Sonstige
Filtern
Sprache
- Englisch (42) (entfernen)
Schlagworte
- Datenbank (42) (entfernen)
Institut
- Sonstige (42) (entfernen)
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.
The Decision Support System (DSS) is one of the key objectives of the European co-funded research project SafetyCube in order to better support evidence-based policy making. Results will be assembled in the form of a DSS that will present for each suggested road safety measure: details of risk factor tackled, measure, best estimate of casualty reduction effectiveness, cost-benefit evaluation and analytic background. The development of the DSS presents a great potential to further support decision making at local, regional, national and international level, aiming to fill in the current gap of comparable measures effectiveness evaluation. In order to provide policy-makers and industry with comprehensive and well-structured information about measures, it is essential that a systems approach is used to ensure the links between risk factors and all relevant safety measures are made fully visible. The DSS is intended to become a major source of information for industry, policy-makers and the wider road safety community.
Although the annual traffic accident statistics published by the national police is available in public, the detailed traffic accident data has not been released in Korea. Recently the Ministry of Land, Infrastructure and Transport recognized the importance of in-depth accident data to enhance road traffic safety and initiated a research project to establish a collection of the detailed accident data. The main objective of the project is a feasibility study to establish KIDAS (Korea In-Depth Accident Study). Within this project, three university hospitals which are located in mid-size cities have been selected to collect accident data. Annually, more than 500 cases of accidents have been collected from the in-patient's interviews and diagnosis. Unlike GIDAS (German In-Depth Accident Study), currently on-site investigation can"t be performed by the Korean police. The only available data is patient medical records, patient's description of accident circumstances and the damaged vehicle. Occasionally the police provide the accident investigation reports containing very brief information on accident causation and vehicle safety. In a first step, the concept of KIDAS is to adopt the format of iGLAD (Initiative for the Global Harmonization of Accident Data) for harmonization. Since the currently collected accident information is extremely limited compared with GIDAS, the other sources of data and calculations such as KNCAP vehicle data, pc-crash simulations, vehicle registration information, insurance company data are utilized to complete the iGLAD template. Results from KIDAS_iGLAD and the cases of assessment of active safety devices such as AEBS, ESC, and LDWS will be evaluated.
While it is important to track trends in the number of road accidents in different countries using national statistics, there is a need for data with more detailed information, so called in-depth accident data. For this reason, several accident data projects emerged worldwide in recent years. However, also different data standards were established and so comparative analysis of international in-depth data has been very hard to conduct, so far. This is why the project iGLAD (Initiative for the Global Harmonization of Accident Data) was established and created the prerequisites for building up a standardized dataset out of the common denominator of different in-depth accident databases from Europe, USA and Asia. In the first phase, the project received funding from ACEA to compile an initial database. To accomplish this, a suitable data scheme has been defined, a pilot study has been conducted as proof of concept and the recoding of the first common data base has been initiated. Also, to prepare the project for its self-supporting continuation in the next years, a business model has been developed. This paper reports the history and status of the project, the current challenges and the creation of a capable consortium to maintain the data. In mid-2014, the initial database containing 1550 cases from 10 different countries will be completed and a first detailed view on this data will be possible.
An approach to the standardization of accident and injury registration systems (STAIRS) in Europe
(1998)
STAIRS is a European Commission funded study whose aim is to produce a set of guidelines for a harmonised, crash injury database. The need to evaluate the effectiveness of the forthcoming European Union front and side impact directives has emphasised the need for real world crash injury data-sets that can be representative of the crash population throughout Europe. STAIRS will provide a methodology to achieve this. The ultimate aim of STAIRS is to produce a set of data collection tools which will aid decision making on vehicle crashworthiness as well as providing a means to evaluate the effectiveness of safety regulations. This paper will disseminate the up-to-date findings of the group as they try to harmonise their methods. The stage has been reached where studies into the diverse methods of the UK, French and German systems of crash injury investigation have been undertaken. An assessment has already been made of the relationships between the three current systems in order to define the areas of agreement and divergence. The conclusions reached stated that there were many areas that are already closely related and that the differences were only at the detailed level. With the emphasis on secondary safety and injury causation, core data sets were decided upon, taking into account: vehicle description, collision configuration, structural response of vehicles, restraint and airbag performance, child restraint performance, Euro NCAP, pedestrian and vehicle occupant kinematics, injury description and causation. Each variable was studied objectively, the important elements isolated and developed into a form that all partners were agreeable on. A glossary of terms is being developed as the project progresses which includes ISO standards and other definitions from the associated CAREPLUS project, which addresses the comparability of national data sets. A major consideration of the group was the data collection method to be employed. The strengths and weaknesses of each study were investigated to obtain a clear idea of which aspects offered the best way forward. The quality of this information and transference into a common format, as well as the necessary error checking systems to be employed have just been completed and are described. In tandem with this area of study the problem of the statistical relationship of each sample to the national population is also being investigated. The study proposes a mechanism to use a sample of crash injury data to represent the national and international crash injury problem
Powered Two Wheelers (PTWs) accidents constitute one of the road safety problems in Europe. PTWs fatalities represent 22% at EU level in 2006, having increased during last years, representing an opposite trend compared to other road users" figures. In order to reduce these figures it is necessary to investigate the accident causation mechanisms from different points of view (e.g.: human factor, vehicle characteristics, influence of the environment, type of accident). SAFERIDER project ("Advanced telematics for enhancing the SAFEty and comfort of motorcycle RIDERs", under the European Commission "7th Framework Program") has investigated PTW accident mechanisms through literature review and statistical analyses of National and In-depth accident databases; detecting and describing all the possible PTW's accident configurations where the implementation of ADAS (Advanced Driver Assistance Systems) and IVIS (In-Vehicle Information Systems) could contribute to avoid an accident or mitigate its severity. DIANA, the Spanish in-depth database developed by CIDAUT, has been analyzed for that purpose. DIANA comprises of accident investigation teams, in close cooperation with police forces, medical services, forensic surgeons, garages and scrap yards. An important innovation is the fact that before injured people arrive to hospitals, photographs and explanations about the possible accident injury mechanisms are sent to the respective hospitals (via 3G GPRS technology). By this, additional information to medical staff can be provided in order to predict in advance possible internal injuries and select the best medical treatment. This methodology is presented in this paper. On the other hand, the main results (corresponding to road, rider and PTW characteristics; pre and post-accident manoeuvres; road layout; rider behaviour; impact points; accident causations;...) from the analyses of the PTW accidents used for SAFERIDER are shown. Only accident types relevant to ADAS and IVIS devices have been considered.
Since its beginning in 1999, the German In-Depth Accident Study (GIDAS) evolved into the presumably leading representative road traffic accident investigation in Europe, based on the work started in Hanover in 1973. The detailed and comprehensive description of traffic accidents forms an essential basis for vehicle safety research. Due to the ongoing extension of demands of researchers, there is a continuous progress in the techniques and systematic of accident investigation within GIDAS. This paper presents some of the most important developments over the last years. Primary vehicle safety systems are expected to have a significant and increasing influence on reducing accidents. GIDAS therefore began to include and collect active safety parameters as new variables from the year 2005 onwards. This will facilitate to assess the impact of present and future active safety measures. A new system to analyse causation factors of traffic accidents, called ACASS, was implemented in GIDAS in the year 2008. The whole process of data handling was optimised. Since 2005 the on-scene data acquisition is completely conducted with mobile tablet PCs. Comprehensive plausibility checks assure a high data quality. Multi-language codebooks are automatically generated from the database structure itself and interfaces ensure the connection to various database management systems. Members of the consortium can download database and codebook, and synchronize half a terabyte of photographic documentation through a secured online access. With the introduction of the AIS 2005 in the year 2006, some medical categorizations have been revised. To ensure the correct assignment of AIS codes to specific injuries an application based on a diagnostic dictionary was developed. Furthermore a coding tool for the AO classification was introduced. All these enhancements enable GIDAS to be up to date for future research questions.
Police records about traffic accidents like used by IRTAD (International Road Traffic and Accident Database) and CARE (Community Road Accident Database) do not represent all road injuries. For instance, road accidents of bicyclists without a counterpart are usually not reported. Furthermore, IRTAD-like data contains hardly any information on injury outcome and accident circumstances. This information gap leads to an under-representation of the safety concerns of the most vulnerable road users like children and the elderly both in accident research and safety promotion. Injury registration for the European Injury Database (IDB), in turn, combines details of accident causation with diagnostic information that can be used to assess injury severity and long term consequences. The IDB is collecting data from hospital emergency department patients and is being implemented in a growing number of countries. In this article IDB results on mode of transport and injury outcome are presented from a sample of nine EU member states.
The increasing economics in India has an enormous growth of its road traffic. As observed from official Indian accident statistics the number of road fatalities are one of the highest worldwide. In contrast to most industrialized nations they have an rapidly increasing trend. To come along with this trend it becomes more than essential to understand the traffic accident situation. The official Indian accident statistics gives a glimpse of only basic information. Therefore more detailed data is needed. By using In-depth accident data and officially representative statistics the current accident situation can be evaluated in India, if a suitable weighting methodology is considered. Hence in 2009/2010 a pilot study with the collaboration partner JP-Research India pvt. Ldt. was gathered in Tamil Nadu in south of India. In-depth accident investigations were done around the Coimbatore area on four highways. At first, the collected data is evaluated. Due to consequent and continuous further development based on the first approach a methodology similar to NASS/CDS/GES in the US and GIDAS in Germany was developed. Of course all relevant accident related parameters including pictures and severity information were collected. As a matter of fact based on scaled sketches and reconstruction benefit analyses can be done in order to analyze the accident scenery in India. As a first outcome influence from infrastructure, missing education and vehicle safety were identified as key parameters in order to reduce the number of accidents and casualties. To compare the accident situation against international standards an accident classification for left hand traffic was developed based on the German Insurance classification system. Looking into detail additional accident types were identified and added to create an Indian accident type catalogue. The positive results encouraged several OEMs to participate in this investigation and together with BOSCH a consortium was established in 2010/11. Within one year from beginning in May 2011 about 200 highway accidents were collected, reported and reconstructed using the new standard. Hence a first good overview of the accident situation is available for the Coimbatore Tamil Nadu area. The major target for establishing accident investigations is the extension towards other states of India and urban areas to achieve a better overview of the accident scenery. Therefore local and national authorities have to be embedded in order to strengthen the awareness against traffic safety.