Mikhail Kanevski

Active Learning Methods for Remote Sensing Image Classification

In this paper, we propose two active learning algorithms for semiautomatic definition of training samples in remote sensing image classification. Based on predefined heuristics, the classifier ranks the unlabeled pixels and automatically chooses those that are considered the most valuable for its improvement. Once the pixels have been selected, the analyst labels them manually and the process is iterated. Starting with a small and nonoptimal training set, the model itself builds the optimal set of samples which minimizes the classification error. We have applied the proposed algorithms to a variety of remote sensing data, including very high resolution and hyperspectral images, using support vector machines. Experimental results confirm the consistency of the methods. The required number of training samples can be reduced to 10% using the methods proposed, reaching the same level of accuracy as larger data sets. A comparison with a state-of-the-art active learning method, margin sampling, is provided, highlighting advantages of the methods proposed. The effect of spatial resolution and separability of the classes on the quality of the selection of pixels is also discussed.

A Survey of Active Learning Algorithms for Supervised Remote Sensing Image Classification

Defining an efficient training set is one of the most delicate phases for the success of remote sensing image classification routines. The complexity of the problem, the limited temporal and financial resources, as well as the high intraclass variance can make an algorithm fail if it is trained with a suboptimal dataset. Active learning aims at building efficient training sets by iteratively improving the model performance through sampling. A user-defined heuristic ranks the unlabeled pixels according to a function of the uncertainty of their class membership and then the user is asked to provide labels for the most uncertain pixels. This paper reviews and tests the main families of active learning algorithms: committee, large margin, and posterior probability-based. For each of them, the most recent advances in the remote sensing community are discussed and some heuristics are detailed and tested. Several challenging remote sensing scenarios are considered, including very high spatial resolution and hyperspectral image classification. Finally, guidelines for choosing the good architecture are provided for new and/or unexperienced user.

Learning Relevant Image Features With Multiple-Kernel Classification

The increase in spatial and spectral resolution of the satellite sensors, along with the shortening of the time-revisiting periods, has provided high-quality data for remote sensing image classification. However, the high-dimensional feature space induced by using many heterogeneous information sources precludes the use of simple classifiers: thus, a proper feature selection is required for discarding irrelevant features and adapting the model to the specific problem. This paper proposes to classify the images and simultaneously to learn the relevant features in such high-dimensional scenarios. The proposed method is based on the automatic optimization of a linear combination of kernels dedicated to different meaningful sets of features. Such sets can be groups of bands, contextual or textural features, or bands acquired by different sensors. The combination of kernels is optimized through gradient descent on the support vector machine objective function. Even though the combination is linear, the ranked relevance takes into account the intrinsic nonlinearity of the data through kernels. Since a naive selection of the free parameters of the multiple-kernel method is computationally demanding, we propose an efficient model selection procedure based on the kernel alignment. The result is a weight (learned from the data) for each kernel where both relevant and meaningless image features automatically emerge after training the model. Experiments carried out in multi- and hyperspectral, contextual, and multisource remote sensing data classification confirm the capability of the method in ranking the relevant features and show the computational efficience of the proposed strategy.

Classification of Very High Spatial Resolution Imagery Using Mathematical Morphology and Support Vector Machines

We investigate the relevance of morphological operators for the classification of land use in urban scenes using sub-metric panchromatic imagery. A support vector machine is used for the classification. Six types of filters have been employed: opening and closing, opening and closing by reconstruction, and opening and closing top hat. The type and scale of the filters are discussed, and a feature selection algorithm called recursive feature elimination is applied to decrease the dimensionality of the input data. The analysis performed on two QuickBird panchromatic images showed that simple opening and closing operators are the most relevant for classification at such a high spatial resolution. Moreover, mixed sets combining simple and reconstruction filters provided the best performance. Tests performed on both images, having areas characterized by different architectural styles, yielded similar results for both feature selection and classification accuracy, suggesting the generalization of the feature sets highlighted.

Supervised change detection in VHR images using contextual information and support vector machines

In this paper we study an effective solution to deal with supervised change detection in very high geometrical resolution (VHR) images. High within-class variance as well as low between-class variance that characterize this kind of imagery make the detection and classification of ground cover transitions a difficult task. In order to achieve high detection accuracy, we propose the inclusion of spatial and contextual information issued from local textural statistics and mathematical morphology. To perform change detection, two architectures, initially developed for medium resolution images, are adapted for VHR: Direct Multi-date Classification and Difference Image Analysis. To cope with the high intra-class variability, we adopted a nonlinear classifier: the Support Vector Machines (SVM). The proposed approaches are successfully evaluated on two series of pansharpened QuickBird images.

Environmental data mining and modeling based on machine learning algorithms and geostatistics

Abstract The paper presents some contemporary approaches to spatial environmental data analysis. The main topics are concentrated on the decision-oriented problems of environmental spatial data mining and modeling: valorization and representativity of data with the help of exploratory data analysis, spatial predictions, probabilistic and risk mapping, development and application of conditional stochastic simulation models. The innovative part of the paper presents integrated/hybrid model—machine learning (ML) residuals sequential simulations—MLRSS. The models are based on multilayer perceptron and support vector regression ML algorithms used for modeling long-range spatial trends and sequential simulations of the residuals. ML algorithms deliver non-linear solution for the spatial non-stationary problems, which are difficult for geostatistical approach. Geostatistical tools (variography) are used to characterize performance of ML algorithms, by analyzing quality and quantity of the spatially structured information extracted from data with ML algorithms. Sequential simulations provide efficient assessment of uncertainty and spatial variability. Case study from the Chernobyl fallouts illustrates the performance of the proposed model. It is shown that probability mapping, provided by the combination of ML data driven and geostatistical model based approaches, can be efficiently used in decision-making process.

Unsupervised Change Detection With Kernels

In this letter, an unsupervised kernel-based approach to change detection is introduced. Nonlinear clustering is utilized to partition in two a selected subset of pixels representing both changed and unchanged areas. Once the optimal clustering is obtained, the learned representatives of each group are exploited to assign all the pixels composing the multitemporal scenes to the two classes of interest. Two approaches based on different assumptions of the difference image are proposed. The first accounts for the difference image in the original space, while the second defines a mapping describing the difference image directly in feature spaces. To optimize the parameters of the kernels, a novel unsupervised cost function is proposed. An evidence of the correctness, stability, and superiority of the proposed solution is provided through the analysis of two challenging change-detection problems.

Machine Learning Feature Selection Methods for Landslide Susceptibility Mapping

This paper explores the use of adaptive support vector machines, random forests and AdaBoost for landslide susceptibility mapping in three separated regions of Canton Vaud, Switzerland, based on a set of geological, hydrological and morphological features. The feature selection properties of the three algorithms are studied to analyze the relevance of features in controlling the spatial distribution of landslides. The elimination of irrelevant features gives simpler, lower dimensional models while keeping the classification performance high. An object-based sampling procedure is considered to reduce the spatial autocorrelation of data and to estimate more reliably generalization skills when applying the model to predict the occurrence of new unknown landslides. The accuracy of the models, the relevance of features and the quality of landslide susceptibility maps were found to be high in the regions characterized by shallow landslides and low in the ones with deep-seated landslides. Despite providing similar skill, random forests and AdaBoost were found to be more efficient in performing feature selection than adaptive support vector machines. The results of this study reveal the strengths of the classification algorithms, but evidence: (1) the need for relying on more than one method for the identification of relevant variables; (2) the weakness of the adaptive scaling algorithm when used with landslide data; and (3) the lack of additional features which characterize the spatial distribution of deep-seated landslides.

Semisupervised Transfer Component Analysis for Domain Adaptation in Remote Sensing Image Classification

In this paper, we study the problem of feature extraction for knowledge transfer between multiple remotely sensed images in the context of land-cover classification. Several factors such as illumination, atmospheric, and ground conditions cause radiometric differences between images of similar scenes acquired on different geographical areas or over the same scene but at different time instants. Accordingly, a change in the probability distributions of the classes is observed. The purpose of this work is to statistically align in the feature space an image of interest that still has to be classified (the target image) to another image whose ground truth is already available (the source image). Following a specifically designed feature extraction step applied to both images, we show that classifiers trained on the source image can successfully predict the classes of the target image despite the shift that has occurred. In this context, we analyze a recently proposed domain adaptation method aiming at reducing the distance between domains, Transfer Component Analysis, and assess the potential of its unsupervised and semisupervised implementations. In particular, with a dedicated study of its key additional objectives, namely the alignment of the projection with the labels and the preservation of the local data structures, we demonstrate the advantages of Semisupervised Transfer Component Analysis. We compare this approach with other both linear and kernel-based feature extraction techniques. Experiments on multi- and hyperspectral acquisitions show remarkable cross- image classification performances for the considered strategy, thus confirming its suitability when applied to remotely sensed images.

SVM-Based Boosting of Active Learning Strategies for Efficient Domain Adaptation

We propose a procedure that efficiently adapts a classifier trained on a source image to a target image with similar spectral properties. The adaptation is carried out by adding new relevant training samples with active queries in the target domain following a strategy specifically designed for the case where class distributions have shifted between the two acquisitions. In fact, the procedure consists of two nested algorithms. An active selection of the pixels to be labeled is performed on a set of candidates of the target image in order to select the most informative pixels. Along the inclusion of the pixels to the training set, the weights associated with these samples are iteratively updated using different criteria, depending on their origin (source or target image). We study this adaptation framework in combination with a SVM classifier accepting instance weights. Experiments on two VHR QuickBird images and on a hyperspectral AVIRIS image prove the validity of the proposed adaptive approach with respect to existing techniques not involving any adjustments to the target domain.