DocumentCode :
524405
Title :
Detection by collaborative intrinsic images and vertical projection histogram integration
Author :
Dong, Yongxin ; Wang, Jingling ; Zhang, Qin
Author_Institution :
Dept. of Inf. Eng., Commun. Univ. of China, Beijing, China
Volume :
3
fYear :
2010
fDate :
22-24 June 2010
Abstract :
This paper detects image sequences using a method by collaborative vertical projection histogram and principal axis-based integration. Instead of the conventional detection method intrinsic images proposes the relation of background and foreground is multiplication, in log domain this relation becomes addition. In the multi-target image sequence, the method combined with vertical projection histogram can detect individuals from each other. Compared with the traditional background subtraction method and gaussian mixture model method,the experimental results verify the effectiveness and advantage of the method.
Keywords :
Gaussian processes; image sequences; object detection; Gaussian mixture model method; background subtraction method; collaborative intrinsic images; image detection; multitarget image sequence; principal axis-based integration; vertical projection histogram integration; Computer science education; Educational technology; Histograms; Image sequences; International collaboration; Layout; Lighting; Motion detection; Reflectivity; Target tracking; detection; intrinsic images; vertical projection histogram;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Education Technology and Computer (ICETC), 2010 2nd International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-6367-1
Type :
conf
DOI :
10.1109/ICETC.2010.5529584
Filename :
5529584
Link To Document :
بازگشت