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

Pavement disease three-dimensional reconstruction method based on deep learning

A deep learning and disease technology, which is applied in the field of 3D reconstruction of pavement diseases based on deep learning, can solve problems such as blockage and disconnection, and achieve the effects of small calculation amount, fast calculation speed and low equipment cost.

Inactive Publication Date: 2021-05-14
HEBEI UNIV OF TECH
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the deficiencies of the existing technology, the technical problem to be solved by the present invention is to avoid traffic jams and disconnections on the road during the collection of road surface disease information, build a road surface disease database, and use deep learning to perform three-dimensional reconstruction of road surface diseases and extract disease features

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 disease three-dimensional reconstruction method based on deep learning
  • Pavement disease three-dimensional reconstruction method based on deep learning
  • Pavement disease three-dimensional reconstruction method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] Specific examples of the present invention are given below. The specific embodiments are only used to further describe the present invention in detail, and do not limit the protection scope of the present application.

[0024] The present invention provides the use of DJI Phantom 4RTK UAV. The camera parameters carried are: lens FOV84°; 8.8mm / 24mm (equivalent to 35mm format); aperture f / 2.8-f / 11; -∞), ISO range video: 100-3200 (automatic), 100-6400 (manual); image resolution is 4864×3648 (4:3); 5472×3648 (3:2), the effective frame size of the photo is 5472×3648. The maximum flight speed is 58KM / h, DNSS positioning accuracy: multi-frequency multi-system high-precision RTKGNSS vertical 1.5cm+1ppm (RMS); horizontal 1cm+1ppm (RMS). This type of UAV can use the carrier phase difference technology (RTK) to connect to the network, and it does not need to measure the phase control point, and the operation is simple. The mapping accuracy meets GB / T 7930-20081:500 topographic ...

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 a pavement disease three-dimensional reconstruction method based on deep learning. The method comprises the steps of: carrying out oblique photographing on a pavement through employing an unmanned aerial vehicle; obtaining a plurality of images in different directions; constructing a standardized pavement disease database through a large number of pavement disease maps which are collected at different angles and are of different types; and realizing three-dimensional reconstruction of pavement diseases through the deep learning method; and carrying out morphological feature extraction on the reconstructed diseases. The three-dimensional model of the diseases is obtained through continuous comparison and correction with the CAD model, the morphological characteristics of the diseases can be accurately extracted, and the accuracy can reach 1.4 mm.

Description

technical field [0001] The invention relates to the field of artificial intelligence and three-dimensional reconstruction of road surface diseases, in particular to a method for three-dimensional reconstruction of road surface diseases based on deep learning. Background technique [0002] As of the end of 2019, my country's total highway mileage was 5.013 million kilometers, ranking first in the world. After the road is completed and put into use, due to the influence of vehicle load, climate and other factors, many road surface diseases such as cracks, ruts, subsidence, potholes, wave wrapping, looseness, etc. will appear after a period of time. If not handled in time, it will affect the quality of the road. Normal service life. Therefore, the three-dimensional reconstruction of pavement damage is particularly important for pavement maintenance and repair decisions. [0003] The current 3D road surface reconstruction method mainly relies on detection vehicles equipped wit...

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): G06F30/13G06F30/27G06K9/34G06K9/46G06K9/62G06N3/04G06N3/08G06T7/11G06T17/00
CPCG06F30/13G06F30/27G06T17/00G06T7/11G06N3/08G06T2207/20081G06V10/267G06V10/44G06N3/045G06F18/23213G06F18/241
Inventor 李家乐刘涛王雪菲马国伟
Owner HEBEI UNIV OF TECH