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

Car backing obstacle avoidance early warning method and system based on travelable area identification

A driving area and early warning system technology, applied in scene recognition, character and pattern recognition, instruments, etc., can solve the problems of easy missing detection, troublesome data processing, and inaccurate range measurement of ranging models, etc., to achieve a variety of solutions and improve The effect of robustness

Pending Publication Date: 2022-02-18
珠海研果科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method based on obstacle target detection and ranging model has the following disadvantages: First, there are many types of obstacle targets, which are prone to problems such as troublesome data collection, data processing, and easy missed detection; The distance measurement is not accurate enough

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
  • Car backing obstacle avoidance early warning method and system based on travelable area identification
  • Car backing obstacle avoidance early warning method and system based on travelable area identification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] A kind of reversing obstacle avoidance warning method based on drivable area recognition, see figure 1 , including the following steps:

[0041] S1: Collect sample data; the sample data includes various reversing sample images and annotation information; the annotation information includes the drivable area marked in the reversing sample image;

[0042] S2: Train the sample data to obtain a drivable area recognition model;

[0043] S3: Receive the real-time reversing image, and use the drivable area recognition model to identify the drivable area of ​​the reversing image;

[0044] S4: Receive real-time reversing information, and give an early warning based on the reversing information and the driving area.

[0045] In this embodiment, the reversing sample image includes a reversing image captured by an on-vehicle camera installed on the body shell, and the reversing sample image can be obtained by downloading from the network, uploading from a shooting device, or dire...

Embodiment 2

[0062] A reversing obstacle avoidance warning system based on drivable area recognition, see figure 2 , including the following steps:

[0063] Sampling unit 1: used to collect sample data; the sample data includes various reversing sample images and labeling information; the labeling information includes the drivable area marked in the reversing sample image;

[0064] Training unit 2: connected to the sampling unit 1; the training unit 2 is used to train the sample data to obtain a drivable area recognition model;

[0065] Recognition unit 3: connected to the training unit 2; the recognition unit 3 is used to receive the real-time reversing image, and use the drivable area recognition model to identify the drivable area of ​​the reversing image;

[0066] Early warning unit 4: connected to the identification unit 3; the early warning unit 4 is used to receive real-time reversing information, and perform early warning according to the reversing information and the driving are...

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 provides a car backing obstacle avoidance early warning method and system based on travelable area identification. The method comprises the following steps: collecting sample data, wherein the sample data comprises various car backing sample images and annotation information, the annotation information comprises a drivable area annotated in the car backing sample image; training the sample data to obtain a travelable area identification model; receiving a real-time reversing image, and recognizing the travelable area of the reversing image through the travelable area recognition model; and receiving real-time backing-up information, and performing early warning according to the backing-up information and the driving area. According to the method, the obstacle is indirectly recognized by adopting the travelable area recognition and the relation between the travelable area and the position of the to-be-traveled area, the problems that in the prior art, obstacle targets are various in variety, missing detection is prone to occurring, and short-distance ranging is not accurate enough are solved, and the robustness of visual recognition of the vehicle backing obstacle is improved.

Description

technical field [0001] The invention belongs to the technical field of vehicle equipment, and in particular relates to an early warning method and system for reversing and avoiding obstacles based on drivable area recognition. Background technique [0002] The existing vehicle reversing system mainly collects the reversing image, detects the obstacle target in the reversing image, then uses the ranging model to measure the distance of the obstacle target, and finally performs the reversing obstacle avoidance warning according to the distance from the obstacle target. This method based on obstacle target detection and ranging model has the following disadvantages: First, there are many types of obstacle targets, which are prone to problems such as troublesome data collection, data processing, and easy missed detection; The ranging under distance is not accurate enough. Contents of the invention [0003] In view of the defects in the prior art, the present invention provide...

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): G06V20/58G06V10/22G06V10/774G06V10/764G06K9/62B60Q9/00
CPCB60Q9/007G06F18/24G06F18/214
Inventor 谭文胜田池来彦栋
Owner 珠海研果科技有限公司
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