作者：杨宏韬1,2,3, 高慧斌1, 刘鑫1
作者单位：1. 中国科学院长春光学精密机械与物理研究所, 吉林 长春 130033;
2. 中国科学院大学, 北京 100049;
3. 长春工业大学电气与电子工程学院, 吉林 长春 130012
关键词：光电经纬仪;空间配准;小波神经网络;序贯极限学习机
摘要：
针对光电经纬仪数据融合系统中的空间配准问题,提出复合函数小波神经网络序贯极限学习机光电经纬仪空间配准算法。该算法将小波理论引入到极限学习机中,利用小波函数和任意分段连续非线性函数构造极限学习机隐层节点激励函数,小波函数的伸缩因子和平移因子根据输入数据范围进行初始化,并结合极限学习机在线学习方法进行训练。实验结果表明:改进小波序贯极限学习机的光电经纬仪空间配准算法可以使光电经纬仪的测量精度提高到3以内,与标准极限学习机空间配准算法相比,该算法能够实现在线增量式快速学习,具有更好的泛化性能。
Research on modified wavelet online sequential extreme learning machine in space registration for photoelectric theodolite
YANG Hongtao1,2,3, GAO Huibin1, LIU Xin1
1. Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, China;
2. University of Chinese Academy of Sciences, Beijing 100049, China;
3. College of Electronic and Electrical Engineering, Changchun University of Technology, Changchun 130012, China
Abstract: An algorithm using composite functions and wavelet neural networks(WNN) in online sequential extreme learning machines (OS-ELM) was proposed to solve the problem in the space registration of photoelectric theodolite data fusion system. The wavelet theory was introduced to extreme learning machines and the wavelet function and bounded non-constant piecewise continuous function were used to build an hidden-node excitation function for extreme learning machine. The contraction-expansion and shift factors of the wavelet function were initiated with the input data range and it was trained in combination with the online learning methods of extreme learning machine. Experimental results show that this algorithm can improve the measurement accuracy of photoelectric theodolite to within 3" and has fast online learning speed and good generalization compared with standard space registration algorithms.
Keywords: photoelectric theodolite;space registration;WNN;OS-ELM
2015, 41(10): 1-5 收稿日期: 2015-02-26;收到修改稿日期: 2015-04-13
基金项目: 国家863计划项目(2008AA0047)
作者简介: 杨宏韬(1982-),男,吉林长春市人,博士,研究方向为光电测量与信息融合。
参考文献
[1] 刘瑜,何友,王海鹏,等. 基于平方根容积卡尔曼滤波的目标状态与传感器偏差扩维联合估计算法[J]. 吉林大学学报:工学版,2015,45(1):314-321.
[2] 李军辉,杨峰,程咏梅,等. 一种多传感器实时误差配准算法研究[J]. 传感技术学报,2010,23(5):713-716.
[3] 崔亚奇,熊伟,何友. 基于ＭＬＲ的机动平台传感器误差配准算法[J]. 航空学报,2012,33(1):118-128.
[4] Nassib N, Robort H. Bishop solution to a multisensor tracking problem with sensor registration error[J]. IEEE T-AES,1999,35(1):354-363.
[5] 余建国,刘梅,包玖红. 基于星光测量天基传感器实时定标在弹道目标跟踪应用[J]. 电子与信息学报,2013,35(4):915-920.
[6] Karmiely H, Hava T S. Sensor registration using neural network[J]. IEEE Transactions on Aerospace and Electronic Systems,2000,36(1):85-100.
[7] 杨宏韬,高慧斌,张淑梅. 极限学习机方法在经纬仪空间配准中的应用[J]. 红外与激光工程,2013,42(12):3517-3521.
[8] Liang N Y, Huang G B, Saratchandran P, et al. A fast and accurate online sequential learning algorithm for feedforward networks[J]. IEEE Transactions on Neural Networks,2006,17(6):1411-1423.
[9] Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: theory and applications[J]. Neurocomputing,2006,70(1):489-501.
[10] Lan Y, Yeng C S, Huang G B. Ensemble of online sequential extreme learning machine[J]. Neurocomputing,2009,72(1):3391-3395.
[11] 全丽萍,李晓理,王巧智. 多分辨率小波极限学习机[J]. 北京科技大学学报,2014,36(12):1712-1719.
[12] Cao J W, Lin Z P, Huang G B. Composite function wavelet neural networks with extreme learning machine[J].Neurocomputing,2010(73):1405-1416.
