{"title":"Spectral Response of Two Hyperspectral Cameras for UXO Endmember Selection","authors":"Milan Bajić, B. Potočnik","doi":"10.18690/um.feri.1.2024.9","DOIUrl":null,"url":null,"abstract":"There is currently no recommended procedure for acquiring endmembers in hyperspectral target detection when targets are larger than a single pixel. What is the best approach when multiple cameras are available for a dataset construction? This study examines the differences between hyperspectral cameras Specim IQ and Specim Imspector V9 that recorded the same surfaces under the same lighting conditions. A white balance card and a mortar mine are considered. As calibration procedures for cameras differ, raw data without processing are compared, and the same wavelength range is chosen. Clear differences are noticed between the spectra of the two cameras. Finally, guidelines for selecting statistically reliable endmembers and constructing an endmember dataset are provided based on the obtained results.","PeriodicalId":517885,"journal":{"name":"ROSUS 2024 - Računalniška obdelava slik in njena uporaba v Sloveniji 2024: Zbornik 18. strokovne konference","volume":"85 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ROSUS 2024 - Računalniška obdelava slik in njena uporaba v Sloveniji 2024: Zbornik 18. strokovne konference","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.18690/um.feri.1.2024.9","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
There is currently no recommended procedure for acquiring endmembers in hyperspectral target detection when targets are larger than a single pixel. What is the best approach when multiple cameras are available for a dataset construction? This study examines the differences between hyperspectral cameras Specim IQ and Specim Imspector V9 that recorded the same surfaces under the same lighting conditions. A white balance card and a mortar mine are considered. As calibration procedures for cameras differ, raw data without processing are compared, and the same wavelength range is chosen. Clear differences are noticed between the spectra of the two cameras. Finally, guidelines for selecting statistically reliable endmembers and constructing an endmember dataset are provided based on the obtained results.