Internship | Computer vision for highway inspection

There are many possibilities for a project in the field of road inspection. A number of research directions are listed below to give you a better understanding on what your internship/graduation project could look like. The exact topic of your project will be determined based on your interests and background, so please mention these in your application.Possible projects:Road segmentation for lane width estimation: The vehicles used to obtain the 3D profile of the road drive across all highway lanes. However, the hard shoulders are not measured. For this project, we are interested in the width of each line, including the hard shoulder by using dashcam footage of the vehicles. The idea is that by automatic segmentation, an accurate estimate of the lane width can be made.Classification of crack like structures: Across the whole Dutch highway system are a large variety of different possible damage types. We are interested in classifying each piece of damage as carefully as possible. Currently, it is challenging to accurately classify different crack-like structures that have similar visual features, such as actual cracks, local repairs, pavement joints, road markings, or long stretches of general wear. In this project, you will investigate (deep learning) solutions to perform this automatic classification.Pavement type classification: Not all asphalt is the same, there are actually several different types of asphalt used to pave the Dutch highways. It is difficult to accurately estimate the amount of general wear accurately without knowing the exact asphalt type. A rough porous type of asphalt might look damaged if you would think it was a fine, dense piece of asphalt. During this project, you will create an algorithm to classify different types of asphalt based, or even estimate the approximate stone-size distribution within the asphalt.You will perform this assignment in the Intelligent Imaging department. TNO’s Intelligent Imaging group is specialized in image processing, image enhancement, image analysis, visual pattern recognition, artificial intelligence and deep learning. This young, passionate, creative and committed group (50 people) works with partners on technological breakthroughs for innovations in important societal and economic themes, developing knowledge in various research areas including both AI (e.g. learning with less data or hybrid AI) as well as crucial non-AI knowledge, real-time algorithms, edge processing and information fusion.The project duration is flexible, but preferably within the range of 6 to 12 months. Please mention in your application whether you are looking for an internship or a graduation project, the preferred length of your project and your desired starting date. When doing an internship/graduation project at TNO you will receive an appropriate internship fee.Keywords to describe this project include: Artificial intelligence, Computer Vision, Image Classification, Detection, Segmentation, Deep Learning, Machine Learning , Road Inspection, Highway Pavement Inspection.