Robotica · 2021 · 12 citations · 27 references
ComputingAutonomous SystemsComputer ScienceAutonomous VehiclesComputer VisionUnderwater RoboticsAutonomous Underwater VehiclesMarine Robot ControlUnderwater Vehicle DesignVisual TrackingAutonomous Underwater Vehicle ControlFuzzy ControlIntelligent ControlParticle Swarm ControlParticle Swarm OptimizationTarget TrackingUnderwater Target TrackingUnderwater Vehicle Control
SUMMARY 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 correlation filter (KCF) tracker and a novel fuzzy controller. The model is trained to learn an online correlation filter 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.
27
Visual object tracking using adaptive correlation filters
D.S. Bolme, J. Ross Beveridge, Bruce A. Draper et al. · 2010 · 3.3K citations
Struck: Structured output tracking with kernels
Sam Hare, Amir Saffari, Philip H. S. Torr · 2011 · 1.8K citations
Visual Tracking with Fully Convolutional Networks
Lijun Wang, Wanli Ouyang, Xiaogang Wang et al. · 2015 · 1K citations