Pub Date : 1999-06-21DOI: 10.1109/CVBVS.1999.781091
P. Dainty, J. Boyce, C. Dimitropoulos, P. Edmundson, D. Toulson, M. Bernhardt
Three aspects of object recognition and tracking are evaluated on forward-looking infrared data from two wavebands. The combination of a correlator with a Kalman filter and a neural network embedded within the tracking loop is shown to increase true recognitions and decrease false recognitions. Large training sets may be reduced by condensing via a k-nearest-neighbour algorithm without significant loss of network performance. Systems combining information from the two wavebands show only a slight improvement over the best single band channel.
{"title":"Dual-band ATR for forward-looking infrared images","authors":"P. Dainty, J. Boyce, C. Dimitropoulos, P. Edmundson, D. Toulson, M. Bernhardt","doi":"10.1109/CVBVS.1999.781091","DOIUrl":"https://doi.org/10.1109/CVBVS.1999.781091","url":null,"abstract":"Three aspects of object recognition and tracking are evaluated on forward-looking infrared data from two wavebands. The combination of a correlator with a Kalman filter and a neural network embedded within the tracking loop is shown to increase true recognitions and decrease false recognitions. Large training sets may be reduced by condensing via a k-nearest-neighbour algorithm without significant loss of network performance. Systems combining information from the two wavebands show only a slight improvement over the best single band channel.","PeriodicalId":394469,"journal":{"name":"Proceedings IEEE Workshop on Computer Vision Beyond the Visible Spectrum: Methods and Applications (CVBVS'99)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116285069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1999-06-21DOI: 10.1109/CVBVS.1999.781094
D. G. Arnold, K. Sturtz, V. Velten
The temperature of a surface viewed by a long-wave infrared camera can be predicted by a thermophysical model (a conservation of energy statement at the surface of a unit volume). However this prediction currently requires at least 24 hours of previous imagery in order to estimate the parameters of the model. Absolute invariants, relative invariants, and quasi-invariants provide three possible methods for circumventing this obstacle. Lie group analysis is a fundamental tool for systematically exploring invariance and for finding the appropriate transformations groups. This paper discusses the relevant parts of Lie group analysis and uses them to find the transformation groups and absolute invariants of the thermophysical model. The goal is to recognize objects based upon a composition of materials that are identified using invariant features of infrared imagery.
{"title":"Invariants of the LWIR thermophysical model","authors":"D. G. Arnold, K. Sturtz, V. Velten","doi":"10.1109/CVBVS.1999.781094","DOIUrl":"https://doi.org/10.1109/CVBVS.1999.781094","url":null,"abstract":"The temperature of a surface viewed by a long-wave infrared camera can be predicted by a thermophysical model (a conservation of energy statement at the surface of a unit volume). However this prediction currently requires at least 24 hours of previous imagery in order to estimate the parameters of the model. Absolute invariants, relative invariants, and quasi-invariants provide three possible methods for circumventing this obstacle. Lie group analysis is a fundamental tool for systematically exploring invariance and for finding the appropriate transformations groups. This paper discusses the relevant parts of Lie group analysis and uses them to find the transformation groups and absolute invariants of the thermophysical model. The goal is to recognize objects based upon a composition of materials that are identified using invariant features of infrared imagery.","PeriodicalId":394469,"journal":{"name":"Proceedings IEEE Workshop on Computer Vision Beyond the Visible Spectrum: Methods and Applications (CVBVS'99)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129553581","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：