Video-based abnormal event detection method and video-based abnormal event detection device applied to expressway

A technology for abnormal events and highways, applied in the direction of neural learning methods, computer components, instruments, etc., can solve the problems of difficult and accurate identification of abnormal events, slow recognition speed of abnormal events, and slow recognition speed, so as to achieve accurate recognition results, Easy to misjudgment, the effect of accurate judgment results

Pending Publication Date: 2020-08-07
北京巨视科技有限公司
View PDF6 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, on the expressway, abnormal events such as retrograde, throwing, and pedestrian intrusion occur frequently, which are likely to cause serious traffic accidents
[0003] Existing abnormal event detection based on applications on highways generally transmits a large number of videos to the background for analysis, making it difficult to accurately identify various abnormal events, and the recognition speed is slow
[0004] The above-mentioned existing technical solutions have the following defects: the existing abnormal event detection system based on expressways is difficult to accurately identify abnormal events, and the identification speed of abnormal events is slow

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-based abnormal event detection method and video-based abnormal event detection device applied to expressway
  • Video-based abnormal event detection method and video-based abnormal event detection device applied to expressway

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] Embodiment 1 of the present invention provides a video-based abnormal event detection method applied on expressways. The main process steps are as follows:

[0054] Obtain video images on the highway and preprocess the video images;

[0055] Perform frame difference calculation on the acquired video image to divide the motion area of ​​the video image. Because the occurrence of abnormal events will cause motion on the video image, it is beneficial to perform frame difference calculation on the acquired video image to divide the motion area of ​​the video image. Accurately and quickly locate abnormal areas;

[0056] Detect the divided motion areas to identify whether the object is a vehicle or a pedestrian;

[0057] According to the identified object, identify the abnormal event as retrograde or congestion or throwing or pedestrian intrusion.

[0058] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, t...

Embodiment 2

[0085] refer to figure 2 Embodiment 2 of the present invention provides a video-based abnormal event detection device applied on expressways, including:

[0086] The video image acquisition module is used to obtain the video image and preprocess the video image, zoom and enhance the video image;

[0087] The motion area detection module is used to receive the acquired video image and perform frame difference operation detection on the video image using an adaptive threshold method, divide the motion area of ​​the video image, and input the detected area to the object detection module;

[0088] The object detection module is used to receive the divided motion areas, detect each motion area, identify whether the object is a vehicle or a pedestrian, and send the detection results to the abnormal event discrimination module;

[0089] The abnormal event discrimination module is used to identify the abnormal event as retrograde or congestion or throwing or pedestrian intrusion accor...

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 relates to the technical field of road traffic safety, and aims to provide a video-based abnormal event detection method and device applied to an expressway, and the method comprises thesteps: obtaining a video image; performing frame difference operation on the acquired video image, and dividing a motion area of the video image; detecting each divided motion area, and identifying whether an object is a vehicle or a pedestrian; according to the identified object object, identifying that the abnormal event is retrograde motion or congestion or throwing or pedestrian intrusion. The problems that an existing abnormal event detection system based on an expressway is difficult to accurately identify an abnormal event, and the identification speed of the abnormal event is low aresolved. The method has the advantages that abnormal events such as retrograde motion, congestion, throwing and pedestrian intrusion can be accurately and quickly judged, the recognition result is transmitted to the background, analysis based on the background is not needed, and the requirement for a transmission network is greatly reduced.

Description

technical field [0001] The invention relates to the technical field of road traffic safety, in particular to a video-based abnormal event detection method and device applied on expressways. Background technique [0002] At present, with the increase of the number of motor vehicles, the congestion problem on the road is becoming more and more serious, especially on the expressway. With the reform of the expressway toll mode, the ETC segmental toll model has become popular. The gate frame is installed in sections on the expressway, and then the monitoring camera and hardware analysis equipment are installed on the gate frame to collect video images and perform billing. When the vehicle passes through the toll booth, the on-board equipment will realize vehicle identification, information writing and automatically deduct the corresponding funds from the pre-bound IC card or bank account, so as to realize rapid traffic opening and effectively alleviate the problem of road congest...

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): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06V20/44G06V20/41G06N3/045
Inventor 席方凯王海峰
Owner 北京巨视科技有限公司
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
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