Title :
A New Approach for Real-Time Detection of Abandoned and Stolen Objects
Author :
Wang, Weihua ; Liu, Zhijing
Author_Institution :
Sch. of Comput. Sci. & Technol., Xidian Univ., Xi´´an, China
Abstract :
In this paper a new approach aimed at automatic identify events of abandoned and stolen objects detection in video surveillance system is described. Our method mainly includes three steps of data processing: the first processing phrase is object extraction, involving a background subtraction algorithm which dynamically updates two sets of background. Then, extracted objects are classified as static or dynamic objects. Finally, a decision-making model is employed to calculate a confidence score for the classification about event, and an alarm will be automatically triggered if the score of corresponding action is higher than a pre-defined threshold. Also, the robustness and efficiency of the method is tested on our real-time video surveillance system and evaluated by public database such as AVSS 2007 datasets.
Keywords :
alarm systems; decision making; feature extraction; object detection; pattern classification; video surveillance; automatically triggered alarm; background subtraction algorithm; data processing; decision making model; dynamic object; object extraction; predefined threshold; public database; real time detection; static object; stolen object; video surveillance system; Cameras; Histograms; Image color analysis; Object detection; Pixel; Video surveillance; background subtraction; decision-making model; object classification; real-time; video surveillance;
Conference_Titel :
Electrical and Control Engineering (ICECE), 2010 International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-6880-5
DOI :
10.1109/iCECE.2010.40
