620 Ingenieurwissenschaften und zugeordnete Tätigkeiten
Filtern
Schlagworte
- Condition survey (2)
- Zustandsbewertung (2)
- Belastung (1)
- Betonstraße (Oberbau) (1)
- Camera (1)
- Data base (1)
- Data processing (1)
- Datenbank (1)
- Datenverarbeitung (1)
- Decke (Straße) (1)
Institut
- Abteilung Straßenbautechnik (2)
- Sonstige (1)
In Germany, expenditure for the construction of new and maintenance of existing federal highways is currently at a record level of EUR 8 billion per year. In connection with the planned infrastructure policy reforms it is necessary to further develop the planning tools for dimensioning and substance assessment of road structures in order to increase the efficiency of construction measures. The stress caused by traffic is of central importance here. Since unevenness in the road surface has a significant influence on the dynamic part of the wheel load, dynamic effects must be explicitly taken into account. As a result, increasing unevenness can lead to higher dynamic loads and, in the context of a corresponding number of wheel rollovers, to disproportionate damage to the road structure. In general, a shock factor is taken into account during dimensioning, which is to be considered as a function of vehicle suspension, load, speed and evenness. This approach is not sufficient for concrete road structures executed as slabs. In the normal case, only the periodically occurring individual event of a transverse contraction joint, superimposed by irreversible and/or temporary slab deformations, can lead to a significant increase in the dynamic wheel load. In addition, the existing slab deformations are tied to many boundary conditions and can therefore vary greatly in their characteristics. For the further development of methods for dimensioning and residual substance assessment with regard to their accuracy, a three-dimensional slab-specific view of the road surface is therefore appropriate. In this paper, a suitable measuring method for three-dimensional surface laser scanning and an algorithm for the classification of slab deformations are presented.
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.