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

An Optimization Method of Traffic Sign Bounding Box

A technology of traffic signs and optimization methods, applied in the field of computer vision, can solve the problems of inaccurate bounding boxes of traffic signs and reduced accuracy of traffic sign recognition.

Active Publication Date: 2019-06-18
TSINGHUA UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In some current traffic sign detection methods (such as cascade classifiers), the obtained traffic sign bounding boxes are usually not accurate enough, resulting in a decrease in the accuracy of traffic sign recognition

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 Optimization Method of Traffic Sign Bounding Box
  • An Optimization Method of Traffic Sign Bounding Box
  • An Optimization Method of Traffic Sign Bounding Box

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] The specific embodiments of the present invention will be described in further detail below in conjunction with the drawings and embodiments. The following examples are used to illustrate the present invention, but not to limit the scope of the present invention.

[0015] In order to overcome the problems of low accuracy of traffic sign bounding boxes and low accuracy of recognized traffic sign recognition in existing traffic sign detection (for example, cascaded classifiers), the present invention provides to classify pixels in the bounding box to obtain For the initial shape, the deformation parameters are obtained based on the initial shape, and the energy function is continuously optimized based on the shape and deformation parameters, and finally an optimized bounding box is obtained.

[0016] figure 1 The flow chart of the method for optimizing the bounding box of traffic signs in the present invention is shown. As shown in the figure, the method includes:

[0017] S1. ...

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 present invention provides a method for optimizing a bounding box of a traffic sign, comprising: S1, initially marking each pixel in the original bounding box to obtain the initial shape of the traffic sign; S2, based on the initial shape and The standard shape of the traffic sign, obtaining initial deformation parameters; S3, optimizing the energy function based on the initial shape and deformation parameters, obtaining better shape and deformation parameters; and S4, based on the more optimal shape and deformation parameters, Multiple iterative operations are performed on the energy function to obtain an optimized bounding box. The traffic sign bounding box obtained by the present invention is more accurate, and the traffic sign recognition accuracy rate is higher than that of the prior art.

Description

Technical field [0001] The present invention relates to the field of computer vision, and more specifically, to a method for optimizing traffic sign bounding boxes. Background technique [0002] Modern transportation is highly developed, road conditions are becoming more and more complex, and traffic safety and other issues are becoming more and more important. Intelligent transportation systems can effectively alleviate traffic jams and reduce traffic accidents. [0003] Traffic signs are graphic symbols that display traffic laws and road information. They are used to manage traffic and indicate the direction of driving to ensure smooth roads and safe driving. In intelligent transportation systems, traffic sign recognition is a very important part. Traffic sign recognition technology can prompt or warn drivers, so as to achieve the purpose of alleviating traffic congestion and reducing traffic accidents. [0004] In traffic sign recognition, compared with large-size road images, ...

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): G06K9/00G06K9/32G06K9/46
CPCG06V20/582G06V20/62G06V10/44G06V2201/09
Inventor 胡事民朱哲卢嘉铭
Owner TSINGHUA UNIV