基于边缘检测及RBF神经网络的遥感图像帧特征动态识别技术  

Dynamic Recognition Technology of Remote Sensing Image Frame Features Based on Edge Detection and RBF Neural Network

作　　者：薛薇 张锋[2] 凡静 王博 李娜 XUE Wei;ZHANG Feng;FAN Jing;WANG Bo;LI Na(Computer Department,Xi'an Jiaotong University City College,Xi'an 710018,China;School of Electrical Engineering,Xi'an Jiaotong University,Xi'an 710049,China)

机构地区：[1]西安交通大学城市学院计算机系,西安710018 [2]西安交通大学电气学院,西安710049

出　　处：《计算机测量与控制》2023年第7期163-168,共6页Computer Measurement &Control

基　　金：西安交通大学城市学院2020年度校级科研项目(202002X03)。

摘　　要：为解决分辨率超限问题,实现对遥感图像帧特征对象的精准识别,提出基于边缘检测及RBF神经网络的遥感图像帧特征动态识别技术;求解微分算子与OTSU阈值,并以此为基础,确定边缘节点追踪参数的取值范围,实现对遥感图像边缘检测;根据RBF神经网络机制的构建标准,推导神经性激活函数,完成RBF神经网络识别模型的设计;在所选遥感图像中,实施帧特征分割处理,再联合动态合并条件,计算超像素指标与并行识别参量,完成基于边缘检测及RBF神经网络的遥感图像帧特征动态识别方法的设计;实验结果表明,在边缘检测与RBF神经网络模型的作用下,主机元件在长、宽、高3个方向上对于遥感图像帧特征对象的识别精度都达到了100%,分辨率超限问题得到较好解决,符合精准识别遥感图像特征的实际应用需求。In order to solve the problem of resolution overrun and realize the accurate recognition of remote sensing image frame feature objects,a dynamic recognition technology of remote sensing image frame feature based on edge detection and radical basis function(RBF)neural network is proposed.The differential operator and OTSU threshold are solved to determine the value range of the tracking parameters of the edge node,and realize the edge detection of the remote sensing image.According to the construction standard of the RBF neural network mechanism,the neural activation function is deduced,and the RBF neural network recognition model is designed.In the selected remote sensing image,the frame feature segmentation processing is implemented,and then combined with the dynamic merging conditions,the super-pixel index and parallel recognition parameters are calculated,and the dynamic recognition method of remote sensing image frame feature based on the edge detection and RBF neural network is completed.The experimental results show that under the action of the edge detection and RBF neural network model,the recognition accuracy of the host component for the remote sensing image frame feature object in three directions of length,width and height reaches 100%,and the problem of resolution overrun is well solved,which meets the practical application requirements of the accurate recognition of remote sensing image features.

关 键 词：边缘检测 RBF神经网络 遥感图像 帧特征 动态识别 OTSU阈值 神经性激活函数 超像素 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]