29 research outputs found
Élaborer une approche d'assistance à la navigation à inspiration cognitive pour les personnes souffrant d'une incapacité visuelle majeure: Cas du piéton non voyant
No full textLes personnes non voyantes font face à des défis quotidiens au cours de leurs activités de navigation. Afin d’offrir des solutions technologiques pour les aider à surmonter ces défis, il est nécessaire d’élaborer une méthodologie de recherche appropriée qui prend en considération leurs besoins spécifiques. Cette méthodologie nécessite des connaissances multidisciplinaires et une capacité de travailler avec des équipes provenant de différents domaines.
Nous entamons cette thèse par un aperçu sur les différentes approches de conception adoptées en ingénierie et en réadaptation. Nous exposerons les principes de l’approche classique d’ingénierie, puis du design participatif, ensuite du design universel et enfin notre nouvelle approche de conception que nous nommons ‘le design cognitif’.
Nous mettons en évidence le potentiel de cette nouvelle approche pour fournir des solutions qui répondent aux attentes et aux besoins des personnes non voyantes. Cette approche sert à améliorer la conscience situationnelle chez ces individus pendant leurs activités de navigation dans des zones urbaines.
Dans un premier temps, nous avons étudié la nature de la représentation mentale de l’espace chez les personnes non voyantes. Après cela, nous avons modélisé la configuration de cette représentation mentale en nous basant sur les schémas d’image. Ces schémas permettent de capturer de manière claire et significative les différentes relations qui existent entre les éléments de la représentation mentale. Ensuite, nous avons élaboré un modèle conceptuel sémantique de données spatiales utiles pour aider les individus non voyants dans leurs différentes tâches de navigation et de wayfinding. Ces données doivent être structurées de façon hiérarchique afin de garantir une meilleure communication entre l’outil d’assistance et l’utilisateur non voyant. Enfin, nous avons intégré ce modèle sémantique avec la norme ISO 19133:2005 développée pour soutenir les services de suivi et de navigation des clients mobiles. Nous avons aussi utilisé un scénario type de navigation qui illustre l’apport et la contribution du design cognitif pour concevoir des outils d’assistance pour les personnes non voyantes.Blind people encounter many challenges during their daily activities of navigation. In order to develop technological solutions to assist them, it is necessary to elaborate an appropriate research methodology that take into account the specific needs of people suffering from such a disability. This methodology requires multidisciplinary knowledge and the ability to work with teams with widely different backgrounds.
First of all, we propose an overview of different approaches of design adopted in rehabilitation and engineering, beginning with the classical engineering approach, then progressing to participatory design, universal design and a novel approach of design that we call ‘cognitive design’.
Then, we highlight the potential of this latter approach in providing solutions that meet the expectations and the needs of disabled people. This approach helps to provide blind people with heightened situation awareness during their navigational activities within urban areas.
At the beginning, we investigated the nature of the mental representation of space used by blind persons. We then represented this information using image schemata as these capture in a meaningful way the different features that make up the spatial configuration. Next, we elaborated a semantic model of useful geospatial data which will serve to assist the visually impaired in various tasks of navigation and wayfinding. These data must be hierarchically structured in order to guarantee a better communication between the device and blind users. After that, we integrated this semantic model with basic geographic information useful for tracking and navigation activities, using the ISO 19133:2005 data standard developed for Location-based Services. A typical scenario is used to show the contribution and value of adopting the cognitive design approach to develop an assistive tool for blind pedestrians
Developing a combined Light Detecting And Ranging (LiDAR) and Building Information Modeling (BIM) approach for documentation and deformation assessment of Historical Buildings
No full textCultural heritage plays a fundamental role in preserving the collective memory of a nation.
However, it is noted that many historical buildings suffer from serious deformation that may lead to deterioration or loss. In this paper, we propose an approach for documentation and deformation assessment of historical buildings based on the combination of Terrestrial Light Detecting And Ranging (LiDAR) technology and Building Information Models (BIM). In order to digitally archive the current state of a historical building, classical surveying techniques (Traversing, Levelling and GPS) are integrated with Terrestrial Laser scanner (TLS). A Leica Scan Station C10 is used to accomplish the 3D point cloud acquisition. In addition, Leica GNSS Viva GS15 receivers, a Leica Total Station TCR 1201+ and a Leica Runner 24 are used for classical surveying. The result is a 3D point cloud with high resolution, which is referenced according to the local geodetic reference system Ain el Abd UTM 37N. This point cloud is then used to create a 3D BIM that represents the ideal condition of the building. This BIM also contains some important architectural components of the historical building. To detect and assess the deformation of building’s parts that require an urgent intervention, a comparison between the 3D point cloud and the 3D BIM is performed. To achieve this goal, the main parts of the building in the BIM model (such as ceilings and walls) are compared with the corresponding segments of the 3D point cloud according to the normal vectors of each part. A case study that corresponds to a historical building in Jeddah Historical City named ’Robat Banajah’ is presented to illustrate the proposed approach. This building was built to serve pilgrims that want to perform the fifth pillar of Islam. Then, it was endowed (waqf) as a charity housing for widows and disabled. The results of assessing deformations of the case study show that some rooms are in a degraded condition requiring urgent restoration (distortions reach up to 22 cm), while other building parts are in a non-critical condition.</jats:p
Developing a combined Light Detecting And Ranging (LiDAR) and Building Information Modeling (BIM) approach for documentation and deformation assessment of Historical Buildings
No full textCultural heritage plays a fundamental role in preserving the collective memory of a nation.
However, it is noted that many historical buildings suffer from serious deformation that may lead to deterioration or loss. In this paper, we propose an approach for documentation and deformation assessment of historical buildings based on the combination of Terrestrial Light Detecting And Ranging (LiDAR) technology and Building Information Models (BIM). In order to digitally archive the current state of a historical building, classical surveying techniques (Traversing, Levelling and GPS) are integrated with Terrestrial Laser scanner (TLS). A Leica Scan Station C10 is used to accomplish the 3D point cloud acquisition. In addition, Leica GNSS Viva GS15 receivers, a Leica Total Station TCR 1201+ and a Leica Runner 24 are used for classical surveying. The result is a 3D point cloud with high resolution, which is referenced according to the local geodetic reference system Ain el Abd UTM 37N. This point cloud is then used to create a 3D BIM that represents the ideal condition of the building. This BIM also contains some important architectural components of the historical building. To detect and assess the deformation of building’s parts that require an urgent intervention, a comparison between the 3D point cloud and the 3D BIM is performed. To achieve this goal, the main parts of the building in the BIM model (such as ceilings and walls) are compared with the corresponding segments of the 3D point cloud according to the normal vectors of each part. A case study that corresponds to a historical building in Jeddah Historical City named ’Robat Banajah’ is presented to illustrate the proposed approach. This building was built to serve pilgrims that want to perform the fifth pillar of Islam. Then, it was endowed (waqf) as a charity housing for widows and disabled. The results of assessing deformations of the case study show that some rooms are in a degraded condition requiring urgent restoration (distortions reach up to 22 cm), while other building parts are in a non-critical condition
Élaboration d’un modèle de données spatiales à inspiration cognitive pour assister la navigation des piétons non voyants
No full textA comparative analysis on the use of a cellular automata Markov chain versus a convolutional LSTM model in forecasting urban growth using sentinel 2A images
No full textCities are facing many challenges related to urban growth. This phenomenon has prompted decision-makers to adopt innovative approaches for planning based on accurate forecasting of urban growth. Among the most widely used forecasting methods, there are Cellular Automata (CA) based methods and Recurrent Neural Networks (RNN) based methods. The accuracy of these forecasting models is strongly related to data quality, data availability, Model calibration and Model validation. In this paper, a comparative analysis between three forecasting methods is presented based on a temporal sequence of Sentinel 2A images. The main goal of this study is to assess the performance of these models which are of CA-Markov Chain, MLP-Markov and ConvLSTM in terms of accuracy, complexity, and feasibility. The case study is carried out on the city of Casablanca in Morocco. After implementing these three forecasting methods, the obtained results show that the Kappa coefficient of MLP-Markov, CA-Markov and ConvLSTM is, respectively, 89,40%; 97,20%; and 94,50%. In terms of complexity, the ConvLSTM method is more complex due to the number of elementary operations. In terms of feasibility, the ConvLSTM method is more demanding in terms of data volume since it is a Deep Learning model. Accordingly, CA-Markov based methods, in particular MLP-Markov, show a great potential for forecasting urban growth, especially for short term forecasting when there are not enough satellite images available to adopt a Deep Learning approach such as ConvLSTM
Extending the IFC Standard to Enable Road Operation and Maintenance Management through OpenBIM
No full textOpen Building Information Modelling (OpenBIM) is a collaborative project management process. Its application to road infrastructures is currently limited. OpenBIM standards for infrastructure are still under development. One of these standards is the Industry Foundation Classes (IFC), which is a data architecture for modelling infrastructure projects. The current and upcoming releases of IFCRoad focus on structuring data for the design and construction phases of an infrastructure’s lifecycle. Semantics of the O&M process phase are not fully integrated within these standards. This paper proposes an extension of the IFC schema to enrich this standard with semantics inherent in the O&M phase of road infrastructures. This extension, based on IFCInfra4OM ontology, allows the OpenBIM process to be fully applied to road infrastructures. Its implementation on a case study relative to the A7 Agadir–Marrakech Highway in Morocco enables, on the one hand, analysis and compliance with O&M management requirements on the basis of a single container: the IFC-BIM-based model. On the other hand, it allows comparison of the OpenBIM process with that of ClosedBIM for the integration of O&M data into BIM for a road infrastructure
IFCInfra4OM: An Ontology to Integrate Operation and Maintenance Information in Highway Information Modelling
No full textBuilding information modelling (BIM) is increasingly appropriate for infrastructure projects, and in particular for transport infrastructure. It is a digital solution that integrates the practices of the construction industry in facility management during the whole life cycle. This integration is possible through a single tool, which is the 3D digital model. Nevertheless, BIM standards, such as industry foundation classes, are still in the pipeline for infrastructure management. These standards do not fully meet the requirements of operation and maintenance of transport infrastructure. This paper shows how BIM could be implemented to address issues related to the operation and maintenance phase for transport infrastructure management. For this purpose, a new ontological approach, called Industry Foundation Classes for Operation and Maintenance of Infrastructures (IFCInfra4OM), is detailed. This ontology aims to standardise the use of building information modelling for operation and maintenance in road infrastructures. To highlight the interest of the proposed ontological approach, a building information model of a section on the A7 Agadir–Marrakech Highway in Morocco is produced according to IFCInfra4OM. The methodology is presented. The results obtained, including the IFCInfra4OM data model, are submitted. In the last section, an overview of the IFC extension approach is submitted
Soqia-Advice: A Web-GIS Advisory Platform for Efficient Irrigation in Arboriculture
No full textThe determination of water requirements for crops holds a crucial role in optimizing irrigation and enhancing agricultural productivity. However, identifying these needs remains a significant challenge due to the variety of factors influencing this decision, such as meteorological conditions, soil structure, and the phenological stages of each crop. In this study, we propose the design and development of a dedicated web-based irrigation advisory platform for arboriculture named ‘Soqia-Advice’. This platform will provide services to farmers, advisors, and decision-makers. The proposed methodology is based on four main steps: (1) need assessments; (2) definition of functionalities to fulfill these needs; (3) design of the overall architecture and the conceptual data model; and (4) implementation of key features of the module dedicated to farmers. The prototype of the “Farmer” module was tested on a farm in Azrou city, Morocco, as a case study. Seven-day weather forecasts were seamlessly integrated using the Weatherbit API. Additionally, the irrigation schedule was accurately displayed, ensuring efficient water management. Functionality tests were conducted on each menu to ensure the seamless and reliable operation of all planned features. The results were rigorously assessed to ensure that each feature aligned with the identified needs
Remote Sensing Crop Water Stress Determination Using CNN-ViT Architecture
No full textEfficiently determining crop water stress is vital for optimising irrigation practices and enhancing agricultural productivity. In this realm, the synergy of deep learning with remote sensing technologies offers a significant opportunity. This study introduces an innovative end-to-end deep learning pipeline for within-field crop water determination. This involves the following: (1) creating an annotated dataset for crop water stress using Landsat 8 imagery, (2) deploying a standalone vision transformer model ViT, and (3) the implementation of a proposed CNN-ViT model. This approach allows for a comparative analysis between the two architectures, ViT and CNN-ViT, in accurately determining crop water stress. The results of our study demonstrate the effectiveness of the CNN-ViT framework compared to the standalone vision transformer model. The CNN-ViT approach exhibits superior performance, highlighting its enhanced accuracy and generalisation capabilities. The findings underscore the significance of an integrated deep learning pipeline combined with remote sensing data in the determination of crop water stress, providing a reliable and scalable tool for real-time monitoring and resource management contributing to sustainable agricultural practices
Study of the Potential of a Local Geoid Model for Extracting the Orthometric Heights from GPS Measurements in Topographic Works
No full textDue to the rapid development and expansion of geodetic applications, the determination of orthometric heights in an accurate manner is considered as one of the most required conditions to carry out such projects. Obtaining orthometric heights using traditional methods of levelling is time and cost consuming. Hence, investigating other techniques that provide the same accuracy, as leveling methods, but requiring less time and cost is very gainful. Recently, satellite positioning techniques and their applications are being used increasingly in geodetic projects. So, it is interesting to study the efficiency of such techniques for obtaining orthometric heights. GPS methods provide highly accurate measurement of ellipsoidal heights. However, the conversion of ellipsoid heights to orthometric heights may be achieved using geoid models. The objective of this research is to study the efficiency of using a local geoid model as an alternative method to obtain orthometric heights from GPS measurements. This paper proposes a methodology to generate such local geoid models. Then, the results of using the generated local geoid model for Jeddah city in Saudi Arabia are presented. These results indicate that the difference among estimated undulations values from the local geoid model and undulations values calculated from leveling techniques ranges from 1.8 cm to -1.1 cm. with a maximum standard deviation of 56 mm. These results confirm that the creation of a local geoid model is an effective method that gives the required accuracy for topographic works. Keywords: GPS/Levelling method, Local geoid model, Krigging method
