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

High efficiency vehicle detection method

A vehicle detection and high-efficiency technology, applied in the field of intelligent transportation, can solve problems such as inapplicable light changes, achieve the effects of reducing omissions, small amount of calculation, and improving detection accuracy

Active Publication Date: 2012-06-13
QINGDAO HISENSE TRANS TECH
View PDF6 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem that the existing vehicle detection method is not suitable for the time period when the light changes are relatively obvious, the present invention provides a vehicle detection method, which has a better detection effect on vehicle presence and vehicle motion information, and effectively prevents false detection and Target omission

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
  • High efficiency vehicle detection method
  • High efficiency vehicle detection method
  • High efficiency vehicle detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] Embodiment one, see figure 1 As shown, the efficient vehicle detection method in this embodiment includes vehicle presence information detection and vehicle motion information detection, specifically,

[0043] Vehicle presence information detection includes the following steps:

[0044] S11. Statistical background image model;

[0045] This step is mainly completed when the system is just powered on. By statistically analyzing the background image model, it is convenient to distinguish the foreground target point from the background target point in the subsequent steps.

[0046] In this step, the classic mixed Gaussian modeling method is preferably used to count the background image model.

[0047] S12. Perform a difference operation on the current frame image and the background image to obtain an image-background difference map;

[0048] Using the background image model counted in the previous step, the gray value of the current frame image and the gray value of the...

Embodiment 2

[0067] Embodiment 2, based on the judgment of car existence information and the judgment of car sports hall information in embodiment 1, this embodiment also includes the step of judging whether there is a vehicle passing through:

[0068] S31, using the direction gradient histogram in step S22 to determine whether the current frame image contains the front of the vehicle;

[0069] In this specific embodiment, it is judged in the following manner, since the edge information of the front of the car is the most abundant, the edge information of the corresponding interval of Q3 is the most abundant, followed by Q2, and Q1 is the smallest. In step S31, the method for judging whether the current frame image contains the front of the car is as follows: , if the following conditions are met at the same time, the head is included, otherwise it is not included:

[0070] Q3 > Q1;

[0071] Q3﹤5×Q1;

[0072] 1 / 3×(Q1+Q2)﹤Q2﹤3×(Q1+Q2).

[0073] S32. If it is judged that there is no car m...

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 a high efficiency vehicle detection method comprising steps of vehicle existing information detection and vehicle moving information detection. More particularly, the vehicle existing information detection comprises the following steps: (11), carrying out statistics on a background image model; (12), calculating an image-background difference graph; (13), carrying out binarization processing on the image-background difference graph; and (14), determining whether there is a vehicle or not. Moreover, the vehicle moving information detection comprises the following steps: (21), carrying out difference on two adjacent frames of images and extracting edge points for the difference image; (22), carrying out statistics on a gradient direction histogram of the edge points of the difference image; and (23), determining whether there is a vehicle in a moving state. According to the invention, the provided vehicle detection method has high detection precision and a good detection effect.

Description

technical field [0001] The invention relates to a vehicle detection method and belongs to the technical field of intelligent transportation. Background technique [0002] In the field of intelligent transportation technology, effective extraction of vehicle motion and presence information is a very important link in intelligent transportation. At present, the main vehicle detection methods are: the invention with the publication number CN101226691 and the invention name "Vehicle Counting Method Based on Video Image" The patent uses basic background modeling technology to detect foreground target points and estimate vehicle information by counting the gray value probability distribution of pixels, and realizes vehicle counting using computer vision technology. During dawn and evening, when the day-night transition and light changes are more obvious, due to the sharp drop in image brightness and contrast, it is easy to miss the target and the detection effect is not ideal. ...

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): G08G1/01G06T7/00G06K9/00
Inventor 刘韶孙婷婷朱中裴雷
Owner QINGDAO HISENSE TRANS 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