Centre dedocumentation
scientifique

Transfer learning from citizen science photographs enables plant species identification in UAV imagery / Salim Soltani in ISPRS Open Journal of Photogrammetry and Remote Sensing, vol 5 (August 2022)  

Public [article]  inISPRS Open Journal of Photogrammetry and Remote Sensing > vol 5 (August 2022) . - n° 100016 Titre : Transfer learning from citizen science photographs enables plant species identification in UAV imagery Type de document : Article/Communication Auteurs : Salim Soltani, Auteur ; Hannes Feilhauer, Auteur ; Robbert Duker, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 100016 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] base de données naturalistes [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] distribution spatiale [Termes IGN] données localisées des bénévoles [Termes IGN] espèce végétale [Termes IGN] filtrage de la végétation [Termes IGN] identification de plantes [Termes IGN] image captée par drone [Termes IGN] orthoimage couleur [Termes IGN] science citoyenne [Termes IGN] segmentation sémantique Résumé : (auteur) Accurate information on the spatial distribution of plant species and communities is in high demand for various fields of application, such as nature conservation, forestry, and agriculture. A series of studies has shown that Convolutional Neural Networks (CNNs) accurately predict plant species and communities in high-resolution remote sensing data, in particular with data at the centimeter scale acquired with Unoccupied Aerial Vehicles (UAV). However, such tasks often require ample training data, which is commonly generated in the field via geocoded in-situ observations or labeling remote sensing data through visual interpretation. Both approaches are laborious and can present a critical bottleneck for CNN applications. An alternative source of training data is given by using knowledge on the appearance of plants in the form of plant photographs from citizen science projects such as the iNaturalist database. Such crowd-sourced plant photographs typically exhibit very different perspectives and great heterogeneity in various aspects, yet the sheer volume of data could reveal great potential for application to bird’s eye views from remote sensing platforms. Here, we explore the potential of transfer learning from such a crowd-sourced data treasure to the remote sensing context. Therefore, we investigate firstly, if we can use crowd-sourced plant photographs for CNN training and subsequent mapping of plant species in high-resolution remote sensing imagery. Secondly, we test if the predictive performance can be increased by a priori selecting photographs that share a more similar perspective to the remote sensing data. We used two case studies to test our proposed approach with multiple RGB orthoimages acquired from UAV with the target plant species Fallopia japonica and Portulacaria afra respectively. Our results demonstrate that CNN models trained with heterogeneous, crowd-sourced plant photographs can indeed predict the target species in UAV orthoimages with surprising accuracy. Filtering the crowd-sourced photographs used for training by acquisition properties increased the predictive performance. This study demonstrates that citizen science data can effectively anticipate a common bottleneck for vegetation assessments and provides an example on how we can effectively harness the ever-increasing availability of crowd-sourced and big data for remote sensing applications. Numéro de notice : A2022-488 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.1016/j.ophoto.2022.100016 Date de publication en ligne : 23/05/2022 En ligne : https://doi.org/10.1016/j.ophoto.2022.100016 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100956 [article]

Integration of GNSS observations with volunteered geographic information for improved navigation performance / Tarek Hassan in Journal of applied geodesy, vol 16 n° 3 (July 2022)  

Public [article]  inJournal of applied geodesy > vol 16 n° 3 (July 2022) . - pp 265 - 277 Titre : Integration of GNSS observations with volunteered geographic information for improved navigation performance Type de document : Article/Communication Auteurs : Tarek Hassan, Auteur ; Tamer Fath-Allah, Auteur ; Mohamed Elhabiby, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 265 - 277 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] données GNSS [Termes IGN] données localisées des bénévoles [Termes IGN] Google Earth [Termes IGN] hauteur du bâti [Termes IGN] modélisation 3D [Termes IGN] OpenStreetMap [Termes IGN] positionnement par GNSS [Termes IGN] signal GNSS [Vedettes matières IGN] Traitement de données GNSS Résumé : (auteur) Pedestrian and vehicular navigation relies mainly on Global Navigation Satellite System (GNSS). Even if different navigation systems are integrated, GNSS positioning remains the core of any navigation process as it is the only system capable of providing independent solutions. However, in harsh environments, especially urban ones, GNSS signals are confronted by many obstructions causing the satellite signals to reach the receivers through reflected paths. These No-Line of Sight (NLOS) signals can affect the positioning accuracy significantly. This contribution proposes a new algorithm to detect and exclude these NLOS signals using 3D building models constructed from Volunteered Geographic Information (VGI). OpenStreetMap (OSM) and Google Earth (GE) data are combined to build the 3D models incorporated with GNSS signals in the algorithm. Real field data are used for testing and validation of the presented algorithm and strategy. The accuracy improvement, after exclusion of the NLOS signals, is evaluated employing phase-smoothed code observations. The results show that applying the proposed algorithm can improve the horizontal positioning accuracy remarkably. This improvement reaches 10.72 m, and the Root Mean Square Error (RMSE) drops by 1.64 m (46 % improvement) throughout the epochs with detected NLOS satellites. In addition, the improvement is analyzed in the Along-Track (AT) and Cross-Track (CT) directions. It reaches 6.89 m in the AT direction with a drop of 1.076 m in the RMSE value, while it reaches 8.64 m with a drop of 1.239 m in the RMSE value in the CT direction. Numéro de notice : A2022-496 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article DOI : 10.1515/jag-2021-0063 Date de publication en ligne : 23/03/2022 En ligne : https://doi.org/10.1515/jag-2021-0063 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100986 [article]

Detecting land use and land cover change on Barbuda before and after the Hurricane Irma with respect to potential land grabbing: A combined volunteered geographic information and multi sensor approach / Andreas Rienow in International journal of applied Earth observation and geoinformation, vol 108 (April 2022)  

Public [article]  inInternational journal of applied Earth observation and geoinformation > vol 108 (April 2022) . - n° 102732 Titre : Detecting land use and land cover change on Barbuda before and after the Hurricane Irma with respect to potential land grabbing: A combined volunteered geographic information and multi sensor approach Type de document : Article/Communication Auteurs : Andreas Rienow, Auteur ; Jan Schweighöfer, Auteur ; Torben Dedring, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 102732 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] anthropisation [Termes IGN] Antilles (îles des) [Termes IGN] carte thématique [Termes IGN] changement d'occupation du sol [Termes IGN] détection de changement [Termes IGN] données issues des réseaux sociaux [Termes IGN] données localisées des bénévoles [Termes IGN] éclairage public [Termes IGN] image Sentinel [Termes IGN] image Terra-MODIS [Termes IGN] occupation du sol [Termes IGN] OpenStreetMap [Termes IGN] tempête [Termes IGN] utilisation du sol Résumé : (auteur) Two months after the hurricanes Irma and Maria hit Barbuda, the construction of a new international airport led to accusations of degrading the Codrington Lagoon National Park and contravening the conventions of the Ramsar Program. Scientists have analyzed the aftermath with respect to historical legacies, disaster capitalism, manifestation of climate injustices and green gentrification. The main objective of this study was to quantify and allocate land use and land cover change (LULCC) in Barbuda before and after the 2017 Hurricane disasters. Remote sensing data and volunteered geographic information were analyzed to detect the potential changes in natural LULC so that human activities and the emergence of artificial surfaces could be detected. Human-induced LULCC occurred at different sites on the island, with decreased activities in Codrington, but increased and continued activities at Coco and Palmetto Points. With an accuracy of 97.1 %, we estimated a total increase of vegetated areas by 6.56 km2, and a simultaneous slight increase in roads and buildings with a total length of 249.67 km and a total area of 1.43 km2. The vegetation condition itself depict a steady decrease since 2017. New hotspots of human activity emerged on the island in the Codrington Lagoon National Park. Numéro de notice : A2022-233 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/IMAGERIE Nature : Article DOI : 10.1016/j.jag.2022.102732 Date de publication en ligne : 02/03/2022 En ligne : https://doi.org/10.1016/j.jag.2022.102732 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100123 [article]

Mining crowdsourced trajectory and geo-tagged data for spatial-semantic road map construction / Jincai Huang in Transactions in GIS, vol 26 n° 2 (April 2022)  

Public [article]  inTransactions in GIS > vol 26 n° 2 (April 2022) . - pp 735 - 754 Titre : Mining crowdsourced trajectory and geo-tagged data for spatial-semantic road map construction Type de document : Article/Communication Auteurs : Jincai Huang, Auteur ; Yunfei Zhang, Auteur ; Min Deng, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 735 - 754 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Bases de données localisées [Vedettes matières IGN] Géomatique [Termes IGN] base de données routières [Termes IGN] carrefour [Termes IGN] carte routière [Termes IGN] contenu généré par les utilisateurs [Termes IGN] données localisées des bénévoles [Termes IGN] données routières [Termes IGN] extraction de traits caractéristiques [Termes IGN] information sémantique [Termes IGN] intégration de données [Termes IGN] navigation automobile [Termes IGN] vitesse [Termes IGN] Wuhan (Chine) Résumé : (auteur) The road map is a fundamental part of a spatial data infrastructure (SDI), and is widely applied in navigation, smart transportation, and mobile location services. Recently, with the ubiquity of positioning devices, crowdsourced trajectories have become a significant data resource for road map construction and updating. However, existing trajectory-based methods mainly place emphasis on extracting road geometry features and may ignore continuous updating of road semantic information. Hence, we propose a divide-and-conquer method to construct a spatial-semantic road map by incorporating multiple data sources (e.g., crowdsourced trajectories and geo-tagged data). The proposed method divides road map construction into two sub-tasks, road structure reconstruction and road attributes inference. The road structure reconstruction process starts to partition raw trajectory data into different cliques of roadways and road intersections, and then extracts various targeted road structures by analyzing the turning modes in different trajectory cliques. The road attributes inference process aims to infer three pieces of crucial semantic information about road speeds, turning rules, and road names from crowdsourced trajectories and geo-tagged data. The case studies in Wuhan were examined to illustrate that the proposed method can construct a routable road map with enhanced geometric structures and rich semantic information, providing a beneficial data solution for car navigation and SDI update. Numéro de notice : A2022-364 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1111/tgis.12879 Date de publication en ligne : 17/12/2021 En ligne : https://doi.org/10.1111/tgis.12879 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100583 [article]

Volunteered geographic information mobile application for participatory landslide inventory mapping / Raden Muhammad Anshori in Computers & geosciences, vol 161 (April 2022)  

Public [article]  inComputers & geosciences > vol 161 (April 2022) . - n° 105073 Titre : Volunteered geographic information mobile application for participatory landslide inventory mapping Type de document : Article/Communication Auteurs : Raden Muhammad Anshori, Auteur ; Guruh Samodra, Auteur ; Djati Mardiatno, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 105073 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web [Termes IGN] approche participative [Termes IGN] base de données [Termes IGN] cartographie thématique [Termes IGN] données localisées des bénévoles [Termes IGN] effondrement de terrain [Termes IGN] géopositionnement [Termes IGN] inventaire [Termes IGN] Java (île de) [Termes IGN] téléphonie mobile Résumé : (auteur) Participatory landslide inventory mapping using the Volunteered Geographic Information (VGI) mobile app is a promising method to produce a landslide inventory map. The aim of this research is to describe the development and implementation of the VGI mobile app for participatory landslide inventory mapping. The architecture VGI mobile app is developed on the basis of Free Open-source Software for Geospatial Application server-client software to ensure reproducibility and flexibility, and to reduce cost. Anyone can reproduce, modify, and share the code, which suggests improvement in the collective ability to use, prepare, and landslide inventory update. Landslide inventory using VGI mobile app shows that the tool and method successfully map landslides in the landslide prone area (Magelang Regency, Central Java Province, Indonesia) with fairly high levels of effectiveness and convenience. Magelang Regency, one of the landslide prone areas in Java, is located in the intermountain basin surrounded by Menoreh Mountain, Merapi, Merbabu, Suropati-Telomoyo Complex, and Sumbing Volcano. In this study, landslide inventory mapping using VGI mobile app was applied in Magelang Regency by 17 volunteers from BPBD (Regional Agency for Disaster Management) Magelang Regency for three days. Landslides area occurred from 2017 to 2019 were properly identified and mapped by the volunteers. The sizes of landslides varied from 5.2 m2 to 4,632.5 m2, and the average was 208.2 m2. A team of volunteer was able to map 7-10 landslides per day. Participatory mapping using VGI mobile app reduces the time in transferring field data to a GIS database, in contrast to conventional participatory landslide inventory mapping. VGI mobile app allows users to provide new geographical landslide data, share landslide data rapidly, ensure consistency of landslide data, and improve accessibility of landslide data. The use of the VGI mobile app for participatory landslide inventory mapping provides new opportunities to improve risk assessment, preparedness, and early action and warning to landslide hazard. Numéro de notice : A2022-189 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1016/j.cageo.2022.105073 Date de publication en ligne : 22/02/2022 En ligne : https://doi.org/10.1016/j.cageo.2022.105073 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99918 [article]

Modular multi-dimensional tool for emergency evacuation including location-based social network data / Ilil Blum Shem-Tov in Journal of location-based services, vol 16 n° 1 (March 2022)  

Permalink

Analysis of factors affecting adoption of volunteered geographic information in the context of national spatial data infrastructure / Munir Ahmad in ISPRS International journal of geo-information, vol 11 n° 2 (February 2022)  

Permalink

Discovering transition patterns among OpenStreetMap feature classes based on the Louvain method / Yijiang Zhao in Transactions in GIS, vol 26 n° 1 (February 2022)  

Permalink

Maps, volunteered geographic information (VGI) and the spatio-discursive construction of nature / Juan Astaburuaga in Digital Geography and Society, vol 3 (2022)  

Permalink

Measuring and mapping long-term changes in migration flows using population-scale family tree data / Caglar Koylu in Cartography and Geographic Information Science, vol 49 n° 2 (February 2022)  

Permalink

An approach for multi-scale urban building data integration and enrichment through geometric matching and semantic web / Abdulkadir Memduhoglu in Cartography and Geographic Information Science, vol 49 n° 1 (January 2022)  

Permalink

Attributing pedestrian networks with semantic information based on multi-source spatial data / Xue Yang in International journal of geographical information science IJGIS, vol 36 n° 1 (January 2022)  

Permalink

Automated construction of a French Entity Linking dataset to geolocate social network posts in the context of natural disasters / Gaëtan Caillaut (2022)  

Permalink

CIME: Context-aware geolocation of emergency-related posts / Gabriele Scalia in Geoinformatica [en ligne], vol 26 n° 1 (January 2022)  

Permalink

Detecting and visualizing observation hot-spots in massive volunteer-contributed geographic data across spatial scales using GPU-accelerated kernel density estimation / Guiming Zhang in ISPRS International journal of geo-information, vol 11 n° 1 (January 2022)  

Permalink