An Iterative Inference Procedure Applying Conditional Random Fields for Simultaneous Classification of Land Cover and Land Use

Abstract

ABSTRACT:Land cover and land use exhibit strong contextual dependencies. We propose a novel approach for the simultaneous classification of land cover and land use, where semantic and spatial context is considered. The image sites for land cover and land use classification form a hierarchy consisting of two layers: a land cover layer and a land use layer. We apply Conditional Random Fields (CRF) at both layers. The layers differ with respect to the image entities corresponding to the nodes, the employed features and the classes to be distinguished. In the land cover layer, the nodes represent super-pixels; in the land use layer, the nodes correspond to objects from a geospatial database. Both CRFs model spatial dependencies between neighbouring image sites. The complex semantic relations between land cover and land use are integrated in the classification process by using contextual features. We propose a new iterative inference procedure for the simultaneous classification of land cover and land use, in which the two classification tasks mutually influence each other. This helps to improve the classification accuracy for certain classes. The main idea of this approach is that semantic context helps to refine the class predictions, which, in turn, leads to more expressive context information. Thus, potentially wrong decisions can be reversed at later stages. The approach is designed for input data based on aerial images. Experiments are carried out on a test site to evaluate the performance of the proposed method. We show the effectiveness of the iterative inference procedure and demonstrate that a smaller size of the super-pixels has a positive influence on the classification result.

Contextual Land Use Classification: How Detailed Can the Class Structure Be?

“…For classifying land cover and land use, we apply the contextual classification method presented (Albert et al, 2015), where a detailed description of the approach can be found. The approach performs a simultaneous classification of land cover and land use while considering semantic as well as spatial context.…”

“…In (Albert et al, 2014) we presented a two-step land use classification approach which was extended to include an iterative inference procedure in (Albert et al, 2015). In both approaches, CRFs are applied separately for land cover and land use classification.…”

“…A detailed description of the features can be found in (Albert et al, 2015). These features incorporate statistical parameters (e.g.…”

“…Both CRFs apply an explicit model of spatial dependencies between neighbouring sites, i.e. pixels (Albert et al, 2014) or super-pixels (Albert et al, 2015) in the case of land cover and segments in the case of land use. The dependencies between land cover and land use are implicitly integrated in the classification process by using contextual features.…”

“…For this purpose, we perform a step-wise refinement of the land use classes, following the hierarchical structure of most object catalogues for land use databases. The investigation is based on an approach for the contextual classification of aerial imagery to determine both land cover and land use (Albert et al, 2015). Whereas land cover is determined at the level of small image segments, land use classification is applied to objects from an existing geospatial database.…”