Research project T4/DD/07 (Research action T4)
The project aims to improve techniques of remote sensing image processing for land cover mapping and their integration into a geographic information system. The quality and the updating of these inventories are to be the basis of a sustainable and efficient land management.
The project is motivated by the absence of an effective tool capable of processing the spatial information of remote sensing images and of using ancillary data structured into a geographic information system during the land cover interpretation. From then on, operational programmes of land cover cartography and inventory are essentially based on visual interpretation techniques. The use of land cover data into a geographic information system requires efficient stocking of the expertise acquired during the interpretation as well as on all information on its reliability. The updating of these data, soon necessary, will not be feasible in an effective manner unless the expertise acquired during the interpretation is used again. In addition, new sensors will allow in a near future to map land cover at scales lower than 1:25 000, and therefore to detail current inventories.
From then on, it is proposed to develop a method and a software improving the recognition and the interpretation of land cover, coupled with a geographic information system, in order to improve the use of spatial information and ancillary data during the interpretation of multi-sensors and multi-sources data, to preserve classification rules and their accuracy into a geographic information system, and to stock the expertise resulting from the interpretation in order to use it again (updating of more detailed inventory on a larger scale).
The project is proposed for a first two years phase:
The first phase corresponds to the adaptation and to the validation of a classification software by a decision tree (already applied for the interpretation of pigmented cutaneous lesion images) for the land cover interpretation from remote sensing and ancillary data structured in a multi-sensors and multi-sources geographic information system. This method has the advantage of providing explicit classification rules and being adaptable according to the evolution of techniques. This software would be coupled with a geographic information system in order to stock the results of interpretation, the accumulated expertise, and the resulting classification rules.
If the first phase proves to be successful, a second phase would consist in the re-utilisation of this expertise in order to update a land cover inventory (recent high resolution data and RADAR data), to detail a land cover inventory at a larger scale, and to re-establish land cover changes over a period of 25 years.
At the end of the first phase, the main product is a software of assistance to the land cover recognition and interpretation from remote sensing data, coupled with a geographic information system, under the form of a demonstrator, portable on PC, interactive, evolutive, explicit (classification rules), cumulative (accumulation of the expertise) and adaptive (to new data).
This software will be developed by a trans-sectorial team associating geographers and engineers. The project will be guided by preferential relationships with an expected end-user implied in the inventory, the monitoring and the mapping of land cover: the European Topic Center CORINE Land Cover.
