Title :
A new adaptive background updating method for motion detection
Author :
Chen, Mei ; Xu, X.L.
Author_Institution :
Sch. of Inf. Sci. & Eng., Fujian Univ. of Technol., Fuzhou, China
Abstract :
This paper makes improvements on motion detection method which uses background updating, specifically: using adaptive threshold. The D value is introduced to the iterative method calculating adaptive threshold value in order to obtain a more suitable one. In our experiment, the D value has some relationship with the region in which the gray scale occur most often. The D value is adjusted with the region. The background model is established by using the statistical average method. The current background is updating to prevent the background model from degradation. The median filter method is adopted to eliminate the noise. The experimental results show that the improved methods have significantly solved the problems of miss detection of slow movement targets and background model degradation.
Keywords :
image denoising; image motion analysis; iterative methods; median filters; object detection; statistical analysis; D value; adaptive background updating method; adaptive threshold value; gray scale; iterative method; median filter method; motion detection method; noise elimination; slow movement target miss detection; statistical average method; adaptive threshold; background subtraction; background updating; target detection;
Conference_Titel :
Information Science and Control Engineering 2012 (ICISCE 2012), IET International Conference on
Conference_Location :
Shenzhen
Electronic_ISBN :
978-1-84919-641-3
DOI :
10.1049/cp.2012.2477