Change detection based on remote sensing images plays an important role in the field of remote sensing analysis, and it has been widely used in many areas, such as resources monitoring, urban planning, disaster assessment, etc. In recent years, it has aroused widespread interest due to the explosive development of artificial intelligence (AI) technology, and change detection algorithms based on deep learning frameworks have made it possible to detect more delicate changes (such as the alteration of small buildings) with the help of huge amounts of remote sensing data, especially high-resolution (HR) data. Although there are many methods, we still lack a deep review of the recent progress concerning the latest deep learning methods in change detection. To this end, the main purpose of this paper is to provide a review of the available deep learning-based change detection algorithms using HR remote sensing images. The paper first describes the change detection framework and classifies the methods from the perspective of the deep network architectures adopted. Then, we review the latest progress in the application of deep learning in various granularity structures for change detection. Further, the paper provides a summary of HR datasets derived from different sensors, along with information related to change detection, for the potential use of researchers. Simultaneously, representative evaluation metrics for this task are investigated. Finally, a conclusion of the challenges for change detection using HR remote sensing images, which must be dealt with in order to improve the model’s performance, is presented. In addition, we put forward promising directions for future research in this area.

In recent years, building change detection has made remarkable progress through using deep learning. The core problems of this technique are the need for additional data (e.g., Lidar or semantic labels) and the difficulty in extracting sufficient features. In this paper, we propose an end-to-end network, called the pyramid feature-based attention-guided Siamese network (PGA-SiamNet), to solve these problems. The network is trained to capture possible changes using a convolutional neural network in a pyramid. It emphasizes the importance of correlation among the input feature pairs by introducing a global co-attention mechanism. Furthermore, we effectively improved the long-range dependencies of the features by utilizing various attention mechanisms and then aggregating the features of the low-level and co-attention level; this helps to obtain richer object information. Finally, we evaluated our method with a publicly available dataset (WHU) building dataset and a new dataset (EV-CD) building dataset. The experiments demonstrate that the proposed method is effective for building change detection and outperforms the existing state-of-the-art methods on high-resolution remote sensing orthoimages in various metrics.

The accurate matching of multisource, multi-temporal remote sensing images is challenging because of significant nonlinear intensity differences (NIDs) and severe geometric distortions. To address these problems, we developed a robust image matching method: oriented filter-based matching (OFM). OFM is insensitive to NIDs, while exhibiting scale and rotational invariance. First, salient feature points with multiscale attributes were detected in the Gaussian-scale space of the input images. Then, the images were convoluted using multi-oriented filters, and unified feature maps were constructed by the extraction of orientation indices using effective data pooling operations. The constructed feature maps were highly resistant to NIDs. Five filters were integrated into the OFM framework to investigate their applicabilities in different application scenarios. Next, a novel rotation-invariant feature descriptor was constructed, using a dominant direction determination approach and a descriptor-grouping strategy. The dominant direction determination approach enables accurate dominant direction estimation, whereas the descriptor-grouping strategy improves the stability of the method under different rotational angles. Finally, brute-force matching was implemented to obtain initial matches; an improved mismatch elimination method was used to identify reliable putative matches. To evaluate the performance of OFM, we created a large dataset comprising 4,427 pairs of multitemporal optical–optical, optical–synthetic aperture radar (SAR), optical–infrared, and optical–depth images. OFM outperformed state-of-the-art methods in terms of number of correct matches, recall, inlier ratio, root mean square error and success rate. Our implement is publicly available ¹ .

Automatic extraction of region objects from high-resolution satellite imagery presents a great challenge, because there may be very large variations of the objects in terms of their size, texture, shape, and contextual complexity in the image. To handle these issues, we present a novel, deep-learning-based approach to interactively extract non-artificial region objects, such as water bodies, woodland, farmland, etc., from high-resolution satellite imagery. First, our algorithm transforms user-provided positive and negative clicks or scribbles into guidance maps, which consist of a relevance map modified from Euclidean distance maps, two geodesic distance maps (for positive and negative, respectively), and a sampling map. Then, feature maps are extracted by applying a VGG convolutional neural network pre-trained on the ImageNet dataset to the image X, and they are then upsampled to the resolution of X. Image X, guidance maps, and feature maps are integrated as the input tensor. We feed the proposed attention-guided, multi-scale segmentation neural network (AGMSSeg-Net) with the input tensor above to obtain the mask that assigns a binary label to each pixel. After a post-processing operation based on a fully connected Conditional Random Field (CRF), we extract the selected object boundary from the segmentation result. Experiments were conducted on two typical datasets with diverse region object types from complex scenes. The results demonstrate the effectiveness of the proposed method, and our approach outperforms existing methods for interactive image segmentation.

Building subclass segmentation, aimed at predicting classes of buildings (high-rise zone, low-rise zone, single high-rise, and single low-rise) from satellite images, is beneficial in numerous applications, including human geography, urban planning, and humanitarian aid. However, problems, such as complex scenes and similar characteristics of different building categories make it difficult for general models to balance the accuracy of localization and classification in building subclass segmentation. Therefore, this article proposes a novel network for building subclass segmentation called building subclass segmentation network (BSSNet), which uses two subnetworks to divide and conquer the problem. The first network guides the building locations through binary building segmentation, called localization network. The spatial gradient fusion module in the localization network improves the binary segmentation result by supervising the spatial gradient map of prediction. The second network is a classification network, which predicts building subclasses. Intermediate features of the second network are optimized by contrastive learning loss to improve feature consistency. Finally, predictions of the two networks are combined to obtain the final result. The experimental results demonstrate that our BSSNet can perform significant improvements on the Hainan dataset we produced and the xBD dataset. In particular, the BSSNet achieves the best performance compared to current methods on the Hainan dataset.

Highway markings (HMs) are representative elements of inventory digitalization in highway scenes. The accurate position, semantics, and maintenance information of HMs provide significant support for the intelligent management of highways. This article presents a robust and efficient approach for extracting, reconstructing, and degrading analyzing HMs in complex highway scenes. Compared with existing road marking extraction methods, not only can extract HMs in presence of wear and occlusion from point clouds, but we also perform a degradation analysis for HMs. First, the HMs candidate area is determined accurately by sophisticated image processing. Second, the prior knowledge of marking design rules and edge-based matching model that leverages the standard geometric template and radiometric appearance of HMs is used for accurately extracting and reconstructing solid lines and nonsolid markings of HMs, respectively. Finally, two degradation indicators are constructed to describe the completeness of the marking contour and consistency within the marking. Comprehensive experiments on two existing highways revealed that the proposed methods achieved an overall performance of 95.4% and 95.4% in the recall and 93.8% and 95.5% in the precision for solid line and nonsolid line markings, respectively, even with imperfect data. Meanwhile, a database can be established to facilitate agencies' efficient maintenance.