Tracking of sea and air flows from sequential satellite images by the relaxation-contour method

Authors:
M. A. Morozov
Affiliations:
Institute of Automation and Control Processes, Far East Division, Russian Academy of Sciences, Vladivostok, Russia 690041
Venue:
Pattern Recognition and Image Analysis
Year:
2008

Citing 2
Cited 0

On the Detection of Dominant Points on Digital Curves

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Correlation-Relaxation-Labeling Framework for Computing Optical Flow - Template Matching from a New Perspective

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

A method for visualizing the dynamics of water and air masses in the form of velocity fields obtained from the time series of satellite images is proposed. The method is based on the contour approach to the selection of inhomogeneities to be traced (tracers). The main criterion for choosing a tracer is the shape of the contour (geometrical context). The procedure applied for the optimal tracer selection is based on the method of relaxation labeling. The efficiency of the proposed method is estimated by comparison with that of the traditional cross-correlation approach.