Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Traffic video visibility detecting method based on road surface brightness and least square approach

A technology of least square method and detection method, which is applied in measuring devices, material analysis through optical means, image data processing, etc., and can solve problems such as poor timeliness, low precision, and high price

Inactive Publication Date: 2014-03-12
南京汇川图像视觉技术有限公司
View PDF4 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to overcome the problems of high price of traditional visibility meter and low precision, low stability and poor timeliness of the traditional detection method in road visibility detection in the prior art, and provides a camera-based calibration , brightness calculation and objective function optimization traffic video visibility detection method, the present invention is mainly used in the highway monitoring system that adopts PTZ camera, at first the video image that PTZ camera collects is processed, extracts the road surface area that satisfies the condition, guarantees road surface Consistency of height and brightness, excluding surrounding noise interference, solves the problem of poor stability of traditional methods, and only calculates the road surface area that meets the conditions in units of image lines when calculating visibility values, rather than all pixels of the entire image Calculate one by one, improve the calculation speed, more suitable for real-time monitoring

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
  • Traffic video visibility detecting method based on road surface brightness and least square approach
  • Traffic video visibility detecting method based on road surface brightness and least square approach
  • Traffic video visibility detecting method based on road surface brightness and least square approach

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] In conjunction with accompanying drawing, the traffic video visibility detection method based on road surface apparent brightness and least square method of the present embodiment is characterized in that read the apparent brightness value of road surface in the road traffic video and combine least square method to establish objective function and calculate visibility value V met , including the following steps:

[0067] 1) Road traffic video image collection: Use the PTZ camera for road test on the highway to collect video images in foggy weather. When the visibility is lower than 20 meters, the highway will be closed; when the visibility exceeds 200 meters, the vision is good and no monitoring is required, so it is generally concerned The visibility distance is between 20 and 200 meters. Therefore, the collected video images must meet the requirements that the distance from the camera to the bottom row of pixel areas of the image is not more than 20 meters, and the top...

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 traffic video visibility detecting method based on the road surface brightness and the least square approach, and belongs to the technical fields of video image processing and visibility detecting. The detecting method comprises the following steps: 1) acquiring road traffic video images; 2) calibrating the acquired images by a Pan / Tilt / Zoom camera to extract a road surface region of interest (ROI); 3) extracting a road surface region formed by pixel points with the same brightness in the ROI and calculating the value of the road surface brightness; 4) by virtue of combination with the Koschmieder theory and the least square principle, building a squared brightness difference objective function to obtain the optimal solution of an extinction coefficient k; 5) transforming the optimal solution of the extinction coefficient k into image visibility distance Vmet; 6) drawing a curve of visibility changing along with time, observing the visibility condition and performing prejudgment. Proven by experiments, the method is compatible with an existing common traffic condition monitoring system, high in calculation accuracy, high in speed, excellent in robustness to noise, and wide in application prospect.

Description

technical field [0001] The invention relates to the technical fields of video image processing and visibility detection, and more specifically, to a traffic video visibility detection method based on road surface brightness and least square method. Background technique [0002] Severe weather such as fog and haze is a factor that seriously affects driving safety on expressways. Traffic congestion and even vicious accidents caused by low visibility occur frequently every year. According to relevant research reports, traffic accidents occurring in special weather account for about 24% of the total traffic accidents. Therefore, timely, accurate and effective monitoring and early warning of road visibility in severe weather is of great significance. Traditional visibility monitoring instruments are expensive, often costing hundreds of thousands, and cannot be deployed densely. At the same time, visibility monitoring instruments use the dynamic scattering mechanism of the atmosp...

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): G01N21/17G06T7/00
Inventor 李勃吴炜龚俊钱亚枫于海峰陈惠娟阮雅端陈启美
Owner 南京汇川图像视觉技术有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products