OEM&Lieferant Ausgabe 1/2020

92 Engineering Partner Gaining a better grasp of these mechanisms is the only way to reduce misclassification to a minimum and comply with the ISO 26262 and ISO/PAS 21448 safety standards for the reduction of, for example, unknown or unsafe scenarios. That’s why, as part of its research activities, ARRK Engineering has developed the foundations of a framework for better un- derstanding how CNNs work, and ultimately improving their object classification capabili- ties. This framework makes it easy to identify and eliminate vulnerabilities in a CNN, thus minimizing the risk of errors and accidents caused by incorrect classifications. There is a strong push in the automotive industry to develop better advanced driver assistance systems (ADASs) with the help of, for instance, new hardware with more efficient and robust sensors or more power- ful algorithms. In the ample research being conducted in this area, the recognition rate in Image: © ARRK Engineering Automatic image recognition is only capable of identifying objects – such as people—with a certain degree of proba- bility. Errors in object recognition pose a major safety risk in autonomous driving. Automatic object classification and image processing for autonomous driving Reliable pedestrian recognition: framework supports the analysis of neural networks By Annika Mahl, ARRK Engineering Highly advanced artificial intelligence (AI) and convolutional neural network (CNN) technology has made the auto- matic detection of a range of objects possible. Still, it will never be possible to fully eliminate erroneous classifications – one reason the reliability of automatic image processing must continue to improve. The correct classification of objects is a matter of life or death in autonomous driving, and this requires a deeper understanding of decision- making processes within the neural networks. Image: © ambrozinio/shutterstock.com automatic image processing is of central im- portance. “What’s key to autonomous driving is that the algorithms for object recognition work fast and yield a minimal error rate,” ex- plains Václav Diviš, senior engineer for ADAS & Autonomous Driving at ARRK Engineering. “But it will only be possible to develop optimal safety features for autonomous driving once we have understood neural networks down to the last detail.” To achieve this goal, ARRK Engineering has established an evaluation framework for machine learning in the form of software as part of its research activities. This software will enable deeper insight into the recognition process of neural networks. From there, it will be possible to optimize algorithms and improve automatic object recognition. The experiment also served to gain a better understanding of how neural networks work. Training the neural network The first step was to select a reliable gener- ative adversarial network (GAN) architecture, consisting of two neural networks – one gen- S H A R E