模糊神经网络在机载相机稳像中的应用

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.

Type-II fuzzy neural networks with self-organizing recurrent intervals for image stabilization of the airborne camera

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.