基于TDRNN的大气层外弹道式空间红外目标识别

刘涛; 吕江北; 王书宏; 卢焕章

doi:10.3724/SP.J.1146.2009.00015

基于TDRNN的大气层外弹道式空间红外目标识别

doi: 10.3724/SP.J.1146.2009.00015

计量
- 文章访问数: 3746
- HTML全文浏览量: 87
- PDF下载量: 827
- 被引次数: 0
出版历程
- 收稿日期: 2009-01-07
- 修回日期: 2009-06-29
- 刊出日期: 2010-01-19

Exo-atmospheric Discrimination of Infrared Ballistic Space Target Based on the Time-Delay Recurrent Neural Network

摘要

摘要: 该文提出一种基于时延回归神经网络(TDRNN)的大气层外弹道式空间红外目标识别方法。该网络采用自适应时间延迟器和输出层回归结构，可以针对输入时间序列信号的局部时变信息自适应选择延迟步长，而且具有边跟踪边识别的记忆性动态识别功能。综合考虑弹道式空间目标热物参数和运动状态、空间环境辐射和红外传感器效应等因素，仿真了典型弹道式空间目标的动态红外辐射强度数据，进行了目标识别实验研究。仿真结果表明，提出的TDRNN网络对于弹道式空间红外目标有很强的分类能力。
- 目标识别; 空间目标; 红外辐射; 时延回归神经网络
Abstract: This paper presents a Time-Delay Recurrent Neural Network (TDRNN) for exo-atmospheric ballistic space infrared target discrimination. The TDRNN employs adaptive time delays and recurrences where the adaptive time delays make the network choose the optimal values of time delays for the temporal location of important information in the input sequence, and the recurrences enable the network to have dynamic discrimination function. The IR radiation data of space target considering the sensor effect is simulated, taking into account the synthetic factors of heat parameter and motion, the space environment radiation and the sensor effect. The target discrimination experiment is developed, based on dynamic IR radiation simulated data of four typical ballistic space target. The simulation results show that TDRNN have better discrimination ability.

HTML全文

参考文献(1)

[1] 武春风, 张伟, 李洁, 等. 基于时空信息的红外成像系统在探测识别目标时所面临的问题及分析[J]. 光学技术, 2005, 31(2):231-234.Wu Chun-feng, Zhang Wei, and Li Jie, et al.. Problems and itsanalysis of infrared imaging detection and identificationfacing[J]. Optical Technique, 2005, 31(2): 231-234. [2] 张兵. 光学图像末制导中的点目标检测与识别算法研究[D].[博士论文], 国防科技大学, 2005.Zhang Bing. Point target detection and recognitionalgorithms in optical image terminal homing system[D].[Ph.D. dissertation], National University of DefenseTechnology, 2005. [3] Cheryl R. Exo-atmospheric discrimination of thrusttermination debris and missile segments[J]. Johns HopkinsAPL Technical Digest, 1998, 19(3): 315-321. [4] Xiao Huai-tie and Zhuang Zhao-wen. Aircraft targetrecognition using adaptive time-delay neural network[C][J].NAECON 1997., Proceedings of the IEEE 1997 National,Aerospace and ecectronics conference.1997, 2:764-768 [5] Kim Sung-suk. Time-delay recurrent neural network fortemporal correlations and prediction[J].Neurocomputing.1998, 20(2):253-263 [6] Kim Sung-suk and Mark Hasegawa-johnson, et al..Automatic recognition of pitch movements using multilayerperceptron and time-delay recursive neural network[J].IEEESignal Processing Letters.2004, 11(7):645-648 [7] 肖业伦. 航空航天器运动的建模[M]. 北京: 北京航空航天大学出版社, 2006: 52-74.Xiao Ye-lun. Dynamics Modeling of Aeronautic andAtmospheric Flight[M]. Beijing University of Aeronautics andAstronautics Press, 2006: 52-74. [8] 毛红霞, 李霞, 等. 空间目标与环境红外特性理论建模及其场景生成[J]. 红外与激光工程, 2007, 36(5): 607-610.Mao Hong-xia and Li Xia, et al.. Simulation of infraredradiation from outer space targets and environment, and itsgeneration technique of scene[J]. Infrared and LaserEngineering, 2007, 36(5): 607-610. [9] 曹西征, 郭立红. 基于图像的飞行器红外辐射特性测量[J]. 光学技术, 2007, 22(2): 299-304.Cao Xi-zheng and Guo Li-hong. Measurement of the infraredradiation characteristic of the aerobat based on images[J].Optical Technique, 2007, 22(2): 299-304.

施引文献

资源附件(0)

访问统计