A method, device and electronic device for intelligent selection of pavement crack image preprocessing

A technology for pavement cracks and intelligent selection, applied in the field of image processing, can solve the problems of selecting the optimal preprocessing method for pavement images with different characteristics, and the inability to perform preprocessing operations on pavement images, so as to avoid feature extraction and data reconstruction, and reduce weights. Quantity, the effect of reducing correlation

Active Publication Date: 2022-07-29
BEIJING UNIV OF POSTS & TELECOMM
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing methods are often unable to select the optimal preprocessing method for road images with different characteristics, and it is impossible to perform targeted preprocessing operations on road images.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method, device and electronic device for intelligent selection of pavement crack image preprocessing
  • A method, device and electronic device for intelligent selection of pavement crack image preprocessing
  • A method, device and electronic device for intelligent selection of pavement crack image preprocessing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to specific embodiments and accompanying drawings.

[0055] In the prior art, the preprocessing methods used for pavement crack images mainly include: histogram equalization, bilateral filtering, and morphological opening operation. Each preprocessing method will be described in detail below.

[0056] (1) Histogram equalization

[0057] An important application of histogram equalization grayscale transformation is generally used in image enhancement processing. It uses the histogram to adjust the gray value of the image, enhances the global contrast of the image, and makes the gray value more evenly distributed on the histogram. Images processed by histogram equalization tend to have clearer textures and richer details, and at the same time, the image information entropy will also increase,...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an intelligent selection method, device and electronic equipment for pavement crack picture preprocessing. The pavement crack picture preprocessing method includes: acquiring a pavement crack picture to be processed; for the pavement crack picture to be processed, according to the target The neural network model determines a preprocessing action; the target neural network model is obtained by training based on a training data set of road surface crack pictures with different characteristics; the road surface crack picture to be processed is preprocessed by using the preprocessing action. The intelligent selection method of pavement crack image preprocessing is based on a deep reinforcement learning algorithm, and an algorithm that automatically selects the optimal preprocessing method for pavement image data with different characteristics, thereby further improving the recognition accuracy of pavement cracks.

Description

technical field [0001] The invention relates to the technical field of picture processing in artificial intelligence, in particular to an intelligent selection method, device and electronic equipment for preprocessing of road crack pictures. Background technique [0002] When identifying cracks in pavement pictures, the quality of the image itself will directly affect the design of subsequent algorithms and the accuracy of its effects, etc. Therefore, it is necessary to perform appropriate preprocessing operations on the pictures before the identification operation. The main purpose of image preprocessing is to eliminate some noise information in the image, enhance the readability of effective information, optimize the data information to a greater extent, and provide high-quality conditions for subsequent image processing. However, the existing methods are often unable to select optimal preprocessing methods for road images with different characteristics, and thus cannot pe...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06T5/00G06T7/00
CPCG06T5/002G06T7/0004G06T2207/10004G06T2207/20024G06T2207/20036G06T2207/20081G06T2207/20084G06T2207/30132
Inventor 徐国爱蔺岩徐国胜
Owner BEIJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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