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

Road surface disease homologous multi-feature image acquisition system, device and method

An image acquisition, multi-feature technology, applied in image enhancement, image analysis, image data processing and other directions, can solve the problems of low reconstruction accuracy, poor stability and high equipment cost of road 3D model

Active Publication Date: 2021-02-02
CHANGAN UNIV
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the shortcomings of the above-mentioned prior art, and provide a system, device and method for acquiring multi-feature images of road surface diseases, so as to solve the problems of high equipment cost, low reconstruction accuracy and poor stability of the road surface three-dimensional model in the prior art. technical problem

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
  • Road surface disease homologous multi-feature image acquisition system, device and method
  • Road surface disease homologous multi-feature image acquisition system, device and method
  • Road surface disease homologous multi-feature image acquisition system, device and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0130] refer to figure 1 and figure 2 A homologous multi-feature image acquisition device for road surface diseases based on stereoscopic imaging includes a camera system and an electronic control system; the camera system is connected to the rear of the vehicle by a fixed buckle 1, an upper cross bar 3 and a lower cross bar 7; the fixed card The buckle 1 is inserted into the top seam of the rear of the car, and is connected with the upper cross bar 3 through the fixing bandage 2; the upper cross bar 3 is in contact with the upper part of the rear of the car, and the contact pressure is increased by tightening the fixing bandage 2, and the middle part of the upper cross bar 3 is fixed There are two main longitudinal rods 4 with upper hinges 10; the lower cross rod 7 is placed at the protruding position at the lower part of the rear of the vehicle, and the lower cross rod 7 is adsorbed to the vehicle through a built-in magnetic block to enhance stability, and the middle part o...

Embodiment 3

[0133] On the basis of embodiment 2, refer to Figure 4 , set the camera frame parameters, and determine the image acquisition range and precision. Three 12-megapixel cameras 13 are used, fixed on the camera fixing bar 11 by sliding the camera bracket 12, the distance between the cameras 13 is set to 0.6m, and the camera fixing bar 11 is adjusted to be 0.8 meters away from the ground. Under this setting, a single captured image can cover 1×2.5=2.5m 2 The minimum resolution distance on the image is 0.27mm / pixel.

[0134] refer to Figure 5 , to set the shooting parameters of the camera, and to determine the image acquisition speed and positional relationship. The preset detection vehicle running speed is 20km / h, and the shooting frame rate of the camera 13 is set to 10 pictures / second. Then at the first moment, the first camera 13 takes an image 1-1, the second camera 13 takes an image 1-2, and the third camera 13 takes an image 1-3, and there are 75 % coincidence rate; at...

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 road surface disease homologous multi-feature image acquisition system, device and method, and the method comprises the steps of collecting all road surface images photographed by k cameras at t moments at fixed time intervals, and obtaining a three-dimensional point cloud model of a road surface photographed by the k cameras at the t moments; obtaining a depth image, a color image and an overlapped image of the road surface through the three-dimensional point cloud model of the pavement, and obtaining a road surface disease homologous multi-feature image; according to the method, a point cloud model is calibrated, so that a generated image is an orthographic image and is not influenced by a shooting angle and a shooting position; the method generates homologous multi-feature images including a three-dimensional depth image, a two-dimensional color image and a superimposed image, and the images have a complete superposition characteristic, so that the deep learning efficiency is improved.

Description

【Technical field】 [0001] The invention relates to the field of road surface disease detection, in particular to a system, device and method for acquiring homologous multi-feature images of road surface diseases. 【Background technique】 [0002] As of the end of 2019, the total mileage of national highways has reached 5.01 million kilometers, of which 4.95 million kilometers are road maintenance mileage. With the rapid growth of road infrastructure scale, the demand for road surface disease detection and maintenance is becoming more and more urgent. At present, the best method for automatic detection of pavement defects is to use deep learning, and deep learning is a data-driven method that requires self-learning through a large number of image samples. Usually, in pavement disease recognition, the images used in deep learning are generally two-dimensional color images, and a small number of scholars use three-dimensional depth images for learning and recognition. [0003] A...

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 Applications(China)
IPC IPC(8): G06T7/70G06T7/50G06T7/11G06T7/80G06T17/00G06K9/62G06F17/16
CPCG06T7/70G06T7/50G06T7/11G06T7/85G06T17/00G06F17/16G06T2207/10028G06V10/757
Inventor 杨旭管进超丁玲汪海年刘经纬
Owner CHANGAN UNIV