Vehicle window throwing object detection method based on real-time video

A technology of real-time video and detection methods, applied in the field of pattern recognition, can solve the problems of inability to achieve efficient and large-scale all-weather real-time monitoring, limited coverage area, affecting traffic safety, etc. Difficulty managing effects

Pending Publication Date: 2021-03-12
JIANGXI HONGDU AVIATION IND GRP
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, with the rapid development of the economy, the use of cars is becoming more and more common, and various bad habits of driving and riding in cars are also emerging, such as throwing paper towels, mineral water bottles and other garbage from the car windows. Window throwing behavior not only destroys the appearance of the city, pollutes the urban environment, and affects traffic safety, but most of the garbage thrown from the window is left on the motorway, which seriously threatens the life safety of sanitation workers
[0003] How to control the uncivilized behavior of car window parabolic behavior has become a difficult problem that city managers must face. At present, it mainly relies on manual video surveillance to detect car window parabolic behavior. This method is time-consuming and laborious, with limited coverage and detection time gaps. Unable to realize efficient and large-scale all-weather 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
  • Vehicle window throwing object detection method based on real-time video
  • Vehicle window throwing object detection method based on real-time video
  • Vehicle window throwing object detection method based on real-time video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] In order to make the technical means, creative features, goals and effects achieved by the present invention easy to understand, the present invention will be further described below in conjunction with specific illustrations.

[0030] A kind of car window parabolic detection method based on real-time video, concrete steps are as follows:

[0031] 1) Get the video stream and decode it

[0032] Collect real-time video streams through front-end cameras or obtain video streams from third-party platforms, and use ffmpeg and cuda to hard-decode video streams;

[0033] 2) Moving target detection

[0034] Utilizing the correlation between the front and back frames in the video image sequence, the vibe algorithm is used to process each frame of image decoded in step 1), to eliminate background interference, and quickly detect the moving target area of ​​all images. The specific process is as follows figure 2 Shown:

[0035] First, use the first frame of the video sequence t...

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

A vehicle window throwing object detection method based on a real-time video comprises the following steps: acquiring and decoding a video stream, processing each decoded frame of image by using the relevance of front and back frames in a video image sequence so as to detect the moving target areas of all images, extracting the moving target areas, tracking the extracted moving target areas, and finally, judging whether the moving target is a vehicle window throwing object or not according to the inherent position, size and motion characteristics of the thrown object, and if the moving targetis judged to be the vehicle window throwing object, identifying the license plate of the vehicle which throws the object. According to the invention, the vehicle window throwing object behavior in themonitoring video can be detected without human participation, the real-time performance can be ensured, the detection accuracy can be ensured, the license plate of the vehicle with the vehicle windowparabolic behavior can be identified, efficient and large-scale all-weather real-time monitoring can be achieved, time and labor are saved, and the problem of difficult management is solved.

Description

technical field [0001] The invention relates to the technical field of pattern recognition, in particular to a real-time video-based window parabola detection method. Background technique [0002] At present, with the rapid development of the economy, the use of cars is becoming more and more common, and various bad habits of driving and riding in cars are also emerging, such as throwing paper towels, mineral water bottles and other garbage from the car windows. Window throwing behavior not only destroys the appearance of the city, pollutes the urban environment, and affects traffic safety, but also most of the garbage thrown from the window is left on the motorway, which seriously threatens the life safety of sanitation workers. [0003] How to control the uncivilized behavior of car window parabolic behavior has become a difficult problem that city managers must face. At present, it mainly relies on manual video surveillance to detect car window parabolic behavior. This me...

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): G06T7/136G06T7/155G06T7/194G06T7/215G06K9/00G08G1/017H04N7/18
CPCG06T7/136G06T7/155G06T7/194G06T7/215H04N7/18G08G1/0175G06T2207/10016G06T2207/30252G06V20/42G06V20/46G06V2201/07
Inventor 王欣欣叶超吴斌贠周会谢吉朋应艳丽王旭黄江林贾楠周继强王丽峰
Owner JIANGXI HONGDU AVIATION IND GRP
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