This article presents a method to know the position of object or moving robot in the plane while the camera is moving dynamically. An Inverse Perspective mapping (IPM) approach has been embedded in a monocular camera on Head of Pepper Humanoid Robot (Softbank Robotics) for real time position determination of other object or robot in plane. While the Pepper head is moving, it is difficult to determine position or distance to objects in front of the robot with any different degree of certainity. By applying IPM, a linear relationship between the IPM frame and world frame becomes the key element to know the position of object while the head is static but when the head orientation changes the IPM is modified to adapt the linear relationship between both frames. So, the proposed method is based on the extraction of accurate bird’s-eye view. The method includes the Image Acquistion, IPM Filtering, Detection Phase, Region of Interest Selection and Pixel remapping.

An Inverse Perspective Mapping Approach using Monocular Camera of Pepper Humanoid Robot to Determine the Position of Other Moving Robot in Plane

Muhammad Hassan Tanveer;Antonio Sgorbissa
2018-01-01

Abstract

This article presents a method to know the position of object or moving robot in the plane while the camera is moving dynamically. An Inverse Perspective mapping (IPM) approach has been embedded in a monocular camera on Head of Pepper Humanoid Robot (Softbank Robotics) for real time position determination of other object or robot in plane. While the Pepper head is moving, it is difficult to determine position or distance to objects in front of the robot with any different degree of certainity. By applying IPM, a linear relationship between the IPM frame and world frame becomes the key element to know the position of object while the head is static but when the head orientation changes the IPM is modified to adapt the linear relationship between both frames. So, the proposed method is based on the extraction of accurate bird’s-eye view. The method includes the Image Acquistion, IPM Filtering, Detection Phase, Region of Interest Selection and Pixel remapping.
File in questo prodotto:
File Dimensione Formato  
final_manuscript.pdf

accesso aperto

Tipologia: Documento in Post-print
Dimensione 876.82 kB
Formato Adobe PDF
876.82 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11567/918991
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact