Aerial infrared target tracking method based on KCF for frequency-domain scale estimation

This paper addresses the problem of controlling a rotary wing Unmanned Aerial Vehicle (UAV) tracking a target moving on ground. The target tracking problem by UAVs has received much attention recently and several techniques have been developed in literature most of which have been applied to fixed wing aircrafts. The use of quadrotor UAVs, the subject of this paper, for target tracking presents several challenges especially for highly maneuvering targets since the development of time-optimal controller (required if target is maneuvering fast) for quadrotor UAVs is extremely difficult due to highly non-linear dynamics. The primary contribution of this paper is the development of a proportional navigation (PN) based method and its implementation on quad-rotor UAVs to track moving ground target. The PN techniques are known to be time-optimal in nature and have been used in literature for developing guidance systems for missiles. There are several types of guidance laws that come within the broad umbrella of the PN method. The paper compares the performance of these guidance laws for their application on quadrotors and chooses the one that performs the best. Furthermore, to apply this method for target tracking instead of the traditional objective of target interception, a switching strategy has also been designed. The method has been compared with respect to the commonly used Proportional Derivative (PD) method for target tracking. The experiments and numerical simulations performed using maneuvering targets show that the proposed tracking method not only carries out effective tracking but also results into smaller oscillations and errors when compared to the widely used PD tracking method.

Download Full-text

An Improved Trace Method for Moving Target under Occlusion

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.672-674.1931 ◽

2014 ◽

Vol 672-674 ◽

pp. 1931-1934

Author(s):

Yu Bing Dong ◽

Guang Liang Cheng ◽

Ming Jing Li

Keyword(s):

Mathematical Model ◽

Target Tracking ◽

Difficult Problem ◽

Block Matching ◽

Experimental Results ◽

Polar Coordinates ◽

Moving Target ◽

Trajectory Prediction ◽

Tracking Method

Occlusion is a difficult problem to be solved in the process of target tracking. In order to solve the problem of occlusion, a new tracking method combined with trajectory prediction and multi-block matching is presented and studied,and a mathematical model of trajectory prediction of moving target is established in polar coordinates and verified through some experiments. The experimental results show that the new tracking method can be better to trace and forecast the moving target under occlusion.

Download Full-text

Non-linear Maneuvering Target Tracking Method Using PIP

Journal of Korean institute of intelligent systems ◽

10.5391/jkiis.2007.17.1.136 ◽

2007 ◽

Vol 17 (1) ◽

pp. 136-142

Author(s):

Hyun-Seung Son ◽

Jin-Bae Park ◽

Young-Hoon Joo

Keyword(s):

Target Tracking ◽

Maneuvering Target Tracking ◽

Tracking Method ◽

Maneuvering Target ◽

Non Linear

Download Full-text

Research on Underwater Target Tracking Based on Contour Detection

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.317-319.890 ◽

2011 ◽

Vol 317-319 ◽

pp. 890-896

Author(s):

Ming Jun Zhang ◽

Yuan Yuan Wan ◽

Zhen Zhong Chu

Keyword(s):

Prediction Model ◽

Target Tracking ◽

Tracking System ◽

Contour Detection ◽

Motion Prediction ◽

Moving Target ◽

Contour Extraction ◽

Tracking Accuracy ◽

Tracking Method ◽

Underwater Target

The traditional centroid tracking method over-relies on the accuracy of segment, which easily lead to loss of underwater moving target. This paper presents an object tracking method based on circular contour extraction, combining region feature and contour feature. Through the correction to circle features, the problem of multiple solutions causing by Hough transform circle detection is avoided. A new motion prediction model is constructed to make up the deficiency that three-order motion prediction model has disadvantage of high dimension and large calculation. The predicted position of object centroid is updated and corrected by circle contour, forming prediction-measurement-updating closed-loop target tracking system. To reduce system processing time, on the premise of the tracking accuracy, a dynamic detection method based on target state prediction model is proposed. The results of contour extraction and underwater moving target experiments demonstrate the effectiveness of the proposed method.

Download Full-text

Feature Fusion Video Target Tracking Method Based on Convolutional Neural Network

Laser & Optoelectronics Progress ◽

10.3788/lop57.041502 ◽

2020 ◽

Vol 57 (4) ◽

pp. 041502

Author(s):

刘美菊 Liu Meiju ◽

曹永战 Cao Yongzhan ◽

朱树云 Zhu Shuyun ◽

杨尚奎 Yang Shangkui

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Target Tracking ◽

Feature Fusion ◽

Tracking Method ◽

Video Target Tracking

Download Full-text