Evaluation of underwater 3D reconstruction methods for Archaeological Objects: Case study of Anchor at Mediterranean Sea
| Autor: | Jean Triboulet, Sébastien Druon, Arnuad Meline, Bruno Jouvencel, Yadpiroon Onmek |
|---|---|
| Přispěvatelé: | Robotique mobile pour l'exploration de l'environnement (EXPLORE), Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier (LIRMM), Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM), Université de Nîmes (UNIMES) |
| Rok vydání: | 2017 |
| Předmět: |
060102 archaeology
business.industry Computer science 3D reconstruction ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Point cloud Triangulation (computer vision) Image processing 06 humanities and the arts 02 engineering and technology RANSAC Archaeology Euclidean distance Computer Science::Computer Vision and Pattern Recognition 0202 electrical engineering electronic engineering information engineering Pinhole camera model 020201 artificial intelligence & image processing 0601 history and archaeology Computer vision 14. Life underwater Artificial intelligence Underwater business [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing |
| Zdroj: | 3rd International Conference on Control, Automation and Robotics ICCAR: International Conference on Control, Automation and Robotics ICCAR: International Conference on Control, Automation and Robotics, Apr 2017, Nagoya, Japan. pp.394-398, ⟨10.1109/ICCAR.2017.7942725⟩ |
| DOI: | 10.1109/iccar.2017.7942725 |
| Popis: | International audience; The objective of this paper is to develop 3D underwater reconstruction of archeology object, which is based on a mono-camera. The underwater images are obtained from a calibrated camera system. We first solve the problem of image processing by applying the well-known filter, therefore to improve quality of underwater images. The features of interest between image pairs are selected by well-known methods: a FAST detector and FLANN descriptor. Subsequently, the RANSAC method is applied to reject outlier points. The putative inliers are matched by triangulation to produce sparse point clouds in 3D space, using a pinhole camera model and Euclidean distance estimation. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|