In the frame of the ULB spin-off project named RePRO glass we are developing a new optical technology aiming to perform quality inspection for car windscreen industrial applications. This technology is basically working as a large scanner: the windscreen is translated by a linear stage system in front of the camera system and shape and thickness maps are retrieved from the captured images of the camera system. In general we have two types of signals (Phase Measuring Deflectometry – PMD and Refractive-PROfilometry-RePRO signals) captured by the cameras of the camera system: one signal is a pattern deflected by the windscreen and it is used to retrieve the shape (PMD camera signal) while the second signal is a pattern projected (by a projector system) behind the object and it is used to obtain the thickness information (RePRO camera signal). An alpha version of the RePRO glass prototype has been integrated in the chemical-physics department laboratory of the ULB. Once shape and thickness measurements are obtained, data must be merged together and matched correctly. For this reason it is required to detect the following windscreen features from the PMD camera images: the external border of the windscreen, the internal “black” border of the windscreen (considering the “transition region” in the windscreen black strip) and the areas dedicated for the Advanced Driver Assistance Systems (ADAS). Areas of all these regions must be determined as well. This project can so be split in the following tasks:

i) Literature review of the feature recognition methods for border detection. The images of the windscreen will present a pattern that has to be filtered as well.

ii) Implementation in C++ of the feature recognition method to detect the external and internal borders of the windscreen black strip.

iii) Implementation in C++ of the algorithm measuring the areas of the windscreen transparent and ADAS regions;

iv) Possibility to define several areas in the transparent part of the windscreen considering references provided by car producers (bonus task).

v) Redaction of the relative documentation in the RePRO glass product design document.

Keywords: Image processing, image recognition.

Type of work: 5% experimental, 85% coding, 10% documentation.

Contact:
Dr. Wassilis Tzevelecos wtzevele@ulb.be, Olivier Debeir odebeir@ulb.ac.be

Supervisor:
Ing. Vincent Van Pelt vvpelt@ulb.ac.be