| 高光谱数据森林类型统计模式识别方法比较评价 |
| |
| 引用本文： | 陈尔学,李增元,谭炳香,梁毓照,张则路.高光谱数据森林类型统计模式识别方法比较评价[J].林业科学,2007,43(1):84-89. |
| |
| 作者姓名： | 陈尔学 李增元 谭炳香 梁毓照 张则路 |
| |
| 作者单位： | 1. 中国林业科学研究院资源信息研究所,北京,100091
2. 吉林省汪清林业局,汪清,133200 |
| |
| 基金项目： | 国家高技术研究发展计划(863计划) |
| |
| 摘 要： | 在我国东北地区获取EO-1 Hyperion高光谱数据,以高空间分辨率的全色SPOT-5数据及其影像分割结果为辅助,通过外业测量获取真实可靠的森林类型空间分布数据.以这些数据为地面实状数据,对现代先进的统计模式识别方法用于森林类型识别的效果进行比较评价,总结可以有效解决有限样本条件下高光谱分类问题的基于统计模式识别的森林类型分类技术方案.评价结果表明:对高光谱数据进行降维处理,并采用更加有效的二阶统计量估计方法,进而应用将空间上下文信息和光谱信息相结合的分类算法,如ECHO,可以有效提高高光谱数据森林类型的识别精度.
|
| 关 键 词： | 高光谱 统计模式识别 森林类型 |
| 文章编号： | 1001-7488(2007)01-0084-06 |
| 修稿时间： | 2005-05-25 |
Validation of Statistic Based Forest Types Classification Methods Using Hyperspectral Data |
| |
| Chen Erxue,Li Zengyuan,Tan Bingxiang,Liang Yuzhao,Zhang Zelu.Validation of Statistic Based Forest Types Classification Methods Using Hyperspectral Data[J].Scientia Silvae Sinicae,2007,43(1):84-89. |
| |
| Authors: | Chen Erxue Li Zengyuan Tan Bingxiang Liang Yuzhao Zhang Zelu |
| |
| Institution: | 1. Institue of Forest Resources Information Techniques, CAF Beijing 100091 ; 2. Wangqing Forest Bureau of Jilin Province Wangqing 133200 |
| |
| Abstract: | With much higher spectral resolution, hyperspectral remote sensing data has higher potential capability to identify land cover types than traditional multispectral data. But under limited training sample size, increased dimension of remote sensing data means decreased samples/dimension ratio, which can lead to low classification accuracy if common statistic based pattern classification methods were used. One scene of EO_1 Hyperion hyperspectral data was acquired for the test site in north_east of China. In order to aid for ground true information collection, 2.5 m SPOT_5 PAN image was segmented into self_closure polygons. Detailed ground true data was surveyed according to the boundary of each polygon. Based on these ground true data, the hyperspectral data was used to validate the forest types identification accuracy of several advanced statistic classification methods. Finally, one classification scheme being able to effectively solve the small train sample problems for forest type classification using hyperspectral data was suggested. It was shown that forest type classification accuracy can be improved if advanced feature extraction method, much more effective second order statistic parameter estimation method, and context_sensitive samples classifier such as ECHO was applied. |
| |
| Keywords: | EO-1 Hyperion |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
