Fusion of tracking techniques to enhance adaptive real-time tracking of arbitrary objects
- In visual adaptive tracking, the tracker adapts to the target, background, and conditions of the image sequence. Each update introduces some error, so the tracker might drift away from the target over time. To increase the robustness against the drifting problem, we present three ideas on top of a particle filter framework: An optical-flow-based motion estimation, a learning strategy for preventing bad updates while staying adaptive, and a sliding window detector for failure detection and finding the best training examples. We experimentally evaluate the ideas using the BoBoT dataseta. The code of our tracker is available online.
Author of HS Reutlingen | Rätsch, Matthias |
---|---|
URN: | urn:nbn:de:bsz:rt2-opus4-1015 |
DOI: | https://doi.org/10.1016/j.procs.2014.11.025 |
eISSN: | 1877-0509 |
Erschienen in: | Procedia computer science |
Publisher: | Elsevier |
Place of publication: | Amsterdam |
Document Type: | Journal article |
Language: | English |
Publication year: | 2014 |
Tag: | adaptive tracking; optical flow; particle filter; sliding window |
Volume: | 39 |
Issue: | 6th International conference on Intelligent Human Computer Interaction, IHCI 2014 |
Page Number: | 4 |
First Page: | 162 |
Last Page: | 165 |
DDC classes: | 620 Ingenieurwissenschaften und Maschinenbau |
Open access?: | Ja |
Licence (German): | Creative Commons - Namensnennung, nicht kommerziell, keine Bearbeitung |