Skip to content
Free planNo credit card requiredStart writing
AI for Research home
AI for Research home
Dashboard
Sign inGet started

Search 250 million research papers

Read the abstract, see who wrote it and who cites it, and get the citation in APA, MLA, Chicago or Harvard.

About 10,000 papers for “Point cloud”

Cloud Point

Hawley's Condensed Chemical Dictionary · 2007

Cited by 0

Point/Cloud

C Douglas · IDEA JOURNAL · 2023

Laser scanning holds out the possibility of extreme certainty. Digital scanning has become deeply integrated in contemporary archaeological surveying, and in architectural heritage and preservation contexts digital scans are now common. Certainty in this text-based essay is understood as an affect, an experiential quality rather than an absolute measure. It does not question the possibility or usefulness of precise measurement (although it does question the rhetorical use of exactitude and precision), but explores the imaginative role of exactitude in this form of digital imaging. It makes readings of a series of moving-image works that use point clouds generated by laser scanning. Rhetorically, the term ‘point cloud’ is suspended between the apparent certainty and exactitude of the mathematical point, and the vague ungraspability of vapour. Rather than expressing exactitude and objectivity, the works discussed here highlight ambiguities of human perception, and seek to see from nonhuman perspectives (the driverless car, the kāhu/hawk, and an oak forest). It concludes by suggesting that such works in particular, and point cloud imagery in general, can be understood in terms of a diffusive material imaginary.

Cited by 1Open access

Cloud Point

AACC Technical · AACC International eBooks · 2009

Cereals & Grains Association is a nonprofit organization dedicated to advancing the knowledge and understanding of cereal grain science through research leadership, education, superior technical service, and advocacy.

Cited by 0

Point cloud

Joris S. M. Vergeest, Imre Horváth, Surface Set · 2009

In this paper a reverse engineering-based methodology is proposed for shape design and manipulation. Based on the reuse of existing physical objects, reverse engineering (RE) provides a shortcut to shape modeling. The major issues to be solved are: a) Finding the optimal strategy for 3D digitizing of shape, b) Identifying those modeling entities, their nature and their parameterization, that are needed and suited for conceptual shape design, c) Representing the measured data in accordance with those entities and d) Insertion of the parametrized entities into the destination model. We present a methodology to effectively integrate the forward/reverse shape engineering activities. Furthermore, we outline a practical, algorithmic solution to the free-form pattern recognition problem. 1. Shape design puts requirements on Reverse Engineering Reverse engineering (RE) was originally motivated by the need for digitized models in downstream processes (Ingle 1994, Várady 1997). Typically it was economically justified to put much effort in activities such as high-density 3D scanning and user-involved model building. A diagram of the key activities in, what we refer to as conventional RE, is shown in figure 1a. The most important factors for conventional RE are the positional accuracy of the data points and the validity of the geometric model (e.g. when its boundary representation is derived). Also typical for conventional RE is that the input is commonly an existing, previously manufactured part. If RE should support conceptual shape design, then the input and output of the RE process are different to those of the conventional one. The methodology shown in figure 1b is based on the assumption that the designer is about to create and to evaluate a number of design concepts of the product. The input of RE can then be a physical artifact created manually, to serve as a starting point for shape. Also a rapidly prototyped physical model (resulting from precedent design studies) may be scanned for redesign and/or for merging with the current design, see dashed lines in figure 1. 1 a) Conventional RE Physical object 3D scanning

Cited by 0

Scene cognition pattern of point cloud-generalization point cloud

Chun Liu, Jia Shoujun, Hangbin Wu et al. · SHILAP Revista de lepidopterología · 2022

With the rapid development of sensor technology and observation platform, point cloud data that is viewed as primary data of remote sensing, has gradually become an important information carrier. Moreover, it plays an increasingly significant role in the national major strategic needs such as geological disaster situation awareness, natural resources quantitative investigation and road traffic safety services. At the same time, driven by point cloud observation equipment and national major strategic needs, spatial scenes have changed from perception to cognition, and new requirements for cognitive processing algorithms and computing power have also been put forward. Therefore, based on the basic framework of point cloud scene cognition, this paper analyzes the research status of multi-source point cloud coupled observation, summarizes the key progress of point cloud scene cognition and typical applications in major national strategic needs, and summarizes the main problems facing point cloud scene cognition at present. On this basis, this paper focuses on the cutting-edge challenges of cloud scene cognition, avoids the traditional Euclidean space and turns to the high-dimensional tensor manifold space for point cloud data processing, proposes the scientific concept and technical framework of generalized point cloud, and provides a new research idea for the algorithm and computing power of cognitive processing of point cloud scene.

Cited by 2Open access

Point Cloud GAN

Chunliang Li, Manzil Zaheer, Yang Zhang et al. · arXiv (Cornell University) · 2018

Generative Adversarial Networks (GAN) can achieve promising performance on learning complex data distributions on different types of data. In this paper, we first show a straightforward extension of existing GAN algorithm is not applicable to point clouds, because the constraint required for discriminators is undefined for set data. We propose a two fold modification to GAN algorithm for learning to generate point clouds (PC-GAN). First, we combine ideas from hierarchical Bayesian modeling and implicit generative models by learning a hierarchical and interpretable sampling process. A key component of our method is that we train a posterior inference network for the hidden variables. Second, instead of using only state-of-the-art Wasserstein GAN objective, we propose a sandwiching objective, which results in a tighter Wasserstein distance estimate than the commonly used dual form. Thereby, PC-GAN defines a generic framework that can incorporate many existing GAN algorithms. We validate our claims on ModelNet40 benchmark dataset. Using the distance between generated point clouds and true meshes as metric, we find that PC-GAN trained by the sandwiching objective achieves better results on test data than the existing methods. Moreover, as a byproduct, PC- GAN learns versatile latent representations of point clouds, which can achieve competitive performance with other unsupervised learning algorithms on object recognition task. Lastly, we also provide studies on generating unseen classes of objects and transforming image to point cloud, which demonstrates the compelling generalization capability and potentials of PC-GAN.

Cited by 18Open access

Point Cloud Manager

Omar A. Mures, Alberto Jaspe Villanueva, Emilio J. Padrón et al. · Advances in data mining and database management book series · 2016

Recent advances in acquisition technologies, such as LIDAR and photogrammetry, have brought back to popularity 3D point clouds in a lot of fields of application of Computer Graphics: Civil Engineering, Architecture, Topography, etc. These acquisition systems are producing an unprecedented amount of geometric data with additional attached information, resulting in huge datasets whose processing and storage requirements exceed usual approaches, presenting new challenges that can be addressed from a Big Data perspective by applying High Performance Computing and Computer Graphics techniques. This chapter presents a series of applications built on top of Point Cloud Manager (PCM), a middleware that provides an abstraction for point clouds with arbitrary attached data and makes it easy to perform out-of-core operations on them on commodity CPUs and GPUs. Hence, different kinds of real world applications are tackled, showing both real-time and offline examples, and render-oriented and computation-related operations as well.

Cited by 0

Point Cloud Compression

Peter Schelkens, Rufael Mekuria · Data Archiving and Networked Services (DANS) · 2015

Cited by 1Open access

Point Cloud Compression

Ge Li, Wei Gao, Wen Gao · 2024

The fast developments of 3D vision technologies and applications have raised the great interests from both the academia and industry communities.3D point clouds can have the strong capability of providing immersive visual experience and highprecision 3D modeling of scenes.We have witnessed the significant progress of compression, processing, and analysis technologies for point clouds.Especially, the available limited bandwidth always restricts the storage and transmission of point clouds, and efficient compression and streaming technologies have been explored broadly.Similar to big image and video data, the huge amount of data of point clouds require more efficient compression algorithms to obtain a desirable rate-distortion tradeoff.Standardization organizations (e.g., MPEG, JPEG, AVS, etc.) and corporations have invested many efforts to develop the non-learning and learning methods to better exploit redundancies for compressing the massive point cloud data.The quality improvements from point cloud compression with constrained bandwidth play a critical role in boosting the application utilities of point clouds in the wild.This book contains 11 chapters, where the first two chapters give the introduction and background knowledge, and the last chapter discusses the future works of point cloud technologies.Chapters 3-10, which are the main part of this book, focus on the key technologies and standards in point cloud compression.Among these chapters, Chaps.3-6 present the fundamental knowledge about compression technologies, such as prediction coding, transform coding, quantization techniques, and entropy coding.Chapters 7-10 discuss the MPEG and AVS standards for point cloud compression, such as MPEG V-PCC, MPEG G-PCC, AVS PCC, and the ongoing AI-based PCC.Chapter 1 introduces the basic concepts of point clouds, acquisition equipment, representative datasets, typical application fields, development trends, and challenges.Chapter 2 mainly focuses on the background knowledge of point cloud compression, which starts with the fundamentals of information theory.Afterward, point cloud compression technologies are generally introduced.Additionally, point cloud quality evaluation methods are also described.v vi Preface Chapters 3-6 are technical chapters on the main coding tools, including prediction, transform, quantization, and entropy coding for the efficient compression of point clouds.Chapter 7 describes the MPEG standard for geometry-based point cloud compression (MPEG G-PCC), including the coding scheme, geometry coding, attribute coding, quantization, entropy coding techniques, and emerging standard activities.Chapter 8 presents the AVS standard for point cloud compression (AVS PCC), which begins with a brief introduction of the AVS point cloud compression standard timeline and synopsis.Afterward, the geometry octree, geometry predictive tree, attribute prediction, attribute transform, and attribute entropy coding are discussed in detail.Chapter 9 introduces the MPEG standard for video-based point cloud compression (MPEG V-PCC), including the encoding and decoding frameworks of V-PCC, point cloud projection approach, and projected video compression methods.Chapter 10 focuses on the deep learning-based point cloud compression methods, including the basic principles, the related neural network design and optimization methods, and the MPEG AI-3DGC standard.Note that the China AVS working group has established a group working on the standardization efforts for AI-based PCC in 2023.Chapter 11 summarizes future works on point cloud technologies from different technical perspectives, including the main coding tools, MPEG G-PCC standard, AVS point cloud compression standard, MPEG V-PCC standard, and deep Learningbased point cloud compression technologies.This book analyzes and presents the advanced point cloud compression technologies, which have shown significant progresses in recent years.As a textbook on 3D point cloud compression technologies and standardization, this book comprises the above selected chapters.Through the progressive presentation, readers can comprehensively understand and master the basic knowledge, the main techniques, and the development trends of point cloud compression.To the best of our knowledge, this is the first comprehensive compilation of all aspects of point cloud compression technologies, as well as the standardization efforts.We hope you enjoy this book and join the growing community of point cloud compression enthusiasts.

Cited by 30Open access

outcrop-point-cloud

Wang, Xin · Figshare · 2018

Example Outcrop Point Cloud for Estimating Historical Shear Deformations.

Cited by 1Open access

Point cloud classes.

Jerzy Orlof (20489803), Paweł Ozimek (20489806), Piotr Łabędź (20489809) et al. · Figshare · 2024

<div><p>Visual analysis has applications in diverse fields, including urban planning and environmental management. This study explores viewshed generation using two distinct datasets: Digital Surface Model (DSM) and LiDAR (Light Detection and Ranging) point cloud data. We assess the differences in viewsheds derived from these sources, evaluating their respective strengths and weaknesses. The DSM accurately captures terrain features and elevation changes, offering a comprehensive view of the land surface. Conversely, LiDAR point cloud data delivers detailed three-dimensional information, enabling precise mapping of terrain features and object detection. Our comparative analysis based on six selected locations with varied topographical arrangements considers factors such as visual acuity and computational efficiency. Additionally, we discuss the application of DSM and LiDAR point cloud data in view analysis, emphasizing their value in line-of-sight assessments and field operations. The results indicate greater precision of viewsheds created based on LiDAR point clouds. The analysis reveals that the greater precision in comparing differences between DSM and point LiDAR data ranges from 1.42% to 5.94%, while the results subtraction falls between 1.05% and 3.89% for the conditions analyzed, indicating a high degree of accuracy in the method. However, this process demands significant computational resources. It is best applied in limited areas, particularly in urban environments where such data is crucial for supporting research decisions.</p></div>

Cited by 0Open access

Original point cloud.

Weilin Wu (13736), Chunquan Liu (3844171), Haoran Zheng (388894) · Figshare · 2024

<div><p>With the rapid development of intelligent connected vehicles, there is an increasing demand for hardware facilities and onboard systems of driver assistance systems. Currently, most vehicles are constrained by the hardware resources of onboard systems, which mainly process single-task and single-sensor data. This poses a significant challenge in achieving complex panoramic driving perception technology. While the panoramic driving perception algorithm YOLOP has achieved outstanding performance in multi-task processing, it suffers from poor adaptability of feature map pooling operations and loss of details during downsampling. To address these issues, this paper proposes a panoramic driving perception fusion algorithm based on multi-task learning. The model training involves the introduction of different loss functions and a series of processing steps for lidar point cloud data. Subsequently, the perception information from lidar and vision sensors is fused to achieve synchronized processing of multi-task and multi-sensor data, thereby effectively improving the performance and reliability of the panoramic driving perception system. To evaluate the performance of the proposed algorithm in multi-task processing, the BDD100K dataset is used. The results demonstrate that, compared to the YOLOP model, the multi-task learning network performs better in lane detection, drivable area detection, and vehicle detection tasks. Specifically, the lane detection accuracy improves by 11.6%, the mean Intersection over Union (mIoU) for drivable area detection increases by 2.1%, and the mean Average Precision at 50% IoU (mAP50) for vehicle detection improves by 3.7%.</p></div>

Cited by 0Open access

Ubiquitous Point Cloud

Bisheng Yang, Zhen Dong, Fuxun Liang et al. · 2024

Point clouds from LiDAR and photogrammetry are vital and vast sources of geospatial information besides remote sensing imagery. This book provides the latest theory and methodology for point cloud processing with AI to better serve earth observation, 3D vision, autonomous driving, smart city, and geospatial information applications. It covers various aspects of 3D geospatial information, including data capturing, fusing, geocomputing, modeling, and vast downstream applications. With the inclusion of numerous illustrations, diagrams, and practical applications, readers will better understand the point cloud, and its technical challenges, and learn how to utilize point cloud in different fields. Features Provides in-depth point cloud processing pipeline, cutting-edge theory, and technology with AI. Includes many specific applications of point cloud in the geospatial field. Offers a comprehensive step-by-step guide from theory to application in point cloud processing. Includes ample supplementary materials including datasets, tools, and other online resources. Helps readers across many disciplines, from geospatial to engineering, to understand the vast application of point clouds and how to further generate new ideas and innovative thoughts. This book is an excellent resource for researchers, academics, students, and professionals in a variety of fields including Geomatics, Remote Sensing, Cartography and Geographic Information Systems, Data Science, Geography, Earth Science, and more.

Cited by 7