Video traffic flow statistical method based on unmanned aerial vehicle and time sequence characteristic

A technology of traffic flow and statistical methods, applied in the field of image processing, to achieve the effect of strong scalability, eliminating interference errors, and saving complicated operations

Active Publication Date: 2017-10-13
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS +1
View PDF8 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Purpose of the invention: In order to solve the existing deficiencies and problems, the pres

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
  • Video traffic flow statistical method based on unmanned aerial vehicle and time sequence characteristic
  • Video traffic flow statistical method based on unmanned aerial vehicle and time sequence characteristic
  • Video traffic flow statistical method based on unmanned aerial vehicle and time sequence characteristic

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0039] Example

[0040] Step 1. Collect images and input statistical area information.

[0041] Step 1-1, shoot and record the drone vertically above the road intersection to get the traffic flow video of the intersection, such as figure 2 shown;

[0042] Step 1-2, select the position in the video of the lane where traffic flow needs to be counted, as the area condition input system to be counted, generally select the area with relatively pure color between the white line of the lane and the crosswalk, such as image 3 shown.

[0043] In step 2, the background image is extracted by the median method calculation.

[0044] Step 2-1, from the start time of video statistics to the end time of statistics, take 30 video images at equal time intervals, and use the first image as the calibration image;

[0045] Step 2-2, since the video shot by the drone in the air will inevitably shake, it is necessary to perform matching transformation to eliminate the shake to avoid the error ...

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 video traffic flow statistical method based on an unmanned aerial vehicle and time sequence characteristics and belongs to the image processing technical field. According to the method, a traffic flow video is obtained through the photographing of the unmanned aerial vehicle above a road intersection; image matching is performed on the obtained video, so that influence caused by jitter can be eliminated; a background image is extracted through using a median value selecting method; each frame of image of the video is matched again with the background image; feature extraction is performed on specified regions of matched images, so that a feature time sequence histogram is obtained; and the feature time sequence histogram is analyzed, so that the traffic flow of lanes can be obtained. According to the method, regional features are simply and efficiently extracted, interference error caused by the jitter of the unmanned aerial vehicle is eliminated several times, and therefore, the statistics of the traffic flow is more accurate. The method has the advantages of simplicity, high efficiency, high adaptability, high expandability and a very broad application prospect.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a traffic flow statistics method based on unmanned aerial vehicles and time series feature video processing. Background technique [0002] Intelligent transportation has become the development trend in the future, and how to automatically and efficiently manage the transportation system is also a current hot spot. As a part of intelligent transportation, traffic flow detection plays an important role in traffic monitoring management and urban road construction. [0003] In recent years, the main traffic flow detection technologies include: magnetic induction detection technology, wave frequency detection technology and video detection technology. The video detection technology has the advantages of flexible installation, low cost, and easy management and maintenance. With the development of image processing technology and computer vision, the traffic flow de...

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
IPC IPC(8): G08G1/065G06K9/00G06T5/00G06T7/00
CPCG06T5/002G06T7/0002G08G1/065G06T2207/30236G06T2207/30242G06T2207/10016G06V20/52G06V2201/08
Inventor 刘宁钟张晨周敏朱志超王勇
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap