首页 | 本学科首页   官方微博 | 高级检索  
     

智能测量热成像系统MRTD的应用方法分析
引用本文:孙军月,马冬梅.智能测量热成像系统MRTD的应用方法分析[J].红外与激光工程,2006,35(4):401-404.
作者姓名:孙军月  马冬梅
作者单位:中国科学院长春光学精密机械与物理研究所,吉林,长春,130033
摘    要:针对已提出的基于神经网络智能测量热成像系统最小可分辨温差(MRTD)的方法,简要阐述其实现方法、理论根据、神经网络算法模型以及测试结果分析.MRTD智能测量是建立在大量主观训练数据的基础上,影响主观MRTD测试的各因素也同样影响最终智能测量的准确性.综合考虑算法模型等因素,分析了影响智能MRTD测试精度的各因素以及尽量减小其影响应采取的措施.同时,讨论了智能MRTD测量的实际意义以及将其应用到实际测量中还需进一步研究与解决的问题.

关 键 词:最小可分辨温差  智能MRTD测量  BP神经网络  MRTD测试精度  红外成像系统参数测试与评估
文章编号:1007-2276(2006)04-0401-04
收稿时间:2005-10-12
修稿时间:2005-11-12

Analysis of intelligent MRTD testing for thermal imaging system
SUN Jun-yue,MA Dong-mei.Analysis of intelligent MRTD testing for thermal imaging system[J].Infrared and Laser Engineering,2006,35(4):401-404.
Authors:SUN Jun-yue  MA Dong-mei
Affiliation:Changchun Institute of Optics, Fine Mechanics and Physics,Chinese Academy of Sciences, Changchun 130033, China
Abstract:Aiming at the method based on intelligent MRTD(Minimum Resolvable Temperature Difference) testing for thermal imaging system using ANN,the realized process,theory foundation,model of neural network and testing deviation were introduced briefly.The intelligent MRTD testing was based on the subjective training data,so the factors affecting the subjective nature of the observers also influenced the accuracy of intelligent testing.Considering the errors of the arithmetic and model,the main factors were discussed in detail in order to decrease the influence on the accuracy of intelligent testing.At the same time,the signification of intelligent MRTD testing and the problems of further research were also mentioned.
Keywords:MRTD  Intelligent MRTD testing  Back-propagation neural network  Accuracy of MRTD testing  Testing and evaluation parameters of the infrared imaging system
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号