Martin Roehder

Pedestrian crossing detecting as a part of an urban pedestrian safety system

Although recent statistics demonstrate a decrease in pedestrian fatalities, the absolute number of accident related deaths is sufficiently high to justify research in the area of vulnerable road user protection. Research has shown that situation awareness, which requires a significant amount of context information, is critical to timely intervention. Altered pedestrian behavior, due to traffic regulation, requires context information. For example, crosswalk presence and location knowledge can be of importance in pedestrian crossing scenarios. Therefore this paper discusses the implementation of a crosswalk detection algorithm, using Fourier transformation, augmented bipolarity, inverse perspective mapping template matching and edge orientation ratios for classification.

Improving Pedestrian Safety in Urban Scenarios Through Autonomous Collision Avoidance

More than 8000 pedestrian deaths per year in the European Union alone have prompted research into active pedestrian protection systems for motor vehicles. This paper introduces requirements of a collision avoidance system and a practical realization in the form of an experimental vehicle prototype capable of emergency braking and steering maneuvers. The main foci of the paper are the description of the environmental model, its implementation using approaches from the field of computer graphics and suitable testing methods allowing for the assessment of overall system quality. Finally we present the results obtained in both artificial test scenarios as well as actual real world environments.