Estimating the 3D center point of an object with Kinect sensor RGB-D images

• Gustavo Fardo Armênio UTFPR
• João Alberto Fabro UTFPR
• Renzo De Rosa Tognella UTFPR
• Felipe Pierre Conter UNILA
• Marlon Vaz De Oliveira UTFPR / IFPR
• Everson De Souza Silva UTFPR

Resumo

This article describes the estimation of a 3D point using a Kinect sensor and the Robot Operating System (ROS) along with You Only Look Once (YOLO) for object detection. The Kinect sensor provides RGB-D images, which are used to create a Point Cloud representing the geometry of the environment. ROS is used as a robotics development framework, while YOLO is employed to identify objects in the scene. The article presents the packages used, the datasets used for measurement, and the configuration of ROS and YOLO. Additionally, the functionalities of RViz, a 3D visualization tool used in the tests, are explored. Furthermore, it covers the methods employed, the acquired data, and an analysis of the error margin in relation to the measurement of the distance between the Kinect and the object. The findings and techniques presented in this study contribute to addressing the challenges faced in the RoboCup@Home competition, specifically in the context of object manipulation tasks.

Palavras-chave: 3D point, object manipulation, object detection, Kinect sensor, ROS, point cloud