Title :
Detecting motion in out-of-register pictures
Author_Institution :
Dept. of Comput. Sci., Cornell Univ., Ithaca, NY, USA
Abstract :
A novel technique is described that can be applied to a sequence of pictures to detect moving objects and segment them from the stationary background. It does not require the pictures to be in-register, and is suitable for cases where the camera moves while the pictures are taken. Its greatest advantage is the simplicity and efficiency in which it can be implemented. By the use of fast Fourier transforms, the detection of moving objects in a pair of pictures takes about the same computation time as a simple convolution between two pictures of the same size (three Fourier transforms)
Keywords :
fast Fourier transforms; pattern recognition; picture processing; convolution; fast Fourier transforms; motion detection; moving object detection; out-of-register pictures; picture processing; picture sequences; Cameras; Computer science; Fourier transforms; Frequency domain analysis; Layout; Motion detection; Object detection; Registers; TV; Tracking;
Conference_Titel :
Computer Vision and Pattern Recognition, 1988. Proceedings CVPR '88., Computer Society Conference on
Conference_Location :
Ann Arbor, MI
Print_ISBN :
0-8186-0862-5
DOI :
10.1109/CVPR.1988.196310