Projects
Fundamental study on self-lubricating characteristics of polymer from the perspective of wear response, interfacial dynamics and the formation of transfer layer. Ghent University
Investigating particle generation and transfer layer dynamicity at micron-scale provides precise information on the polymer wear process. Parameters contributing specifically to mild, transition and severe wear are studied for its physical interaction process in continuous sliding using advanced image based in-situ monitoring of contact surface. Thereby understanding the complex self-protecting and lubricating nature of polymers.
...
Enhancing Road Safety through UAV captured Aerial Footage and Deep Learning: Object Detection, Risk Prediction, and Real-time Analysis. Hasselt University
Visual servoing control in a cluttered environment based on artificial intelligence. University of Antwerp
Multi-camera Computational Video Architectures Hasselt University
Using data science and decision support tools for autonomous operation of safety-critical electricity grid infrastructure KU Leuven
The European energy system is undergoing a massive transformation as part of broader climate change mitigation efforts and energy security concerns. While societally important, this transformation, most notably the rapidly increasing proliferation of variable renewable energy sources (wind and solar) and accelerating demand electrification (heat, transport, industry), threatens to destabilise the electric grid and even cause large-scale ...
Differentiable programming for improving and accelerating image processing and computer vision algorithms. Ghent University
Differentiable programming is a new programming paradigm that generalizes many existing “deep learning” techniques. In this project, we develop and investigate a new framework for differentiable programming for image processing. We will generate efficient code for parallel processing
architectures (multicore CPU, GPUs, FPGAs) and apply the framework to relevant problems in the domains of computer vision and sensor fusion.
3DEEP: ultrafast, deep learning-based single-shot 3D profilometry. University of Antwerp
Aerial Object Detection KU Leuven
Nowadays, most computer vision problems are solved using artificial intelligence. These techniques outperform traditional computer vision algorithms in most scenarios and even allow the use of computer vision for a variety of challenging new fields. One of these fields is remote sensing. Using artificial intelligence we are able to automatically extract complex metadata, which aids in the decision making process of governments, industries, ...