Fuzzy Analysis of Satellite Images to Find Phytoplankton Blooms
A knowledge-based approach to automatic classification of Coastal Zone Color Scanner (CZCS) images of the west Florida Shelf is described. The approach is utilized to monitor red tides and phytoplankton plumes, such as green river off the west Florida shelf. CZCS images are initially segmented by the un-supervised mrFCM algorithm, then a knowledge based system is applied to the centroid values of resultant clusters to label case I & case II waters, green river and red tide. Our knowledge base consists of a rule based system and an embedded Neural Network. Our results show, among 25 ground truth images, this system can correctly recognize all 15 images with green river and 10 images without. The system can correctly classify 75% of the pixels belonging to green river. A time series of red tide in 1978 is also successfully identified.
Was this content written or created while at USF?
Citation / Publisher Attribution
Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, v. 2, p. 1430-1435
Scholar Commons Citation
Zhang, Mingrui; Hall, Lawrence; Goldgof, Dmitry; and Muller-Karger, Frank E., "Fuzzy Analysis of Satellite Images to Find Phytoplankton Blooms" (1997). Marine Science Faculty Publications. 1183.