- Download 8
- File Size 180 KB
- File Count 1
- Create Date October 5, 2021
- Last Updated October 5, 2021
D2.3 Report and Multisensor based human tracking algorithm implemented - ABSTRACT
This document reports the advancements developed in the context of WP2, describing the work conducted and the achievements accomplished during EURECAT’s work on task T2.3 “Multi-sensor tracking of workers” and the completion of the standalone Sharework Module M#3 “Human tracking”.
The aim of WP2 is to deliver a knowledge base and develop robotic cognition. In particular, this knowledge base should contain accessible information regarding human and robot tasks, should contain tools for analysing the human-operator’s workspace to detect task-specific
objects, monitor human activity and predict human tasks’ evolution, while a primitive’s learning algorithm will provide the robot with the ability to learn from demonstrations.
During task T2.3, the problems associated with the development of a robust method for detecting workers and tracking their poses has been addressed. The focus has been set on developing a reliable 3D human pose detection (able to detect the 3D poses of all the workers present in the environment simultaneously using RGB-D cameras) and, afterwards, designing a robust multi-sensor fusion algorithm (able to correctly associate the human bodies detected by the different cameras, fuse the associated information and filter them).
We have integrated them to a particular ROS package with the respective nodes. Those can be easily integrated to the core system of Sharework.
All above contributions are detailed in dedicated sections of this document.