An optimisation of Gaussian mixture models for integer processing units
- Submitting institution
-
Kingston University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11-34-1366
- Type
- D - Journal article
- DOI
-
10.1007/s11554-014-0402-5
- Title of journal
- Journal of Real-Time Image Processing
- Article number
- -
- First page
- 273
- Volume
- 13
- Issue
- -
- ISSN
- 1861-8200
- Open access status
- Out of scope for open access requirements
- Month of publication
- -
- Year of publication
- 2017
- 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
-
-
- Research group(s)
-
-
- Citation count
- 1
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Motion detection algorithms use float-point operations and may not be directly deployable on the low-cost and low-power processors that only support integer-based operations. This paper addresses this by offering an optimisation of Gaussian mixture models suitable for integer processing units. Such technique may be particularly significant in applications where a large number of low-cost low-power cameras are required and/or energy consumption must be low (e.g., when cameras are powered by a battery or a solar cell).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -