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

Automobile taillight state recognition method

A technology of state recognition and automobile taillights, which is applied in the field of computer vision and assisted driving, can solve the problems that the recognition accuracy depends on the detection accuracy of taillights, and the recognition results are not smooth enough in time sequence, so as to achieve the effect of superior performance and generalization ability

Pending Publication Date: 2020-11-03
ANHUI TSINGLINK INFORMATION TECH
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in practical applications, the recognition accuracy of this type of method depends on the detection accuracy of taillights, and is affected by the image resolution of taillights caused by the distance between vehicles, so the recognition results are not smooth enough in timing

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
  • Automobile taillight state recognition method
  • Automobile taillight state recognition method
  • Automobile taillight state recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043]To further illustrate the features of the present invention, please refer to the following detailed description and accompanying drawings of the present invention. The attached drawings are for reference and description only, and are not intended to limit the protection scope of the present invention.

[0044] like figure 1 As shown, this embodiment discloses a method for recognizing the state of an automobile taillight, including the following steps S1 to S3:

[0045] S1. Acquire a vehicle rear image to be identified, and input it into a pre-trained taillight state recognition model, where the taillight state recognition model includes a feature extraction network and a taillight state discrimination network;

[0046] S2, using the feature extraction network to extract the taillight feature vector of the rear image of the vehicle;

[0047] S3, using the tail light state discrimination network to process the tail light feature vector to identify the state of the automo...

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 an automobile taillight state recognition method, which belongs to the technical field of computer vision and aided driving, and comprises the following steps: acquiring a to-be-recognized automobile tail image, and inputting the to-be-recognized automobile tail image into a pre-trained taillight state recognition model which comprises a feature extraction network and a taillight state discrimination network; utilizing a feature extraction network to extract a taillight feature vector of the taillight image; and processing the taillight feature vector by using a taillight state discrimination network, and identifying the state of the automobile taillight. According to the method, the attention mechanism-based convolutional recurrent neural network is designed to directly extract the taillight features from the taillight image, and the brightness change of the taillight before and after the moment is reasoned, so that the state of the automobile taillight in a complex environment can be stably and effectively identified.

Description

technical field [0001] The invention relates to the technical field of computer vision and assisted driving, in particular to a method for recognizing the state of an automobile taillight. Background technique [0002] The taillight status is the main basis for the driver to judge the driving intention of the vehicle ahead. When driving in the daytime, the driver may not be able to effectively receive the warning information from the taillights of the vehicle ahead due to factors such as inattention, sight distance, and light intensity, resulting in untimely driving predictions and traffic safety problems. Therefore, fast and effective vehicle taillight status recognition is an urgent problem to be solved in the field of assisted driving. [0003] Vision-based vehicle taillight status recognition is mainly to identify the type and lighting state of the taillights by analyzing the image data including the taillights, so as to predict the driving intention of the vehicle ahea...

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): G06K9/00G06N3/04G06N3/08G06K9/46G06K9/62
CPCG06N3/08G06V20/584G06V10/40G06N3/045G06F18/24G06F18/214
Inventor 戴亮亮张卡何佳尼秀明
Owner ANHUI TSINGLINK INFORMATION TECH
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