This paper presents a novel method addressing the classification task of satellite images when limited labeled data is available together with a large amount of unlabeled data. Instead of using semi-supervised classifiers, we solve the problem by learning a high-level features, called semisupervised ensemble projection (SSEP). More precisely, we propose to represent an image by projecting it onto an ensemble of weak training (WT) sets sampled from a Gaussian approximation of multiple feature spaces. Given a set of images with limited labeled ones, we first extract preliminary features, e.g., color and textures, to form a low-level image description. We then propose a new semisupervised sampling algorithm to build an ensemble of informative WT sets by exploiting these feature spaces with a Gaussian normal affinity, which ensures both the reliability and diversity of the ensemble. Discriminative functions are subsequently learned from the resulting WT sets, and each image is represented by concatenating its projected values onto such WT sets for final classification. Moreover, we consider that the potential redundant information existed in SSEP and use sparse coding to reduce it. Experiments on high-resolution remote sensing data demonstrate the efficiency of the proposed method.Index Terms-Ensemble projection (EP), feature representation, image classification, semisupervised learning.
Purely bottom-up, unsupervised target segmentation is one of the most challenging problems in satellite image interpretation within the computer vision community. In this paper, we focus on the problem of automatically segmenting aircrafts from high-resolution satellite images based on the idea of co-segmentation. First, we selectively segment out the regions of interest (ROIs) from the satellite images. Then, we apply a region based shadow detection and removal approach to remove shadows. Finally, the anisotropic heat diffusion model is employed to fulfill our co-segmentation task. Experimental results on a given dataset have demonstrated the effectiveness of our method.
This paper presents a semi-supervised method for learning informative image representations, which is a crucial but challenging step for remote sensing image classification. More precisely, we propose to represent an image by projecting it onto an ensemble of prototype sets sampled from a Gaussian approximation of multiple feature spaces. Given a set of images with a few labeled ones, we first extract preliminary features, e.g. color and textures, to form a low-level image description. We then build an ensemble of informative prototype sets by exploiting these feature spaces with a Gaussian normal affinity. Discriminative functions are subsequently learned from the resulting prototype sets, and each image is represented by concatenating their projected values onto such prototypes for final classification. Experiments on two high-resolution remote sensing image sets demonstrate the efficiency of the proposed method on remote sensing image classification with different classifiers.Index Terms-Semi-supervised feature learning, ensemble projection, remote sensing image classification
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.