3D vehicle detection method based on key point regression

A technology of vehicle detection and key points, applied in neural learning methods, instruments, biological neural network models, etc., to achieve high efficiency, strong practicability, and easy installation

Pending Publication Date: 2020-05-08
BEIJING UNION UNIVERSITY
View PDF4 Cites 5 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 3D vehicle detection based on monocular vision, and propose a 3D vehicle detection method based on key point regression

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
  • 3D vehicle detection method based on key point regression
  • 3D vehicle detection method based on key point regression
  • 3D vehicle detection method based on key point regression

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0039] 1. Train the model according to step 1, and then detect the test picture to obtain the coordinates (844, 272, 1073, 430) of the target vehicle.

[0040] 2. Intercept the vehicle target according to the instructions in step 2 to obtain the pixel matrix P 0 :

[0041] [[[68 55 69]

[0042] [53 40 54]

[0043] [48 33 47]

[0044] ...,

[0045] [53 41 61]

[0046] [61 49 67]

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 3D vehicle detection method based on key point regression. According to the method, 3D detection can be carried out on a front vehicle target in a driving scene so as to obtain three-dimensional information of a vehicle target; compared with a 2D vehicle target detection technology, the method has the advantages that richer scene information and higher-precision basic data can be provided for an automatic driving vehicle decision-making system, the decision-making system is helped to make more accurate judgment, and the safety of the automatic driving vehicle is improved. Therefore, the method has a wide application prospect. Compared with other 3D vehicle detection methods, the method has the advantages that pixel depth, radar and other data are not needed, onlycommon RGB image information acquired by the monocular vision camera is needed, and the detection result is reliable.

Description

technical field [0001] The invention relates to a method for 3D detection of a vehicle target in a driving scene, which belongs to the field of computer vision calculation. Background technique [0002] Nowadays, driverless car technology is developing rapidly. In terms of environmental perception methods used in car driving, visual sensors can obtain higher, more accurate, and richer road scene environmental information than sensors such as ultrasound and lidar, and the price is lower. for cheap. In vision-based road scene perception and target behavior intention analysis technology, front vehicle detection is a very important link. It is the basic data necessary for the decision-making system. To make a more accurate judgment, it is necessary to perform 3D detection on the vehicle to obtain the 3D information of the target. Therefore, it is particularly important to propose a 3D vehicle detection method. [0003] A 3D vehicle detection method based on key point regressi...

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): G06K9/00G06K9/34G06K9/46G06N3/04G06N3/08
CPCG06N3/08G06V20/584G06V10/267G06V10/462G06V2201/08G06N3/045
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