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

Fine identification method for various targets and elements in traffic scene based on segmentation technology

A technology for fine recognition of traffic scenes, applied in the field of traffic scenes, can solve problems such as poor recognition effect, achieve the effect of improving recognition accuracy and recognition effect

Active Publication Date: 2022-08-05
GUANGDONG FEIDA TRAFFIC ENG CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, it is often necessary to identify various objects and elements in traffic scenes, but the current recognition methods generally have the problem of poor recognition effect

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
  • Fine identification method for various targets and elements in traffic scene based on segmentation technology
  • Fine identification method for various targets and elements in traffic scene based on segmentation technology
  • Fine identification method for various targets and elements in traffic scene based on segmentation technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] In order to make the objectives, technical solutions and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below.

[0049] The present invention provides a method for finely identifying various targets and elements in a traffic scene based on segmentation technology, including the following specific steps:

[0050] S1, acquire an image of the traffic scene, and randomly select a point A in the image of the traffic scene;

[0051] S2, take point A as the origin, send out a ray, and extend the ray in the opposite direction, thereby dividing the image of the traffic scene into two groups of areas;

[0052] S3, initialize a threshold T, usually take the average gray value of each area;

[0053] S4, and obtain the probability that the threshold value T occupies in the region by calculating the gray value i;

[0054] The calculation steps are as follows:

[0055] Step 1: Calculate the sum N of the numb...

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 belongs to the technical field of traffic scenes, and particularly relates to a fine recognition method for various targets and elements of a traffic scene based on a segmentation technology, and the method comprises the following specific steps: S1, obtaining an image of the traffic scene, and randomly selecting a point A in the image of the traffic scene; s2, taking the point A as an original point, emitting a ray outwards, and reversely extending the ray so as to segment the image of the traffic scene into two groups of areas; s3, initializing a threshold value T, and usually taking an average gray value of each region; s4, calculating the gray value i to obtain the probability of the threshold value T in the region; and S5, after the probability of the threshold value T in the region is obtained, the proportion of each threshold value T in the corresponding region is obtained through a maximum entropy segmentation algorithm, and the method not only can improve the recognition effect, but also can improve the recognition accuracy.

Description

technical field [0001] The invention relates to the technical field of traffic scenes, in particular to a method for finely identifying various objects and elements of traffic scenes based on segmentation technology. Background technique [0002] Transportation refers to the industry engaged in the transportation of passengers and goods and the transmission of language and pictures, including transportation and post and telecommunications, and belongs to the tertiary industry in the national economy. There are five modes of transportation: railways, highways, waterways, airways, and pipelines. Posts and telecommunications include both postal services and telecommunications. At present, it is often necessary to identify various objects and elements in the traffic scene, but the current identification methods generally have the problem of poor identification effect. [0003] To this end, we propose a segmentation technology-based method for fine-grained recognition of various...

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): G06V10/26G06V20/54G06V10/10G06T7/90G06T7/136G06F17/18
CPCG06V10/267G06T7/136G06T7/90G06V20/54G06V10/16G06F17/18Y02T10/40
Inventor 胡翠云陈曼娜傅宏伟钟建斌林春招刘锋
Owner GUANGDONG FEIDA TRAFFIC ENG CO LTD
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