did=333 task=did=333 YACVID - UBC3V Dataset - Details

Yet Another Computer Vision Index To Datasets (YACVID) - Details

Stand: 2024-03-19 10:34:23 - Overview

ok - did=333 - task=task - dviews=1649
Attribute Current content New content
Name (Institute + Shorttitle)UBC3V Dataset 
Description (include details on usage, files and paper references)UBC3V is a synthetic dataset for training and evaluation of single or multiview depth-based pose estimation techniques. The nature of the data is similar to the data used in the famous Kinect paper of Shotton et al., but with a few distinctions:

* The dataset distinguishes the back-front and left-right sides of the body.
* The camera location is relatively unconstrained.
* The dataset has three randomly located cameras for each pose, which makes it suitable for multiview pose estimation settings.
* It is freely available to the public.

A. Shafaei, J. J. Little. Real-Time Human Motion Capture with Multiple Depth Cameras. in 13th Conference on Computer and Robot Vision, Victoria, Canada, 2016. 
URL Linkhttps://github.com/ashafaei/ubc3v 
Files (#)
References (SKIPPED)
Category (SKIPPED)multiview depth based pose estimation  
Tags (single words, spaced)depth segmentation pose 
Last Changed2024-03-19 
Turing (2.12+3.25=?) :-)