With the increasing autonomy of vehicles, more and more precise systems for intelligent environment perception are needed. Since classical image processing algorithms are limited in their possibilities and their accuracy, more and more Deep Learning-based systems are being used, which in turn push today's hardware to its limits.

Multi-task learning offers the possibility to solve several computer vision tasks simultaneously and to combine several systems for intelligent environment perception. The required computing effort and the quality of the results can thus be improved.

Multi-task learning is an integral part of efficiently realising Deep Learning-based systems for intelligent environment perception on today's embedded hardware.