Title :
A comparative study of pedestrian detection methods using classical Haar and HoG features versus bag of words model computed from Haar and HoG features
Author :
Brehar, Raluca ; Nedevschi, Sergiu
Author_Institution :
Comput. Sci. Dept., Tech. Univ. of Cluj-Napoca, Cluj-Napoca, Romania
Abstract :
The bag of words model has been actively adopted by content based image retrieval and image annotation techniques. We employ this model for the particular task of pedestrian detection in two dimensional images, producing this way a novel approach to pedestrian detection. The experiments we have done in this paper compare the behavior of discriminative recognition approaches that use AdaBoost on codebook features versus Adaboost trained on primitive features that may be extracted from a two dimensional image. By primitive features we refer in this paper to Haar features and Histogram of Oriented Gradients both being extremely used in object recognition in general and in pedestrian detection in particular. The conclusion of our experiments is that the codebook representation performs better than the primitive feature representation.
Keywords :
Haar transforms; content-based retrieval; feature extraction; image retrieval; learning (artificial intelligence); object recognition; traffic engineering computing; AdaBoost; bag of words model; classical Haar features; classical HoG features; codebook features; content based image retrieval; discriminative recognition approach; image annotation techniques; object recognition; oriented gradients; pedestrian detection methods; two dimensional image extraction; Computational modeling; Feature extraction; Histograms; Humans; Machine learning algorithms; Shape; Training;
Conference_Titel :
Intelligent Computer Communication and Processing (ICCP), 2011 IEEE International Conference on
Conference_Location :
Cluj-Napoca
Print_ISBN :
978-1-4577-1479-5
Electronic_ISBN :
978-1-4577-1481-8
DOI :
10.1109/ICCP.2011.6047884