类时PCC从88.1%提高到92.2%,区分精度从91.0%提高到96.5%,误分率从19.0%减少到7.5%。作业效率也明显提高。
The objective of this study is to evaluate the land cover classification accuracy for incorporating spatial information such as texture fatures and the enhancement images were made with Laplacian operator. It has been tested using SPOT·HRV multispectral data. 9 cases have been used to evaluate the approach and the classification accuracies have been compared. As a result, PCC(Probability of Correct Classification) and the Division Accuracy are increasde respectively from 88.1% to 92.2% and 91.0% to 96.5%. The Error Ratio is decreased from 19.0% to 7.5%.
出处
《干旱区地理》
CSCD
北大核心
1993年第3期52-58,共7页
Arid Land Geography
关键词
卫星图象
覆盖图
空间信息
spatial information enhancement image, division accuracy, PCC