Virtual Reality & Intelligent Hardware
Virtual Reality & Intelligent Hardware
News » More
Visual perception driven 3D building structure representation from airborne laser scanning point cloud
Three-dimensional (3D) building models with unambiguous roof plane geometry parameters, roof structure units, and linked topology are essential data for many applications related to human activities in urban environments. The task of 3D reconstruction from point clouds is still in the phase of development, especially to recognize and interpret roof topological structures. Methods This paper proposes a novel visual perception-based approach to automatically decompose and reconstruct building point clouds into meaningful and simple parametric structures, while these mutual relationships between roof plane geometry and roof structure units are expressed by a hierarchical topology tree. It starts with roof plane extraction performed by a multi-label graph cut energy optimization framework, and then a roof structure graph (RSG) model is constructed to describe the roof topological geometry with common adjacency, symmetry, and convexity rules. Moreover, a progressive roof decomposition and refinement are performed, generating a hierarchical representation of 3D roof structures models. Finally, a visual plane fitted residuals or areas constraint process is adopted to generate the RSG model in different levels of details. Results Two airborne laser scanning (ALS) datasets with different point densities and roof styles were tested, and the performance evaluation metrics are obtained by the International Society for Photogrammetry and Remote Sensing (ISPRS), achieving correctness and accuracy in terms of 97.7% and 0.29m, respectively. Conclusions The standardized assessment results demonstrate the effectiveness and robustness of the proposed approach, showing its abilities to generate a variety of structural models, even in the presence of missing data.
Deep learning based point cloud registration: an overview
Point cloud registration aims at finding a rigid transformation to align one point cloud to another one. It is a fundamental problem in computer vision and robotics, which has been widely used in various applications, such as 3D reconstruction, SLAM (simultaneous localization and mapping), and autonomous driving. Over the last decades, many researchers have devoted themselves to tackle this challenging problem. Recently, the success of deep learning in high-level vision tasks has been extended to different geometric vision tasks. Various kinds of deep learning based point cloud registration methods have been proposed to exploit different aspects of the problem. However, a comprehensive overview of these approaches is still missing. To this end, in this paper, we summarize recent progress and present a comprehensive overview for deep learning based point cloud registration. We classify the popular approaches into different categories such as, correspondences-based or correspondences-free, effective modules: feature extractor, matching, outlier rejection, and motion estimation. Furthermore, we discuss the merits and demerits in detail. We provide a systematic and compact framework towards currently proposed methods and discuss future research directions.
Urban 3D modeling with mobile laser scanning：a review
Mobile laser scanning (MLS) systems mainly comprise laser scanners and mobile mapping platforms. Typical MLS systems are able to acquire three-dimensional point clouds with 1-10 centimeter point spacing at a normal driving or walking speed in the street or indoor environments. The MLS' advantages of efficiency and stability make it a quite practical tool for three-dimensional urban modeling. This paper reviews the latest advances in 3D modeling of the LiDAR-based mobile mapping system (MMS) point cloud, including LiDAR Simultaneous Localization and Mapping (SLAM), point cloud registration, feature extraction, object extraction, semantic segmentation, and deep learning processing. Then typical urban modeling applications based on MMS are also discussed.
A survey on monocular 3D human pose estimation
Recovering human pose from an RGB image or a video has drawn increasing attention in recent years due to its minimum sensor requirements and broad applicability in diverse fields, e.g., human-computer interaction, robotics, video analytics and augmented reality. Although a large amount of work has been devoted to this field, 3D human pose estimation based on monocular images or videos remains a very challenging task due to a variety of difficulties such as depth ambiguities, occlusion, background clutters and lack of training data. In this survey, we will summarize recent advances in monocular 3D human pose estimation, discuss capabilities and limitations of different approaches, present a summary of the extensively used datasets and metrics, and finally conclude this paper with a discussion of several future research directions.
Survey on lightweighting methods of huge 3D models for online Web3D visualization
Background With the rapid development of Web3D technologies, online Web3D visualization , especially for complex models or scenes, has been a great yet heavy demand. As the serious conflict between Web3D system load and the resource consumption in processing these huge models, the huge 3D model lightweighting methods for online Web3D visualization are reviewed in this paper. Methods Observing the geometry redundance introduced by man-made operations in modeling procedure, several categories of lightweighting related work which aim for reducing the data amount and resource consumption for Web3D visualization are elaborated. Results With comparing perspectives, the characteristics of each method are summarized and within the reviewed methods, the geometric redundance removal which achieves the lightweight goal by detecting and removing the repeated components is an appropriate way for current online Web3D visualization. Meanwhile, the learning algorithm, though not practical at present, is our expected topic. Conclusions Various aspects should be considered in an efficient lightweight method for online Web3D visualization, including characteristics of original data, combination or extended of the existed methods, and even scheduling strategy, cache management, rendering mechanism. Meanwhile, innovation methods, especially the learning algorithm is worth exploring.