特征匹配在视觉定位、同时定位和映射(SLAM)、图像拼接等方面都有应用

Proj：202404 CMC-R(R.W.--Reference)

南京 河海大学

资助丰富Fundamental Research Funds of China for the Central Universities, Grant/Award Number: B230205048; Jiangsu Higher Education Reform Research Project, Grant/Award Number: 2021JSJG143; Postgraduate Research & Practice Innovation Program of Jiangsu Province, Grant/Award Number: KYCX23_0685; Yunnan Provincial Science and Technology Department, Grant/Award Number: 202203AA080009; 14th Five-Year Plan for Educational Science of Jiangsu Province, Grant/Award Number: D/2021/01/39; 2022 Undergraduate Practice Teaching Reform Research Project of Hohai University

1. 特征提取Feature Extraction

特征提取是特征匹配的关键环节。

为了匹配一对图像，第一步是使用特征检测器发现图像中的特征。

在传统的方法中，可以根据图像中像素强度的变化来识别特征。相比之下，基于深度学习的方法使用卷积神经网络生成特征映射ÿ