Faster R-CNN-based bridge crack instance segmentation method
A bridge and crack technology, applied in the field of bridge crack instance segmentation based on FasterR-CNN, can solve the problems of low detection efficiency, low efficiency, incomplete cracks, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0063] Example: as attached figure 1 As shown, the present invention provides a bridge crack instance segmentation method based on Faster R-CNN, which includes the following steps:
[0064] Step 1: Build a bridge crack data set
[0065] 1) First, normalize the collected 2000 bridge crack images and normalize them to 256×256 resolution bridge crack images;
[0066] 2) Use geometric transformation, linear transformation, and image filtering algorithms to amplify the number of normalized bridge crack images;
[0067] Specifically, in order to ensure the balance of the number of various types of bridge crack images in the data set, for multiple types of bridge crack images, namely, cracked bridge crack images, meshed bridge crack images, horizontal bridge crack images, longitudinal bridge crack images, The crack images of the pit-type bridge and the bridge images without cracks are processed. After a series of digital image processing (including geometric transformation, linear transform...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap