LI Bin-bing,HUANG Lei,LIU Da-wei.Research for Optimal Scale on the Remote Sensing Image Recognition of Gully Distribution in Loess Hilly-Gully Region[J].Research of Soil and Water Conservation,2014,21(04):158-162.
黄土丘陵沟壑区切沟分布的遥感图像识别最优尺度研究
- Title:
- Research for Optimal Scale on the Remote Sensing Image Recognition of Gully Distribution in Loess Hilly-Gully Region
- 分类号:
- S157.1
- 摘要:
- 本研究提出了一种基于最优尺度分割和阈值统计优化的切沟提取新方法。首先，通过灰度共生矩阵（GLCM）内部对象方差和空间自相关系数，建立了一个最优分割尺度选择目标函数，经试验得到了研究区内农路、切沟、耕地（山坡地、梯田）、林地的最优分割尺度分别为24，31，36，42；在影像分割基础上，提出了切沟提取阈值统计优化方法，即结合NDVI、光谱亮度值（BRIGHTNESS）和纹理（GLCM）特征变量，通过K-means和两步聚类法（TwoStep Cluster），分别确定切沟候选对象和假阳性对象的不同分类阈值，为切沟提取打下基础；经过t-statistics检验，显示光谱亮度值和纹理变量在95%的置信水平上均显著，从而表明提取阈值具有稳定性和可靠性。
- Abstract:
- This paper brought forward a new method of optimal segmentation scale and threshold methods. maximum of objective function was established by using Moran's I index and intrasegment variance of GLCM and was tested in study area, the results of the optimal partition scale were 24, 31, 36, 42 for agriculture road, gully, cultivated land (slope, terrace) and the forestland in research area. Based on optimal segmentation scale selection, the threshold methods estimated by K-means cluster analysis and TwoStep Cluster using NDVI, BRIGHTNESS and GLCM were established to identify gully candidates and separate gullies from false positives. In order to find out whether the clusters are sufficiently different to represent the false positives, a t-test performed for GLCM, BRIGHTNESS showed that those tome parameters were significant at 95% of the confidence level, therefoe, suggested that the threshold of clusters were reliable and robust.
参考文献/References:
[1] 中国科学院黄土高原综合科学考察队.黄土高原地区土壤侵蚀区域特征及其治理途径[M].北京:中国科学技术出版社,1990:66.
[2] Knight J, Spencer J, Brooks A, et al. Large-area, high-resolution remote sensing based mapping of alluvial gully erosion in Australia's tropical rivers[C]//Proceedings of the 5th Australian Stream Management Conference. Australian Rivers:Making a Difference. Charles Sturt University, Thurgoona, New South Wales, 2007:199-204.
[3] 杜国明,雷国平,宗晓丹.东北典型黑土漫岗区切沟侵蚀空间格局分析[J].水土保持研究,2011,18(2):94-98.
[4] 秦高远,周跃,杨黎.切沟侵蚀研究初探[J].水土保持研究,2007,14(5):84-86.
[5] 范昊明,王铁良,蔡强国,等.东北黑土漫岗区侵蚀沟发展模式研究[J].水土保持研究,2007,14(6):328-334.
[6] 尹佳宜,伍永秋,汪言在.采用不同方法测量切沟的误差分析[J].水土保持研究,2008,15(1):12-16.
[7] Definiens A G. Definiens eCognition Developer 8 User Guide[J]. Definens AG, Munchen, Germany, 2009.
[8] Baatz M, Benz U, Dehghani S, et al. eCognition User Guide[M]. Munich, Definiens, 2000.
[9] Haralock R M, Shapiro L G. Computer and robot vision[M]. Addison-Wesley Longman Publishing Co., Inc., 1991.
[10] Fotheringham A S, Brunsdon C, Charlton M. Quantitative Geography:Perspectives on Spatial Data Analysis[M]. UK:Sage, 2000.
相似文献/References:
[1]秦高远,周跃,杨黎.切沟侵蚀研究初探——以云南省文山县新开田村为例[J].水土保持研究,2007,14(05):84.
QIN Gao-yuan,ZHOU Yue,YANG Li.Primary Research on Erosion of Gully——Taking Wenshan County in Yunnan Province as an Example[J].Research of Soil and Water Conservation,2007,14(04):84.
[2]尹佳宜,伍永秋,汪言在.采用不同方法测量切沟的误差分析[J].水土保持研究,2008,15(01):12.
YIN Jia-yi,WU Yong-qiu,WANG Yan-zai.Error Analysis of Gullies’ Measurement with Different Methods[J].Research of Soil and Water Conservation,2008,15(04):12.
[3]李斌兵,黄磊.基于面向对象技术的黄土丘陵沟壑区切沟遥感提取方法研究[J].水土保持研究,2013,20(03):115.
LI Bin-bing,HUANG Lei.Study on Recognition of the Gully in Loess Hilly-Gully Region Based on Object-Oriented Technology[J].Research of Soil and Water Conservation,2013,20(04):115.
备注/Memo
收稿日期:2013-10-16;改回日期:2013-11-20。
基金项目:国家自然科学基金资助项目（41171224）
作者简介:李斌兵(1968-),女,陕西西安人,博士,硕士生导师,研究方向:地图学与地理信息系统,土壤侵蚀预报模型。E-mail:libinbing8@vip.sina.com