Road condition acquisition and assessment are the key to guarantee their permanent availability. In order to maintain a country's whole road network, millions of high-resolution images have to be analyzed annually. Currently, this requires cost and time excessive manual labor. We aim to automate this process to a high degree by applying deep neural networks. Such networks need a lot of data to be trained successfully, which are not publicly available at the moment. In this paper, we present the GAPs dataset, which is the first freely available pavement distress dataset of a size, large enough to train high-performing deep neural networks. It provides high quality images, recorded by a standardized process fulfilling German federal regulations, and detailed distress annotations. For the first time, this enables a fair comparison of research in this field. Furthermore, we present a first evaluation of the state of the art in pavement distress detection and an analysis of the effectiveness of state of the art regularization techniques on this dataset.
Camera-monitor systems (CMS) can be used in motor vehicles to display the driver's rear view on a monitor mounted inside the vehicle. This also offers the possibility of replacing conventional exterior mirrors with suitable CMS and thereby implementing new design concepts with aerodynamic advantages. However, as exterior mirrors are safety-relevant vehicle parts for securing the driver's indirect rear view (requirements specified in UN Regulation No. 46), the question arises whether CMS can provide an equivalent substitute for mirrors. In the scope of this study, CMS and conventional exterior mirrors were compared and assessed in test drives and static tests under different external conditions. On the one hand, the examination of technical aspects, and on the other hand, issues pertaining to the design of the human-machine interaction, were the objects of the study. Two vehicles were available for the trials with passenger vehicles: A vehicle, manufactured in small series, which is already equipped with CMS as sole replacement for the exterior mirrors, as well as a compact class vehicle which had a CMS retrofitted by the car manufacturer in addition to conventionally used exterior mirrors. The latter could be covered exclusively for trips with CMS. A tractor unit with semitrailer was available for the truck trials. The driver's cabin was equipped with a CMS system developed by the vehicle manufacturer. In general, it was shown that it is possible to display the indirect rear view sufficiently for the driver, both for cars and trucks, using CMS which meet specific quality criteria. Depending on the design, it is even possible to receive more information about the rear space from a CMS than is possible with mirror systems. It was also shown that the change from mirrors to CMS requires a certain period of familiarisation. However, this period is relatively short and does not necessarily result in safety-critical situations.
Within the automotive context camera monitor systems (CMS) can be used to present views of the traffic situation behind the vehicle to the driver via a monitor mounted inside the cabin. This offers the opportunity to replace classical outside rearview mirrors and therefore to implement new design concepts, aerodynamically optimized vehicle shapes and to reduce the width of the vehicle. Further, the use of a CMS offers the potential to implement functionalities like warnings or situation-adaptive fields of view that are not feasible with conventional rearview mirrors. Despite these potential advantages, it is important to consider the possible technical constraints of this technology and its effect on driver perception and behavior. On the technical side next to the field of view and die robustness of die system, aspects as its functionality at day and night as well as under varying weather conditions should be object to scientific investigation. Concerning human machine interaction, it has to be considered, that the perception of velocities and distances of approaching vehicles might be different for CMS as compared to conventional rearview mirrors and potential influences of factors as the Position of the displays or drivers' age should be taken into account. In order to shed light on these and further open issues, BASt is currently conducting a study that will cover the use of CMS under controlled conditions as well in real traffic. The first part of the study will focus on passenger cars, while in a second step the empirical investigation will be extended to heavy goods vehicles, where the potentials as well as the limitations of CMS might differ considerably. The presentation will cover the first part, with regard to the experimental design, implementation and initial results if already available.
The Traffic Accident Research Institute at University of Technology Dresden investigates about 1,000 accidents annually in the area around and in Dresden. These datasets have been summarized and evaluated in the GIDAS (German Accident In-Depth Study) project for 13 years. During the project it became apparent that the specific traffic situation of a covert exit of a passenger car and an intersecting two-wheeler involves a high risk potential. This critical situation develops in a large part due to the lack of visibility between the driver and the intersecting bike. In this paper the accident avoidance potential of front camera systems with lateral field of view, which allows the driver to have an indirect sight into the crossing street area will be presented.
The changed focus in vehicle safety technology from secondary to primary safety systems need to evolve new methods to investigate accidents, high critical, critical and normal driving situations. Current Naturalistic Driving Studies mostly use vehicles that are highly equipped with additional measuring devices, video cameras, recording technology, and sensors. These equipped fleets are very expensive regarding the setup and administration of the study. Due to the great rarity of crashes it is additionally necessary to have a high distribution and a homogeneous distribution of subject groups. At the end all these facts are leading to a very expensive study with a manageable number of data. Smartphones are becoming more and more popular not only for younger people. Contrary to traditional mobile phones they are mostly equipped with sensors for acceleration and yaw rates, GPS modules as well as cameras in high definition resolution. Additionally they have high-performance processors that enable the execution of CPU-intensive tools directly on the phone. The wide distribution of these smartphones enables researchers to get high numbers of users for such studies. The paper shows and demonstrates a software app for smartphones that is able to record different driving situations up to crashes. Therefore all relevant parameter from the sensors, camera and GPS device are saved for a given duration if the event was triggered. The complete configuration is independently adjustable to the relevant driver and all events were sent automatically to the research institute for a further process. Direct after the event, interviews with the driver can be done and important data regarding the event itself are documented. The presentation shows the methodology and gives a demonstration of the working progress as well as first results and examples of the current study. In the discussion the advantages of this method will be discussed and compared with the disadvantages. The paper shows an alternative method to investigate real accident and incident data. This method is thereby highly cost efficient and comparable with existing methods for benefit estimation.