Please wait a minute...
img

Wechat

Remote Sensing Technology and Application  2012, Vol. 27 Issue (3): 339-346    DOI: 10.11873/j.issn.1004-0323.2012.3.339
    
Object-oriented High Resolution Image Classification based on Association-rule
Zhang Yang,Zhou Ziyong
(State Key Laboratory of Petroleum Resource and Prospecting,China University of Petroleum,Beijing 102200,China)
Download:  PDF (2888KB) 
Export:  BibTeX | EndNote (RIS)      
Abstract  

This paper has explored the method of high resolution image classification by combining association rule mining and object-oriented method.Firstly,according to the theory of Classification Based on Association (CBA),and a modified classifier builder was discussed.Secondly,the object-oriented high resolution image classification was achieved by image segmentation,feature extraction,association-rule extracted and classifier building.After that,Class Association Rules (CARs) was mined by the process of CBA-RG.It was proved that these rules correspond with the features of the ground object.According to the order of “confidence → spectrum complexity → support → generation sequence”,a modified classifier was built based on these rules.Finally,we evaluated the precision of the classification result and compared it with the result of K-Nearest Neighbors.The experiment shows that the precision is relatively high and can move away from the dependence on the expert knowledge in a certain degree.

Key words:  Association rule      Object-oriented      High resolution image     
Received:  21 July 2011      Published:  23 January 2013
TP 751  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors

Cite this article: 

Zhang Yang,Zhou Ziyong. Object-oriented High Resolution Image Classification based on Association-rule. Remote Sensing Technology and Application, 2012, 27(3): 339-346.

URL: 

http://www.rsta.ac.cn/EN/10.11873/j.issn.1004-0323.2012.3.339     OR     http://www.rsta.ac.cn/EN/Y2012/V27/I3/339

[1]Zhou Chunyan,Wang Ping,Zhang Zhenyong,et al.Classification of Urban Land based on Object-oriented Information Extraction Technology[J].Remote Sensing Technology and Application,2008,23(1):31-35.[周春艳,王萍,张振勇,等.基于面向对象信息提取技术的城市用地分类[J].遥感技术与应用,2008,23(1):31-35.]
[2]Deng Yuanyuan,Wu Zhaocong,Yi Lina,et al.Research on Object-oriented Classification of Agricultural Land based on High Resolution Images[J].Remote Sensing for Land & Resources,2010,4:117-121.[邓媛媛,巫兆聪,易俐娜,等.面向对象的高分辨率影像农用地分类[J].国土资源遥感,2010,4:117-121.]
[3]Zhang Xueru,Liu Linshan,Zhang Yili,et al.Extraction of Shrub Vegetation by Object-Oriented Classification Method based on ENVI ZOOM in High-altitude Area:A Case of Dingri County[J].Geograph and Geo-Information Science,2010,26(4):104-108.[张学儒,刘林山,张镱锂,等.基于ENVI ZOOM面向对象的高海拔灌丛植被提取—以定日县为例[J].地理与地理信息科学,2010,26(4):104-108.]
[4]Zhang Jun,Yu Qingguo,Hou Jiahuai.Object-oriented Classification and Information Extraction based on High Spatial Resolution Remote Sensing Image[J].Remote Sensing Technology and Application.2010,25(1):112-117.[张俊,于庆国,侯家槐.面向对像的高分辨率影像分类与信息提取[J].遥感技术与应用,2010,25(1):112-117.]
[5]Peng Haitao,Ke Changqing.Study on Object-oriented Remote Sensing Image Classification based on Multi-levels Segmentation[J].Remote Sensing Technology and Application,2010,25(1):149-154.[彭海涛,柯长青.基于多层分割的面向对象遥感影像分类方法研究[J].遥感技术与应用,2010,25(1):149-154.]
[6]Zhang Chunyan,Guo Shan,Guan Yanning,et al.The Approaches of Land Cover Classification of the Wuda Coal Fire Area[J].Journal of Remote Sensing,2011,15(1):148-162.[张春燕,郭杉,关燕宁,等.煤田火区特征的土地覆盖分类方法[J].遥感学报,2011,15(1):148-162.] 
[7]Agrawal R,Imielinski T,Swami A.Mining Association Rules between Sets of Items in Large Databases[C]//Proceedings of the ACM SIGMOD Conference on Management of Data,Washington DC,USA,1993:207-216.
[8]Ma Chaofei,Liu Jianqiang.Multidimensional and Quantitative Association Rule Mining from Remote Sensing Images[J].Remote Sensing Technology and Application,2003,18(4):243-247.[马超飞,刘建强.遥感图像多维量化关联规则挖掘[J].遥感技术与应用,2003,18(4):243-247.]
[9]Li Tongjun,Yue Lihua,Li Yan.Two Phase Spatial Association Rule Mining Algorithm based on Image Segmentation[J].Computer Applications and Software,2005,22(11):8-10.[李国钧,岳丽华,李艳.基于图像分割的两阶段空间关联规则挖掘算法[J].计算机应用与软件,2005,22(11):8-10.]
[10]Qin K,Guan Z Q,Li D R.The Methods of Remote Sensing Image Mining based on Concept Lattice[C]//Proceedings of SPIE-The International Society for Optical Engineering,Bellingham,WA,2003,5286(1):254-259.
[11]Ding Q,Ding Q,Perrizo W.Association Rule Mining on Remotely Sensed Images using P-tree[C]//Carbonell J G,et al,eds.Advances in Knowledge Discovery and Data Mining,2336.Heidelberg,Berlin:Springer-Verlag,2002.66-79.
[12]Guan Xianming.Feature-unit Association Rule Mining from High Spatial Resolution Remote Sensing Images[D].Nanjing:Nanjing Normal University,2010.[关显明.高分辨率遥感影像特征基元关联规则挖掘研究[D].南京:南京师范大学,2010.]
[13]Liu B,Hsu W,Ma Y.Integrating Classification and Association Rule Mining[C]//Proceedings of 4th ACM International Conference on KDD.New York,1998:80-86.
[14]Dong G Z,Li J Y.Efficient Mining of Emerging Patterns:Discovering Trends and Differences[C]//Proceedings of the 5th International Confereuce on KDD.San Diego,1999:43-52.
[15]Li W M,Han J W,Pei J.CMAR:Accurate and Efficient Classification based on Multiple Class-association Rules[C]//Proceedings of the IEEE International Confereuce on Data Mining,California,2001:369-376.
[16]Yin X X,Han J W.CPAR:Classification based on Predictive Association Rules[C]//Proceedings of the 2003 SIAM International Confereuce on Data Mining (SDM03),San Francisco,2003:34-42.
[17]Xu X Y,Han G Q,Min H Q.Construct Concise and Accurate Classifier by Atomic Association Rules[C]//Proceedings of the International Conference on Machine Learning and Cybernetics,New York,2004,8:1604-1609.
[18]Walter V.Object-based Classification of Remote Sensing Data for Change Detection [J].ISPRS Journal of Photogrammetry &Remote Sensing,2004,58:225-238.

No Suggested Reading articles found!