Title :
Extraction of motion from spatio-temporal image using the 3-dimensional Hough transform
Author :
Iida, Hidenobu ; Hwang, Junghyun ; Ozawa, Shinji
Author_Institution :
Dept. of Electr. Eng., Keio Univ., Yokohama, Japan
Abstract :
A method which extracts the speed and direction of several moving objects in a spatio-temporal image using the 3-D Hough transform is described. The estimation of target feature parameters, such as velocity, is based on the contour matching technique. In practice, the solution to this problem is reliable on the assumption of little noise and occlusion in the image. Hence, the 3-D Hough transform is an effective method for the extraction of the global pattern features from the noise and scattered points spread over the image space. Therefore, the method is used for extracting the velocity of the moving objects in the image sequence
Keywords :
Hough transforms; feature extraction; image sequences; motion estimation; parameter estimation; 3-D Hough transform; contour matching technique; moving object velocity extraction; noise; scattered points; spatio-temporal image; target feature parameters; Image analysis; Image segmentation; Image sequence analysis; Image sequences; Layout; Motion analysis; Noise shaping; Object detection; Scattering; Shape;
Conference_Titel :
Communications, Computers and Signal Processing, 1993., IEEE Pacific Rim Conference on
Conference_Location :
Victoria, BC
Print_ISBN :
0-7803-0971-5
DOI :
10.1109/PACRIM.1993.407194