Data mining of network-constrained trajectories has broad applications in the GIScience field. The calculation of a complete trajectory similarity matrix is a key step in various data mining algorithms. However, computing this matrix is computationally intensive for large datasets, as it involves numerous point-to-point shortest-path (PPSP) queries. To tackle this issue, we propose a new spatiotemporal construct called the space-time tree, which directly delineates the network distance from a query trajectory to any network space-time point. By constructing the space-time tree, we can efficiently compute the trajectory similarity matrix without additional PPSP queries. The space-time tree supports several similarity metrics, including closest pair distance, furthest pair distance, longest common subsequence (LCSS), and distance-weighted LCSS. It can further integrate with advanced spatiotemporal query techniques for scalable partial trajectory similarity matrix calculations. A case study using real datasets was conducted to apply the space-time tree in the trajectory clustering application. The results show that the space-time tree completed the clustering task on 0.5 million trajectories within 49 minutes, achieving a nearly 147-fold speedup compared to state-of-the-art methods.

Class activation map (CAM) based weakly-supervised semantic segmentation (WSSS) of remote sensing (RS) images has attracted extensive research interests for its potential in reducing annotation cost. However, challenged by unconstrained activation issue, existing methods struggle to delineate object boundaries clearly, making them particularly difficult to separate multiple densely packed objects, which are common in RS images. By conducting an in-depth analysis of RS image characteristics, we observed a strong correlation between object shapes and their semantics. Inspired by this finding, we propose an Intrinsic Shape Activation Network (ISANet) to learn the category-relevant shape priors as geometry constraints for target-focused region activation in WSSS of RS images. The key idea is to distill the intrinsic shape priors from the hybrid features that are deterministic in classification. Specifically, we adopt a dual-branch architecture to decouple the learning of shape and texture features and leverage a shape awareness alignment module to generate boundary-clear CAMs for computing pseudo labels. In this way, CAMs are generated with perception of target shapes, which increases the completeness of activation regions and alleviates the ultrarange responses. Extensive experiments demonstrates the superiority of our method in delineating densely-packed objects with clear contours, which is especially beneficial for separating multiple targets in RS images. Our method improves the mIoU of the state-of-the-art method by 7.9% and 3.3% on the NWPU VHR-10 and iSAID dataset respectively.

UAV real-time photogrammetry is important to promote the rapid generation of photogrammetry 4D product, intelligent information extraction and rapid remote sensing mapping, and efficient large-scale 3D modeling. However, for real-time processing of low-overlap large-format image sequence, there remains two challenges: (1) Large-format images result in greater data volume and computational load, posing challenges for real-time online processing on regular-performance computing units, requiring more efficient algorithms; (2) Low-overlap images make it difficult for matching correspondences to cover the entire overlapping area at real-time, leading to significant challenges for real-time and robust relative orientation. Therefore, this paper proposes a robust Real-Time Orientation method for Low-overlap Large-format UAV Images (RTO-LLI), which can robustly handle these kind of data in real-time. Firstly, robust initialization method for real-time processing of low-overlap large-format images was designed to ensure a high-success-rate of SLAM initialization. Secondly, constant velocity hypothesis tracking enables fast orientation during constant-speed flight. Thirdly, when the second step false, using real-time pose estimation method based on multilevel matching and coarse-to-fine optimization to robustly solve the precision image pose. Fourthly, final (third-level) pose optimization method based on the IRLS algorithm with suitable search area, which can compute higher-precision image pose in real-time. Finally, real-time mapping based on parallel processing for low-overlap images can generate high-precision 3D point maps and complete feature extraction for the next frame in real-time. Experiments conducted on several different types of scenes show that: (1) the processing speed of RTO-LLI significantly surpasses traditional offline methods: PhotoScan, OpenMVG, Colmap. RTO-LLI can handle large-format UAV image sequence (single-imagery has 20-million-pixels) at a speed of 1.5 frames-per-second, meeting the demands of real-time UAV photogrammetry tasks; (2) RTO-LLI is the only method that has successfully completed real-time tasks in all 50-times repeated experiments for four different types of scenes, demonstrating robustness far superior to other classical SLAM solutions; (3) the-displacement-error of the estimated Pose by RTO-LLI is less than 1/2000 of the-trajectory-length, and the average-reprojection-error is less than 1.5 pixels, almost as well as traditional offline methods. RTO-LLI method meets the efficiency, robustness and accuracy requirements of real-time photogrammetry for low-overlap large-format UAV images.

Underwater instance segmentation plays a pivotal role in various applications. Among them, coral instance segmentation is of great significance in the fields of marine biology and environmental monitoring, and is crucial for comprehensive understanding of coral reef ecosystems. Traditional methods for underwater instance segmentation predominantly rely on RGB images. However, the complex morphology of corals and strong background interference often result in poor segmentation outcomes. To tackle these problems, this study presents a novel multimodal instance segmentation method, termed UMIS-YOLO, which is grounded in the YOLO architecture. UMIS-YOLO incorporates a dual backbone network design that substantially enhances the feature extraction capabilities for both RGB images and depth images, thereby improving the effectiveness of instance segmentation. At the same time, we propose two innovative plug-and-play modules: the Frequency Domain Feature Enhancement Fusion (FDFEF) module and the Residual Feature Fusion (RFF) module. The FDFEF module leverages Fourier transform to enhance the features of both modalities in the frequency domain, employing learnable weights to enable the complementary integration of amplitude and phase information. While the RFF module utilizes a residual learning strategy to efficiently merge low-level and high-level features prior to the segmentation head, thereby improving pixel-level segmentation accuracy. Additionally, we introduce a challenging high-resolution dataset, UMIS-Coral, which comprises RGB images and depth images captured in complex coral environments. Meanwhile, we expand the depth images for the UIIS dataset to further verify the effectiveness of UMIS-YOLO. The experimental results indicate that the UMIS-YOLO model achieved mAP50 and mAP75 improvements of 2.3 and 3.0 on the UMIS-Coral dataset, as well as 3.9 and 2.8 on the UIIS dataset, respectively. Furthermore, the model is characterized by its lightweight architecture and rapid segmentation capabilities. The source code and the dataset are publicly accessible at https://github.com/zhangsanhulk/UMIS-YOLO.

Building vector maps play an essential role in many remote sensing (RS) applications, thereby boosting the deep learning (DL)-based automatic building vector extraction methods. These approaches have achieved pleasant overall accuracy, but their predict-style framework struggles with perceiving subtle details within a tiny area, such as corners and adjacent walls. In this study, we introduce a denoising diffusion framework called DiffVector to generate representations for direct building vector extraction from the RS images. First, we develop a hierarchical diffusion transformer (HiDiT) to conditionally generate robust representations for detecting nodes and extracting corresponding features. The conditions of HiDiT are multilevel boundary attentive maps encoded from input RS images through a topology-concentrated Swin Transformer (TCSwin). Subsequently, an edge-biased graph diffusion transformer (EGDiT) takes extracted node features as conditions to produce new visual descriptors for the adjacency matrix prediction. In EGDiT, we replace the standard self-attention (SA) operation with an edge-biased attention (EBA) to inject edge information for training stabilization. Furthermore, given typical challenges of training difficulty and weak perceptive ability in convectional diffusion paradigms, we conduct an isomorphic training strategy (ITS), ensuring that the training procedures of both HiDiT and EGDiT precisely mirror the inference phase. Quantitative and qualitative experiments have evidently demonstrated that DiffVector can achieve competitive performance compared with existing modern approaches, especially in the metrics assessing topology quality.

High-quality image segmentation is fundamental to pixel-level geospatial analysis in remote sensing, necessitating robust segmentation quality assessment (SQA), particularly in unsupervised settings lacking ground truth. Although recent deep learning (DL) based unsupervised SQA methods show potential, they often suffer from coarse evaluation granularity, incomplete assessments, and poor transferability. To overcome these limitations, this paper introduces Panoramic Quality Mapping (PQM) as a new paradigm for comprehensive, pixel-wise SQA, and presents SegAssess, a novel deep learning framework realizing this approach. SegAssess distinctively formulates SQA as a fine-grained, four-class panoramic segmentation task, classifying pixels within a segmentation mask under evaluation into true positive (TP), false positive (FP), true negative (TN), and false negative (FN) categories, thereby generating a complete quality map. Leveraging an enhanced Segment Anything Model (SAM) architecture, SegAssess uniquely employs the input mask as a prompt for effective feature integration via cross-attention. Key innovations include an Edge Guided Compaction (EGC) branch with an Aggregated Semantic Filter (ASF) module to refine predictions near challenging object edges, and an Augmented Mixup Sampling (AMS) training strategy integrating multi-source masks to significantly boost cross-domain robustness and zero-shot transferability. Comprehensive experiments demonstrate that SegAssess achieves state-of-the-art (SOTA) performance and exhibits remarkable zero-shot transferability to unseen masks. The code is available at https://github.com/Yangbn97/SegAssess.

Deep learning methods have been widely used to map building contours automatically in high-resolution remote sensing images over recent years. However, most deep learning-based methods still require complex post-processing to generate regular contours. P2PFormer is an advanced method that can directly obtain the positions and sequences of general geometric primitives like points, lines, and angles (corners) of a building instance without complex post-processing. Nevertheless, due to the inherent limitations of ROI-Align, P2PFormer faces significant challenges in primitive detection. ROI-Align utilizes a uniform sampling approach for feature extraction, it inevitably introduces a high proportion of invalid sampling points into the extracted features. Resulting in missed and false detections of building primitives, ultimately affecting the accuracy of building contour extraction. To address these issues, we propose P2PFormerV2, which introduces a contour feature enhancer to improve P2PFormer. The contour feature enhancer increases the proportion of valid feature sampling points and enhances the extraction of contour-aware features, significantly improving the accuracy of primitive segmentation. This enhancer comprises three key components: the sparse feature extractor, the dense feature extractor, and the feature fusion module. The sparse feature extractor optimizes the sampling strategy to increase the proportion of valid feature sampling points; the dense feature extractor generates rich contour features and provides additional supervision signals; the feature fusion module integrates the outputs of the first two components to further enhance the extraction of contour features. Experimental results demonstrate that P2PFormerV2 achieves average precisions (AP) of 74.7%, 79.6%, and 64.2% in the WHU, CrowdAI, and WHU-Mix datasets, respectively, significantly outperforming the original P2PFormer and other existing advanced methods. Our findings about the shortcomings of ROI-Align and the importance of improving the effective feature extraction provides insights for future building extraction research.

The sun glint poses a significant challenge in optical remote sensing of the ocean using unmanned aerial vehicles (UAVs). It contaminates the oceanographic information within the images, not only obscuring underwater seafloor features but also increasing the radiance reflectance within the images, which is detrimental for the study and monitoring of the marine environment. Currently, there are two main approaches for sun glint correction in optical imagers (in this context, referring to visible light images captured in RGB channels): methods based on sea surface statistical model and methods based on deep learning. To assess the potential application of sun glint correction methods on UAV RGB imagery, this paper reviews and summarizes both types of methods. Through experimental evaluation, our examines the usability of these methods in UAV-based ocean remote sensing, providing a scientific foundation for obtaining high-quality marine monitoring images. The experimental results indicate that traditional sea surface statistical model-based methods developed for satellite imagery face challenges when transitioning to high-resolution UAV imagery. Conversely, deep learning-based methods show promise for sun glint correction in UAV RGB imagery. Although these methods are still in the early exploration stage, they hold the potential to offer innovative and efficient solutions for mitigating sun glint effects in high-resolution UAV RGB imagery.

Ensuring the correctness of road network data is critical for navigation, traffic control and urban planning. Errors like missing roads and absent connections can hinder its quality. Trajectory data emerges as a cost-effective source to uncover such errors. Existing methods often analyze the mismatches between trajectories and road networks to identify specific errors. They heavily rely on manually established rules and fail to fully leverage the diverse patterns of trajectories and the underlying road network structure. The article introduces a sequential classification approach to detect diverse road network errors. It starts with partial map matching (PMM) to associate trajectories with a road network, allowing unmatched portions. Context features are subsequently extracted by encoding patterns in the map matching (MM) outputs, raw trajectories and road network. Finally, a bidirectional recurrent neural network (BiRNN) model is trained to identify the network error category for each trajectory point. Experiments were performed on detecting errors in OpenStreetMap (OSM) road network with a real-world trajectory dataset. It demonstrates that the proposed method achieves accuracy over 96%, significantly surpassing four baselines. An ablation study confirms the necessity of considering different types of context features. This method advances error detection by effectively utilizing trajectories in identifying diverse network errors.

Fast, high-precision texture maps and high-frame-rate level of detail (LOD) generation for realistic 3-D models are foundational data infrastructures for smart cities. However, LOD generation faces three main issues: reduced model accuracy from mesh simplification, inefficient texture memory utilization, and browsing lag with detail loss. This article proposed a novel LOD rendering method with multilevel structure-keeping mesh simplification and fast texture alignment for realistic 3-D models. First, a multilevel structure-keeping mesh simplification method with mesh segmentation and vertex classification was used to generate a simplified mesh with high-precision structure preservation. Second, a fast texture alignment method was proposed that uses segmentation information and least-squares conformal map (LSCM) parameterization to acquire texture blocks. The method integrated integral images and a precise multitemplate strategy to align texture blocks, to obtain texture maps with high completeness and high occupancy. Finally, by integrating these methods, an LOD generation method with fast multilevel pyramid construction and adaptive tree organization is proposed. This method achieved high-precision multilevel structure keeping, along with a high-occupancy rate of texture maps, facilitating a high frame rate for LOD model construction. Compared with quadratic error function (QEF), quadratic error metrics (QEMs), low-poly, computational geometry algorithms library (CGAL), and Nvdiffrec, the proposed mesh simplification algorithm demonstrated average accuracy improvements of 12.1%, 24.2%, 57.1%, 17.9%, and 3.2%, respectively. Compared with open multi-view environment (OpenMVE), ContextCapture, and Xatlas, the proposed texture alignment algorithm achieved average occupancy improvements of 27.74%, 11.89%, and 4.80%, respectively. Compared with the state-of-the-art ContextCapture and Smart3D, the proposed method for browsing large-scale realistic 3-D models increased the frame rate by 17.3% and 14.4%, respectively.

Most of the existing deep learning-based hyperspectral image (HSI) classification algorithms are based on supervised learning, where large number of annotated labels with high acquisition cost are required. Self-supervised learning (SSL) methods can learn abundant representations using large amount of unlabeled data, thereby reducing the reliability of labels. Particularly, SSL based on Masked Image Modeling (MIM) can extract fine-grained features, which is well-suited for HSI classification as a pixel-level interpretation task. However, MIM has scarcely been investigated in HSI classification. Current algorithms lack a comprehensive consideration of the multiscale spectral-spatial characteristics of HSI when constructing the pre-training task, and there exists high computational cost and redundancy when applied to large-scale HSI. Therefore, this paper develops an SSL framework based on Spectral-Spatial Hierarchical Masked Modeling (S2HM2) for large-scale HSI classification. Considering the spectral-spatial characteristics of HSI, 3D masking strategy and spectral-spatial consistency loss are proposed to construct MIM task. To fully exploit features at each scale, hierarchical 3D Feature Pyramid Network (3D-FPN) is designed as decoder for both pre-text and downstream tasks in a “pixel-to-pixel” manner. In addition, Multi-Scale Masked Feature Modeling (MS-MFM) task is proposed to further facilitate the multiscale feature learning. The SSL pre-training is guided by both MIM and MS-MFM. Experimental results on two large-scale hyperspectral datasets, i.e., WHU-OHS and WHU-H2SR, demonstrate the superiority of the proposed method. Furthermore, transfer learning experiments are conducted on a variety of hyperspectral datasets, where classification accuracies are boosted in most of the scenarios. Source code will be made available at https://github.com/tulilin/S2HM2.

The rapid processing, analysis, and mining of remote sensing big data using intelligent interpretation technology on remote sensing cloud computing platforms (RS-CCPs) have emerged as a new trend. However, existing RS-CCPs primarily focus on optimizing data storage and intelligent computing for common visual representation, overlooking key characteristics of remote sensing data such as large image size, large-scale change, multiple data channels, and geographic knowledge embedding. This oversight hinders computational efficiency and accuracy in remote sensing image interpretation. To address this, we have developed the LuoJia-AI platform, comprising the LuoJiaSET standard large-scale sample database and the dedicated deep learning framework, LuoJiaNET. This platform achieves state-of-the-art performance on five crucial remote sensing interpretation tasks: scene classification, object detection, land-use classification, change detection, and multi-view 3D reconstruction. LuoJia-AI bridges the gap between the sample database and the deep learning framework, exhibiting significant potential for high-precision remote sensing mapping applications.

Clustering the trajectories of vehicles moving on road networks is a key data mining technique for understanding human mobility patterns, as well as their interactions with urban environments. The development of efficient and scalable trajectory clustering algorithms, however, still faces challenges because of the computational costs when measuring similarities among a large number of network-constrained trajectories. To address this problem, a novel trajectory clustering framework based on the well-developed Density-Based Spatial Clustering of Applications with Noise (DBSCAN) approach is proposed. This proposed framework accurately quantifies similarities using a trajectory representation of continuous polylines in the space and time dimensions, and does not require trajectory discretization. Further, the proposed framework utilizes the space-time buffering concept to formulate ε-neighborhood queries that directly retrieve the ε-neighbors of trajectories and thus avoids computing a trajectory similarity matrix. State-of-the-art trajectory databases and index structures are incorporated to further improve trajectory clustering performance. A comprehensive case study was carried out using an open dataset of 20,161 trajectories. Results show that the proposed framework efficiently executed trajectory clustering on the large test dataset within 3 min. This was approximately 2,700 times faster than existing DBSCAN algorithms.

The availability of Spatiotemporal Big Data has provided a golden opportunity for time geographical studies that have long been constrained by the lack of individual-level data. However, how to store, manage, and query a huge number of time geographic entities effectively and efficiently with complex spatiotemporal characteristics and relationships poses a significant challenge to contemporary GIS platforms. In this article, a hierarchical compressed linear reference (CLR) model is proposed to transform network-constrained time geographic entities from three-dimensional (3D) (x, y, t) space into two-dimensional (2D) space. Accordingly, time geographic entities can be represented as 2D spatial entities and stored in a classical spatial database. The proposed CLR model supports a hierarchical linear reference system (LRS) including not only underlying a link-based LRS but also multiple higher-level route-based LRSs. In addition, an LRS-based spatiotemporal index structure is developed to index both time geographic entities and the corresponding hierarchical network. The results of computational experiments on large datasets of space–time paths and prisms show that the proposed hierarchical CLR model is effective at storing and managing time geographic entities in road networks. The developed index structure achieves satisfactory query performance in milliseconds on large datasets of time geographic entities.

The use of delay-Doppler maps (DDMs) measured by Global Navigation Satellite System Reflectometry (GNSS-R) for target detection and location is a hot issue because of the potentially global coverage and short revisit periods of GNSS-R satellite missions. Existing researches have explored the detection of oil rigs, oil spills, sea ice, and other targets with spaceborne GNSS-R. However, these researches may not fully consider the advantages of multiple GNSS-R satellites, for example, Cyclone Global Navigation Satellite System (CYGNSS) which has eight satellites. Two problems of using multiple GNSS-R satellites for detection and location are how to estimate the sea clutter that is used to cancel the clutter in DDMs and how to remove location ambiguity caused by the transformation from the delay-Doppler (DD) domain to the spatial domain. In this article, an oil rig is taken as an example for detection and location with multiple GNSS-R satellites. To distinguish the oil rig from sea clutter, this article uses subspace projection to estimate the clutter and subtract the estimation from the DDMs. Moreover, after the clutter cancellation, this article projects the potential oil rig coordinates in the DD domain into a uniform coordinate system and removes the location ambiguity based on multisatellites fusion. The measured DDMs collected by CYGNSS are employed to conduct experiments to validate the feasibility of the proposed methods for detection and location with DDMs. By subtracting the estimated sea clutter from DDMs, the potential oil rig can be indicated in the DD domain. Two location experiments can calculate the unambiguous coordinate of the oil rig with a deviation less than 4 km.

This paper introduces a cross-scale attention based end-to-end learning framework for tree crown detection via UAV imagery. Given that UAV images covered a large forests, the illumination variations, shadow obstacles and texture repetition always lead to inaccurate tree crown detection results. We introduce a cross-scale attention based mechanism to address the above issues, enabling the tree crown detection framework to reason about the RGB texture information and depth information introduced by the automatically generated depth map jointly. Compared to traditional image based tree crown detection methods, our approach learns prior over geometrical structure information from the real 3D world, which is robust to the texture repetition and small tree crowns. The experimental results demonstrated that the proposed approach outperforms the traditional CNN based method.

Beidou geostationary earth orbit (GEO) satellite-based global navigation satellite system reflectometry (GNSS-R) technique has been developed for measuring surface deformation in a carrier-phase-based, cost-effective, and continuous manner. However, several improper assumptions in the original system and method, such as neglecting the slight GEO satellite movement during angle determination and deeming inter-channel phase difference as time-invariant, can introduce certain errors in estimating the surface deformation. In this work, these issues were analyzed and improved for more accurate estimations. Utilizing a Wilkinson power divider, the inter-channel phase error is estimated and calibrated with direct signal in the master channel. The GEO-motion phase error is theoretically modelled and compensated for based on precise ephemeris. A compensating algorithm of GNSS-R deformation retrieval technique utilizing Beidou GEO satellites is presented, by which encouraging results are yielded from field experiments emulating long-term monitoring. On artificial targets, the retrieval root mean square (RMSE) is better than 8 mm.

This article presents a context-aware tracing strategy (CATS) for crisp edge detection with deep edge detectors, based on an observation that the localization ambiguity of deep edge detectors is mainly caused by the mixing phenomenon of convolutional neural networks: Feature mixing in edge classification and side mixing during fusing side predictions. The CATS consists of two modules: A novel tracing loss that performs feature unmixing by tracing boundaries for better side edge learning, and a context-aware fusion block that tackles the side mixing by aggregating the complementary merits of learned side edges. Experiments demonstrate that the proposed CATS can be integrated into modern deep edge detectors to improve localization accuracy. With the vanilla VGG16 backbone, in terms of BSDS500 dataset, our CATS improves the F-measure (ODS) of the RCF and BDCN deep edge detectors by 12 and 6 percent, respectively when evaluating without using the morphological non-maximal suppression scheme for edge detection.

Detecting buildings with structure information (e.g., rooflines) from satellite images is a significant yet challenging task. Existing methods usually suffer from the spatial and spectral diversity and complexity of the architectures. In this paper, a deep learning-based approach is proposed to extract structured building rooflines. We use convolutional neural networks to detect corner and line segment primitives. Meanwhile, a collaborative branch of semantic annotation information is combined to obtain the building segmentation map, which ensures the spatial and topological relations of the extracted primitives. Experiments on the SpaceNet dataset show that our proposed approach improves the accuracy of building extraction. Furthermore, the planar graph representation promotes three-dimensional (3D) reconstruction and other subsequent applications.

Individual driving final destination prediction supports location-based services such as personalized service recommendations, traffic navigation, and public transport dispatching. However, real-time destination prediction is challenging due to the complexity of temporal dependencies, and the strong influence of travel spatiotemporal semantics and spatial correlations. Besides temporal context, the nearby urban functionalities of traveling zones and departure regions, and the crucial positions on the road network where trajectory points located would reflect the travel intentions of drivers. However, these spatial factors are rarely considered in existing studies. To fill this gap, we propose a real-time individual driving destination prediction model LSI-LSTM based on an attention-aware Long Short-Term Memory (LSTM) by taking Location Semantics and Location Importance of trajectory points into account. More specifically, a trajectory location semantics extraction method (t-LSE) enriches feature description with prior knowledge for implicit travel intentions learning. t-LSE represents urban functionality through Points of Interest (POIs) using Term Frequency-Inverse Document Frequency (TF-IDF). Meanwhile, a novel trajectory spatial attention mechanism (t-SAM) captures the trajectory points that strongly correlate to candidate destinations based on the location importance inferred from the driving status, i.e., turning angle, driving speed, and traveled distance. Comparative experiments with three baseline methods, i.e., Hidden Markov Model, Random Forest, and LSTM, demonstrate significant prediction accuracy improvements of LSI-LSTM on four individual trajectory datasets. Further analyses validate the effectiveness of the proposed semantic extraction method and attention mechanism, and also discuss the factors that may affect the prediction results.

This paper presents a new semi-supervised method for land cover classification using Sentinel-2 time-series images, which can deal with the problem of unclear observations. First, the MCCR method, which is constituted by the matrix completion (MC) of unclear observations and feature-adaptive collaborative representation (CR) based classifier, is adopted to handle the data quality problem. Second, by fusing RF, AdaBoost, and MCCR, a tri-training process is proposed to iteratively select the semi-labeled samples, considering the difference of classification certainty in different classifiers and classes. Experiments on two sets of Sentinel-2 images are conducted to validate the effectiveness of the proposed semi-supervised method.

As the second largest freshwater lake in Yunnan Province of China, Erhai Lake has suffered harmful algal blooms (HABs) since 1996. In January 2017, Dali government issued a series of ecological protection measures to prevent the outbreak of HABs. In order to evaluate the effectiveness of those protection measures, we studied the spatiotemporal distribution of HABs in Erhai Lake by using multi-source remote sensing data during 2016-2018. The results demonstrate that coverage area and frequency of HABs occurrence were decreasing after January 2017, which indicates a good respond to water protection regulations. However, in 2018, HABs still occurred around residential and tourist area. Furthermore, drastic measures also impeded local economic development due to shuttering businesses and banning farming around lake. Therefore, there is still a long way to go for local government to achieve long-term goals of sustainable economy and water environment stability of Erhai region.

Existing spatial clustering methods primarily focus on points distributed in planar space. However, occurrence locations and background processes of most human mobility events within cities are constrained by the road network space. Here we describe a density-based clustering approach for objectively detecting clusters in network-constrained point events. First, the network-constrained Delaunay triangulation is constructed to facilitate the measurement of network distances between points. Then, a combination of network kernel density estimation and potential entropy is executed to determine the optimal neighbourhood size. Furthermore, all network-constrained events are tested under a null hypothesis to statistically identify core points with significantly high densities. Finally, spatial clusters can be formed by expanding from the identified core points. Experimental comparisons performed on the origin and destination points of taxis in Beijing demonstrate that the proposed method can ascertain network-constrained clusters precisely and significantly. The resulting time-dependent patterns of clusters will be informative for taxi route selections in the future.

This paper presents a new building indicator based on the multi-angle images, the angular difference feature (ADF), which characterizes angular properties from high-resolution ZY-3 multi-view images. The method for detecting buildings based on ADF consists of two main steps: ADF feature extraction and a post-processing step to refine the results by simultaneously incorporating the spectral and geometrical information. Experiments are conducted with three ZY-3 images acquired over Chinese cities. The proposed ADF achieves promising building detection performance over both highly dense urban areas and suburban areas, with an overall accuracy of better than 89% for all the three data sets.

In this article, we propose an automatic method for building area extraction from optical high-resolution imagery by using the recently developed morphological building index (MBI). First, the original MBI feature is calculated to highlight the potential buildings in the imagery. Second, a post-processing framework is used to remove false alarms by taking advantages of the spectral, shadow and shape information. Third, an intensity feature of building area is generated from the buildings and finally the building area result is obtained. Experiments on two high-resolution images are conducted to validate the effectiveness and robustness of the proposed method.

Speckle inherent in synthetic aperture radar (SAR) images usually complicates visual interpretation and brings difficulty to information extraction for applications. Current speckle filters are mainly developed for single SAR image or an image pair (InSAR or PolInSAR). Although some multichannel filters are proposed, they only exploit pixel intensity to identify statistically homogeneous pixels (SHPs). In this paper, we present a new unified approach to filter multitemporal SAR images by adaptively estimating complex covariance matrix-based multitemporal filtering, named CCM-MTF. The key idea is to employ generalized likelihood ratio (GLR) test on the Wishart distributed initial CCM to evaluate the similarity between two pixels. A special design is given to the initial CCM estimation, in which temporal samples are used instead of spatially neighboring samples. Then, a threshold determined by the asymptotic distribution of the logarithm of GLR test statistics at a fixed significance level is used to select spatial SHPs for the reference pixel. Subsequently, the filtering is implemented by estimation of the final CCM from original SAR scattering vector over SHP pixels, and all filtered target information channels including intensity, interferometric phase, and coherence can be explicitly derived from the final CCM. The effectiveness of the proposed CCM-MTF method is validated by experiments on both simulated and real multitemporal SAR images. Both qualitative and quantitative comparisons between CCM-MTF and four state-of-the-art SAR filters are carried out to demonstrate its advantages in terms of speckle suppression as well as detail preservation for all the three information channels.

To achieve precise sensor orientation of high- resolution satellite imagery (HRSI), ground control points (GCPs) or height models are necessary to remove biases in orientation parameters. However, measuring GCPs is costly, laborious, and time consuming. We cannot even acquire well-defined GCPs in some areas. In this paper, a strip constraint model is established according to the geometric invariance that the biases of image points remain the same in dividing a strip image into standard images. Based on the rational function model and the strip constraint model, a feasible sensor orientation approach for HRSI with the strip constraint is presented. Through the use of the strip constraint, the bias compensation parameters of each standard image in the strip can be solved simultaneously with sparse GCPs. This approach remains effective even when the intermediate standard images in the strip are unavailable. Experimental results of the three ZiYuan-3 data sets show that two GCPs in the first image and two GCPs in the last image are sufficient for the sensor orientation of all the standard images in the strip. An orientation accuracy that is better than 1.1 pixels can be achieved in each standard image. Moreover, the inconsistent errors of tie points between adjacent standard images can also be reduced to less than 0.1 pixel. This result can guarantee that the generated complete digital orthophoto map of the whole strip is geometrically seamless.

This paper proposes a novel adjustment model for mosaicking low-overlap sweeping images captured by medium-altitude unmanned aerial vehicle (UAV) with a long focal length. Commonly used methods are not suitable for this type of data. Three innovations are proposed to make this possible: first, building a new error model denoted by an error homograph matrix, which includes the camera parameter error, perspective center error, image attitude error, and the error of projection plane; second, the error homograph matrix is considered an unknown variable and is optimized, instead of optimizing the exterior orientation element in commonly used photogrammetry method; and third, the proposed algorithm is a global optimization, avoiding the cumulative error that appeared in traditional homographic-based methods. The results reveal that the proposed adjustment model can effectively eliminate the misalignments in the seam lines, compared to the direct homograph transformation. The numerical experiment results also demonstrate that the algorithm has perfect convergence and stability. In addition, this method is also suitable for low-altitude UAV images when the covered area can be regarded as a plane.

Multiple InSAR techniques are increasingly being developed for earth observation. However, among them, persistent scatterers-based InSAR (PSI) techniques fail to obtain enough measurement points (MPs) in rural mountainous area due to the lack of persistent scatterers (PSs), such as ma-made structures, rocks, and outcrops, etc. In this paper, Distributed Scatterers-based InSAR (DS-InSAR) algorithm, exploiting both persistent scatterers and distributed scatterers (DSs) widely spreading in rural areas, is proposed to make up the limitation of persistent scatterers-based technique when monitoring mountainous landslides. There are two key steps to preprocess DSs in DS-InSAR algorithm: selecting DS candidates and estimating optimal interferometric phases. The selected DSs and PSs are combined for further processing using traditional PSI procedure. A qualitative and quantitative simulation analysis was operated to validate the DS-InSAR algorithm. Then, both PSI and DS-InSAR were implemented to monitor Xishan landslide in western mountainous region of Sichuan province, based on high-resolution TerraSAR-X images. The obtained results demonstrate that DS-InSAR could detect much more MPs and provide more reliable deformation information.

Precipitation stations are important components of a hydrological monitoring network. Given their critical role in rainfall forecasting and flood warnings, along with limited observation resources, determining the optimal locations to deploy precipitation stations presents an important problem. In this paper, we use a maximal covering location problem to identify the best precipitation station sites. Considering the terrain conditions and the characteristics of a rainfall network, the original maximal covering location model is modified with the introduction of a set of additional constraints. The minimum density requirement is used to determine a precipitation station’s coverage range, and three weighting schemes are used to evaluate each demand object’s covering priority. As a typical mountainous watershed with high annual precipitation, the Jinsha River Basin is selected as the study area to test the applicability of the proposed method. Results show that the proposed method is effective for precipitation station configuration optimization, and the model solution achieves higher coverage than the real-world deployment. Compared with the commercial solver CPLEX, a genetic algorithm-based heuristic can significantly reduce the computation time when the problem size is large. Several deployment strategies are also discussed for establishing the optimal configuration of precipitation stations.

Polygonal vector data are important for representing countries, lakes, residential settlements, and other polygonal features. The proper representation of polygonal vector data is the basis of efficient rendering and picking and quick access and display of the analysis results based on polygons (e.g., 3D overlaying and surface area measurement in mountainous areas) in a virtual globe. However, polygonal vector data are displayed using texture-based or boundary-based approaches in most existing virtual globes. The texture-based approach cannot easily support interactive operations (e.g., picking) and spatial analysis (e.g., adjacency analysis and spatial measurement). The boundary-based approach treats the holes as independent features; however, it is difficult to recognize which boundaries constitute a polygon. Further research is needed on how to better organize the polygons to support efficient rendering, picking, and analysis in a virtual globe. In this article, we propose two methods to drape interior filled 2D polygons onto a multi-resolution 3D terrain. Both proposed methods combine polygon clipping and polygon triangulation. The difference between the two methods is in the way holes are eliminated. Method 1 recursively subdivides a terrain triangle until the child-triangles contain no holes; every resulting clipped polygon, which is then triangulated, contains no holes. Method 2 directly clips a polygon against a terrain triangle and creates bridge edges to transform the resulting polygons with holes to degenerate polygons that are further triangulated. The experimental results demonstrate that both proposed methods can efficiently process polygons with holes resulting in appropriate numbers of triangles. The processed interior-filled polygons remain close to the terrain surface in a virtual globe. Both proposed methods support real-time rendering of polygonal vector data in a virtual globe.

Existing methods that incorporate spatial information into a traditional Bag-of-Visual-Words (BoVW) model consider the spatial arrangement of an image but ignore pixel homogeneity in land-use remote sensing images. In this letter, we present an improved correlaton model to jointly integrate appearance, spatial correlation, and pixel homogeneity using multiscale segmentation. The effectiveness of the proposed method was tested on a ground truth image data set of 21 land-use classes manually extracted from high-resolution remote sensing images. The experimental results demonstrate that our improved correlaton model can promote classification and outperforms existing methods such as the traditional BoVW model, spatial pyramid matching model, and the traditional correlaton model.

Different Earth-observing (EO) sensors have various capabilities for diverse observing tasks. Sensor planning services make the choice of web-ready sensors for specific observing tasks with regard to observing requests and sensor capabilities. Sensor capabilities rely on various parameters; thus, choosing EO sensors for specific observing tasks relying directly on these parameters is a multicriteria decision process. A sensor's capability can be drawn from these parameters with the help of an algorithm. Furthermore, if divided into different clusters based on capabilities, applicable sensors can be more easily chosen for a category of observing tasks. In this paper, a spaceborne EO optical sensor static capability index (SSCI) mechanism is drawn from an evaluation-and-clustering algorithm, which is composed of a self-organizing neural map in combination with weighted principal component analysis. The scheme of SSCI relies on no expert analysis system and thus is more flexible and efficient. EO scenarios of disaster reactions are among the application of this algorithm. In particular, scenarios of flooding disaster forecasting, relief aiding, and postdisaster loss assessment within the framework of International Charter on Space and Major Disasters have been utilized for experiments. They have shown that the SSCI assessing algorithm is feasible and stable, and the EO optical sensor clustering algorithm based on SSCI can offer reasonable clustering accuracies of EO optical sensors. In our experiments, the EO optical sensor SSCI computation and clustering algorithm had a time consumption within 2 s and 2 min, respectively, and memory consumption within 200 MB on a normal personal computer.

This letter concentrates on scattering mechanism classification of polarimetric synthetic aperture radar (PolSAR) images. Scattering mechanism classes are defined as the combinations of dominant and secondary scattering mechanisms. With three metrics extracted from the observed coherency matrix, an unsupervised classifier is proposed to classify PolSAR pixels into eight combinations of surface scattering, double-bounce scattering, and volume scattering. When applying the proposed method to simulated data, the Kappa coefficient is 0.891. It effectively classifies the dominant mechanism, and the Kappa coefficient is 0.127 higher than that of the H/α method. Experiment using uninhabited aerial vehicle SAR data shows that the proposed method is able to identify secondary mechanism in forests and urban areas. This method is not only a good classifier free of specific polarimetric decomposition but also can serve as a preclassification step of sophisticated classification scheme.

Visualization of geospatial data provenance aims to provide a user-friendly way for easy navigation and increased understanding of the derivation history of geoscientific results. Most existing work focuses on provenance modeling and management. This paper proposes to interleave map and faceted metadata for geospatial data provenance visualization and navigation. It shows how provenance in Web-geoprocessing workflows can be visualized at four levels: feature, dataset, service, and knowledge. A prototypical system, named GeoPWProv, is developed to demonstrate the applicability of the approach.

Geospatial data provenance records sources and processing steps that are used in deriving geospatial data products. In the Web of Data environment enabled by Linked Data technologies, sources and processing steps, such as geospatial data and geoprocessing services, can be published as part of the Web of Data. To take full advantages of the machine-understandable format and linkages among heterogeneous data items in the Web of Data, this paper proposes to publish geospatial data provenance into the Web of Data. In particular, it analyzes how a catalogue for provenance, i.e., geospatial data provenance managed by a geospatial metadata catalog service, can be published into the Web of Data using a Linked Data approach. Consequently, queries over linked geospatial data provenance are analyzed and tested to demonstrate the benefits of the approach.

A new algorithm, RGB-belief propagation (RGB-BP), for dense corresponding pixel matching between aerial epipolar images is proposed in this letter. Evolved from the traditional belief-propagation algorithm, RGB-BP makes full use of all the three color components, R, G, and B, and simplifies the parameter settings. In order to reduce the impact of the obvious color differences between corresponding pixels, RGB-BP reduces the sensitivity of central pixels and increases the contribution of neighboring pixels. Three pairs of aerial epipolar images are tested using RGB-BP. The experimental results demonstrate the effectiveness of RGB-BP.

Bi-static remote sensing with GPS signal (direct and reflect signals) has supported some researches in soil moisture measuring, sea state estimating and sea altimetry monitoring. In these researches the special designed receivers are generally required, such as the "delay-mapping" GPS receiver or open loop differential real-time receiver, because they can find the characteristics of the reflected electromagnetic wave affected by the object. Now the commercial single frequency GPS receiver becomes more lighter, smaller and lower power, it is potentially capable of sea remote sensing. However it is ignored. In this paper, a ground based GPS-R technology with single frequency receiver is introduced. The technology is based on both the scatter theory from the rough surface and the GPS double difference theory of carrier phase. This paper describes the GPS-R instrument, introduces the basic method and shows the result of GPS-R experiments on bridge. These results provide good initial conditions for widespread sea state monitoring if using GPS-R receiver network . this paper also discusses the results under the influence of the satellite elevation and single difference .

In a service-oriented geo scientific research environment, individual geospatial services must be chained together as Web geoprocessing workflows to solve a complex geoscientific problem. The development of Web geoprocessing workflows can be divided into three phases: process modeling, process model instantiation, workflow execution. Provenance, or called lineage, records the derivation history of a data product. This paper presents a provenance framework for Web geoprocessing workflows. Such a framework includes the provenance representation, provenance recording, provenance storage, provenance service, and provenance applications. The concept of "three levels of geospatial provenance" is used to advocate the categories of provenance at the knowledge, service, and data level. The three-level view addresses the derivation history in the three-phase development of Web geoprocessing workflows. The applications of provenance are demonstrated by allowing re-orchestration of geoprocessing workflows at different phases using different levels of provenance and creating a more flexible system for Web geoprocessing workflows.

Because the advances in research technologies and the geospatial data with which they deal are diverse and complex. The OGC Web Processing Service (WPS) has several areas of complexity. Basic request-response mechanisms need to contend with delays/failures, especially for mid-term or long-term actions. The asynchronicity in communication between a user and the corresponding Web processing service, or between two services, is significant. The Web Notification Service (WNS), an OGC notification and communication service by which a client may conduct asynchronous dialogues (message interchanges) with one or more other services, can be useful when satisfying a client request requires many collaborating services and/or when there are significant delays in satisfying the request. WNS-based asynchronous notification middleware has been implemented by augmenting the OGC Web Processing Service with message-based asynchronous notification to resolve WPS asynchronous communication and notification problems.

A new star identification algorithm based on matching probability is proposed for satellite attitude determination. In this algorithm, the brightest observed star is considered as the primary star, and the radial geometry pattern is constructed by linking the primary star to the other adjacent stars in the FOV. When a link is matched with star database, the two corresponding stars in the star database are recorded. The star with the most appearance times is regarded as the correspondence of the primary star. Experiments show that the computation time and the storage requirement of the algorithm are small, and the identification rate is high, compared with improved triangle matching algorithms.

A new approach is presented to extract more robust affine invariant features for image matching. The novelty of our approach is a hierarchical filtering strategy for affine invariant feature detection, which is based on information entropy and spatial dispersion quality constraints. The concept of spatial dispersion quality is introduced to quantify the spatial distribution of features. Moreover, an integrated algorithm combined by the filtering strategy, maximally stable extremal region (MSER) and scale invariant feature transform, is introduced for affine invariant feature extraction. Since Mikolajczyk et al. identified that MSER is the best detector in many cases, we design an experiment to compare our approach (ED-MSER) with the standard MSER. By using two stereo pairs and an image sequence with different types of imagery, the experiment indicates that ED-MSER can always get much higher repeatability and matching score compared to the standard MSER and other algorithms, thus benefiting the subsequent image matching and many other applications.

In distributed image mining using Web services, Web services implement individual mining algorithms. These services, together with those services providing data and data preprocessing functions, must be chained together dynamically to solve complex real world problems in mining applications. Service composition, the process of creating the service chain, can be divided into three phases: process modeling, process model instantiation, and workflow execution. Semantic Web technologies have been widely used to enable automation in the process-modeling phase. Instantiation of a process model into a concrete workflow or executable service chain requires detailed specification of the metadata for datasets and service instances. This paper explores metadata tracking in instantiating process models. Semantics-enabled metadata are generated and propagated through a service chain. Furthermore, a novel service chaining method based on metadata validation is introduced. Some use cases demonstrate how our approach can contribute to the generation of an executable service chain.

A new stochastic search strategy inspired by the clonal selection theory in an artificial immune system is proposed for dimensionality reduction of hyperspectral remote-sensing imagery. The clonal selection theory is employed to describe the basic features of an immune response to an antigenic stimulus in order to meet the requirement of diversity in the antibody population. In our proposed strategy, dimensionality reduction is formulated as an optimization problem that searches an optimum with less number of features in a feature space. In line with this novel strategy, a feature subset search algorithm, clonal selection Feature-Selection (CSFS) algorithm, and a feature-weighting algorithm, Clonal-Selection Feature-Weighting (CSFW) algorithm, have been developed. In the CSFS, each solution is evolved in binary space, and the value of each bit is either 0 or 1, which indicates that the corresponding feature is either removed or selected, respectively. In CSFW, each antibody is directly represented by a string consisting of integer numbers and their corresponding weights. These algorithms are compared with the following four well-known algorithms: sequential forward selection, sequential forward floating selection, genetic-algorithm-based feature selection, and decision-boundary feature extraction using the hyperspectral remote-sensing imagery acquired by the Pushbroom Hyperspectral Imager and the Airborne Visible/Infrared Imaging Spectrometer, respectively. Experimental results demonstrate that CSFS and CSFW outperform other algorithms and hence provide effective new options for dimensionality reduction of hyperspectral remote-sensing imagery.

The artificial immune network (AIN), which is a new computational intelligence model based on artificial immune systems inspired by the vertebrate immune system, has been widely utilized for pattern recognition and data analysis. However, due to the inherent complexity of current AIN models, their application to remote-sensing image classification has been rather limited. This paper presents a novel supervised classification algorithm based on a multiple-valued immune network, which is a novel AIN model, to perform remote-sensing image classification. The proposed method trains the immune network using the samples of regions of interest and obtains an immune network with memory to classify the remote-sensing imagery. Two experiments with different types of images are performed to evaluate the performance of the proposed algorithm in comparison with other traditional image classification algorithms: Parallelepiped, Minimum Distance, Maximum Likelihood, and Back-Propagation Neural Network. The results evince that the proposed algorithm consistently outperforms the traditional algorithms in all the experiments and, hence, provides an effective option for processing remote-sensing imagery.

With the widespread use of the Internet a large amount of geographical information is currently being stored and delivered over the Internet. Geographic references of Web page are information entities that are discovered from the context and can be mapped to some geographic locations. They are very useful for explaining real world information and for knowledge discovery. In the paper, a Geo-ontology is designed and developed to describe geographic references on the Semantic Web. Based on it, a tool is developed to georeferencing and the result is saved in OWL .The research is an attempt to step to Semantic Web and provide us with direction for future work.

Geographic Information System Grid integrates geographic information systems and Grid technology for data gathering, accessing, transmitting and service, in different I/O patterns, built upon massive storage systems. Existing non-standardized multi-source and multi-scale data lack spatial information sharing either internally or externally between organizations or departments, especially in national or global applications. HUSt is a massive storage system that was built at Wuhan National Laboratory for Optoelectronics, in China. There are heterogeneous storage areas in the system, including Object-based Storage System for the main data storing especially for the data searched frequently, Virtual Interface based Storage System for the data required at high transfer speed, and InfiniBand based SAN for high performance. HUSt is primarily meant for research on the organization and key technologies of storage systems for the next generation Internet. The goal is to unify network storage and construct a peta-byte storage system, which supports GIS Grid and applications.

The movement of 3D Object in virtual environment is complicated to present because of the complexity of the motion representation and the large quantity of its data. In this paper, we represent the motion of moving 3D objects in function or time series form, and introduce Hyper-Rectangle Compression (HRC) to compress and store the motion sample data as vector time series by predictive transform and quantization. We also discuss different indexing techniques, like hashing, R/sup +/ tree and IP indexing, to make the query efficient.