Search

Satellite imagery often exhibits large spatial extent areas that encompass object classes with considerable variability. This often limits large-scale model generalization with machine learning algorithms. Notably, acquisition conditions, including dates, sensor position, lighting condition, and sensor types, often translate into class distribution shifts introducing complex nonlinear factors and hamper the potential impact of machine learning classifiers. This paper investigates the challenge of exploiting satellite images using convolutional neural networks (CNN) for settlement classification where the class distribution shifts are significant. We present a large-scale human settlement mapping workflow based-off multiple modules to adapt a pretrained CNN to address the negative impact of distribution shift on classification performance. To extend a locally trained classifier onto large spatial extents areas we introduce several submodules: First, a human-in-the-loop element for relabeling of misclassified target domain samples to generate representative examples for model adaptation; second, an efficient hashing module to minimize redundancy and noisy samples from the mass-selected examples; and third, a novel relevance ranking module to minimize the dominance of source example on the target domain. The workflow presents a novel and practical approach to achieve large-scale domain adaptation with binary classifiers that are based-off CNN features. Experimental evaluations are conducted on areas of interest that encompass various image characteristics, including multisensors, multitemporal, and multiangular conditions. Domain adaptation is assessed on source–target pairs through the transfer loss and transfer ratio metrics to illustrate the utility of the workflow. [ABSTRACT FROM PUBLISHER]

The classification of hyperspectral and multimodal remote sensing data is affected by two key problems: the high dimensionality of the input data and the limited number of the labeled samples. In this letter, a multimetric learning approach that combines feature extraction and active learning (AL) is introduced to deal with these two issues simultaneously. In particular, distinct metrics are assigned to different types of features and then learned jointly. In this way, multiple features are projected into a common feature space, in which AL is then performed in conjunction with $k$- nearest neighbor classification to enrich the set of labeled samples. Experiments on two sets of remote sensing data illustrate the effectiveness of the proposed framework in terms of both classification accuracy and computational requirements. [ABSTRACT FROM PUBLISHER]

Classification of remotely sensed hyperspectral images via supervised approaches is typically affected by high dimensionality of the spectral data and a limited number of labeled samples. Dimensionality reduction via feature extraction and active learning (AL) are two approaches that researchers have investigated independently to deal with these two problems. In this paper, we propose a new method in which the feature extraction and AL steps are combined into a unique framework. The idea is to learn and update a reduced feature space in a supervised way at each iteration of the AL process, thus taking advantage of the increasing labeled information provided by the user. In particular, the computation of the reduced feature space is based on the large-margin nearest neighbor (LMNN) metric learning principle. This strategy is applied in conjunction with $k$-nearest neighbor ( $k$-NN) classification, for which a new sample selection strategy is proposed. The methodology is validated experimentally on four benchmark hyperspectral data sets. Good improvements in terms of classification accuracy and computational time are achieved with respect to the state-of-the-art strategies that do not combine feature extraction and AL. [ABSTRACT FROM PUBLISHER]

Adapting a pretrained classifier with unlabeled samples from an image for classification of another related image is a common domain adaptation strategy. However, traditional adaptation methods are not effective when the drift of spectral signatures is significant. Instead of iteratively redefining classifier parameters or decision boundaries, we exploit similar data geometries of images and preserve essential common data characteristics in a joint manifold space where similar samples are clustered. The proposed classification framework is based on aligning two global data manifolds with bridging pairs. In addition to global structures, we also consider the local scale by incorporating similar local clusters into the alignment process. In experiments with challenging temporal and spatially disjoint hyperspectral data sets, the proposed framework provides favorable classification results compared to two baseline methods, naive $k$-NN in both the original space and the manifold derived from pooled data. In comparisons with four state-of-the-art domain adaptation benchmark methods, the proposed method is demonstrated to be a competitive domain adaptation method, especially for the case when spectral changes between two data domains are significant. Results also provide insights related to the usefulness of incorporating global and local geometric characteristics of remote sensing data for domain adaptation studies. [ABSTRACT FROM PUBLISHER]

Multitemporal hyperspectral images provide valuable information for a wide range of applications related to supervised classification, including long-term environmental monitoring and land cover change detection. However, the required ground reference data are time-consuming and expensive to acquire, motivating researchers to investigate options for reusing limited training data for classification of other temporal images. Current studies that address high dimensionality and nonstationarity inherent in temporal hyperspectral data for classification are limited for the case where significant spectral drift exists between images. In this paper, we adapt and extend two manifold alignment (MA) methods for classification of multitemporal hyperspectral images in a common manifold space, assuming that the local geometries of two temporal spectral images are similar. The first method exploits a locally based manifold configuration of a source image (considered to be the “prior” manifold), and the second approach links local manifolds of two images using bridging pairs. In addition to exploiting manifolds estimated with spectral information for MA, we also demonstrate how spatial information can be incorporated into the MA methods. When evaluated using three Hyperion data sets, the proposed methods outperform four baseline approaches and two state-of-the-art domain adaptation methods. The advantages of the proposed MA methods are more evident when significant spectral drift exists between two temporal images. In addition to the promising classification results, the proposed methods establish a domain adaptation framework for analysis of temporal hyperspectral data based on data geometry. [ABSTRACT FROM AUTHOR]

Incorporating disparate features from multiple sources can provide valuable diverse information for remote sensing data analysis. However, multisource remote sensing data require large quantities of labeled data to train robust supervised classifiers, which are often difficult and expensive to acquire. A mixture-of-kernel approach can facilitate the construction of an effective formulation for acquiring useful samples via active learning (AL). In this paper, we propose an ensemble multiple kernel active learning (EnsembleMKL-AL) framework that incorporates different types of features extracted from multisensor remote sensing data (hyperspectral imagery and LiDAR data) for robust classification. An ensemble of probabilistic multiple kernel classifiers is embedded into a maximum disagreement-based AL system, which adaptively optimizes the kernel for each source during the AL process. At the end of each learning step, a decision fusion strategy is implemented to make a final decision based on the probabilistic outputs. The proposed framework is tested in a multisource environment, including different types of features extracted from hyperspectral and LiDAR data. The experimental results validate the efficacy of the proposed approach. In addition, we demonstrate that using ensemble classifiers and a large number of disparate but relevant features can further improve the performance of an AL-based classification approach. [ABSTRACT FROM PUBLISHER]

Active learning, which has a strong impact on processing data prior to the classification phase, is an active research area within the machine learning community, and is now being extended for remote sensing applications. To be effective, classification must rely on the most informative pixels, while the training set should be as compact as possible. Active learning heuristics provide capability to select unlabeled data that are the “most informative” and to obtain the respective labels, contributing to both goals. Characteristics of remotely sensed image data provide both challenges and opportunities to exploit the potential advantages of active learning. We present an overview of active learning methods, then review the latest techniques proposed to cope with the problem of interactive sampling of training pixels for classification of remotely sensed data with support vector machines (SVMs). We discuss remote sensing specific approaches dealing with multisource and spatially and time-varying data, and provide examples for high-dimensional hyperspectral imagery. [ABSTRACT FROM PUBLISHER]