Trainable classifier-fusion schemes: An application to pedestrian detection

Author

Ludwig, Oswaldo ; Delgado, David ; Gonçalves, Valter ; Nunes, Urbano

Author_Institution

Dept. of Electr. & Comput. Eng., Univ. of Coimbra, Coimbra, Portugal

fYear

2009

fDate

4-7 Oct. 2009

Firstpage

1

Lastpage

6

Abstract

This work proposes a novel classifier-fusion scheme using learning algorithms, i.e. syntactic models, instead of the usual Bayesian or heuristic rules. Moreover, this paper complements the previous comparative studies on DaimlerChrysler Automotive Dataset, offering a set of complementary experiments using feature extractor and classifier combinations. The experimental results provide evidence of the effectiveness of our methods regarding false positive rate, AUC, and accuracy, which reached 96.67%.

Keywords

feature extraction; image classification; learning (artificial intelligence); traffic engineering computing; DaimlerChrysler automotive dataset; feature extractor; heuristic rules; learning algorithm; pedestrian detection; syntactic model; trainable classifier-fusion scheme; Automotive engineering; Bagging; Bayesian methods; Boosting; Covariance matrix; Feature extraction; Histograms; Intelligent robots; Intelligent transportation systems; Neural networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Transportation Systems, 2009. ITSC '09. 12th International IEEE Conference on

Conference_Location

St. Louis, MO

Print_ISBN

978-1-4244-5519-5

Electronic_ISBN

978-1-4244-5520-1

Type

conf

DOI

10.1109/ITSC.2009.5309700

Filename

5309700