Centre de documentation
scientifique

Underwater calibration in near real time: Focus on detection optimized by AI and selection of calibration patterns / Loïca Avanthey (2020)  

Public Titre : Underwater calibration in near real time: Focus on detection optimized by AI and selection of calibration patterns Type de document : Article/Communication Auteurs : Loïca Avanthey, Auteur ; Laurent Beaudoin, Auteur Editeur : New York : Institute of Electrical and Electronics Engineers IEEE Année de publication : 2020 Conférence : IGARSS 2020, 2020 IEEE International Geoscience and Remote Sensing Symposium 26/09/2020 02/10/2020 Waikoloa, Hawaï Etats-Unis proceedings IEEE Importance : n° 9324519 Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie [Termes IGN] capteur imageur [Termes IGN] couple stéréoscopique [Termes IGN] dioptre [Termes IGN] étalonnage [Termes IGN] reconstruction 3D [Termes IGN] scène sous-marine Résumé : (auteur) The 3D reconstruction of underwater scenes from pairs of stereoscopic images requires to model the sensor. To take into account the refraction in the environment and to be compatible with the operational field constraints, we use the compensated pinhole model (the diopter is considered as an additional lens) whose parameters are estimated by an in situ calibration with a pattern. In this article, we propose an optimization by AI of the pattern detection to have real-time feedback and a process which selects on the fly the shots allowing to improve the estimation quality of the model so the manipulation can be stopped when sufficient number of relevant images has been reached. We present the results obtained on a database made up of 60,000 images taken in swimming pools and at sea. Numéro de notice : C2020-039 Affiliation des auteurs : IGN (2020- ) Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1109/IGARSS39084.2020.9324519 Date de publication en ligne : 17/02/2021 En ligne : https://doi.org/10.1109/IGARSS39084.2020.9324519 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102625

Underwater field equipment of a network of landmarks optimized for automatic detection by AI / Laurent Beaudoin (2020)  

Public Titre : Underwater field equipment of a network of landmarks optimized for automatic detection by AI Type de document : Article/Communication Auteurs : Laurent Beaudoin, Auteur ; Loïca Avanthey, Auteur Editeur : New York : Institute of Electrical and Electronics Engineers IEEE Année de publication : 2020 Conférence : IGARSS 2020, 2020 IEEE International Geoscience and Remote Sensing Symposium 26/09/2020 02/10/2020 Waikoloa, Hawaï Etats-Unis proceedings IEEE Importance : n° 9323589 Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] apprentissage profond [Termes IGN] détection automatique [Termes IGN] détection de cible [Termes IGN] point d'appui [Termes IGN] reconstruction 3D Résumé : (auteur) To qualify the point clouds obtained by 3D reconstruction of a global study area in close-range remote sensing, control points, whose position has been measured essentially manually in the field with an instrument whose precision is known, are used. In the underwater environment, equipping the field and carrying out these measurements is a complex operation to perform due to the peculiarities of the environment. We present in this article a first step towards the automation of this task, the automatic detection of targets by a deep learning algorithm which will serve to correctly position the control points locally, and a simplification of the manual measurement which will serve in future work to control the results of automatic readings. Numéro de notice : C2020-040 Affiliation des auteurs : IGN+Ext (2020- ) Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1109/IGARSS39084.2020.9323589 En ligne : https://doi.org/10.1109/IGARSS39084.2020.9323589 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102626