Histogram of oriented principal components for cross-view action recognition
- Submitting institution
-
The University of Lancaster
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 249320819
- Type
- D - Journal article
- DOI
-
10.1109/TPAMI.2016.2533389
- Title of journal
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Article number
- -
- First page
- 2430
- Volume
- 38
- Issue
- 12
- ISSN
- 0162-8828
- Open access status
- Out of scope for open access requirements
- Month of publication
- February
- Year of publication
- 2016
- 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)
-
B - Data Science
- Citation count
- 66
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The paper proposes a novel solution to address the problem of view-invariant representation of 3D point cloud videos in human action recognition. It solves the difficulties caused by changes in camera viewpoints and action execution speed by identifying appropriate interest-points within a point cloud sequence. This paper is significant in showing for the first time that the detected interest points are reliable and repeatable irrespective of changes in viewpoint and action execution speed, and thus, results in a robust human activity recognition system. The work received follow-on funding from an Innovate UK project (£98K) with Digital Rail Ltd.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
