Unlock instant, AI-driven research and patent intelligence for your innovation.

Suspicious object detection method and device

A suspicious and detection system technology, applied in the field of image processing, can solve problems such as hidden dangers of suspicious objects and restrictions on the level of urban public security management

Inactive Publication Date: 2017-06-13
CHONGQING KAIZE TECH
View PDF6 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] With the rapid development of urban economy, the expansion of urban areas and the increase of urban population and other factors, the pressure on urban public security management is also increasing, and the increase of public security police force is far from meeting the actual needs. Traditional manpower prevention and The post-processing public security management model has begun to restrict the further improvement of urban public security management, especially under the influence of terrorist attacks, suspicious objects with abnormal residence time have caused serious damage to airports, railway stations, subway stations, bank ATMs and other public places. huge security risk

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
  • Suspicious object detection method and device
  • Suspicious object detection method and device
  • Suspicious object detection method and device

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0027] Please refer to figure 2 , figure 2 It is a flowchart of a suspicious object detection method provided by the first embodiment of the present invention. The method is applied to a suspicious object detection system. The system includes a camera and a computer. The following will figure 2 The illustrated process is elaborated, and the method includes:

[0028] Step S110: The computer receives the video information collected by the camera in real time.

[0029] Step S120: Based on the pre-saved background image, a moving target detection algorithm is used to obtain a moving target in each frame of the video information.

[0030] The moving target detection algorithm may be a multi-Gaussian model algorithm, background subtraction method, adjacent frame difference method, optical flow method, etc.

[0031] Taking the background subtraction method as an example, the computer subtracts the difference between each frame image and the pre-saved background image according to the vide...

no. 2 example

[0054] Please refer to image 3 , image 3 It is a flowchart of a suspicious object detection method provided by the second embodiment of the present invention. The method is applied to a suspicious object detection system, and the system includes a camera, a computer, and an alarm device. The following will image 3 The illustrated process is explained, and the method includes:

[0055] Step S210: The computer receives the video information collected by the camera in real time.

[0056] Step S220: Based on the pre-saved background image, a moving target detection algorithm is used to obtain a moving target in each frame of the video information.

[0057] Step S230: Perform image segmentation on the video information based on the moving target tracking algorithm to obtain the sensitive time of the moving target in the monitoring area of ​​the camera, where the sensitive time is the moving target The staying time or disappearing time in the monitoring area of ​​the camera.

[0058] St...

no. 3 example

[0065] Please refer to Figure 4 , Figure 4 It is a flowchart of a suspicious object detection method provided by the third embodiment of the present invention. The method is applied to a suspicious object detection system, and the system includes a camera and a computer. The following will Figure 4 The illustrated process is elaborated, and the method includes:

[0066] Step S300: The computer obtains multiple frames of image information of the surveillance area of ​​the camera in a continuous time.

[0067] Step S301: Perform modeling learning on the multi-frame image information based on the mixed Gaussian distribution background model.

[0068] Step S302: Save a frame of image determined after learning as a background image.

[0069] Due to the fact that in practical applications, there are problems such as day and night alternation, background disturbance, and illumination changes, if the same background image is used all the time, larger errors will be caused. Therefore, the ...

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 provides a suspicious object detection method and device, and belongs to the field of image processing. The method comprises the following steps that: a computer receives video information collected by a camera in real time; a pre-stored background image is taken as a basis, and a motion target detection algorithm is adopted to obtain a target under a motion state in each frame of image of the video image; on the basis of a motion target tracing algorithm, carrying out image segmentation on the video information to obtain the sensitive time of the target under the motion state in the surveillance area of the camera, wherein the sensitive time is the dwell time or the extinction time of the target under the motion state in the surveillance area of the camera; comparing the sensitive time with the first preset time; and when the sensitive time exceeds the first preset time, on the basis of a support vector machine classification algorithm, whether the target under the motion state is the suspicious object or not is judged. The method is used for detecting the suspicious object with the abnormal dwell time so as to reduce potential safety hazards in public places including airports, railway stations, metro stations, bank ATM (Automatic Teller Machine) and the like.

Description

Technical field [0001] The present invention relates to the field of image processing, in particular to a suspicious object detection method and device. Background technique [0002] With the rapid development of urban economy, the expansion of urban areas and the increase of urban population, the current pressure on urban public security management is also increasing, and the increase in public security police is far from meeting actual needs. Traditional manpower prevention and The public security management model based on post-event processing has begun to restrict the further improvement of the level of urban public security management, especially due to the impact of terrorist attacks, suspicious objects with abnormal detention time have caused problems in public places such as airports, railway stations, subway stations, bank ATM machines, etc. A huge safety hazard. Summary of the invention [0003] In view of this, the purpose of the embodiments of the present invention is...

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): G06T7/215G06K9/00G06K9/46
CPCG06T2207/10016G06V20/42G06V10/462
Inventor 吴军屈景春李腾谭海燕张辉
Owner CHONGQING KAIZE TECH