ABSTRACT
This chapter introduces what we call patch-based classification for land cover mapping. This task consists of classifying image patches of fixed size, and attributing the estimated class to the central pixel of the patch to produce a land cover map. This kind of approach is suitable when the available data is sparsely annotated: the only requirement is the location of patches of which the class is known. Typically, examples of terrain truth allowing this approach can be GPS coordinates associated with land cover class, or manually annotated polygons in GIS, etc. This approach involves deep networks that input a patch of image, and produce a single value that represents the class of this patch: hence training this kind of network requires only input image patches, and associated class values. Once the training of a network is done, producing land cover maps consists of applying the model on each patch of a remote sensing image, and storing the value of the estimated class in the output image. The advantage of this kind of approach is its suitability to sparsely annotated datasets. Its implementation subtleties and limitations will be discussed in this chapter.
