Researchers at the University of Pisa, Istituto Italiano di Tecnologia, Alpen-Adria-Universitat Klagenfurt, and TU Delft recently developed a new taxonomy to label videos of humans manipulating objects. The taxonomy was explicitly designed for enabling the labeling of human grasping videos.
The new taxonomy incorporates movements before the grasping of objects, for bi-manual grasps, and non-prehensile strategies. In addition, the researchers used this taxonomy to create a labeled dataset containing videos of humans performing daily activities that involve object manipulation. In the future, this labeled dataset could be used to train both existing and new algorithms on image recognition, robotic grasping, and robotic manipulation tasks. In addition, the taxonomy could help to compile other datasets and label other videos of humans manipulating objects.
Click here to read the original article published by Tech Xplore.
Please give your feedback on this article or share a similar story for publishing by clicking here.
