Unlock instant, AI-driven research and patent intelligence for your innovation.

System and method for automatically identifying cement pavement diseases based on digital images

A digital image and automatic recognition technology, applied in the field of computer vision, can solve the problems of poor disease detection effect, high labor intensity, and errors that cannot meet the requirements

Pending Publication Date: 2020-10-16
福建中航赛凡信息科技有限公司
View PDF6 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For maintenance road sections of hundreds of kilometers or even thousands of kilometers, it is necessary to make more accurate investigation and statistics on diseases. At present, manual measurement is mainly used for road surface disease detection, which has low work efficiency, high labor intensity, and the error cannot meet the requirements. The existing pavement maintenance technology is mainly manual, resulting in high maintenance cost, low efficiency and difficult maintenance
At present, the detection and identification of diseases is mainly based on traditional image technology, supplemented by manual judgment, and there are few road surface disease detection technologies based on deep learning. These technical solutions have certain limitations. The detection effect of the disease in the image is poor, misjudgment is prone to occur, and the accuracy is not high, which makes the cost of maintenance too high and the efficiency low
[0003] In recent years, the road condition monitoring system of high-grade highways has become more and more perfect, and the required detection level has become higher and higher. Traditional detection methods can no longer meet the needs of high-grade highway detection.

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
  • System and method for automatically identifying cement pavement diseases based on digital images
  • System and method for automatically identifying cement pavement diseases based on digital images
  • System and method for automatically identifying cement pavement diseases based on digital images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0182] by Figure 6 For example, send the picture to the deep network model for detection and identification, and detect the disease: corner peeling, board corner break.

[0183] a. According to the picture naming rules and the detection and recognition results, the information of the corner peeling and fracture disease in the picture is as follows:

[0184]

[0185]

[0186] in:

[0187] Starting point number = kilometers + [meters / 1000]

[0188] =4522+(0.831)=4522.831

[0189] End point chainage = starting point chainage + [length / 1000]

[0190] =4522.831+(0.002515)≈4522.834

[0191] Length, width and area are calculated by the estimation method proposed by the present invention Uplink: A (B represents downlink)

[0192] b. According to the picture naming rules and the detection and classification results, it can be known that the board corner fracture disease information of the picture is as follows:

[0193]

[0194] Starting point number = kilometers + [met...

Embodiment 2

[0199] Example 2 Taking picture 7 as an example, the picture is sent to the deep network model for detection and identification, and the disease: crack is detected.

[0200] According to the image naming rules and the detection and classification results, it can be known that the crack disease information of the image is as follows:

[0201]

[0202] Starting point number = kilometers + [meters / 1000]

[0203] =4523+(0.280)=4523.280

[0204] End point chainage = starting point chainage + [length / 1000]

[0205] =4523.280+(0.0036)≈4523.284

[0206] Length, width, area are calculated by the estimation method that the present invention proposes

[0207] Uplink: A (B stands for downlink)

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 relates to the technical field of computer vision, in particular to a system and a method for automatically identifying cement pavement diseases based on digital images. According to themethod, a deep convolutional neural network model is established, a pavement disease data training set is made and imported into a network model for training, diseases recognized by the model are framed, the actual area of the diseases is estimated, the diseases in the image are detected and recognized, and the area and the length of the road surface diseases in an actual road are calculated. Thedetection precision is improved, the cost is saved, the efficiency is improved, and the method is better in effect compared with a traditional image technology and suitable for road maintenance.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a system and method for automatic identification of cement pavement diseases based on digital images. Background technique [0002] At present, for the maintenance of road diseases, it is necessary to accurately understand the damage of the relevant road sections, and make a maintenance plan according to the type, area, damage degree and damage location of the disease. For maintenance road sections of hundreds of kilometers or even thousands of kilometers, it is necessary to make more accurate investigation and statistics on diseases. At present, manual measurement is mainly used for road surface disease detection, which has low work efficiency, high labor intensity, and the error cannot meet the requirements. The existing pavement maintenance technology is mainly manual, resulting in high maintenance cost, low efficiency and difficult maintenance. At present, the detect...

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
IPC IPC(8): G06T7/00G06T7/80G06T7/62G06K9/62G06N3/08G06N3/04
CPCG06T7/0002G06T7/80G06T7/62G06N3/08G06N3/045G06F18/253
Inventor 李正楷郑屹山
Owner 福建中航赛凡信息科技有限公司