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.

Deep convolutional neural networks (CNNs) have gotten a lot of press in the last several years, especially in domains like computer vision (CV) and remote sensing (RS). However, achieving superior performance with deep networks highly depends on a massive amount of accurately labeled training samples. In real-world applications, gathering a large number of labeled samples is time-consuming and labor-intensive, especially for pixel-level data annotation. This dearth of labels in land-cover classification is especially pressing in the RS domain because high-precision, high-quality labeled samples are extremely difficult to acquire, but unlabeled data is readily available. In this study, we offer a new semi-supervised deep semantic labeling framework for semantic segmentation of high-resolution RS images to take advantage of the limited amount of labeled examples and numerous unlabeled samples. Our model uses transformation consistency regularization (TCR) to encourage consistent network predictions under different random transformations or perturbations. We try three different transforms to compute the consistency loss and analyze their performance. Then, we present a deep semi-supervised semantic labeling technique by using a hybrid transformation consistency regularization (HTCR). A weighted sum of losses, which contains a supervised term computed on labeled samples and an unsupervised regularization term computed on unlabeled data, may be used to update the network parameters in our technique. Our comprehensive experiments on two RS datasets confirmed that the suggested approach utilized latent information from unlabeled samples to obtain more precise predictions and outperformed existing semi-supervised algorithms in terms of performance. Our experiments further demonstrated that our semi-supervised semantic labeling strategy has the potential to partially tackle the problem of limited labeled samples for high-resolution RS image land-cover segmentation.

Clouds inevitably exist in satellite images, which limits the processing and application of satellite images to a certain extent. Therefore, cloud detection is a preprocessing task in satellite image extraction and analysis processing. However, the existing methods are difficult to mine robust features, and the number of parameters and computation is large, which is not conducive to the deployment of the model. In this letter, CloudViT, a lightweight vision transformer network for cloud detection from satellite imagery, is proposed. In detail, to utilize dark channel priors in multispectral imagery to guide the network to learn features, a multi-scale dark channel extractor is used to first predict dark channels, and then the dark channel features and image features are input to the attention mechanism-based dark channel-guided context aggregation module to enhance image features, which in turn makes cloud detection results more accurate. At the same time, to enhance the transfer ability of the network between different satellite sensors, a plug-and-play channel adaptive module is proposed to deal with the inconsistency of the number of different satellite sensor bands. Experimental results on the Landsat7 dataset show that our network CloudViT outperforms state-of-the-art methods while keeping the number of parameters and computation small. At the same time, the experimental results on transfer to three other datasets show that using the channel adaptation module can greatly improve the transfer ability of the model.

Multimodal image registration is critical yet challenging for remote sensing image processing. Due to the large nonlinear intensity differences between the multimodal images, conventional search algorithms tend to get trapped into local optima when optimizing the transformation parameters by maximizing mutual information (MI). To address this problem, inspired by transfer learning, we propose a novel search algorithm named transfer optimization (TO), which can be applied to any optimizer. In TO, an optimizer transfers its better individuals to the other optimizer in each iteration. Thus, TO can share information between two optimizers and take advantage of their search mechanisms, which is helpful to avoid the local optima. Then, the registration of the multimodal remote sensing images using TO is presented. We compare the proposed algorithm with several state-of-the-art algorithms on real and simulated image pairs. Experimental results demonstrate the superiority of our algorithm in terms of registration accuracy.

Semantic segmentation for high-resolution remote sensing imagery is a pivotal component of land use and land cover categorization, and height estimation is essential for rebuilding the 3D information of an image. Because of the higher intra-class variation and smaller inter-class dissimilarity, these two challenging tasks are generally treated separately. This paper proposes a fully convolutional network that can tackle these problems simultaneously by estimating the land-cover categories and height values of pixels from a single aerial image. To handle these tasks, we develop a multi-task learning architecture (JSH-Net) that employs a shared feature representation and exploits their potential consistency across tasks, resulting in robust features and better prediction accuracy. Specifically, we propose a novel skip connection module that aggregates the contexts from the encoder part to the decoder part, bridging the semantic gap between them. In addition, we propose a progressive refinement strategy to recover detailed information about the objects. Moreover, we also proposed a height estimation branch on the head of the model to utilize shared features. The experiments we conducted on ISPRS 2D Labelling dataset verified that our network provided precise results of semantic segmentation and height estimation from two output branches and outperformed other state-of-the-art approaches.