CONF Duffner_FG_2011/IDIAP Exploiting Long-Term Observations for Track Creation and Deletion in Online Multi-Face Tracking Duffner, Stefan Odobez, Jean-Marc EXTERNAL https://publications.idiap.ch/attachments/papers/2011/Duffner_FG_2011.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/Duffner_Idiap-RR-01-2011 Related documents IEEE Conference on Automatic Face and Gesture Recognition 2011 IEEE Santa Barbara, USA 525-530 978-1-4244-9140-7 In many visual multi-object tracking applications, the question when to add or remove a target is not trivial due to, for example, erroneous outputs of object detectors or observation models that cannot describe the full variability of the objects to track. In this paper, we present a real-time, online multi-face tracking algorithm that effectively deals with missing or uncertain detections in a principled way. To this end, we propose to use long-term image observations, and an explicit probabilistic filtering framework that decides when to add or remove a target from the tracker. We evaluated the proposed method on three different difficult datasets with a total length of more than 9 hours and show a significant increase in performance of the tracking. REPORT Duffner_Idiap-RR-01-2011/IDIAP Exploiting Long-Term Observations for Track Creation and Deletion in Online Multi-Face Tracking Duffner, Stefan Odobez, Jean-Marc EXTERNAL https://publications.idiap.ch/attachments/reports/2010/Duffner_Idiap-RR-01-2011.pdf PUBLIC Idiap-RR-01-2011 2011 Idiap Rue Marconi 19, CH-1920 Martigny January 2011 In many visual multi-object tracking applications, the question when to add or remove a target is not trivial due to, for example, erroneous outputs of object detectors or observation models that cannot describe the full variability of the objects to track. In this paper, we present a real-time, online multi-face tracking algorithm that effectively deals with missing or uncertain detections in a principled way. To this end, we propose to use long-term image observations, and an explicit probabilistic filtering framework that decides when to add or remove a target from the tracker. We evaluated the proposed method on three different difficult datasets with a total length of almost 10 hours and show a significant increase in performance of the tracking.