Search

High- and very high-resolution (HR, VHR) remote sensing (RS) images can provide comprehensive and intricate spatial information for land cover classification, which is particularly crucial when analyzing complex built-up environments. However, the application of HR and VHR images to large-scale and detailed land cover mapping is always constrained by the intricacy of land cover classification models, the exorbitant cost of collecting training samples, and geographical changes or acquisition conditions. To overcome this limitation, we propose an unsupervised domain adaptation (UDA) with contrastive learning-based discriminative feature augmentation (CLDFA) for RS image classification. In detail, our method first utilizes contrastive learning (CL) through a memory bank in order to memorize sample features and improve model performance, where the approach employs an end-to-end Siamese network and incorporates dynamic pseudo-label assignment and class-balancing strategies for adaptive domain joint learning. By transferring classification models trained on a source domain (SD) to an unlabeled target domain (TD), our proposed UDA method enables large-scale land cover mapping. We conducted experiments using a massive five billion-pixels dataset as the SD and tested the HR and VHR RS images of five typical Chinese cities as the TD and applied the method on the completely unlabeled world view 3 (WV3) image of Urumqi city. The experimental results demonstrate that our method excels in large-scale HR and VHR RS image classification tasks, highlighting the advantages of semantic segmentation based on end-to-end deep convolutional neural networks (DCNNs). [ABSTRACT FROM AUTHOR]

Impervious surface information is an important indicator to describe urban development and environmental changes. The substantial increase in impervious surface area will have a significant impact on the regional landscape and environment. Therefore, the timely and accurate acquisition of large-scale impervious surface percentage (LISP) is of great significance for urban management and ecological assessment. However, previous LISP estimation methods often ignored the impact of regional geographic environment and climate differences on remote sensing information, resulting in low overall accuracy and obvious regional differences in the estimated results. Thus, in this study, based on the time-series characteristics of multi-temporal remote sensing images combined with the information on geographical environment and climate heterogeneity, a method of time-series remote sensing image fusion and LISP estimation based on regional divisions was proposed. Firstly, the entire region was divided into several regions according to the spatial differences of Köppen–Geiger climate data and MODIS NDVI time-series data. Subsequently, adaptive time-series image fusion methods and remote sensing feature construction methods were proposed for different regions. Finally, the proposed method was used to estimate the percentage of impervious surfaces in other years in Asia. The results indicate that the overall R2 of each region is better than 0.82, and the estimation models have a good ability to transfer across time and can directly estimate the impervious surface percentage in other years without using additional samples. In addition, compared with other existing impervious surface products, the proposed method has higher overall estimation accuracy and regional consistency. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNN) have attracted tremendous attention in the remote sensing community due to its excellent performance in different domains. Especially for remote sensing scene classification, the CNN-based methods have brought a great breakthrough. However, it is not feasible to fully design and train a new CNN model for remote sensing scene classification, as this usually requires a large number of training samples and high computational costs. To alleviate these limitations of fully training a new model, some work attempts to use the pretrained CNN models as feature extractors to build feature representation of scene images for classification and has achieved impressive results. In this scheme, how to construct feature representation of scene image via the pretrained CNN model becomes the key process. Existing studies paid a little attention to build more discriminative feature representation by exploring the potential benefits of multilayer features from a single CNN model and different feature representations from multiple CNN models. To this end, this paper presents a fusion strategy to build the feature representation of the scene images by integrating multilayer features of a single pretrained CNN model, and extends it to a framework of multiple CNN models. For these purposes, a multiscale improved Fisher kernel coding method is used to build feature representation of the scene images on convolutional layers, and a feature fusion approach based on two feature subspace learning methods [principal component analysis (PCA)/spectral regression kernel discriminant analysis and PCA/spectral regression kernel locality preserving projection] is proposed to construct final fused features for scene classification. For validation and comparison purposes, the proposed approaches are evaluated with two challenging high-resolution remote sensing datasets and shows the competitive performance compared with existing state-of-the-art baselines such as fully trained CNN models, fine tuning CNN models, and other related works. [ABSTRACT FROM AUTHOR]

In very high resolution (VHR) remote sensing (RS) classification tasks, conventional pixel-based contextual information extraction methods such as morphological profiles (MPs), extended MPs (EMPs) and MPs with partial reconstruction (MPPR) with limited numbers, sizes and shapes of structural elements (SEs) cannot perfectly match all sizes and shapes of the objects in an image. To overcome such limitation, we introduce novel spatial feature extractors, namely, the superpixel-guided morphological profiles (SPMPs), where the superpixels are used as SEs in opening by reconstruction and closing by reconstruction operations. Moreover, to avoid possible side effects from unusual maximum and minimum values within superpixels, the mean pixel value of superpixels is adopted (SPMPsM). Additionally, new decision forest based on penalizing the attributes in previous trees, the ForestPA is introduced and evaluated through a comparative investigation on three VHR multi-/hyperspectral RS image classification tasks. Support vector machine and benchmark ensemble classifiers, including bagging, AdaBoost, MultiBoost, ExtraTrees, Random Forest and Rotation Forest, are adopted. The experimental results confirm the effectiveness and superior performances of the proposed SPMPs and SPMPsM relative to those of the MPs and MPPR. Moreover, ForestPA outperforms only bagging and is not suitable for learning from large numbers of samples with high dimensionality from the computational efficiency and classification accuracy perspective. [ABSTRACT FROM AUTHOR]

Pixel-based contextual classification methods, including morphological profiles (MPs), extended MPs, attribute profiles (APs), and MPs with partial reconstruction (MPPR), have shown the benefits of using geometrical features extracted from very-high resolution (VHR) images. However, the structural element sequence or the attribute filters that are necessarily adopted in the above solutions always result in computationally inefficient and redundant high-dimensional features. To solve the second problem, we introduce maximally stable extremal regions (MSER) guided MPs (MSER_MPs) and MSER_MPs(M), which contains mean pixel values within regions, to foster effective and efficient spatial feature extraction. In addition, the extremely randomized decision tree (ERDT) and its ensemble version, ExtraTrees, are introduced and investigated. An extremely randomized rotation forest (ERRF) is proposed by simply replacing the conventional C4.5 decision tree in a rotation forest (RoF) with an ERDT. Finally, the proposed spatial feature extractors, ERDT, ExtraTrees, and ERRF are evaluated for their ability to classify three VHR multispectral images acquired over urban areas, and compared against C4.5, Bagging(C4.5), random forest, support vector machine, and RoF in terms of classification accuracy and computational efficiency. The experimental results confirm the superior performance of MSER_MPs(M) and MSER_MPs compared to MPPR and MPs, respectively, and ExtraTrees is better for spectral-spatial classification of VHR multispectral images using the original spectra stacked with MSER_MPs(M) features. [ABSTRACT FROM AUTHOR]

The possibility theory, which is an extension of fuzzy sets and fuzzy logic, has shown considerable potential for solving active learning (AL) problems, particularly for multiclass scenarios' classification. Hence, two recently proposed fuzzy multiclass AL algorithms (classification ambiguity (CA) and fuzzy C‐order ambiguity (FCOA)) are investigated to properly generalise them for classifying hyperspectral images, and two improved versions of the CA and FCOA are proposed. In addition to comparing the performances of the original and improved algorithms, several other state‐of‐the‐art AL methods are evaluated, such as breaking ties, margin sampling, and multi‐class level uncertainty, with or without diversity criteria such as angle‐based diversity (ABD), clustering‐based diversity (CBD), and enhanced clustering‐based diversity (ECBD). Tests on two benchmark hyperspectral images confirm that the proposed improved algorithms are superior to and more effective than the original ones. [ABSTRACT FROM AUTHOR]

Scene classification from remote sensing images provides new possibilities for potential application of high spatial resolution imagery. How to efficiently implement scene recognition from high spatial resolution imagery remains a significant challenge in the remote sensing domain. Recently, convolutional neural networks (CNN) have attracted tremendous attention because of their excellent performance in different fields. However, most works focus on fully training a new deep CNN model for the target problems without considering the limited data and time-consuming issues. To alleviate the aforementioned drawbacks, some works have attempted to use the pretrained CNN models as feature extractors to build a feature representation of scene images for classification and achieved successful applications including remote sensing scene classification. However, existing works pay little attention to exploring the benefits of multilayer features for improving the scene classification in different aspects. As a matter of fact, the information hidden in different layers has great potential for improving feature discrimination capacity. Therefore, this paper presents a fusion strategy for integrating multilayer features of a pretrained CNN model for scene classification. Specifically, the pretrained CNN model is used as a feature extractor to extract deep features of different convolutional and fully connected layers; then, a multiscale improved Fisher kernel coding method is proposed to build a mid-level feature representation of convolutional deep features. Finally, the mid-level features extracted from convolutional layers and the features of fully connected layers are fused by a principal component analysis/spectral regression kernel discriminant analysis method for classification. For validation and comparison purposes, the proposed approach is evaluated via experiments with two challenging high-resolution remote sensing data sets, and shows the competitive performance compared with fully trained CNN models, fine-tuning CNN models, and other related works. [ABSTRACT FROM PUBLISHER]

Feature representation is a classic problem in the machine learning community due to the fact that different representations can entangle and hide more or less the different explanatory factors of variation behind the raw data. Especially for scene classification, its performance generally depends on the discriminative power of feature representation. Recently, unsupervised feature learning attracts tremendous attention because of its ability to learn feature representation automatically. However, reliable performance of feature representations by unsupervised learning always requires a large number of features and complex framework of mid-level feature representation. To alleviate such drawbacks, this paper presents a new framework of mid-level feature representation, which does not need learn many convolutional features during the unsupervised feature learning process, and has few parameter settings. In detail, the unsupervised feature learning method, sparse autoencoder, is employed to learn relatively small number of convolutional features from input dataset, and then extended features are extracted from the learned features by a multiple normalized difference features extraction method to compose a derivative feature set. At mid-level feature representation stage, in order to avoid poor performance of standard pooling technology in solving problems brought by rotation and translation of scene images, global feature descriptors (histogram moments, mean, variance, standard deviation) are utilized to build mid-level feature representations of images. For validation and comparison purposes, the proposed approach is evaluated via experiments with two challenging high-resolution remote sensing datasets. The results demonstrate that the approach is effective, and shows strong performance for remotely sensed scene classification. [ABSTRACT FROM PUBLISHER]

Due to the lack of clear shape, texture characteristics, and abundant spectral or spatial information of urban objects, traditional per-/sub-pixel analysis and interpretation for moderate-resolution-remote sensing data are always confused by such shortcomings as dependence on special skills, requirements to a priori knowledge and training samples, complex process, time-consuming and subjective operations, etc.. In order to alleviate such disadvantages, an automatic approach is proposed to classify vegetation, water, impervious surface areas (dark and bright), and bare land from the Operational Land Imager (OLI) sensor data of Landsat-8 in urban areas, which can be employed by common users to automatically obtain land-cover maps for urban applications. In detail, a preliminary classification result is achieved based on a new vegetation and water masking index (VWMI), the normalized difference vegetation index (NDVI), and a new normalized difference bare land index (NDBLI), which are acquired automatically from the remote-sensing images based on available knowledge of spectral properties. VWMI is designed to extract vegetation and water information together with a simpler threshold, while NDBLI is developed to identify dark impervious surfaces and bare land in this work. A modification strategy is further proposed to improve preliminary classification results by a linear model. For this purpose, a stable sample selection method based on the histogram is developed to select training samples from the preliminary classification result and to build a non-linear support vector machine (SVM) model to reclassify the classes. For validation and comparison purposes, the proposed approach is evaluated via experiments with real OLI data of two study areas, Nanjing and Ordos. The results demonstrate that the approach is effective in automatically obtaining urban land-cover classification maps from OLI data for thematic analysis. [ABSTRACT FROM PUBLISHER]

The detection of building edges from very high resolution (VHR) remote sensing imagery is essential to various geo-related applications, including surveying and mapping, urban management, etc. Recently, the rapid development of deep convolutional neural networks (DCNNs) has achieved remarkable progress in edge detection; however, there has always been the problem of edge thickness due to the large receptive field of DCNNs. In this paper, we proposed a multi-scale erosion network (ME-Net) for building edge detection to crisp the building edge through two innovative approaches: (1) embedding an erosion module (EM) in the network to crisp the edge and (2) adding the Dice coefficient and local cross entropy of edge neighbors into the loss function to increase its sensitivity to the receptive field. In addition, a new metric, Ene, to measure the crispness of the predicted building edge was proposed. The experiment results show that ME-Net not only detects the clearest and crispest building edges, but also achieves the best OA of 98.75%, 95.00% and 95.51% on three building edge datasets, and exceeds other edge detection networks 3.17% and 0.44% at least in strict F1-score and Ene. In a word, the proposed ME-Net is an effective and practical approach for detecting crisp building edges from VHR remote sensing imagery. [ABSTRACT FROM AUTHOR]

To investigate the performance of extreme gradient boosting (XGBoost) in remote sensing image classification tasks, XGBoost was first introduced and comparatively investigated for the spectral-spatial classification of hyperspectral imagery using the extended maximally stable extreme-region-guided morphological profiles (EMSER_MPs) proposed in this study. To overcome the potential issues of XGBoost, meta-XGBoost was proposed as an ensemble XGBoost method with classification and regression tree (CART), dropout-introduced multiple additive regression tree (DART), elastic net regression and parallel coordinate descent-based linear regression (linear) and random forest (RaF) boosters. Moreover, to evaluate the performance of the introduced XGBoost approach with different boosters, meta-XGBoost and EMSER_MPs, well-known and widely accepted classifiers, including support vector machine (SVM), bagging, adaptive boosting (AdaBoost), multi class AdaBoost (MultiBoost), extremely randomized decision trees (ExtraTrees), RaF, classification via random forest regression (CVRFR) and ensemble of nested dichotomies with extremely randomized decision tree (END-ERDT) methods, were considered in terms of the classification accuracy and computational efficiency. The experimental results based on two benchmark hyperspectral data sets confirm the superior performance of EMSER_MPs and EMSER_MPs with mean pixel values within region (EMSER_MPsM) compared to that for morphological profiles (MPs), morphological profile with partial reconstruction (MPPR), extended MPs (EMPs), extended MPPR (EMPPR), maximally stable extreme-region-guided morphological profiles (MSER_MPs) and MSER_MPs with mean pixel values within region (MSER_MPsM) features. The proposed meta-XGBoost algorithm is capable of obtaining better results than XGBoost with the CART, DART, linear and RaF boosters, and it could be an alternative to the other considered classifiers in terms of the classification of hyperspectral images using advanced spectral-spatial features, especially from generalized classification accuracy and model training efficiency perspectives. [ABSTRACT FROM AUTHOR]

Land-cover map is the basis of research and application related to urban planning, environmental management and ecological protection. Land-cover updating is an essential task especially in a rapidly urbanizing region, where fast development makes it necessary to monitor land-cover change in a timely manner. However, conventional approaches always have the limitations of large amounts of sample collection and exploitation of relational knowledge between multi-modality remote sensing datasets. With some global land-cover products being available, it is important to produce new land-cover maps based on the existing land-cover products and time series images. To this end, a novel transfer learning based automatic approach was proposed for updating land cover maps of rapidly urbanizing regions. In detail, the proposed method is composed of the following three steps. The first is to design a strategy to extract reliable land-cover information from the historical land-cover map for one of the images (source domain). Then, a novel relational knowledge transfer technique is applied to transfer label information. Finally, classifiers are trained on the transferred samples with spatio-spectral features. The experimental results show that aforementioned steps can select sufficient effective samples for target images, and for the main land-cover classes in a rapidly urbanizing region; the results of an updated map show good performance in both precision and vision. Therefore, the proposed approach provides an automatic solution for urban land-cover mapping with a high degree of accuracy. [ABSTRACT FROM AUTHOR]

With the development of remote sensing technology and the advent of high-resolution images, obtaining data has become increasingly convenient. However, the acquisition of small manhole cover information still has shortcomings including low efficiency of manual surveying and high leakage rate. Recently, deep learning models, especially deep convolutional neural networks (DCNNs), have proven to be effective at object detection. However, several challenges limit the applications of DCNN in manhole cover object detection using remote sensing imagery: (1) Manhole cover objects often appear at different scales in remotely sensed images and DCNNs' fixed receptive field cannot match the scale variability of such objects; (2) Manhole cover objects in large-scale remotely-sensed images are relatively small in size and densely packed, while DCNNs have poor localization performance when applied to such objects. To address these problems, we propose an effective method for detecting manhole cover objects in remotely-sensed images. First, we redesign the feature extractor by adopting the visual geometry group (VGG), which can increase the variety of receptive field size. Then, detection is performed using two sub-networks: a multi-scale output network (MON) for manhole cover object-like edge generation from several intermediate layers whose receptive fields match different object scales and a multi-level convolution matching network (M-CMN) for object detection based on fused feature maps, which combines several feature maps that enable small and densely packed manhole cover objects to produce a stronger response. The results show that our method is more accurate than existing methods at detecting manhole covers in remotely-sensed images. [ABSTRACT FROM AUTHOR]