A method of accurate target ranging based on monocular vision

A distance measurement method and monocular vision technology, applied to measuring devices, radio wave measurement systems, instruments, etc., to achieve the effect of low cost, strong robustness, and simple hardware environment

Inactive Publication Date: 2021-07-09
BEIJING UNION UNIVERSITY
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem of using visual calculation to measure the distance of the target in the image, and propose a method for precise distance measurement of the target based on monocular vision

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
  • A method of accurate target ranging based on monocular vision
  • A method of accurate target ranging based on monocular vision
  • A method of accurate target ranging based on monocular vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0042] 1. Carry out camera calibration for the camera used according to step 1, and obtain the internal parameter matrix of the camera:

[0043]

[0044] Extrinsic parameter matrix:

[0045]

[0046] 2. According to the instructions in step 2, select the key points of the distance measurement of the target in the image, such as Figure 5 As shown in , get the pixel coordinates of the ranging key point (390,488);

[0047]3. According to the ranging process in step 3, measure the distance of the selected target key points to obtain the measured value D 1 =(16.761826,3.163548),D 2 =(18.503681,3.618550) (unit: meter);

[0048] 4. According to step 4, error correction is performed on the two distance values ​​obtained, and the final corrected target measurement value D=(17.284383,3.300049) (unit: meter) is output;

[0049] 5. The comparison between the measured value and the true value is as follows: (unit: meter)

[0050] direction Measurements true value ...

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

A method for precise target ranging based on monocular vision belongs to the field of computer vision computing, and is mainly used in the target ranging technology of vehicles ahead in intelligent driving scene perception. The method is mainly divided into four parts: camera calibration, key point selection of target ranging, target ranging, and error correction. By selecting appropriate ranging key points, combining multiple ranging algorithms and correcting ranging errors, the precise distance of the target is finally obtained. This method can be applied in many industries based on visual computing, such as distance measurement of vehicles in front of unmanned vehicles, urban traffic vehicle detection and behavioral intention analysis, intelligent robot target distance measurement and other applications. This method is more accurate than other visual ranging methods.

Description

Technical field: [0001] The invention relates to a method for precise distance measurement of a target in an image, which belongs to the field of computer vision calculation. Background technique: [0002] With the rapid development of artificial intelligence technology, the combination of traditional automobile industry and information technology has made great progress in the research of automobile intelligent driving technology. Many large companies have invested heavily in research and development in this field, such as foreign Google, Toyota, Domestic Baidu, BYD and other companies have launched smart driving cars, and the experimental results are satisfactory. Visual computing mainly uses computers to simulate human visual functions, that is, to extract, process and understand the image information of objective things, and finally use it for actual detection, measurement and control. Vision is an important functional means for human beings to observe and understand th...

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 Patents(China)
IPC IPC(8): G01S11/12
CPCG01S11/12
Inventor 刘宏哲王永森
Owner BEIJING UNION UNIVERSITY
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