ROS wrapper for real-time multi-person pose estimation with a single camera

For robots to be deployable in human occupied environments, the robots must have human-awareness and generate human-aware behaviors and policies. OpenPose is a library for real-time multi-person keypoint detection. We have considered the implementation of a ROS package that would allow the estimatio...

Descripción completa

Detalles Bibliográficos
Autores: Arduengo García, Miguel, Jorgensen, Steven Jens, Hambuchen, Kimberly, Sentis, Luis, Moreno-Noguer, Francesc, Alenyà Ribas, Guillem|||0000-0002-6018-154X
Tipo de recurso: informe técnico
Fecha de publicación:2017
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/110929
Acceso en línea:https://hdl.handle.net/2117/110929
Access Level:acceso abierto
Palabra clave:robots
Classificació INSPEC::Automation::Robots
Àrees temàtiques de la UPC::Informàtica::Robòtica
Descripción
Sumario:For robots to be deployable in human occupied environments, the robots must have human-awareness and generate human-aware behaviors and policies. OpenPose is a library for real-time multi-person keypoint detection. We have considered the implementation of a ROS package that would allow the estimation of 2d pose from simple RGB images, for which we have introduced a ROS wrapper that automatically recovers the pose of several people from a single camera using OpenPose. Additionally, a ROS node to obtain 3d pose estimation from the initial 2d pose estimation when a depth image is synchronized with the RGB image (RGB-D image, such as with a Kinect camera) has been developed. This aim is attained projecting the 2d pose estimation onto the point-cloud of the depth image.