森林训练样本自动提取算法(TDA)已在Landsat图像分析中得到了成功应用,笔者以广西苍梧县广平镇为研究区,采用2007年ALOS、2011年RapidEye遥感图像,试验该算法在高分辨率图像中的应用。研究首先根据图像光谱特性自动识别出纯净森林训练样本,然后依据归一化的整合森林指数图像提取两期森林/非森林分类结果并以此进行林地变化检测,经过精度分析结果表明,面积总误差为-2.6%,空间位置精度为87.7%,说明该算法可有效地从高分辨率遥感图像提取出纯净的森林训练样本,为森林/非森林分类以及变化检测提供基础数据。
Abstract
The algorithm of forest training data automation(TDA)has been successfully applied to Landsat images. Taking Guangping Town, Cangwu County, Guangxi Province as the study area, we selected the ALOS image of 2007 and the RapidEye image of 2011 to explore the algorithm’s application in high resolution remote sensing images. The pure forest training samples were automatically identifed at first, and the change detection result was then obtained by the forest/non-forest classification which extracted by the normalized integrated forest index image involved in the anlaysis.The accurate evaluation results showed that the total area error was -2.6% and the spatial location accuracy was 87.7%. It was shown that this algorithm could be effectively applied to high resolution remote sensing images to extract pure forest training samples for the forest/non-forest classification and change detection as the original data.
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 徐新良, 刘纪远, 庄大方, 等. 中国林地资源时空动态特征及驱动力分析[J]. 北京林业大学学报,2004,26(1):41-46.Xu X L,Liu J Y,Zhuang D F,et al.Spatial-temporal characteristics and driving forces of woodland resource changes in China[J].Journal of Beijing Forestry University,2004, 26(1):41-46.
[2] 张连华,庞勇,岳彩荣,等.基于缨帽变换的景洪市时间序列Landsat影像森林扰动自动识别方法研究[J].林业调查规划,2012,38(2):6-12.Zhang L H, Pang Y, Yue C R, et al.Forest disturbance automatic identification method based on time series landsat image of tasseled cap transformation[J]. Forest Inventory and Planning, 2012,38(2):6-12.
[3] 佃袁勇.基于遥感影像的变化检测研究[D].武汉:武汉大学, 2005.Dian Y Y.Research on change detection in remote sensing imagery[D].Wuhan: Wuhan University,2005.
[4] 秦琳.基于RS的森林资源变化信息提取研究[J]. 林业勘察设计,2010,59(1):20-23.Qin L.Extracting change information of forest resources based on RS[J]. Forestry Prospect and Design, 2010,59(1):20-23.
[5] 李世明,王志慧,韩学文,等.森林资源变化遥感监测技术研究进展[J]. 北京林业大学学报, 2011,33(3):132-138.Li S M,Wang Z H,Han X W,et al.Overview of forest resources change detection methods using remote sensing techniques[J]. Journal of Beijing Forestry University, 2011,33(3):132-138.
[6] Pattanaik C,Reddy C S,Reddy P M.Assessment of spatial and temporal dynamics of tropical forest cover:A case study in Malkangiri district of Orissa,India[J]. Journal of Geographical Sciences,2011,21(1):176-192.
[7] 贾文娟,韦雪花,王秀兰,等.北京永定河流域森林植被覆盖研究[J]. 林业调查规划, 2011,36(4):21-24.Jia W J, Wei X H, Wang X L,et al. Research on Beijing Yongding River basin forest vegetation coverage changes[J]. Forest Inventory and Planning, 2011,36(4):21-24.
[8] 周蔚.基于TM的森林资源地类动态估计方法及应用[D].南京:南京林业大学,2010.Zhou W.Estimation method of forest resources land type variations and its application based on TM image[D].Nanjing: Nanjing Forestry University,2010.
[9] 邓书斌.林冠状态变化遥感监测方法研究[D]. 青岛:山东科技大学, 2007.Deng S B.A Study on the appolch of remote sensing dynamic mcnitoring of canopy staie Changes[D]. Qingdao:Shandong University of Science and Technology,2007.
[10] 李世明,王志慧,李增元,等.基于邻近相关图像和决策树分类的森林景观变化检测[J]. 林业科学, 2011,47(9):69-74.Li S M, Wang Z H, Li Z Y, et al. A forest change detection model based on neighborhood correlation images and decision tree classification[J]. Scientia Silvae Sinicae, 2011,47(9):69-74.
[11] Masek J,Huang C,Wolfe R,et al. North American forest disturbance mapped from a decadal Landsat record[J].Remote Sensing of Environment,2008,112(6):2914-2926.
[12] Huang C,Song K,Kim S,et al.Use of a dark object concept and support vector machines to automate forest cover change analysis[J].Remote Sensing of Environment, 2008,112(3):970-985.
[13] 赵英时.遥感应用分析原理与方法[M].北京:科学出版社,2003.
[14] 李春干.红树林遥感信息提取与空间演变机理研究[M].北京:科学出版社,2013.
基金
收稿日期:2014-02-26 修回日期:2014-06-02
基金项目:广西林业科技项目(201423); 国土资源公益性行业科研专项项目(201211028-6)
第一作者:张连华,工程师,硕士。E-mail:sdzhanglh@126.com。
引文格式:张连华,李春干. 高分辨率遥感图像森林训练样本自动提取及其在变化检测中的应用[J]. 南京林业大学学报:自然科学版,2015,39(3):13-17.
PDF(2458923 KB)
