Abstract
Rapid and effective identification and extraction of road cracks has always been a major difficulty in road detection and maintenance. This paper applies the Deeplabv3 + model to road crack extraction, and proposes a new joint identification method for road cracks based on open network data and open source convolutional neural network. Based on the semantic segmentation theory and Deeplabv3+ neural network, this method uses baidu street view map as the training data set. By adjusting the proportion weight of road cracks and background, the training network model can quickly and accurately identify road cracks. Experimental results show that this method has achieved a good effect on crack segmentation: Mean Intersection over Union(MIOU) of this method is more than 70%, and the processing speed is 1 second/sheet, which is better than FCN algorithm.The results of road crack information extraction are similar to those of manual interpretation, which indicates that this method is feasible for quality evaluation of municipal roads.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
