Abstract
The similar analysis of time sequence images to achieve image matching is a foundation of tasks in dynamic environments, such as multi-object tracking and dynamic gesture recognition. Therefore, we propose a matching method of time sequence images based on the Siamese network. Inspired by comparative learning, two different comparative parts are designed and embedded in the network. The first part makes a comparison between the input image pairs to generate the correlation matrix. The second part compares the correlation matrix, which is the output of the first comparison part, with a template, in order to calculate the similarity. The improved loss function is used to constrain the image matching and similarity calculation. After experimental verification, we found that it not only performs better, but also has some ability to estimate the camera pose.
Highlights
Judging the relationship of an image pair is a common issue in the field of computer vision
Image matching [1,2,3] refers to judging the relationship between image pairs by identifying the same or similar scenes, objects, shapes, and semantics of two images
With the rapid development of image matching technology, many approaches based on the Siamese network [4,5] are proposed
Summary
Judging the relationship of an image pair is a common issue in the field of computer vision. It has an important effect in SfM (structure from motion), image retrieval, pose estimation, and stereo match. Due to its unique architecture, the Siamese network performs much better compared to other networks in face recognition [6,7], instance segmentation [8], object tracking [9,10,11,12], and so on It is considered as a promising network in image matching.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.