AUTOMATED MAPPING OF LAND COVER USING SEQUENCES OF AERIAL IMAGERY

摘要

A system has an aerial image database (816) containing sensor data (814) representing a plurality of aerial images of an area having multiple sub-areas. A processor (12) applies a classifier (822) to the sensor values to identify a label for each sub-area in each aerial image and to thereby generate an initial label sequence (824) for each sub-area. The processor (12) identifies a most likely land cover state (828) for each sub-area based on the initial label sequence 824, a confusion (matrix 806) and a transition matrix (832). For each sub-area, the processor stores the most likely land cover state sequence for the sub-area.