Abstract
We propose a method for tracking groups from single and multiple cameras with disjointed fields of view. Our formulation follows the tracking-by-detection paradigm in which groups are the atomic entities and are linked over time to form long and consistent trajectories. To this end, we formulate the problem as a supervised clustering problem in which a structural SVM classifier learns a similarity measure appropriate for group entities. Multicamera group tracking is handled inside the framework by adopting an orthogonal feature encoding that allows the classifier to learn inter- and intra-camera feature weights differently. Experiments were carried out on a novel annotated group tracking data set, the DukeMTMC-Groups data set. Since this is the first data set on the problem, it comes with the proposal of a suitable evaluation measure. Results of adopting learning for the task are encouraging, scoring a +15% improvement in F1 measure over a nonlearning-based clustering baseline. To the best of our knowledge, this is the first proposal of its kind dealing with multicamera group tracking.
Highlights
T HE fast-growing interest in automated analysis of crowds and social gatherings for surveillance and security applications opens new challenges for the computer vision community as well
To previous work [11], [12], we recently proposed a group detection algorithm that works over temporal windows [13] to account for sociological as well as physical evidence
We evaluate the results using our proposed performance measure that accounts for both group detection and group tracking errors
Summary
T HE fast-growing interest in automated analysis of crowds and social gatherings for surveillance and security applications opens new challenges for the computer vision community as well. Group dynamics drives collective behavior by encouraging people to engage in acts they might otherwise consider unthinkable under typical social circumstances [3]. Crowds and gatherings are constant features of the social world, and groups have proven to be the constitutional and structural building blocks of events related to them. This observation has led to an increased emphasis on group detection and tracking in the automatic analysis of surveillance video
Sign-in/Register to view highlights & summary 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 callMore From: IEEE Transactions on Circuits and Systems for Video Technology
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.
