Title :
Pareto-Front Analysis and AdaBoost for Person Detection Using Heterogeneous Features
Author :
Mekonnen, A.A. ; Lerasle, Frederic ; Herbulot, A.
Author_Institution :
LAAS, France Univ. de Toulouse, Toulouse, France
Abstract :
In this paper, a boosted cascade person detection framework with heterogeneous pool of features is presented. The framework unveils a new feature selection scheme based on Pareto-Front analysis and AdaBoost. At each cascade node, Pareto-Front analysis is used to select dominant features thereby reducing the total number of features to a size easily manageable by AdaBoost. The final detector achieves a very low Miss Rate of 0.07 at 10-4 False Positives Per Window on the INRIA public dataset.
Keywords :
Pareto analysis; feature extraction; learning (artificial intelligence); object detection; AdaBoost; INRIA public dataset; Pareto-front analysis; boosted cascade person detection framework; cascade node; dominant feature selection; feature selection scheme; heterogeneous features; Boosting; Decision trees; Detectors; Feature extraction; Histograms; Support vector machines; Training; Ad-aBoost; Feature Selection; Pareto-Front Analysis; Pattern Recognition; Person Detection;
Conference_Titel :
Systems, Man, and Cybernetics (SMC), 2013 IEEE International Conference on
Conference_Location :
Manchester
DOI :
10.1109/SMC.2013.736
