A Brief Survey of Feature Based Image Matching

The image matching task, which aims to find the correspondence between elements across images, is a fundamental component for many computer vision applications. In visual simultaneous localization and mapping algorithms, the pose can be estimated on the basis of correspondences between multiple measurements obtained by on-board cameras. Feature-based image matching methods have rapidly developed and been widely utilized in the past few decades due to their robustness and accuracy. In this paper, feature-based image matching task is reviewed according to its process, including feature detection, feature description, and feature matching.