Latent regression forest : structured estimation of 3D hand poses
- Submitting institution
-
The University of Birmingham
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 48290332
- Type
- D - Journal article
- DOI
-
10.1109/TPAMI.2016.2599170
- Title of journal
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Article number
- -
- First page
- 1374
- Volume
- 39
- Issue
- 7
- ISSN
- 0162-8828
- Open access status
- Technical exception
- Month of publication
- August
- 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)
-
-
- Citation count
- 15
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper presents a novel framework for real-time 3D hand pose estimation from a depth image. This is significant because the framework improves both accuracy and efficiency drastically by combining structural information into the random forest. The framework has been widely applied to computer vision problems that require structured search, either spatially or temporally. A newly presented dataset is still considered one of the main datasets in this area and widely used and cited. The new framework is patented in USA (US9311713B2) and Korea (1017580640000). PhD students working on this paper have been snapped up by Microsoft Research and Twitter.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -