Title :
HOG and color based adaboost pedestrian detection
Author :
Qing Liu ; Yongyu Qu
Author_Institution :
Sch. of Autom., Wuhan Univ. of Technol., Wuhan, China
Abstract :
Pedestrian detection is one of the most important research areas in intelligent video surveillance. How to detect the pedestrian fast and accurately is the main target. This research is based on the feature extraction method proposed in paper. aiming at its defect in speed, we introduce the boosted cascade method to train the classifier, realize the Gentle Adaboost using linear SVM. We only need 3 hours to finish the training procedure, this method not only improves the detection accuracy, it also boosts the detection speed greatly. Our test on INRIA shows the effectiveness of the method.
Keywords :
feature extraction; object detection; pattern classification; support vector machines; traffic engineering computing; video surveillance; HOG; boosted cascade method; classifier; color based Adaboost pedestrian detection; feature extraction; gentle Adaboost; intelligent video surveillance; linear SVM; Boosting; Classification algorithms; Educational institutions; Feature extraction; Machine learning algorithms; Support vector machines; Training; boosted cascade; gentle adaboost; pedestrian detection;
Conference_Titel :
Natural Computation (ICNC), 2011 Seventh International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-9950-2
DOI :
10.1109/ICNC.2011.6022084
