Spatial and Structured SVM for Multilabel Image Classification

Satoru Koda, Abdallah Zeggada, Farid Melgani, Ryuei Nishii

Abstract: We describe a novel multilabel classification approach based on a support vector machine (SVM) for the extremely high-resolution remote sensing images. Its underlying ideas consist to: 1) exploit inter-label relationships by means of a structured SVM and 2) incorporate spatial contextual information by adding to the cost function a term that encourages spatial smoothness into the structural SVM optimization process. The resulting formulation appears as an extension of the traditional SVM learning, in which our proposed model integrates the output structure and spatial information simultaneously during the training. Numerical experiments conducted on two different UAV- and airborne-acquired sets of images show the interesting properties of the proposed model, in particular, in terms of classification accuracy.