This contribution presents a method to segmentate video scenes hierachically into different moving objects and subobjects using a 2 -dimensiona1 description of these scenes. Therefore information from single images as well as information from successive images is used to spit up a scene into different objects. Furthermore each of these objects is characterized by a transform h(x, T) which is implicitely describing the surface and the three-dimensional motion of the moving objects in the scene. Using this description an object oriented prediction of the image contents from one image to the next as it may be used in low bitrate image coding is possible.
Segmentation and motion estimation in image sequences
Sensing and Reconstruction of Three-Dimensional Objects and Scenes ; 1990 ; Santa Clara,CA,United States
Proc. SPIE ; 1260
1990-01-01
Conference paper
Electronic Resource
English
Object-oriented motion estimation and segmentation in image sequences
Automotive engineering | 1991
|Motion estimation on infrared image sequences
SPIE | 1999
|British Library Conference Proceedings | 1994
|Feature Guided Pixel Matching and Segmentation in Motion Image Sequences
British Library Conference Proceedings | 1995
|Motion estimation in image sequences for traffic applications
Tema Archive | 2000
|