Recognition of Surface Irregularities on Roads: a machine learning approach on 3D models
Roads are composed of various sorts of materials and with the constant use they expose different kinds of cracks or potholes. The aim of the current research is to present a novel automated classification method to be applied on these faults, which can be located on rigid pavement type. In order to...
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Objeto de conferencia |
| Lenguaje: | Inglés |
| Publicado: |
2018
|
| Materias: | |
| Acceso en línea: | http://sedici.unlp.edu.ar/handle/10915/73213 |
| Aporte de: |
| Sumario: | Roads are composed of various sorts of materials and with the constant use they expose different kinds of cracks or potholes. The aim of the current research is to present a novel automated classification method to be applied on these faults, which can be located on rigid pavement type. In order to collect proper representation of faults, a Kinect device was used, leading to three-dimensional point cloud structures. Images descriptors were used in order to establish the type of pothole and to get information regarding fault dimensions. |
|---|