Detection and Tracking of Vortices on Oceanographic Images

This paper deals with the problem of automatic interpretation of oceanographic images for vortices detection, modelization and tracking. We present a framework allowing the vortices detection. The processing is split into three parts: apparent motion computation from the image sequence, local interpretation of apparent motion and geometric modelization of the vortices. This scheme allows an efficient approach for vortices segmentation on very large image sequences. A set of experimental data shows the use of such framework for processing Advanced Very High Resolution Radiometer (AVHRR) and Coastal Zone Color Scanner (CZCS) image sequences

[1]  Ramesh C. Jain,et al.  Vector Field Analysis for Oriented Patterns , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Thomas S. Huang,et al.  Salient structure analysis of fluid flow , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Janet Aisbett,et al.  Optical Flow with an Intensity-Weighted Smoothing , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  B. G. Schunck The image flow constraint equation , 1986 .

[5]  Hans-Hellmut Nagel,et al.  An Investigation of Smoothness Constraints for the Estimation of Displacement Vector Fields from Image Sequences , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Robin N. Strickland,et al.  Nonlinear phase portrait models for oriented textures , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Bruce A. Thomas,et al.  Image Models for 2-D Flow Visualization and Compression , 1994, CVGIP Graph. Model. Image Process..

[8]  Solomon Lefschetz,et al.  Differential Equations: Geometric Theory , 1958 .