RGBD-Dog: Predicting Canine Pose from RGBD Sensors
- Submitting institution
-
The University of Bath
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 205404377
- Type
- E - Conference contribution
- DOI
-
10.1109/CVPR42600.2020.00836
- Title of conference / published proceedings
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- First page
- 8333
- Volume
- -
- Issue
- -
- ISSN
- 1063-6919
- Open access status
- Compliant
- Month of publication
- August
- Year of publication
- 2020
- 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
-
4
- Research group(s)
-
-
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- While research on automatic estimation of 3D human shape and body pose is common, there is very little comparable work for animals. The paper presents the first method to estimate canine 3D shape and body pose using a Kinect-style (RGBD) camera. It also describes and makes publicly available the first 3d shape and motion capture data set of canines – including multiple breeds. The novelty of our work and claims for ‘first of a kind’ are further quoted by authors in subsequent work [Biggs et al, ECCV 2020].
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -