JPH057364A - Picture monitoring device - Google Patents

Abstract

PURPOSE:To obtain detecting results of an intruding object at faster time intervals while a conventional detecting performance of the intruding object is maintained. CONSTITUTION:A picture signal from an ITV camera 1 is converted into a digital signal by an A/D converter 11, in a specified sampling rate outputted at a time interval DELTAt from a sampling pulse generating circuit 10, and the result is stored as a pictrue data of the time t=ti, in a picture memory 12. When the picture data of time t=ti enters the picture memory 12, a picture memory controlling circuit 16 transmits both this picture and the one fetched n sheets before to a difference binarizing circuit 14. The difference binarizing circuit 14 finds a difference between both pictures transferred, and converts it into a difference binarized picture in which a picture element having a change is expressed as '1', and stores it in a difference binarizing memory 15. A CPU 13 analyzes a changing area by using the difference binarized picture in the difference binarizing memory 15. By which, whether the changing area is an intruding object or not is decided.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image monitoring device for detecting an intruding object in a monitoring area.

[0002]

2. Description of the Related Art One example of this type of image monitoring apparatus is shown in FIG. That is, the ITV camera (imaging unit) 1 captures an image in the monitoring area 8 and converts it into an electric signal. The image captured by the ITV camera 1 is processed by the transmission line 2 into the processing device 3, the display device 5, and the video tape recorder (hereinafter simply referred to as VTR).
Sent to 7. The display device 5 displays the surveillance image captured by the ITV camera 1, and the VTR 7 records the surveillance image captured by the ITV camera 1 continuously or when an intruding object is detected.

On the other hand, the processing device 3 performs the following intruding object detection processing, for example. That is, the image signal from the ITV camera 1 is A / D converted at a predetermined sampling rate and stored in an image memory (not shown) as image data at time t = ti, for example. The image data at the time t = ti has
The time t = t when it was taken into the image memory before this
Inter-pixel difference calculation is performed with the image data of i-1,
The difference image is obtained. The calculated difference image is converted into a difference binarized image in which the changed pixel is represented by "1".

Then, the changed area is analyzed using the difference binary image, and when it is determined that the changed area is an intruding object, an alarm device 6 is sounded or a monitor is displayed on the display device 5. To see what the intruding object is,
If R7 is not in operation, it is operated to record an image of an intruding object detected or an image input from the ITV camera 1. If it is determined that the object is not an intruding object, the image is continuously captured and the above procedure is repeated.

By the way, change area extraction (intrusion object detection)
As a pixel-to-pixel calculation for, a difference from a background image when there is no intruding object or a time-series difference between images captured at a predetermined time interval is generally used. With the difference from the background image, even if the intruding object is stopped, it can be detected, but if the environment such as the brightness is changing, such as outdoors, the background image must be updated to find the intruding object. Also has the characteristic that it produces a change area.

In the case of the time series difference, since the difference is generally made at relatively close time intervals, the ability to follow environmental changes is excellent, but when the intruding object stops, it cannot be detected.
Further, even if the intruding object is moving, the difference between the two screens has a feature that both the disappearing portion and the occurring portion of the intruding object are detected.

To eliminate the latter drawback of time series difference,
Instead of two screens of t = ti and t = ti-1, further t = ti +
Using three consecutive 1 screens, the difference calculation is performed on the front 2 screens and the rear 2 screens respectively, and the intruding object in the image of t = ti is detected by the logical product of the two difference images obtained. In some cases, there is a method.

FIGS. 5 and 6 are diagrams showing the timing when a change area is extracted and analyzed by a time series difference. FIG. 5 shows a case where two consecutive images are used, and FIG. 6 shows three consecutive images. The timing when using is shown.

In FIG. 5, (a) represents the image capturing, (b) represents the timing of extracting and analyzing the changed region, and the region si represents the time t = ti-1 to t =.
This indicates that the change up to ti is being analyzed. (C)
Represents the timing at which the result of the analysis comes out, and an alarm is sounded here, or the imaged image at this time is displayed on the display device 5 or recorded in the VTR 7 if necessary.

In FIG. 6, (a) represents the capture of the image as in FIG. 5, and (b) represents the timing for extracting and analyzing the changed region as in FIG. When three consecutive images are used, the time t = ti− after capturing the images in order to extract the change area by the logical product of the differences between the two images.
The time di at which the difference image with the image captured in 1 is calculated,
The time pi-1 at which the differential binarized image at time t = ti-1 is obtained and analyzed by the logical product of the difference image between time t = ti-2 and time t = ti-1 obtained previously. However, similar to FIG. 5, the result can be obtained at the timing of (c). When an intruding object is detected, the alarm device 6 is sounded, displayed on the display device 5, and recorded in the VTR 7, as in the case of FIG.

[0011]

In a typical image monitoring apparatus, the time-series difference is used rather than the background difference in many cases with a focus on the followability to environmental changes. In this case, if the image capturing interval is too short, the movement of the intruding object becomes relatively small, and it becomes difficult to extract the changed region. Therefore, the capturing time is generally set to 0.4 seconds to 1 second. Target.

However, in such a case, the time interval at which the image is analyzed and the result is obtained is determined by the image acquisition time interval, and therefore the result is generally obtained only in the set 0.4 second to 1 second unit. It will not be possible. In other words, the screen for detecting and displaying an intruding object is updated only in 0.4 seconds to 1 second, and the monitor directly or by the VT
There was a problem in that it was difficult to see when trying to confirm continuous changes such as tracking by recording after recording in R.

Further, if an intruding object is not determined by one differential binary image but an attempt is made from a plurality of differential binary images, a plurality of differential binary images are obtained by the conventional method. Therefore, there is a problem in that it takes 0.4 to 1 second, which is several times as long, and it takes time to obtain a result.

Therefore, it is an object of the present invention to provide an image monitoring apparatus capable of obtaining the detection result of an intruding object at a fast time interval without changing the detection performance of the intruding object as compared with the conventional case.

[0015]

SUMMARY OF THE INVENTION An image monitoring apparatus of the present invention is an image pickup means for picking up an image in a monitoring area, and an image pickup means for continuously taking in images picked up by this image pickup means at predetermined time intervals. Means and the image acquisition time interval of this acquisition means
When t is set, the intrusion into the monitoring area is performed by performing a predetermined calculation between images that are continuously captured and separated by n × Δt (n ≧ 2, n is an integer). And a detection means for detecting an object.

[0016]

When the image capturing time interval is Δt, n × Δt (n
≧ 2, n is an integer) By performing a predetermined calculation between images that are distant from each other, by detecting an intruding object (extracting a changed region), the intruding object detecting performance is the same as the conventional one, but a fast time The detection result of the intruding object is obtained at intervals. Therefore, the intruding object detection image is directly or V
When checking after recording on TR, the movement of change can be seen smoothly.

[0017]

DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described below with reference to the drawings. The same parts as those in FIG. 4 will be described with the same reference numerals.

FIG. 1 shows the arrangement of an image monitoring apparatus according to this embodiment. In the figure, an image signal sent from the ITV camera 1 to the processing device 3 is converted into a digital signal by the A / D converter 11 at a predetermined sampling rate output from the sampling pulse generation circuit 10 at a time interval of Δt. , And is stored in the image memory 12 as image data at time t = ti. Here, the image memory 12
Is a memory that can store a plurality of image data.

The image memory 12 is the image memory management circuit 1
Managed by 6. That is, the image memory management circuit 16
When the image data at time t = ti is stored in the image memory 12, the image data is sent to the difference binarization circuit 14 between this image and the image captured n sheets before. The difference binarization circuit 14 takes the difference between the two sent images, converts the changed pixel into a difference binarized image represented by “1”, and stores it in the difference binarized memory 15.

The CPU 13 analyzes the changed area using the difference binary image stored in the difference binary memory 15 and determines whether the changed area is an intruding object. When it is determined that the object is an intruding object, the alarm device 6 is sounded, the monitor confirms what the intruding object is on the display device 5, and when the VTR 7 is not operating, it is activated. Image of the intruding object or ITV
The image input from the camera 1 is recorded. If it is determined that the object is not an intruding object, the image is continuously captured and the above operation is repeated.

As described above, the image memory management circuit 16 continuously performs management such that each time an image is captured, the difference between the image data of the image captured n sheets before is captured. In other words, in order to repeat this operation continuously, it is necessary to have at least (n + 1) planes of image memory inside, so that this memory is managed to be used repeatedly and images separated by n are sent out one after another. Become.

FIG. 2 is a timing chart showing how images are captured and analyzed when a change area is extracted from two continuous images. The figure (a) shows the image capture timing, and if this time interval is Δt, Δ
t is faster than the conventional image acquisition time, for example, 0.2
The time interval is about a second. The same figure (b) shows the timing of obtaining the difference image from the two images and analyzing the changed area. Here, the two images that are difference images are n × Δt
= If the image difference calculation is performed for about 0.6 seconds in the conventional case where the images are separated from each other by n images having the conventional image capture time interval, the value is about n = 3.

When an image is captured at a certain time t = ti, this image is the nth previous image, that is, the time t = ti-n × Δt.
= T i -3Δt = t i -3, the difference calculation is performed to obtain the difference binarized image, and the change region is analyzed.
This time is si, and the analysis result is obtained at the timing shown in FIG. When it is determined that there is an intruding object, the alarm device 6 is sounded, a monitor image is displayed on the display device 5 as necessary, and recorded in the VTR 7 as in the conventional case.

Further, since n × Δt = 3Δt is equal to the conventional image capturing time interval, the analysis performance at si is the same as the conventional one. Time t = t + Δ after the result at si
When t = ti + 1 and the image is captured, as in the case of time t = ti, the images separated by n sheets, that is, time t = ti + 1-
A difference image from the image of (n × Δt) = ti + 1 −3Δt = ti-2 is calculated to obtain a difference binarized image, and the change region is analyzed. By repeating the above operation, the same analysis result as the conventional acquisition time interval is 1 / n
Will be obtained at time intervals of.

Although it is assumed here that an intruding object is detected using one differential binarized image and a monitor image is displayed on the display device 5 or recorded on the VTR 7, one differential binarized image is used. Even if the final decision is made by analyzing a plurality of differential binarized images instead of making an image decision, an image for analysis can be obtained at a speed of 1 / n faster than before The result of object detection can be obtained faster than before.

As described above, the basic point of the present embodiment that is different from the conventional analysis method is that the difference calculation for extracting the change area (detecting the intruding object) is not performed between consecutive images, but n pieces are changed. This is to be done between distant images. That is, image data sent in the image memory at Δt intervals,
By selecting the image data sent at the time of n sheets before and performing the difference calculation, n times faster than before, for example, 0.
The change area can be extracted in units of 2 seconds.

In the above description, the change area is detected using two consecutive images, but the same effect can be obtained even if the change area is detected using three consecutive images. Can be obtained. FIG. 3 is a timing chart showing how images are captured and analyzed when a change area is extracted from three consecutive images. FIG. 9A shows the timing of capturing an image. When this time interval is Δt, Δt is a time interval faster than the conventional image capturing time, for example, about 0.2 seconds.

FIG. 3B shows the timing of extracting the change area from the three images. The method is basically the same as the conventional one, and the difference between the front two images and the rear two images is obtained. The image is obtained, and the change area is extracted by the logical product. However, the two images that are difference images are not continuous images that have been captured, but are images that are n apart from each other such that n × Δt = conventional image capture time interval.
If the image difference calculation is performed in about 6 seconds, n
= About 3.

As the analysis processing of the intruding object when the image is captured at a certain time t = ti, the time di for calculating the differential image when the image is captured and the time t = ti-n × Δt = t
i −3Δt = ti−3, time t = ti−
3 and time t = ti −2 × (n × Δt) = ti−6Δt =
By the logical product of the difference image with the image captured in ti-6,
Similarly, it is divided into time pi-3 for calculating the differential binarized image at time t = ti -3 .DELTA.t = ti-3.

That is, when an image is captured at a certain time t = ti, this image is the nth previous image, that is, n × Δt =
The difference is calculated with the image 3Δt before. Subsequently, the change area is analyzed by taking the logical product of the difference image obtained at the time t = ti-n.times..DELTA.t = ti-3.DELTA.t obtained previously and obtaining the difference binary image. Then, the analysis result is obtained at the timing shown in FIG. When it is determined that there is an intruding object, the alarm device 6 is sounded, a monitor image is displayed on the display device 5 as necessary, and recorded in the VTR 7 as in the conventional case.

Further, since n × Δt is equal to the conventional image capture time interval, the analysis performance when taking the difference image is the same as the conventional one. After the result of p i −n × Δt is obtained,
At time t = t + .DELTA.t = ti + 1, when the image is captured, the image separated by n sheets, that is, the time t is obtained as at time t = ti.
= Ti + 1- (n * [Delta] t) = ti + 1-3 [Delta] t = ti-2 The difference image with the image is calculated, and the difference image obtained previously is ANDed to obtain the difference binarization. An image is obtained (pi-2) and the changed area is analyzed. By repeating the above operation, the same analysis result as that of the conventional acquisition time interval can be obtained at a time interval of 1 / n as compared with the conventional one. In the above description, n = 3 has been described, but as described above, this is an example, and it is not always necessary.

As described above, according to the above embodiment,
In order to detect an intruding object, the time interval for obtaining the difference between the images is not changed, the time interval for capturing the image is increased, and the time interval of the resulting differential binarized image is shorter than before. By setting the interval, the detection result of the intruding object can be obtained at a fast time interval without changing the detection performance of the intruding object as compared with the conventional case. Therefore, when confirming the detection image of the intruding object directly or after recording it on the VTR, it is possible to smoothly see the movement of the change. In addition, when an attempt is made to analyze an intruding object using a plurality of differential binary images, the differential binary image can be obtained at a fast time interval, so that the analysis result of the intruding object can be obtained quickly. ..

In the above embodiment, the image memory management circuit has been described as managing the image memory.
Of course, the CPU can perform the function of the image memory management circuit, in which case the system can be simplified. Further, it is needless to say that the present invention does not necessarily have the configuration of FIG. 1 or the timings of FIG. 2 and FIG. 3, and various applications can be made without changing the gist of the present invention.

[0034]

As described above in detail, according to the present invention, it is possible to provide an image monitoring apparatus capable of obtaining the detection result of an intruding object at a fast time interval without changing the detection performance of the intruding object as compared with the conventional case.

[Brief description of drawings]

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

FIG. 2 is a timing chart showing how images are captured and analyzed when a change area is extracted from two continuous images.

FIG. 3 is a timing chart showing how images are captured and analyzed when a change area is extracted from three consecutive images.

FIG. 4 is a configuration diagram showing an example of an image monitoring device.

FIG. 5 is a timing chart showing how images are captured and analyzed when a change area is extracted from two continuous images in the related art.

FIG. 6 is a timing chart showing a state of image capture and analysis when a change area is extracted from three conventional continuous images.

[Explanation of symbols]

1 ... ITV camera (imaging means), 3 ... processing device, 5
...... Display device, 6 ... Alarm device, 7 ... VTR, 8 ...
Monitoring area, 10 ... Sampling pulse generation circuit, 11
...... A / D converter, 12 ...... Image memory, 13 ...... CP
U, 14 ... Differential binarization circuit, 15 ... Differential binarization image memory, 16 ... Image memory management circuit.

 ─────────────────────────────────────────────────── ─── Continuation of the front page (72) Inventor Shozo Abe 70 Yanagicho, Sachi-ku, Kawasaki-shi, Kanagawa Toshiba Yanagimachi Factory

Claims (1)

Claim: What is claimed is: 1. An image pickup unit for picking up an image in a monitoring area, an image pickup unit for continuously taking in images picked up by the image pickup unit at predetermined time intervals, and an image pickup unit. When the image capturing time interval of the means is set to Δt, a predetermined calculation is performed between images continuously captured for n × Δt (n ≧ 2, n is an integer). An image monitoring apparatus comprising: a detection unit that detects an intruding object in the monitoring area.