An Image Segmentation Process Enhancement for Land Cover Mapping from Very High Resolution Remote Sensing Data Application in a Rural Area

In this chapter, we describe a procedure for enhancing the automatic image segmentation for land cover mapping from Very High Resolution images. The increased need for large scale mapping (1:10000) for local territorial monitoring led to think about mapping production. Nowadays mapping production for land cover and land use (LUC) is mainly performed with human photo-interpretation. This approach can be extremely time consuming, expensive and tedious for data producers. This is confirmed from the evidence of rural areas where the use of the GIS database for LUC is less numerous than the GIS urban database. In the last decade, Geographic Object-Based Image Analysis (GEOBIA) has been developed by the image processing community. This new paradigm builds on theory, methods and tools for replicating the human photo-interpretation process from remote sensing data (Hay and Castilla 2008). However, the GEOBIA community is still fragile and suffers from a lack of protocols and standards for operational LUC mapping applications. Currently, human photo-interpretation seems a safer option. The objective of this research is to find an alternative to this time consuming and expensive use of human expertise. We explored the limits of GEOBIA to propose an automatic image segmentation enhancement for an operational mapping application. Questions behind this study were: What is a good segmentation? How can we obtain it?