One-Class Remote Sensing Classification From Positive and Unlabeled Background Data

One-class classification is a common situation in remote sensing, where researchers aim to extract a single land type from remotely sensed data. Learning a classifier from labeled positive and unlabeled background data, which is the case-control sampling scenario, is efficient for one-class remote sensing classification because labeled negative data are not necessary for model training. In this study, we propose a novel positive and background learning with constraints (PBLC) algorithm to address this one-class classification problem. With user-specified information of maximum probability as the constraint, PBLC infers the posterior probability of positive class directly in one-step model training. We test PBLC on a synthetic dataset and a real aerial photograph to perform different one-class classification tasks. Experimental results demonstrate that PBLC can successfully train linear and nonlinear classifiers including generalized linear model, artificial neural network, and convolutional neural network. Probabilistic and binary predictions by PBLC are more similar to the gold-standard positive-negative method, outperforming the two-step positive and background learning algorithm that post-calibrates a naïve classifier based on an estimated constant. Hence, the proposed PBLC algorithm has the potential to solve one-class classification problems in the case-control sampling scenario.