Title :
Property protection system based on Omni-Directional Vision Sensors
Author :
Tang, Yiping ; Hu, Feihu ; Yang, Guanbao ; Lin, Bei
Author_Institution :
Coll. of Inf. Eng., Zhejiang Univ. of Technol., Hangzhou, China
Abstract :
In this paper, a surveillance system which provides the protection for property in public places is proposed. Firstly, aiming at the problem of small visual field, Omni-Directional Vision Sensors (ODVS) which has 360 degree and non-dead-angle view is used to capture panoramic images of scene. Secondly, two backgrounds are constructed for detecting a temporarily stationary object, which one is short-term and another is long-term. At last, find out the real thief among the people in the scene and capture the details of it.
Keywords :
computer vision; image sensors; object detection; video surveillance; computer vision; omni-directional vision sensors; property protection system; stolen objects detection; surveillance system; thief tracking; Adaptation model; Feature extraction; Image edge detection; Object detection; Pixel; Real time systems; Sensors; Gauss multimodal backgrounds; ODVS; computer vision; different frame rates; stolen objects detection; thief tracking;
Conference_Titel :
Image and Signal Processing (CISP), 2010 3rd International Congress on
Conference_Location :
Yantai
Print_ISBN :
978-1-4244-6513-2
DOI :
10.1109/CISP.2010.5648316
