An Extended Kalman Filter Based Object Tracking Algorithm for Autonomous Guided Truck Using 1-Layer Laser Scanner

2018 ◽  
Author(s):  
Kwangseok Oh ◽  
Taejun Song ◽  
Hyewon Lee
Keyword(s):  
Mathematical Model ◽  
Performance Evaluation ◽  
Kalman Filter ◽  
Object Tracking ◽  
Extended Kalman Filter ◽  
Laser Scanner ◽  
Tracking Algorithm ◽  
Optimal Controller ◽  
Linear Quadratic ◽  
Point Data

This paper describes an extended Kalman filter based object tracking algorithm for autonomous guided truck using 1-layer laser scanner. The 1-layer laser scanner has been used to obtain 2D cloud point data to detect the preceding object for tracking control. The object tracking algorithm proposed in this study consists of perception, decision, and control stages. In the perception stage, object’s information such as relative coordinate and yaw angle has been derived based on coordinate transformation, clustering, and state estimation algorithm using the obtained point data from laser scanner. In order to estimate object’s states such as coordinate and velocity, the extended Kalman filter has been used in this study. Based on the estimated states of the object, the desired path has been derived for calculation of steering angle. The simplified mathematical model of the truck has been derived to design optimal controller. The optimal controller designed in this study is based on the linear quadratic regulator for computing the optimal angle of steering module used for tracking. In order for reasonable performance evaluation, actual data from laser scanner and the derived mathematical model of truck have been used. The developed tracking algorithm and performance evaluation have been designed and conducted on Matlab/Simulink environment. Results of the performance evaluation show that the developed object tracking algorithm has been able to track the preceding object using 1-layer laser scanner.

scholarly journals Object tracking algorithm for unmanned surface vehicle based on improved mean-shift method

2020 ◽  
Vol 17 (3) ◽  
pp. 172988142092529
Author(s):  
Zuquan Xiang ◽  
Tao Tao ◽  
Lifei Song ◽  
Zaopeng Dong ◽  
Yunsheng Mao ◽  
...  
Keyword(s):  
Kalman Filter ◽  
Extended Kalman Filter ◽  
Autonomous Navigation ◽  
Mean Shift ◽  
Tracking Algorithm ◽  
Similarity Function ◽  
Unmanned Surface Vehicle ◽  
Feature Map ◽  
Center Position ◽  
Self Organizing

The unmanned surface vehicle has the characteristics of high maneuverability and flexibility. Object detection and tracking skills are required to improve the ability of unmanned surface vehicle to avoid collisions and detect targets on the surface of the water. Mean-shift algorithm is a classic target tracking algorithm, but it may fail when pixel interference and occlusion occur. This article proposes a tracking algorithm for unmanned surface vehicle based on an improved mean-shift optimization algorithm. The method uses the self-organizing feature map spatial topology to reduce the interference of the background pixels on the target object and predicts the center position of the object when the target is heavily occluded according to the extended Kalman filter. First, a self-organizing feature map model is built to classify pixels in a rectangular frame and the background pixels are extracted. Then, the method optimizes the extended Kalman filter solution process to complete the prediction and correction of the target center position and introduces a similarity function to determine the target occlusion. Finally, numerical analyses based on a ship model sailing experiment are performed with the help of OpenCV library. The experimental results validated that the proposed method significantly reduces the cumulative error in the tracking process and effectively predicts the position of the target between continuous frames when temporary occlusion occurs. The research can be used for target detection and autonomous navigation of unmanned surface vehicle.

Sign in / Sign up

Export Citation Format

Share Document