Pattern recognition methods as tools of restoration project in Maavesi water area

In this report we examine the usability of different computational image segmentation and recognition methods as a tool of water area restoration projects. An airborne, mosaic image of Maavesi water area in South-east Finland was measured in September 2000 with a three-channel camera covering parts from the spectrum in red, green and infra-red wavelengths. Image segmentation and recognition methods were then applied in purpose to recognise and localize the aquatic macrophyte plant communities into several groups or by species. Results were confirmed by a field study performed in September-October 2001. The main interest of image processing was to have data for design and monitoring of water plant biomass removal in near future.