Title :
Beacon Tracking with an Embedded Omni-vision System
Author :
Fu, Huazhu ; Cao, Zuoliang ; Röning, Juha
Author_Institution :
Sch. of Mech. Eng., Tianjin Univ. of Technol., Tianjin, China
Abstract :
This paper presents an embedded omni-vision navigation system which involves beacon tracking and vehicle localization. A new tracking algorithm, the Feature Matching Embedded Particle Filter, is proposed. A global localization method for omni-vision based on coordinate transformation is also proposed. The Digital Signal Processor (DSP) provides a hardware platform for an on-board tracker. Our dynamic navigator employs the DSP tracker to follow landmarks in real time during the arbitrary movement of the vehicle and computes its position for localization based on time sequence images analysis. Experimental results demonstrated that the navigation system can efficiently offer the vehicle guidance.
Keywords :
digital signal processing chips; embedded systems; navigation; real-time systems; tracking; vehicles; arbitrary movement vehicle; beacon tracking; digital signal processor; dynamic navigator; embedded omni vision system; feature matching embedded particle filter; global localization method; hardware platform; onboard tracker; real time landmarks; time sequence images analysis; vehicle guidance; vehicle localization; Digital signal processing; Digital signal processors; Lenses; Mechanical engineering; Monte Carlo methods; Navigation; Particle filters; Particle tracking; Signal processing algorithms; Vehicles; Particle Filter; embedded; multi-object tracking;
Conference_Titel :
Natural Computation, 2009. ICNC '09. Fifth International Conference on
Conference_Location :
Tianjin
Print_ISBN :
978-0-7695-3736-8
DOI :
10.1109/ICNC.2009.296
