Description
Date depot: 16 mai 2019
Titre: Spatio-temporal feature extraction for monitoring environmental changes from heterogeneous high frequency image times series
Directrice de thèse:
Nicole VINCENT (LIPADE)
Directeur de thèse:
Camille KURTZ (LIPADE)
Domaine scientifique: Sciences et technologies de l'information et de la communication
Thématique CNRS : Images et vision
Resumé:
1. CONTEXT
Our Environment is perpetually subject to changes in space and time with significantly varying triggers, frequencies, magnitudes and also consequences to humans. It is critical to monitor Earth surface processes (e.g. coastal erosion, surface deformation, land cover changes) to improve our scientific understanding and knowledge of complex human-environmental interactions.
In collaboration between Computer Sciences and Geo-sciences laboratories, the project TIMES (2018-2021) funded by the ANR aims to produce new knowledge on the dynamics landscape objects from the exploitation of the mass of available heterogeneous geospatial data (point cloud data, aerial and satellite images) acquired with very-high temporal frequency. The objective is to develop and validate novel data processing and analysis methods for environmental monitoring of landscape objects.
2. RESEARCH PROJECT
In the context of this project, the recruited student will investigate the extraction of spatio-temporal features for analyzing change detection from satellite image time series. The originality relies on extracting these features based on the multi‐source variables from the data stream, rather than the extraction of features at each sample time. We will focus on the development of original object-based approaches, adapted to heterogeneous geospatial data, in order to exploit the spatio-temporal relationships of the data.
Doctorant.e: Chelali Mohamed Tayeb