JPH04306781A - Detection of change for monitor picture - Google Patents

Abstract

PURPOSE:To facilitate the monitoring of invasion by area-dividing a picture processing monitor screen, storing a reference value as to a reference rod for respective areas and calculating the area of a changed picture based on the reference value when there is a change in a monitoring area in a monitoring status so as to judge an invading object. CONSTITUTION:A picture processor 3 consists of a picture processing monitor 1 displaying the processing result of the picture and an operation monitor 2 giving the instruction of an operation procedure. The reference rod 6 is vertically erected in the area becoming a monitoring object among the respective areas divided with the picture processing monitor 1. The reference value is inputted by adjusting a cross cursor at both ends of the reference rod 6 and clicking a mouse 5. When the change occurs in the monitoring area 7 in an invasion monitoring state, the picture processor 3 extracts the area where the change occurs and calculates a real size by the measuring value of the size on the screen and the reference value. Thus, the invaded object is judged from the real size of the area where the change occurs.

Description

[Detailed description of the invention]

0001

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method for detecting changes in monitoring images for remotely monitoring intruders from the outside.

0002

[Background Art] When detecting an intruding object by image processing and determining whether it is an intruding object, the area of the part that has changed on the screen is calculated, and if the area is greater than a specified value, it is determined that there is an intruding object. The most common method is to

[0003] This method is roughly divided into two types: one that makes a determination based only on the area of the changed part on the screen, and the other that determines the actual size of the invading object from its position on the screen. ■ Use under limited conditions such that the size of the intruding object on the screen can be predicted to some extent (such as making only the entrance/exit door or window the monitoring area). ■ To find out the actual size of an intruding object, monitor the same area with multiple cameras, calculate the distance from the camera to the object based on the difference in the size of the intruding object captured by each camera, and calculate the distance between this distance and the camera. Calculate the actual size of the intruding object from the focal length of the lens. ■ In order to know the actual size of the intruding object, input each coordinate on the screen of the monitoring area and the distance to the camera in advance.

0004

[Problem to be Solved by the Invention] Method (2) cannot be used unless the size of the invading object on the screen is known in advance. Method (2) requires multiple cameras, which increases costs, and requires the focal length of the lens and the position of the camera to be determined in advance, making it impossible to freely set the monitoring area. Method (2) also requires that the focal length of the lens be determined in advance. Moreover, when the monitoring area is large, it takes a lot of effort to measure and input the distance from each coordinate on the screen to the camera. The present invention aims to solve the above problems.

[0005]

[Means for Solving the Problems] A method for detecting changes in a surveillance image according to the present invention includes a surveillance camera that photographs a surveillance area, an image processing monitor that displays processing results of the photographed image, and an image processing device. , the image processing monitor screen is divided into areas, a reference object whose length or area has been measured in advance is placed within the area, a reference value for each area is stored, and a change occurs within the monitoring area in the monitoring state. In some cases, the image processing device calculates in which region of the divided areas of the image processing monitor the change is located, calculates the area of the image where the change has occurred based on the reference value of the area, and It is characterized by issuing an alarm when the area is within a predetermined range.

[0006]

[Operation] By dividing the monitor screen into areas and placing a reference object whose length and area have been measured in advance in that area, the actual area of the intruding object can be obtained and judgments can be made by comparing it with the reference value. can.

[0007]

DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be specifically described below with reference to embodiments shown in the drawings. FIG. 1 shows an embodiment of the present invention, and FIG. 1(a) is a block diagram of an image processing device;
(b) is an explanatory diagram showing an example of a monitoring area. Figure 1(a)
, the image processing device 3 includes an image processing monitor 1 for displaying image processing results and an operation monitor 2 for instructing operation procedures.
A monitoring camera 4 for capturing an image of the monitoring area 7 shown in (b), a mouse 5 for inputting reference values, and a keyboard 8 for inputting operation commands are connected. In this example, the reference object to be imprinted within the monitoring area 7 is a reference rod 6 with a length of 1 m.

First, the reference value is input, and the operation procedure is displayed on the operation monitor 2. According to the first instruction (see FIG. 6), the user views the image on the image processing monitor 1 and sets the surveillance camera 4 (FIG. 2A). When the camera settings are completed, the number of image divisions on the image processing monitor 1 is selected from the display on the operation monitor 2 and input using the keyboard 8.

When a key is input, the image from the camera 4 and the crosshatch image of the selected number of divisions are combined and output on the image processing monitor 1 (FIG. 2B), and the following instructions are displayed on the operation monitor 2. will be displayed (Figure 7). In this example, four divisions are selected. Generally, the number of divisions is set to be large when the depth of the monitoring image is deep, and set to be small when the depth of the monitoring image is shallow.

[0010] Look at the combined image and press the "G" key if you like it, and press the "ESC" key if you want to change the number of divisions. When the “ESC” key is pressed, the image processing monitor 1
The crosshatch disappears from the image displayed (FIG. 2B) (FIG. 2A), the image on the operation monitor 2 returns to its previous state (FIG. 6), and the number of divisions can be entered again. When the "G" key is pressed, a cross cursor is displayed on the image processing monitor 1 (Figure 2C), the next instruction is displayed on the operation monitor 2 (Figure 8), and the system waits for input from the mouse 5. . A flowchart for selecting the number of divisions is shown in FIG.

Of the areas divided by the image processing monitor 1, a reference rod 6 is vertically erected in the area to be monitored. By operating the mouse 5 and placing the cross cursor on one end of the reference rod 6 (FIG. 2D) and left-clicking, a dot is drawn at the position of the cross cursor (FIG. 2E). Next, place the cross cursor on the other end of the reference rod 6 (FIG. 2F) and left-click to draw a straight line between it and the previously drawn point (FIG. 2G).

The image processing device 3 calculates in which area the straight line is drawn based on the coordinates of the lower end of the straight line, and displays the area number and the length of the straight line on the operation monitor 2 (Fig.
),Remember. For convenience, area numbers are assigned sequentially from the top left (FIG. 2H). For example, in the case of quadrant calculation, if the x-coordinate of the lower end of the line to be examined is larger than 1/2 of the number of pixels in the horizontal direction of the screen, then the calculation is in the right half of the screen (
If the y-coordinate is smaller than 1/2 of the number of pixels in the vertical direction (Fig. 2I), this point is in the upper half of the screen (Fig. 2J), so the position of this straight line is area 1 at the upper right of the screen. I understand (Figure 2K).

After drawing a straight line in one area, move the reference rod 6 to the next area and input in the same way (Fig. 3
A). After drawing points and straight lines, make corrections as follows. After drawing a point, if the position of the point has shifted (Figure 3B), right-click the mouse 5 to erase the point (
Figure 3C). After drawing a straight line, if the position of the straight line deviates from the reference rod 6 (FIG. 3D), right-click to erase the line (FIG. 3E). The point at one end of the straight line at this time remains as it is, and the operation monitor 2 displays that the stored length of the straight line has been erased (FIG. 9). If you try to draw a straight line again in an area where a line has already been drawn, the cross cursor will stop moving (FIG. 3F) and a message will appear on the operation monitor asking if you want to overwrite (FIG. 10). When the "Y" key is pressed, the previous straight line is erased, only the new straight line remains (Figure 3G), and the length of the new straight line is stored as the reference value for this area. If you press "N", the newly drawn straight line will be erased (Fig. 3H).

[0014] Either enter the reference value in all areas or
Press the "ESC" key to finish the reference value input process, and a confirmation message to create a data file will be displayed on the operation monitor (Figure 11).Press the "Y" key to display the area where the straight line is drawn. saves the length of the straight line and "0" for the undrawn area together with the selected number of divisions in the data file.Press the "N" key to return to the reference value input state (Figure 8) and save the straight line as "0". can be redrawn.A flowchart for inputting the reference value is shown in FIG.

The data file is read into the memory of the image processing device 3 when the intrusion monitoring state is entered. When a change occurs within the monitoring area (FIG. 4A), the image processing device 3 extracts the area where the change occurred (FIG. 4B), and determines where in the divided area the coordinates of a specific point in that area are located. Calculate (Figure 4C). Further, the reference value of the area number is searched, and the actual size is calculated based on the measured value of the size of the extracted area on the screen and the reference value. For example, in the case of Figure 4A,
The actual size is calculated as follows.

This changed area is area 1 from FIG. 4C.
judged to belong to. The standard value for area 1 is 50,
Assuming that the height on the screen of the extracted area is 80 and the area is 1500, a reference bar of 100 cm is 50 cm on the screen in this area.
So, take the ratio, 100cm:50=xcm:80
∴x=160cm Therefore, the actual height of the extracted area is 160cm. Also, for the area, take the square of the ratio, 1002 cm2 :502 =x:1500
∴x=6000cm2 Therefore, the actual area of the extracted region is 6000cm2.

In this way, the intruding object is determined based on the actual size of the area where the change occurred. Furthermore, if there is a change outside the monitoring area (FIG. 5A), the actual magnitude will be as follows. First, we extracted the area where there was a change (Fig. 5B
), calculate the area of the changed region (Fig. 5C). At this time, since the reference value of this area 0 is 0, the above calculation is not performed and the actual height and area are set to 0.

Therefore, even if there is a change on the screen outside the monitoring area, the change is canceled in the process of processing by the image processing device 3, and erroneous judgments are not made. A flowchart for determining the actual size is shown in FIG.

[0019]

[Effects of the Invention] As described above, the present invention provides the following effects. ■There are no special installation conditions due to image processing,
You can freely set the monitoring area. Therefore, even when adding image processing to a conventional image monitoring system, there is no need to change camera settings. ■After setting up the camera, you can find out the actual size of the intruding object by simply inputting the reference value according to the instructions on the monitor screen, making it easy to change the monitoring area. ■By inputting a reference value, it is possible to simultaneously mask areas other than intruding objects that may cause changes (e.g. trees and clouds).

[Brief explanation of drawings]

FIG. 1 is a block diagram showing an example of the configuration of an apparatus for implementing the present invention.

FIG. 2 is an image processing monitor screen of a monitoring area showing a processing procedure according to the present invention.

FIG. 3 is an image processing monitor screen showing processing procedures in other areas.

FIG. 4 is an image processing monitor screen showing a processing procedure when a change occurs within the monitoring area.

FIG. 5 is an image processing monitor screen showing a processing procedure when a change occurs outside the monitoring area.

FIG. 6 is an operation monitor screen showing contents of operation instructions.

FIG. 7 is an operation monitor screen showing contents of operation instructions.

FIG. 8 is an operation monitor screen showing contents of operation instructions.

FIG. 9 is an operation monitor screen showing contents of instruction for operation.

FIG. 10 is an operation monitor screen showing contents of operation instructions.

FIG. 11 is an operation monitor screen showing contents of operation instructions.

FIG. 12 is an operation monitor screen showing contents of operation instructions.

FIG. 13 is a flowchart for selecting the number of divisions.

FIG. 14 is a flowchart of reference value input.

FIG. 15 is a flowchart for determining the actual size.

[Explanation of symbols]

1 Image processing monitor 2 Operation monitor 3 Image processing device 4 Surveillance camera 5 Mouse 6 Reference rod 7 Monitoring area 8 Keyboard

Claims (1)

[Claims] 1. A surveillance camera that images a surveillance area; an image processing monitor that displays processing results of the captured image;
The image processing device divides the image processing monitor screen into areas, places a reference object whose length or area has been measured in advance in the area, stores the reference value for each area, and divides the monitoring area in the monitoring state. When a change occurs in the area, the image processing device calculates in which area of the divided area of the image processing monitor the change is located, and the area of the image where the change occurs is set to the reference value of the area. 1. A method for detecting a change in a surveillance image, the method comprising calculating the area based on the area and issuing an alarm when the area is within a predetermined range.