Online Unsupervised Learning Classification of Pedestrian and Vehicle for Video Surveillance. Issue 1 (1st January 2017)

• Record Type: Journal Article
• Authors: He, Yi; Sang, Nong; Gao, Changxin; Han, Jun
• Is Part Of: Chinese journal of electronics. Volume 26:Issue 1(2017)
• Page Start: 145
• Page End: 151
• Publication Date: 2017-01-01
• Subjects: Online learning -- Unsupervised -- Objects classification -- Video surveillance; feature extraction -- image classification -- image motion analysis -- pedestrians -- road vehicles -- support vector machines -- traffic engineering computing -- unsupervised learning -- video surveillance; online unsupervised learning classification -- video surveillance -- online label strategy -- morphological features -- temporal features -- online filtering procedure -- SVM classifier -- vehicle classifier -- pedestrian classifier -- pedestrian polymorphism -- vehicle diversity; Electronics -- Periodicals; Electronics -- China -- Periodicals; Electronics; China; Periodicals; 621.38105
• DOI: 10.1049/cje.2016.08.011
• Languages: English
• ISSNs: 1022-4653

Abstract

Abstract : This paper presents an online unsupervised learning classification of pedestrians and vehicles for video surveillance. Different from traditional methods depending on offline training, our method adopts the online label strategy based on temporal and morphological features, which saves time and labor to a large extent. It extract the moving objects with their features from the original video. An online filtering procedure is adopted to label the moving objects according to certain threshold of speed and area feature. The labeled objects are sent into a SVM classifier to generate the pedestrian & vehicle classifier. Experimental results illustrate that our unsupervised learning algorithm is adapted to polymorphism of the pedestrians and diversity of the vehicles with high classification accuracy.