Convolutional neural network-based concrete structure surface microcrack feature extraction method
A technology of convolutional neural network and concrete structure, which is applied in the direction of neural learning method, biological neural network model, neural architecture, etc., can solve the problems of semantic segmentation network model, such as large data calculation volume, large labor input, high requirements for hardware equipment, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0049] Embodiment 1: as figure 1 As shown, the feature extraction method of concrete structure surface microcracks based on convolutional neural network includes the following six steps:
[0050] Step 1. Establish an image classification data set containing microcracks and background on the surface of the concrete structure;
[0051] Step 2, constructing a two-category convolutional neural network for the identification of micro-crack areas on the surface of concrete structures;
[0052] Step 3, using the data set established in step 1 to train and verify the convolutional neural network constructed in step 2;
[0053] Step 4, using the convolutional neural network trained and verified in step 3 to identify the micro-crack area in the surface image of the concrete structure;
[0054] Step 5, performing skeletonization on the microcrack area in the image identified in step 4;
[0055] Step 6, extracting features of microcracks according to the skeleton of the microcrack regi...
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