Online Training of Object Detectors from Unlabeled Surveillance Video
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.
Cite
Text
Celik et al. "Online Training of Object Detectors from Unlabeled Surveillance Video." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2008. doi:10.1109/CVPRW.2008.4563067Markdown
[Celik et al. "Online Training of Object Detectors from Unlabeled Surveillance Video." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2008.](https://mlanthology.org/cvprw/2008/celik2008cvprw-online/) doi:10.1109/CVPRW.2008.4563067BibTeX
@inproceedings{celik2008cvprw-online,
title = {{Online Training of Object Detectors from Unlabeled Surveillance Video}},
author = {Celik, Hasan and Hanjalic, Alan and Hendriks, Emile A. and Boughorbel, Sabri},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2008},
pages = {1-7},
doi = {10.1109/CVPRW.2008.4563067},
url = {https://mlanthology.org/cvprw/2008/celik2008cvprw-online/}
}