Method, device and storage medium for non-destructive semantic segmentation of high-resolution images of concrete cracks
A semantic segmentation and concrete technology, applied in image analysis, image enhancement, image data processing, etc., can solve problems such as excessive calculation, unbalanced categories, and reduced ability of the model to recognize background information
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0048] Such as figure 1 As shown, this embodiment provides a method for lossless semantic segmentation of concrete crack high-score images, including:
[0049] S01: Obtain a high-resolution image of the concrete surface;
[0050] S02: Using a sliding window to intercept the high-resolution image of the concrete surface into several partial images;
[0051] S03: Input several partial images into the pre-trained concrete crack initial identification model one by one, and screen out all the identified local images with crack probability greater than the preset threshold; wherein, the concrete crack initial identification model is based on historical concrete crack height Obtained by training the traditional convolutional neural network with image data;
[0052] S04: Input the selected partial images into the pre-trained concrete crack semantic segmentation model one by one, and output the corresponding pixel-by-pixel classification concrete crack semantic segmentation map, so a...
Embodiment 2
[0069] Such as figure 2 As shown, this embodiment provides a device for lossless semantic segmentation of high-score concrete crack images, including:
[0070] Image acquisition module 1, used to acquire high-score images of concrete surfaces;
[0071] The preprocessing module 2 is used to intercept the high-score image of the concrete surface into several partial images by adopting a sliding window;
[0072] The initial identification module 3 is used to input several local images into the pre-trained concrete crack initial identification model one by one, and screen out the identified partial images whose crack probability is greater than the preset threshold;
[0073] The semantic segmentation module 4 is used to input the selected local images one by one into the pre-trained concrete crack semantic segmentation model, and output the corresponding pixel-by-pixel semantic segmentation map of concrete cracks, so as to realize the lossless semantic segmentation of high-scori...
Embodiment 3
[0077] This embodiment provides a computer-readable storage medium, which stores a computer program, and when the computer program is loaded by a processor, executes the method for non-destructive semantic segmentation of a concrete crack high-score image as described in Embodiment 1.
[0078] Those skilled in the art should understand that the embodiments of the present application may be provided as methods, systems, or computer program products. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
[0079] The present application is described with reference to flowcharts and / or block ...
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com