DocumentCode :
2611488
Title :
Active Learning Based Pedestrian Detection in Real Scenes
Author :
Yang, Tao ; Jing Li ; Quan Pan ; Zhao, Chunhui ; Zhu, Yiqiang
Author_Institution :
Coll. of Autom. Control, Northwestern Polytech. Univ., Xi´´an
Volume :
4
fYear :
0
fDate :
0-0 0
Firstpage :
904
Lastpage :
907
Abstract :
This work presents an active learning based method for pedestrian detection in complicated real-world scenes. Through analyzing the distribution of all positive and negative samples under every possible feature, a highly efficient weak classifier selection method is presented. Moreover, a novel boosting architecture is given to get satisfied false positive rate (FPR) and false negative rate (FNR) with few weak classifiers. A unique characteristic of the algorithm is its ability to train special cascade classifier dynamically for each individual scene. The benefit is that the trained classifier will only focus on the differences between the positive samples and the limited negative samples of each individual scene, thus greatly reduce the complexity of classification and achieve robust detection result even with few classifiers. A real-time pedestrian detection system is developed based on the proposed algorithm. The system produces fast and robust detection results as demonstrated by extensive experiments which use video sequences under different environments
Keywords :
image classification; image sequences; learning (artificial intelligence); object detection; surveillance; video signal processing; active learning; boosting architecture; cascade classifier; false negative rate; false positive rate; image classification; pedestrian detection; video sequences; video surveillance; weak classifier selection; Automatic control; Boosting; Detectors; Educational institutions; Face detection; Layout; Object detection; Real time systems; Robustness; Underwater tracking;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition, 2006. ICPR 2006. 18th International Conference on
Conference_Location :
Hong Kong
ISSN :
1051-4651
Print_ISBN :
0-7695-2521-0
Type :
conf
DOI :
10.1109/ICPR.2006.208
Filename :
1699986
Link To Document :
بازگشت