Jian Wang, Junlin Wang, Hongkun Jiang, Xiaolin Tian, A. Xu
{"title":"基于DEM地形因子和纹理特征分析的月球地形自动识别","authors":"Jian Wang, Junlin Wang, Hongkun Jiang, Xiaolin Tian, A. Xu","doi":"10.1109/ICICTA.2015.137","DOIUrl":null,"url":null,"abstract":"A new auto method to identify the lunar terrain of LROC DEM data has been proposed. The new method combined topographic factors and the texture feature parameter together to form feature vectors for descripting the different lunar terrains of DEM. Then the new method will normalize these feature vectors for getting the better classifying results. Normalized feature vectors would be clustered to two categories, which are lunar mare and lunar highland. The new method has been tested by near 1000 different terrain samples of DEM data and the testing results were satisfied compared with known methods, especially for lunar mare areas, the correct recognition rates of the new method were more than 88.29%, and the overall correct recognition rates of the new method were up to 95%.","PeriodicalId":231694,"journal":{"name":"2015 8th International Conference on Intelligent Computation Technology and Automation (ICICTA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Lunar Terrain Auto Identification Based on DEM Topographic Factor and Texture Feature Analysis\",\"authors\":\"Jian Wang, Junlin Wang, Hongkun Jiang, Xiaolin Tian, A. Xu\",\"doi\":\"10.1109/ICICTA.2015.137\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A new auto method to identify the lunar terrain of LROC DEM data has been proposed. The new method combined topographic factors and the texture feature parameter together to form feature vectors for descripting the different lunar terrains of DEM. Then the new method will normalize these feature vectors for getting the better classifying results. Normalized feature vectors would be clustered to two categories, which are lunar mare and lunar highland. The new method has been tested by near 1000 different terrain samples of DEM data and the testing results were satisfied compared with known methods, especially for lunar mare areas, the correct recognition rates of the new method were more than 88.29%, and the overall correct recognition rates of the new method were up to 95%.\",\"PeriodicalId\":231694,\"journal\":{\"name\":\"2015 8th International Conference on Intelligent Computation Technology and Automation (ICICTA)\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2015-06-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2015 8th International Conference on Intelligent Computation Technology and Automation (ICICTA)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICICTA.2015.137\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 8th International Conference on Intelligent Computation Technology and Automation (ICICTA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICICTA.2015.137","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Lunar Terrain Auto Identification Based on DEM Topographic Factor and Texture Feature Analysis
A new auto method to identify the lunar terrain of LROC DEM data has been proposed. The new method combined topographic factors and the texture feature parameter together to form feature vectors for descripting the different lunar terrains of DEM. Then the new method will normalize these feature vectors for getting the better classifying results. Normalized feature vectors would be clustered to two categories, which are lunar mare and lunar highland. The new method has been tested by near 1000 different terrain samples of DEM data and the testing results were satisfied compared with known methods, especially for lunar mare areas, the correct recognition rates of the new method were more than 88.29%, and the overall correct recognition rates of the new method were up to 95%.