Robust and adaptive keypoint-based object tracking
2016 (English)In: Advanced Robotics, ISSN 0169-1864, E-ISSN 1568-5535, Vol. 30, no 4, 258-269 p.Article in journal (Refereed) PublishedText
Object tracking is a fundamental ability for a robot; manipulation as well as activity recognition relies on the robot being able to follow objects in the scene. This paper presents a tracker that adapts to changes in object appearance and is able to re-discover an object that was lost. At its core is a keypoint-based method that exploits the rigidity assumption: pairs of keypoints maintain the same relations over similarity transforms. Using a structured approach to learning, it is able to incorporate new appearances in its model for increased robustness. We show through quantitative and qualitative experiments the benefits of the proposed approach compared to the state of the art, even for objects that do not strictly follow the rigidity assumption.
Place, publisher, year, edition, pages
Robotics Society of Japan , 2016. Vol. 30, no 4, 258-269 p.
learning, Object tracking, real-time tracker, pose estimation, keypoints
Computer Vision and Robotics (Autonomous Systems)
IdentifiersURN: urn:nbn:se:kth:diva-185078DOI: 10.1080/01691864.2015.1129360ISI: 000372182900003ScopusID: 2-s2.0-84960959205OAI: oai:DiVA.org:kth-185078DiVA: diva2:919728
QC 201604142016-04-142016-04-112016-04-14Bibliographically approved