Biologically-Inspired Motion Encoding for Robust Global Motion Estimation
- Submitting institution
-
Queen Mary University of London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 469
- Type
- D - Journal article
- DOI
-
10.1109/TIP.2017.2651394
- Title of journal
- IEEE Transactions on Image Processing
- Article number
- -
- First page
- 1521
- Volume
- 26
- Issue
- 3
- ISSN
- 1057-7149
- Open access status
- Compliant
- Month of publication
- January
- 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
-
2
- Research group(s)
-
-
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The first biologically-inspired illumination invariant global motion estimator that emulates the behaviour of the lower layers of the visual cortex. The paper also provides a closed-form expressions for the Adelson-and-Bergen motion perception model for 2D motion (original model was analysed for 1D only). The model is used as part of the QM Baby Sensing Safety System funded by the EPSRC Innovation Fund (2016-2017), which led the company Summer Infant to donate hardware to support validation on a specific architecture in an assisted living application under real-world illumination conditions (Michael Fusco, VP Product Development, mfusco@summerinfant.com).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -