基于CNN的多尺寸航拍图像定位方法的研究与实现

Research and implementation of multi-size aerial image positioning method based on CNN

图像定位常用于无人机视觉导航,传统的无人机视觉导航广泛采用景象匹配导航方式,随着计算机技术的不断发展,深度学习技术为视觉导航的实现提供了新途径。以无人机的垂直侦查为背景,将飞行区域的航拍图像划分成大小相同的若干网格,每个网格代表一类区域,用网格图像制作数据集训练卷积神经网络(CNN)。基于AlexNet设计了一种融合显著性特征的全卷积网络模型,有效实现了一个基于CNN的多尺寸输入的滑动窗口分类器,并提出了一种邻域显著性参照定位策略来筛选分类结果,从而实现多尺寸航拍图像的定位。

Image positioning is the key of UAV visual navigation.Scene matching navigation is widely used in traditional UAV visual navigation.With the continuous development of computer technology,deep learning technology provides a new way for the realization of visual navigation.In this context,this research mainly focuses on image localization based on convolution neural network.In this paper,based on the vertical reconnaissance of UAV,the aerial image of flight area is divided into several grids of the same size,each grid represents a class of regions,and the convolutional neural network(CNN)is trained by making data sets of grid images.This paper designs a fully convolutional network model based on AlexNet,which integrates saliency features.It effectively implements a sliding window classifier with CNN multi-size input,and proposes a neighborhood saliency reference positioning strategy to filter the classification results,so as to realize the positioning of multi-size aerial images.