DocumentCode
1657411
Title
Adaptive threshold shadow detection based on image block statistics
Author
Xu, Liang ; Zhang, Liang ; Han, Ping ; Wu, Ren-biao
Author_Institution
Tianjin Key Lab. for Adv. Signal Process., Civil Aviation Univ. of China, Tianjin
fYear
2008
Firstpage
1372
Lastpage
1375
Abstract
In this paper, based on the mixed Gaussian modeling and segmentation of moving objects and shadow, we propose an adaptive threshold shadow detection method based on image block statistics. The experiments of the video sequences with the different light and environmental conditions show that the method can remove the shadow of the moving target very well, and it also can choose the threshold adaptively.
Keywords
Gaussian processes; image motion analysis; image segmentation; image sequences; object detection; statistical analysis; video signal processing; adaptive threshold shadow detection; image block statistics; mixed Gaussian modeling; moving object segmentation; video sequence; Adaptive signal detection; Adaptive signal processing; Gaussian distribution; Image edge detection; Image segmentation; Object detection; Statistics; Target tracking; Vehicle detection; Video signal processing;
fLanguage
English
Publisher
ieee
Conference_Titel
Signal Processing, 2008. ICSP 2008. 9th International Conference on
Conference_Location
Beijing
Print_ISBN
978-1-4244-2178-7
Electronic_ISBN
978-1-4244-2179-4
Type
conf
DOI
10.1109/ICOSP.2008.4697387
Filename
4697387
Link To Document