Real-time online trajectory map-matching has emerged as a critical component in the era of location-based services (LBS) and intelligent transportation systems (ITS). It refers to the process of aligning a user’s GPS trajectory data with the corresponding road network in real-time. This technology has significant implications for various industries and applications. As our reliance on LBS and ITS continues to grow, the demand for faster, more accurate, and more reliable trajectory map-matching methods becomes increasingly important. Contemporary online map-matching predominantly employs stream processing techniques. Based on stream processing frameworks, we propose a heterogeneous hybrid architecture for map-matching. The architecture integrates Spark Streaming and graphics processing unit (GPU) heterogeneous computing for the first time. The hidden Markov model is employed as the map-matching algorithm, and Spark Streaming serves as the distributed processing platform. We conduct map-matching experiments using a GPS taxi trajectory dataset in Beijing’s Haidian District. The results demonstrate that in comparison to other analogous research, our framework’s performance has increased by over ten times, possessing a superior data processing capability and lower latency. This research provides a novel approach of stream-based heterogeneous computation for processing large-scale geographic data.

Recently, hyperspectral image (HSI) classification methods based on Transformers have developed rapidly. However, these methods still face challenges in handling the widely varying scales and diverse spatial distribution patterns commonly found in HSIs. To address these issues, this article proposes a simple, yet novel HSI classification framework named the spectral view attention Transformer (SVAFormer). Built on the Transformer mechanism, this framework enhances the integration of spectral and spatial features by allowing the spectral token, corresponding to the pixel to be classified, to access spatial neighborhood information from multiple perspectives and levels. Specifically, the framework employs random masking techniques to provide spectral tokens with spatial neighborhood information from different viewpoints, enabling the model to handle diverse land-cover distribution patterns. Additionally, the framework introduces a spectral token-aware pooling layer between adjacent Transformer blocks, which preserves the central role of spectral tokens while progressively expanding the spatial scale represented by each token. This reduces the Transformer’s focus on spatially fragmented information and enables spectral tokens to concentrate on spatial neighborhood information at various levels and scales. The key characteristic of this framework is its ability to effectively handle land-cover features of different scales and shapes by strengthening the fusion of spectral and spatial characteristics. Experimental results on multiple public datasets demonstrate that our framework outperforms previous state-of-the-art methods. For the sake of reproducibility, the source code of SVAFormer will be publicly available athttps://github.com/chenning0115/SVAFormer.

Illegal construction is a common problem often encountered by cities with rapid development, which is hard to deal with for multiple reasons. Though these illegal buildings are primarily defined by laws and regulations, they still have physical characteristics in common that makes them identifiable. In this study, we propose an illegal building monitoring method based on satellite images and deep learning techniques, named Illegal Building Monitoring Network (IBMNet), to improve the data collection capacity for monitoring new illegal buildings. IBMNet is an end-to-end pixel-wise segmentation network with two flows: the Segment Flow, which includes a Siamese encoder and an Attention Fusion Module (AFM), and the Edge Flow, which uses Gated Convolutional Layers to extract edge information. We implement and evaluate our model in China, a country with fast development and struggling with illegal buildings. In addition to the conventional metrics, we propose a set of specialized metrics to evaluate the model’s ability to discriminate illegal buildings and legal buildings(OAB, F1Band IoUB). The model achieves great results on the Illegal Building Monitoring Dataset (IBMD) with an F1 score of 0.7990 and IoUBof 0.7449, showing its great ability in detecting illegal buildings in various scenarios and distinguishing them from legal buildings. Compared to existing methods based on urban database, IBMNet has a higher time resolution and a larger space coverage, making it more accessible in data and cost-effective for governments. The proposed method are also promising in other cities and countries with similar problems.

Topological road-boundary detection using remote sensing imagery plays a critical role in creating high-definition (HD) maps and enabling autonomous driving. Previous approaches follow an iterative graph-growing paradigm for road-boundary extraction, where road boundaries are predicted vertex by vertex and instance by instance to output a graph, resulting in limitations of low inference speed. In this work, we formulate the road boundaries as polylines instead of a graph and propose a novel polyline transformer for topological road-boundary detection, termed PolyRoad. PolyRoad is built on the transformer architecture and is capable of detecting all road boundaries in parallel, which greatly improves the training and inference speed compared with the graph-based methods. To perform bipartite matching between the ground truth and predicted polylines, we develop a polyline matching cost to measure the distance, considering the order of open and closed polylines. In addition, we propose three different losses for supervising polyline learning: the order-oriented$L1$loss, direction loss, and mask loss. The order-oriented$L1$loss provides the point-level supervision to constrain the absolute position of each point of the road-boundary polylines. The direction loss provides the direction-level supervision to constrain the geometry shape of the predicted polylines by supervising the relative position of adjacent points. The mask loss provides the pixel-level supervision of the predicted polylines by converting the vector-format polylines into raster-format binary masks. Comprehensive experiments are conducted on the Topo-boundary dataset. Quantitative and qualitative results show that PolyRoad achieves superior performance than prior methods in both pixel-level and geometry-level metrics. More notably, PolyRoad achieves$3.37 \times $and$22.85 \times $faster inference speeds than Enhanced-iCurb and VecRoad, respectively.

In recent years, there have been significant advancements in hyperspectral image (HSI) classification methods using contrastive learning. However, these methods often fail to effectively screen and mine negative samples during the construction of contrastive learning pairs. This oversight introduces negative samples that belong to the same class as the positive samples, thereby limiting the effectiveness of contrastive learning. To address this issue, we propose a novel HSI classification framework based on contrastive learning that flexibly supports the selection and mining of negative samples. Specifically, before training the contrastive learning task, we use pseudolabel information to guide the mining of negative samples, eliminating those with pseudolabels of the same class as the anchor samples. This approach strengthens the alignment between the optimization directions of the contrastive learning task and the classification task. In addition, we improve the contrastive learning process by introducing a controlled mixture of hard and easy negative samples, which enhances the accuracy of HSI classification. The pivotal characteristic of this study lies in enhancing the effectiveness of HSI classification based on contrastive learning through effective filtering and mining of negative samples. Experimental comparisons across multiple public datasets demonstrate the superiority of our proposed method over state-of-the-art algorithms.

Semantic segmentation is an essential technique in remote sensing. Until recently, most related research has focused primarily on advancing semantic segmentation models based on monomodal imagery, and less attention has been given to models that utilize multimodal remote sensing data. Moreover, most current multimodal approaches consider only limited bimodal situations and cannot simultaneously utilize three or more modalities. The increase in expensive computational costs associated with previous feature fusion paradigms hinders their application in broader cases. How to design a unified method to cover a wide variety of quantity-agnostic modalities for multimodal semantic segmentation remains unsolved issues. To address the aforementioned challenges, this study explores a feasible way and proposes a cost-effective multimodal sensing semantic segmentation model (MultiSenseSeg). MultiSenseSeg employs multiple lightweight modality-specific experts (MSEs), an adaptive multimodal matching (AMM) module, and a single feature extraction pipeline to efficiently model intra- and inter-modal relationships. Benefiting from these designs, the proposed MultiSenseSeg can serve as a unified multimodal model capable of addressing both monomodal and bimodal cases and readily extrapolating to scenarios with more modalities, thereby achieving semantic segmentation of arbitrary quantities of multimodal data. To evaluate the performance of our method, we select several state-of-the-art (SOTA) semantic segmentation models from the past three years and conduct extensive experiments on two public multimodal datasets. The results show that MultiSenseSeg can not only achieve higher accuracy but also exhibits user-friendly modality extrapolation, allowing end-to-end training for consumer-grade users based on limited hardware resources. The model’s code will be available at https://github.com/W-qp/MultiSenseSeg.

Cross‐city point of interest (POI) recommendation for tourists in an unfamiliar city has high application value but is challenging due to the data sparsity. Most existing models attempt to alleviate the sparsity problem by learning the user preference transfer and drift. However, they either fail to simultaneously model the preference transfer and drift in both long‐ and short‐term user preferences or cannot accomplish the task of the next POI recommendation, which is crucial for a wide spectrum of applications ranging from transportation and urban planning to advertising. To address the limitation, we proposed a user preference transfer and drift network (UPTDNet) for cross‐city next POI recommendation. UPTDNet excels at cross‐city recommendations by learning the transfer and drift of both long‐ and short‐term preferences. For short‐term preference, dual recurrent neural network‐based (RNN‐based) branches are designed to model preference transfer from tourist’s current city and drift among different user roles. For long‐term preference, a mapping function and user similarity calculation are employed for preference transfer from the tourist’s home city and drift among individual users. Experiments are conducted on the Gowalla and Foursquare datasets, and the results show that UPTDNet consistently and significantly outperforms state‐of‐the‐art models by an average of 10.22% to 22.63% in the next POI recommendation task. Ablation study and further analysis validate the effectiveness and plausibility of considering both user preference transfer and drift in the cross‐city recommendation.

Location prediction based on spatio-temporal footprints in social media is instrumental to various applications, such as travel behavior studies, crowd detection, traffic control, and location-based service recommendation. In this study, we propose a model that uses geotags of social media to predict the potential area containing users’ next locations. In the model, we utilize HiSpatialCluster algorithm to identify clustering areas (CAs) from check-in points. CA is the basic spatial unit for predicting the potential area containing users’ next locations. Then, we use the LINE (Large-scale Information Network Embedding) to obtain the representation vector of each CA. Finally, we apply BiLSTM-CNN (Bidirectional Long Short-Term Memory-Convolutional Neural Network) for location prediction. The results show that the proposed ensemble model outperforms the single LSTM or CNN model. In the case study that identifies 100 CAs out of Weibo check-ins collected in Wuhan, China, the Top-5 predicted areas containing next locations amount to an 80% accuracy. The high accuracy is of great value for recommendation and prediction on areal unit.

Geo-tagged travel photos on social networks often contain location data such as points of interest (POIs), and also users’ travel preferences. In this paper, we propose a hybrid ensemble learning method, BAyes-Knn, that predicts personalized tourist routes for travelers by mining their geographical preferences from these location-tagged data. Our method trains two types of base classifiers to jointly predict the next travel destination: (1) The K-nearest neighbor (KNN) classifier quantifies users’ location history, weather condition, temperature and seasonality and uses a feature-weighted distance model to predict a user’s personalized interests in an unvisited location. (2) A Bayes classifier introduces a smooth kernel function to estimate a-priori probabilities of features and then combines these probabilities to predict a user’s latent interests in a location. All the outcomes from these subclassifiers are merged into one final prediction result by using the Borda count voting method. We evaluated our method on geo-tagged Flickr photos and Beijing weather data collected from 1 January 2005 to 1 July 2016. The results demonstrated that our ensemble approach outperformed 12 other baseline models. In addition, the results showed that our framework has better prediction accuracy than do context-aware significant travel-sequence-patterns recommendations and frequent travel-sequence patterns.

Spatial interactions underlying consecutive sequential snapshots of spatial distributions, such as the migration flows underlying temporal population snapshots, can reflect the details of spatial evolution processes. In the era of big data, we have access to individual-level data, but the acquisition of high-quality spatial interaction data remains a challenging problem. Most research has been focused on distributions of movable objects or the modelling of spatial interaction patterns, with few attempts to identify hidden spatial interaction patterns from temporal transitions of spatial distributions. In this article, we introduced an approach to infer spatial interaction patterns from sequential snapshots of spatial population distributions by incorporating linear programming and the spatial constraints of human movement. Experiments using synthetic data were conducted using four simple scenarios to explore the characteristics of our method. The proposed method was used to extract interurban flows of migrants during the Chinese Spring Festival in 2016. Our research demonstrated the feasibility of using discrete multi-temporal snapshots of population distributions in space to infer spatial interaction patterns and offered a general analytical framework from snapshot data to spatial interaction patterns.

Rotating fan-beam scatterometer (RFSCAT) is a new type of satellite scatterometer that was proposed about one decade ago.However, just as other rotating scatterometers, relatively larger wind retrieval errors occur in the nadir and outer regions than in the middle regions of the swath. In order to address this problem, a modified wind vector retrieval algorithm for RFSCAT is presented in this paper. The new algorithm is featured with adaptively extending the range of wind direction for each wind vector cell position across the whole swath according to the distribution histogram of the retrieved wind direction bias. Simulation experiments demonstrated that the new established algorithm can effectively improve the wind direction retrieval accuracy in the nadir and outer regions of the RFSCAT swath.

According to the lower efficiency and larger wind direction errors in the nadir region of the swath, a new combined wind retrieval algorithm is proposed for conically scanning scatterometer in this paper. The presented algorithm has the dual advantages of both higher efficiency and higher wind direction retrieval accuracy by combining the wind speed standard deviation algorithm and the wind direction interval retrieval(DIR) algorithm. It adopts wind speed standard deviation as criterion for searching possible wind vector solutions and retrieves potential wind direction interval for the first and second ambiguities based on the change rate of the wind speed standard deviation. Some SeaWinds L2A data and collocated buoy data were used to validate the algorithm. Retrieval experiments indicated that the algorithm can significantly reduce the wind direction retrieval errors in the nadir region.

Over recent years, massive geospatial information has been produced at a prodigious rate, and is usually geographically distributed across the Internet. Grid computing, as a recent development in the landscape of distributed computing, is deemed as a good solution for distributed geospatial data management and manipulation. Thus, the Grid computing technology can be applied to integrate various distributed resources into a ‘super-computer’ that enables efficient distributed geospatial query processing. In order to realize this vision, an effective mechanism for building the distributed geospatial query workflow in the Grid environment needs to be elaborately designed. The workflow-building technology aims to automatically transform the global geospatial query into an equivalent distributed query process in the Grid. In response to this goal, detailed steps and algorithms for building the distributed geospatial query workflow in the Grid environment are discussed in this article. Moreover, we develop corresponding software tools that enable Grid-based geospatial queries to be run against multiple data resources. Experimental results demonstrate that the proposed methodology is feasible and correct.

Nowadays, GIS software is entering a new era of Grid GIS. Represented by Grid GIS, the next generation GIS has become the frontline and hot issue in both the academic community and the industrial sector. However, implementing Grid GIS is confronted with a great deal of challenges, among which Grid-based geospatial computational task processing is the key issue. This paper proposes a new conceptual framework for Grid-based geospatial computational task processing, i.e., a mechanism that efficiently processes the Grid-based geospatial computational task submitted by users and obtains reliable results so as to improve the geospatial information sharing and cooperative computation capability. Design issues for the proposed framework are discussed, and then some concluding remarks are presented.

Experiments and theoretical analysis demonstrate that the polarimetric scatterometer has the potential in enhancing the accuracy of the wind vector retrieval. However, currently, there is no special wind vector retrieval algorithm for the polarimetric scatterometer. Based on the distribution characteristic of the objective function, a modified wind vector retrieval algorithm was designed for the conically scanning polarimetric scatterometer in this paper. Simulation experiments indicated that this algorithm could further improve the retrieval precision of the polarimetric scatterometer in comparison with the traditional algorithm, especially in the nadir- and outer-swath. By extending the wind direction range for the first and second ambiguity in the nadir- and outer-swath, the algorithm can effectively reduce the uncertainty of the wind direction solutions with error magnitude of 0° to 15°. Up to 2° improvement in wind direction retrieval can be achieved in the nadir track.

Data Grid provides distributed resources for dealing with large-scale applications that generate huge volume data sets, while the Peer-to-Peer architecture provides the maximum autonomy and scalability. Combing their features, we have built a P2P Data Grid prototype as a high-available coordinated platform for storing, processing, and mining the massive Geospatial data. Replication strategy is the most challenging issue in building such systems, which includes the replica production, dissemination, location, selection, updating, synchronization and consistency maintaining. We exploit the replica production based on the spatial content, the replica dissemination based on DHT and directory, and the replica selection and maintenance problem in this paper.