Abstract
Temporal alignment of videos is an important requirement of tasks such as video comparison, slicing, synchronization, and classification. Most of the approaches proposed to date for video alignment treat videos equivalent and leverage dynamic programming algorithms whose parameters are manually tuned. In this paper, we develop a semi-global alignment algorithm for aligning depth videos and use human movement tracking as an application. The key idea is to integrate the temporal constraints to select a template for each input depth frame such that the overall similarity of aligned templates and all input frames are maximized. By registering resampled videos of a single person, our method improves the accuracy by more than 12.4%. This accuracy improvement is also confirmed by our experiments of registering videos of different persons. It is hence evident that our proposed method finds the pattern of movement of people and correctly aligns the frames between the input video and template video.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
