|
|||||
|
|
| 面向对象技术在城市绿地信息提取中的应用 | |
| 引用本文： | 蒲智,刘萍,杨辽,葛挺进.面向对象技术在城市绿地信息提取中的应用[J].福建林业科技,2006,33(1):40-44. |
| 作者姓名： | 蒲智 刘萍 杨辽 葛挺进 |
| 作者单位： | 1. 新疆农业大学林学院,新疆,乌鲁木齐,830052;新疆林业学校,新疆,乌鲁木齐,830011 2. 新疆农业大学林学院,新疆,乌鲁木齐,830052 3. 中国科学院新疆生态与地理研究所,新疆,乌鲁木齐,830011 4. 新疆生产建设兵团林业调查规划设计院,新疆,乌鲁木齐,830011 |
| 摘 要： | 以乌鲁木齐市为例,采用高分辨率卫星QuickBird数据为主要信息源,应用面向对象的多尺度分割技术,对城市绿地信息的提取方法进行了研究。利用专题层分割影像,结合成员隶属度函数,实现城市绿地信息的自动提取。研究表明使用该方法提取信息速度快、准确率高、成本低,可以实现城市绿地信息的快速而准确的提取。 |
| 关 键 词： | 高分辨率遥感 分类 面向对象 城市绿地 eCognition |
| 文章编号： | 1002-7351（2006）01-0040-05 |
| 收稿时间： | 2005-10-19 |
| 修稿时间： | 2005-10-192005-12-09 |
Study on Extraction of Urban Green Space Using Object-oriented Classification Method |
|
| PU Zhi,LIU Ping,YANG Liao,GE Ting-jin.Study on Extraction of Urban Green Space Using Object-oriented Classification Method[J].Journal of Fujian Forestry Science and Technology,2006,33(1):40-44. | |
| Authors: | PU Zhi LIU Ping YANG Liao GE Ting-jin |
| Institution: | 1. College of Forestry, Xinjiang Agricultural University, Urumqi 830052, China ; 2. Xinjiang Forestry School, Urumqi 830011, China ; 3. Xinfiang Institute of Ecology and Geography, Chinese Academy of Science, Urumqi 830011, China ; 4. Institute of Forest Inventory and Planning, Xinfiang Production and Construction Group, Urumqi 830011, China |
| Abstract: | Monitoring urban green space is one of the major environmental applications in remote sensing today.As the main data sources for urban green space high-resolution imagery provides a good basis for recognizing and monitoring small-scale structure changes.Going far beyond the methodical limits of pixel-based and manual interpretation approaches,multi-resolution image segmentation and object-oriented image analysis approaches are used for extracting information from satellite remote sensing data.This paper discusses about the extraction of urban green space from a QUICKBIRD image using this new technique.It allows the segmentation of an image into highly homogeneous image objects in any chosen resolution and generation of a network of image objects.The process does not classify single pixel but rather image object.Not only spectral information but also spatial,physical and contextual characteristics of image objects are used for classification.The green space has been effectively extracted from the QuickBird image by using Fuzzy Classification Method that based on rules.The result of green space information extraction is promising and precision of classification is higher. |
| Keywords: | high resolution remote sensing classification object-oriented urban green space eCognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |