Title :
Ensemble of classifiers for pedestrian recognition
Author :
Gáspár-Papanek, Csaba ; Kardkovács, Zsolt T.
Author_Institution :
Dept. of Telecommun. & Media Inf., Budapest Univ. of Technol. & Econ., Budapest, Hungary
Abstract :
Pedestrian recognition is one of the most important aspects of intelligent vehicle systems of the future. The challenge of this task lies in the difficulty of defining the pedestrian in terms of image processing. The article describes a data mining based decision system that solves a subtask of this complex problem: our solution is able to predict whether there is a pedestrian in the image from DaimlerChrysler Automative Dataset or not.
Keywords :
data mining; image classification; object recognition; DaimlerChrysler Automative Dataset; classifier ensemble; data mining; decision system; image processing; intelligent vehicle system; pedestrian recognition; Accuracy; Biological neural networks; Data mining; Data models; Image edge detection; Training;
Conference_Titel :
Cognitive Infocommunications (CogInfoCom), 2011 2nd International Conference on
Conference_Location :
Budapest
Print_ISBN :
978-1-4577-1806-9
Electronic_ISBN :
978-963-8111-78-4
