This project addresses the current technological difficulties of rapid and automatic reconstruction of large scale areas and seeks solutions for the development of accurate, robust and scalable methods and systems for processing the big data captured by active and passive sensors in order to produce a realistic virtual representation.
The research objectives can be better categorized in three primary areas of investigation involving fundamental research, namely:
1. extraction of structural information from data captured from passive and active remote sensors i.e. aerial/satellite images and LiDAR, and reconstructing terrain, buildings, cars and tree models representing the acquired area
2. reproduction of realistic appearance for the 3D models from imagery captured from ground, oblique-aerial and satellite sensors, and fusing this information into realistic composite texture atlases
3. delineation of geospatial information from remote sensor data i.e. road networks from satellite images and LiDAR
Academic Requirements: We are looking for a highly motivated and creative individual who enjoys working in a collaborative research environment. Good communication skills and fluency in English are required. Applicants should have a strong academic training, including an undergraduate and/or graduate degree in a relevant discipline i.e. computer vision or computer graphics, and have excellent mathematical and programming skills (e.g. C++, Python). Having experience with deep learning and a background in GPU programming are desirable and will be considered a plus.
How to Apply: Send your resume/CV to Charalambos Poullis ([email protected]). Please include degree transcripts and a list of references.