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

An automatic parking space detection method based on Tu neural network

A neural network, automatic parking technology, applied in neural learning methods, biological neural network models, neural architectures, etc., to achieve the effect of reducing costs, high detection accuracy, and low labeling requirements

Active Publication Date: 2021-08-10
NAT INNOVATION INST OF DEFENSE TECH PLA ACAD OF MILITARY SCI
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the technical problem that image-based parking space detection technology adopts multi-stage processing and parking space inspection relies on artificial rule-based reasoning in post-processing

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
  • An automatic parking space detection method based on Tu neural network
  • An automatic parking space detection method based on Tu neural network
  • An automatic parking space detection method based on Tu neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] Such as figure 2Shown, shown in embodiment 1 of the present invention comprises the following steps:

[0047] S1. Install fisheye cameras in four directions: front, rear, left, and right;

[0048] S2. Collect images from fisheye cameras in four directions, front, rear, left, and right of the vehicle, and convert them into a top view centered on the vehicle position. This process is realized through projection transformation and splicing operations of the surround-view images.

[0049] S3. Input the top view into the parking space detection module based on the graph neural network, detect the four corner positions of the parking space in the image, and identify the parking space type;

[0050] S3.1. For each frame of top view, it is first scaled to a standard size of 600x600 pixels.

[0051] S3.2. Input the image data in S3.1 into the image encoder of the parking space detection module based on the graph neural network, and output the image feature F; input the image ...

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 technical field of automatic driving, and specifically provides an automatic parking parking space detection method based on a graph neural network. Install image acquisition equipment in the four directions of the front, rear, left, and right of the vehicle; use the image acquisition equipment to collect images in the four directions of the vehicle, front, rear, left, and right and convert them into a top view centered on the vehicle position; input the top view into the parking space detection module based on the graph neural network, and detect The four corner positions of the parking space in the image, and identify the type of parking space; send the detected parking space information to the planning control module, calculate the parking route and control the vehicle to automatically drive into the detected target parking space to realize automatic parking . The automatic parking space detection method based on the graph neural network of the present invention can obtain the precise location of the parking space only by relying on the image data captured by the surround-view camera. The parking position of the parking vehicle is judged, and the detection accuracy is high.

Description

technical field [0001] The invention belongs to the technical field of automatic driving, and in particular relates to an automatic parking parking space detection method based on a graph neural network. Background technique [0002] Automatic parking based on computer vision is an important application of driverless driving. Compared with manual parking, automatic parking technology has more precise parking path and simpler parking operation, which can reduce scratches and collisions caused by manual operation errors, making the parking process safer and more efficient. [0003] Parking space detection based on ultrasonic radar detection is a mature and widely used technology. Detection based on ultrasonic radar relies on other vehicles around the target parking space. When there are no referenced parking vehicles around the target parking space, the target parking space cannot be effectively identified. Even if there is a reference parked vehicle, the position of the aut...

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): G08G1/14B60W30/06G06K9/62G06N3/04G06N3/08
CPCG08G1/143B60W30/06G06N3/08G06N3/045G06F18/241
Inventor 许娇龙赵大伟肖良闵称
Owner NAT INNOVATION INST OF DEFENSE TECH PLA ACAD OF MILITARY SCI
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