High Spatial Resolution Remote-Sensing Imagery Research Articles

Irrigated Crop Types Mapping in Tashkent Province of Uzbekistan with Remote Sensing-Based Classification Methods.

Appropriate crop type mapping to monitor and control land management is very important in developing countries. It can be very useful where digital cadaster maps are not available or usage of Remote Sensing (RS) data is not utilized in the process of monitoring and inventory. The main goal of the present research is to compare and assess the importance of optical RS data in crop type classification using medium and high spatial resolution RS imagery in 2018. With this goal, Landsat 8 (L8) and Sentinel-2 (S2) data were acquired over the Tashkent Province between the crop growth period of May and October. In addition, this period is the only possible time for having cloud-free satellite images. The following four indices “Normalized Difference Vegetation Index” (NDVI), “Enhanced Vegetation Index” (EVI), and “Normalized Difference Water Index” (NDWI1 and NDWI2) were calculated using blue, red, near-infrared, shortwave infrared 1, and shortwave infrared 2 bands. Support-Vector-Machine (SVM) and Random Forest (RF) classification methods were used to generate the main crop type maps. As a result, the Overall Accuracy (OA) of all indices was above 84% and the highest OA of 92% was achieved together with EVI-NDVI and the RF method of L8 sensor data. The highest Kappa Accuracy (KA) was found with the RF method of L8 data when EVI (KA of 88%) and EVI-NDVI (KA of 87%) indices were used. A comparison of the classified crop type area with Official State Statistics (OSS) data about sown crops area demonstrated that the smallest absolute weighted average (WA) value difference (0.2 thousand ha) was obtained using EVI-NDVI with RF method and NDVI with SVM method of L8 sensor data. For S2-sensor data, the smallest absolute value difference result (0.1 thousand ha) was obtained using EVI with RF method and 0.4 thousand ha using NDVI with SVM method. Therefore, it can be concluded that the results demonstrate new opportunities in the joint use of Landsat and Sentinel data in the future to capture high temporal resolution during the vegetation growth period for crop type mapping. We believe that the joint use of S2 and L8 data enables the separation of crop types and increases the classification accuracy.

Fully Deformable Convolutional Network for Ship Detection in Remote Sensing Imagery

In high spatial resolution remote sensing imagery (HRSI), ship detection plays a fundamental role in a wide variety of applications. Despite the remarkable progress made by many methods, ship detection remains challenging due to the dense distribution, the complex background, and the huge differences in scale and orientation of ships. To address the above problems, a novel, fully deformable convolutional network (FD-Net) is proposed for dense and multiple-scale ship detection in HRSI, which could effectively extract features at variable scales, orientations and aspect ratios by integrating deformable convolution into the entire network structure. In order to boost more accurate spatial and semantic information flow in the network, an enhanced feature pyramid network (EFPN) is designed based on deformable convolution constructing bottom-up feature maps. Additionally, in considering of the feature level imbalance in feature fusion, an adaptive balanced feature integrated (ABFI) module is connected after EFPN to model the scale-sensitive dependence among feature maps and highlight the valuable features. To further enhance the generalization ability of FD-Net, extra data augmentation and training methods are jointly designed for model training. Extensive experiments are conducted on two public remote sensing datasets, DIOR and DOTA, which then strongly prove the effectiveness of our method in remote sensing field.

A Relation-Augmented Embedded Graph Attention Network for Remote Sensing Object Detection

Multiclass geospatial object detection in high spatial resolution remote sensing imagery (HSRI) is still a challenging task. The main reason is that the objects in HRSI are location-variable and semantic-confusable, which results in the difficulties in differentiating the complicated spatial patterns and deriving the implicitly semantic labels among different categories of objects. In this article, we propose a relation-augmented embedded graph attention network (EGAT), which enables the full exploitation of the underlying spatial and semantic relations among objects for improving the detection performance. Specifically, we first construct two sets of spatial and semantic graphs of objects–objects for object relations modeling. Second, a Siamese architecture-based embedding spatial and semantic graph attention network is designed for relations reasoning, which is implemented by introducing the long short-term memory (LSTM) mechanism into the EGAT, for learning the relations among different categories of intraobjects and interobjects. Driven by the spatial and semantic LSTM, the EGAT-LSTM can adaptively focus on the critical information of reason graphs for spatial–semantic correlation discrimination in the embedding non-Euclidean feature space. By this way, the EGAT-LSTM can effectively capture the global and local spatial–semantic relationships of objects–objects, and then produce relations-augmented features for improving the performance of object detection. We conduct comprehensive experiments on three public datasets for multiclass geospatial object detection. Our method achieves state-of-the-art performance, which demonstrates the superiority and effectiveness of the proposed method.

A New Individual Tree Species Recognition Method Based on a Convolutional Neural Network and High-Spatial Resolution Remote Sensing Imagery

Tree species surveys are crucial to forest resource management and can provide references for forest protection policy making. The traditional tree species survey in the field is labor-intensive and time-consuming, supporting the practical significance of remote sensing. The availability of high-resolution satellite remote sensing data enable individual tree species (ITS) recognition at low cost. In this study, the potential of the combination of such images and a convolutional neural network (CNN) to recognize ITS was explored. Firstly, individual tree crowns were delineated from a high-spatial resolution WorldView-3 (WV3) image and manually labeled as different tree species. Next, a dataset of the image subsets of the labeled individual tree crowns was built, and several CNN models were trained based on the dataset for ITS recognition. The models were then applied to the WV3 image. The results show that the distribution maps of six ITS offered an overall accuracy of 82.7% and a kappa coefficient of 0.79 based on the modified GoogLeNet, which used the multi-scale convolution kernel to extract features of the tree crown samples and was modified for small-scale samples. The ITS recognition method proposed in this study, with multi-scale individual tree crown delineation, avoids artificial tree crown delineation. Compared with the random forest (RF) and support vector machine (SVM) approaches, this method can automatically extract features and outperform RF and SVM in the classification of six tree species.

RSNet: The Search for Remote Sensing Deep Neural Networks in Recognition Tasks

Deep learning algorithms, especially convolutional neural networks (CNNs), have recently emerged as a dominant paradigm for high spatial resolution remote sensing (HRS) image recognition. A large amount of CNNs have already been successfully applied to various HRS recognition tasks, such as land-cover classification and scene classification. However, they are often modifications of the existing CNNs derived from natural image processing, in which the network architecture is inherited without consideration of the complexity and specificity of HRS images. In this article, the remote sensing deep neural network (RSNet) framework is proposed using an automatically search strategy to find the appropriate network architecture for HRS image recognition tasks. In RSNet, the hierarchical search space is first designed to include module- and transition-level spaces. The module-level space defines the basic structure block, where a series of lightweight operations as candidates, including depthwise separable convolutions, is proposed to ensure the efficiency. The transition-level space controls the spatial resolution transformations of the features. In the hierarchical search space, a gradient-based search strategy is used to find the appropriate architecture. In RSNet, the task-driven architecture training process can acquire the optimal model parameters of the switchable recognition module for HRS image recognition tasks. The experimental results obtained using four benchmark data sets for land-cover classification and scene classification tasks demonstrate that the searched RSNet can achieve a satisfactory accuracy with a high computational efficiency and, hence, provides an effective option for the processing of HRS imagery.

Delineating Mixed Urban “Jobs-Housing” Patterns at a Fine Scale by Using High Spatial Resolution Remote-Sensing Imagery

The spatial distribution pattern of jobs and housing plays a vital role in urban planning and traffic construction. However, obtaining the jobs-housing distribution at a fine scale (e.g., the perspective of individual jobs-housing attribute) presents difficulties due to a lack of social media data and useful models. With user data acquired from a location-based service provider in China, this study employs a deep bag-of-features network (BagNet) to classify remote-sensing (RS) images into various jobs-housing types. Considering Wuhan, one of the fastest developing cities in China, as a case study area, three jobs-housing types (i.e., only working, only living, and both working and living) at the land-parcel level are obtained. We demonstrate that the multiscale random sampling method can reduce the influence of image noise, increase the utilization of training data, and reduce network overfitting. By altering the network structure and the training strategy, BagNet achieved excellent fitting accuracy for identifying each jobs-housing type (overall accuracy > 0.84 and kappa > 0.8). For the first time, we demonstrate that urban socioeconomic characteristics can be obtained from high-resolution RS images using deep learning techniques. Additionally, we conclude that the total level of mixing within Wuhan is not high at present; however, Wuhan is continuously improving the mixture of jobs and housing. This study has reference value for extracting urban socioeconomic characteristics from RS images and could be used in urban planning as well as government management.

Scene classification based on the bag-of-visual-words and Doc2Vec models for high-spatial resolution remote-sensing imagery

A probabilistic topic model (PTM) combined with the bag-of-visual-words model is a common method to bridge the so-called “semantic gap” problem in remote-sensing image classification research. Owing to the inherent shortcomings of PTMs, such as time consumption and failures to consider a spatial arrangement of various objects, we introduce a natural language processing document-to-vector (Doc2Vec) model, to capture the high-level semantic information of the images, instead of a PTM. The model characterizes words and documents as dense, low-dimensional vectors and implements a simplified, shallow neural network to train a language model and word vectors. It is expected to mine semantic information of remote-sensing images from a new perspective. We also improve the low-level feature quality by using feature-specific sampling methods. Two high-spatial resolution remote-sensing image datasets, UC Merced and RSSCN7, are employed to conduct a scene classification experiment to discuss the performance of the Doc2Vec model. The experimental results show that the Doc2Vec model is highly efficient in mining semantic information of the images, compared with the state-of-the-art methods.

An adaptive scale estimating method of multiscale image segmentation based on vector edge and spectral statistics information

ABSTRACTScale computation for multiscale image segmentation has become one of the key scientific problems in urgent need to be solved in the field of geographic object-based image analysis (GEOBIA). Due to the complexity of High Spatial Resolution Remote-Sensing Imagery (HSRRSI) data itself and the scale distribution differences among geographic features, it is difficult to effectively design a global scale parameter model to guide parameters setting in large scale regions and automatically produce an acceptable segmentation result simultaneously. Utilizing the vector edge and spectral statistics information, an adaptively global scale computation method named Global Scale Computation with Vector Edge (GSCVE) has been developed for multiscale segmentation, which is firstly proposed and implemented on mean-shift segmentation algorithm as an example. The highlight of the GSCVE algorithm is that it can calculate global scale parameters for multiscale image segmentation adaptively. The validity of GSCVE algorithm was verified directly by taking GeoEye and QuickBird images as segmentation experiments sample data, respectively. In addition, comparing with the renowned eCognition® multiscale segmentation algorithm, the relative advantages of GSCVE algorithm with adaptive property and the concurrence segmentation results of large and small scale geographic features are illustrated by the visual evaluation experiments simultaneously.

A Sparse Dictionary Learning-Based Adaptive Patch Inpainting Method for Thick Clouds Removal from High-Spatial Resolution Remote Sensing Imagery.

Cloud cover is inevitable in optical remote sensing (RS) imagery on account of the influence of observation conditions, which limits the availability of RS data. Therefore, it is of great significance to be able to reconstruct the cloud-contaminated ground information. This paper presents a sparse dictionary learning-based image inpainting method for adaptively recovering the missing information corrupted by thick clouds patch-by-patch. A feature dictionary was learned from exemplars in the cloud-free regions, which was later utilized to infer the missing patches via sparse representation. To maintain the coherence of structures, structure sparsity was brought in to encourage first filling-in of missing patches on image structures. The optimization model of patch inpainting was formulated under the adaptive neighborhood-consistency constraint, which was solved by a modified orthogonal matching pursuit (OMP) algorithm. In light of these ideas, the thick-cloud removal scheme was designed and applied to images with simulated and true clouds. Comparisons and experiments show that our method can not only keep structures and textures consistent with the surrounding ground information, but also yield rare smoothing effect and block effect, which is more suitable for the removal of clouds from high-spatial resolution RS imagery with salient structures and abundant textured features.

SVM-based soft classification of urban tree species using very high-spatial resolution remote-sensing imagery

ABSTRACTClassification from remote-sensing data has proved to be fast and effective for mapping tree species. However, the interference from background noise and the weak spectral separability among most tree species have negative impacts on classification accuracy and may make conventional classification methods inappropriate. To solve this problem, a soft classification approach is presented. It consists of the technologies of soft partition, defuzzifying, and feature-location analyses (referred to here as F-L analyses). The soft partition is conducted by combined binary support vector machines, enabling a natural prototype of fuzzy clusters to be formed. Unsure members (members means both patches and pixels) in the clustering prototype can be defuzzified afterwards. F-L analyses run through the entire process in two ways: (1) by adding density description to feature space for classification and (2) through density-constrained defuzzifying. The former can enrich the feature space, thus making the soft partition perform better. By using the latter, the credibility of a class label is indicated by several weighted fuzzy measures in the form of hierarchical densities, thereby reducing the uncertainty of the defuzzifying. Experiments indicate that only 63% of members on average are surely allocated in a clustering prototype and the remainder can be ensured by the explored defuzzifying approach. The mean overall accuracy (OA) of the defuzzified members is very close to that of the originally allocated sure ones. A comparative assessment shows that the mean OA and mean kappa statistic value of members defuzzified using the explored fuzzy measure are, on average, 3.84 and 4.89% respectively higher than those using conventional maximum membership measures. Experiments also show that the former is superior to the latter in regard to the formation of complete tree crown objects.

A Comparative Study of Sampling Analysis in the Scene Classification of Optical High-Spatial Resolution Remote Sensing Imagery

Scene classification, which consists of assigning images with semantic labels by exploiting the local spatial arrangements and structural patterns inside tiled regions, is a key problem in the automatic interpretation of optical high-spatial resolution remote sensing imagery. Many state-of-the-art methods, e.g., the bag-of-visual-words model and its variants, the topic models and unsupervised feature learning-based approaches, share similar procedures: patch sampling, feature learning and classification. Patch sampling is the first and a key procedure, and it has a considerable influence on the results. In the literature, many different sampling strategies have been used, e.g., random sampling and saliency-based sampling. However, the sampling strategy that is most suitable for the scene classification of optical high-spatial resolution remote sensing images remains unclear. In this paper, we comparatively study the effects of different sampling strategies under the scenario of scene classification of optical high-spatial resolution remote sensing images. We divide the existing sampling methods into two types: random sampling and saliency-based sampling. Here, we consider the commonly-used grid sampling to be a specific type of random sampling method, and the saliency-based sampling consists of keypoint-based sampling and salient region-based sampling. To compare their performances, we rely on a standard bag-of-visual-words model to learn the global features for testing because of its simplicity, robustness and efficiency. In addition, we conduct experiments using a Fisher kernel framework to validate our conclusions. The experimental results obtained on two commonly-used datasets using different feature learning methods show that random sampling can provide comparable and even better performance than all of the saliency-based strategies.

Multiagent Object-Based Classifier for High Spatial Resolution Imagery

Object-based classification, including object-based segmentation and classification, has been applied for the classification of high spatial resolution imagery due to the increase in the spatial resolution and the limited spectral resolution. Because of the independent design of the object-based segmentation and classification in many of the traditional object-based classification methods, additional work is required to select the appropriate segmentation algorithms to match the classification algorithms. The object-based segmentation algorithms, e.g., the fractal net evolution approach (FNEA), have been successfully utilized to provide the homogeneous regions, and are the basis of object-based classification. However, the traditional FNEA algorithm is greatly influenced by the global control strategy of the region-growing procedure. In addition, the existing object classification methods take little account of the object context information, which is important for high spatial-resolution image interpretation. To improve the accuracy of the object-based classification, in this paper, a multiagent object-based classification framework (MAOCF) for high-resolution remote sensing imagery is proposed. The proposed approach avoids the issue of segmentation algorithm selection by unifying the processing of object-based segmentation and classification through the use of a 4-tuple agent model. In the uniform framework, a multiagent object-based segmentation (MAOS) algorithm is proposed to optimally control the procedure of object merging. In addition, a MAOC is proposed to utilize the contextual information from the surrounding objects by taking advantage of the benefits of a multiagent system, e.g., strong interaction, high flexibility, and parallel global control capability. Due to the characteristics of a multiagent system, MAOCF has the potential for a parallel computing ability. Three experiments with different types of images were performed to evaluate the performance of MAOS and MAOC in comparison to other segmentation and classification algorithms: 1) mean-shift segmentation; 2) FNEA; 3) recursive hierarchical segmentation; and 4) the majority voting object-based classification method. The experimental results demonstrate that MAOS and MAOC give a stable performance with high spatial resolution remote-sensing imagery, and are competitive with the other methods.

An Energy-Driven Total Variation Model for Segmentation and Classification of High Spatial Resolution Remote-Sensing Imagery

An energy-driven total variation (TV) formulation is proposed for the segmentation of high spatial resolution remote-sensing imagery. The TV model is an effective tool for image processing operations such as restoration, enhancement, reconstruction, and diffusion. Due to the relationship between the TV model and the segmentation problem, in this letter, a TV-based approach is investigated for segmentation of high-spatial-resolution remote-sensing imagery. Subsequently, an object-based classification method, i.e., majority voting, is used to classify the segmented results. In experiments, the proposed TV-based method is compared with the widely used fractal net evolution approach and the clustering segmentation methods such as the expectation–maximization and $k$ -means. The performances of the segmentation and the classification are evaluated based on both thematic and geometric indices.