Visual tracking is an essential building block for target tracking and capture of the underwater vehicles. On the basis of remotely autonomous control architecture, this paper has proposed an improved kernelized corre...
详细信息
Visual tracking is an essential building block for target tracking and capture of the underwater vehicles. On the basis of remotely autonomous control architecture, this paper has proposed an improved kernelizedcorrelationfilter (KCF) tracker and a novel fuzzy controller. The model is trained to learn an online correlationfilter from a plenty of positive and negative training samples. In order to overcome the influence from occlusion, the improved KCF tracker has been designed with an added self-discrimination mechanism based on system confidence uncertainty. The novel fuzzy logic tracking controller can automatically generate and optimize fuzzy rules. Through Q-learning algorithm, the fuzzy rules are acquired through the estimating value of each state action pairs. An S surface based fitness function has been designed for the improvement of learning based particle swarm optimization. Tank and channel experiments have been carried out to verify the proposed tracker and controller through pipe tracking and target grasp on the basis of designed open frame underwater vehicle.
暂无评论