Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for splicing and homogenizing road face images collected by double-linear-array cameras under linear laser illumination condition

A technology of line lasers and lighting conditions, applied in instruments, computer parts, calculations, etc., can solve the problems of high risk, affecting disease identification, low accuracy, etc., achieving good homogenization effect, good robustness, real-time strong effect

Active Publication Date: 2014-04-09
NANJING UNIV OF SCI & TECH
View PDF2 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The commonly used detection method in the past is to use artificial visual observation, which is inefficient, affects traffic, and is highly dangerous, and there are large subjective differences in the detection results, and the accuracy is not high. At present, with the expansion of the road network, the manual method can no longer meet the requirements. ; Therefore, the automatic detection method of road surface defects based on digital images has been widely studied and used to overcome the above defects. A series of intelligent and efficient road detection equipment makes it possible to obtain road information on a large scale, quickly and accurately. The detection equipment generally consists of Composed of proprietary vehicles and on-board sensors, the software generally consists of a road surface image acquisition module and a later-stage disease identification and processing module, which can complete the detection of the road without affecting normal traffic, and grasp the road conditions in a timely and accurate manner. Provides an important basis for formulating conservation measures
[0004] Road surface image acquisition is the premise of later disease identification processing, and the quality of the collected images also directly affects the accuracy and effect of identification; currently, road surface image acquisition generally adopts dual line array cameras with line laser lighting, because the standard lane width is 3.75m, requiring one The detection can cover the entire lane, and the dual-camera method can reduce the deformation of the image and improve the detection accuracy of the disease. Generally, it is difficult for the scanning lines of two line-scan cameras to overlap accurately, so the direct splicing of the scanned images will cause the left and right images to have a sense of misalignment. And generally there are some overlapping images in the middle, how to quickly and automatically complete the automatic registration of the two images and accurately stitch them together is one of the problems that need to be solved; in addition, due to the inhomogeneity of the current line laser (compared with natural light) , so that the image captured by the camera has a large number of light and dark stripes, resulting in poor visual effect of the image, which will also seriously affect the later disease identification. How to effectively eliminate such light and dark stripes is another problem that needs to be solved

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
  • Method for splicing and homogenizing road face images collected by double-linear-array cameras under linear laser illumination condition
  • Method for splicing and homogenizing road face images collected by double-linear-array cameras under linear laser illumination condition
  • Method for splicing and homogenizing road face images collected by double-linear-array cameras under linear laser illumination condition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0041] combine Figure 1 to Figure 4 , the present invention is a method for mosaicing and homogenizing pavement images collected by dual line array cameras under the illumination of line lasers, which mainly includes installing a line scan camera and a line laser at the rear of the vehicle, image mosaicing, detecting lane lines and traffic markings, Grayscale correction (homogenization), image enhancement and other processes are performed on lane lines and non-traffic marking areas. Firstly, the road surface image is collected by the dual-line scan camera installed at the rear of the vehicle; secondly, the images are spliced ​​so that the images collected by the left and right line-scan cameras are merged into one image; again, the lane lines and traffic markings are detected on the image, this step The purpose is to eliminate the influence of lane lines an...

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 method for splicing and homogenizing road face images collected by double-linear-array cameras under the linear laser illumination condition. Two linear-scanning cameras are mounted on the top of the tail of a vehicle, a linear laser is used for illumination, a mileage sensor is used for triggering the cameras to shoot road face images, images obtained by the two cameras are spliced to form one image, lane line and running mark detection is carried out on the image, image gamma correction, namely homogenizing, is carried out on non-lane-line and non-running-mark areas in the image, and image intensification is carried out finally. The real time performance of the method can meet the requirement for real-time collection and real-time homogenizing, interference on image homogenizing of lane lines and running marks can be omitted in the homogenizing effect, and the robustness can be adaptive to images of various road faces like expressways, provincial level roads and municipal roads.

Description

technical field [0001] The invention relates to the field of image acquisition under line laser lighting conditions, and is a double-camera acquisition image splicing method and an image homogenization method under line laser lighting conditions, especially a road pavement image homogenization method, which is especially widely used in highways and provincial Various road surface disease detection fields such as highways and municipal roads. Background technique [0002] With the increase of highway mileage in our country, the supporting highway maintenance management has also become a complex system engineering, especially the maintenance task of highway, which has become one of the key factors to ensure its normal operation; If it is discovered and repaired, the maintenance cost of the road surface will be greatly reduced, and it will also provide a reliable guarantee for safe driving; how to conduct a comprehensive inspection and positioning of the entire road surface saf...

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): G06K9/60G06K9/62
Inventor 吕建勇唐振民张涛
Owner NANJING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products