Pedestrian target tracking of UAV platform based on improved TLD algorithm

Bin Zhou; Ali Jin; Yu Zhang; Yudi Zhang; Mingdong Zhao

doi:10.1117/12.2645945

23 January 2023 Pedestrian target tracking of UAV platform based on improved TLD algorithm

Bin Zhou, Ali Jin, Yu Zhang, Yudi Zhang, Mingdong Zhao

Proceedings Volume 12557, AOPC 2022: Optical Sensing, Imaging, and Display Technology; 125570B (2023) https://doi.org/10.1117/12.2645945
Event: Applied Optics and Photonics China 2022 (AOPC2022), 2022, Beijing, China

Abstract

Pedestrian target tracking based on the UAV platform can be widely used in traffic control, field search, and military reconnaissance. It is an important research task of computer vision and intelligent cruise. Aiming at the limitations of the UAV surveillance system in moving pedestrian target tracking, such as background change, pedestrian deformation, occlusion interference, and lack of real-time performance, the dual Kalman filter is used to improve the traditional TLD tracking algorithm, the proposed method can accelerate the correction of the predicted detection area, reduce the disturbance of the environment background and the target deformation to the pedestrian tracking accuracy, and reduce the detection time by using the adaptive adjustment method of the detection area to offset the time cost caused by double Kalman filtering, to improve the Algorithm’s real-time performance. The test results show that the proposed method has high accuracy, stability, and real-time performance in pedestrian target tracking based on the UAV platform.

Citation Download Citation

Bin Zhou, Ali Jin, Yu Zhang, Yudi Zhang, and Mingdong Zhao "Pedestrian target tracking of UAV platform based on improved TLD algorithm", Proc. SPIE 12557, AOPC 2022: Optical Sensing, Imaging, and Display Technology, 125570B (23 January 2023); https://doi.org/10.1117/12.2645945

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available