3D object localisation with 2D CNN object detector and 2D odometry
[ 1 ] Instytut Robotyki i Inteligencji Maszynowej, Wydział Automatyki, Robotyki i Elektrotechniki, Politechnika Poznańska | [ D ] phd student | [ P ] employee
[2.2] Automation, electronics, electrical engineering and space technology
2022
chapter in monograph / paper
english
- object detection
- pose estimation
- mapping
EN In this paper, we deal with the problem of objects detection and 3D position estimation by a mobile-manipulating robot equipped with an RGB-D camera and 2D laser scanner. Instead of estimating 3D position from a single image using CNN, we propose an application of CNN-based 2D object detection and gradient-based optimization that allows estimating 3D object poses from a sequence of images and robot poses obtained from an on-board 2D localization system.
90 - 93
CC BY (attribution alone)
publisher's website
final published version
at the time of publication
20