Transparency-Aware Segmentation of Glass Objects to Train RGB-Based Pose Estimators

Robotic manipulation requires object pose knowledge for the objects of interest. In order to perform typical household chores, a robot needs to be able to estimate 6D poses for objects such as water glasses or salad bowls. This is especially difficult for glass objects, as for these, depth data are...

Popoln opis

Bibliografske podrobnosti

Principais autores:	Maira Weidenbach, Tim Laue, Udo Frese
Format:	Artigo
Jezik:	Inglês
Izdano:	MDPI AG 2024-01-01
Serija:	Sensors
Teme:	neural networks training data transparent objects bounding box segmentation pose estimation
Online dostop:	https://www.mdpi.com/1424-8220/24/2/432
Oznake:	Označite Brez oznak, prvi označite!