Classification de données massives de télédétection

Abstract : Thanks to high resolution imaging systems and multiplication of data sources, earth observation(EO) with satellite or aerial images has entered the age of big data. This allows the development of new applications (EO data mining, large-scale land-use classification, etc.) and the use of tools from information retrieval, statistical learning and computer vision that were not possible before due to the lack of data. This project is about designing an efficient classification scheme that can benefit from very high resolution and large datasets (if possible labelled) for creating thematic maps. Targeted applications include urban land use, geology and vegetation for industrial purposes.The PhD thesis objective will be to develop new statistical tools for classification of aerial andsatellite image. Beyond state-of-art approaches that combine a local spatial characterization of the image content and supervised learning, machine learning approaches which take benefit from large labeled datasets for training classifiers such that Deep Neural Networks will be particularly investigated. The main issues are (a) structured prediction (how to incorporate knowledge about the underlying spatial and contextual structure), (b) data fusion from various sensors (how to merge heterogeneous data such as SAR, hyperspectral and Lidar into the learning process ?), (c) physical plausibility of the analysis (how to include prior physical knowledge in the classifier ?) and (d) scalability (how to make the proposed solutions tractable in presence of Big RemoteSensing Data ?)
Complete list of metadatas

Cited literature [462 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-02073908
Contributor : Abes Star <>
Submitted on : Wednesday, March 20, 2019 - 12:20:09 PM
Last modification on : Wednesday, September 11, 2019 - 4:52:44 PM
Long-term archiving on : Friday, June 21, 2019 - 2:11:32 PM

File

2018theseAudebertN.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-02073908, version 1

Citation

Nicolas Audebert. Classification de données massives de télédétection. Vision par ordinateur et reconnaissance de formes [cs.CV]. Université de Bretagne Sud, 2018. Français. ⟨NNT : 2018LORIS502⟩. ⟨tel-02073908⟩

Share

Metrics

Record views

522

Files downloads

239