With the growing spatial resolution of satellite images, high spatial resolution (HSR) remote sensing imagery scene classification has become a challenging task due to the highly complex geometrical structures and spatial patterns in HSR imagery. The key issue in scene classification is how to understand the semantic content of the images effectively, and researchers have been looking for ways to improve the process. Convolutional neural networks (CNNs), which have achieved amazing results in natural image classification, were introduced for remote sensing image scene classification. Most of the researches to date have improved the final classification accuracy by merging the features of CNNs. However, the entire models become relatively complex and cannot extract more effective features. To solve this problem, in this paper, we propose a lightweight and effective CNN which is capable of maintaining high accuracy. We use MobileNet V2 as a base network and introduce the dilated convolution and channel attention to extract discriminative features. To improve the performance of the CNN further, we also propose a multidilation pooling module to extract multiscale features. Experiments are performed on six datasets, and the results verify that our method can achieve higher accuracy compared to the current state-of-the-art methods.

Landscape mapping and pattern analysis of fine-grained urban functional zones (UFZ) are of great research value in the field of urban planning and urban development assessment. Previous studies employing multispectral images have largely enabled only coarse-grained land-use classification of urban areas. By contrast, hyperspectral images can provide very detailed spectral features and have shown some potential to facilitate fine-grained classification of urban areas. In this article, we evaluate and analyze the classification of fine-grained UFZ in the central city of Wuhan, Hubei, China, using GaoFen-5 (GF-5) hyperspectral satellite imagery. We first compare the performance of hyperspectral data (GF-5) and classical multispectral data (Landsat 8) for the classification of fine-grained functional zones of cities by employing two classical classification algorithms and two deep learning methods. We also propose the deep learning-based spectral-spatial unified networks combined with a fully connected conditional random field (SSUN-CRF) algorithm for fine-grained UFZ mapping to enable better landscape pattern analysis. We then analyze the landscape pattern of the main urban areas of Wuhan by combining ten landscape indicators based on the precise UFZ classification results. Experimental results illustrate the followings. First, compared to multispectral images, hyperspectral images can allow for a more accurate UFZ classification. Second, deep learning classification algorithms can better exploit hyperspectral image data, with the SSUN-CRF algorithm, in particular, being able to achieve an overall accuracy of 93.86% and a Kappa coefficient of 92.08%. Finally, the landscape pattern analysis demonstrates that hyperspectral remote sensing imagery shows significant potential in mapping fine-grained UFZ. It is beneficial for further urban study and planning.

Over the past decade, many excellent data sharing efforts have enriched the remote sensing scene classification (SC) methods. These datasets have achieved great success in complex high-level semantic information interpretation. However, most existing datasets are collected from standard and ungeoreferenced image patches for algorithm training and evaluation. These datasets do not fit for practical applications and cannot be directly applied in further geographical study. Accordingly, we provide a large range high-resolution SC dataset with multiple time phases, called “ W u h an M ulti a pplication V HR S cene classification dataset (WH-MAVS).” It facilitates the study of SC and scene change detection (SCD) algorithms. Moreover, it can also be directly employed to perform a variety of real-life land use application tasks. To the best of our knowledge, this is the first free, publicly available, georeferenced, and annotated dataset to cover almost an entire megacity. The WH-MAVS was collected and annotated from Google Earth imagery with the same spatial resolution and uniform nonoverlapping patch size, covering the central area of Wuhan, China. The total number of scene samples is 47 137, which belong to 14 classes with 23 567 labeled patches for each time phase in 2014 and 2016, respectively. The geographic coordinates of all samples in both time phases exhibit one-to-one correspondence with 23 202 unchanged image patches of scene categories and 365 changed ones. The distribution of the number of samples in each class is highly imbalanced; moreover, there are large intraclass differences and indistinguishable interclass variances. These characteristics are closer to the real land use/land cover application tasks and introduce further challenges to the related algorithm research. In addition, we conducted benchmark experiments on SC and SCD based on the WH-MAVS dataset with widely used deep learning models. DenseNet169 was found to achieve the best performance. The overall accuracies are 91.07% and 92.09%, respectively, in the 2014 and 2016 validation sets of WH-MAVS. Furthermore, SCD obtained by DenseNet169 has a binary change detection accuracy of 89.56% and a multiple (from–to) change detection accuracy of 86.70%. Over and above the research value of the algorithm, it is also proven to have practical applications in fields such as urban planning, landscape pattern analysis, and urban dynamic monitoring and analysis.

Automatic image registration (AIR) has been widely studied in the fields of medical imaging, computer vision, and remote sensing. In various cases, such as image fusion, high registration accuracy should be achieved to meet application requirements. For satellite images, the large image size and unstable positioning accuracy resulting from the limited manufacturing technology of charge-coupled device, focal plane distortion, and unrecorded spacecraft jitter lead to difficulty in obtaining agreeable corresponding points for registration using only area-based matching or feature-based matching. In this situation, a coarse-to-fine matching strategy integrating two types of algorithms is proven feasible and effective. In this paper, an AIR method for application to the fusion of ZY-1-02C satellite imagery is proposed. First, the images are geometrically corrected. Coarse matching, based on scale invariant feature transform, is performed for the subsampled corrected images, and a rough global estimation is made with the matching results. Harris feature points are then extracted, and the coordinates of the corresponding points are calculated according to the global estimation results. Precise matching is conducted, based on normalized cross correlation and least squares matching. As complex image distortion cannot be precisely estimated, a local estimation using the structure of triangulated irregular network is applied to eliminate the false matches. Finally, image resampling is conducted, based on local affine transformation, to achieve high-precision registration. Experiments with ZY-1-02C datasets demonstrate that the accuracy of the proposed method meets the requirements of fusion application, and its efficiency is also suitable for the commercial operation of the automatic satellite data process system.

In this paper, shadow detection and compensation are treated as image enhancement tasks. The principal components analysis (PCA) and luminance based multi-scale Retinex (LMSR) algorithm are explored to detect and compensate shadow in high resolution satellite image. PCA provides orthogonally channels, thus allow the color to remain stable despite the modification of luminance. Firstly, the PCA transform is used to obtain the luminance channel, which enables us to detect shadow regions using histogram threshold technique. After detection, the LMSR technique is used to enhance the image only in luminance channel to compensate for shadows. Then the enhanced image is obtained by inverse transform of PCA. The final shadow compensation image is obtained by comparison of the original image, the enhanced image and the shadow detection image. Experiment results show the effectiveness of the proposed method.

Convolutional neural networks (CNNs) have made significant advances in remote sensing scene classification (RSSC) in recent years. Nevertheless, the limitations of the receptive field cause CNNs to suffer from a disadvantage in capturing contextual information. To address this issue, vision transformer (ViT), a novel model that has piqued the interest of academics, is used to extract latent contextual information in remote sensing scene classification. However, when confronted with the challenges of large-scale variations and high interclass similarity in scene classification images, the original ViT has the drawback of ignoring important local features, thereby causing the model’s performance to degrade. Consequently, we propose the hierarchical contextual feature-preserved network (HCFPN) by combining the advantages of CNNs and ViT. First, a hierarchical feature extraction module based on ResNet-34 is utilized to acquire the multilevel convolutional features and high-level semantic features. Second, a contextual feature-preserved module takes advantage of the first two multilevel features to capture abundant long-term contextual features. Then, the captured long-term contextual features are utilized for multiheaded cross-level attention computing to aggregate and explore the correlation of multilevel features. Finally, the multiheaded cross-level attention score and high-level semantic features are classified. Then, a category score average module is proposed to fuse the classification results, whereas a label smoothing approach is utilized prior to calculating the loss to produce discriminative scene representation. In addition, we conduct extensive experiments on two publicly available RSSC datasets. Our proposed HCPFN outperforms most state-of-the-art approaches.