Road void size automatic measuring and calculating method based on deep learning segmentation
CN119027483APending Publication Date: 2024-11-26CHANGAN UNIV
View PDF 0 Cites 0 Cited by
Patent Information
- Application Number
- CN202410992195.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-23
- Publication Date
- 2024-11-26
Smart Images

Figure CN119027483A_ABST
Abstract
The invention discloses a road void size automatic measuring and calculating method based on deep learning segmentation, and belongs to the technical field of underground disease detection. According to the method, a void calculation equation is obtained through a built void entity model, and the actual area of a road void region is finally obtained by combining a deep learning segmentation model trained in advance. Compared with a traditional manual detection technology, the method has the advantages that the efficiency is remarkably improved, the precision is remarkably improved, meanwhile, compared with a traditional manual void size estimation method, the method can more accurately recognize typical radar image features of void diseases and calculate the sizes of the void diseases, and the method has great benefits in the field of road hidden disease detection and is suitable for popularization and application. And the labor cost of void disease detection can be obviously reduced.
Need to check novelty before this filing date? Find Prior Art
