Search Results (30)

Accurately measuring the six degrees of freedom (6-DoF) pose of a sample is a critical prerequisite for applications in robotic sample handling, optical metrology, and industrial quality control. Our pose estimation problem requires matching a small, partial observation of 4–20 discrete 3D points to a reference point set of up to 50 points. Popular registration algorithms such as Go-ICP, TEASER++, and MAC are designed for large-scale correspondence problems and do not perform reliably in our operating regime. Therefore, we propose an improved geometric hashing method that robustly estimates the rigid transformation in the presence of noise and outliers, and demonstrate its effectiveness and speed using both simulated and real-world datasets. Full article

Crash severity prediction is critical for emergency response, infrastructure spending, and risk communication. Although machine learning has been widely applied to this problem, three gaps prevent practical deployment: uncalibrated probability scores, SHAP-based explanations whose faithfulness has not been verified, and models never tested outside their training jurisdiction. The proposed framework, SAE-XCrash (Safety-Aware and Explainable Crash Severity Prediction), addresses all three using two public datasets—US-Accidents (7.0 million records, 2016–2023) and UK STATS19 (approximately 1,010,000 records, 2016–2022)—with strict temporal splits throughout. Notably, the US-Accidents severity label measures traffic disruption duration, not injury outcome; results should be interpreted accordingly. Previously unknown label-schema drift led to a revised binary target with Severity 4 as the only positive class. Five classifiers are compared. Post hoc isotonic calibration reduces Expected Calibration Error by 97.3% at negligible discrimination cost. A four-step quantitative SHAP audit confirms statistically significant deletion faithfulness; however, explanation stability fails at realistic perturbation levels (54.3% low-stability fraction at sigma = 0.05), driven by spatial data sparsity in sparse geohash cells—a negative result that carries direct operational implications for deployment. A three-tier cross-dataset transfer experiment (zero-shot, recalibration, full retrain) shows that temporal features transfer robustly across jurisdictions, while spatial memorization is the primary generalization barrier. All code, split indices, and model artifacts are publicly available. Full article

With the growing demand for precise absolute pose estimation of landers in lunar exploration missions, crater database-based navigation technology has become a core path to achieving this goal, but it faces challenges of low efficiency in large-scale data retrieval and insufficient matching robustness. To address these issues, a coarse-to-fine crater matching framework with database fast searching and robust triangle similarity matching is proposed. A Geo-KD search algorithm is designed to realize fast and accurate retrieval of craters within the field of view by combining Geohash and KD-tree. A robust triangle similarity matching algorithm is constructed through local neighborhood crater screening, triangle similarity matching, and mismatching elimination based on Random Sample Consensus (RANSAC) and Local Motion Consistency (LMC). Experiments show that the algorithm achieves an average retrieval time of 20 ms with an F₁-score of 0.8 for the global lunar database with 1.29 million craters. It has an F₁-score more than 0.746 and a single-frame matching time less than 1.005 s under lunar orbital phase, landing phase, and different camera pitch angles, outperforming other advanced algorithms and meeting on-orbit real-time requirements, providing reliable support for the absolute pose estimation of lunar probes. Full article

The growing frequency of extreme weather, earthquakes, fires, and environmental hazards underscores the need for real-time monitoring and predictive management at the urban scale. Conventional three-dimensional spatial information systems, which rely on orthophotos and ground surveys, often suffer from computational inefficiency and data overload when processing large and heterogeneous datasets. To address these limitations, this study introduces a three-dimensional GeoHash-based geocoding algorithm designed for lightweight, real-time, and attribute-driven digital twin operations. The proposed method comprises five integrated steps: generation of 3D GeoHash grids using longitude, latitude, and altitude coordinates; integration with GIS-based urban 3D models; level optimization using the Shape Overlap Ratio (SOR) with a threshold of 0.90; representative object labeling through weighted volume ratios; and altitude correction using DEM interpolation. Validation using a testbed in Sillim-dong, Seoul (10.19 km²), demonstrated that the framework achieved approximately 9.8 times faster 3D modeling performance than conventional orthophoto-based methods, while maintaining complete object recognition accuracy. The results confirm that the 3D GeoHash framework provides a unified spatial key structure that enhances data interoperability across querying, visualization, and simulation. This approach offers a practical foundation for operational digital twins, supporting high-efficiency 3D mapping and predictive disaster management toward resilient and data-driven urban systems. Full article

One of the most common problems in modern urban environments is traffic congestion, which leads to unreliable bus arrival times and passenger delays. In this study, we apply various machine learning models to predict traffic density with the aim of improving the accuracy of bus arrival time estimations. A large dataset comprising over 100,000 instances containing attributes such as date and time, maximum, minimum, and average speed, longitude, latitude, and geohash is utilized to classify traffic density as either “1 (High)” or “0 (Low).” We implement and compare five machine learning models: Logistic Regression, Gradient Boosting, Support Vector Machine (SVM), K-Nearest Neighbors (K-NN), and Naïve Bayes. The results demonstrate the potential of machine learning in reducing unnecessary delays and enhancing the accuracy of bus arrival predictions. This research contributes to improving the efficiency of public transportation systems in the future. Full article

High-definition (HD) maps are essential for safe and reliable autonomous driving, but their growing size and the need for real-time updates pose significant challenges for in-vehicle storage and communication efficiency. This study proposes a lightweight and scalable HD map provisioning system based on Geohash spatial indexing and Smart Roadside Units (Smart RSUs). The system divides HD map data into Geohash-based spatial blocks and enables vehicles to request only the map segments corresponding to their current location, reducing storage burden and communication load. To validate the system’s effectiveness, we constructed a simulation environment where multiple vehicle clients simultaneously request map data from a Smart RSU. Experimental results showed that the proposed Geohash-based approach achieved an average response time (RTT) of 1244.82 ms—approximately 296.3% faster than the conventional GPS-based spatial query method—and improved database query performance by 1072.6%. Additionally, we demonstrate the system’s scalability by adjusting Geohash levels according to road density, using finer blocks in urban areas and coarser blocks in rural areas. The hierarchical nature of Geohash also enables consistent integration of blocks with different resolutions. These results confirm that the proposed method provides an efficient and real-time HD map delivery framework suitable for dynamic and dense traffic environments. Full article

In modern fishery management, fishing vessel trajectory data are used to monitor and analyze fishing vessel activities. However, trajectory data are often of low quality, probably due to environmental factors, equipment failures, signal loss and operation errors, leading to numerous outliers in these data. These outliers not only undermine the credibility of the data but also negatively affect the subsequent data mining and decision-making. In this study, a data cleaning method for the identification of outlier points in fishing vessel trajectories based on the Geohash geocoding algorithm is given, which involves several key steps: obtaining and preprocessing the raw trajectory data; generating the corresponding Geohash codes for each ship position based on its latitude and longitude; calculating the reachable distance considering the time interval between the current point and the following points and their speeds; querying the neighborhood of the current point based on the reachable distance; and obtaining all Geohash codes of the reachable areas of the fishing vessels within the time interval as the reachable range grid set of the current position. The reachable range grid set of the current position is compared with the reachable range grid sets of the previous point identified as normal and the next point in the fishing vessel trajectory. If there is no intersection, it is determined that the current fishing vessel position is an outlier, and this point will be excluded. The method proposed in this study is able to effectively identify outliers in trajectory data, achieving efficient and effective trajectory data cleaning and improving the accuracy and reliability of the data. Full article

Accurate and robust visual localization is essential for autonomous lunar landing. This study presents a new crater-based method that addresses challenges posed by environmental uncertainties such as camera pose deviations, the number of craters within the scene, and the image brightness. Our method combines crater Geohash encoding for efficient database retrieval with an improved principal component analysis (PCA) for crater detection. The detected craters are ranked, retaining those with fewer but more accurate detections to meet localization requirements. Crucially, we introduce a consistency matching technique that exploits the linear relationship between position shifts and pixel offsets, enhancing both localization accuracy and computational efficiency. Experimental results across diverse scenes and simulation conditions demonstrate 100% matching accuracy with an average matching time under 0.8 s. Reprojection errors remain below 3 px, significantly outperforming methods like triangle similarity matching (TSM) and direct matching (DM). This validates the proposed method’s high precision and stability for near real-time lunar localization. Full article

The rapid advancement of the Internet of Things (IoT) and mobile devices has made location-based services (LBSs) increasingly prevalent, significantly improving daily convenience and work efficiency. However, this widespread usage has raised growing concerns about privacy and security, particularly during data outsourcing to cloud servers, where users’ location information and related data are susceptible to breaches by malicious actors or attackers. Traditional privacy-preserving spatial keyword schemes often employ Bloom filters for data encoding and storage. While Bloom filters offer high lookup speeds, they suffer from limitations such as a relatively high false positive rate in certain scenarios and poor space efficiency. These issues can adversely affect query accuracy and overall user experience. Furthermore, existing schemes have not sufficiently addressed the multi-attribute characteristics of spatial textual data. At the same time, relying solely on cloud servers for large-scale data processing introduces additional challenges, including heavy computational overhead, high latency, and substantial communication costs. To address these challenges, we propose a cloud–edge collaborative privacy-preserving dynamic spatial keyword query scheme with multi-attribute cost constraints. This scheme introduces a novel index structure that leverages security-enhanced Xor filter technology and Geohash techniques. This index structure not only strengthens query security and efficiency but also significantly reduces the false positive rate, thereby improving query accuracy. Moreover, the proposed scheme supports multi-attribute cost constraints and dynamic data updates, allowing it to adapt flexibly to practical requirements and user-specific needs. Finally, through security analysis and experimental evaluation, we demonstrate that the proposed scheme is both secure and effective. Full article

Timely, region-based geo-maps like choropleths are essential for smart city applications like traffic monitoring and urban planning because they can reveal statistical patterns in geotagged data. However, because data overloading is brought on by the quick inflow of massive geospatial data, creating these visualizations in real time presents serious difficulties. This paper introduces ApproxGeoMap, a novel system designed to efficiently generate approximate geo-maps from fast-arriving georeferenced data streams. ApproxGeoMap employs a stratified spatial sampling method, leveraging geohash tessellation and Earth Mover’s Distance (EMD) to maintain both accuracy and processing speed. We developed a prototype system and tested it on real-world smart city datasets, demonstrating that ApproxGeoMap meets time-based and accuracy-based quality of service (QoS) constraints. Results indicate that ApproxGeoMap significantly enhances efficiency in both running time and map accuracy, offering a reliable solution for high-speed data environments where traditional methods fall short. Full article

This study introduces a method for classifying traffic flow segments on expressways to estimate impact zones in merging/diverging sections and accident-prone sites. I propose a spatiotemporal dynamic segmentation approach that enables real-time identification of traffic hazard sections, reflecting changes in traffic flow, as opposed to traditional traffic analysis based on predefined segments in a node–link network. This methodology uses high-resolution vehicle trajectory data to precisely identify unstable and low-speed traffic sections. Using the geohash algorithm, the area is hierarchically segmented based on the standard deviation of speed in general traffic flow, facilitating the identification of unstable traffic flow patterns. For eight expressway routes, traffic flow was categorized into stable or minimum-size spaces. From a total of 1207 segments, 943 unstable flow segments were identified. The impact zones of the merging and diverging sections on Expressway 50 were analyzed using the results of spatial segmentation. Furthermore, by comparing traffic data before and after accidents, I assessed the short- and long-term effects of accidents on traffic flow. The proposed methodology provides precise data essential for reducing the likelihood of traffic accidents and for predicting post-accident congestion and duration. The patterns of such accident impact zones can contribute to preventing secondary accidents by providing advance information to following vehicles through various communication methods, including those involving autonomous vehicles. This enables effective traffic management strategies and rapid responses to accidents. Full article

Linear spatial data are primarily used in Geographic Information Systems (GISs) to represent spatial data in the form of roads, rivers, railways, and utility lines. Linear spatial data are mostly composed of one-dimensional linear elements, incorporating geometric attributes such as location, direction, and length, as well as the interconnections of these elements. In the case of roads, this information is used to map and analyze traffic data, such as vehicle movements, on the road network. This study aims to propose an area-based spatial analysis method that allows for the flexible application of analysis scales using individual vehicle data, as opposed to node and link generation for linear road networks. The analysis focused on nine expressways, conducting a microscopic analysis of speed-homogeneous sections. The final analysis showed that out of 375 cells, 91 cells in the final 12 division cells did not meet the homogeneity criteria. This discrepancy was ascertained to be due to vehicles decelerating or accelerating when entering or exiting highways at ramps or interchanges, not due to directional speed differences but lane-specific speed variations. The final cells with large speed deviations were found to be influenced by connections to highway on-ramps or off-ramps. In contrast, sections with small speed variations within a cell were influenced by traffic factors such as connection points and traffic volume, which hindered normal driving. As a result, this study validated that traffic information from highways, typically provided as linear data, could be divided into cells based on real-time GPS speed data and presented on an area-based scale. While dividing regions based on fixed intervals does not pinpoint exact speed change points, this study found that reasonable segmentation is possible based on spatial size and speed-homogeneous sections. Full article

Spatiotemporal big data contain information in multiple dimensions such as space and time. Spatiotemporal data have the characteristics of large volume, intricate spatiotemporal relationship, and uneven spatiotemporal distribution. Index structure is one of the most important technologies used to improve system data analysis and workload. However, it is difficult to dynamically adjust with data density, resulting in increased maintenance costs and retrieval complexity. At the same time, maintaining the proximity of spatiotemporal data in spatial or temporal dimensions is crucial for efficient spatiotemporal analysis. To address these challenges, this paper proposes a learned index method, GLMI (Geohash and piecewise linear model-based index for spatiotemporal data). GLMI uses dynamic space partitioning based on the Hilbert curve to reduce the impact of data skew on index performance. In the time dimension, a piecewise linear model was constructed using the ShrinkingCone algorithm, and a buffer was designed to support the fast writing of spatiotemporal data. Compared with the current mainstream traditional high-dimensional indexes and the ZM index, GLMI has a smaller space consumption and shorter construction time compared to high-dimensional learned indexes on real traffic itinerary and trajectory record datasets. Meanwhile, GLMI also has an advantage in query efficiency. Full article

Remote sensing image is a vital basis for land management decisions. The protection of remote sensing images has seen the application of blockchain’s notarization function by many scholars. Yet, research on efficient retrieval of such images on the blockchain remains sparse. Addressing this issue, this paper introduces a blockchain-based spatial index verification method using Hyperledger Fabric. It linearizes the spatial information of remote sensing images via Geohash and integrates it with LSM trees for effective retrieval and verification. The system also incorporates IPFS as an underlying storage unit for Hyperledger Fabric, ensuring the safe storage and transmission of images. The experiments indicate that this method significantly reduces the latency in data retrieval and verification without impacting the write performance of Hyperledger Fabric, enhancing throughput and providing a solid foundation for efficient blockchain-based verification of remote sensing images in land registry systems. Full article

This paper presents a novel geohash-based approach for predicting traffic incident locations using machine learning algorithms. The study utilized a three-stage model for predicting the locations of traffic incidents, which encompassed accidents, breakdowns, and other incidents. In the model, firstly, ArcGIS was used to convert the coordinates of traffic incidents into geohash areas, leading to the definition of incident locations. Secondly, variables affecting traffic incidents were extracted, and a dataset was created by utilizing the values of these variables in geohash fields. Finally, machine learning algorithms such as decision tree (DT), k-nearest neighbor (k-NN), random forest (RF), and support vector machine (SVM) algorithms were used to predict the geohash region of traffic incidents. After conducting hyperparameter optimization, we evaluated the efficacy of various machine learning algorithms in predicting the location of traffic incidents using different evaluation metrics. Our findings indicate that the RF, SVM, and DT models performed the best, with accuracy percentages of 91%, 88%, and 87%, respectively. The findings of the research revealed that traffic incident locations can be successfully predicted with the geohash-based forecasting model. The results offer traffic managers and emergency responders new perspectives on how to manage traffic incidents more effectively and improve drivers’ safety. Full article