Dealing with coloured point cloud acquired from terrestrial laser scanner, this paper identifies remaining challenges for a new data structure: the <i>smart point cloud</i>. This concept arises with the statement that massive and discretized spatial information from active remote sensing technology is often underused due to data mining limitations. The generalisation of point cloud data associated with the heterogeneity and temporality of such datasets is the main issue regarding structure, segmentation, classification, and interaction for an immediate understanding. We propose to use both point cloud properties and human knowledge through machine learning to rapidly extract pertinent information, using user-centered information (smart data) rather than raw data. A review of feature detection, machine learning frameworks and database systems indexed both for mining queries and data visualisation is studied. Based on existing approaches, we propose a new 3-block flexible framework around device expertise, analytic expertise and domain base reflexion. This contribution serves as the first step for the realisation of a comprehensive smart point cloud data structure.

3D models derived from point clouds are useful in various shapes to optimize the trade-off between precision and geometric complexity. They are defined at different granularity levels according to each indoor situation. In this article, we present an integrated 3D semantic reconstruction framework that leverages segmented point cloud data and domain ontologies. Our approach follows a part-to-whole conception which models a point cloud in parametric elements usable per instance and aggregated to obtain a global 3D model. We first extract analytic features, object relationships and contextual information to permit better object characterization. Then, we propose a multi-representation modelling mechanism augmented by automatic recognition and fitting from the 3D library ModelNet10 to provide the best candidates for several 3D scans of furniture. Finally, we combine every element to obtain a consistent indoor hybrid 3D model. The method allows a wide range of applications from interior navigation to virtual stores.

Monitoring the structure of forest stands is of high importance for forest managers to help them in maintaining ecosystem services. For that purpose, Unmanned Aerial Vehicles (UAVs) open new prospects, especially in combination with Light Detection and Ranging (LiDAR) technology. Indeed, the shorter distance from the Earth’s surface significantly increases the point density beneath the canopy, thus offering new possibilities for the extraction of the underlying semantics. For example, tree stems can now be captured with sufficient detail, which is a gateway to accurately locating trees and directly retrieving metrics—e.g., the Diameter at Breast Height (DBH). Current practices usually require numerous site-specific parameters, which may preclude their use when applied beyond their initial application context. To overcome this shortcoming, the machine learning Hierarchical Density-Based Spatial Clustering of Application of Noise (HDBSCAN) clustering algorithm was further improved and implemented to segment tree stems. Afterwards, Principal Component Analysis (PCA) was applied to extract tree stem orientation for subsequent DBH estimation. This workflow was then validated using LiDAR point clouds collected in a temperate deciduous closed-canopy forest stand during the leaf-on and leaf-off seasons, along with multiple scanning angle ranges. The results show that the proposed methodology can correctly detect up to 82% of tree stems (with a precision of 98%) during the leaf-off season and have a Maximum Scanning Angle Range (MSAR) of 75 degrees, without having to set up any site-specific parameters for the segmentation procedure. In the future, our method could then minimize the omission and commission errors when initially detecting trees, along with assisting further tree metrics retrieval. Finally, this research shows that, under the study conditions, the point density within an approximately 1.3-meter height above the ground remains low within closed-canopy forest stands even during the leaf-off season, thus restricting the accurate estimation of the DBH. As a result, autonomous UAVs that can both fly above and under the canopy provide a clear opportunity to achieve this purpose.

Digital investigations of the real world through point clouds and derivatives are changing how curators, cultural heritage researchers and archaeologists work and collaborate. To progressively aggregate expertise and enhance the working proficiency of all professionals, virtual reconstructions demand adapted tools to facilitate knowledge dissemination. However, to achieve this perceptive level, a point cloud must be semantically rich, retaining relevant information for the end user. In this paper, we review the state of the art of point cloud integration within archaeological applications, giving an overview of 3D technologies for heritage, digital exploitation and case studies showing the assimilation status within 3D GIS. Identified issues and new perspectives are addressed through a knowledge-based point cloud processing framework for multi-sensory data, and illustrated on mosaics and quasi-planar objects. A new acquisition, pre-processing, segmentation and ontology-based classification method on hybrid point clouds from both terrestrial laser scanning and dense image matching is proposed to enable reasoning for information extraction. Experiments in detection and semantic enrichment show promising results of 94% correct semantization. Then, we integrate the metadata in an archaeological smart point cloud data structure allowing spatio-semantic queries related to CIDOC-CRM. Finally, a WebGL prototype is presented that leads to efficient communication between actors by proposing optimal 3D data visualizations as a basis on which interaction can grow.

ABSTRACT:This paper proposes an interoperable model for managing high dimensional point clouds while integrating semantics. Point clouds from sensors are a direct source of information physically describing a 3D state of the recorded environment. As such, they are an exhaustive representation of the real world at every scale: 3D reality-based spatial data. Their generation is increasingly fast but processing routines and data models lack of knowledge to reason from information extraction rather than interpretation. The enhanced smart point cloud developed model allows to bring intelligence to point clouds via 3 connected meta-models while linking available knowledge and classification procedures that permits semantic injection. Interoperability drives the model adaptation to potentially many applications through specialized domain ontologies. A first prototype is implemented in Python and PostgreSQL database and allows to combine semantic and spatial concepts for basic hybrid queries on different point clouds.

Virtual 3D city models act as valuable central information hubs supporting many aspects of cities, from management to planning and simulation. However, we noted that 3D city models are still underexploited and believe that this is partly due to inefficient visual communication channels across 3D model producers and the end-user. With the development of a formalized 3D geovisualization approach, this paper aims to support and make the visual identification and recognition of specific objects in the 3D models more efficient and useful. The foundation of the proposed solution is a knowledge network of the visualization of 3D geospatial data that gathers and links mapping and rendering techniques. To formalize this knowledge base and make it usable as a decision-making system for the selection of styles, second-order logic is used. It provides a first set of efficient graphic design guidelines, avoiding the creation of graphical conflicts and thus improving visual communication. An interactive tool is implemented and lays the foundation for a suitable solution for assisting the visualization process of 3D geospatial models within CAD and GIS-oriented software. Ultimately, we propose an extension to OGC Symbology Encoding in order to provide suitable graphic design guidelines to web mapping services.

3D geovisualization is essential in urban planning as it assists the analysis of geospatial data and decision making in the design and development of land use and built environment. However, we noted that 3D geospatial models are commonly visualized arbitrarily as current 3D viewers often lack of design instructions to assist end users. This is especially the case for the occlusion management in most 3D environments where the high density and diversity of 3D data to be displayed require efficient visualization techniques for extracting all the geoinformation. In this paper, we propose a theoretical and operational solution to manage occlusion by automatically computing best viewpoints. Based on user’s parameters, a viewpoint management algorithm initially calculates optimal camera settings for visualizing a set of 3D objects of interest through parallel projections. Precomputed points of view are then integrated into a flythrough creation algorithm for producing an automatic navigation within the 3D geospatial model. The algorithm’s usability is illustrated within the scope of a fictive exploratory phase for the public transport services access in the European quarter of Brussels. Eventually, the proposed algorithms may also assist additional urban planning phases in achieving their purposes.

ABSTRACT:This paper deals with the viewpoint management in 3D environments considering an allocentric environment. The recent advances in computer sciences and the growing number of affordable remote sensors lead to impressive improvements in the 3D visualisation. Despite some research relating to the analysis of visual variables used in 3D environments, we notice that it lacks a real standardisation of 3D representation rules. In this paper we study the "viewpoint" as being the first considered parameter for a normalised visualisation of 3D data. Unlike in a 2D environment, the viewing direction is not only fixed in a top down direction in 3D. A non-optimal camera location means a poor 3D representation in terms of relayed information. Based on this statement we propose a model based on the analysis of the computational display pixels that determines a viewpoint maximising the relayed information according to one kind of query. We developed an OpenGL prototype working on screen pixels that allows to determine the optimal camera location based on a screen pixels colour algorithm. The viewpoint management constitutes a first step towards a normalised 3D geovisualisation.