Abstract
Aiming at the target missing and the target confusion in the multi-target tracking when the targets approach or cross each other in wireless sensor networks, a rough and precision association mixing FCM algorithm is proposed. The key idea is to implement the multi-target precise tracking by decomposing multi-sensor data association problem to single sensor problem and simplifying the multitarget tracking to single-target tracking. First, some interference of the observed data from the sensors was eliminated by rough correlation based on the threshold algorithm. Then the remaining data were fuzzy clustered through respectively establish FCM algorithm in each sensor observation space. Every clustered data were integrated into one datum by optimal linear fusion and was used to forecasteach target state by Kalman filter. The simulation results show that the correct association rate of track increases to 98.3%from 86.7% compare with traditional method. The proposed algorithm can also effectively avoid multi-target tracking confusion and greatly reduce the complexity and computation of multi-target tracking in WSN.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.