3D Scene Data Research Articles

Retracted: 3D Real Scene Data Collection of Cultural Relics and Historical Sites Based on Digital Image Processing.

[This retracts the article DOI: 10.1155/2022/9471720.].

Assessing the visibility of urban greenery using MLS LiDAR data

Given the ecological, cultural and psychological functions of urban vegetation, a growing number of studies have focused on daily accessible greenery visibility. Mobile laser scanning (MLS) can rapidly obtain dense point clouds that can be used to extract vegetation. To address this issue, we propose a novel method for calculating the green view index (GVI) based on MLS three-dimensional (3D) point clouds. In our study, the GVI was specified as the ratio of greenery viewing angles to the total number of viewing angles in view. The GVI calculation procedure was as follows. First, the vegetation points were extracted using the density-based spatial clustering of applications with noise (DBSCAN) algorithm and the PointNet++ deep learning algorithm. Second, based on the GVI specification, a virtual camera was constructed in a 3D point scenario to estimate greenery viewing angles in view and generate depth images, and then, the GVI value was calculated. This method is flexible and can be used to calculate the GVI at any site with any direction where 3D point scene data are available, and thus, it is suitable for evaluating various types of urban greenery. We conducted a case human-centered assessment of road greenery in a partial area of Jinshan District in Fuzhou, China, based on MLS point clouds, evaluating visible greenery and analyzing the relations among the GVI, greening pattern, and road green belt mode. The results showed that the overall visible greenery in the study area was good and that the GVI value of most road sections was more than 15 %. The method has potential for urban green space planning and management.

3D Real Scene Data Collection of Cultural Relics and Historical Sites Based on Digital Image Processing.

Traditional digital geometry mainly focuses on local geometric features such as curvature and normal of 3D models. Although the curvature can describe the geometric curvature of the model surface, these local geometric properties cannot describe the global functional structure and associated properties of the 3D model. The purpose of this paper was to study the accurate splicing of cultural relic fragments based on the intrinsic structural features of the 3D model, such as geometry, texture, and function, whose method is the key to realizing the virtual reconstruction of damaged cultural relics. In this paper, a method for analyzing the intrinsic structure of 3D point cloud data is proposed, the feature representation method of 3D discrete curves and surfaces is studied, and a method for identifying geometric features of 3D point clouds based on the similarity measure of the principal curvature is proposed, which realizes the effective extraction of geometric features of the 3D point cloud model of cultural relics. By calculating the visual curvature distribution of the model under multiscale constraints, the effective extraction of the structural primitives of cultural relics with rich surface noise is realized. The experimental results in this paper show that the initial matching time is 1.416 seconds, the final matching time is 1.555 seconds, the average number of iterations is 13, the average stitching error is 1.7233 mm, and the standard deviation is 1.0265 mm. The experimental data show that the algorithm proposed in this chapter has good convergence characteristics and effectively avoids the divergence phenomenon that is easy to occur in the existing stitching algorithms.

Research on Big Data Traffic Operation Based on Intelligent Holographic 3D Image Vision

Aiming at the needs of refined and visualized management of transportation infrastructure, the 3D hologram acquisition technology integrating 3D laser scanning, tilt photogrammetry, and other technologies are used to acquire and integrate the 3D scene data of transportation infrastructure through indoor and outdoor and air and ground integration and build a 3D hologram spatial model that comprehensively reflects the three-dimensional information of transportation infrastructure. The technical solution for the acquisition, integration, and management of transport infrastructure data is formed. Through research and practice, it can be proved that the integrated indoor and outdoor 3D hologram data technology of transportation infrastructure can explore the technical basis for the comprehensive construction of 3D hologram data of transportation infrastructure and can effectively expand the data content of the transportation geographic information service platform and provide stronger technical support for the province's transportation industry management, operation monitoring, emergency disposal, and public services.

A comparison of methods for 3D scene shape retrieval

3D scene shape retrieval is a brand new but important research direction in content-based 3D shape retrieval. To promote this research area, two Shape Retrieval Contest (SHREC) tracks on 2D scene sketch-based and image-based 3D scene model retrieval have been organized by us in 2018 and 2019, respectively. In 2018, we built the first benchmark for each track which contains 2D and 3D scene data for ten (10) categories, while they share the same 3D scene target dataset. Four and five distinct 3D scene shape retrieval methods have competed with each other in these two contests, respectively. In 2019, to measure and compare the scalability performance of the participating and other promising Query-by-Sketch or Query-by-Image 3D scene shape retrieval methods, we built a much larger extended benchmark for each type of retrieval which has thirty (30) classes and organized two extended tracks. Again, two and three different 3D scene shape retrieval methods have contended in these two tracks, separately. To solicit state-of-the-art approaches, we perform a comprehensive comparison of all the above methods and an additional new retrieval methods by evaluating them on the two benchmarks. The benchmarks, evaluation results and tools are publicly available at our track websites (Yuan et al., 2019 [1]; Abdul-Rashid et al., 2019 [2]; Yuan et al., 2019 [3]; Abdul-Rashid et al., 2019 [4]), while code for the evaluated methods are also available: http://github.com/3DSceneRetrieval.

Building hierarchical structures for 3D scenes based on normalized cut

AbstractThe growing number of 3D scene data available online brings in new challenges for scene retrieval, understanding, and synthesis. Traditional shape processing methods have difficulty to manage 3D scenes because such methods ignore the contextual information, that is, the spatial relationship between the objects or groups of objects, which plays a significant role in describing scenes. Therefore, a context‐aware representation is needed to deal with such a problem. In this paper, we propose a method to build scene hierarchies based on contextual information. Given a 3D scene, we first use the interaction bisector surface to measure the affinity between different objects/elements of the scene and then apply the normalized cut method to build a hierarchical structure for the whole scene. The resulting hierarchical structure contains not only the relationship between the individual objects but also the relationship between object groups, which provides much richer information of the scene compared with a flat structure that only describes the contacts or affinity between the individual objects. We test our method using several public databases and show that the resulting structure is more consistent with the ground truth. We also show that our method can be used for point cloud segmentation and outperforms previous methods.

OPTIMIZED ORGANIZATION AND ADAPTIVE VISUALIZATION OF COMPLICATED MOUNTAIN DISASTER 3D SCENES FOR DIVERSE TERMINALS

Abstract. Mountain disaster scenes usually contains various geographical entities, which are dynamic and complicated. Therefore, the construction of mountain disaster 3D scenes has great significance for disaster simulation, analysis and prediction. 3D visualization and interactive analysis of complicated mountain disaster scenes should accommodate users who have access to various terminals in disaster emergency response. However, most of the existing 3D visualization methods can only deal with 3D scene data organization and scheduling for single terminal or limited kinds of geographical entities. Due to performance constraints, it’s difficult for Mobile devices to support efficient visualization of complicated mountain disaster 3D scenes, either. To address these issues, we research the key technologies for efficient visualization of mountain disasters on diverse terminals. We utilize the B/S architecture and research its impact on rendering frame rate and the relationship of terminal characteristics and parameters through analysis of terminal characteristics and parameters, e.g. hardware performance, screen size and resolution, network environment, and rendering frame rate requirements. Then we analyze the diverse organization of mountain disaster scene data and explore the methods of constructing efficient spatial index by taking into account the characteristics of diverse terminals. An adaptive scene analysis method is subsequently designed to select the optimal model. Finally, based on the diverse organization of various data in the scene, a corresponding dynamic scheduling method is proposed to realize the adaptive visualization of complicated mountain disaster 3D scenes for diverse terminals.

A Robust 3D-2D Interactive Tool for Scene Segmentation and Annotation.

Recent advances of 3D acquisition devices have enabled large-scale acquisition of 3D scene data. Such data, if completely and well annotated, can serve as useful ingredients for a wide spectrum of computer vision and graphics works such as data-driven modeling and scene understanding, object detection and recognition. However, annotating a vast amount of 3D scene data remains challenging due to the lack of an effective tool and/or the complexity of 3D scenes (e.g. clutter, varying illumination conditions). This paper aims to build a robust annotation tool that effectively and conveniently enables the segmentation and annotation of massive 3D data. Our tool works by coupling 2D and 3D information via an interactive framework, through which users can provide high-level semantic annotation for objects. We have experimented our tool and found that a typical indoor scene could be well segmented and annotated in less than 30 minutes by using the tool, as opposed to a few hours if done manually. Along with the tool, we created a dataset of over a hundred 3D scenes associated with complete annotations using our tool. Both the tool and dataset will be available at http://scenenn.net.

Toward the Physical-Information Fundamentals of Three-Dimensional Displays

The well-known groups of information three-dimensional displays (further—3D displays) with habitual names “stereoscopic,” “holographic,” “volumetric,” “integral imaging,” “light field,” etc., were historically formed without any common classification criteria. However, 3D displays as physical (optical) information systems should have the fundamental classification criteria. Such criteria are introduced in this paper in the form of physical-information modalities (further – modalities) identifying the physical-information formats of 3D image recordings in the working media of 3D displays. The modalities are based on four physical-information categories defined as four possible combinations of two kinds of 3D scene data representation (the object O representation and the representation by angular spectrum S of spherical waves) and two physical forms of each representation implementation (the ray optics R and diffraction optics D concepts). The modality of 3D display defines the primary physical-information properties of 3D image recording in the working medium. The true 3D image properties follow from the primary ones taking into account the relevant psychophysiological properties of the human visual system. The human visual system directly perceives 3D image light distribution that have passed through the optical scheme of 3D display after exiting the working medium. The limits of the proposed theory are discussed.

SceneGrok

With modern computer graphics, we can generate enormous amounts of 3D scene data. It is now possible to capture high-quality 3D representations of large real-world environments. Large shape and scene databases, such as the Trimble 3D Warehouse, are publicly accessible and constantly growing. Unfortunately, while a great amount of 3D content exists, most of it is detached from the semantics and functionality of the objects it represents. In this paper, we present a method to establish a correlation between the geometry and the functionality of 3D environments. Using RGB-D sensors, we capture dense 3D reconstructions of real-world scenes, and observe and track people as they interact with the environment. With these observations, we train a classifier which can transfer interaction knowledge to unobserved 3D scenes. We predict a likelihood of a given action taking place over all locations in a 3D environment and refer to this representation as an action map over the scene. We demonstrate prediction of action maps in both 3D scans and virtual scenes. We evaluate our predictions against ground truth annotations by people, and present an approach for characterizing 3D scenes by functional similarity using action maps.

Scalable Multi-Platform Distribution of Spatial 3D Contents

Virtual 3D city models provide powerful user interfaces for communication of 2D and 3D geoinformation. Providing high quality visualization of massive 3D geoinformation in a scalable, fast, and cost efficient manner is still a challenging task. Especially for mobile and web-based system environments, software and hardware configurations of target systems differ significantly. This makes it hard to provide fast, visually appealing renderings of 3D data throughout a variety of platforms and devices. Current mobile or web-based solutions for 3D visualization usually require raw 3D scene data such as triangle meshes together with textures delivered from server to client, what makes them strongly limited in terms of size and complexity of the models they can handle. This paper introduces a new approach for provisioning of massive, virtual 3D city models on different platforms namely web browsers, smartphones or tablets, by means of an interactive map assembled from artificial oblique image tiles. The key concept is to synthesize such images of a virtual 3D city model by a 3D rendering service in a preprocessing step. This service encapsulates model handling and 3D rendering techniques for high quality visualization of massive 3D models. By generating image tiles using this service, the 3D rendering process is shifted from the client side, which provides major advantages: (a) The complexity of the 3D city model data is decoupled from data transfer complexity (b) the implementation of client applications is simplified significantly as 3D rendering is encapsulated on server side (c) 3D city models can be easily deployed for and used by a large number of concurrent users, leading to a high degree of scalability of the overall approach. All core 3D rendering techniques are performed on a dedicated 3D rendering server, and thin-client applications can be compactly implemented for various devices and platforms.

SCALABLE MULTI-PLATFORM DISTRIBUTION OF SPATIAL 3D CONTENTS

Abstract. Virtual 3D city models provide powerful user interfaces for communication of 2D and 3D geoinformation. Providing high quality visualization of massive 3D geoinformation in a scalable, fast, and cost efficient manner is still a challenging task. Especially for mobile and web-based system environments, software and hardware configurations of target systems differ significantly. This makes it hard to provide fast, visually appealing renderings of 3D data throughout a variety of platforms and devices. Current mobile or web-based solutions for 3D visualization usually require raw 3D scene data such as triangle meshes together with textures delivered from server to client, what makes them strongly limited in terms of size and complexity of the models they can handle. In this paper, we introduce a new approach for provisioning of massive, virtual 3D city models on different platforms namely web browsers, smartphones or tablets, by means of an interactive map assembled from artificial oblique image tiles. The key concept is to synthesize such images of a virtual 3D city model by a 3D rendering service in a preprocessing step. This service encapsulates model handling and 3D rendering techniques for high quality visualization of massive 3D models. By generating image tiles using this service, the 3D rendering process is shifted from the client side, which provides major advantages: (a) The complexity of the 3D city model data is decoupled from data transfer complexity (b) the implementation of client applications is simplified significantly as 3D rendering is encapsulated on server side (c) 3D city models can be easily deployed for and used by a large number of concurrent users, leading to a high degree of scalability of the overall approach. All core 3D rendering techniques are performed on a dedicated 3D rendering server, and thin-client applications can be compactly implemented for various devices and platforms.

Scene modelling from sparse 3D data

Sparse 3D measurements of real scenes are readily estimated from N-view image sequences using structure-from-motion techniques. In this paper, we present a geometric theory for reconstruction of surface models from sparse 3D data captured from N camera views. Based on this theory, we introduce a general N-view algorithm for reconstruction of 3D models of arbitrary scenes from sparse data. This algorithm reconstructs a surface model which converges to an approximation of the real scene surfaces and is consistent with the feature visibility in all N-views. To achieve efficient reconstruction independent of the number of views a recursive reconstruction algorithm is developed which integrates the feature visibility independently for each view. This approach is shown to converge to an approximation of the real scene structure and have a computational cost which is linear in the number of views. It is assumed that structure-from-motion estimates of 3D feature locations are consistent with the multiple view visual geometry and do not contain outliers. Uncertainty in 3D feature estimates is incorporated in the feature visibility to achieve reliable reconstruction in the presence of noise inherent in estimates of 3D scene structure from real image sequences. Results are presented for reconstruction of both real and synthetic scenes together with an evaluation of the reconstruction performance in the presence of noise. The algorithm presented in this paper provides a reliable and computationally efficient approach to model reconstruction from sparse 3D scene data.

Web‐Based Remote Renderingwith IBRAC (Image‐Based Rendering Acceleration and Compression)

Recent advances in Internet and computer graphics stimulate intensive use and development of 3D graphics on the World Wide Web. To increase efficiency of systems using 3D graphics on the web, the presented method utilizes previously rendered and transmitted images to accelerate the rendering and compression of new synthetic scene images. The algorithm employs ray casting and epipolar constraints to exploit spatial and temporal coherence between the current and previously rendered images. The reprojection of color and visibility data accelerates the computation of new images. The rendering method intrinsically computes a residual image, based on a user specified error tolerance that balances image quality against computation time and bandwidth. Encoding and decoding uses the same algorithm, so the transmitted residual image consists only of significant data without addresses or offsets. We measure rendering speed‐ups of four to seven without visible degradation. Compression ratios per frame are a factor of two to ten better than MPEG2 in our test cases. There is no transmission of 3D scene data to delay the first image. The efficiency of the server and client generally increases with scene complexity or data size since the rendering time is predominantly a function of image size. This approach is attractive for remote rendering applications such as web‐based scientific visualization where a client system may be a relatively low‐performance machine and limited network bandwidth makes transmission of large 3D data impractical.