Combining multiple resolutions into hierarchical representations for kernel-based image classification
This work addresses the scale limitation in GEOBIA for remote sensing applications, though it appears incremental as it builds on existing hierarchical and kernel-based methods.
The authors tackled the problem of limited scale handling in geographic object-based image analysis (GEOBIA) by proposing a multiscale classification approach using hierarchical representations from images at different resolutions, which improved classification accuracy on an urban task compared to single-scale methods.
Geographic object-based image analysis (GEOBIA) framework has gained increasing interest recently. Following this popular paradigm, we propose a novel multiscale classification approach operating on a hierarchical image representation built from two images at different resolutions. They capture the same scene with different sensors and are naturally fused together through the hierarchical representation, where coarser levels are built from a Low Spatial Resolution (LSR) or Medium Spatial Resolution (MSR) image while finer levels are generated from a High Spatial Resolution (HSR) or Very High Spatial Resolution (VHSR) image. Such a representation allows one to benefit from the context information thanks to the coarser levels, and subregions spatial arrangement information thanks to the finer levels. Two dedicated structured kernels are then used to perform machine learning directly on the constructed hierarchical representation. This strategy overcomes the limits of conventional GEOBIA classification procedures that can handle only one or very few pre-selected scales. Experiments run on an urban classification task show that the proposed approach can highly improve the classification accuracy w.r.t. conventional approaches working on a single scale.