Search Results (61)

Pedestrian intrusion in coal yard work areas is a major cause of accidents, posing challenges for the safe supervision of coal yards. Existing visual detection methods suffer under poor lighting and a lack of 3D data. To overcome these limitations, this study introduces a robust pedestrian intrusion detection method based on 3D LiDAR. Our approach consists of three main components. First, we propose a novel pedestrian detection network called EFT-RCNN. Based on Voxel-RCNN, this network introduces an EnhancedVFE module to improve spatial feature extraction, employs FocalConv to reconstruct the 3D backbone network for enhanced foreground–background distinction, and utilizes TeBEVPooling to optimize bird’s eye view (BEV) generation. Second, a precise 3D hazardous area is defined by combining a polygonal base surface, determined through on-site exploration, with height constraints. Finally, a point–region hierarchical judgment method is designed to calculate the spatial relationship between pedestrians and the hazardous area for graded warning. When evaluated on the public KITTI dataset, the EFT-RCNN network improved the average precision for pedestrian detection by 4.39% in 3D and 4.68% in BEV compared with the baseline, while maintaining a real-time processing speed of 28.56 FPS. In practical tests, the pedestrian detection accuracy reached 92.9%, with an average error in distance measurement of 0.054 m. The experimental results demonstrate that the proposed method effectively mitigates complex environmental interference, enables robust detection, and provides a reliable means for the proactive prevention of pedestrian intrusion accidents. Full article

Traditional unmanned aerial vehicle (UAV) path planning methods for image-based 3D reconstruction often rely solely on geometric information from initial models, resulting in redundant data acquisition in non-architectural areas. This paper proposes a UAV path planning method via semantic segmentation of 3D reality mesh models to enhance efficiency and accuracy in complex scenarios. The scene is segmented into buildings, vegetation, ground, and water bodies. Lightweight polygonal surfaces are extracted for buildings, while planar segments in non-building regions are fitted and projected into simplified polygonal patches. These photography targets are further decomposed into point, line, and surface primitives. A multi-resolution image acquisition strategy is adopted, featuring high-resolution coverage for buildings and rapid scanning for non-building areas. To ensure flight safety, a Digital Surface Model (DSM)-based shell model is utilized for obstacle avoidance, and sky-view-based Real-Time Kinematic (RTK) signal evaluation is applied to guide viewpoint optimization. Finally, a complete weighted graph is constructed, and ant colony optimization is employed to generate a low-energy-cost flight path. Experimental results demonstrate that, compared with traditional oblique photogrammetry, the proposed method achieves higher reconstruction quality. Compared with the commercial software Metashape, it reduces the number of images by 30.5% and energy consumption by 37.7%, while significantly improving reconstruction results in both architectural and non-architectural areas. Full article

Secret sharing is a robust data protection technique that secures sensitive information by partitioning it into multiple shares, such that the original data can only be reconstructed when a sufficient number of shares are combined. While this method has seen remarkable progress in the realm of images, its exploration and application in 3D models remain in their early stages. Given the growing prominence of 3D models in multimedia applications, ensuring their security and privacy has emerged as a critical area of research. At present, secret sharing approaches for 3D models predominantly rely on the vertex coordinates of the model as the basis for embedding and reconstructing secret messages. However, due to the limited quantity of vertex coordinates, these methods face significant constraints in embedding capacity, thereby limiting the potential of 3D models in secure data sharing. In contrast, the vertex indices of polygons, characterized by higher information density and greater structural flexibility, present a promising alternative medium for embedding secret shares. Building on this premise, the present study investigates the feasibility of leveraging shared vertex indices as a foundation for message embedding. It highlights the advantages of this approach in enhancing both the embedding capacity and the overall security of 3D models. By integrating the Chinese Remainder Theorem into vertex index-based sharing, the proposed method strengthens existing algorithms, offering improved model protection and enhanced embedding security. Experimental evaluations reveal that, compared to traditional vertex coordinate-based methods, incorporating vertex indices into secret sharing techniques significantly increases embedding efficiency while bolstering the security of 3D models. This study not only introduces an innovative approach to safeguarding 3D model data but also paves the way for the broader application of secret sharing techniques in the future. Full article

Simplifying building contours involves reducing data volume while preserving the continuity, accuracy, and essential characteristics of building shapes. This presents significant challenges for sequence representation and generation. Traditional methods often rely on complex rule design, feature engineering, and iterative optimization. To overcome these limitations, this study proposes a Transformer-based Polygon Simplification Model (TPSM) for the end-to-end vector simplification of building contours. TPSM processes ordered vertex coordinate sequences of building contours, leveraging the inherent sequence modeling capabilities of the Transformer architecture to directly generate simplified coordinate sequences. To enhance spatial understanding, positional encoding is embedded within the multihead self-attention mechanism, allowing the TPSM to effectively capture relative vertex positions. Additionally, a self-supervised reconstruction mechanism is introduced, where random perturbations are applied to input sequences, and the model learns to reconstruct the original contours. This mechanism enables TPSM to better understand underlying geometric relationships and implicit simplification rules. Experiments were conducted using a 1:10,000 building dataset from Shenzhen, China, targeting a simplification scale of 1:25,000. The results demonstrate that TPSM outperforms five established simplification algorithms in controlling changes to building area, orientation, and shape fidelity, achieving an average intersection over union (IoU) of 0.901 and a complexity-aware IoU (C-IoU) of 0.735. Full article

Point cloud data, known for their accuracy and ease of acquisition, are commonly used for reconstructing level of detail 2 (LoD-2) building models. However, factors like object occlusion can cause incompleteness, negatively impacting the reconstruction process. To address this challenge, this paper proposes a method for reconstructing LoD-2 building models from incomplete point clouds. We design a generative adversarial network model that incorporates geometric constraints. The generator utilizes a multilayer perceptron with a curvature attention mechanism to extract multi-resolution features from the input data and then generates the missing portions of the point cloud through fully connected layers. The discriminator iteratively refines the generator’s predictions using a loss function that is combined with plane-aware Chamfer distance. For model reconstruction, the proposed method extracts a set of candidate polygons from the point cloud and computes weights for each candidate polygon based on a weighted energy term tailored to building characteristics. The most suitable planes are retained to construct the LoD-2 building model. The performance of this method is validated through extensive comparisons with existing state-of-the-art methods, showing a 10.9% reduction in the fitting error of the reconstructed models, and real-world data are tested to evaluate the effectiveness of the method. Full article

Polygon reconstruction is widely used across various fields. Although the current polygon reconstruction algorithms have achieved near-linear time complexity, they still fail to meet the speed demands imposed by the exponential growth in polygon numbers. The development of GPU technology provides a promising solution to this issue. This paper proposes a GPU-based algorithm that leverages hash tables and memory pools to transform the polygon reconstruction problem into an efficiently parallelizable task. Experimental results on Nvidia RTX 2080Ti demonstrate that the new algorithm achieves 17× and 46× speedups on Manhattan and non-Manhattan polygon test sets, respectively. Compared to traditional CPU algorithms, the new algorithm significantly improves processing speeds, especially when handling layouts with complex polygons. It demonstrates strong scalability and performance advantages, providing crucial support for enhancing the overall efficiency of CAD tools. Full article

Three-dimensional indoor models have wide applications in fields such as indoor navigation, civil engineering, virtual reality, and so on. With the development of LiDAR technology, automatic reconstruction of indoor models from point clouds has gained significant attention. We propose a new framework for generating indoor 3D digital models from point clouds. The proposed method first generates a room instance map of an indoor scene. Walls are detected and projected onto a horizontal plane to form line segments. These segments are extended, intersected, and, by solving an integer programming problem, line segments are selected to create room polygons. The polygons are converted into a raster image, and image connectivity detection is used to generate a room instance map. Then the roofs of the point cloud are extracted and used to perform an overlap analysis with the generated room instance map to segment the entire roof point cloud, obtaining the roof for each room. Room boundaries are defined by extracting and regularizing the roof point cloud boundaries. Finally, by detecting doors and windows in the scene in two steps, we generate the floor plans and 3D models separately. Experiments with the Giblayout dataset show that our method is robust to clutter and furniture point clouds, achieving high-accuracy models that match real scenes. The mean precision and recall for the floorplans are both 0.93, and the Point–Surface Distance (PSD) and standard deviation of the PSD for the 3D models are 0.044 m and 0.066 m, respectively. Full article

In this paper, a layered method based on focal depth is proposed for the fast generation of computational holograms. The method layers objects with focal depth as spacing and approximates triangles on the object as projections on the layers based on the physical properties of the focal depth to simplify the computation. Finally, the diffraction distributions of all layers are calculated via angular spectral diffraction and superimposed to obtain the hologram. The proposed method has been proven to be about 20 times faster on a CPU than the analytical polygon-based method. A hologram containing tens of thousands of triangles can be computed on a GPU in a fraction of a second. In addition, this method makes it easy to attach complex textures, which is difficult with polygon-based analysis methods. Finally, holograms of objects with complex textures were generated, and the three-dimensionality of these holograms was confirmed by numerical and optical reconstruction. Full article

Patient-specific 3D models of the human mandible are finding increasing utility in medical fields such as oral and maxillofacial surgery, orthodontics, dentistry, and forensic sciences. The efficient creation of personalized 3D bone models poses a key challenge in these applications. Existing solutions often rely on 3D statistical models of human bone, offering advantages in rapid bone geometry adaptation and flexibility by capturing a range of anatomical variations, but also a disadvantage in terms of reduced precision in representing specific shapes. Considering this, the proposed parametric model allows for precise manipulation using morphometric parameters acquired from medical images. This paper highlights the significance of employing the parametric model in the creation of a personalized bone model, exemplified through a case study targeting mandibular prognathism reconstruction. A personalized model is described as 3D point cloud determined through the utilization of series of parametric functions, determined by the application of geometrical morphometrics, morphology properties, and artificial neural networks in the input dataset of human mandible samples. With 95.05% of the personalized model’s surface area displaying deviations within −1.00–1.00 mm relative to the input polygonal model, and a maximum deviation of 2.52 mm, this research accentuates the benefits of the parametric approach, particularly in the preoperative planning of mandibular deformity surgeries. Full article

The aim of the paper is to identify an efficient method for transforming the point cloud into parametric objects in the fields of architecture, engineering and construction by four main steps: 3D survey of the structure under investigation, generation of a new point cloud based on feature extraction and identification of suitable threshold values, geometry reconstruction by semi-automatic process performed in Rhinoceros/Grasshopper and BIM implementation. The developed method made it possible to quickly obtain geometries that were very realistic to the original ones as shown in the case study described in the paper. In particular, the application of ShrinkWrap algorithm on the simplify point cloud allowed us to obtain a polygonal mesh model without errors such as holes, non-manifold surfaces, compenetrating surfaces, etc. Full article

This study presents the creation of a virtual reality experience for the Museo Preistorico dei Balzi Rossi e Zona Archeologica (hence Balzi Rossi Museum) commemorating the centenary of Prince Albert I Grimaldi’s archaeological work at the site. The project aims to preserve and convey the site’s heritage through advanced VR technology. Photogrammetry was used for 3D reconstruction of the entire Balzi Rossi coastal cliffs, including the notable “Caviglione” and “Florestano” caves, known for their upper Paleolithic rock engravings. Two subsequent development phases produced the final public VR experience, incorporating Nanite technology for enhanced visual fidelity. This advancement resulted in a more detailed and immersive VR experience, presenting the Balzi Rossi cliffs across different historical periods, including the Würm glaciation. Key to this phase was optimizing the VR experience for performance, focusing on stable frame rates and minimizing motion sickness, and integrating a multi-lingual interface for broader accessibility. Since November 2023, the VR setup at Balzi Rossi Museum has been an educational and interactive feature enabling visitors to virtually explore the site’s history. This study aims to describe a process for optimizing and enabling the creation of VR experiences while maintaining a high polygon count within the context of small teams. Full article

Comparison of the ⁸⁷Sr/⁸⁶Sr signatures of archaeological osteological material with features of geological provinces can be applied to determine the places of birth and living of individuals. Such reconstructions were conducted for both humans and domestic animals at the Late Bronze–Early Iron Age sites of the Crimea. The Crimean Peninsula is an interesting testing polygon for such research because it is characterized by a diverse geological situation within a relatively small area. The initial data allowed us to distinguish between three groups of mobility at the Bai-Kiyat I settlement and two groups at the Dolgii Bugor site. The Bai-Kiyat I site is located on the seacoast, so the proxy line for this area will correspond to the value of the ratio of strontium isotopes in seawater (0.7092). The inhabitants of this settlement, including a child from a burial on the settlement, are characterized by this value of strontium isotopes. Other groups include nonlocal people. The data obtained indicate that the steppe zone of the Northern Black Sea region was an ecumene, within which active mobility of groups of people was registered. This mobility is associated primarily with the pastoral type of economy in the period from the Chalcolithic to the Early Iron Age. Full article

This work explores the possibility of automating the aerial survey of bridges to generate high-resolution images necessary for digital damage inspection. High-quality unmanned aerial vehicle (UAV) based 3D reconstruction of bridges is an important step towards autonomous infrastructure inspection. However, the calculation of optimal camera poses remains challenging due to the complex structure of bridges and is therefore often conducted manually. This process is time-consuming and can lead to quality losses. Research in this field to automate this process is yet sparse and often requires high informative models of the bridge as the base for calculations, which are not given widely. Therefore, this paper proposes an automated camera pose calculation method solely based on an easily accessible polygon mesh of the bridge. For safe operation, point cloud data of the environment are used for automated ground detection and obstacle avoidance including vegetation. First, an initial set of camera poses is generated based on a voxelized mesh created in respect to the quality requirements for 3D reconstruction using defined camera specification. Thereafter, camera poses not fulfilling safety distances are removed and specific camera poses are added to increase local coverage quality. Evaluations of three bridges show that for diverse bridge types, near-complete coverage was achieved. Due to the low computational effort of the voxel approach, the runtime was kept to a minimum, even for large bridges. The subsequent algorithm is able to find alternative camera poses even in areas where the optimal pose could not be placed due to obstacles. Full article

Delineating and modelling building roof plane structures is an active research direction in urban-related studies, as understanding roof structure provides essential information for generating highly detailed 3D building models. Traditional deep-learning models have been the main focus of most recent research endeavors aiming to extract pixel-based building roof plane areas from remote-sensing imagery. However, significant challenges arise, such as delineating complex roof boundaries and invisible boundaries. Additionally, challenges during the post-processing phase, where pixel-based building roof plane maps are vectorized, often result in polygons with irregular shapes. In order to address this issue, this study explores a state-of-the-art method for planar graph reconstruction applied to building roof plane extraction. We propose a framework for reconstructing regularized building roof plane structures using aerial imagery and cadastral information. Our framework employs a holistic edge classification architecture based on an attention-based neural network to detect corners and edges between them from aerial imagery. Our experiments focused on three distinct study areas characterized by different roof structure topologies: the Stadsveld–‘t Zwering neighborhood and Oude Markt area, located in Enschede, The Netherlands, and the Lozenets district in Sofia, Bulgaria. The outcomes of our experiments revealed that a model trained with a combined dataset of two different study areas demonstrated a superior performance, capable of delineating edges obscured by shadows or canopy. Our experiment in the Oude Markt area resulted in building roof plane delineation with an F-score value of 0.43 when the model trained on the combined dataset was used. In comparison, the model trained only on the Stadsveld–‘t Zwering dataset achieved an F-score value of 0.37, and the model trained only on the Lozenets dataset achieved an F-score value of 0.32. The results from the developed approach are promising and can be used for 3D city modelling in different urban settings. Full article

The main population of ~5000 threatened Gunnison sage-grouse (GUSG; Centrocercus minimus) in Colorado depends on sagebrush plants that are killed by wildfires, with recovery taking decades, so frequent fire is a threat, but did it occur historically? Early land surveys showed that the historical (preindustrial) fire rotation (FR), the expected period to burn area equal to a focal land area, was 90–143 years in GUSG ranges, which is not classed as frequent fire (≤25 years). However, recent research, based on fire scars on trees at ten sites near sagebrush, suggested some frequent fire historically in the main population. That study was not spatial, essential to estimate FR, so spatial data were created in GIS with land-survey reconstructions, survey dates, fire-scar sites, mapped sagebrush, and Thiessen polygons around sites. The previous study assumed fires that burned 2+ sites likely burned across sagebrush. Historical FRs were calculated several ways over a common period. A recovery estimate of FR was 90–135 years, a land-survey estimate was 82–131 years, and three spatial scar-based estimates were 93–107 years, showing agreement. However, the comparison found that only 8.8% of the land-survey fire area was detected at fire-scar sites. Detailed analysis showed that 10 fire-scar sites were insufficient to detect historical fire sizes and distributions across the large 168,753 ha sagebrush area. Adequate fire reconstruction could require ~45–60 fire-scar sites, making it feasible to study only ~30,000 ha of sagebrush. Using the two remaining methods, which cross-validate, showed frequent fire did not occur historically in the study area, as historical FRs were 82–135 years. Full article