Mirko Nentwig

Hardware-in-the-loop testing of computer vision based driver assistance systems

In this research paper we investigate the applicability of real-time generated computer graphics for mono camera lane and vehicle detection algorithms. First we introduce a developed hardware-in-the-loop simulator and describe two solutions for the input of the synthetic images. Then the creation of the camera and environment model used for the tests is focused. Therefore first requirements hold by the lane and vehicle detection algorithms are mentioned and different fields of application are described. Finally we demonstrate the applicability on three scenarios derived from real test drives and compare the results to reality.

A method for the reproduction of vehicle test drives for the simulation based evaluation of image processing algorithms

Since the 1980s computer aided engineering (CAE) and simulation (CAS) methods are widely used in the car development process. First the focus was set on crash simulation and car body design. Since a few years due to the rapidly increasing complexity of new electronic systems these techniques are applied in the development and test processes of advanced driving assistance systems (ADAS). There are a lot of motivations, such as cost reduction and safety issues. As a result of these efforts it is possible to reduce the development cycle times and to increase the quality of the products drastically. In this publication the next step in computer aided engineering is taken. The reproduction of a real test drive is described and simulation quality is examined by a vehicle detection algorithm. First an introduction about the motivation for using synthetic generated images for the test of computer vision applications is given. The next section of this paper deals with vehicle detection in general and gives a more detailed introduction to appearance based methods, especially the used Haar-wavelet based approach. The method for the reproduction of a real test drive is described in detail and the application is shown. The results are evaluated by comparing the detection results of classifier between simulation and reality frame by frame. Further the relevant frames of the evaluation are analysed. Finally, a conclusion and outlook about the possible applications and improvements is made

Concerning the applicability of computer graphics for the evaluation of image processing algorithms

In this publication the simulation quality for the application in an ADAS test system is investigated. First requirements regarding to the light transport and image generation system are defined. Next the different shadow simulation techniques are compared to a real scene. In general computer graphics images are too ideal for the evaluation of image processing algorithms, e.g. the contribution of scene background is not depending on the distance. Therefore different approaches for increasing the perceived realism, such as depth-of-field, motion-blur and noise are analyzed. Finally the strength of a calibrated camera simulation is demonstrated by comparing hypotheses generated by vehicle detection system in a real scene and in the simulation.

Hardware-in-the-Loop-Test von vorausschauenden Fahrerassistenzsystemen

Die neue Generation von Fahrerassistenzsystemen verwendet neben physikalischen Umfelddaten auch logische Informationen zur vorausschauenden Berechnung von Fahrsituationen. Diese Informationen stammen aus Navigationsdatenbanken, von Serviceprovidern oder aus der Vernetzung mit anderen Fahrzeugen. Fur die Absicherung derartiger Systeme an einem Hardware-in-the-Loop-Prufstand ist eine Integration dieser Daten in bestehende Testprozesse notwendig. In diesem Artikel wird aufgezeigt, wie die Audi AG gemeinsam mit der Audi Electronics Venture GmbH durch den Einsatz innovativer technischer Losungen eine Simulation derartiger Szenarien ermoglicht.

Hardware-in-the-loop test of advanced driver assistance systems

The new generation of advanced driver assistance systems uses physical environment data along with logical information for the predictive computation of driving situations. This data is obtained from navigation databases, service providers or from networks with other vehicle. It is important to integrate this information into available test processes to assure these systems in the Hardware-in-the-loop test bench. This article demonstrates how Audi AG and Audi Electronics Venture GmbH use innovative technological solutions to facilitate the simulation of such scenarios.