Unlock instant, AI-driven research and patent intelligence for your innovation.

A system and method for detecting traffic lights in automatic driving

A technology of automatic driving and traffic lights, applied in the direction of reasoning methods, instruments, scene recognition, etc., can solve problems such as poor robustness, and achieve the effect of solving poor robustness

Active Publication Date: 2022-07-12
AUTOCORE INTELLIGENT TECH NANJING CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a brand-new traffic light detection method to solve the problem of poor robustness of the traffic light detection method in traditional automatic driving

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 system and method for detecting traffic lights in automatic driving
  • A system and method for detecting traffic lights in automatic driving
  • A system and method for detecting traffic lights in automatic driving

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0022] Considering the poor robustness of traditional traffic light detection methods, there are many parameters that need to be adjusted.

[0023] Therefore, see figure 1 and Figures 3 to 9 , the present invention provides a traffic light detection method in automatic driving, comprising the following steps:

[0024] S1: the map loading module 100 loads the map information, and utilizes the 3d position information of the pre-detection target in the vector map marker space to obtain the coordinates of the pre-detection target under the map coordinate system;

[0025] It should be noted that the 3D information of pre-detection targets has been manually marked in the map (pre-detection targets refer to pedestrians, landmarks, buildings, horse routes, traffic lights and many other targets marked in the map).

[0026] S2: calibrate the relationship between the camera coordinate system of the camera in the perception module 200 relative to the vehicle body coordinate system;

...

Embodiment 2

[0067] see figure 2 and image 3 , in order to solve the problem of poor robustness of traditional detection, the present invention also provides a traffic light detection system in automatic driving, including:

[0068] The map loading module 100 is used to describe the 3D position information of the pre-detected target in the space by establishing a map coordinate system;

[0069] The perception module 200, including a camera and a lidar, is connected to the map loading module 100, and the coordinates of the pre-detected target in the map coordinate system are correspondingly converted into the camera coordinate system coordinates under the camera through the external parameters of the camera and the lidar, and the camera is passed through the camera. The internal parameters of the camera coordinate system coordinates are correspondingly converted into image coordinate system coordinates;

[0070] The positioning module 300 is connected to the map loading module 100 and t...

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 relates to a traffic light detection system and method in automatic driving, comprising: acquiring coordinates of a pre-detection target in a map coordinate system; calibrating the relationship between a camera coordinate system of a camera and a vehicle body coordinate system; acquiring vehicle body attitude information in real time, and calculating The current attitude information of the camera; the position of the traffic light is determined; the color classification is carried out after sending the cropped picture that only contains the traffic light, and the color of the traffic light is obtained; Combined with positioning information and map information, by training the target detection model and classification model for traffic lights, the purpose of identifying the color of traffic lights and the remaining seconds is achieved, and the model is accelerated by an inference engine to achieve real-time processing on embedded devices. It solves the problem of poor robustness of traditional traffic light detection methods.

Description

technical field [0001] The invention relates to a traffic light detection system and method in automatic driving, and belongs to the technical field of intelligent auxiliary driving. Background technique [0002] Automatically detecting the position and status of the traffic lights ahead during driving is an important technology in advanced assisted driving and unmanned driving. Usually, the detection of traffic lights is difficult due to complex traffic scenes, drastic changes in lighting, and camera resolution. [0003] At present, the traditional detection methods for traffic lights process the image through threshold segmentation, morphological transformation and other operations to obtain the object area of ​​interest in the image, and then use specific prior knowledge, such as regional connectivity, aspect ratio, shape , relative position, etc., process these areas, filter layer by layer, and finally get the area where the traffic light is located, and then determine ...

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): G06V20/58G06V10/25G06V10/26G06V10/764G06V10/774G06V10/82G06V10/94G06K9/62G06N5/04
CPCG06N5/04G06V20/584G06V10/94G06V10/25G06V10/267G06V2201/07G06F18/24G06F18/214
Inventor 苏畅周路翔王洪尧张旸陈诚
Owner AUTOCORE INTELLIGENT TECH NANJING CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com