JPH07182570A - Image monitoring device - Google Patents

Abstract

PURPOSE:To provide an image monitoring device which prevents the omission of detection by detect-processing a moving object with plural stop values and can clearly record the detected moving object by executing diaphragm-control by using the image density of the area of a detected invading object. CONSTITUTION:The device is provided with an image pickup means 1 picking-up the image within a monitoring area, a conversion means 10 consecutively fetching the image picked-up by the image pickup means 1 and digitizing it, a moving object extraction means 11 extracting the moving object within the monitoring area by processing the image digitized by this conversion means 10, a diaphragm control means 33 varying a stop value of the image pickup means 1 to plural stop values based on an output from this moving object extraction means 11, or a diaphragm control means 33 controlling the stop value of the image pickup means 1 by the density of the moving object based on outputs from a recording means 32 recording the image picked-up by the image pickup means 1 and the moving object extraction means 11.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image monitoring apparatus for automatically detecting a moving object invading a monitoring area and confirming what the moving object is.

[0002]

2. Description of the Related Art The following is known as an example of this type of image monitoring apparatus. That is, for example, the ITV camera (imaging unit) captures an image in the imaging region and converts it into an electric signal.

An image signal picked up by this ITV camera is sent to a processing device through a transmission line, and the processing device detects a moving object. When a moving object is detected, an alarm device is sounded or a display control unit is used to display a graphic or a character indicating an abnormality on the display device.

The processing unit carries out the following processing. That is, first, the images of the imaging region are continuously captured by the processing device from the ITV camera.

The processing device performs analog-digital conversion of the captured image signal at regular intervals and stores it in the image memory. In the changed area extraction unit, the difference object between the data taken in the image memory and the reference image previously taken in the background image memory is binarized and binarized by a certain constant value (luminance threshold value) to change the object area. Ask for.

As a result, the pixel of the original change area is "1".
Detected as. The processing device extracts the moving object region by analyzing the detected change region by using projection or labeling.

The initial background image is taken in at the time of starting the apparatus, but the background image needs to be updated in accordance with changes in the environment. Therefore, the background image is updated by the background update control unit when the moving object is not extracted by the moving object extraction unit.

[0008]

By the way, in the conventional image monitoring apparatus as described above, an image monitoring apparatus for detecting an abnormality such as an intruding object by a change in a captured image is used as in an outdoor environment. When used in an environment where the irradiation conditions change, if the aperture of the ITV camera is fixed, the captured image will be too bright or too dark and the contrast of the image will not be sufficient, so the image will not change easily. In some cases, an omission of detection occurs, or even if an image at the time of detection is recorded, the intruding object is not clearly recorded.

To ensure that the captured image always has a sufficient contrast, the ITV of auto iris
A camera can be used, but when the iris is changing, a large change appears in the captured image, which causes erroneous detection.

Therefore, when the iris is changing,
A device that does not perform the detection process has been proposed. But,
In the case of this device, the detection process is frequently interrupted in a place that is intermittently affected by the automobile headlight or the like.

Further, in the image at the time of detection, since the control of the diaphragm is influenced by the ambient light, the intruding object may not be clearly recorded as in the case where the diaphragm is fixed. Therefore, the present invention has been made in view of the above points, and provides an image monitoring apparatus capable of preventing detection omission by performing detection processing of an intruding object with a plurality of aperture values. Has an aim.

Another object of the present invention is to:
An object of the present invention is to provide an image monitoring apparatus capable of recording a detected intruding object clearly and clearly by controlling the aperture using the image density of the detected area of the intruding object.

[0013]

According to the present invention, in order to solve the above-mentioned problems, an image pickup means for picking up an image in a monitoring area and an image picked up by this image pickup means are continuously fetched and digitized. Converting means, a moving object extracting means for extracting a moving object in the monitoring area by processing the image digitized by the converting means, and the imaging means based on the output from the moving object extracting means. An image monitoring apparatus, comprising: an aperture control unit that changes the aperture value of 1 to a plurality of aperture values.

According to the present invention, the image pickup means for picking up the image in the surveillance area, the converting means for continuously taking in the images picked up by the image pickup means and digitizing them, and the digitizing means for digitizing them. Based on the output from the moving object extraction means, the recording means for recording the image captured by the imaging means, and the moving object extraction means for processing the captured image to extract the moving object in the monitoring area. An image monitoring apparatus comprising: an aperture control unit that controls the aperture value of the imaging unit according to the density of the moving object.

[0015]

In other words, by performing the moving object detection process with a plurality of aperture values, detection omission is prevented, and the detected moving object is detected by performing aperture control using the image density of the area of the detected intruding object. It can be recorded clearly.

[0016]

Embodiments of the present invention will be described below with reference to the drawings. FIG. 2 is a configuration example of the present invention. For example, the ITV camera (imaging unit) 1 captures an image in the imaging region with the initial value F _i of the aperture value and converts it into an electric signal.

The image signal picked up by the ITV camera 1 is sent to the processing device 3 through the transmission line 4, and the processing device 3 detects a moving object. When a moving object is detected, the alarm device 6 is sounded, a graphic or a character indicating an abnormality is displayed on the display device 5, and at the same time, it is recorded in the recording device 32 described later.

In this case, the processing unit 3 controls the aperture of the ITV camera 1 by the aperture control unit 33, which will be described later, so that the moving object can be clearly captured. The processing device 3 can be represented by the block diagram shown in FIG.

That is, the images of the image pickup area 7 are continuously captured by the processing device 3 from the ITV camera 1. The processing device 3 A / Ds the captured image signal at regular intervals.
The converter 10 performs analog-to-digital conversion and stores it in the captured image memory 8.

The change area extraction unit 16 calculates a difference between the data captured in the captured image memory 8 and the reference image previously stored in the reference image memory 9, and outputs a binary value at a certain fixed value (threshold of brightness). Then, the variable object area 12 is obtained by converting (FIG. 3).

As a result, the pixel in the original change region is detected as "1" as shown in FIG. 4 (d). The detected change area is analyzed by using projection as shown in FIG. 5 or labeling as shown in FIG. 6 to extract the moving body area 20.

When the mobile body area 20 is extracted, the alarm device 6
Is sounded, the display control unit 19 is used to display a graphic or a character indicating an abnormality on the display device 5, and an image captured in the recording device 32 such as a VTR is recorded.

At the same time, the aperture control unit 33 controls the aperture by the following method so that a moving object can be clearly captured. The aperture control unit 33 determines the aperture value using, for example, the peak and variance of the density histogram of the moving object region 20.

FIG. 7 is a diagram showing an example of aperture control.
That is, when the intruder appears dark as shown in FIG. 7A, the density histogram of the moving object region 20 extracted by the moving object extraction unit 11 is as shown in FIG. 7B.

By comparing the density distribution σ _m of the density histogram of FIG. 7B with the density histogram distribution σ _i of the moving object area in the case of an ideal image which has been set in advance, a sufficient moving object area is obtained. It is detected that the contrast is not taken, and it is determined that the diaphragm needs to be adjusted.

When it is judged that the aperture needs to be adjusted, the peak value I _p of the density histogram of FIG. 7B and the center value I _{c of the} density are compared. In the case of FIG. 7B, I _p <
Since it is I _c, it is determined that the moving object region 20 is dark, and I
A signal for opening the diaphragm is issued to the TV camera 1.

7 (c) and 7 (d) are a density image of the captured image and the moving object area 20 after the aperture is opened. Further, when the intruder appears bright as shown in FIG. 7E, the density histogram of the moving object region 20 extracted by the moving object extraction unit 11 is as shown in FIG. 7F.

By comparing the density distribution σ _m of the density histogram of FIG. 7 (f) with the density histogram distribution σ _i of the moving object area in the case of an ideal image which is set in advance, a sufficient moving object area is obtained. It is detected that the contrast is not obtained, and the peak value I _p of the density histogram of FIG. _7F is compared with the center value I _{c of the} density.

In the case of FIG. 7 (f), since I _p > I _c, it is determined that the moving object area 20 is bright, and a signal for closing the aperture is issued to the ITV camera 1. 7 (g),
(H) is a density histogram of the captured image and the moving object region 20 after the aperture is closed.

FIG. 8 is a flowchart of the present invention. When the processing is started, the image of the imaging area 7 is captured from the ITV camera 1 to the processing device 3.

The processing device 3 receives the captured image signal as A /
The D converter 10 performs analog-to-digital conversion and stores it in the reference image memory 9 (step S1). After the reference image is captured in the reference image memory 9, the images of the imaging region 7 are continuously captured by the processing device 3 from the ITV camera 1, and the processing device 3 captures the captured image signal at regular intervals. A / D converter 10 performs analog-to-digital conversion,
The captured image is stored in the image memory 8 (step S2).

The change area extraction unit 16 calculates the difference between the data captured in the captured image memory 8 and the data in the reference image memory 9 and, as shown in FIG. for change object region 12 by binarizing (step S _3, S _4).

As a result, the pixel in the original change region is detected as "1" as shown in FIG. 4 (d). The detected change region is analyzed by using projection as shown in FIG. 5 or labeling as shown in FIG. 6 to analyze the moving object region 20.
Is extracted (step S5).

Here, when the moving object area 20 is extracted, the alarm device 6 is sounded, a graphic or a character indicating an abnormality is displayed on the display device 5 by using the display control unit 19, or it is taken into the recording device 32. Record images (step S
6, S7).

At the same time, the aperture control unit 33 causes the density histogram of the moving object region 20 (see FIG. 7B,
(F)) is obtained, and its variance σ _m and peak value I _p are calculated. (Step S8).

When the dispersion σ _m of the density histogram of the moving object area 20 is larger than the density histogram distribution σ _i of the moving object area in the case of an ideal image, it is determined that the contrast is sufficient, and the aperture control is performed. Not performed (step S9).

When the density histogram variance σ _m of the moving object region 20 is smaller than the density histogram variance σ _i of the moving object region in the ideal image, the moving object region does not have sufficient contrast. Judgment is made and the aperture is controlled as follows.

That is, if the peak value I _p of the density histogram of the moving object area is smaller than the center value I _{c of the} density,
It is determined that the density of the moving object region 20 is too low, and a signal for opening the aperture is issued to the ITV camera 1 (step S
10, S11).

If the peak value I _p of the density histogram of the moving object area is larger than the center value I _c of the density, it is determined that the density of the moving object area 20 is too high, and the ITV camera 1 is closed by a signal. Is issued (step S1
2).

In the above description, the distribution σ _m of the density histogram of the moving object area 20 is simply smaller than the density histogram distribution σ _i of the moving object area in the ideal image, and the peak value I _p is the center value of the density. If it is smaller than I _c , the diaphragm is opened, and if the peak value I _p is larger than the central value I _{c of the} density, the diaphragm is closed. However, n diaphragm states are prepared, and a table as shown in FIG. The state of the diaphragm may be determined by pulling.

FIG. 9 shows an example in which the diaphragm state F _m is obtained when the peak value is I _p and the variance is σ _m . FIG. 10 is a flow chart showing an example in which a moving object is detected while variously changing the aperture value.

When the processing is started, the image of the image pickup area 7 is taken in from the ITV camera 1 to the processing device 3 at the aperture value Fi ₀ . The processing device 3 performs analog-digital conversion on the captured image signal by the A / D converter 10 and stores it in the reference image memory 9 (step S21).

After the reference image is captured in the reference image memory 9, the images in the image pickup area 7 are continuously captured by the processing device 3 from the ITV camera, and the processing device 3 captures the captured image signal for a predetermined time. Every A / D converter 10 performs analog-to-digital conversion and stores it in the captured image memory 8 (step S22).

The change area extraction unit 16 calculates the difference between the data captured in the captured image memory 8 and the data stored in the reference image memory 9, and the difference is calculated to be 2 at a certain fixed value (threshold of brightness) as shown in FIG. The variable object region 12 is obtained by digitizing (steps S23 and S24).

As a result, the pixel in the original change area is detected as "1" as shown in FIG. 4 (d). The detected change region is analyzed by using projection as shown in FIG. 5 or labeling as shown in FIG. 6 to analyze the moving object region 20.
Is extracted (step S25).

Here, when the moving object area 20 is extracted, the alarm device 6 is sounded, a graphic or a character indicating an abnormality is displayed on the display device 5 by using the display control unit 19, or it is taken into the recording device 32. Record images (step S2)
6, S27).

If the moving object area is not extracted,
The above processes are repeated with the aperture values set to Fi ₁ , Fi ₂ , Fi ₃ ... (Step S28). 11 and 12 are diagrams showing an example in which a moving object is detected while variously changing the aperture value.

FIG. 11A shows an example in which the intruder 33 is in the shadow of a building. In such a case, the density histogram of the entire screen at the initial aperture value Fi ₀ seems to have sufficient contrast as shown in FIG. 11B, but the area 34 in the shadow of the building is The density histogram is shown in FIG.
As in (c), the lower the density value is, the more the image is solidified and the sufficient contrast is not obtained.

For this reason, the change area extraction unit 16 cannot extract the change area successfully, and the moving object area cannot be detected. When the moving object area is not detected, the aperture value is changed as shown in the flowchart of FIG.

The changed aperture value is Fi ₁ (Fi ₀ > Fi
₁ ), the captured image is shown in FIG.
As shown in FIG. 11F, the density histogram of the region 34 in the shadow of the building that is saturated as shown in FIG. 11E but does not have sufficient contrast at the aperture value Fi ₀ is shown in FIG.
As you can see, you can get enough contrast.

Therefore, the change area extraction section 16 extracts the change area successfully, and the moving object area is successfully detected. FIG. 12A shows an example in which the intruder 33 is hit by a spotlight.

In such a case, the density histogram of the entire screen at the initial aperture value Fi ₀ seems to have sufficient contrast as shown in FIG. 12B, but the area 35 in the spotlight is illuminated. The density histogram is
As shown in FIG. 12C, the lower the density is, the more the image is solidified and the sufficient contrast is not obtained.

For this reason, the change area extraction unit 16 cannot extract the change area successfully, and the moving object area cannot be detected. When the moving object area is not detected, the aperture value is changed as shown in the flowchart of FIG.

The changed aperture value is Fi ₁ (Fi ₀ > Fi
₁ ), the captured image is shown in FIG.
As shown in FIG. 1E, the density histogram of the area 35 illuminated by the spotlight that is saturated but does not have sufficient contrast at the aperture value Fi ₀ is shown in FIG.
As shown in 2 (f), a sufficient contrast can be obtained.

Therefore, the change area extraction section 16 extracts the change area successfully, and the moving object area is successfully detected. Although one embodiment of the present invention has been described above, it goes without saying that various modifications can be made without changing the gist of the present invention.

As described above, according to the present invention, by performing the detection processing of an intruding object with a plurality of aperture values, detection omission can be prevented and the image density of the area of the detected intruding object is used to reduce the aperture. By controlling, the detected intruding object can be clearly recorded.

[0057]

Therefore, as described in detail above, according to the present invention, it is possible to provide an image monitoring apparatus capable of preventing detection omission by performing detection processing of an intruding object with a plurality of aperture values. .

Further, according to the present invention, it is possible to provide an image monitoring apparatus capable of clarifying a detected intruding object by performing aperture control using the image density of the detected area of the intruding object. it can.

[Brief description of drawings]

FIG. 1 is a block diagram showing a processing device used in an image monitoring device according to an embodiment of the present invention.

FIG. 2 is a diagram showing a configuration of an image monitoring apparatus in the same manner.

FIG. 3 is a diagram illustrating detection of a changing object area based on background difference.

FIG. 4 is a diagram showing how a differential binary image is generated.

FIG. 5 is a diagram in which a moving object is extracted using projection.

FIG. 6 is a diagram in which a moving object is extracted using labeling.

FIG. 7 is a diagram showing an example of a state of aperture control.

FIG. 8 is a flowchart showing an example of the operation of the present invention.

FIG. 9 is a diagram showing an example of a table of aperture values.

FIG. 10 is a flowchart showing another example of the operation of the present invention.

FIG. 11 is a diagram showing an example in which a moving object is detected by changing an aperture value.

FIG. 12 is a diagram showing an example in which a moving object is detected by changing an aperture value.

[Explanation of symbols]

1 ... ITV camera, 2 ... moving object, 3 ... processing device, 4 ...
Transmission device, 5 ... Display device, 6 ... Alarm device, 7 ... Monitoring area (imaging area), 8 ... Captured image memory, 9 ... Background image memory, 10 ... A / D converter, 11 ... Moving object extraction unit,
12 ... Changing object region, 14 ... Moving object selecting unit, 16 ... Changing region extracting unit, 19 ... Display control unit, 20 ... Moving object region, 32 ... Recording device, 33 ... Aperture control unit, 34 ... Shadow of building. Area that is illuminated, 35 ... Area that is illuminated by the spotlight.

Claims (2)

[Claims] 1. An image pickup means for picking up an image in a monitoring area, a conversion means for continuously taking in an image picked up by the image pickup means and digitizing the image, and a digitized image is processed by the converting means. By doing so, moving object extracting means for extracting a moving object in the monitoring area, and aperture control means for changing the aperture value of the image capturing means to a plurality of aperture values based on the output from the moving object extracting means, An image monitoring apparatus comprising: 2. An image pickup means for picking up an image in the surveillance area, a converting means for continuously taking in the images picked up by the image pickup means and digitizing the image, and a processing for processing the digitized image by the converting means. Thereby, the moving object extracting means for extracting the moving object in the monitoring area, the recording means for recording the image captured by the image capturing means, and the density of the moving object based on the output from the moving object extracting means. And an aperture control means for controlling the aperture value of the image pickup means according to the above.