神经网络预测控制的航空相机前向像移补偿方法研究

doi:10.3969/j.issn.1000-1093.2012.06.012

兵工学报 ›› 2012, Vol. 33 ›› Issue (6): 706-711.doi: 10.3969/j.issn.1000-1093.2012.06.012

神经网络预测控制的航空相机前向像移补偿方法研究

仲崇亮^1,2,3，丁亚林^1,3，付金宝^2,3

（1.中国科学院长春光学精密机械与物理研究所中国科学院航空光学成像与测量重点实验室，吉林长春 130033；2.中国科学院研究生院，北京 100039； 3.中国科学院长春光学精密机械与物理研究所，吉林长春 130033）

收稿日期:2010-08-10 修回日期:2010-08-10 上线日期:2014-03-04
作者简介:仲崇亮（1985—），男，博士研究生

Forward Image Motion Compensation for Aerial Camera Based on Neural Network Predictive Control

ZHONG Chong-liang^1,2,3， DING Ya-lin^1,3， FU Jin-bao^2,3

(1.Key Laboratory of Airborne Optical Imaging and Measurement, Changchun Institute of Optics, Fine Mechanics and Physics,Chinese Academy of Sciences，Changchun 130033, Jilin, China；2.Graduate University of Chinese academy of Sciences,Beijing 100039, China; 3.Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences，Changchun 130033, Jilin, China)

Received:2010-08-10 Revised:2010-08-10 Online:2014-03-04

摘要/Abstract

摘要： 为了对某全景式航空相机所产生的前向像移进行补偿，对前向像移产生的原理进行分析，并对像移补偿的方法进行研究。根据该型相机的工作原理，找到前向像移产生的机理。用神经网络模型（NNM）对系统时域响应的非线性特性进行辨识。根据NNM给出的扫描反射镜补偿角速度的预测值，通过最优算法调整控制信号，使被控对象跟踪理想补偿角速度的性能达到最优。该方法在该型相机前向像移补偿上克服了传统PID控制方法中所存在的不足，即精度低、响应慢、适应性差。实验结果表明：采用神经网络预测控制，扫描反射镜的实际补偿角速度输出跟踪理想补偿角速度的性能良好，优于传统方法。该方法可以应用于该型航空相机的像移补偿中。

关键词: 自动控制技术, 航空相机, 前向像移, 像移补偿, 神经网络, 预测控制

Abstract: In order to compensate forward image motion of a certain aviation camera, the reasons for it were analyzed, and the compensation methods were studied. Firstly, the mechanism of image motion was found out on the basis of the camera’s principle. Secondly, a neural network model (NNM) was used to identify the nonlinear characteristics of the system’s response in time domain. Finally, according to the prediction given by NNM, the control signal was adjusted by using optimal algorithm to make the tracking performance of the scanning mirror optimal. This method overcomes some shortcomings of traditional PID control, such as low accuracy, slow response and weak adaptability. The compensation results show that the compensated angular speed of scanning mirror can track the desired angular speed.

Key words: automatic control technology, aviation camera, forward image motion, image motion compensation, neural network, predictive control

中图分类号:

TP391.4

仲崇亮，丁亚林，付金宝. 神经网络预测控制的航空相机前向像移补偿方法研究[J]. 兵工学报, 2012, 33(6): 706-711.

ZHONG Chong-liang， DING Ya-lin， FU Jin-bao. Forward Image Motion Compensation for Aerial Camera Based on Neural Network Predictive Control[J]. Acta Armamentarii, 2012, 33(6): 706-711.

参考文献

［1］徐抒岩，于涛，韩诚山，等. 一种空间相机偏流角间歇式实时调整方法[J]. 光学精密工程，2009，17(8): 1908-1914.
XU Shu-yan, YU Tao, HAN Cheng-shan, et al. One batch type real-time adjusting of drift angle of space camera[J]. Optics and Precision Engineering, 2009, 17(8): 1908-1914. (in Chinese)
[2] 李仕，张葆，孙辉. 一种航空斜视成像异速像移实时恢复算法[J]. 光学精密工程, 2009, 17(4): 895-900.
LI Shi, ZHANG Bao, SUN Hui. A real-time restoration algorithm for aerial side-oblique images with different rates of image motion[J]. Optics and Precision Engineering, 2009, 17(4): 895-900. (in Chinese)
[3] 黄浦, 葛文奇, 李友一, 等. 航空相机前向像移补偿的线性自抗扰控制[J]. 光学精密工程,2011, 19(4):812-819.
HUANG Pu, GE Wen-qi, LI You-yi, et al. Linear auto disturbance rejection control of forward image motion compensation in aerial cameras[J]. Optics and Precision Engineering, 2011, 19(4): 812-819. (in Chinese)
[4] 王运, 颜昌翔. 基于差分法的空间相机像移速度矢量计算[J]. 光学精密工程,2011, 19(5): 1054-1060.
WANG Yun, YAN Chang-xiang. Computation of image motion velocity vector for space camera based on difference method[J]. Optics and Precision Engineering, 2011, 19(5): 1054-1060. (in Chinese)
[5] 李兴华. 高分辨力空间摄影相机像移补偿控制技术研究[D]. 长春：中国科学院长春光学精密机械与物理研究所,2000.
LI Xin-hua. Study on motion compensating control system in high-resolution space camera[D]. Changchun：Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, 2000. (in Chinese)
[6] 耿洁, 刘向东, 陈振, 等. Preisach迟滞逆模型的神经网络分类排序[J]. 光学精密工程, 2010, 18(4): 855-862.
GENG Jie, LIU Xiang-dong, CHEN Zhen, et al. Realization of sorting & taxis of Preisach inverse hysteresis model using neural network[J]. Optics and Precision Engineering, 2010, 18(4): 855-862. (in Chinese)
[7] 陈浩, 朱娟, 刘艳滢, 等. 利用脉冲耦合神经网络的图像融合[J]. 光学精密工程, 2010, 18(4): 995-1001.
CHEN Hao, ZHU Juan, LIU Yan-ying, et al. Image fusion based on pulse coupled neural network[J]. Optics and Precision Engineering, 2010, 18(4): 995-1001. (in Chinese)
[8] 武治国, 王延杰. 基于自适应PCNN和小波变换的多聚焦图像融合算法[J]. 光学精密工程, 2010, 18(3): 708-715.
WU Zhi-guo, WANG Yan-jie. Multi-focus image fusion algorithm based on adaptive PCNN and wavelet transform[J]. Optics and Precision Engineering, 2010, 18(3): 708-715. (in Chinese)
[9] 娄帅,丁振良,袁峰,等. 应用Hopfield神经网络和小波域隐Markov树模型的图像复原[J]. 光学精密工程, 2009, 17(11): 2828-2834.
LOU Shuai, DING Zhen-liang, YUAN Feng, et al. Image restoration based on Hopfield neural network and wavelet domain HMT model[J]. Optics and Precision Engineering, 2009, 17(11): 2828-2834. (in Chinese)
[10] 沈铖武, 王志乾, 刘畅, 等. BP神经网络在多位置捷联寻北系统中的应用[J]. 光学精密工程, 2009,17(8): 1890-1895.
SHENG Cheng-wu, WANG Zhi-qian, LIU Chang, et al. The application of BP neural network on the multi-position strap-down north seeking system[J]. Optics and Precision Engineering, 2009, 17(8): 1890-1895. (in Chinese)
[11] 朱福珍, 李金宗, 朱兵, 等. 基于径向基函数神经网络的超分辨率图像重建[J]. 光学精密工程, 2010, 18(6): 1444-1451.
ZHU Fu-zhen, LI Jin-zong, ZHU Bing, et al. Super resolution image reconstruction based on RBF neural network [J]. Optics and Precision Engineering, 2010, 18(6): 1444-1451. (in Chinese)
[12] Soloway D, Haley P J. Neural generalized predictive control[C]∥Proceedings of the International Symposium on Intelligent Control. IEEE, 1996：277-281.

[1]	陈桂明，许令亮. 基于非线性扰动补偿的超局部无模型永磁同步电机电流预测控制[J]. 兵工学报, 2024, 45(4): 1129-1140.
[2]	王尔烈，王帅，皮大伟，王洪亮，王显会，谢伯元. 某纯电驱动重载车辆能耗预测模型[J]. 兵工学报, 2024, 45(4): 1229-1236.
[3]	刘梦真, 黄广炎, 张宏, 周宏元, 刘思宇. 小样本驱动特征分段网络的防护材料折痕检测[J]. 兵工学报, 2024, 45(3): 963-974.
[4]	秦国华, 娄维达, 林锋, 徐勇. 基于Cotes求积法和神经网络的稳定域判断及铣削参数优化新方法[J]. 兵工学报, 2024, 45(2): 516-526.
[5]	吕卫民, 孙晨峰, 任立坤, 赵杰, 李永强. 一种基于TCN-LGBM的航空发动机气路故障诊断方法[J]. 兵工学报, 2024, 45(1): 253-263.
[6]	刘江涛, 周乐来, 李贻斌. 复杂地形六轮独立驱动与转向机器人轨迹跟踪与避障控制[J]. 兵工学报, 2024, 45(1): 166-183.
[7]	许鹏, 邢伯阳, 刘宇飞, 李泳耀, 曾怡, 郑冬冬. 基于扩张状态观测器和模型预测方法的四足机器人抗干扰复合控制[J]. 兵工学报, 2023, 44(S2): 12-21.
[8]	李曹妍, 郭振川, 郑冬冬, 魏延岭. 基于分布式模型预测控制的多机器人协同编队[J]. 兵工学报, 2023, 44(S2): 178-190.
[9]	刘畅, 雷红波, 林时尧, 范世鹏, 王江. 基于多模型网络的激光末制导炮弹诸元解算方法[J]. 兵工学报, 2023, 44(9): 2745-2755.
[10]	张凯歌, 卢志刚, 聂天常, 李志伟, 郭宇强. 面向无人装备的智能边缘计算软技术分析[J]. 兵工学报, 2023, 44(9): 2611-2621.
[11]	刘冰, 郝新红, 周文, 杨瑾. 基于BAS-BPNN的调频无线电引信目标与扫频干扰识别方法[J]. 兵工学报, 2023, 44(8): 2391-2403.
[12]	周宇, 曹荣刚, 栗苹, 马啸. 一种用于外场试验图像的引信炸点检测方法[J]. 兵工学报, 2023, 44(8): 2453-2464.
[13]	吴礼洋, 呙鹏程, 刘超, 李文强. 基于注意力机制增强残差网络的雷达信号调制类型识别[J]. 兵工学报, 2023, 44(8): 2310-2318.
[14]	解宝琦, 李英顺, 王德彪, 隋欢欢. 一种坦克炮长瞄准镜系统状态评估的方法[J]. 兵工学报, 2023, 44(8): 2414-2423.
[15]	刘懿, 任济寰, 吴祥, 薄煜明. 基于集成迁移学习的新装备装甲车辆分类[J]. 兵工学报, 2023, 44(8): 2319-2328.

神经网络预测控制的航空相机前向像移补偿方法研究

Forward Image Motion Compensation for Aerial Camera Based on Neural Network Predictive Control

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价