Image-based Taillight Detection and Recognition Method

An identification method and taillight technology, applied in the field of image processing, can solve the problem of low detection accuracy of taillights, and achieve the effects of reducing judgment dependence and training complexity, efficient and accurate classification, and accurate detection and segmentation.

Active Publication Date: 2019-10-15
TAIYUAN UNIV OF TECH
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem of low taillight detection accuracy caused by the excessive dependence of the existing taillight detection method on a single color space, and to make up for the vacancy of the existing method in the direction of taillight state recognition, the present invention proposes an image-based taillight detection and identification method

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
  • Image-based Taillight Detection and Recognition Method
  • Image-based Taillight Detection and Recognition Method
  • Image-based Taillight Detection and Recognition Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0044] An image-based taillight detection and recognition method, such as figure 1 The method flow chart includes the following steps:

[0045] Step S1: Perform image preprocessing on the input image, and use the gradient sharpening method to enhance the contrast of the original image. The gradient sharpening uses the Laplacian sharpening method, and the Laplacian kernel used is:

[0046]

[0047] And cut the original image, and take the lower 4 / 5 part of the original image as the actual detection area of ​​the tail light; Figure 2a To input the original image, Figure 2b It is the image to be detected after sharpening and cutting.

[0048] Step S2: Obtain the taillight area based on color feature segmentation, and adopt a multi-color space information feature interaction method. The specific steps are as follows:

[0049] Step S21). The color 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 discloses an image-based taillight detection and recognition method. The method utilizes the real-time image of the front vehicle collected by an ordinary camera, performs preprocessing through gradient sharpening and image clipping, and performs self-adaptation in combination with HSI and RGB color spaces. Threshold segmentation extracts the color information of taillights; extracts contours and uses geometric conditions to constrain the same group of taillights through filtering denoising and morphological transformation; based on SVM, the state information is processed hierarchically, and the semantic interpretation of the front car taillight image is output. As an important part of the vehicle-mounted advanced driving assistance system, the present invention has better processing effects and real-time processing capabilities for the detection of front and rear lights and state information judgment in complex urban environments.

Description

Technical field [0001] The invention belongs to the field of image processing, and specifically relates to an image-based tail light detection and recognition method. Background technique [0002] Road traffic safety is a global issue. How to use intelligent driving assistance systems to help drivers avoid safety risks has become a hot topic now. Intelligent driving assistance systems focus on a comprehensive perception of the surrounding driving environment, such as providing the driver with information about roads, surrounding vehicles, traffic signs, etc., so as to help the driver have a safe plan for the car's driving route. At present, relevant researches mostly focus on road detection, traffic light recognition, pedestrian detection and obstacle recognition, but there are few studies on the impact of surrounding vehicles on the driving state of the vehicle. The taillight information of the preceding vehicle, the light language, is an important means of expressing the route...

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): G06K9/00G06K9/34G06K9/46G06K9/62
CPCG06V20/584G06V10/267G06V10/56G06V2201/08G06F18/2411
Inventor 谢刚续欣莹谢新林白博郭磊
Owner TAIYUAN UNIV OF TECH
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