Spectral-360: A Physics-Based Technique for Change Detection
- Submitting institution
-
University of East London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 28
- Type
- E - Conference contribution
- DOI
-
10.1109/CVPRW.2014.65
- Title of conference / published proceedings
- 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops
- First page
- 405
- Volume
- -
- Issue
- -
- ISSN
- 2160-7516
- Open access status
- Out of scope for open access requirements
- Month of publication
- June
- Year of publication
- 2014
- 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)
-
1 - Intelligent Systems
- Citation count
- 25
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work addressed the issue of illumination variation in change detection algorithms, which has prohibited the practical use of such algorithms in real life applications. This challenge was addressed through the use of a physics-based approach to model the spectral reflectance of surfaces. This novel technique was patented US8983134B2 [1] and rated amongst the top four best algorithms by IEEE Change Detection Workshop 2014 (click CDW-14 top menu, http://www.changedetection.net/). Six IEEE Transaction papers used Spectral-360 amongst state-of-the-art benchmarking algorithms. For example, DOI:10.1109/TIP.2017.2695882 (Table II Second best in three parameters) and DOI:10.1016/j.cosrev.2018.01.004 (best reflectance approach for intensity features).
[1] https://patents.google.com/patent/US9047677B2
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -