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

Expressway night license plate anti-dazzling snapshot method based on deep learning algorithm

A technology of deep learning and expressways, applied to devices using optical methods, calculations, computer components, etc., can solve the problems of driver's eye glare, high fill light brightness, and inability to see the road ahead, etc., to improve driving Safety, the effect of improving road traffic safety

Active Publication Date: 2021-10-26
成都格林希尔德交通科技有限公司
View PDF10 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] Due to the need to collect vehicle characteristic information and passing records, multiple ETC gantry frames are set up along the highway, and a large number of intelligent monitoring and recording equipment are installed on them. In order to clearly record and identify vehicle license plates at night, the supplementary light on the gantry frames The number of lights increases correspondingly, but in order to take clear pictures, the brightness of the supplementary light is often higher. Many drivers report that the brightness of the supplementary light is too high, especially when driving head-on, the time for the supplementary light to shine on the driver's eyes is about In about 1-2 seconds, this will temporarily dazzle the driver's eyes and make it impossible to see the road ahead;

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
  • Expressway night license plate anti-dazzling snapshot method based on deep learning algorithm
  • Expressway night license plate anti-dazzling snapshot method based on deep learning algorithm
  • Expressway night license plate anti-dazzling snapshot method based on deep learning algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0052] Anti-glare capture method of license plate at night based on deep learning algorithm, such as Figure 10 As shown, the snapping device 1 used in the snapping method is installed on the gantry 2; the gantry 2 is fixedly erected at the corresponding position along the expressway road 3; the snapping device 1 includes a fixed angle mounted on the gantry 2, and the reciprocating swing mechanism 20 that can swing back and forth within a certain angle; the camera assembly 10 includes a speed measuring camera 11 and a license plate recognition camera 12; the installation angles of the speed measuring camera 11 and the license plate recognition camera 12 can be the same or different; the reciprocating swing mechanism 20 is a crank rocker mechanism, the crank is connected to the drive motor, and the rocker is fixedly connected to the fill light 30 through bolts or buckles, so that the fill light 30 can follow the rocker within a certain angle. Reciprocating swing; the supplement...

Embodiment 2

[0070] In order to improve the speed at which the processor 50 processes images and further improve the longitude of car light recognition, a better implementation is: in the step b, the processor 50 first performs a preprocessing step on the photo image, and the preprocessing The steps include a Gamma correction step, a grayscale image step, a Gaussian blur step, and a ROI clipping step;

[0071] like Figure 5As shown, in the step of graying the picture, usually, the color of the light source of the car lights at night in the captured photo image is a white or yellow ring-shaped area, which is obviously different from the background of the road surface and other vehicles in the image. , in order to maintain the balance of the R, G, and B channels, the gray value is defined as:

[0072]

[0073] In the above formula, I is the gray value, and R, G, and B are the RGB brightness values ​​of each pixel in the picture;

[0074] Gaussian blur, also called Gaussian smoothing, i...

Embodiment 3

[0078] When using a speed measuring camera 11 to take pictures, it is impossible to distinguish the high and low beams of the vehicle. In some dangerous road conditions, when the gantry is required to further record the state of the vehicle's headlights, or when encountering a steep road section, it is difficult to identify the low beam. In view of the above situation, a better implementation is: the camera assembly 10 includes two speed cameras 11 with different installation heights and installation angles, one speed camera 11 has a low installation height and a small angle with respect to the horizontal plane , used to identify low beam lights, another speed camera 11 is installed at a high height and has a relatively large angle with respect to the horizontal plane; at least two photoelectric sensors 51 with different heights are arranged on the column of the gantry 2, and the signal of the photoelectric sensor 51 Line is connected with the signal input terminal of processor...

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 field of expressway safe driving and vehicle-road cooperation intelligent devices, and particularly relates to an expressway night license plate anti-dazzling snapshot method based on a deep learning algorithm. The method comprises the steps of arranging a speed measurement camera, and enabling the speed measurement camera to recognize the position of a night vehicle headlamp in real time so as to control a light supplement lamp to swing along with the movement of a vehicle, so that it is guaranteed that the irradiation range of the light supplementing lamp is always located below the front windshield of the vehicle and above a license plate area, namely it is guaranteed that the license plate identification camera normally identifies the license plate. Meanwhile, the light supplementing lamp is prevented from directly irradiating the eyes of a driver, so that the road traffic safety of an expressway is greatly improved. According to the method, especially for different types of vehicles, the light supplementing lamp can be accurately controlled, so that the driving safety of the vehicles is improved.

Description

technical field [0001] The invention belongs to the technical field of expressway safe driving and monitoring, and in particular relates to an anti-glare capture method for expressway license plates at night based on a deep learning algorithm. Background technique [0002] Due to the need to collect vehicle characteristic information and passing records, multiple ETC gantry frames are set up along the highway, and a large number of intelligent monitoring and recording equipment are installed on them. In order to clearly record and identify vehicle license plates at night, the supplementary light on the gantry frames The number of lights increases correspondingly, but in order to take clear pictures, the brightness of the supplementary light is often higher. Many drivers report that the brightness of the supplementary light is too high, especially when driving head-on, the time for the supplementary light to shine on the driver's eyes is about In about 1-2 seconds, this will ...

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): G06K9/00G06K9/20G06N3/04G01P3/38
CPCG01P3/38G06N3/045
Inventor 肖丰陈子龙廖文俊李平飞谭金慧
Owner 成都格林希尔德交通科技有限公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com