Vision-based Detection of Road Users and Infrastructure Elements for Automated Driving

The topic of this paper is the implementation and analysis of vision algorithms for the detection of static and dynamic objects in videos. These algorithms are typically components of the visual perception module of modern driver assistance systems or even autonomous cars. Whereas the vast majority of todays' papers from the vision community uses convolutional deep neural networks (CNNs), this paper explores the more traditional approaches, namely HOG (Histogram of Oriented Gradients) as well as SVM (Support Vector Machine). The static and dynamic objects which are to be recognized are traffic signs and motorcycles, respectively. These two object classes have been chosen, since traffic signs are on one hand relatively easy to detect and on the other hand, motorcycles state a much more complex task. Thus, this paper tackles differently difficult tasks with a single set of algorithms.