Abrupt motion tracking using a visual saliency embedded particle filter
- Submitting institution
-
The University of Essex
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1147
- Type
- D - Journal article
- DOI
-
10.1016/j.patcog.2013.11.028
- Title of journal
- Pattern Recognition
- Article number
- -
- First page
- 1826
- Volume
- 47
- Issue
- 5
- ISSN
- 0031-3203
- Open access status
- Out of scope for open access requirements
- Month of publication
- May
- Year of publication
- 2014
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
D - Robotics and Embedded Systems (RES)
- Citation count
- 46
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This highly-cited paper reported a novel abrupt motion tracking algorithm. Significantly, the work integrates the saliency model with a particle filter for recovering lost track, thereby greatly enhancing tracking robustness and performance for fast moving objects i.e. important for complex real-world scenarios. It provided both the novel computational method for the model and its corresponding tracking framework. Future applications are likely in autonomous vehicles and human motion tracking. The work has impacted several other areas including multi-camera surveillance networks (Waleed Ejaz, Queen's University, Canada) and multi-object tracking in videos of sports (Isabelle Bloch, LTCI France).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -