Maps are quickly becoming outdated, about 10 % of the objects change annually. This project focuses on methods to automatically interpret newly acquired sensor data to detect and update the changed objects in the digital map. The sensor data includes high resolution 2D aerial image data and 3D laser scanner data. Our approach is to use the existing (old) digital maps to learn how various objects appear in these 2D and 3D datasets. The PhD researcher's task is to design a deep learning network to semantically segment airborne sensor data, making use of a huge training dataset derived from the fusion of map and sensor data. For (3D) point clouds derived from stereo (2D) images we aim to build a combined 3D and 2D classification approach, to be able to later classify both point clouds and imagery. Alongside this PhD position, one Postdoc will work on the generation of training data, and one other PhD student will work on the delineation of data into map objects.

The specific tasks in this project are to design of neural networks for image and point cloud classification using massive training data, to image and point cloud classification and domain adaptation, and to change detection between sensor data and map data.

• An MSc degree, obtained no more than 5 years ago, related to computer vision, or geo-informatics, with excellent expertise in acquisition and processing of geo-information, and programming (Python, Tensorflow or PyTorch)
• Excellent study results and experience with the use and further development of deep neural networks
• Be at ease communicating and discussing with various Dutch project partners (in English). In joint meetings research results must be presented to them and the next steps discussed

• An inspiring multidisciplinary and challenging international and academic environment. The university offers a dynamic ecosystem with enthusiastic colleagues in which internationalization is an important part of the strategic agenda
• Fulltime employment for 4 years with a starting salary of €2.541,- gross per month in the first year and increasing to €3.247,- gross per month in the fourth year
• Tailor-made educational/development program of at least 6 months (30EC), including visits to conferences.
• An annual holiday allowance of 8% of the gross annual salary, and an annual year-end bonus of 8.3%.
• Total of 41 holidays per year in case of fulltime employment.
• Professional and personal development programs;
• Costs for moving to Enschede may be reimbursed.

The Department of Earth Observation Science (EOS) is engaged in education, research and capacity building on earth observation, image analysis and geo-health. The department develops and applies methods for the extraction of large scale geo-information from airborne and terrestrial sensors. It holds expertise in laser scanning technology, sensor integration, point cloud processing, scene understanding and 3D landscape and building modelling. The expertise of the department covers spatial statistics, image analysis, deep learning, monitoring and data integration. Geo-health relates the dynamics of diseases to the geo context. This is done by modelling the spread of diseases and their explanatory variables and includes the understanding of the emergence of diseases at various scales.