QQ客服 官方微博 反馈留言

	Extracting fly ash site information using decision tree classification
	Liu Qingsheng; Liu Gaohuan
	2012
会议名称	2012 5th International Congress on Image and Signal Processing, CISP 2012, October 16, 2012 - October 18, 2012
会议地点	Chongqing, China
关键词	Fly ash Data mining Decision trees Remote sensing Signal processing Vegetation
页码	429-433
英文摘要	Fly ash not only pollutes the environment but also endangers the human health. Rapid, real-time, accurate identification of fly ash by means of remote sensing is of great significance for protecting the environment and the human health. In this paper, by analyzing the spectral information of the typical surface features in Baotou City, based on Landsat 5 TM image data, it adopted the decision tree classification to extract fly ash in the study area. Firstly, we analyze the spectral characteristics of the typical objects and the relationship between them in the study area. Secondly, we established the decision tree, used Soil-adjusted Vegetation Index (SAVI), Modified Normalized Difference Water Index (MNDWI), Normalized Difference Built-up Index (NDBI) and Spectrum Threshold Method to classify the image respectively. Ultimately, post-process the classified image with shape feature and location feature. The total classification accuracy was up to 70.7%. The experimental results show that the method is suitable for the automatic extraction of fly ash information, that what combined with the visual interpretation, can achieve high accuracy. 2012 IEEE.
收录类别	EI
会议录出版者	IEEE Computer Society
语种	英语
内容类型	会议论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/31010]
专题	地理科学与资源研究所_历年回溯文献
推荐引用方式 GB/T 7714	Liu Qingsheng,Liu Gaohuan. Extracting fly ash site information using decision tree classification[C]. 见:2012 5th International Congress on Image and Signal Processing, CISP 2012, October 16, 2012 - October 18, 2012. Chongqing, China.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。