Abstract
Although many visual tracking algorithms have made many achievements in video sequences, they have not been confirmed to work well on the real robot systems with the unpredictable changes and limited computing capabilities. In order to face the complex practical conditions, including huge scale variation, occlusion and long-term task, this paper develops a CF-based long-term tracking algorithm. The main strategies are as follows. A novel confidence score is proposed to judge tracking reliability, and the tracking drift is corrected to keep the target’s long-term appearance. Furthermore, once the target is lost, it can be relocated by the multi-scale search. Our tracker performs favorably against other CF-based trackers with strong engineering applicability. Finally, experiments on the datasets and an UAV are carried out to verify the effectiveness for real robot systems.
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.
