This paper considers the data association problem for multi-target tracking . Multiple hypothesis tracking is a popular algorithm for solving this problem . It is NP-hard and is is quite complicated for tracking a large number of targets or tracking maneuvering targets . To improve tracking performance and enhancerobustness, we propose a randomized multiple model multiple hypothesis tracking method . It yields a randomized data association solution which maximizes the expectation of the logarithm of the posterior probability . The probability that the target follows a specific dynamicmodel is derived by jointly optimizing the multiple possible models and dataassociation hypotheses, and it does not require prior mode transitionprobabilities . Simulations demonstrate the efficiency and superior results of the algorithm over interacting multiple modelMultiple model multiple hypothesistracking. It is more robust for tracking multiple maneuveringtargets.

Author(s) : Haiqi Liu, Xiaojing Shen, Zhiguo Wang, Fanqin Meng, Junfeng Wang, Pramod, Varshney

Links : PDF - Abstract

Code :
Coursera

Keywords : multiple - tracking - randomized - hypothesis - model -

Leave a Reply

Your email address will not be published. Required fields are marked *