Training their algorithms with CUDA, researchers from Poland published a paper that presents a new image processing solution that will monitor pavement surfaces by using downward facing cameras placed on the rear of a vehicle. Cracks are the most requiring type of pavement distresses to detect and classify automatically. Due to its nature are easily absorbed by other types of pavement surface damages. Moreover, the diversity of pavement surface makes the image detection system requiring efficient computer algorithms.
The paper presents the solutions tested on surface distress data which were collected automatically using downward facing cameras placed orthogonally to road pavement axis. Presented results focus on the crack-type pavement distresses. The achieved accuracy of the transverse, longitudinal and meshing cracks recognition based on the initial dataset prepared especially for this system, show it has very good chances to work efficiently with large image datasets collected during the inspection car runs.
The researchers from Poznan University of Technology mention CUDA is “desirable since in this kind of task we have to deal with enormous amount of data (e.g., one hour of data capture covers about 30km of the one-lane pavement section and is expected to be few gigabytes large).”
Read the research paper >>
Intelligent Monitoring System to Detect Asphalt Cracks
Aug 25, 2015
Discuss (0)
Related resources
- DLI course: Deep Learning for Industrial Inspection
- DLI course: Building Real-Time Video AI Applications
- GTC session: Live from GTC: A Conversation with Ansys
- GTC session: Harnessing Computer Vision and Traffic Cameras for Urban Traffic Monitoring
- GTC session: Ferrovial’s Journey: From Vision to Reality in the Infrastructure Sector
- NGC Containers: MATLAB