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

Abnormal moving object detection system and method thereof

A moving object detection and moving object technology, applied in the direction of instruments, character and pattern recognition, computer parts, etc., to achieve the effect of simple algorithm

Pending Publication Date: 2018-07-06
李刚毅
View PDF8 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This disclosure, while a video-based object tracking technique, is not object tracking-based anomalous motion detection

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
  • Abnormal moving object detection system and method thereof
  • Abnormal moving object detection system and method thereof
  • Abnormal moving object detection system and method thereof

Examples

Experimental program
Comparison scheme
Effect test

example

[0068] The purpose of realization is to use the video stream generated by IP camera shooting to realize the abnormal detection of object motion direction in the hot zone. The detection process is as follows.

[0069] 1) in such as Image 6 Calibrated hotspot (white square box), first test line and second test line (two white parallel lines in white square box) in the video area shown

[0070] A hot zone refers to one or more specific sub-areas that are focused on monitoring in a video area. If no hotspot is marked, the entire video frame area is a hotspot.

[0071] The first detection line and the second detection line are used to determine the moving direction of the object in the video. If the tracked moving object in the video passes through the second detection line first and then through the first detection line, it is considered that the object's motion direction is abnormal.

[0072] 2) Detect objects in video frames

[0073] In one embodiment of the present disclo...

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 an abnormal moving object detection method used for video hotspot detection. The method includes the following steps of assigning a hotspot, a first detection line and a second detection line in a monitoring video; detecting moving objects in the video hotspot; tracing the detected moving objects in later video frames; utilizing a double-detection-line method for recordingthe movement directions of the moving objects in the video hotspot to judge whether or not the movement trails of the moving objects are abnormal; when the moving objects with abnormal movement trails are found, triggering an alarm and outputting a result for storage. By discovering multiple monitored objects in the hotspot of the monitoring video, tracing all the objects separately and meanwhileutilizing the movement direction trends of the objects to judge the movement direction of each traced object, alarm noise is greatly reduced.

Description

technical field [0001] 本公开涉及一种对象检测系统及其方法,尤其是涉及用于视频热区(ROI, Regionof Interest)异常运动对象的对象检测系统及其方法。 Background technique [0002] 在诸如安保检测、交通检测之类的、涉及对象识别和追踪的特定场所的 热区检测中,已经存在很多热区对象检测方法。 [0003] 例如,中国发明专利申请公开CN107241572A公开了一种学员实训视频 追踪评价系统,其通过人员佩戴标志来识别人员身份,并通过人员位置来判 断其是否超出其允许范围。此公开内容需要利用人员佩戴的标志来锁定被识 别对象,需要训练特定的对象识别模型,因此其实施例只适用于特定的场景, 实施成本较高。并且通过人员位置来判断是否超出允许的活动范围是比较初 级的检测。 [0004] 此外,例如,中国实用新型专利公开CN 206258954 U公开了一种基于人 体运动方向检测的无人值守商店门禁系统,其利用RFID识别被监测物体, 并利用微波雷达监测人体运动。该公开内容使用的是RFID和微波雷达设备 进行检测,不适用于采用计算机视频技术进行对象检测。 [0005] 再例如,中国发明专利申请公开CN105844665A公开了一种视频对象追 踪方法及装置,其利用初始帧内标记样本实时训练对象追模型,并利用实时 训练的对象追踪模型对对象在视频中进行持续追踪。此公开内容虽然是一种 基于视频的对象追踪技术,但不是基于对象追踪技术进行的对象异常运动检 测。 [0006] 因此,需要一种能够在监测热区中发现多个被监测的对象并分别对各个 对象进行追踪,同时判断每个被追踪运动对象的运动方向的系统。 Contents of the invention [0007] 为此,本公开的目的是利用对象识别技术在监测视频的监测热区中发现 多个被监测的对象,并分别对各个对象进行追踪,同时判断每个被追踪运动 对象的运动方向。如果被追踪运动对象的运动方向不符合预定义的规则,则 自动报警,并保存相关视频帧存档备查。 [0008] 为了实现上述目的,根据本公开的一个方面,提供一种用于视频热区检 测的异常运动对象检测方法,包括以下步骤:a)在监控视频中指定热区、第 一检测线和第二检测线;b)检测视频热区...

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): G06K9/00
CPCG06V40/103G06V20/52
Inventor 李刚毅
Owner 李刚毅
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com