16 September 1994 Parallel motion estimation using an annealed Hopfield neural network
Author Affiliations +
Proceedings Volume 2308, Visual Communications and Image Processing '94; (1994) https://doi.org/10.1117/12.186008
Event: Visual Communications and Image Processing '94, 1994, Chicago, IL, United States
Abstract
An annealed Hopfield neural network has been shown to solve an image segmentation problem and good image segmentation was successfully achieved. In this paper, a new motion estimation algorithm using an annealed Hopfield neural network is developed. Motion estimation process can simply be described as finding the corresponding pixels in the consecutive images. Optimization function Eme1 equals Eg to achieve this simple process is defined first. This optimization function finds the motion vector for a given pixel in a frame by finding a corresponding pixel in the next frame. However, the image sequence usually contains the noise. In this case, only finding the corresponding pixels does not work well in estimating the correct vector field. To make the motion vectors smooth within a moving object and to make the motion vectors different between the objects moving in different directions, weak continuity constraints terms, Eme2 equals Ed + Es + Ep, are added to the previously defined optimization function Eme1, resulting in Eme equals Eme1 + Eme2. Eme2 controls the smoothness of the detected motion vectors within objects as well as maintains the motion vector boundaries between the objects moving to the different directions. Simulation are done for the synthetic image sequence and the real image sequence.
© (1994) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yungsik Kim, Yungsik Kim, } "Parallel motion estimation using an annealed Hopfield neural network", Proc. SPIE 2308, Visual Communications and Image Processing '94, (16 September 1994); doi: 10.1117/12.186008; https://doi.org/10.1117/12.186008
PROCEEDINGS
11 PAGES


SHARE
Back to Top