Monocular vision and license plate number-based vehicle distance measurement method

A measurement method, monocular vision technology, applied in the direction of sight distance measurement, measuring device, measuring distance, etc., can solve the problems of poor real-time performance and accuracy, sensitivity to light, etc., and achieve high accuracy, simple method, and false detection rate small effect

Inactive Publication Date: 2017-06-06
深圳市美好幸福生活安全系统有限公司
View PDF5 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problems of light sensitivity, poor real-time performance and poor accuracy in current vehicle detection and ranging, we propose a robust vehicle distance measurement method using the license plate area to measure the distance between two vehicles

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
  • Monocular vision and license plate number-based vehicle distance measurement method
  • Monocular vision and license plate number-based vehicle distance measurement method
  • Monocular vision and license plate number-based vehicle distance measurement method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The flow chart of the present invention is as figure 1 As shown, firstly, the video image collected by the vehicle camera is converted into an HSV color space image, and then an appropriate color threshold is selected to convert the color image into a binary image, and then filter technology is used to filter out background pixels that have nothing to do with the background color of the license plate. Enhance the pixel information of the license plate part. Finally, the boundary position of the license plate is determined by the projection method, and the license plate is extracted from the original image according to the boundary position, and the license plate extraction part is completed. Linearize the extracted license plate boundary to obtain the vertex coordinates of the license plate area. The internal parameters of the camera are calibrated by using the Tsai two-step algorithm and the checkerboard sum algorithm. Finally, the vehicle distance is measured using t...

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 image processing, and relates to a monocular vision-based front vehicle detection and distance measurement algorithm. According to the method, the vehicle detection and vehicle distance measurement can be conducted by using a method of combining machine vision and prior knowledge and geometric algorithm. The method is realized by comprising the following steps: (1) converting a video image, acquired by a vehicular camera, into a grey image; (2) performing filtering and noise reduction processing to the grey image; (3) positioning and extracting a license plate area by utilizing a projection method, and determining four apexes of the license plate; (4) correcting the interior parameters of the camera by utilizing Tsai two-step algorithm and checkerboard algorithm; and (5) finally, calculating the distance of the front vehicle by utilizing P4P algorithm according to the obtained interior parameter of the camera and the apexes of the license plate. According to the method, the problem of excessive detection errors generated by using a machine vision method alone can be solved, the vehicle distance measurement can be accurately and effectively realized, and the real-time requirement on control of smart vehicles can be met.

Description

technical field [0001] The invention relates to a front vehicle detection and ranging algorithm based on monocular vision. The method proposes a method of combining machine vision with prior knowledge and geometric algorithms for vehicle detection. It belongs to the field of image processing and machine vision and can be applied to Accurate and efficient detection of vehicles in front and accurate measurement of vehicle distance. Background technique [0002] Road traffic accidents have brought huge losses to people's lives and property and the national economy, and traffic accidents are mainly caused by not keeping a safe distance between vehicles. It can be seen that it is very important to timely detect the distance between the current vehicle and the vehicle in front and make an early warning as a part of the advanced driver assistance system. [0003] In terms of machine vision for vehicle detection and tracking, it is mainly divided into two categories: one is based o...

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): G01C3/00
CPCG01C3/00
Inventor 高振国张开岭李树刚陈丹杰姚念民李培华郑延景潘伟
Owner 深圳市美好幸福生活安全系统有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap