The Effect of Pixel-Level Fusion on Object Tracking in Multi-Sensor Surveillance Video

Author

Cvejic, N. ; Nikolov, S.G. ; Knowles, H.D. ; Loza, A. ; Achim, A. ; Bull, D.R. ; Canagarajah, C.N.

Author_Institution

Univ. of Bristol, Bristol

fYear

2007

fDate

17-22 June 2007

Firstpage

1

Lastpage

7

Abstract

This paper investigates the impact of pixel-level fusion of videos from visible (VIZ) and infrared (IR) surveillance cameras on object tracking performance, as compared to tracking in single modality videos. Tracking has been accomplished by means of a particle filter which fuses a colour cue and the structural similarity measure (SSIM). The highest tracking accuracy has been obtained in IR sequences, whereas the VIZ video showed the worst tracking performance due to higher levels of clutter. However, metrics for fusion assessment clearly point towards the supremacy of the multiresolutional methods, especially Dual Tree-Complex Wavelet Transform method. Thus, a new, tracking-oriented metric is needed that is able to accurately assess how fusion affects the performance of the tracker.

Keywords

image resolution; image sequences; particle filtering (numerical methods); sensor fusion; video surveillance; wavelet transforms; IR sequences; dual tree-complex wavelet transform method; fusion assessment; infrared surveillance cameras; multisensor surveillance video; object tracking; particle filter; pixel-level fusion; single modality videos; structural similarity measure; tracking-oriented metric; visible surveillance cameras; Cameras; Filtering; Fuses; Histograms; Humans; Infrared surveillance; Optical fiber communication; Particle tracking; Target tracking; Video sequences;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on

Conference_Location

Minneapolis, MN

ISSN

1063-6919

Print_ISBN

1-4244-1179-3

Electronic_ISBN

1063-6919

Type

conf

DOI

10.1109/CVPR.2007.383433

Filename

4270431