Posterior Probability Based Multi-classifier Fusion in Pedestrian Detection

This paper presents a novel method for pedestrian detection at measurement level. At feature extraction stage, we use Histogram of Oriented Gradient to describe the feature of pedestrian and non-pedestrian. To decrease the time cost, we reduce the dimension by using PCA. The base classifiers used in posterior probability based multi-classifier fusion are posterior probability based SVM, Naive Bayesian and Minimum Distance Classifier, respectively. To estimate the accuracy of fusion result, stratified cross-validation is used. Experimental results on pedestrian databases prove the efficiency of this work.

[1]  Anil K. Jain,et al.  Statistical Pattern Recognition: A Review , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Anil K. Jain,et al.  A Principled Approach to Score Level Fusion in Multimodal Biometric Systems , 2005, AVBPA.

[3]  Subhash C. Bagui,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2005, Technometrics.

[4]  Jon Atli Benediktsson,et al.  Multiple Classifier Systems , 2015, Lecture Notes in Computer Science.

[5]  Christopher J. C. Burges,et al.  A Tutorial on Support Vector Machines for Pattern Recognition , 1998, Data Mining and Knowledge Discovery.

[6]  Keung-Chi Ng,et al.  Consensus diagnosis: a simulation study , 1992, IEEE Trans. Syst. Man Cybern..

[7]  Mohamed A. Deriche,et al.  A New Technique for Combining Multiple Classifiers using The Dempster-Shafer Theory of Evidence , 2002, J. Artif. Intell. Res..

[8]  Hua Huang,et al.  Pedestrian Detection Using Boosted HOG Features , 2008, 2008 11th International IEEE Conference on Intelligent Transportation Systems.

[9]  James C. Bezdek,et al.  Decision templates for multiple classifier fusion: an experimental comparison , 2001, Pattern Recognit..

[10]  John Platt,et al.  Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods , 1999 .

[11]  Ignacio Parra,et al.  Combination of Feature Extraction Methods for SVM Pedestrian Detection , 2007, IEEE Transactions on Intelligent Transportation Systems.

[12]  Dariu Gavrila,et al.  An Experimental Study on Pedestrian Classification , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Ludmila I. Kuncheva,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2004 .

[14]  Robert P. W. Duin,et al.  The combining classifier: to train or not to train? , 2002, Object recognition supported by user interaction for service robots.

[15]  Dariu Gavrila,et al.  Multi-cue Pedestrian Detection and Tracking from a Moving Vehicle , 2007, International Journal of Computer Vision.

[16]  Angel D. Sappa,et al.  Adaptive Image Sampling and Windows Classification for On-board Pedestrian Detection , 2007 .

[17]  Adam Krzyżak,et al.  Methods of combining multiple classifiers and their applications to handwriting recognition , 1992, IEEE Trans. Syst. Man Cybern..

[18]  Sargur N. Srihari,et al.  A theory of classifier combination: the neural network approach , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[19]  Robert P. W. Duin,et al.  Experiments with Classifier Combining Rules , 2000, Multiple Classifier Systems.

[20]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).