Comparing Visual Data Fusion Techniques Using FIR and Visible Light Sensors to Improve Pedestrian Detection

Author

Thomanek, Jan ; Ritter, Marc ; Lietz, Holger ; Wanielik, Gerd

Author_Institution

Ingenieurgesellschaft Auto und Verkehr GmbH, Berlin, Germany

fYear

2011

fDate

6-8 Dec. 2011

Firstpage

119

Lastpage

125

Abstract

Pedestrian detection is an important field in computer vision with applications in surveillance, robotics and driver assistance systems. The quality of such systems can be improved by the simultaneous use of different sensors. This paper proposes three different fusion techniques to combine the advantages of two vision sensors -- a far-infrared (FIR) and a visible light camera. Different fusion methods taken from various levels of information representation are briefly described and finally compared regarding the results of the pedestrian classification.

Keywords

FIR filters; cameras; computer vision; driver information systems; image classification; image representation; image sensors; pedestrians; sensor fusion; FIR; computer vision; driver assistance system; far-infrared sensor; information representation; pedestrian classification; pedestrian detection; visible light camera; visible light sensor; vision sensor; visual data fusion technique; Cameras; Feature extraction; Finite impulse response filter; Image sensors; Sensor fusion; Vectors; Classification; Data Fusion; Image Processing; Pedestrian Detection;

fLanguage

English

Publisher

ieee

Conference_Titel

Digital Image Computing Techniques and Applications (DICTA), 2011 International Conference on

Conference_Location

Noosa, QLD

Print_ISBN

978-1-4577-2006-2

Type

conf

DOI

10.1109/DICTA.2011.27

Filename

6128669