Title :
Online training of object detectors from unlabeled surveillance video
Author :
Celik, Hasan ; Hanjalic, Alan ; Hendriks, Emile A. ; Boughorbel, Sabri
Author_Institution :
Delft Univ. of Technol., Delft
Abstract :
One of the decisive steps in automated surveillance and monitoring is object detection. A standard approach to constructing object detectors consists of annotating large data sets and using them to train a detector. Nevertheless, due to unavoidable constraints of a typical training data set, supervised approaches are inappropriate for building generic systems applicable to a wide diversity of camera setups and scenes. To make a step towards a more generic solution, we propose in this paper a method capable of learning and detecting, in an online and unsupervised setup, the dominant object class in a general scene. The effectiveness of our method is experimentally demonstrated on four representative video sequences.
Keywords :
image sequences; learning (artificial intelligence); monitoring; object detection; video signal processing; video surveillance; automated monitoring video; automated surveillance video; object detectors; training data set; unlabeled surveillance video; video sequences; Boosting; Buildings; Cameras; Computerized monitoring; Detectors; Layout; Object detection; Surveillance; Training data; Video sequences;
Conference_Titel :
Computer Vision and Pattern Recognition Workshops, 2008. CVPRW '08. IEEE Computer Society Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
978-1-4244-2339-2
Electronic_ISBN :
2160-7508
DOI :
10.1109/CVPRW.2008.4563067