Improved sum-of-squared-differences tracking algorithm for thermal vision systems

Grzegorz Bieszczad; Tomasz Sosnowski; Henryk Madura

doi:10.1117/12.900540

8 September 2011 Improved sum-of-squared-differences tracking algorithm for thermal vision systems

Grzegorz Bieszczad, Tomasz Sosnowski, Henryk Madura

Proceedings Volume 8193, International Symposium on Photoelectronic Detection and Imaging 2011: Advances in Infrared Imaging and Applications; 81932R (2011) https://doi.org/10.1117/12.900540
Event: International Symposium on Photoelectronic Detection and Imaging 2011, 2011, Beijing, China

Abstract

A modification of Sum-of-Squared-Differences algorithm is proposed to improve tracking efficiency of small objects in infra-red image sequences. The reason to use SSD algorithm is its better performance in tracking small objects, than in model based tracking algorithms. However traditional Sum-of-Squared-Differences (SSD) algorithm is sensitive to partial or full occlusions, background clutter and changes in object appearance. To increase immunity to this kind of noises the modification in model update procedure was developed. The experimental results illustrate that the proposed modification to SSD algorithm can improve overall algorithm performance in infrared operation. The paper describes the Sum-of-Squared Differences algorithm and its principal features in tracking objects on thermal image sequences. Next modification to SSD algorithm is described. Finally the experimental results are presented with comparison between traditional and modified SSD algorithm.

Citation Download Citation

Grzegorz Bieszczad, Tomasz Sosnowski, and Henryk Madura "Improved sum-of-squared-differences tracking algorithm for thermal vision systems", Proc. SPIE 8193, International Symposium on Photoelectronic Detection and Imaging 2011: Advances in Infrared Imaging and Applications, 81932R (8 September 2011); https://doi.org/10.1117/12.900540

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