Real-time object pose recognition and tracking with an imprecisely calibrated moving RGB-D camera

K. Pauwels, V. Ivan, E. Ros, S. Vijayakumar

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We introduce a real-time system for recognizing and tracking the position and orientation of a large number of complex real-world objects, together with an articulated robotic manipulator operating upon them. The proposed system is fast, accurate and reliable and yet does not require precise camera calibration. The key to this high level of performance is a continuously-refined internal 3D representation of all the relevant scene elements. Occlusions are handled implicitly in this approach and a soft-constraint mechanism is used to obtain the highest precision at a specific region-of-interest. The system is well-suited for implementation on Graphics Processing Units and thanks to a tight integration of the latter's graphical and computational capability, scene updates can be obtained at framerates exceeding 40 Hz. We demonstrate the robustness and accuracy of this system on a complex real-world manipulation task involving active endpoint closed-loop visual servo control in the presence of both camera and target object motion.
Original languageEnglish
Title of host publicationIntelligent Robots and Systems (IROS 2014), 2014 IEEE/RSJ International Conference on
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages2733-2740
Number of pages8
DOIs
Publication statusPublished - 1 Sep 2014

Keywords

  • graphics processing units
  • image sensors
  • manipulators
  • object recognition
  • object tracking
  • pose estimation
  • real-time systems
  • robot vision
  • RGB-D camera
  • articulated robotic manipulator
  • camera object motion
  • computational capability
  • graphical capability
  • position tracking
  • precise camera calibration
  • real-time object pose recognition
  • real-time object pose tracking
  • real-time system
  • soft constraint mechanism
  • target object motion
  • Cameras
  • Robot vision systems
  • Solid modeling
  • Three-dimensional displays
  • Tracking

Fingerprint

Dive into the research topics of 'Real-time object pose recognition and tracking with an imprecisely calibrated moving RGB-D camera'. Together they form a unique fingerprint.

Cite this