24 May 2013 Fast car/human classification methods in the computer vision tasks
Author Affiliations +
Abstract
In this paper we propose a method for classification of moving objects of “human” and “car” types in computer vision systems using statistical hypotheses and integration of the results using two different decision rules. FAR-FRR graphs for all criteria and the decision rule are plotted. Confusion matrix for both ways of integration is presented. The example of the method application to the public video databases is provided. Ways of accuracy improvement are proposed.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Boris V. Vishnyakov, Boris V. Vishnyakov, Ivan K. Malin, Ivan K. Malin, Yuri V. Vizilter, Yuri V. Vizilter, Shih-Chia Huang, Shih-Chia Huang, Sy-Yen Kuo, Sy-Yen Kuo, } "Fast car/human classification methods in the computer vision tasks", Proc. SPIE 8791, Videometrics, Range Imaging, and Applications XII; and Automated Visual Inspection, 87911L (24 May 2013); doi: 10.1117/12.2020149; https://doi.org/10.1117/12.2020149
PROCEEDINGS
10 PAGES


SHARE
RELATED CONTENT

Visual surveillance in maritime port facilities
Proceedings of SPIE (March 24 2008)
Mining tools for surveillance video
Proceedings of SPIE (December 17 2003)
Shadow detection using 2D cepstrum
Proceedings of SPIE (May 04 2009)
Automated video surveillance: teaching an old dog new tricks
Proceedings of SPIE (December 16 1993)

Back to Top