Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Robust person and object tracking in LWIR and VIS based on a new template matching method

: Müller, Thomas

Postprint urn:nbn:de:0011-n-3325391 (176 KByte PDF)
MD5 Fingerprint: 2361129321f93f6cb8ae33c517cdd5ba
Copyright Society of Photo-Optical Instrumentation Engineers. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.
Erstellt am: 31.3.2015

Sadjadi, Firooz A. (Ed.) ; Society of Photo-Optical Instrumentation Engineers -SPIE-, Bellingham/Wash.:
Automatic target recognition XXIV : 5 - 6 May 2014, Baltimore, Maryland, United States
Bellingham, WA: SPIE, 2014 (Proceedings of SPIE 9090)
ISBN: 978-1-628-41027-3
Paper 90900P, 14 S.
Conference "Automatic Target Recognition" <24, 2014, Baltimore/Md.>
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IOSB ()
object tracking; person tracking; Template Matching; cross correlation; normalized cross correlation; structural matching; thermal infrared; LWIR and MWIR image sequences; VIS image sequences; visual-optical and infrared image data; multi spectral surveillance

Template matching is one of the oldest techniques in computer vision. It has been applied in a variety of different applications using cross correlation as distance measurement or derivates of it. But so far, the success of object tracking is very limited despite the promising structural similarity search that is done thereby. Based on an analysis of the underlying reasons, a new kind of measurement is proposed therefore to open up far more of the potential the structural search inherently offers. This new measurement does not sum up differences in color space like the cross correlation but outputs the number of matching pixels in percent. As a key feature, local color variations are considered in order to properly handle the different character of homogeneous and highly structured regions and to model the relations between them. Furthermore, relevant differences between templates are expatiated and stressed while irrelevant contributions to the measurement function are widely suppressed in order to avoid unnecessary distortions on the measurement and, therefore, on the search decision. The presented results document the advantages in comparison to the measurements known from the literature. Different objects and persons in LWIR and VIS image sequences are tracked to illustrate the performance and the benefit in a broad field of applications.