Extracting fly ash site information using decision tree classification
文献类型：会议论文
| 作者 | Liu Qingsheng; Liu Gaohuan |
| 出版日期 | 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 |
| 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. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
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。