There have been massive improvements in autonomous driving, and other related capabilities in the automotive industry in recent years. Driven by the pioneers in the industry, full market adoption of these technologies is approaching quickly. Deep learning is a major enabler in the space of autonomous driving systems and is used for various tasks including the detection of other vehicles, classification of traffic signs and obstacle recognition. For machine drivers to become safer than human drivers however, there is still some way to go. Experts agree nonetheless that deep learning will take this hurdle in the coming years.
In partnership with Bosch, Merantix is working on evaluating and improving deep learning tools in autonomous driving. We are creating, training and evaluating neural nets that recognize objects, such as traffic lights, signs and cars, from driver-assistance system sensor data (i.e. videos and images). Our system visualizes the characteristics of a trained neural network based on state of the art research. Besides visualizing the parametrization of the neural network itself, the tool is also able to highlight relevant regions of an image, which triggered decisions by the neural network and quantify those.
Find below our open-source project:
Number of Papers
published in top-tier journals and conferences on visualizing neural networks.
of automakers do not have a hacking countermeasure strategy in place.
faster growth rate of the connected car market vs. the total car market.
Your data and knowledge,
Schedule an appointment