Knowledge-Based Segmentation for Remote-Sensing

In order to cope with the large volume of remotely-sensed data available now and expected in the future, efficient automatic processing techniques are required. A particular problem in automatic interpretation of this data is the identification of relevant connected regions in the image, i.e. segmentation. This can generally only be achieved to a required degree of accuracy if performed manually. This paper describes the current implementation of a system for automatic segmentation of multi-tempora l remotely-sensed images which exploits prior knowledge to isolate the regions of interest. The system is directed principally towards the applications of crop and environmental monitoring.