SciELO - Scientific Electronic Library Online

 issue50Dissimilarity-based classification for stochastic models of embedding spaces applied to voice pathology detectionAnalytical model of wheel-rail contact force due to the passage of a railway vehicle on a curved track author indexsubject indexarticles search
Home Pagealphabetic serial listing  

Services on Demand



Related links

  • On index processCited by Google
  • Have no similar articlesSimilars in SciELO
  • On index processSimilars in Google


Revista Facultad de Ingeniería Universidad de Antioquia

Print version ISSN 0120-6230
On-line version ISSN 2357-53280


CATUCHE, Juan; STERLING, Julio  and  BACCA-CORTES, Bladimir. Tracking of ground-trajectories and target using an airship and artificial vision. Antioquia [online]. 2009, n.50, pp.122-134. ISSN 0120-6230.

This paper presents a robotic autonomous system composed by an indoors airship, a wireless video system, a PC and a tracking software for ground trajectory and high contrasted target tracking. The airship’s model has been simplified in order to get its lineal model, with which we defined the control objectives as relative heading and distance between the airship and groundtargets. A PD control strategy has been designed as airship’s heading as distance to goals, reaching a stabilization time of 5s and a overshoot of 5%. The video camera is the only feedback sensor; its images are processed for: trajectory segmentation using the Hough transform, Canny operator and a median filter; and ground-target segmentation, using color detection in the HIS space. Lineal, curved and lineal-curved combination trajectories tests were performed, reaching heading errors less than ±14o and distance of ±5pixels. Ground-targets tracking tests were performed, describing lineal and curved trajectories and reaching distance errors of ±39pixels, which corresponds to 8,33% image’s dimensions and orientation along goals’ heading of ±12o.

Keywords : Mobile robotics; blimp; artificial vision; trajectory tracking; target tracking.

        · abstract in Spanish     · text in Spanish     · Spanish ( pdf )


Creative Commons License All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License