Showing papers in "The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences in 2019"

Mapping poverty in the philippines using machine learning, satellite imagery, and crowd-sourced geospatial information

Abstract: . Mapping the distribution of poverty in developing countries is essential for humanitarian organizations and policymakers to formulate targeted programs and aid. However, traditional methods for obtaining socioeconomic data can be time-consuming, expensive, and labor-intensive. Recent studies have demonstrated the effectiveness of combining machine learning and satellite images to estimate wealth in sub-Saharan African countries (Xie et al., 2016, Jean et al., 2016). In this study, we investigate the extent to which this method can be applied in the context of the Philippine archipelago to predict four different socioeconomic indicators: wealth level, years of education, access to electricity, and access to water. We also propose an alternative, cost-effective approach that leverages a combination of volunteered geographic information from OpenStreetMap and nighttime lights satellite imagery for estimating socioeconomic indicators. The best models, which incorporate regional indicators as predictors, explain approximately 63% of the variation in asset-based wealth. Our findings also indicate that models trained on publicly available, volunteer-curated geographic data achieve the same predictive performance as that of models trained using proprietary satellite images.

Using dji phantom 4 rtk drone for topographic mapping of coastal areas

Abstract: . Imagery acquisition systems by Unmanned Aerial Vehicles (UAVs) have been rapidly evolving within the last few years. In mapping applications, it is the introduction of a considerable amount of Ground Control Points (GCPs) that enables the final reconstruction of a real-scale framed model. Since the survey of GCPs generally requires the use of total stations or GNSS receivers in Real Time Kinematic (RTK), either with or without a Network approach (NRTK), this on-site operation is particularly time consuming. In addition, the lack of clearly image-recognizable points may force the use of artificial markers (signalised GCPs) whenever no features are naturally available in the field. This implies a real waste of time for the deployment of the targets, as well as for their recovery. Recently, aircrafts’ manufacturers have integrated the on-board RTK capability on their UAVs. In such a way, the high precision GNSS system allows the 3D position detection of the camera at the time of each capture within few centimetres. In this work, we tested the DJI Phantom 4 RTK for the topographic survey of a coastal section in the Northern Adriatic Sea (Italy). The flights were performed flying at an 80 m altitude to ensure a Ground Sample Distance (GSD) of about 2 centimetres. The site extended up to 2 kilometres longitudinally. The results confirm that the on-board RTK approach really speeds up the precise mapping of coastal regions and that a single GCP may be needed to make a reliable estimation of the focal length.

Geometric features analysis for the classification of cultural heritage point clouds

Abstract: . In the last years, the application of artificial intelligence (Machine Learning and Deep Learning methods) for the classification of 3D point clouds has become an important task in modern 3D documentation and modelling applications. The identification of proper geometric and radiometric features becomes fundamental to classify 2D/3D data correctly. While many studies have been conducted in the geospatial field, the cultural heritage sector is still partly unexplored. In this paper we analyse the efficacy of the geometric covariance features as a support for the classification of Cultural Heritage point clouds. To analyse the impact of the different features calculated on spherical neighbourhoods at various radius sizes, we present results obtained on four different heritage case studies using different features configurations.

Deep Learning for Semantic Segmentation of 3d Point Cloud

Abstract: . Cultural Heritage is a testimony of past human activity, and, as such, its objects exhibit great variety in their nature, size and complexity; from small artefacts and museum items to cultural landscapes, from historical building and ancient monuments to city centers and archaeological sites. Cultural Heritage around the globe suffers from wars, natural disasters and human negligence. The importance of digital documentation is well recognized and there is an increasing pressure to document our heritage both nationally and internationally. For this reason, the three-dimensional scanning and modeling of sites and artifacts of cultural heritage have remarkably increased in recent years. The semantic segmentation of point clouds is an essential step of the entire pipeline; in fact, it allows to decompose complex architectures in single elements, which are then enriched with meaningful information within Building Information Modelling software. Notwithstanding, this step is very time consuming and completely entrusted on the manual work of domain experts, far from being automatized. This work describes a method to label and cluster automatically a point cloud based on a supervised Deep Learning approach, using a state-of-the-art Neural Network called PointNet++. Despite other methods are known, we have choose PointNet++ as it reached significant results for classifying and segmenting 3D point clouds. PointNet++ has been tested and improved, by training the network with annotated point clouds coming from a real survey and to evaluate how performance changes according to the input training data. It can result of great interest for the research community dealing with the point cloud semantic segmentation, since it makes public a labelled dataset of CH elements for further tests.

Digital twin: a hbim-based methodology to support preventive conservation of historic assets through heritage significance awareness

Abstract: . During preliminary phases of conservation projects, a considerable amount of heterogeneous datasets are produced, gathered, analysed and interpreted. Abundant researches have gradually proven that Historic Building Information Modelling (HBIM) is a relevant alternative for the collaborative management of information related to existing structures. Apart from the obvious benefits of HBIM for information exchange among stakeholders during conservation project, the potential of such processes to support preservation strategies should not be neglected. Moreover, the recent developments of HBIM web-interfaces illustrate the need for additional investigation in strengthening the relationships between the digital model and the real-world to better support preventive conservation of heritage places. Besides, values-based approaches for the elaboration of conservation strategies have been gradually adopted in the last decades, both in academic and professional sector. In this paper, we propose a comprehensive methodology to structure and integrate the cultural significance of tangible and intangible elements into HBIM models to be further taken into account in the analysis and simulation of data. This article suggests the application of Digital Twin (DT) principles to support site managers in the preventive conservation of their assets. Based on the analysis and simulations of data captured by onsite sensors, threats to the site integrity and corresponding preventive solution can be predicted in the DT environment. The integration and structuration of Heritage Values in HBIM models allow further evaluation process to estimate the impact of each suggested interventions on the conservation of features of significance.

Uav for mapping historic buildings: from 3d modelling to bim

Abstract: . Preventive actions of cultural heritage continuously emerge in order to preserve the identity of the respective civilizations, retain its cultural significance and ensure its accessibility to present and future generations. 3D geomatics technologies along with UAV systems are widely used for documenting existing structures especially in difficult-to-access areas. In addition, Building Information Modelling (BIM) for cultural heritage gains ground towards the sustainable management, update and maintenance of the information. To this context, the current work generates a Historic Building Information Modelling (HBIM) model of the “Averof’s Museum of Neohellenic art” located in Metsovo, Greece, by using UAV photogrammetry techniques and additional information derived from the architecture designs of the buildings.

Application of machine and deep learning strategies for the classification of heritage point clouds

Abstract: . The use of heritage point cloud for documentation and dissemination purposes is nowadays increasing. The association of semantic information to 3D data by means of automated classification methods can help to characterize, describe and better interpret the object under study. In the last decades, machine learning methods have brought significant progress to classification procedures. However, the topic of cultural heritage has not been fully explored yet. This paper presents a research for the classification of heritage point clouds using different supervised learning approaches (Machine and Deep learning ones). The classification is aimed at automatically recognizing architectural components such as columns, facades or windows in large datasets. For each case study and employed classification method, different accuracy metrics are calculated and compared.

Scan-to-bim methodology adapted for different application

Abstract: . In this paper we proposed a methodology that describes the major steps of a scan-to-BIM process. The methodology includes six steps: (1) classification of considered elements, (2) definition of required level of detail (GI), (3) scan data acquisition, (4) point cloud registration and segmentation, (5) as-built BIM creation and (6) analysis. The examples of the application of the proposed methodology are demonstrated by creation of as-built BIM models for existing industrial sites and historic buildings. As the results of these case studies have shown, the proposed methodology can be used for as-built BIMs without any prior information.

Indoor Mapping Eyewear: Geometric Evaluation of Spatial Mapping Capability of Hololens

Abstract: Existing indoor mapping systems have limitations in terms of time efficiency and flexibility in complex environments. While backpack and handheld systems are more flexible and can be used for mapping multi-storey buildings, in some application scenarios, e.g. emergency response, a light-weight indoor mapping eyewear or head-mounted system has practical advantages. In this paper, we investigate the spatial mapping capability of Microsoft Hololens mixed reality eyewear for 3D mapping of large indoor environments. We provide a geometric evaluation of 3D mesh data captured by the Hololens in terms of local precision, coverage, and global correctness in comparison with terrestrial laser scanner data and a reference 3D model. The results indicate the high efficiency and flexibility of Hololens for rapid mapping of relatively large indoor environments with high completeness and centimetre level accuracy.

Recreating Cultural Heritage Environments for VR Using Photogrammetry

Abstract: . In this paper, we propose a workflow for recreating places of cultural heritage in Virtual Reality (VR) using structure from motion (SfM) photogrammetry. The unique texture of heritage places makes them ideal for full photogrammetric capture. An optimized model is created from the photogrammetric data so that it is small enough to render in a real-time environment. The optimized model, combined with mesh maps (texture maps, normal maps, etc.) looks like the original high detail model. The capture of a whole space makes it possible to create a VR experience with six degrees of freedom (6DoF) that allows the user to explore the historic place. Creating these experiences can bring people to cultural heritage that is either endangered or too remote for some people to access. The workflow described in this paper will be demonstrated with the case study of Myin-pya-gu, an 11th century temple in Bagan, Myanmar.

Prediction of flash flood susceptibility using fuzzy analytical hierarchy process (fahp) algorithms and gis: a study case of guelmim region in southwestern of morocco

Abstract: . In recent decades, many of the countries around the world as well as the south-western Morocco (Guelmim region, Assaka watershed), was subject to flood-storm causing huge human and material damages. The current study focuses on the Prediction of flash flood susceptibility using Fuzzy Analytical Hierarchy Process (FAHP) algorithms and Geographic Information System (GIS) technical. Flash floods areas were identified based on seven flash flood conditioning factors (Soil Moisture Index (SMI), Drainage Density, Rainfall, LULC, Altitude, Slope and Soil). Using AHP the weight derived for the factors were SMI 37% Rainfall 24.30%, Drainage Density 15.57%, LULC 9.98% Altitude 6.39% Slope of the river basin 4.06% and Soil type 2.70%. Then, applying a fuzzy inference system to create flash flood vulnerability maps. The resulting maps were classified into three categories: low, moderate and high flash flood susceptibility; indicated that the areas at the outlet of the watershed and which are close of the main affluent wadis (Seyyad and Oum Al-Achar) were very susceptible to flooding. This study will be helping these zones to be prioritized for the conservation and managing of flash floods.

From Reality to Parametric Models of Cultural Heritage Assets for Hbim

Abstract: . The ability of managing big amounts of metric information coming from a LiDAR survey and the ability to reproduce high quality 3D models from them are still vivid problems to solve. Is it possible to create detailed models, geometrically and metrically correct, without using a large amount (often redundant) of metric data, such as massive point clouds? Obviously yes, but there are several ways to create a fitting 3D model for a specific research. A good solution is given by NURBS based algorithms that ensure high details of modelling. However, NURBS models can't be used directly on BIM platforms, because they need to be parametrized. In this sense, a parametric model is based on real measurements but each object could be interpreted and approximated based on objective and subjective (critic) view and also based on LODs (levels of detail or development) concerning a particular analysis. This kind of modelling of Cultural Heritage assets, fundamental for HBIM creation, need to be correctly planned especially for classification and definition of its historical features connected to an informative system, because nowadays information and then the semantic dimension are a necessary key points towards documentation analysis. Established this brief introduction, this schematic work will focus on the analysis of FreeCAD open BIM software and Rhinoceros as NURBS 3D modeller for Cultural Heritage is concerned, and whether and how they could integrate their tools for the purpose of managing dynamic high detailed data for the creation of an HBIM platform.

Impact of Virtual Reality Experience on Accessibility of Cultural Heritage

Abstract: . Accessibility plays a main role among the aspects that contribute to the conservation of Cultural Heritage sites. Seismic stability, fragility of the artefacts, conflicts, deterioration, natural disasters, climate change and visitors’ impact are only some of the possible causes that might lead to the inaccessibility of a heritage site for both researchers and visitors. The increasing potential of Information and Communication Technologies (ICT) in the conservation field has resulted in the development of Augmented and Virtual reality (AR and VR) experiences. These ones can be very effective for what concerns the description of the visual experience, but also improve the understanding of a site and even became analytic research tools. This paper presents an inaccessible Buddhist temple in the Myanmar city of Bagan as a case study for the realization of a VR experience that aims at providing accessibility to knowledge and therefore a better understanding of the cultural value. In order to evaluate the effectiveness of the VR for this purpose, a user study has been conducted and its results are reported.

GeoBIM benchmark 2019 : design and initial results

Abstract: GeoBIM, the integration of 3D geoinformation (Geo) with building information models (BIM), is a subject of increasing attention in both domains. A well-known practical challenge for this integration is the mixed state of software support for open standards in each domain that would ease the integration. This is often known by practitioners but poorly documented. In order to solve this problem, we devised the GeoBIM benchmark, in which we compile the experiences of volunteering participants, who perform a guided study to test the software they are most familiar with against a few provided datasets structured in open standards. The aim of the tests is to improve the knowledge of the state of the art in the software support for GeoBIM open standards and to identify points for improvement. In this paper, we present the design of the benchmark, especially explaining and discussing the chosen data to be used with their connected issues to be tested, and some initial results.

Overview of open source software for close range photogrammetry

Abstract: . In the photogrammetric process of the 3D reconstruction of an object or a building, multi-image orientation is one of the most important tasks that often include simultaneous camera calibration. The accuracy of image orientation and camera calibration significantly affects the quality and accuracy of all subsequent photogrammetric processes, such as determining the spatial coordinates of individual points or 3D modeling. In the context of artificial vision, the full-field analysis procedure is used, which leads to the so-called Strcture from Motion (SfM), which includes the simultaneous determination of the camera's internal and external orientation parameters and the 3D model. The procedures were designed and developed by means of a photogrammetric system, but the greatest development and innovation of these procedures originated from the computer vision from the late 90s, together with the SfM method. The reconstructions on this method have been useful for visualization purposes and not for photogrammetry and mapping. Thanks to advances in computer technology and computer performance, a large number of images can be automatically oriented in a coordinate system arbitrarily defined by different algorithms, often available in open source software (VisualSFM, Bundler, PMVS2, CMVS, etc.) or in the form of Web services (Microsoft Photosynth, Autodesk 123D Catch, My3DScanner, etc.). However, it is important to obtain an assessment of the accuracy and reliability of these automated procedures. This paper presents the results obtained from the dome low close range photogrammetric surveys and processed with some open source software using the Structure from Motion approach: VisualSfM, OpenDroneMap (ODM) and Regard3D. Photogrammetric surveys have also been processed with the Photoscan commercial software by Agisoft. For the photogrammetric survey we used the digital camera Canon EOS M3 (24.2 Megapixel, pixel size 3.72 mm). We also surveyed the dome with the Faro Focus 3D TLS. Only one scan was carried out, from ground level, at a resolution setting of ¼ with 3x quality, corresponding to a resolution of 7 mm / 10 m. Both TLS point cloud and Photoscan point cloud were used as a reference to validate the point clouds coming from VisualSFM, OpenDroneMap and Regards3D. The validation was done using the Cloud Compare open source software.

Condition assessment of rc bridges. integrating machine learning, photogrammetry and bim

Abstract: . The survey of building pathologies is focused on reading the state of conservation of the building, composed by the survey of constructive and decorative details, the masonry layering, the crack pattern, the degradation and the color recognition. The drawing of these representations is a time-consuming task, accomplished by manual work by skilled operators who often rely on in-situ analysis and on pictures. In this project three-dimensional an automated method for the condition survey of reinforced concrete spalling has been developed. To realize the automated image-based survey it has been exploited the Mask R-CNN neural network. The training phase has been executed over the original model, providing new examples of images with concrete cover detachments. At the same time, a photogrammetry process involved the images, in order to obtain a point cloud which acts as a reference to a Scan to BIM process. The BIM environment serves as a collector of information, as it owns the ontology to recreate entities and relationships. The information as extracted by neural network and photogrammetry serve to create the pictures which depict the concrete spalling in the BIM environment. A process of projecting information from the images to the BIM recreates the shapes of the pathology on the objects of the model, which becomes a decision support system for the built environment. A case study of a concrete beam bridge in northern Italy demonstrates the validity of the process.

Documenting the Cultural Heritage Routes. The Creation of Informative Models of Historical Russian Churches on Upper Kama Region

Abstract: . The present paper illustrates the documentation activities developed since 2013 on Upper Kama territories, preliminary to an extensive and joint research action within the European project “PROMETHEUS” (2019–2021), which aims to produce digitized databases and models for the management of the main religious monuments present on this Russian area, nowadays endangered by risk of conservation. The project is funded by the EU program Horizon 2020 – R&I – RISE – Research & Innovation Staff Exchange Marie Sklodowska-Curie, and it is aimed at the definition of inter-sectoral collaboration protocols for the development and promotion of a new methodology for the development of reliable 3D databases and models of monumental complexes in Upper Kama region. The project, that involves the collaboration between three Universities (University of Pavia, Italy, Polytechnic University of Valencia, Spain, Perm National Research Polytechnic University, Russia) and two enterprises (EBIME, Spain, SISMA, Italy), aims to promote actions to develop interdisciplinary activities for the documentation, management and production of collaborative H-BIM models, for the start-up of monitoring and development activities on this specific Cultural Heritage. Researches and initiatives conducted in the previous years on Upper Kama territory highlight potentialities and opportunities of digital survey to define a basis of knowledge that is both scientific and technical, for future interventions on endangered architectural heritage, where academies, companies and administrations promote actions to develop interdisciplinary documentation activities through collaborative management H-BIM models and an intervention protocol on Cultural Heritage.

Shining 3d einscan-pro, application and validation in the field of cultural heritage, from the chillida-leku museum to the archaeological museum of sarno

Abstract: . The following contribution focuses on the low-cost Shining 3D EinScan-Pro scanner, above all the analysis of its precision and accuracy. The need to prove the functioning of this instrumentation in practical cases (the sculptures by Eduardo Chillida preserved in the Chillida-Leku Museum and along with some artefacts collected in the Archaeological Museum of Sarno), has led to the comparison and validation of the instrument through a methodology necessarily diversified from the guideline VDI/VDE 2634, part 2 and part 3, characteristics to the test the optical 3D measuring systems with planar measurement, which works according to the triangulation principle. In particular, two types of comparisons were made: geometric-formal and metric-dimensional. The first type of analysis was carried out analysing the geometric parameters of the models, suitable for validating the information: dimensional (difference between some main measurements); superficial (total mesh extension) and of the form (that is, the discrepancies returned through a DEM analysis). The second type of analysis, instead, of the metric type, was carried out. The complete results of the various analyses will be presented and critically discussed within this contribution in order to prove the stability and the metric quality of this hand-held EinScan-Pro, following the comparison with medium-high end systems now well established in the field of cultural heritage survey.

Classification and Integration of Massive 3d Points Clouds in a Virtual Reality (vr) Environment

Abstract: . With the increasing volume of 3D applications using immersive technologies such as virtual, augmented and mixed reality, it is very interesting to create better ways to integrate unstructured 3D data such as point clouds as a source of data. Indeed, this can lead to an efficient workflow from 3D capture to 3D immersive environment creation without the need to derive 3D model, and lengthy optimization pipelines. In this paper, the main focus is on the direct classification and integration of massive 3D point clouds in a virtual reality (VR) environment. The emphasis is put on leveraging open-source frameworks for an easy replication of the findings. First, we develop a semi-automatic segmentation approach to provide semantic descriptors (mainly classes) to groups of points. We then build an octree data structure leveraged through out-of-core algorithms to load in real time and continuously only the points that are in the VR user's field of view. Then, we provide an open-source solution using Unity with a user interface for VR point cloud interaction and visualisation. Finally, we provide a full semantic VR data integration enhanced through developed shaders for future spatio-semantic queries. We tested our approach on several datasets of which a point cloud composed of 2.3 billion points, representing the heritage site of the castle of Jehay (Belgium). The results underline the efficiency and performance of the solution for visualizing classifieds massive point clouds in virtual environments with more than 100 frame per second.

Accuracy Assessment of 3d Models Generated from Google Street View Imagery

Abstract: . Google Street View is a technology implemented in several Google services/applications (e.g. Google Maps, Google Earth) which provides the user, interested in viewing a particular location on the map, with panoramic images (represented in equi-rectangular projection) at street level. Generally, consecutive panoramas are acquired with an average distance of 5–10 m and can be compared to a traditional photogrammetric strip and, thus, processed to reconstruct portion of city at nearly zero cost. Most of the photogrammetric software packages available today implement spherical camera models and can directly process images in equi-rectangular projection. Although many authors provided in the past relevant works that involved the use of Google Street View imagery, mainly for 3D city model reconstruction, very few references can be found about the actual accuracy that can be obtained with such data. The goal of the present work is to present preliminary tests (at time of writing just three case studies has been analysed) about the accuracy and reliability of the 3D models obtained from Google Street View panoramas.

Generative Adversarial Networks for Single Photo 3d Reconstruction

Abstract: . Fast but precise 3D reconstructions of cultural heritage scenes are becoming very requested in the archaeology and architecture. While modern multi-image 3D reconstruction approaches provide impressive results in terms of textured surface models, it is often the need to create a 3D model for which only a single photo (or few sparse) is available. This paper focuses on the single photo 3D reconstruction problem for lost cultural objects for which only a few images are remaining. We use image-to-voxel translation network (Z-GAN) as a starting point. Z-GAN network utilizes the skip connections in the generator network to transfer 2D features to a 3D voxel model effectively (Figure 1). Therefore, the network can generate voxel models of previously unseen objects using object silhouettes present on the input image and the knowledge obtained during a training stage. In order to train our Z-GAN network, we created a large dataset that includes aligned sets of images and corresponding voxel models of an ancient Greek temple. We evaluated the Z-GAN network for single photo reconstruction on complex structures like temples as well as on lost heritage still available in crowdsourced images. Comparison of the reconstruction results with state-of-the-art methods are also presented and commented.

Videogrammetry VS Photogrammetry for Heritage 3d Reconstruction

Abstract: . In the last years we are witnessing an increasing quality (and quantity) of video streams and a growing capability of SLAM-based methods to derive 3D data from video. Video sequences can be easily acquired by non-expert surveyors and possibly used for 3D documentation purposes. The aim of the paper is to evaluate the possibility to perform 3D reconstructions of heritage scenarios using videos ("videogrammetry"), e.g. acquired with smartphones. Video frames are extracted from the sequence using a fixed-time interval and two advanced methods. Frames are then processed applying automated image orientation / Structure from Motion (SfM) and dense image matching / Multi-View Stereo (MVS) methods. Obtained 3D dense point clouds are the visually validated as well as compared with photogrammetric ground truth archived acquiring image with a reflex camera or analysing 3D data's noise on flat surfaces.

An optimised workflow for the interactive experience with cultural heritage through reality-based 3d models: cases study in archaeological and urban complexes

Abstract: . The paper compares two workflows for the achievement of 3D models aimed at in-depth studies on the geometric features of Cultural Heritage artefacts and their dissemination. The purpose is the outlining of pros and cons of different techniques coming from entertainment and video games industry, starting from highly reliable 3D documentation of cultural assets, i.e. architectural/archaeological/urban sites. Two different possible applications are described: (i) procedural modelling used for understanding and visualising reconstruction hypotheses of the vaulted pavilions at Hadrian’s Villa, Tivoli, Rome; (ii) optimisation of 3D high-detailed models, as input files, turned into visual reliable and highly portable assets for game-engines. The first case study is focussed on creating a flexible model for evalueting reconstruction hypotheses and supplying restorers with useful hints for shape completion of ruined pavilions. The second case study makes available detailed digital contents for storytelling historical and cultural events in an attractive way, as in the case of the urban explorative model of Chiuro, a small town in northern Italy.

A deep learning approach for urban underground objects detection from vehicle-borne ground penetrating radar data in real-time

Abstract: . GPRs (Ground Penetrating Radar) are widely adopted in underground space survey and mapping, because of their advantages of fast data acquisition, convenience, high imaging resolution and NDT (Non Destructive Testing) inspection. However, at present, the automation of the GPR data post-processing is low and the identification of underground objects needs expert interpretation. The heavy manual interpretation labor limits the GPR applications in large-scale urban scenarios. According to the latest research, it is still an unsolved problem to detect targets or defects in GPR data automatically and needs further exploration. In this paper, we propose a deep learning method for real-time detection of underground targets from GPR data. Seven typical targets in urban underground space are identified and labelled to construct the training dataset. The constructed dataset is consist of 489 labelled samples including rainwater wells, cables, metal/nonmetal pipes, sparse/dense steel reinforcement, voids. The training dataset is further augmented to produce more samples. DarkNet53 convolutional neural network (CNN) is trained using the constructed training dataset including realistic data and augmented data to extract features of the buried objects. And then the end-to-end YOLO detection framework is used to classify and locate the seven specific categories buried targets in the GPR data in real time. Experiments show that the automatic real-time detection method proposed in this paper can effectively detect the buried objects in the ground penetrating radar image in real time at Shenzhen test site (typical urban road scene).

Crowd4ems: a crowdsourcing platform for gathering andgeolocating social media content in disaster response

Abstract: . Increase in access to mobile phone devices and social media networks has changed the way people report and respond to disasters. Community-driven initiatives such as Stand By Task Force (SBTF) or GISCorps have shown great potential by crowdsourcing the acquisition, analysis, and geolocation of social media data for disaster responders. These initiatives face two main challenges: (1) most of social media content such as photos and videos are not geolocated, thus preventing the information to be used by emergency responders, and (2) they lack tools to manage volunteers contributions and aggregate them in order to ensure high quality and reliable results. This paper illustrates the use of a crowdsourcing platform that combines automatic methods for gathering information from social media and crowdsourcing techniques, in order to manage and aggregate volunteers contributions. High precision geolocation is achieved by combining data mining techniques for estimating the location of photos and videos from social media, and crowdsourcing for the validation and/or improvement of the estimated location. The evaluation of the proposed approach is carried out using data related to the Amatrice Earthquake in 2016, coming from Flickr, Twitter and Youtube. A common data set is analyzed and geolocated by both the volunteers using the proposed platform and a group of experts. Data quality and data reliability is assessed by comparing volunteers versus experts results. Final results are shown in a web map service providing a global view of the information social media provided about the Amatrice Earthquake event.

a Complete Framework Operating Spatially-Oriented Rti in a 3D/2D Cultural Heritage Documentation and Analysis Tool

Abstract: . Close-Range Photogrammetry (CRP) and Reflectance Transformation Imaging (RTI) are two of the most used image-based techniques when documenting and analyzing Cultural Heritage (CH) objects. Nevertheless, their potential impact in supporting study and analysis of conservation status of CH assets is reduced as they remain mostly applied and analyzed separately. This is mostly because we miss easy-to-use tools for of a spatial registration of multimodal data and features for joint visualisation gaps. The aim of this paper is to describe a complete framework for an effective data fusion and to present a user friendly viewer enabling the joint visual analysis of 2D/3D data and RTI images. This contribution is framed by the on-going implementation of automatic multimodal registration (3D, 2D RGB and RTI) into a collaborative web platform (AIOLI) enabling the management of hybrid representations through an intuitive visualization framework and also supporting semantic enrichment through spatialized 2D/3D annotations.

Dead Wood Detection Based on Semantic Segmentation of Vhr Aerial CIR Imagery Using Optimized Fcn-Densenet

Abstract: . The assessment of the forests’ health conditions is an important task for biodiversity, forest management, global environment monitoring, and carbon dynamics. Several research works were proposed to evaluate the state condition of a forest based on remote sensing technology. Concerning existing technologies, employing traditional machine learning approaches to detect the dead wood in aerial colour-infrared (CIR) imagery is one of the major trends due to its spectral capability to explicitly capturing vegetation health conditions. However, the complicated scene with background noise restricted the accuracy of existing approaches as those detectors normally utilized hand-crafted features. Currently, deep neural networks are widely used in computer vision tasks and prove that features learnt by the model itself perform much better than the hand-crafted features. The semantic image segmentation is a pixel-level classification task, which is best suitable to dead wood detection in very high resolution (VHR) mode because it enables the model to identify and classify very dense and detailed components on the tree objects. In this paper, an optimized FCN-DenseNet is proposed to detect dead wood (i.e. standing dead tree and fallen tree) in a complicated temperate forest environment. Since the appearance of dead trees generally occupies greatly different scales and sizes; several pooling procedures are employed to extract multi-scale features and dense connection is employed to enhance the inline connection among the scales. Our proposed deep neural network is evaluated over VHR CIR imagery (GSD-10cm) captured in a natural temperate forest in Bavarian national forest park, Germany, which has undergone on-site bark beetle attack. The results show that the boundary of dead trees can be accurately segmented, and the classification are performed with a high accuracy, even though only one labelled image with moderate size is used for training the deep neural network.

Gis-based mapping of local climate zones using fuzzy logic and cellular automata

Abstract: . Because of the vague distinction between urban and rural areas, the Local Climate Zone (LCZ) scheme was developed to better analyze the effect of Urban Heat Island. To map the LCZs in a city, the World Urban Database and Portal Tool is used as conventional method. However, this requires the assignment of training areas for each LCZ, which entails local knowledge of the area and may introduce errors, as distinction between LCZ types through visual inspection is inconclusive. This paper aims to develop a methodology and GIS tool to enhance and automate the mapping of LCZs using seven LCZ properties (sky view factor, building surface fraction, pervious surface fraction, impervious surface fraction, building height, roughness length, and surface albedo), and apply it in Quezon City, Philippines which comprises varying land use and land cover. Fuzzy Logic was used to determine the membership percentage of 100 m cells to an LCZ type based on these properties. Cellular Automata was implemented using Python to derive the LCZ map from the fuzzy layers. Results show that seven out of ten built-up LCZs and five out of seven land cover LCZs were identified. Through visual inspection on a basemap, the mapped LCZs was confirmed to match with the features of the city. Land Surface Temperature (LST) derived from Landsat 8 showed that each LCZ type displayed temperatures consistent with those observed from literature. The developed methodology and tool is ready to be used in other cities as long as the input layers are generated.

3d virtualization of an underground semi-submerged cave system

Abstract: . Underwater caves represent the most challenging scenario for exploration, mapping and 3D modelling. In such complex environment, unsuitable to humans, highly specialized skills and expensive equipment are normally required. Technological progress and scientific innovation attempt, nowadays, to develop safer and more automatic approaches for the virtualization of these complex and not easily accessible environments, which constitute a unique natural, biological and cultural heritage. This paper presents a pilot study realised for the virtualization of 'Grotta Giusti' (Fig. 1), an underground semi-submerged cave system in central Italy. After an introduction on the virtualization process in the cultural heritage domain and a review of techniques and experiences for the virtualization of underground and submerged environments, the paper will focus on the employed virtualization techniques. In particular, the developed approach to simultaneously survey the semi-submersed areas of the cave relying on a stereo camera system and the virtualization of the virtual cave will be discussed.

Semantic Web Technologies Meet BIM for Accessing and Understanding Cultural Heritage

Abstract: . Within the EU funded project INCEPTION – Inclusive Cultural Heritage in Europe through 3D semantic modelling, the key-targeted achievement is the development of a specific cloud based platform, in order to accomplish the main objectives of accessing, understanding and strengthening European Cultural Heritage by means of enriched 3D models. The whole INCEPTION project is based on the close connection between state-of-the-art architectural modeling technologies (BIM, Building Information Modeling) and the latest cutting-edge web technologies. The platform is grounded on semantic web technologies and makes extensive use of WebGL and RESTful APIs, in order to enrich heritage 3D models by using Semantic Web standards. The INCEPTION platform will be a space for interchange of information and for the dialogue among professionals, students, scholars, curators, non-expert users, etc. Furthermore, the Semantic Web structure interlinks the platform with external Cultural Heritage available linked data and makes it gradually enhanced by specific flexible data structures provided as project specific ontologies. The paper will describe solutions based on the match between BIM, Cloud and Semantic Web.