Pose Determination and Tracking for Autonomous Satellite Capture

Download
  1. (PDF, 715 KB)
AuthorSearch for: ; Search for: ; Search for:
TypeArticle
ConferenceThe 6th International Symposium on Artificial Intelligence, Robotics and Automation in Space, June 2001., Montréal, Québec, Canada
Subjectvision system; satellite proximity operations; motion estimation; pose estimation; tracking
AbstractThis paper presents a concept and initial results of testing a vision system for satellite proximity operations. The system uses natural features on the satellite surfaces and does not require any artificial markers or targets for its operation. The system computes motion of unknown objects, and using object models computes their positions and orientations (pose), and tracks them in images sequences. The system processes images from stereo cameras to compute 3D data. Motion of an unknown object is computed using projective vision. Initial pose of the object is acquired using an approach based on Geometric Probing. The pose is tracked using a fast version of an Iterative Closest Point algorithm. Selected modules of the system have been characterised in a representative environment; the other are undergoing systematic sets of experiments.
Publication date
LanguageEnglish
AffiliationNRC Institute for Information Technology; National Research Council Canada
Peer reviewedNo
NRC number45869
NPARC number5763623
Export citationExport as RIS
Report a correctionReport a correction
Record identifier3ead5120-108d-431b-aee4-5ea825583651
Record created2009-03-29
Record modified2016-05-09
Bookmark and share
  • Share this page with Facebook (Opens in a new window)
  • Share this page with Twitter (Opens in a new window)
  • Share this page with Google+ (Opens in a new window)
  • Share this page with Delicious (Opens in a new window)