KR102108618B1 - Method of searching crime using video synopsis - Google Patents

Abstract

The present invention relates to a method for verifying a crime using a video synopsis, the method comprising: selecting a video desired by a user from CCTV photographed images and inputting a frame count for generating a background; Generating a background based on the original image using the selected image and the input frame count value; Inputting the first time at the time the image was taken and inputting the minimum and maximum values of the width and length of the object to be detected having a size desired by the user using the original image and the binary image; Performing synopsis with the inputted visual information and horizontal and vertical values and processing indexing; Setting a time zone and a speed of the image that the user wants to search based on the synopsis image and additionally inputting a color and direction of the object to be searched; And freely playing the original image, the binary image, and the synopsis image, and storing the final synopsis image on a PC.

Description

Method of searching crime using video synopsis}

The present invention relates to a crime verification method using a video synopsis, and more specifically, to check moving objects of a video captured through CCTV in a short time through a video synopsis function and to display the displayed object by giving the appearance time of the objects. It relates to a method for confirming crime using video synopsis.

Recently, convenience stores, marts, and various shops have been created everywhere, and the importance of crime prevention is also increasing. Currently, many CCTVs are installed indoors and outdoors, and when a crime occurs, the first CCTV is searched. However, the current CCTV system has a simple structure such as shooting, recording, and time search.

In such a conventional CCTV, if a crime occurs, all video information at the estimated time must be checked, so objects passing by may be missed, and the exact time of occurrence and the confirmation of the suspect are delayed.

In addition, there is the inconvenience of copying a CCTV video file on the spot in case of a crime and separately checking it through a PC or mobile device, or directly checking it on the spot.

Republic of Korea Patent Publication No. 10-2014-0057193 discloses a CCTV integrated control system that performs a video surveillance function by generating a synopsis image. The synopsis method generates a synopsis image by setting the longest occurrence time among the occurrence times as a synopsis display time, and when a feature setting command for displaying a synopsis image according to the characteristics of objects is input through the command input unit, according to the characteristic setting command. The synopsis generation unit is controlled so that objects generate a synopsis image for each color, size, movement direction, and speed.

In the case of the above technology, the surveillance image selected by the user among the surveillance images received through the network interface unit or stored in the surveillance image storage unit is signal-processed. Therefore, in generating a synopsis image, it can be processed only on the PC containing the CCTV with the event. In addition, since there is no part for storing the processed synopsis image, there is a problem in that the synopsis must be repeatedly performed to monitor multiple images.

An object of the present invention for solving the above problems is to provide a crime verification method using a video synopsis that performs a task based on a stored image rather than directly accessing CCTV and performing calculations.

In addition, another object of the present invention is to provide a crime verification method using a video synopsis to reduce unnecessary capacity and CPU usage by simply using a program without physical connection to the CCTV body, and to store and check synopsis results as desired by the user. Having

A crime verification method using the video synopsis of the present invention for achieving the above object comprises: selecting a video desired by a user from video captured by CCTV and inputting a frame count for generating a background; Generating a background based on the original image using the selected image and the input frame count value; Inputting the first time at the time the image was taken and inputting the minimum and maximum values of the width and length of the object to be detected having a size desired by the user using the original image and the binary image; Performing synopsis with the inputted visual information and horizontal and vertical values and processing indexing; Setting a time zone and a speed of the image that the user wants to search based on the synopsis image and additionally inputting a color and direction of the object to be searched; And freely playing the original image, the binary image, and the synopsis image, and storing the final synopsis image on a PC.

In the synopsis process, the image of the detected object may be stored, and the size, coordinate value, direction, and color information of the detected object may be stored as text.

To freely play the original video, binary video, and synopsis video, you can adjust the playback area of the video by moving the slider bar, and play it by adjusting the playback status through pause, stop, and rewind buttons.

As described above, according to the present invention, since information of an image is compressed and displayed in a short time so that video can be analyzed quickly and easily, the efficiency of video surveillance tracking an object detected in a recorded video can be maximized.

In addition, according to the present invention, a synopsis image is generated with only a small amount of CPU usage and memory, so that moving objects in the image can be quickly identified, and desired information can be conveniently and easily obtained through a search function such as direction and color.

In addition, according to the present invention, it is possible to quickly process synopsis regardless of the location with only the desired video and this program without physical coupling with the installed CCTV.

In addition, according to the present invention, since a synopsis result desired by a user can be quickly stored in a computer by using a filter such as direction or color, it is possible to shorten the time to check the result even after processing another image.

1 is an overall screen of a video synopsis program according to the present invention.
2 is a flow chart of a crime verification method using a video synopsis according to the present invention.
3A to 3D respectively show an original video playback screen, a binary video playback screen, a result screen after adjusting the size of an object to be detected, and a playback screen after synopsis.
4A and 4B are image files storing object information according to the present invention and text files storing object information.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art to which the present invention pertains may easily practice. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. In addition, in order to clearly describe the present invention in the drawings, parts irrelevant to the description are omitted, and like reference numerals are assigned to similar parts throughout the specification.

Hereinafter, a method of confirming a crime using a video synopsis according to an embodiment of the present invention will be described.

1 is an overall screen of a video synopsis program according to the present invention.

Referring to FIG. 1, the video synopsis program according to the present invention includes a basic menu 10, a segmentation menu 20, a playback screen 30, a playback menu 40, a playback setting 50, a search menu 60, and It comprises a storage button 70.

In the basic menu 10, when a user loads a desired image file, the original image and binary image radio boxes are activated. If the synopsis is performed in the segmentation menu 20 later, the composite video radio box is activated.

The segmentation menu 20 includes basic items to be set in order to proceed with synopsis. There is a part to enter the start time of the image, and a slider bar to set the size of the object desired by the user. The slider bar can check the size of the object to be detected in real time while checking the binary image radio box in the basic menu 10 and adjusting the maximum and minimum values of the width and height. When the segmentation button is pressed, synopsis proceeds according to the user's settings.

In the playback screen 30, an image is played according to the state of the radio box of the basic menu 10. When the synopsis video is played, the state of the playback setting 50 and the search menu 60 is also affected. In addition, the playback status of the image is determined by the playback menu 40.

The playback menu 40 determines a playback state of the playback screen 30. You can tell the current output time of the video and the length of the video, and you can adjust the playback time of the video right by the slider. There are a total of 4 play-related buttons, such as a rewind button, a play button, a pause button, and a stop button.

The reproduction setting 50 may adjust the start time, end time, and image speed of the synopsis image after synopsis is completed.

The search menu 60 is a function capable of searching for information on an object desired by a user in a synopsis image. It is divided into direction search and color search. The direction search searches the same objects appearing and exiting from the top, bottom, left, right, top left, top right, bottom left, and bottom right. During synopsis processing, the object's direction flag information is stored in a text file to retrieve objects that match the search conditions. The color search searches for objects matching 9 colors: red, orange, yellow, green, blue, magenta, black, white, and gray. You can search by selecting two or more colors. During synopsis processing, HSV and RGB data of an object are stored in a text file to load an object with a high frequency value.

The storage button 70 may be stored in a computer by pressing a button when a final synopsis image is determined with information input from the playback setting 50 and the search menu 60.

2 is a flow chart of a crime verification method using a video synopsis according to the present invention, and FIGS. 3A to 3D are original video playback screens, binary video playback screens, result screens for adjusting the size of an object to be detected, and synopsis After the playback screen, respectively, FIGS. 4A and 4B are image files storing object information according to the present invention and text files storing object information.

2 to 4, according to the present invention, a method for verifying a crime using a video synopsis, first selects an image desired by a user from images captured by CCTV, and inputs an associated count for generating a background (foreground) ( S100). That is, a video file to be processed for synopsis is selected and loaded, a background is generated based on the original image, and a frame count for updating the background is input.

Subsequently, a background is generated based on the original image using the selected image and the input frame count value (S110). That is, using the average background method, the number of frames read is counted and averaged for each pixel to generate a background. The generated background is used as the background of the synopsis image.

Subsequently, the first time at which the image was taken is input, and the minimum and maximum values of the width and length of the object to be detected having a desired size are input using the original image (FIG. 3A) and the binary image (FIG. 3B). (S120). In this process, objects meeting the conditions are detected in real time (FIG. 3C).

Next, synopsis is performed with the inputted visual information and horizontal and vertical values, and indexing is processed (S130). Here, indexing is a process of giving each of the first appearances to independent objects judged to be the same object until the first appearance in the video and exit. In addition, in order to proceed with the synopsis, an image of the detected object is stored (FIG. 4A), and information such as the size, coordinate value, direction, and color of the detected object is stored as text (FIG. 4B). After that, the objects detected on the background created based on the original image are uploaded at appropriate time intervals. At this time, when different objects overlap, it is processed through a blending algorithm to make it convenient for the user to check. Through this process, the synopsis image is generated and the detected objects meeting the conditions can be checked at once within about 1 to 3 minutes (FIG. 3D).

Next, based on the synopsis image, the user sets the time zone and speed of the image to search for and additionally inputs the color and direction of the object to be searched (S140).

Subsequently, the original image, the binary image, and the synopsis image are freely reproduced, and the final synopsis image is stored on the PC (S150). At this time, the playback method adjusts the playback area of the video by moving the slider bar, and adjusts the playback state through pause, stop, and rewind buttons.

Here, the image storage sets the time zone and the speed of the image that the user wants to search for, and receives and stores the finally processed image that additionally inputs the color and direction of the object to be searched.

As described above, according to the present invention, a synopsis image can be generated with a small amount of CPU usage to quickly check moving objects in the image, and a search function can conveniently and easily obtain desired information and store synopsis results.

Although the embodiments of the present invention have been described in detail above, the scope of the present invention is not limited thereto, and various modifications and improvements of those skilled in the art using the basic concept of the present invention defined in the following claims are also provided. It belongs to the scope of rights.

10: Basic menu 20: Segmentation menu
30: Playback screen 40: Playback menu
50: Playback settings 60: Search menu
70: Save button

Claims (3)

Selecting a video desired by a user from among images captured by CCTV and inputting a frame count for generating a background;
Generating a background based on the original image using the selected image and the input frame count value;
Inputting the first time at the time the image was taken and inputting the minimum and maximum values of the width and length of the object to be detected having a size desired by the user using the original image and the binary image;
Performing synopsis with the inputted visual information and horizontal and vertical values and processing indexing;
Setting a time zone and a speed of the image that the user wants to search based on the synopsis image and additionally inputting a color and direction of the object to be searched; And
And playing the original image, the binary image, and the synopsis image freely and storing the final synopsis image on a PC. According to claim 1,
The synopsis process is a method of verifying a crime using video synopsis, characterized by storing an image of the detected object and storing the detected object's size, coordinate values, direction, and color information as text. According to claim 1,
To freely play the original video, binary video, and synopsis video, adjust the play area of the video by moving the slider bar, and adjust the playback status through pause, stop, and rewind buttons to check the crime using video synopsis. Way.

Images