A multiple object tracking and detection algorithm using PMHT and FCM

Wen-jun Shi; Shang-qing Shi; Deng-wei Wang

doi:10.1117/12.828533

30 October 2009 A multiple object tracking and detection algorithm using PMHT and FCM

Wen-jun Shi, Shang-qing Shi, Deng-wei Wang

Proceedings Volume 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis; 74950H (2009) https://doi.org/10.1117/12.828533
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China

Abstract

An efficient algorithm based on PMHT and FCM is presented to track and detect the infrared multiple targets from the sequences of IR. Candidate targets can be obtained and saved by preprocessing IR data, and the true target can be detected from the above candidate targets through tracking those targets by PMHT algorithm and prior knowledge. Data association and target detection can be realized by FCM. At the same time, target' disappearing and new targets' emerging phenomena occasionally arise during target tracking. This problem can be solved by 'memorizing and filling'. The proposed approach is validated using actual infrared image sequences. Experiment results indicate high performance of the proposed method.

Citation Download Citation

Wen-jun Shi, Shang-qing Shi, and Deng-wei Wang "A multiple object tracking and detection algorithm using PMHT and FCM", Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 74950H (30 October 2009); https://doi.org/10.1117/12.828533

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