Title :
Statistical modeling of video object´s behavior for improved object tracking in visual surveillance
Author :
Yin, Guo Qing ; Bruckner, Dietmar ; Zucker, Gerhard
Author_Institution :
Inst. of Comput. Technol., Vienna Univ. of Technol., Vienna, Austria
Abstract :
This paper describes a post processing method for detected video objects to enhance the quality of detection. Starting with a basic set of video parameters (such as video frame and time, label of objects, the objects position in pixel, the width and height of object\´s bounding box) statistical parameters (such as arithmetic mean and standard deviation) about features are computed and with these parameters different statistical models are built. These models can be used to estimate the "normality" of an object\´s behavior.
Keywords :
image resolution; object detection; statistical analysis; video signal processing; video surveillance; object tracking; statistical modeling; video object behavior; video object detection; visual surveillance; Arithmetic; Data analysis; Data security; Europe; Object detection; Probability; Random variables; Surveillance; System testing; Unsupervised learning;
Conference_Titel :
AFRICON, 2009. AFRICON '09.
Conference_Location :
Nairobi
Print_ISBN :
978-1-4244-3918-8
Electronic_ISBN :
978-1-4244-3919-5
DOI :
10.1109/AFRCON.2009.5308178
