Publication

Database for 3D human pose estimation from single depth images

Technical Report (2016)

IRI code

IRI-TR-16-05

File

Download the digital copy of the doc pdf document

Abstract

This work is part of the project I-­‐DRESS (Assistive interactive robotic system for support in dressing). The specific objective is the detection of human body postures and the tracking of their movements. To this end, this work aims to create the image database needed for the training of the algorithms of pose estimation for the artificial vision of the robotic system, based on the depth images obtained by a sensor Time-­‐of-­‐Flight (ToF) depth camera type, such as the incorporated by the Kinect One (Kinect v2) device.

Categories

image recognition, object detection.

Scientific reference

M. Arduengo, G. Alenyà and F. Moreno-Noguer. Database for 3D human pose estimation from single depth images. Technical Report IRI-TR-16-05, Institut de Robòtica i Informàtica Industrial, CSIC-UPC, 2016.