Intruder detection for automated access control systems with Kinect device

Author

Minar, Jiri ; Riha, Kamil ; Hejun Tong

Author_Institution

Dept. of Telecommun., Brno Univ. of Technol., Brno, Czech Republic

fYear

2013

fDate

2-4 July 2013

Firstpage

826

Lastpage

829

Abstract

The article deals with the problems of automated access control systems known as tailgating and piggybacking. This article focuses on detection of an unauthorized person, who is passing through a secure door after or with an authorized person. For this detection Kinect device and camera are used. The detection method is based on multilevel-thresholding of input image and subsequent analysis of objects´ shape in each level. Detection algorithm focuses on path tracking of persons in video sequences correct evaluation of tailgating or piggybacking.

Keywords

authorisation; cameras; image segmentation; image sequences; object detection; object tracking; Kinect device; automated access control systems; camera; intruder detection; multilevel image thresholding; path tracking; piggybacking; tailgating; unauthorized person detection; video sequences; Access control; Buffer storage; Cameras; Detection algorithms; Sensors; Video sequences; Automated Access Control System; Kinect; Object Tracking; Piggybacking; Tailgating; Thresholding;

fLanguage

English

Publisher

ieee

Conference_Titel

Telecommunications and Signal Processing (TSP), 2013 36th International Conference on

Conference_Location

Rome

Print_ISBN

978-1-4799-0402-0

Type

conf

DOI

10.1109/TSP.2013.6614054

Filename

6614054