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

Road congestion state detection method based on computer vision

A computer vision and congestion state technology, applied in computer parts, computing, traffic flow detection, etc., can solve problems such as the inability to respond well to traffic congestion, the decline in the accuracy of clustering algorithms, and the occurrence of deviations.

Active Publication Date: 2019-01-04
QINGDAO UNIV
View PDF24 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the method for establishing a background model is difficult to be used in various complex road scenes. When the background model is deviated, the relative traffic congestion situation cannot be well reflected; the Chinese invention patent with the publication number CN103150900B discloses A video-based automatic detection method for traffic congestion events, the method is based on video detection equipment, obtains real-time traffic parameter information at the detection point and transmits it to the background server for storage, and then uses the automatic detection processing equipment to extract historical data for cluster analysis, and then Automatically determine the current traffic jam event
However, it is difficult to select the center of gravity of the clustering algorithm. Sometimes when anomalies appear, the accuracy of the clustering algorithm will decrease, and the congestion detection will also appear biased.

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
  • Road congestion state detection method based on computer vision
  • Road congestion state detection method based on computer vision
  • Road congestion state detection method based on computer vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] This embodiment relates to a specific computer vision-based road congestion state detection process, which specifically includes the following steps:

[0063] Step 1: Capture traffic monitoring images: use the existing road traffic monitoring system, first intercept traffic monitoring videos of different road conditions in the city, intercept a traffic monitoring image every 5 seconds, obtain a large number of RGB format images, and adjust them uniformly to 224 *224*3 size, and calculate the mean value of the three RGB channels of all images, and standardize the input data with 0 mean value as a data set; and mark the data set into three categories: less vehicles, more vehicles and dense vehicles , as the training set for neural network training;

[0064] Step 2: Construct a convolutional neural network: For the three types of vehicle density states, use the migration model training method to construct a convolutional neural network, so that it has the ability to accura...

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 road traffic operation state detection and control, and relates to a road congestion state detection method based on computer vision. The road congestion state detection method specifically comprises the technological steps of firstly classifying and marking data sets formed by processing a large number of collected images to serve as training sets for neural network training, then constructing a convolutional neural network according to the data sets by using a migration model training method, then classifying intercepted real-time traffic monitoring video images through the convolutional neural network, judging the vehicle density state, and finally calculating the optical flow field by using an optical flow algorithm so as to judge the traffic congestion state. The detection method is scientific in design principle and accurate in information collection, the image recognition accuracy reaches 98% and above, the monitoring effect is good, the cost is low, the effect is good, the data calculation method is simple, the judgment accuracy is high, the application is convenient, and the real-time traffic state can be effectively judged.

Description

Technical field: [0001] The invention belongs to the technical field of road traffic operation state detection and control, and relates to a detection method integrating artificial intelligence, convolutional neural network and image processing, in particular to a computer vision-based road congestion state detection method. Background technique: [0002] In recent years, there have been more and more researches on dynamic detection using optical flow technology, and good results have been achieved at the same time; The change of pixels in the time domain and the correlation between adjacent frames to find the corresponding motion relationship between the previous frame and the current frame; in fact, the optical flow vector can be defined as a specific coordinate point on the two-dimensional image plane The instantaneous rate of change of the grayscale, which represents the apparent movement of the image grayscale mode, is a two-dimensional vector field, and the optical flo...

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): G08G1/01G06K9/00G06K9/62
CPCG08G1/0133G06V20/54G06F18/241
Inventor 张志梅赵益刘堃王常颖王国栋
Owner QINGDAO UNIV
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