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

Pavement distress disease image classifying method based on principal component analysis and neural network

A principal component analysis and neural network technology, applied in the field of road detection, can solve problems such as time-consuming, high error rate, and inability to meet the needs of road development, and achieve the effect of improving performance, efficiency and accuracy

Inactive Publication Date: 2018-06-22
重庆亲禾智千科技有限公司
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Manual screening often consumes a lot of time and has a high error rate. Traditional manual-based processing methods can no longer meet the needs of road development

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
  • Pavement distress disease image classifying method based on principal component analysis and neural network
  • Pavement distress disease image classifying method based on principal component analysis and neural network
  • Pavement distress disease image classifying method based on principal component analysis and neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0012] combine figure 1 As shown, the basic flow of the method of the present invention is as follows:

[0013] 1. Image preprocessing: The acquisition of the original disease image is generally obtained by shooting the road surface at a normal speed by a vehicle-mounted high-speed camera. Due to the problems of light, camera imaging, and the strength of the disease, it is quite difficult to directly extract the target from the original image. Therefore, it is generally necessary to do appropriate preprocessing first to eliminate the adverse effects caused by low quality, and enhance the target and other information to facilitate Extraction of disease targets.

[0014] The size of each image in the original disease image set A is normalized, and the normalized disease image set B is obtained:

[0015] Let the pixel value of each pixel in image set A be I(x, y), and the pixel value of each pixel in image set B after normalization is:

[0016] G(x,y)=I(x,y) / max(I)

[0017] N...

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 belongs to the technical field of road detection, and aims to provide a high-efficiency and high-accuracy pavement distress disease image classifying method based on principal componentanalysis and a neural network. Traditional road disease image classification is carried out through an artificial screening mode, consumed time is long, and the error rate is high. By a principal component analysis algorithm and a neural network algorithm, classification of road disease images is realized, original disease images are subjected to size normalization processing, feature vector dimensions of different images are consistent, then principal component analysis features are extracted from image data subjected to normalization processing, dimensions of image data are greatly reduced,then the improved neural network based on a genetic algorithm is established, feature main components with high importance degree are trained, finally, network classification is carried out, a resultis output, and therefore, recognition of the road disease images is finished. The efficiency and accuracy of road disease image screening are improved effectively, and the method is simple, convenientand easy to implement.

Description

technical field [0001] The invention relates to the technical field of road detection, in particular to a method for classifying road damage and disease images based on principal component analysis and neural network. Background technique [0002] With the vigorous development of my country's highway transportation construction, as of the end of 2016, my country's total highway mileage was 4.6963 million kilometers, and highway maintenance mileage was 4.59 million kilometers, accounting for 97.7% of the total highway mileage (Data source: "2016 Statistical Bulletin on the Development of the Transportation Industry" ). Due to the influence of geology, weather and construction, various problems will occur in the use of highways, such as road damage, road collapse, water and electricity pipeline bursts, etc., and with the increase of highway mileage, the difficulty of highway maintenance management also increased. At present, the maintenance of highways usually adopts a very t...

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): G06K9/62G06N3/08
CPCG06N3/086G06F18/2135G06F18/24
Inventor 阎旭袁杨宇张荣华林远江
Owner 重庆亲禾智千科技有限公司