Title :
A multiple detector approach to low-resolution FIR pedestrian recognition
Author :
Mählisch, Mirko ; Oberländer, Matthias ; Löhlein, Otto ; Gavrila, Dariu ; Ritter, Werner
Author_Institution :
Dept. REI/AI, DaimlerChrysler AG, Ulm, Germany
Abstract :
In this paper we present a recognition scheme, which is both reliable and fast. The scheme comprises the simultaneous harmonized use of three powerful detection algorithms, the hyper permutation network (HPN), a hierarchical contour matching (HCM) algorithm and a cascaded classifier approach. Each algorithm is evaluated separately and afterwards, based on the evaluation results, the fusion of the detection results is performed by a particle filter approach.
Keywords :
FIR filters; driver information systems; image matching; image resolution; object detection; road traffic; cascaded classifier approach; detection algorithm; hierarchical contour matching algorithm; hyper permutation network; low-resolution FIR pedestrian recognition; multiple detector approach; particle filter approach; Detection algorithms; Finite impulse response filter; Fusion power generation; Humans; Infrared detectors; Night vision; Object detection; Performance evaluation; Shape; Spatial resolution;
Conference_Titel :
Intelligent Vehicles Symposium, 2005. Proceedings. IEEE
Print_ISBN :
0-7803-8961-1
DOI :
10.1109/IVS.2005.1505123
