The detection and recognition of ships hold significant practical implications for both military and civilian departments. Recent advancements in deep learning technology have led to notable progress in this field. However, the precise detection and recognition of ships remains a challenge, especially in multi-source remote sensing images, due to their different feature expression and resolution. Moreover, the effectiveness of the existing models in complex environments still needs to be further validated. Therefore, in this letter, we construct a new ship dataset which contains five distinct ship categories under a number of complex environments. Different from existing datasets that are based on unimodal data, the new dataset uses multi-modal remote sensing images with different resolutions. On this basis, this study introduces an adaptable and robust ship detection and recognition model, namely SIDE-YOLO. The model incorporates an super-resolution convolutional neural network (SRCNN) and side window (SRSW) based contour feature enhancement module, a SimAM feature attention Resblock (ResBlockSA), and a DConv-based cross-scale feature enhancement block (DCFB), to strengthen the ship edge features, adaptively improve the problem of limited sample in SAR images, and amalgamate multi-scale ship context information, respectively. Validation results demonstrate that the proposed model achieves an average precision (AP) rate [mean AP (mAP)] of 84.31%, surpassing state-of-the-art ship recognition models. Notably, for the civilian ship category, the model exhibits 2.17% and 2.63% higher recall and AP in complex scenes, respectively.

Multi-modal remote sensing images (MRSI) often suffer from severe nonlinear radiation distortions (NRD) and significant geometric distortions, making precise matching challenging. We developed a feature-based matching algorithm to address this issue using edge consistency scale-space and significant relative response (ECSS). By designing an edge consistency filtering (ECF), we construct a scale space that preserves the structural information of MRSI at various scales, enhancing scale invariance. ECSS computes feature descriptors using multi-orientation filtering techniques to construct significant relative responses. This approach not only resists NRD but also utilizes information from all directional filters to build descriptors with higher discriminative power compared to direct filter responses or the maximum index map (MIM). To ensure rotational invariance, ECSS employs a robust technique for estimating the primary orientation. To further optimize matching accuracy and increase the number of effective matching points, ECSS uses a coarse-to-fine matching strategy. This involves using preliminary matching results to estimate the affine transformation between images, which then guides a more refined secondary matching. We evaluated the performance of ECSS on five different MRSI datasets and compared the results with nine state-of-the-art matching methods: ReDFeat, MINIMA-LG, RIFT, MS-HLMO, SRIF, WSSF, POS-GIFT, OFM, and GLS-MIFT. The experimental results demonstrate that ECSS excels in all performance metrics, particularly in terms of stability and matching accuracy when handling MRSI data with high NRD and complex geometric transformations.

Digital Surface Models (DSMs) extracted from multi-view satellite images have extensive applications in the filed of photogrammetry. Although Neural Radiance Fields (NeRF) has shown significant potential in 3D reconstruction, most existing NeRF methods for satellite scenes adopt an end-to-end single-branch network structure, making it difficult to achieve fine-grained modeling of multiple complex terrain simultaneously, and performs poorly in weak-texture regions. Meanwhile, deep MLP structures are prone to information degradation during feature transmission, further affecting the completeness and accuracy of DSMs. To address these challenges, we propose RDS-NeRF, a novel NeRF framework integrating residual feature enhancement and depth supervision. The method introduces a residual feature enhancement structure to alleviate the problem of information degradation during feature transmission in the network and improve the model’s ability to model local details and low-texture regions. Additionally, estimated depth maps are incorporated as global geometric priors to guide the network in constructing more accurate and complete 3D structures. Experiments on the WorldView-3 satellite imagery datasets across multiple typical land cover types (building, road, water body, and vegetation) and complex scenes integrating multiple land features demonstrate that RDS-NeRF outperforms mainstream methods in terms of DSM accuracy, completeness, and novel view synthesis quality. Ablation experiments further validate the complementarity and effectiveness of the residual enhancement and depth supervision mechanisms across different scene types. In conclusion, RDS-NeRF provides a new and effective solution for generating high-quality DSMs from satellite imagery with adaptability to multiple scenes. Code will be available at https://github.com/dfsvdgf/RDS-NeRF.

Conventional pixel-level seamline detection algorithms exhibit exponential time complexity on large, batch-mode remote-sensing mosaics, making it difficult to achieve an optimal trade-off between accuracy and efficiency. This paper introduces a globally optimal and highly efficient seamline detection framework. First, a preliminary seamline network is generated by iteratively clipping valid orthoimage regions with a Voronoi diagram, and image blocks are extracted only within overlap areas to markedly reduce data volume. Second, a cost graph constructed on down-sampled blocks is traversed in a reverse-diagonal Z-pattern; a “local entropy–gradient” composite cost function is applied, and a linear-time dynamic-programming (DP) scheme rapidly produces coarse seamlines that bypass texture-rich regions and confine the search space to a narrow band. Third, a buffer centered on the coarse seamline is created, within which an enhanced Dijkstra algorithm performs pixel-level refinement to accurately avoid complex obstacles. Experiments on the GF-7 data set demonstrate that, compared with five representative methods—SMP-DP, A*, Dijkstra, graph-cut, and OrthoVista—the proposed approach improves geometric accuracy by 14.46%, 58.69%, 50.20%, 17.79%, and 69.30%, respectively; processing efficiency is increased by 12.74%, 19.19%, 49.89%, >500%, and 83.72%, respectively. The algorithm has successfully mosaicked 627 GF-7 scenes covering the entire Henan Province, and has yielded similarly favorable results on ZY-3, GF-1 and GF-3 imagery, underscoring its high applicability and robustness for multi-source, large-format remote-sensing production.

Highway crack segmentation is a critical task for highway infrastructure monitoring and maintenance. While imagery from unmanned aerial vehicles (UAVs) is applied to the task of highway crack segmentation, it has great prospects in terms of speed and range. However, it is difficult to accurately identify road cracks from UAV remote sensing images, because the cracks are very narrow and small, often containing only a few pixels. To improve the segmentation of road cracks in UAV images, this study proposed an improved identification technique based on the U-Net architecture enhanced with a convolutional block attention module, an improved encoder, and the strategy of fusing long and short skip connections. A public road crack dataset was relabelled for network training and a UAV remote sensing road crack dataset containing 1157 images was used to verify the generalization ability of the enhanced network model. Results showed that the proposed method could effectively predict highway cracks in UAV images, with mean intersection over union (mIoU) of 77.47% and crack accuracy of 68.38%, which was better than the traditional U-Net model and some traditional semantic segmentation models. The proposed network is trained quickly by public dataset and can predict the road cracks on the new UAV images with high crack accuracy. This study provides an effective solution for the need to quickly grasp the damage status of roads over a wide area in the case of earthquake and other natural disasters. The highway crack segmentation benchmark dataset has been open sourced at:https://github.com/zhhongsh/UAV-Benchmark-Dataset-for-Highway-Crack-Segmentation.

Accurate land use/land cover (LULC) mapping over a large area is essential to environmentally sustainable development. Recently, the Chinese government established a new national economic zone called the Xiongan New Area, and along with the upcoming large-scale urban construction, this area will inevitably experience a dramatic LULC change, which will threaten the local ecological balance. In this article, we proposed a two-stage approach for LULC mapping in the Xiongan New Area ahead of the forthcoming dense urban construction. The first stage is to obtain base-class maps through a supervised imagery classification. Specifically, we designed a new object-based framework consisting of automatic image segmentation, pixel-based probabilistic estimation, and area-weighted probability statistics for Sentinel-2 multiresolution imagery classification. The second stage is an LULC map refinement process in which the temporal features of each land use category are extracted to refine the LULC classification. Through the implementation of the proposed two-stage approach, an LULC map containing permanent water, temporal water, natural vegetation, barren land, built-up land, and cropland categories can be produced. Through an accuracy assessment, the proposed multiresolution imagery classification method achieved the highest overall accuracy of 88.58% and an average accuracy (AA) of 87.78% compared with conventional classification methods. After obtaining the refined LULC map, we find that the current Xiongan New Area is in a less developed state, that is, cropland accounts for the highest proportion of 51.59%, which is followed by natural vegetation (22.38%) and built-up land (15.69%).

The machine learning algorithm support high efficiency in urban surface mapping based on the moderate resolution and multispectral satellite imagery. In this study, we evaluate eight widely used machine learning-based classification methods. For the specific modality of the moderate resolution and multispectral satellite imagery, nevertheless, even though many labeled datasets target for kinds of remote sensing applications are built recently, the labeled data for the moderate-resolution and multispectral image is still lacked currently. In this study, we carried out a moderate-resolution and multispectral images labeling work in two urban regions, and four-class urban surface and six-class urban surface in terms of the bio-physical and land use are labeled, respectively. Based on the labeled dataset, eight widely used machine learning-based supervised classifiers are selected for the methods evaluation. As the results obtained, the SVM, MLC and ANN achieved the highest accuracy of 88.2%, 85.4% and 84.1% in a simple four-class urban surface mapping experiment. With the increasing requirement of the remote sensing application, more advanced machine learning algorithms would be explored, and the evaluation in our study as well as the labeled dataset can provide a baseline for the future research.

Hyperspectral remote sensing image (HSI) clustering can be defined as the process of segmenting pixels into different sets that satisfy the requirement that the differences between sets are much greater than the differences within sets. According to the fast density peak-based clustering algorithm, we propose an unsupervised HSI clustering method based on the density of pixels in the spectral space and the distance between pixels. For the metric of the density, we present an adaptive-bandwidth probability density function using pixel numbers as the input and the calculated pixel local density as the output, which determines the bandwidth on the basis of the Gaussian assumption. For the metric of the distance, in order to obtain a pixel-level spectral distance, we calculate the Euclidean distance between pixel vectors from the multiple bands. In the proposed approach: 1) use the least-squares method for the curve fitting of the two results; 2) eliminate outliers based on the Pauta criterion; 3) adopt regression calculation; and 4) obtain the cluster centers according to the classification criteria of the local density and the distance between pixel vectors. The other noncluster center points are clustered based on their similarities with the cluster centers by iteration. Finally, we compare the results with those of other unsupervised clustering methods and the reference data sets.

A hierarchical method for subpixel surface water mapping accounting for the high spectral heterogeneity of urban materials is proposed in this paper. Specifically, we first applied water index (WI) for remote sensing image classification at pixel level, afterwards, the land, water, and land-water mixture can be extracted automatically. Then the spectral mixture analysis (SMA) is applied to land-water mixed pixels for water fraction estimation at subpixel level. To obtaining the most representative endmembers in SMA, we designed an adaptive iterative endmember selection method based on the spatial similarity of adjacent pixels. The proposed hierarchical processing method based on WI and SMA (WISMA) is applied to urban areas for reliability evaluation using the Landsat-8 Operational Land Imager (OLI) images. For comparison, four methods at pixel level and subpixel level were chosen respectively. Results indicate that the water maps generated by WISMA correspond as closely with the truth water maps with subpixel precision. And the results showed that the WISMA achieved the best performance in water mapping with comprehensive analysis of different accuracy evaluation indexes (RMSE and SE).