High-Resolution Remote-Sensing Image Classification via an Approximate Earth Mover's Distance-Based Bag-of-Features Model

High-resolution remote-sensing image classification is a challenging task. In this letter, we first propose a bag-of-features (BOF) model-based classification framework for high-resolution remote-sensing images via Earth mover's distance (EMD) to perform histogram matching. Compared with conventional BOF, EMD-based BOF is insensitive to vector quantization and can explore the relations among visual codes. In addition, such relations can be utilized as a key discriminative feature for image classification task. However, EMD is not practically utilized because of expensive computational cost. Motivated by Pele and Werman, we propose a faster approximate EMD (AEMD), and our AEMD-based BOF can inherit the advantages of EMD. Experimental results on a multicategory remote-sensing image data set demonstrate the effectiveness of our classification framework.