Please wait a minute...
J4  2012, Vol. 46 Issue (8): 1540-1545    DOI: 10.3785/j.issn.1008-973X.2012.08.028
光学工程、电信技术     
模糊神经网络在机载相机稳像中的应用
李迪1,2, 陈向坚1,2, 续志军2, 白越1
1.中国科学院 长春光学精密机械及物理研究所, 吉林 长春130033; 2.中国科学院 研究生院,北京 100039
Type-II fuzzy neural networks with self-organizing recurrent intervals
for image stabilization of the airborne camera
LI Di1,2, CHEN Xiang-jian1,2, XU Zhi-jun1, BAI Yue1
1.Chang Chun Institute of optics fine mechanics and physics.Chinese academy of sciences 130033, China;
2. Graduate School of Chinese Academy of Sciences, Beijing 100039, China
 全文: PDF  HTML
摘要:

针对解决微型飞行器空中拍摄的图像抖动问题,采用自组织递归区间二型模糊神经网络的函数逼近及泛化能力对微型飞行器上的相机振动规律进行模拟,预测机载相机的振动矢量.该自组织递归区间二型模糊神经网络的初始规则数为零,所有规则都是通过结构和参数同时在线学习来产生,网络结构学习采用的是在线区间二型模糊群集,提高自组织递归区间二型模糊神经网络的稳定性及计算精度.仿真结果表明:将自组织递归区间二型模糊神经网络与双BP神经网络进行对比,利用自组织递归区间二型模糊神经网络对微型飞行器相机振动矢量进行预测的精度高.

Abstract:

The vibration rule of the airborne camera was studied to solve the image vibration in aerial photography of the micro aircraft vehicle (MAV). A method based on the ability of function approximation of type-II fuzzy neural networks with self-organizing recurrent intervals to simulate the vibration rule of airborne camera in the MAV and predict the vibration displacement vectors during image stabilization was proposed. The type-II fuzzy neural networks with self-organizing recurrent intervals has no initial network rules, all rules are generated from the simultaneous on-line parameter and structure learning, where the network structural learning takes the on-line interval type-II fuzzy-set, which improves the stability and precision of the type-II fuzzy neural networks with self-organizing recurrent intervals. The results show that type-II fuzzy neural network with self-organizing recurrent intervals system is more stable and the higher precision and good real-time performance than combined BP neural networks.

出版日期: 2012-09-23
:  TP 394.1  
基金资助:

国家自然科学基金资助项目(50905174).

通讯作者: 续志军,男,研究员,博导.     E-mail: xuzj538@ciomp.edu.cn
作者简介: 李迪(1982—),男,博士生,从事微型飞行器图像处理技术研究.E-mail:lidi19821111@163.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  

引用本文:

李迪, 陈向坚, 续志军, 白越. 模糊神经网络在机载相机稳像中的应用[J]. J4, 2012, 46(8): 1540-1545.

LI Di, CHEN Xiang-jian, XU Zhi-jun, BAI Yue. Type-II fuzzy neural networks with self-organizing recurrent intervals
for image stabilization of the airborne camera. J4, 2012, 46(8): 1540-1545.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2012.08.028        http://www.zjujournals.com/eng/CN/Y2012/V46/I8/1540

[1] 雷宝权,赵春晖,花永强.基于SIFT算在和Kalman滤波器的航拍图像电子稳像算法 [J].火力与指挥控制.2010,35(10): 47-50.
LEI BaoQuan, ZHAO ChunHui, HUA YongQiang. An EIS algorithm to aerial images based on SIFT and kalman filter [J]. Fire Control and Command Control, 2010, 35(10): 47-50.
[2] 王斌,赵跃进.基于电子稳像跟踪技术的运动滤波算法 [J].光学精密工程,2009,17(1): 202-206.
WANG Bin, ZHAO YueJin. Motion filtering algorithm for tracking technology based on image stabilization [J]. Optics and Precision Engineering, 2009, 17(1): 202-206.
[3] 钟平,于前洋,金光,等.机载摄像设备图像稳定方法探讨[J].光电工程.2002,29(12): 74-83.
ZHONG Ping, YU QianYang, JIN Guang, et al. Study on image stabilizing methods for airborne image pickup equipment [J].OptoElectronic Engineering, 2002,29(12): 74-83.
[4] 陈跃庭,李奇,许东晖,等.投影算法与块匹配法结合的实时数字稳像方法[J].浙江大学学报:工学版,2007,41(9): 1537-1540.
CHEN Yueting, LI Qi, XU Donghui, et al. Realtime digital image stabilization method based on projection algorithm and block matching [J]. Journal of Zhejiang University: Engineering Science, 2007,41(9): 1537-1540.
[5] KARNIK N N, MENDEL J M, LIANG Q. Type2 fuzzy logic systems[J]. IEEE Transactions Fuzzy Systems, 1999,7(6): 643-658.
[6] MENDEL J M. Type2 fuzzy sets made simple[J]. IEEE Transactions Fuzzy Systems,2002,10(2): 117-127.
[7] JOHN R, COUPLAND S. Type2 fuzzy logic: A historical view [J]. IEEE Computtational Intelligence Magazine, 2007, 2(1): 57-62.
[8] CHEN Xiangjian, LI Di, BAI Yue, XU Zhijun. Modeling and NeuroFuzzy adaptive attitude control for EightRotor MAV [J]. International Journal of control, Automation and Systems, 2011, 9(6): 1154-1163.
[9] 李迪,陈向坚,续志军,等.自组织递归区间二型模糊神经网络在动态时变系统辨识中的应用[J].光学精密工程.2011,19(6): 1407-1413.
LI Di, CHEN Xiangjian, XU Zhijun, et到al. A selforganizing recurrent interval typeII fuzzy neural networks for dynamic timevarying system identification [J]. Optics and Precision Engineering, 2011,19(6): 1407-1413.
[10] JUANG C F. A selfevolving internal type2 fuzzy neural network with online structure and parameter learning[J]. IEEE Transactions Fuzzy Systems, 2008,16(6): 1411-1424.
[11] CHEN Xiangjian, LI Di, BAI Yue, etal. Modeling and NeuroFuzzy adaptive attitude control for EightRotor MAV [J].  International Journal of Control, Automation and Systems, 2011, 9(6): 1154-1163.
[12] 陈向坚,李迪,白越,等.模糊神经网络在自适应双轴运动控制系统中的应用[J].光学精密工程.2011,19(8): 1644-1650.
CHEN Xiangjian, LI Di, BAI Yue, etl. TypeII fuzzy neural networks with selforganizing recurrent intervals for dynamic timevarying system identification [J]. Optics and Precision Engineering, 2011,19(8): 1644-1650.
[13] MENDOZA. O, MELIN. P, CASTILLO. Q. Inverse control of cabledriven parallel mechanism using type2 fuzzy neural network [J]. Acta Automatica Sinica, 2010, 36(3): 459-464.
[14] LIN. T. C. Based on interval type2 fuzzyneural network direct adaptive sliding mode control for SISO nonlinear systems [J]. Communications in Nonlinear Science and Numerical Simulation, 2010, 15(12): 4084-4099.
[15] ERDAL. K, YESIM. O, AYSE. C. A, etal. A servo system control with timevarying and nonlinear load conditions using type2 TSK fuzzy neural system [J]. Applied Soft Computing, 2011, 11(8): 5735-5744.
[16] 董文德,徐之梅,李奇.稳像中基于BP神经网络的颤振预测及改进[J].浙江大学学报:工学版,2010,44(12): 2263-2268.
DONG Wende, XU ZhiMei, LI Qi. Vibration forecasting using BP neural network for image stabilization and an improving method [J].Journal of Zhejiang University: Engineering Science, 2010, 44(12): 2263-2268.

No related articles found!