Search

This paper proposes an automatic method for land cover change detection in very-high-spatial-resolution optical remote sensing images based on the automatic selection of training samples using expectation-maximization (EM) and an extreme learning machine classifier, which has two key characteristics: (1) combining the advantages of supervised and unsupervised methods with progressive mask classification. (2) training samples of three classes (changed, unchanged, and unknown) were automatically selected by K-Means and EM, and then further refined by the likelihood function. The method was validated by one dataset of SuperView-1 imagery with a spatial resolution of 2.0 m, two datasets of TripleSat-2 imagery with a spatial resolution of 3.2 m, and one open dataset of Zi-Yuan-3 imagery with a spatial resolution of 5.8 m, and the results were compared with that of three unsupervised methods (iterative slow feature analysis, multivariate alteration detection, and adaptive object-oriented spatial-contextual extraction algorithm), two deep learning methods (convolutional-wavelet neural networks and dual-domain networks), and three supervised classifiers (support vector machine, random forest, and Naive Bayes), showing the effectiveness of this method in decrease of false-positive rates and increase of change detection accuracy. The average and maximum of the accuracy metric F1 score of our method are 0.6842 and 0.8708, respectively; the average F1 score of the unsupervised, deep learning, and supervised methods are 0.5049, 0.4943, and 0.633, respectively. [ABSTRACT FROM AUTHOR]

Although many machine learning methods have been successfully applied for the object-based classification of high resolution (HR) remote sensing imagery, current methods are highly dependent on the spectral similarity between segmented objects and have disappointingly poor performance when dealing with different segmented objects that have similar spectra. To overcome this limitation, this study exploited a knowledge graph (KG) that preserved the spatial relationships between segmented objects and has a reasoning capability that can assist in improving the probability of correctly classifying different segmented objects with similar spectra. In addition, to assist the knowledge graph classifications, an image segmentation method generating segmented objects that closely resemble real ground objects in size was used, which improves the integrity of the object classification results. Therefore, a novel HR remote sensing image classification scheme is proposed that involves a knowledge graph and an optimal segmentation algorithm, which takes full advantage of object-based classification and knowledge inference. This method effectively addresses the problems of object classification integrity and misclassification of objects with the same spectrum. In the evaluation experiments, three QuickBird-2 images and over 15 different land cover classes were utilized. The results showed that the classification accuracy of the proposed method is high, with overall accuracies exceeding 0.85. These accuracies are higher than the K Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF) methods. The evaluated results confirmed that the proposed method offers excellent performance in HR remote sensing image classification. [ABSTRACT FROM AUTHOR]

Aiming at the poor classification effect caused by complex background, large intra-class difference and high interclass similarity in remote sensing scene images, this paper proposed an attentional mechanism and residual contraction unit algorithm based on supervised contrast learning. Firstly, the algorithm improved the effective channel attention mechanism (ECA), and optimized the extraction of image features to be recognized. Then, the algorithm proposed a cooperative residual shrinkage unit algorithm, which is used to filter and eliminate redundant information of images. In addition, supervised contrast learning algorithm was used to enhance the generalization ability of the algorithm. Finally, experiments were carried out with remote sensing image data set and compared with the latest algorithms such as enhanced attention algorithm and scale attention mechanism algorithm. Experimental results show that the proposed algorithm improves the classification accuracy by 1.75% and 2.5% in AID Data Set with 20% training ratio. [ABSTRACT FROM AUTHOR]

A single semantic category label cannot describe comprehensively the image content because remote sensing images contain various object categories. The task of multi-label image classification is more challenging. By exploring the depth graph convolutional network(GCN), this paper made up for the lack of relevance of label semantic information in multi-label remote sensing image classification, proposed a new multi-label remote sensing image classification network, multi-label remote sensing image classification network based on the GCN. It contained three parts: image feature learning module, classifiers learning module based on GCN, and image feature differentiating module. Compared with the related models on the public multi label remote sensing datasets planet and UCM, the method can get better classification results on the multi label remote sensing image classification task. The method used modules such as graph convolution to apply multi-label image classification methods to remote sensing, which improved the model classification ability and shortened the model training time. [ABSTRACT FROM AUTHOR]

Remote sensing image classification is a crucial link when processing remote sensing images. Through classification, remote sensing images are converted into classified features that can be understood and processed by computers running deep applications. However, the traditional remote sensing image classification methods do not meet the actual application requirements. In recent years, the rapid development of deep learning theory has provided a technical approach for solving remote sensing image classification. However, deep learning has the following problems when applied to remote sensing image classification: First, it is impossible to construct an activation function suitable for deep learning models that matches the characteristics of remote sensing images; second, the deep learning classification models have poor effects. In view of this, this paper first studies the activation function and constructs ridge waves with scale, displacement, and direction information. Because a ridge wave has good compact support characteristics, it can more closely approximate the high-dimensional nonlinear decision function and obtain a more effective activation function, thus solving the activation function problem in deep learning modeling. At the same time, to optimize the classifiers included in deep learning models, this paper proposes a sparse collaborative representation classifier that more fully combines the advantages of sparse representation classifiers and collaborative representation classifiers. It can yield the relationship between the competition and the collaboration of the remote sensing image to be classified and better use the characteristics of the remote sensing image, achieving better classification effect. Based on the above ideas, this paper proposes a remote sensing image classification algorithm based on a ridge wave sparse collaborative representation convolutional neural network. Finally, the method in this paper is verified by experiments on "UC Merced Land Use Dataset" and "RSSCN7 Dataset". The results show that the average accuracy of the method proposed in this paper is significantly higher than that of machine learning and other deep learning methods, and the method in this paper has better stability and robustness. [ABSTRACT FROM AUTHOR]

Remote sensing image classification plays an important role in a wide range of applications and has caused widely concerns. During the last few years, great efforts have been made to develop a number of scene classification methods for remote sensing images. However, the existing remote sensing image classification methods do not perform satisfactorily in dealing with multi-class classification problems and rely heavily on the quality of data sets. These disadvantages seriously restrict the application of remote sensing image, including industrial research, analysis and calculation of land use and land coverage. To this end, this paper proposes a remote sensing image classification algorithm based on the sparse regularized feature learning method. Specifically, after constructing bag of features by using speeded up robust features extraction algorithm, direct sparsity optimization-based feature selection method is applied for selecting discriminative features, which is used for constructing support vector machine classifier model. The proposed algorithm has been evaluated and compared with other advanced feature selection methods on four public remote sensing image data sets. The experimental results demonstrate the effectiveness of our proposed image classification algorithm, which has been successfully applied to remote sensing image classification tasks. [ABSTRACT FROM AUTHOR]

With the development of modern remote sensing technology, remote sensing images have become one of the powerful tools for people to understand the Earth and its surroundings. However, there is currently no good classification algorithm that can accurately classify images. In order to accurately classify remote sensing images, this paper studies the content of the article by using fuzzy C-means clustering algorithm and radial basis neural network (RBF). The classification accuracy of SIRI-WHU dataset was analyzed by using the classification accuracy evaluation index such as overall accuracy and Kappa coefficient. The Kappa coefficient of vegetation classification in SIRI-WHU dataset was 0.9678, and the overall accuracy reached 97.18%. According to the classification problem of remote sensing image, according to the characteristics of remote sensing image, the improved model Alex Net-10-FCM is used to classify the remote sensing image dataset, and very high classification accuracy is obtained. [ABSTRACT FROM AUTHOR]

Urban land use/land cover classification and change detection based on remote sensing imagery are of great significance in land use surveying and updating. Based on Wuhan high-resolution aerial and sat- ellite remote sensing images and corresponding GIS vector data, we propose a novel convolutional neural network to apply in the urban land cover classification and change detection. Firstly, a fully atrous convolu- tional neural network (FACNN) is proposed, which could take into account the different scale and LOD (level of detail) of polygons in the GIS vector data. Then, both pixel - based change detection and object - based change detection are analyzed according to the classification maps from FACNN and a previous GIS map. Finally, the effectiveness and advantage of our method are verified by the classification and change de- tection experiments in very high resolution remote sensing images of Wuhan city covering more than 8 000 km2. The proposed FACNN proved outperforming mainstream CNN based methods as FCN-16, U-Net, and Dense-Net, and the precision of the object-based change detection achieved 74.1% and the recall was 96.4%, indicating application prospects for unban GIS map updating. [ABSTRACT FROM AUTHOR]

Because of the uncertainty in remote sensing images and the ill-posedness of the problem, it is difficult for traditional unsupervised classification algorithms to create an accurate classification model. In contrast, pattern recognition methods based on fuzzy set theory, such as fuzzy c-means clustering, can manage the fuzziness of data effectively. Of these methods, the type-2 fuzzy c-means algorithm is better able to control uncertainty. Furthermore, semi-supervised training can use prior knowledge to deal with ill-posedness, and hence is more suitable. Therefore, we propose a novel classification method based the semi-supervised adaptive interval type-2 fuzzy c-means algorithm (SS-AIT2FCM). First, by integrating the semi-supervised approach, an evolutional fuzzy weight index m is proposed that improves the robustness and well-posedness of the model used in the clustering algorithm. This makes the algorithm suitable for remote sensing images with severe spectral aliasing, large coverage areas, and abundant features. In addition, soft constraint supervision is performed using a small number of labeled samples, which optimizes the iterative process of the algorithm and determines the optimal set of features for the data. This further reduces the ill-posedness of the model itself. The experimental data consist of three study areas: SPOT5 imagery from Big Hengqin Island, Guangdong, China, and the Summer Palace, Beijing, China, as well as TM imagery from Hengqin Island. Compared with several state-of-the-art fuzzy classification algorithms, our algorithm improves classification accuracy by more than 5% overall and obtains clearer boundaries in remote sensing images with serious mixed pixels. Moreover, it is able to suppress the phenomenon of isomorphic spectra. • Selecting fuzzy weight index m based on evolution theory. • Introduce semi-supervised approach with fuzzy distance metrics. • Soft constraint supervision optimizes the iterative process. • SS-AIT2FCM is suitable for remote sensing images with severe spectral aliasing. [ABSTRACT FROM AUTHOR]

Remote sensing image scene classification is a fundamental problem, which aims to label an image with a specific semantic category automatically. Recent progress on remote sensing image scene classification is substantial, benefitting mostly from the powerful feature extraction capability of convolutional neural networks (CNNs). Even though these CNN-based methods have achieved competitive performances, they only construct the representation of the image in location-sensitive space-domain. As a result, their representations are not robust to rotation-variant remote sensing images, which influence the classification accuracy. In this paper, we propose a novel feature representation method by introducing a frequency-domain branch to the traditional only-space-domain architecture. Our framework takes full advantages of discriminative features from space domain and location-robust features from the frequency domain, providing more advanced representations through an additional joint learning module, a property that is critically needed to perform remote sensing image scene classification. Additionally, our method produces satisfactory performances on four public and challenging remote sensing image scene data sets, Sydney, UC-Merced, WHU-RS19, and AID. [ABSTRACT FROM AUTHOR]