JPH04213195A - Intruder monitoring system - Google Patents

Abstract

PURPOSE:To prevent mis-extraction caused by the change of climate, time, etc., the moving of things other than persons when the intruder monitoring system is used outdoors. CONSTITUTION:The master picture is generated by cumulating and adding plural raw pictures. The contrast of the raw picture is adjusted according to the brightness of the master picture. The digital picture is generated by finding the absolute value of the difference between the master picture and the raw picture. Whether individual digital picture is a picture representing persons or not is decided by finding the individual area of the digital picture and the moving speed. The system is constructed economically with the general purpose device.

Description

[Detailed description of the invention]

0001

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an intruder monitoring system for detecting intrusion of a person into a predetermined area.

0002

2. Description of the Related Art An intruder monitoring system is a system that detects whether or not a person has invaded a certain area (indoor or outdoor area), and is used for purposes such as vigilance.

Conventionally, in such systems, moving objects (intruders) have been extracted based on changes in gradation values of images obtained by cameras or the like. That is,
An image obtained by a camera, etc. at a certain point in time is compared with an image obtained at the next point in time, and it is assumed that a moving object exists in areas where the gradation value changes, thereby detecting an intruder. It was extracted.

0004

[Problems to be Solved by the Invention] As described above, in the conventional system, moving objects were extracted based on changes in gradation values, which resulted in incorrect extraction, inability to extract, etc., especially when used outdoors. situation could have occurred.

For example, outdoors, photographing conditions change depending on the weather and time of day. That is, in a shooting state where the gradation level is low, situations such as erroneous extraction or failure to extract may occur.

Furthermore, in the conventional system, if a moving object other than a person enters the area to be monitored, there is a possibility that it will be mistakenly extracted as a person. Examples of such moving objects include animals, birds, and the like. Similarly, water surface waves within the monitoring area,
There is a possibility that the shaking of a tree or the like may be mistakenly detected as an intrusion of a person.

[0007] Because of these problems, it has been difficult for conventional systems to continuously and accurately detect only intruders, especially outdoors.

The present invention has been made with the aim of solving these problems, and even when the system is used outdoors, regardless of changes in the weather and time, and even within the monitoring area. To provide an intruder monitoring system that does not erroneously extract a person other than a person as a person even when the person moves.

[0009]

[Means for Solving the Problems] In order to achieve the above object, the present invention provides a camera which obtains a raw image by fixing a predetermined area, and a parent image by cumulatively adding raw images of a predetermined number of frames. A parent image generation means that generates a parent image, a contrast adjustment means that adjusts the contrast of the raw image according to the brightness of the parent image, and a contrast adjustment means that calculates the absolute value of the difference between the parent image and the raw image. subtraction means for generating a digital image corresponding to the moving object showing discrete areas of different brightness;
The digital image has a detection calculation means for determining the individual area and moving speed of the digital image, and a determining means for determining whether the individual digital image is an image showing a person based on the determined area and moving speed. Features.

[0010] Furthermore, a second aspect of the present invention provides parent image updating means for updating a parent image by causing the parent image generation means to generate a parent image at predetermined time intervals; The present invention is characterized in that it has an update interval setting means for calculating a change in brightness by comparing it with an average brightness of , and setting an update time interval for the parent image according to the amount of the change. According to a third aspect of the present invention, the contrast adjustment means includes a plurality of types of contrast enhancement filters that perform processing including contrast enhancement on the raw image, and a filter selection means that selects the contrast enhancement filter according to the brightness of the raw image.
It is characterized by having the following.

[0011] According to a fourth aspect of the present invention, the subtraction means calculates the absolute value of the difference between the parent image and the raw image, and digitizes the image related to the absolute value of the difference using a density threshold. The present invention is characterized by having a means for generating a digital image corresponding to a moving object and showing individual regions having different brightness between the image and the raw image, and for removing minute regions from the digital image as noise.

[0012] According to a fifth aspect of the present invention, the detection calculation means includes means for determining the center of gravity of each digital image, and comparing the position of the determined center of gravity with the position of the center of gravity of the corresponding digital image in the previous image, and detects the movement of the digital image. A means for determining speed.

[0013] According to a sixth aspect of the present invention, the determining means includes means for setting the area and moving speed of the person, and based on the area and moving speed of the digital image and the preset area and moving speed of the person, the determining means determines whether the digital image is a person. and means for determining whether or not the image shows an image.

[0014]

[Operation] In the intruder monitoring system of the present invention, a predetermined number of frames of raw images are cumulatively added to generate a parent image. The brightness of the generated parent image is used to adjust the contrast of the raw image, and the raw image with the adjusted contrast is
It is subjected to processing in the subtraction means together with the parent image.

In the subtraction means, the absolute value of the difference between the parent image and the raw image is determined. The absolute value of this difference is used to generate a digital image. This digital image is an image that shows areas with different brightness between the parent image and the raw image,
This is an image corresponding to a moving object existing within the area to be monitored by the system. Therefore, when there are multiple moving objects, there are multiple digital images.

Based on the digital image thus generated, it is determined whether the moving object is a person. The data on which this determination is based are the individual areas and moving speeds of the digital images described above. This area and moving speed are determined by the detection calculation means. The obtained area and moving speed are input to the determining means, and based on the area and moving speed, it is determined whether the moving object is a person. Therefore, in the present invention, as in the case where the area to be monitored is an outdoor area,
Even if the shooting conditions change and a shooting condition with a low gradation level is forced, the contrast of the raw image is adjusted, so erroneous extraction or an unextractable state does not occur. According to a second aspect of the present invention, the parent image is further updated while changing the time interval according to a change in average brightness. Therefore, in adjusting the contrast of the raw image, the brightness of the parent image updated as appropriate can be used.

In the third aspect of the present invention, the contrast of the raw image is adjusted by selecting a contrast gradation filter. At this time, the contrast enhancement filter is selected depending on the brightness of the raw image. Therefore, the above-mentioned contrast adjustment operation is performed by the simple means of selecting a contrast enhancement filter.

[0018] In claim 4, the digital image is generated as follows. First, the absolute value of the difference between the parent image and the raw image is determined. The absolute value of the determined difference is then digitized at the density threshold. The resulting digital image is an image corresponding to a moving object, as described above. Therefore, in claim 4, a digital image corresponding to a moving object can be obtained by simple means of calculating the absolute value of the difference and digitizing using a density threshold.

[0019] Furthermore, in the fourth aspect of the present invention, minute areas of the digital image are removed as noise. As a result, it is possible to efficiently perform person detection by removing images that clearly do not correspond to people from among the digital images from the targets of calculation and determination.

[0020] In claim 5, the moving speed of the digital image is determined as a change in the position of the center of gravity.

[0021] In claim 6, whether or not the digital image is an image showing a person is determined based on the preset area and moving speed of the person. In other words, if the moving object in the area to be monitored is a person, the area of this moving object should match the empirically obtained area of the person, and the same is true for the moving speed. . Therefore, in claim 6, the area and moving area of the person are set in advance, and the determination is executed using the preset area and moving speed of the person. As a result, it is possible to determine whether the person is a person using simple means.

[0022]

DESCRIPTION OF THE PREFERRED EMBODIMENTS Preferred embodiments of the present invention will be described with reference to the drawings.

FIG. 1 shows the system configuration of an intruder monitoring system according to an embodiment of the present invention. As shown in this figure, this embodiment is comprised of a CCD camera 10, an image processing device 12, and a workstation 14. The CCD camera 10 is an outdoor camera, and is a highly sensitive black and white camera. Further, the image processing device 12 is a device having a resolution of, for example, about 500×500 pixels, and is a device that performs predetermined control on images supplied from the CCD camera 10 and supplies them to the workstation 14.

FIG. 2 shows the internal configuration of the image processing device 12.

As shown in this figure, the image processing device 1
2 is an A/D converter 16 that A/D converts an image obtained by the CCD camera 10;
An image processing section 18 that executes predetermined processing on images digitized by the image processing section 18, a monitor 20 that displays the results of image processing, and an interface that supplies data output from the image processing section 18 to the workstation 14. It consists of a certain GPIB interface 22.

FIG. 3 shows the internal configuration of the workstation 14. The workstation 14 is a GPIB that takes in data output from the image processing device 12.
Interface 24 and GPIB interface 2
4, a monitor 28 that displays data etc. obtained as a result of the processing of the processing device 26, and a disk device 30 that records necessary data. When it is detected that a person has entered the area to be monitored as a result of processing in the processing device 26, etc., an external interface 32 is an interface that sends a detection signal indicating this to the outside from the processing device 26. ing.

Next, the operation of intruder monitoring in this embodiment will be explained.

The areas to be monitored in this embodiment are, for example, the areas shown in FIGS. 4 and 5.

As shown in FIG. 4, the CCD camera 10 in this embodiment is installed on a cliff and arranged to photograph the area below the cliff. This CCD camera 1
0 is connected to a processing device 34 including an image processing device 12 and a workstation 14 shown in FIGS. executed.

The area photographed by the CCD camera 10 is, for example, a rectangular area as shown in FIG. Its size is, for example, about 10m x 10m,
In the state shown in this figure, hills, rocks, trees, etc. exist within the area photographed by the CCD camera 10, and two people 100 and 200 also exist. Next, the operations of the image processing section 18 and the processing device 26 in this embodiment will be explained. In the following explanation, the operations that the image processing section 18 is responsible for are those up to digitization using a density threshold. However, in the present invention, which operations the image processing section 18 is responsible for and which operations the processing device 26 is responsible for are determined entirely by design. Therefore, in the following explanation, the operations of both will be explained without any distinction.

In this embodiment, first, 32 frames of images obtained by the CCD camera 10 are cumulatively added. As a result of this cumulative addition, a parent image is generated.

[0032] The parent image is an actual observed image (raw image) that will be described later.
This is generated as an original image for comparison. The parent image needs to be updated as the natural environment of the area monitored by the CCD camera 10 changes. For example, during periods when the brightness is relatively stable, such as during the day and at night, it is OK to set the time interval for updating the parent image to be long, but during periods when brightness changes rapidly, such as in the morning and evening, It is necessary to shorten the update interval. Therefore, the parent image is updated as follows.

That is, when updating a parent image, the average brightness of the previous parent image and the average brightness of the current parent image are compared. If the difference between the two, that is, the average luminance change is large, it is necessary to shorten the time interval for updating the parent image. Furthermore, if the average brightness change is small, there is no need to update the parent image so frequently. That is, in this embodiment, the update time interval is switched based on the average brightness change of the parent image.

However, the time interval for updating the parent image is limited based on the moving speed of the person.

Next, the CCD camera 10 captures one frame of an actual observed image. The captured actual observation image is filtered by a contrast enhancement filter selected according to its brightness. At this time, since the filter to be selected also changes depending on the background conditions (land, water surface, water edge, etc.), it is necessary to set usable filters in advance according to the area to be monitored.

Further, a histogram smoothing process is performed on a high-contrast image with a high contrast and a low-contrast image with a low contrast, and an optimization filter process is performed on a very low-contrast image with an extremely low contrast.

The actual observation image that has been filtered in this way is subjected to absolute value subtraction with the parent image. That is, the difference between the parent image and the actual observed image is determined, and its absolute value is determined.

The image after such absolute value subtraction is digitized using a density threshold. This digitized image corresponds to an area in the actual observed image where the brightness has changed when viewed from the parent image. Such an image may be generated, for example, by the movement of the person 100, 200 or by the swinging of a tree.

Next, the area of the remaining digital image, that is, the digital image corresponding to the movement of the person 100, 200 or the tree is determined. Next, a change in the center of gravity position of the digital image is determined. This change in the center of gravity position is based on the center of gravity position of the person 100, 200 or the swinging of the tree in the actual observation image from the previous observation, and the center of gravity position of the person 100, 200 or the swinging of the tree in the actual observation image during the current observation. , is required as a change in . This change therefore gives the speed of movement.

The area and moving speed of the digital image thus determined are compared with the preset area and moving speed of the person. In other words, the area and moving speed of the person are known in advance empirically,
Therefore, by this comparison, it is determined whether the moving object related to the digital image is a person.

When the moving object is identified as a person in this manner, a detection signal is output from the processing device 26 to the outside via the external interface 32.

Therefore, in this embodiment, outdoor monitoring can be performed more accurately using the general-purpose image processing device 12, workstation 14, etc. That is, even if the photographing conditions in the monitored area change due to changes in time, etc., this is detected as a change in the average brightness of the parent image, and the parent image is updated accordingly.
It becomes possible to use a contrast enhancement filter for actual observed images.

[0043] When actually applying the system of this embodiment, consideration should be given to the use of lighting equipment for nighttime monitoring, for example, and the use of multiple cameras to eliminate blind spots. It is preferable to take this into consideration. Furthermore, the area and movement of a digital image obtained by digitization using a density threshold generally vary depending on whether the digital image corresponds to a part far from the CCD camera 10 or an image corresponding to a part close to the CCD camera 10. Different speeds. These perspective differences in area and moving speed are
This is an obstacle for the identification of moving objects. Therefore, C.C.D.
The mounting angle (depression angle) and magnification of the camera 10 are set so that this perspective difference can be ignored.

Furthermore, the detection signal output from the workstation 14 can be used, for example, to sound an alarm, start a warning broadcast, warn a host system, etc., but in the present invention, the detection signal can be used for any purpose. It may be used for other purposes.

[0045]

[Effects of the Invention] As explained above, according to the present invention,
Since it is determined whether the person is a person based on the individual area of the digital image and the speed of movement, an unmanned intruder monitoring system can be realized by economical means using general-purpose equipment.

Further, in claim 2, the update time interval is set based on the average luminance change of the parent image, so that even if the photographing conditions of the area to be monitored change depending on the time of day, weather conditions, etc. However, by removing this influence, it is possible to extract a person more accurately.

Furthermore, in claim 3, since filtering is performed using different contrast enhancement filters depending on the brightness of the raw image, contrast enhancement is performed using a suitable filter in response to changes in brightness in the raw image. It can be carried out.

According to claim 4, since digitization is performed using a digital image density threshold value, a stable digital image can always be obtained.

According to claim 5, since the moving speed is determined by determining the center of gravity of the digital image and comparing it with the previous raw image, the moving speed of the center of gravity of the image can be easily determined.

[0050] According to claim 6, it is possible to determine whether the digital image is a person based on the preset area and moving speed of the person.
Only people can be suitably extracted.

[Brief explanation of the drawing]

FIG. 1 is a block diagram showing the system configuration of an intruder monitoring system according to an embodiment of the present invention.

FIG. 2 is a block diagram showing the configuration of an image processing device used in this embodiment.

FIG. 3 is a block diagram showing the configuration of a workstation used in this embodiment.

FIG. 4 is a side view showing an example of a region to be monitored in this embodiment.

FIG. 5 is a plan view showing the area shown in FIG. 4;

[Explanation of symbols]

10 CCD camera 12 Image processing device 14 Workstation 18 Image processing section 26 Processing equipment 34 Processing equipment 100,200 people

Claims (6)

[Claims] 1. A camera that captures a raw image by photographing a predetermined area; a parent image generating means that cumulatively adds raw images of a predetermined number of frames to generate a parent image; a contrast adjustment means for adjusting the contrast of the original image; and determining the absolute value of the difference between the parent image and the raw image, and generates a digital image corresponding to the moving object that indicates individual regions with different brightness in the parent image and the raw image, respectively. a subtraction means;
a detection calculation means for determining the individual area and moving speed of the digital image, and based on the determined area and moving speed,
An intruder monitoring system comprising: determination means for determining whether an individual digital image is an image showing a person. 2. The intruder monitoring system according to claim 1, further comprising parent image updating means for updating the parent image by causing the parent image generating means to generate the parent image at predetermined time intervals, and an average luminance of the parent image. update interval setting means for determining a change in brightness by comparing the brightness with the average brightness of the parent image up to that point, and setting an update time interval for the parent image according to the amount of change;
An intruder monitoring system comprising: 3. The intruder monitoring system according to claim 1, wherein the contrast adjustment means includes a plurality of types of contrast enhancement filters that perform processing including contrast enhancement on the raw image; An intruder monitoring system comprising: filter selection means for selecting a filter. 4. The intruder monitoring system according to claim 1, wherein the subtraction means includes means for determining the absolute value of the difference between the parent image and the raw image, and a means for determining the absolute value of the difference between the parent image and the raw image, and the subtraction means for calculating the absolute value of the difference between the parent image and the raw image. A means for generating a digital image corresponding to a moving object by digitizing the original image and the raw image, showing individual areas with different brightness, and for removing minute areas from the digital image as noise. An intruder monitoring system comprising: 5. The intruder monitoring system according to claim 1, wherein the detection calculation means includes means for determining the center of gravity of each digital image, and a means for determining the center of gravity of each individual digital image, and a position of the center of gravity of the corresponding digital image in the previous raw image. compared to
An intruder monitoring system comprising: means for determining the moving speed of a digital image. 6. The intruder monitoring system according to claim 1, wherein the determining means includes means for setting the area and moving speed of the person, and a means for setting the area and moving speed of the digital image and the preset area and moving speed of the person. An intruder monitoring system comprising: means for determining whether a digital image is an image showing a person based on a moving speed.