Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Road target detection and association method based on millimeter wave radar and vision

A millimeter wave radar, radar target technology, applied in radio wave measurement systems, radio wave reflection/re-radiation, measurement devices and other directions, can solve the problems of low robustness, low robustness, poor detection effect, etc. , to achieve the effect of improving detection accuracy, improving matching accuracy, and fast regression

Pending Publication Date: 2022-03-18
HEFEI UNIV OF TECH +1
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problems of low accuracy and weak robustness existing in the prior art, the present invention provides a road target detection and association method based on millimeter-wave radar and vision, in order to obtain more abundant target information and improve the Correlation accuracy between wave radar detection target and visual detection target, so as to solve the problem of poor detection effect and low robustness of single sensor perception

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 target detection and association method based on millimeter wave radar and vision
  • Road target detection and association method based on millimeter wave radar and vision
  • Road target detection and association method based on millimeter wave radar and vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] In this example, if figure 1 As shown, a target detection and association method based on millimeter-wave radar and vision includes the following steps:

[0039] A. Install the millimeter-wave radar at the front of the car, take the millimeter-wave radar as the origin O, take the front of the vehicle as the X-axis, take the driver's left side as the Y-axis, and take the vehicle directly above as the Z-axis to establish an O-XYZ coordinate system , and the O-XY plane is parallel to the ground, the camera is installed on the roof, and its installation height is Z v , the lens of the camera is perpendicular to the O-XZ plane and horizontal to the O-YZ plane;

[0040] B. Use the Zhang Zhengyou calibration method to calibrate the internal parameters of the camera to obtain the internal parameter matrix M 1 , and the extrinsic parameter matrix M between the camera and the radar is obtained by measurement 2 ;

[0041] C. Improve the YOLOv3 network and perform network train...

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 target detection and association method based on millimeter-wave radar and vision. The method comprises the following steps: 1, installing the millimeter-wave radar and a camera on a vehicle; 2, constructing an improved YOLOv3 network which comprises a main body network and three feature prediction layers, and constructing a loss function and training the network based on DIOU so as to obtain a trained visual detection model; 3, configuring parameters of the millimeter-wave radar, acquiring CAN signals by using the configured millimeter-wave radar, processing the CAN signals, outputting preset frames with different target preset lengths and widths for the millimeter-wave radar, and projecting the preset frames back to a pixel coordinate system; and 4, calculating cost values of the radar target preset frame and the visual target frame through a DIOU-based cost calculation method, and setting a reasonable threshold value for optimization solution through a Hungary algorithm to obtain a global optimal matching result. According to the method, the correlation precision of the millimeter wave radar detection target and the visual detection target can be improved, so that richer target information can be obtained.

Description

technical field [0001] The invention relates to the field of vehicle intelligent detection equipment, in particular to a road target detection and association method based on millimeter wave radar and vision. Background technique [0002] At present, smart cars are equipped with various advanced sensors and communication devices, using deep learning, 5G technology, positioning technology, etc., for safer and more comfortable driving for passengers, and finally realize true driverless driving. [0003] Lidar is expensive, has high resolution, good imaging effect, accurate ranging, and can clearly obtain the size and outline of the target. in different weather conditions. However, its resolution is low, the target classification ability is poor, and it is difficult to obtain the target size and complete outline; the camera is not expensive, and the obtained image information is rich. With the popularity of deep learning, the effect of using the camera for target detection is ...

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): G01S13/86G01S7/41
CPCG01S13/867G01S7/418Y02T10/40
Inventor 张炳力刘文涛姜俊昭潘泽昊张成标徐雨强王怿昕
Owner HEFEI UNIV OF TECH
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
Eureka Blog
Learn More
PatSnap group products