On parameterizing higher-order motion for behaviour recognition
- Submitting institution
-
University of Southampton
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 68651189
- Type
- D - Journal article
- DOI
-
10.1016/j.patcog.2020.107710
- Title of journal
- Pattern Recognition
- Article number
- 107710
- First page
- 1
- Volume
- 112
- Issue
- -
- ISSN
- 0031-3203
- Open access status
- Compliant
- Month of publication
- October
- Year of publication
- 2020
- 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
-
2
- Research group(s)
-
-
- Citation count
- 0
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This is the first computer vision paper to investigate higher orders of motion such as acceleration, concerning the use of acceleration and jerk in video sequences and its application in behaviour recognition. This paper builds upon our previous journal paper (http://dx.doi.org/10.1049/iet-cvi.2017.0429) and our ICDP conference paper (https://bit.ly/3goly6h), which pioneered approaches to detecting heel strikes using our acceleration features. Acceleration features for the first time ever in the 4th Edition of the highly-cited computer-vision textbook on Feature Extraction (https://amzn.to/3brb0R7 pp214-215). The conception of this work was described in keynotes on gait biometrics at CCBR 2016 (https://bit.ly/38mRaEG) and at AVSS (https://bit.ly/2UEUbMu).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
