红外焦平面非均匀性校正的人工神经网络算法
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
红外焦平面应用于红外成像系统具有结构简单、灵敏度高、功耗小等优点,所以得到高度重视和广泛应用。然而,红外焦平面阵列固有的非均匀性,使红外成像系统的温度分辨率下降,图像质量受到严重影响。因此,必须对红外焦平面进行非均匀性校正。
     本论文首先对红外焦平面非均匀性的产生原因进行了探讨,而后选取了便于实际操作的非均匀性定义及大小度量方式,并介绍了几种非均匀性校正算法及其优、缺点。在此基础上,指出自适应非均匀性校正方法是非均匀性校正发展的必然趋势。进而详细介绍了自适应非均匀性校正方法中最具发展前景的人工神经网络校正算法,并对各种人工神经网络算法进行了研究和比较,选取BP神经网络应用于红外焦平面的非均匀性校正。参阅国外文献,给出了的非均匀性BP校正算法的实际应用模型。通过对经典BP校正算法模型的分析研究,针对经典BP校正算法参数难以选取的缺点,提出了一种改进型的BP校正算法——归一化BP校正算法的实现方式,在参数选取的合理性和可行性方面得到了明显的改善。分析归一化BP校正算法的参数选取与算法敛散性之间的关系,对实际应用中参数的选取具有指导作用。对改进的归一化BP校正算法利用Matlab进行了软件仿真,在取得良好的非均匀性校正效果的同时,验证了对归一化BP校正算法理论分析的正确性。最后对算法的硬件可实现性进行了论证。
Infrared focal plane array(IRFPA) can be superior for infrared imaging systems not only because of its simplicity and compactness in structure ,but also because of its high sensitivity and low power depletion. And infrared focal plane array is applied to imaging system widely and attracted lots of attention. Unfortunately, its inherent nonuniformity can degrade image quality and system performance. Hence, nonunifbrmity correction(NUC) becomes necessary.
    The paper firstly describes the reasons of the nonuniformity in the IRFPA. Then several methods of nonuniformity correction(NUC) for IRFPA are analyzed and compared, which leads to that the adaptive correction scheme is the best for the IR imaging system. Following that, artificial neural networks correction technique-back propagation(BP) algorithm is discussed in detail. On the base of above analysis, the unitary BP algorithm is introduced, which has more adaptability than classical BP algorithm. Experiments were performed. The unitary BP algorithm's effectiveness and superiority were verified by simulation. At the end of this paper, the possibility of hardware-realization of the algorithm is validated.
引文
[1] C.L. Carrison and N.A. Foss "Nonuniformity compendation techniques for staring infrared (IR) focal planes" SPIE Vol.178 smart sensors pp99-109(1979)
    [2] A.F. Milton, F.R. Barone, and M.R. Kruer "Influence of nonuniformity on infrared focal plane array performance" OPTICAL ENGINEERING Vol. 24 No. 5pp855-862(1985)
    [3] D.A. Scribner, K.A. Sarkady, J.T. Caulfield, M.R. Kruer, G. Katz, and C.J. Gridley "Nonuniformity correction for staring IR focal plane arrays using scene-based techniques" SPIE Vol.1308 Infrared Detectors and focal plane arrays pp224-234(1990)
    [4] D.A. Scribner, K.A. Sarkady, M.R. KrUer, and J.T. Caulfield "Adaptive Nonuniformity Correction for IR Focal Plane Arrays Using Neural Networks" SPIE Vol.1541 Infrared Sensor:detectors, electronics, and signal processing pp100-109(1991)
    [5] 高云、邬鸣敏、周起勃,“凝视红外焦平面CCD非均匀性校正“,《红外与毫米波学报》,vol.12,第三期,1993
    [6] 岐爱筠,陈光余,“凝视成像识别系统的信号处理方法研究”,《红外与激光技术》,1993,4
    
    
    [7] 施立原,“面列阵焦平面探测器的多点定标非均匀性校正算法及其实现”,红外,2002年第8期,pp24—28
    [8] 王爱丽,“红外焦平面探测器非均匀性校正研究及系统实现”,硕士学位论文,2001
    [9] 吴军辉,郜竹香,张玉竹,“红外成像系统图像空间噪声分析与估计”,红外技术,第23卷第3期,pp19—22,2001年5月
    [10] 熊辉,“红外非均匀性校正研究”,硕士学位论文
    [11] 王钰,陈钱,殷德奎,张保民,“实时红外图像非均匀性校正技术研究”,《红外与毫米波学报》,Vol.18,No.2,1999.4
    [12] D.A. Scribner, K.A. Sarkady, M.R. Kruer, etc, "Adaptive Retina-Like Preprocessing for Imaging Detector Arrays", IEEE, 1993, pp1955—1960
    [13] 何小娟,“红外焦平面探测器的非均匀性校正与算法实现”,红外。2001年第6期,pp1—7
    [14] 陈锐,谈新权,“红外图像非均匀性校正方法综述”,红外技术,第24卷第1期,2002年1月,pp1—3
    [15] 戴葵,《神经网络实现技术》,国防科技大学出版社,1998.7
    [16] 苗大庆,“红外非均匀性校正算法的研究与实现”,1999,硕士学位论文
    [17] B. Widrow, S.D. Stearns, "Adaptive Signal Processing, Prentice-Hall Inc, 1985
    [18] 夏文芳,吴鸿修,李享元,“基于USB的实时数据采集系统及其在Matlab中的应用”,2003年第2期,电子技术应用
    [19] 张宜华,《精通Matlab5》,清华大学出版社,1999
    
    
    [20] 吴军辉、王涛、刘义和、张文攀,“红外图像的非均匀性及其仿真”,《红外技术》,Vol.25 No.5,2003.9
    [21] 任丽香,马淑芬,李方慧,《TMS320C6000系列DSPs的原理与应用》,电子工业出版社,2000.7
    [22] 杨华民,《人工神经网络BP算法局部最小问题研究》,硕士论文,1995
    [23] John G. Harris, Yu-Ming Chiang,"Nonuniformity Correction Using the Constant-Statistics Constraint: Analog and Digital Implementation" SPIE, Vol. 3061,1997.4 pp895-905
    [24] 汤锦亚,仇力,“红外焦平面探测器在导弹导引头上的应用”,《红外技术》,Vol,24 No.2,2002.3 pp14—17
    [25] Abraham Friedenberg, Isaac Goldblatt,"Nonuniformity two-point linear correction errors in infrared focal plane arrays",Opt. Eng, Vol37, No4,1998,4 pp1251-1253
    [26] P.M. Narendra, "Reference-free nonuniformity compensation for IR imaging arrays" SPIE vol. 252. smart sensors Ⅱ pp10-17(1980)
    [27] 姜光,刘上乾,“红外焦平面阵列非均匀性自适应校正算法研究”,《红外与毫米波学报》,Vol.20,No.2 2001.4
    [28] 《国外军用红外焦平面阵列技术》(第二集),中国兵器科学研究院兵器工业情报研究所,1994
    [29] 高云、邬鸣敏、周起勃,“凝视红外焦平面CCD非均匀性校正“,《红外与毫米波学报》,vol.12,第三期,1993
    [30] 杨宜禾、岳敏,《红外系统》,国防工业出版社,1985
    
    
    [31] 闻新、周露、王丹力、熊晓英,matlab神经网络应用设计,科学出版社,2000.9
    [32] 张航、黄攀译,D.Hanselman,B.Littlefield著,《Mastering Matlab6》,清华大学出版社,2002.6,第一版
    [33] June Keun Ji, Jae Ryong Yoon, "Nonuniformity correction scheme for an infrared camera including the background effect due to camera temperature variation", Opt. Eng. 39(4),pp936-940,2000.4
    [34] 刘会通,马红伟,“红外焦平面非均匀性校正若干方案的设计和分析”, 《激光与红外》,Vol.33,No.4,2003.8
    [35] 曹治国,魏洛刚,张天序,桑农,“基于神经网络法的焦平面器件非均匀性校正技术研究”,《红外与激光工程》,Vol.29,No.1,2000.2
    [36] Prayen Reddy, Gerhard de Jager, "Reference Free Nonuniformity Correction for Mercury Cadmium Telluride Infrared Focal Plane Array", IEEE, 1998, pp243—248
    [37] 袁曾任,《人工神经元网络及其应用》,清华大学出版社,1999.10
    [38] 周廷刚,《城市绿量的遥感信息处理及分析评价研究》,博士论文
    [39] 张智星,《Matlab程序设计与应用》,清华大学出版社,2002.4 第一版
    [40] 龚剑,朱亮,《Matlab5.X入门与提高》,清华大学出版社,2000.3
    [41] 苏涛,吴顺君,廖晓群,《高性能数字信号处理与高速实时信号处理》,西安电子科技大学出版社

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700