Fatma Haouas, Z. B. Dhiaf, A. Hammouda, B. Solaiman
{"title":"Towards change detection in bi-temporal images using evidential conflict","authors":"Fatma Haouas, Z. B. Dhiaf, A. Hammouda, B. Solaiman","doi":"10.1109/ATSIP.2018.8364335","DOIUrl":null,"url":null,"abstract":"This paper exposes new method of remote sensed imagery change detection based on the framework of Dempster-Shafer. The method is established on multi-temporal conflict analysis and interpretation, where it was used as a new index of change. In consequence, a pre-change card was produced from the multi-temporal conflict card between the two bi-temporal images and which was deduced from the empty-set mass. It is the proof that the Dempster-Shafer Theory can be applied in a new way for change detection where the conflict imperfection allows mining reliable and not trivial information about change. The effectiveness of the conflict for multi-temporal change mapping was demonstrated using bi-temporal Landsat imagery.","PeriodicalId":332253,"journal":{"name":"2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ATSIP.2018.8364335","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4
Abstract
This paper exposes new method of remote sensed imagery change detection based on the framework of Dempster-Shafer. The method is established on multi-temporal conflict analysis and interpretation, where it was used as a new index of change. In consequence, a pre-change card was produced from the multi-temporal conflict card between the two bi-temporal images and which was deduced from the empty-set mass. It is the proof that the Dempster-Shafer Theory can be applied in a new way for change detection where the conflict imperfection allows mining reliable and not trivial information about change. The effectiveness of the conflict for multi-temporal change mapping was demonstrated using bi-temporal Landsat imagery.