Real time motion estimation using a neural architecture implemented on GPUs
- Submitting institution
-
The University of Westminster
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 98q64
- Type
- D - Journal article
- DOI
-
10.1007/s11554-014-0417-y
- Title of journal
- Real-Time Image Processing
- Article number
- -
- First page
- 731
- Volume
- 11
- Issue
- 4
- ISSN
- 1861-8200
- Open access status
- Compliant
- Month of publication
- March
- 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
-
5
- Research group(s)
-
-
- Citation count
- 4
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The significance of this paper is the parallelisation of the growing neural gas (GNG) algorithm onto graphical card units (GPUs) in order to obtain an acceleration that is particularly important to the design of real-time systems used in computer vision applications (e.g., surveillance of corridors). Experiments were conducted on datasets obtained from INRIA Labs and results were tested on NVIDIA hardware. The method has been included in the workflow of a company in Spain that designs surveillance systems for big campsites such as the Marjal resorts (contact: D. José Luis Albentosa, Director General, CETEL SISTEMAS S.L).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
