Title :
A hierarchical method for detection of moving objects
Author :
Xiong, Wei ; Graffigne, Christine
Author_Institution :
Univ. de Paris-Sud, Orsay, France
Abstract :
This paper deals with segmentation and estimation of motion for two successive images in a sequence whatever the camera situation is (static or mobile). A hierarchical method is described. The model energy is composed of two main parts, one is defined at pixel scale, and the other one on regions. These two terms are optimized alternatively
Keywords :
Markov processes; hierarchical systems; image segmentation; image sequences; motion estimation; object detection; Markov random field; hierarchical method; image regions; image segmentation; image sequence; model energy; motion estimation; moving object detection; pixel scale; Cameras; Convergence; Image segmentation; Lattices; Markov random fields; Motion estimation; Object detection; Optimization methods; Paramagnetic resonance; Relaxation methods;
Conference_Titel :
Image Processing, 1994. Proceedings. ICIP-94., IEEE International Conference
Conference_Location :
Austin, TX
Print_ISBN :
0-8186-6952-7
DOI :
10.1109/ICIP.1994.413680
