数据融合在红外主被动复合成像分割中的应用研究
|
摘要
CO_2相干激光雷达有较高的分辨率,能成距离像和强度像,这两种图像都含有目标大量的本征信息,易于目标识别,由于其采用的是主动成像模式,因此扫描视场较小、作用距离近、容易暴露;而被动红外图像由于采用的是被动成像模式,作用距离较远、不易暴露自身位置,但与此对应,其抗干扰能力差、图像不稳定且探测虚警率高。CO_2相干激光雷达和长波红外被动成像复合输出信息具有互补性和兼容性,可以扩展系统探测目标的空间和时间覆盖范围,提高系统空间分辨率、全天候工作能力及目标识别和抗干扰能力。
本文主要研究数据融合在红外主被动复合成像分割中的应用,分析了主被动成像的特点,通过被动红外系统对目标进行粗略定位,用激光雷达距离强度像进行图像分割,用分割后的图像提取相应的红外图像的融合方法。重点对激光雷达距离像的分割进行研究。
本文主要分为三个部分。首先介绍了被动红外图像和激光雷达图像的仿真原理,包括激光雷达的系统组成和基本原理,激光雷达距离像噪声产生机理和统计模型。进而介绍了用于主被动图像分割的三种方法,即卡尔曼滤波阈值分割方法、背景抑制分割方法和脉冲神经网络分割方法。随后进行了激光雷达距离像与被动红外图像融合的分割实验,对比分析三种方法的分割结果,得出了卡尔曼滤波阈值分割方法能够得到较好的分割效果。将分割后的主被动图像进行三维视觉处理,通过激光雷达距离像与强度像融合与其对比,得出主被动复合的优势。最后研究了卡尔曼滤波阈值分割方法的CNR适用范围,并给出了实验结果。
CO_2 coherent laser radar provides range image and intensity image with high resolution, both of which have a plenty of latent information of the targets, and are suitable for target recognition. As an active imaging sensor, laser radar has the disadvantages of small field of scan view, near interactive distance and large exposure chance. Passive IR image senor has long interactive distance and could not be easily found. However, it has poor anti-interference ability, instable image and high rate of false detection alarm. The output combined information of two sensors could be complement and compatible. The data fusion of CO_2 coherent laser radar and passive IR image could extend the space and time coverage of detecting target, improve the spatial resolution, target identification and anti-interference ability.
Data fusion application in infrared active-passive image compound segmentation is investigated in this paper. Analyzing the characteristic of active passive image, use passive IR image to search targets and laser radar range image to segment the target and background. And then the target in the IR image is extracted by the worked range image. Range image segmentation is the emphasis in this paper.
There are three parts in this paper. Firstly, the simulation principles of passive IR image and laser radar image are introduced, including laser radar system, basic principle and noise statistic model. Secondly, kalman filter threshold segmentation, background suppression and PCNN, which are used to laser radar range image segmentation, are introduced. After that the experiments on active-passive compound image segmentation are simulated. Comparing the results of three methods above, kalman filter threshold segmentation is proper for range image segmentation. The fusion results of active-passive image are better than the fusion of intensity image and range image. At last, the CNR range for kalman filter threshold segmentation is studied and the result are obtained.
本文主要研究数据融合在红外主被动复合成像分割中的应用,分析了主被动成像的特点,通过被动红外系统对目标进行粗略定位,用激光雷达距离强度像进行图像分割,用分割后的图像提取相应的红外图像的融合方法。重点对激光雷达距离像的分割进行研究。
本文主要分为三个部分。首先介绍了被动红外图像和激光雷达图像的仿真原理,包括激光雷达的系统组成和基本原理,激光雷达距离像噪声产生机理和统计模型。进而介绍了用于主被动图像分割的三种方法,即卡尔曼滤波阈值分割方法、背景抑制分割方法和脉冲神经网络分割方法。随后进行了激光雷达距离像与被动红外图像融合的分割实验,对比分析三种方法的分割结果,得出了卡尔曼滤波阈值分割方法能够得到较好的分割效果。将分割后的主被动图像进行三维视觉处理,通过激光雷达距离像与强度像融合与其对比,得出主被动复合的优势。最后研究了卡尔曼滤波阈值分割方法的CNR适用范围,并给出了实验结果。
CO_2 coherent laser radar provides range image and intensity image with high resolution, both of which have a plenty of latent information of the targets, and are suitable for target recognition. As an active imaging sensor, laser radar has the disadvantages of small field of scan view, near interactive distance and large exposure chance. Passive IR image senor has long interactive distance and could not be easily found. However, it has poor anti-interference ability, instable image and high rate of false detection alarm. The output combined information of two sensors could be complement and compatible. The data fusion of CO_2 coherent laser radar and passive IR image could extend the space and time coverage of detecting target, improve the spatial resolution, target identification and anti-interference ability.
Data fusion application in infrared active-passive image compound segmentation is investigated in this paper. Analyzing the characteristic of active passive image, use passive IR image to search targets and laser radar range image to segment the target and background. And then the target in the IR image is extracted by the worked range image. Range image segmentation is the emphasis in this paper.
There are three parts in this paper. Firstly, the simulation principles of passive IR image and laser radar image are introduced, including laser radar system, basic principle and noise statistic model. Secondly, kalman filter threshold segmentation, background suppression and PCNN, which are used to laser radar range image segmentation, are introduced. After that the experiments on active-passive compound image segmentation are simulated. Comparing the results of three methods above, kalman filter threshold segmentation is proper for range image segmentation. The fusion results of active-passive image are better than the fusion of intensity image and range image. At last, the CNR range for kalman filter threshold segmentation is studied and the result are obtained.
引文
1 G. R. Osche, Young. D. S. Imaging Laser Radar in the Near and Far Infrared. Proceedings of the IEEE. 1996, 84(2):103~123
2 J. Y. Wang, B. J. Bartholomew, M. C. Streiff, E. F. Starr. Imaging CO_2 Laser Field Tests. Applied Optics. 1984, 23(15):2526~2571
3 M. B. Mark, J. H. Shapiro. Multipixel multidimensional laser radar system performance. SPIE. 1987, 783:109~122
4 S. M. Hannon, J. H. Shapiro. Active-Passive Detection of Multipixel Targets. SPIE. 1990, 1222:2~23
5 C. Chu, J. Aggarwal. Multi-sensor image interpretation using lasae radar and thermal images. Proc. of the Conference on Artificial Intelligence Applications. 1991:190~196
6 C. Chu, J. Aggarwal. The interpretation of laser radar images by a knowledge-based system. Machine Vision and Applications. 1991:145~163
7 D. Flannery, W. Hahn. Application of ternary phase-amplitude correlation filters to ladar rangeimage. Proc. of SPIE. 1990, 1297:194~206
8 P. Clapis, M. Cullen, D. Harris. Real-time image processing and data fusion of a two-channel imaging laser radar data. Proc. of SPIE. 1992, 1633:281~287
9 C. Tong, S. Rogers, J. Mills, M. Kabrisky. Multisensor data fusion of laser radar and forward looking infrared for target segmentation and enhancement. Proc. of SPIE. 1987, 782:10~19
10 A. Toet. Hierarchical Image Fusion. Machine Vision and Applications. 1990, 3(1):1~11
11 Y. T. Zhou. Multi-Sensor Image Fusion. IEEE. 1994, 1:193~197
12 Mark R. Stevens, J. Ross Beveridge, Michael E. Goss. Visualizing Multi-Sensor Model-Based Object Recognition. Machine Graphics&Vision. 1998, 6(3):279~304
13 Shin-yi, Hsu. Multi-sensor FLIR/LADAR Fusion from A Machine Vision Perspective. SPIE. 1992, 1699:864~870
14 C.Stelios, A Thomopoulos, H. Byron. Multiresolution Fusion of FLIR and Ladar Data for Target Detection with JDEF. SPIE. 1993, 3371:305~315
15 C. Stelios A. Thomopoulos, Chen, H. Byron. Fusion of Ladar and FLIR Data for Enhanced Automatic Target Recognition. SPIE. 1994, 2093:600~609
16 J. Ross Beveridge, Allen Hanson, Durga Panda. Model-based Fusion of FLIR, Color and LADAR. SPIE. 1995, 2589:2~11
17 Joseph Kostakis, Matthew Cooper, Thomas J. Green. Multispectral Active-PassiveSensor Fusion for Ground-Based Target Orientation Estimation. SPIE. 1998, 3371:500~508
18 Joseph Kostakis, Matthew Cooper, Thomas J. Green. Multispectral Sensor Fusion for Ground-Based Target Orientation Estimation :FLIR, LADAR, HRR. SPIE. 1999, 3718.14~24
19 Brent J. Yen, Jeffrey H. Shapiro. Asymptotic Target-Recognition Performance for FLIR and LADAR Systems. SPIE. 2001, 4379:1~14
20 Dennis, W. Ruck, Steven, K. Rogers. Multisensor Fusion Classification with A Multilayer Perceptron. IEEE. 2001, 2:863~868
21 Fred. Selzer, Dan. Gutfiner. Ladar and FLIR Based Sensor Fusion for Automatic Target. SPIE. 1988, 1003:236~248
22 G. Very. Jacques, L. Delanoy. Richard. Model-Based Automatic Target Recognition System for Forwardlooking Groundbased and Airborne Imaging Laser Radars. IEEE. 1996, 84(2):126~163
23 Gavin. Powell, David. Marshall, Richard. Milliken, Keith. Markham. Data Fusion of FLIR and LADAR in Autonomous Weapons Systems.Proceedins of the seventh international conference on information fusion. 2003, 1:54~61
24 Kalman. Rudolph. A New Approach to Linear Filtering and Prediction Problems. Transactions of the ASME-Journal of Basic Engineering. 1960, 688:35~45
25周巨伟,方志良,杨胜杰,杨勇,母国光.θ调制多光谱照相中可见光与红外图像融合的研究.光子学报. 2005, 34(12):1889~1892
26孙玉秋,田岩,彭代强,田金文.双波段红外图像融合的小波分维算法.华中科技大学学报(自然科学版). 2005, 33(4):41~43
27 L. J. Liu, J. Y. Wang. Model-based Object Classification Using Fused Data. SPIE. 1992, 1611:65~76
28邬永革,刘雷健,杨静宇.利用信息融合方法的三维特征提取.计算机研究与发展. 1996, 33(7):528~532
29赵毅.机械透视的多传感器前视红外/激光雷达融合.弹箭技术. 1997:30-32
30黄麟,张晓丽.三维成像激光雷达遥感技术在林业中的应用.世界林业研究. 2006:3~4
31慕金龙,王骐,李琦,王海霞.长波红外主被动复合成像中目标检测仿真研究.红外与激光工程. 2006, 35(5):634~638
32李琦,董国峰,王骐.用于激光成像雷达和被动红外成像复合的目标分类仿真研究.中国激光. 2007, 34(10):1347~1352
33岗萨雷斯.数字图像处理.电子工业出版社. 2005:495~496
34杨志明,王晓蓉,彭军,陈应祖. BP人工神经网络在图像分割中的应用.计算机科学. 2007, 34(3):234~236
35董立岩,苑森淼,刘光远,贾书洪.基于贝叶斯分类器的图像分类.吉林大学学报. 2007, 45(2):249~253
36杨宁,张培林,任国全,李俊.基于量子行为的微粒群优化算法与模糊C均值聚类算法的磨粒图像分割.润滑与密封. 2009, 34(5):79~81
37马丙辰,谌海新,沈振康.基于3D模型的双色红外图像仿真研究.红外与激光工程. 2005, 34(3):287~291
38王章野.地面目标的红外成像仿真及多光谱成像真实感融合研究.浙江大学博士论文. 2002:53~54
39李琦,王永珍,王骐等.相干激光雷达距离像的噪声抑制算法研究.光学学报. 2005, 25(5):581~584
40 Stephen, M. Hannon, Jeffrey H. Shapiro. Laser Radar Target Detection with a Multipixel Joint Range-Intensity Processor. SPIE. 1988, 999:162~175
41 Thomas J. Green, Jr. Jeffery H. Shapiro. Target Detection Performance Using 3-D Laser Radar Images. SPIE. 1991:328~341
42 Thomas J. Green, Jeffrey H. Shapiro. Maximum-likelihood laser radar range profiling with the expectation-maximization algorithm. Optical Engineering. 1992, 11:2343~2353
43徐克宝,朱苹,王军成,宗贵聪,由斌甲,姜洪广.热红外图像的提取及对比度增强处理技术的研究.仪器仪表学报. 2008, 29(4):283~286
44 Donald R. Greer, Irene Fung, Jeffery H. Shapiro. Maximum-Likelihood Multiresolution Laser Radar Range Imaging. IEEE. 1997, 1:36~46
45沈严,杨志卿.距离图像的分层滤波处理算法.西安电子科技大学学报. 2003, 30(1):136~140
46 Haihua Feng, William C. Karl. LADAR Range Image Segmentation using Curve Evolution and Maximum Likelihood Estimation. IEEE. 2005:770~774
47 Jill R. Goldscheider, Alan Q. Li. Variational segmentation by piecewise facet models with appliction to range imagery. IEEE. 2000:812~815
48 Wang Qi, Li Qi, Chen Zhe, Sun Jianfeng, Yao Rui. Range Image Noise Suppression in Laser Imaging System. Opt Laser Tech. 2009, 41(2),140~147
49郭文艳,韩崇昭.基于灰度关联的多传感器融合目标识别方法.传感器与微系统. 2007, 26(9):115~120
50 J. M. Kinser. Foveation by a Pulse-Coupled Neural Networks. IEEE Trans. on Neural Networks. 1999, 10(3):621~625
51宁晓菊.基于脉冲耦合神经网络的图像检索与数据聚类.西安电子科技大学硕士论文. 2004:4~5
52 J. W. Woods, C. H. Radewan. Kalman Filtering in Two Dimensions. IEEE Trans. Infrom. 1976:473~482
2 J. Y. Wang, B. J. Bartholomew, M. C. Streiff, E. F. Starr. Imaging CO_2 Laser Field Tests. Applied Optics. 1984, 23(15):2526~2571
3 M. B. Mark, J. H. Shapiro. Multipixel multidimensional laser radar system performance. SPIE. 1987, 783:109~122
4 S. M. Hannon, J. H. Shapiro. Active-Passive Detection of Multipixel Targets. SPIE. 1990, 1222:2~23
5 C. Chu, J. Aggarwal. Multi-sensor image interpretation using lasae radar and thermal images. Proc. of the Conference on Artificial Intelligence Applications. 1991:190~196
6 C. Chu, J. Aggarwal. The interpretation of laser radar images by a knowledge-based system. Machine Vision and Applications. 1991:145~163
7 D. Flannery, W. Hahn. Application of ternary phase-amplitude correlation filters to ladar rangeimage. Proc. of SPIE. 1990, 1297:194~206
8 P. Clapis, M. Cullen, D. Harris. Real-time image processing and data fusion of a two-channel imaging laser radar data. Proc. of SPIE. 1992, 1633:281~287
9 C. Tong, S. Rogers, J. Mills, M. Kabrisky. Multisensor data fusion of laser radar and forward looking infrared for target segmentation and enhancement. Proc. of SPIE. 1987, 782:10~19
10 A. Toet. Hierarchical Image Fusion. Machine Vision and Applications. 1990, 3(1):1~11
11 Y. T. Zhou. Multi-Sensor Image Fusion. IEEE. 1994, 1:193~197
12 Mark R. Stevens, J. Ross Beveridge, Michael E. Goss. Visualizing Multi-Sensor Model-Based Object Recognition. Machine Graphics&Vision. 1998, 6(3):279~304
13 Shin-yi, Hsu. Multi-sensor FLIR/LADAR Fusion from A Machine Vision Perspective. SPIE. 1992, 1699:864~870
14 C.Stelios, A Thomopoulos, H. Byron. Multiresolution Fusion of FLIR and Ladar Data for Target Detection with JDEF. SPIE. 1993, 3371:305~315
15 C. Stelios A. Thomopoulos, Chen, H. Byron. Fusion of Ladar and FLIR Data for Enhanced Automatic Target Recognition. SPIE. 1994, 2093:600~609
16 J. Ross Beveridge, Allen Hanson, Durga Panda. Model-based Fusion of FLIR, Color and LADAR. SPIE. 1995, 2589:2~11
17 Joseph Kostakis, Matthew Cooper, Thomas J. Green. Multispectral Active-PassiveSensor Fusion for Ground-Based Target Orientation Estimation. SPIE. 1998, 3371:500~508
18 Joseph Kostakis, Matthew Cooper, Thomas J. Green. Multispectral Sensor Fusion for Ground-Based Target Orientation Estimation :FLIR, LADAR, HRR. SPIE. 1999, 3718.14~24
19 Brent J. Yen, Jeffrey H. Shapiro. Asymptotic Target-Recognition Performance for FLIR and LADAR Systems. SPIE. 2001, 4379:1~14
20 Dennis, W. Ruck, Steven, K. Rogers. Multisensor Fusion Classification with A Multilayer Perceptron. IEEE. 2001, 2:863~868
21 Fred. Selzer, Dan. Gutfiner. Ladar and FLIR Based Sensor Fusion for Automatic Target. SPIE. 1988, 1003:236~248
22 G. Very. Jacques, L. Delanoy. Richard. Model-Based Automatic Target Recognition System for Forwardlooking Groundbased and Airborne Imaging Laser Radars. IEEE. 1996, 84(2):126~163
23 Gavin. Powell, David. Marshall, Richard. Milliken, Keith. Markham. Data Fusion of FLIR and LADAR in Autonomous Weapons Systems.Proceedins of the seventh international conference on information fusion. 2003, 1:54~61
24 Kalman. Rudolph. A New Approach to Linear Filtering and Prediction Problems. Transactions of the ASME-Journal of Basic Engineering. 1960, 688:35~45
25周巨伟,方志良,杨胜杰,杨勇,母国光.θ调制多光谱照相中可见光与红外图像融合的研究.光子学报. 2005, 34(12):1889~1892
26孙玉秋,田岩,彭代强,田金文.双波段红外图像融合的小波分维算法.华中科技大学学报(自然科学版). 2005, 33(4):41~43
27 L. J. Liu, J. Y. Wang. Model-based Object Classification Using Fused Data. SPIE. 1992, 1611:65~76
28邬永革,刘雷健,杨静宇.利用信息融合方法的三维特征提取.计算机研究与发展. 1996, 33(7):528~532
29赵毅.机械透视的多传感器前视红外/激光雷达融合.弹箭技术. 1997:30-32
30黄麟,张晓丽.三维成像激光雷达遥感技术在林业中的应用.世界林业研究. 2006:3~4
31慕金龙,王骐,李琦,王海霞.长波红外主被动复合成像中目标检测仿真研究.红外与激光工程. 2006, 35(5):634~638
32李琦,董国峰,王骐.用于激光成像雷达和被动红外成像复合的目标分类仿真研究.中国激光. 2007, 34(10):1347~1352
33岗萨雷斯.数字图像处理.电子工业出版社. 2005:495~496
34杨志明,王晓蓉,彭军,陈应祖. BP人工神经网络在图像分割中的应用.计算机科学. 2007, 34(3):234~236
35董立岩,苑森淼,刘光远,贾书洪.基于贝叶斯分类器的图像分类.吉林大学学报. 2007, 45(2):249~253
36杨宁,张培林,任国全,李俊.基于量子行为的微粒群优化算法与模糊C均值聚类算法的磨粒图像分割.润滑与密封. 2009, 34(5):79~81
37马丙辰,谌海新,沈振康.基于3D模型的双色红外图像仿真研究.红外与激光工程. 2005, 34(3):287~291
38王章野.地面目标的红外成像仿真及多光谱成像真实感融合研究.浙江大学博士论文. 2002:53~54
39李琦,王永珍,王骐等.相干激光雷达距离像的噪声抑制算法研究.光学学报. 2005, 25(5):581~584
40 Stephen, M. Hannon, Jeffrey H. Shapiro. Laser Radar Target Detection with a Multipixel Joint Range-Intensity Processor. SPIE. 1988, 999:162~175
41 Thomas J. Green, Jr. Jeffery H. Shapiro. Target Detection Performance Using 3-D Laser Radar Images. SPIE. 1991:328~341
42 Thomas J. Green, Jeffrey H. Shapiro. Maximum-likelihood laser radar range profiling with the expectation-maximization algorithm. Optical Engineering. 1992, 11:2343~2353
43徐克宝,朱苹,王军成,宗贵聪,由斌甲,姜洪广.热红外图像的提取及对比度增强处理技术的研究.仪器仪表学报. 2008, 29(4):283~286
44 Donald R. Greer, Irene Fung, Jeffery H. Shapiro. Maximum-Likelihood Multiresolution Laser Radar Range Imaging. IEEE. 1997, 1:36~46
45沈严,杨志卿.距离图像的分层滤波处理算法.西安电子科技大学学报. 2003, 30(1):136~140
46 Haihua Feng, William C. Karl. LADAR Range Image Segmentation using Curve Evolution and Maximum Likelihood Estimation. IEEE. 2005:770~774
47 Jill R. Goldscheider, Alan Q. Li. Variational segmentation by piecewise facet models with appliction to range imagery. IEEE. 2000:812~815
48 Wang Qi, Li Qi, Chen Zhe, Sun Jianfeng, Yao Rui. Range Image Noise Suppression in Laser Imaging System. Opt Laser Tech. 2009, 41(2),140~147
49郭文艳,韩崇昭.基于灰度关联的多传感器融合目标识别方法.传感器与微系统. 2007, 26(9):115~120
50 J. M. Kinser. Foveation by a Pulse-Coupled Neural Networks. IEEE Trans. on Neural Networks. 1999, 10(3):621~625
51宁晓菊.基于脉冲耦合神经网络的图像检索与数据聚类.西安电子科技大学硕士论文. 2004:4~5
52 J. W. Woods, C. H. Radewan. Kalman Filtering in Two Dimensions. IEEE Trans. Infrom. 1976:473~482