ORCID Profile
0000-0003-0122-7656
Current Organisation
University College Dublin
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: MDPI AG
Date: 21-10-2022
DOI: 10.3390/RS14205277
Abstract: Current state-of-the-art point cloud data management (PCDM) systems rely on a variety of parallel architectures and erse data models. The main objective of these implementations is achieving higher scalability without compromising performance. This paper reviews the scalability and performance of state-of-the-art PCDM systems with respect to both parallel architectures and data models. More specifically, in terms of parallel architectures, shared-memory architecture, shared-disk architecture, and shared-nothing architecture are considered. In terms of data models, relational models, and novel data models (such as wide-column models) are considered. New structured query language (NewSQL) models are considered. The impacts of parallel architectures and data models are discussed with respect to theoretical perspectives and in the context of existing PCDM implementations. Based on the review, a methodical approach for the selection of parallel architectures and data models for highly scalable and performance-efficient PCDM system development is proposed. Finally, notable research gaps in the PCDM literature are presented as possible directions for future research.
Publisher: Elsevier BV
Date: 04-2018
Publisher: Elsevier BV
Date: 09-2018
Publisher: Informa UK Limited
Date: 20-11-2016
Publisher: Copernicus GmbH
Date: 19-09-2018
DOI: 10.5194/ISPRS-ARCHIVES-XLII-4-671-2018
Abstract: Abstract. Laser scanning data are increasingly available across the globe. To maximize the data's usability requires proper storage and indexing. While significant research has been invested in developing storage and indexing solutions for laser scanning point clouds (i.e. using the discrete form of the data), little attention has been paid to developing equivalent solutions for full waveform (FWF) laser scanning data, especially in a distributed computing environment. Given the growing availability of FWF sensors and datasets, FWF data management solutions are increasingly needed. This paper presents an attempt towards establishing a scalable solution for handling large FWF datasets by introducing the distributed computing solution for FWF data. The work involves a FWF database built atop HBase – the distributed database system running on Hadoop commodity clusters. By combining a 6-dimensional (6D) Hilbert spatial code and a temporal index into a compound indexing key, the database system is capable of supporting multiple spatial, temporal, and spatio-temporal queries. Such queries are important for FWF data exploration and dissemination. The proposed spatial decomposition at a fine resolution of 0.05 m allows the storage of each LiDAR FWF measurement (i.e. pulse, waves, and points) on a single row of the database, thereby providing the full capabilities to add, modify, and remove each measurement record anatomically. While the feasibility and capabilities of the 6D Hilbert solution are evident, the Hilbert decomposition is not due to the complications from the combination of the data’s high dimensionality, fine resolution, and large spatial extent. These factors lead to a complex set of both attractive attributes and limitation in the proposed solution, which are described in this paper based on experimental tests using a 1.1 billion pulse LiDAR scan of a portion of Dublin, Ireland.
Publisher: CRC Press
Date: 13-09-2023
No related grants have been discovered for Michela Bertolotto.