Supercharge Your Innovation With Domain-Expert AI Agents!

A Classified Recognition Method for Freeway Tunnel Parking Events Integrating Multiple Features

A technology of expressways and recognition methods, applied in character and pattern recognition, computer components, instruments, etc., can solve the problems of unsatisfactory binarization segmentation, easy to cause false detection, and local light spots.

Active Publication Date: 2021-06-08
CHONGQING UNIV +1
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the tunnel environment, due to the interference of vehicle lights and system lighting, sometimes local light spots will be formed in the image, resulting in the unsatisfactory effect of binarization segmentation and easy to cause false detection

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
  • A Classified Recognition Method for Freeway Tunnel Parking Events Integrating Multiple Features
  • A Classified Recognition Method for Freeway Tunnel Parking Events Integrating Multiple Features
  • A Classified Recognition Method for Freeway Tunnel Parking Events Integrating Multiple Features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] The method provided in this embodiment is mainly aimed at the actual application scenarios of highway tunnels. By studying the static and dynamic characteristics of parking targets in tunnel scenarios, analyzing the feature differences between actual parking targets and pseudo-parking targets, and integrating multiple features to analyze the parking The target is classified and recognized; this method first combines the corrected ROI of each lane, uses the lane division method and multi-frame foreground fusion method to extract the periodic features of the foreground, analyzes and processes, and then takes the dynamic centroid feature as the head, static color, area The feature is to judge whether there is a parking incident step by step, realize the effective identification of parking targets, and improve the accuracy of parking incident detection in existing expressway tunnels; specifically, it includes the following six steps:

[0047] Step 1: Calibrate the region of ...

Embodiment 2

[0072] The following is a detailed description of the above six steps in combination with the flowchart of the method for classifying and identifying parking events in expressway tunnels:

[0073] Step 1: Calibrate the region of interest, which mainly includes the following three parts:

[0074] Obtain video images from the highway tunnel camera, and manually mark the area of ​​interest of each lane, that is, mark the parking detection area, which can reduce the range of processed images, thereby reducing the amount of calculation and improving the timeliness of the algorithm. The area of ​​interest is generally selected as the accessible area of ​​vehicles in the expressway tunnel, including normal driving lanes and emergency parking belts;

[0075] According to the calibrated coordinates, the 0-1 template map of the region of interest of each lane is generated, that is, a black and white image with a pixel value of 255 in the region of interest and 0 in the non-interest regi...

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 method for grading identification of parking events in expressway tunnels that integrates multiple features. By studying the static and dynamic characteristics of parking targets in tunnel scenes, and analyzing the feature differences between actual parking targets and pseudo-parking targets, a method for merging multiple features is designed. Hierarchical recognition method for parking objects in expressway tunnel scene with features. This method first combines the corrected ROI of each lane, uses the lane division method and the multi-frame foreground fusion method to extract the periodic features of the foreground, analyzes and processes them, and then takes the dynamic centroid feature as the first, and the static color and area features as the auxiliary level. Judging whether there is a parking event occurs, realizing effective identification of parking targets, and improving the accuracy of parking event detection in existing expressway tunnels.

Description

technical field [0001] The invention relates to the technical field of expressway tunnel parking event detection, in particular to a hierarchical recognition method for expressway tunnel parking event combining multiple features. Background technique [0002] With the rapid and continuous development of expressway construction in our country, more and more expressway tunnels have been put into actual operation. Expressway tunnels can efficiently and quickly connect areas with complex traffic environments. At the same time, due to completely different traffic environments, they have become a bottleneck restricting the sustainable and healthy development of expressways. Due to the closedness of the scene and the characteristics of high driving speed, if a parking accident in the tunnel cannot be detected and dealt with effectively in time, it will easily lead to secondary accidents and even serious traffic accidents, seriously affecting the normal operation of the expressway. ...

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): G06K9/00G06K9/32
CPCG06V20/584G06V20/588G06V10/25
Inventor 赵敏孙棣华孙健王荣斌唐毅蒋陈虎
Owner CHONGQING UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com