Infrared laser active imaging and recognition technology
-
摘要:在传统 主动成像系统的基础上,结合目标识别技术搭建了一台 主动成像识别系统实验平台,研究了 主动成像后的目标识别技术。由7个不变Hu矩构成特征量,用由136个权值系数构成BP神经网络算法对黑夜条件下450 m处的运动目标43式冲锋模具枪进行了实验研究。研究显示,采用该方法成功获得了清晰的红外 主动成像效果,对2 740 frame 主动成像图像的统计目标识别率达到了68.87%,其中旋转变换下的统计识别率可达80.05%。该项研究对实际黑夜暗小目标的探测识别具有重要意义。Abstract:An experiment platform for laser active imaging and target recognition was built combining a laser active image system and the target recognition technology, and the target recognition after laser active imaging was mainly researched. The feature vector was comprised of seven invariant Hu moments. The BP neural network algorithm comprised of 136 weight coefficients was used to study the moving target, a 43 submachine gun model at 450 m from the experiment platform at night, and excellent experiment results were obtained. It shows clear imaging effects by 68.87% of target recognition statistic probability in 2 740 frames of laser active imaging, and the probability of rotation transformation reaches 80.05%. These researches are significant to the detection and recognition of little targets at night.
-
[1] DAYTON D,BROWNE S,GONGLEWSKI J. Long-range laser illuminated imaging: analysis and experimental demonstration[J].Opt. Eng.,2001,40(6):1001-1009. [2] 张建,张雷,曾飞,等. 机载 3D探测成像系统的发展现状[J]. 中国光学,2011,4(3):213-232. ZHANG J,ZHANG L,ZENG F,et al.. Development status of airborne 3D imaging lidar systems[J].Chinese Optics,2011,4(3):213-232.(in Chinese) [3] 王智,贾书洪,张晓辉,等. 主动成像的多帧后处理算法研究[J]. 光学 精密工程,2007,15(4):615-621. WANG ZH,JIA SH H,ZHANG X H,et al.. Multiframe post processing algorithm of laser active imaging images[J].Opt. Precision Eng.,2007,15(4):615-621.(in Chinese) [4] 张晟翀,唐树威,朱海波. 主动成像技术研究[J]. 光电技术应用,2009,24(3):9-12. ZHANG SH C,TANG SH W,ZHU H B. Laser active imaging technology[J].Electro-Aptic Thchnology Appl.,2009,24(3):9-12.(in Chinese) [5] 庞春颖,张涛. 主动成像系统探测距离的计算与仿真[J]. 电光与控制,2008,15(2):70-73. PANG CH Y,ZHANG T. Operation range of laser active imaging system computation and simulation[J].Electronics Optic&Control,2008,15(2):70-73.(in Chinese) [6] 刘秉琦,周文武,武东生,等. 双通道 主动探测系统[J]. 光学 精密工程,2012,20(2):241-246. LIU B A,ZHOU W W,WU D SH,et al.. Dual-channel active laser detection system[J].Opt. Precision Eng.,2012,20(2):214-246.(in Chinese) [7] 孙欣. 军用目标识别系统的研究与应用[J]. 光学与光电技术,2012,10(5):80-83. SUN X. Research and application of military target identification systems[J].Opt. Optoelectronic Technol.,2012,10(5):80-83.(in Chinese) [8] 孙红辉,王红霞,田涛. 一种基于不变矩和BP网络的目标识别方法[J]. 微电子学与计算机,2011,28(3):63-69. SUN H H,WANG H X,TIAN T. The recognition method of objects based on moment invariant and BP neural network[J].Microelectronics&Computer,2011,28(3):63-69.(in Chinese) [9] 田华,石圣羽,宗晓萍. 基于不变矩特征及BP神经网络的图像模式识别[J]. 河北大学学报,2008,28(2):214-217. TIAN H,SHI SH Y,ZONG X P. Pattern recognition based on moment invariant feature and BP neural network for image[J].J. Hebei University,2008,28(2):214-217.(in Chinese) [10] 郭婉露. 红外图像目标识别及跟踪技术研究[D].哈尔滨:哈尔滨工程大学,2011. GUO W L. Researches for infrared image target identification and tracking technology [D]. Harbin:Harbin Engineering University,2011.(in Chinese) [11] 吕砚山,赵正琦. BP神经网络的优化及应用研究[J]. 北京化工大学学报,2001,28(1):67-69. LV Y SH,ZHAO ZH Q. Optimization and application research of BP neural network[J].J. Beijing University Chem. Technology,2001,28(1):67-69.(in Chinese) [12] 刘天舒. BP神经网络的改进研究及应用[D].哈尔滨:东北农业大学,2011. LIU T SH. The research and application on BP neural network improvement [D]. Harbin:Northeast Agricultural University,2011.(in Chinese) [13] 冯伟兴,唐墨,贺波.Visual C+ +数字图像模式识别技术详解[M]. 北京:机械工业出版社,2011. FENG W X,TANG M,HE B.Digital image pattern recognition programming using Visual C+ +[M]. Beijing:China Machine Press,2011.(in Chinese) [14] 李鹏,王乐新,赵志敏. 基于概率神经网络的荧光光谱法识别高甘油三脂血清[J]. 发光学报,2011,32(11):1192-1196. LI P,WANG L X,ZHAO ZH M. Hypertriglyceridemia serum recognition using fluorescence spectroscopic analysis based on probabilistic neural networks[J].Chinese J. Luminescence,2011,32(11):1192-1196.(in Chinese)
点击查看大图
计量
- 文章访问数:2975
- HTML全文浏览量:662
- PDF下载量:628
- 被引次数:0