Title :
Statistical method for motion detection in an image sequence
Author :
Guetari, Skander ; Devars, Jean
Author_Institution :
Paris VI Univ., France
Abstract :
This paper presents a new statistical method based on the theory of large numbers for detection of objects in motion in a sequence of images. The method, relying on the occurrence of images as a function of time, combines a grey-level background construction and a discussion of the gradients calculated on the current image by comparison with a reference image
Keywords :
image sequences; motion estimation; number theory; statistical analysis; gradients; grey-level background construction; image sequence; large numbers theory; motion detection; reference image; statistical method; Cameras; Content addressable storage; Cows; Fluctuations; Image segmentation; Layout;
Conference_Titel :
Electrical and Computer Engineering, 1995. Canadian Conference on
Conference_Location :
Montreal, Que.
Print_ISBN :
0-7803-2766-7
DOI :
10.1109/CCECE.1995.526407
