@inproceedings {pub3825,
	title = {Real-Time 3D Pose Estimation from Single Depth Images
},
	author = {Thomas Schn{\"u}rer AND Stefan Fuchs AND Horst-Michael Gro{\ss}},
	year = {2019},
	month = {February},
	abstract = {To allow for safe Human-Robot-Interaction in industrial scenarios like construction plants, it is essential to
always be aware of the location and pose of humans in the shared workspace. We introduce a real-time 3D
pose estimation system using single depth images that is aimed to run on limited hardware, like, e.g. , a
mobile robot. For this, we optimize a CNN-based 2D pose estimation architecture to achieve high frame
rates while simultaneously requiring fewer resources. Building upon this architecture, we extended the system
for 3D estimation to directly predict Cartesian body joint coordinates. We evaluate our system on a newly
created dataset by applying it to a specific industrial workbench scenario. The results show that our system{\textquoteright}s
performance is competitive to the state of the art at more than five times the speed for single person pose
estimation.},
	publisher = {SCITEPRESS},
	booktitle = {14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications}
}