JPS6286990A - Abnormality supervisory equipment - Google Patents

Abstract

PURPOSE:To decrease a malfunction due to a spurious target and to improve remarkably the detection reliability by comparing the picture obtained by a picture input means with a referring picture and deciding the presence and the absence of the abnormality based upon the knowledge for deciding the abnormality stored beforehand. CONSTITUTION:By a detecting area setting means 33, the detecting area of the optional shape is set by using the pointing device such as a light-pen and a graphic tablet while the referring screen is watched. At the time of the actual abnormal supervising, the present picture is inputted from an image pickup device 11 to an input picture memory 21', and a picture processing part 22 extracts the change of the picture from a referring picture memory 24 and an input picture memory 21'. In the referring picture memory 24, the picture of the supervisory area at the time of no abnormalities is inputted from the image pickup device 11 as the referring picture beforehand. From the change of the picture, and the memory contents of a detecting area memory 34 set beforehand, an abnormality deciding means 3 decides at which detecting area the abnormality occurs, and an output means 4 issues the alarm based upon the output from the abnormality deciding means 3.

Description

[Detailed Description of the Invention] (Technical Field) The present invention relates to an image recognition type abnormality monitoring device that detects the presence or absence of an abnormality in an area to be monitored using image input means such as a television camera, and mainly relates to an abnormality monitoring device that detects an abnormality in an area to be monitored. In addition to crime prevention such as theft, it is used for fire detection and accident prevention due to abnormal occurrences in factories.

(Background Art) In a conventional device of this kind, an image processing unit calculates the luminance difference between each pixel of the input direct image and the reference image, and at a certain setting level, two
After converting into a value, the number of pixels in which a luminance difference greater than a set value has occurred is counted, and when the value exceeds a certain set value, it is determined that an abnormality has occurred. Therefore, in addition to malfunctions due to brightness changes caused by shaking of trees widely distributed within the screen, rain, lightning, etc.
Pseudo targets that are difficult to identify using only image processing means, such as household members or guests other than the intruder in an intrusion monitoring device,
It often malfunctioned due to passersby.

(Objective of the Invention) The object of the present invention is to prevent not only malfunctions caused by environmental factors as described above, but also malfunctions caused by small animals such as dogs and cats, and even false targets such as passersby and household members in an intrusion monitoring device. An object of the present invention is to provide an abnormality monitoring device that reduces the number of abnormalities and dramatically improves detection reliability.

(Disclosure of the Invention) FIG. 1 shows a complete diagram of the present invention. In FIG. 1, the image input means 1 includes a visible/near-infrared imaging camera such as a visiphone or CCD, as well as a pyroelectric vidicon-type far-infrared camera that is particularly effective for intruder detection, fire detection, etc. Including an imaging device. In addition to this, a color camera, a wireless camera that wirelessly transmits an image signal, etc. can also be used as the imaging device in the image input means 1. The image signal of the monitoring area captured by the imaging device of the image input means 1 is A/D converted and then sent to the image processing unit V.
It is sent to i2.

An example of an algorithm for image processing in the image processing means 2 is shown in FIG. To explain the operation based on chart 70 in FIG. 2, first, pixel-to-pixel subtraction is performed between a reference image that does not include abnormal signals that is updated at a constant cycle, and the current image that is taken in from the image input means 1 from time to time. The image is converted into an image in which only pixels that have changed in brightness have values. After that, filtering processing using a 3×3 mask is performed to remove noise. Next, slicing processing is performed on each pixel using upper and lower limit values, and only pixels within a certain range are binarized and emphasized. Furthermore, after noise is removed by filtering processing again, labeling processing begins. Of each labeled object, objects with a certain area, ie, a certain number of pixels, or less are removed, and then, for objects with an area larger than a certain area, feature quantities such as the position of the center of gravity, second moment, etc. are calculated. The above procedure is executed for each current image frame, and the extracted object is tracked between frames. sent to.

Next, the abnormality determining means 3, which is a feature of the present invention, will be explained using a specific example. Part C of the abnormality determining means 3 constitutes a so-called expert system. That is, based on the information obtained by the image processing means 2 and the knowledge base 32 stored in advance, the inference unit 31 determines whether there is an abnormality or not (8!). have the ability. The simplest example of an intrusion monitoring device will be explained with reference to FIG. As shown in the figure, it is assumed that the windows of a house are being monitored from the outside with a television camera, and the security area on the screen is set to a security level (O).

Rank and set (1) and (2). In this case, the larger the number of the degree of vigilance, the higher the degree of vigilance required. Now, how the image extracted as a target moves through the warning area set in this way, and depending on its temporal characteristics, whether the target is abnormal (that is, an intruder) or not ( If the rules for determining whether a person is a household member, a passerby, etc.) are stored in the knowledge base 32 as knowledge for determining an abnormality, it is possible to determine whether or not an abnormality exists from the information obtained by the image processing means 2. For example, °
If the target exists only within the window (within alert level (2)), it is a household member, and you should move from alert level (0) to higher alert levels (1) to (2) and stay within alert level (2). It is determined that the person is an intruder. If a single camera has a blind spot depending on the subject to be monitored, it is also possible to install another sensor (such as a human body detection sensor) in the blind spot and make decisions based on rules that also use that information. can.

Furthermore, in another monitoring N&, if the degree of vigilance changes depending on the night and the day (for example, when the day does not require vigilance but the night requires vigilance), another optical sensor or timer is used. It is also possible to determine day and night and determine tg using a rule using that information.

Next, the output means 4 will be explained. This output means 4 has a function of displaying the status when an abnormality determination is made by the abnormality determination means 3, and can adopt various formats. For example, the part where the abnormality has occurred may be displayed blinking or in color on the monitor television, or furthermore, the movement locus of the abnormal part may be displayed. In addition, the printer prints out the location and time of the abnormality, etc.
It is also possible to display different warning dust Xts according to the degree of danger using a buzzer or the like. Furthermore, it is also possible to perform wireless transmission of abnormal signals, wireless transmission of abnormal images, telephone line transmission, etc.

Here, a method for setting a warning area, which is not shown in Fig. f51, will be described. This is set in advance when the device of the present invention is installed in the monitoring area, and is displayed on the screen according to the degree of vigilance required (i.e., vigilance level).
Settings are made using a light pen, a cursor, etc. It is also possible to set up monitoring countermeasures using graphics tablets based on diagrams, photographs, etc.

Although the basic configuration has been described above, various modifications are possible. For example, in order to widen the monitoring area with one monitoring device, it is possible to sequentially switch and use a plurality of image input means. Also, the camera has a zoom function,
If information that appears to be abnormal is obtained, that portion may be enlarged and displayed.

Although the intrusion monitoring device has been described as a specific example of the present invention in FIG. 3, the present invention is also effective in various applications where image monitoring is performed, and the knowledge base ( This can be easily handled by storing rules).

Figure fjS4 is a block diagram showing the first embodiment of the present invention. This embodiment has an intruder determination function. Generally, when an abnormality in a certain place is to be monitored, an image of the monitoring area is captured by the imaging device 11, but the entire monitoring area is not equally dangerous. Therefore, the monitoring fa area is divided into multiple detection areas,
For each detection area, set the degree of risk when an abnormality occurs in that detection area. This is done by the detection area setting means 3.
3, a detection area of an arbitrary shape is set using a pointing device such as a light pen or a graphic tablet while looking at the reference screen. The shape and degree of risk of this detection area are stored in the detection area memory 34. FIG. 5 shows an example of this setting, in which the monitoring area 50 is divided into a detection area 51 with a risk level 1, a detection area 52 with a risk level 2), and a detection area 53 with a risk level 3. Below, the higher the number, the higher the risk.

During actual abnormality monitoring, the current image is input from the imaging device 11 to the input image memory 21°, and the image processing unit 22
extracts image changes from the reference image memory 24 and input image memory 21'. An image of the monitoring area when there is no abnormality is input in advance to the reference image memory 24 from the imaging device 11 as a reference image. The abnormality determination means 3 uses the amount of change in this image and the detection area memory 34 set in advance.
This is to determine in which detection area an abnormality has occurred based on the stored contents. The output means 4 issues an alarm based on the output from the abnormality determination means 3.

At this time, a more appropriate warning can be issued by not only issuing a warning for the occurrence of an abnormality, but also by changing the warning dust depending on the degree of danger. The alarm dust setting memory 41 is used to determine which danger level and which alarm dust alarm is to be issued.
If the alarm is set and the alarm is issued while referring to this memory 41, the alarm can be issued as desired by the supervisor.

Next, the f:pJ2 embodiment of the present invention is shown in FIGS. trJ7
This will be explained based on the diagram. In the previous embodiment, the presence or absence of an abnormality in a certain detection area within the premises was determined and the result of the determination was output, but in this embodiment, for example, a lamp 61 indicating the state of machinery in a factory or the like is used. Consider a case where a detection area 62 is set to surround the lamp 61 for monitoring. At this time, it is abnormal if the lamp 61a lights up and then the lamp 61b lights up, but the lamp 61
Let us assume that there is no abnormality when the lamp 61a and the lamp 61b are turned on at the same time. In such a monitoring target,
Even if an abnormality (lighting of a lamp) occurs in the detection area, an alarm cannot be issued immediately. Therefore, in this embodiment, a configuration is adopted in which the degree of risk is determined based on the change in abnormality in the detection area. FIG. 6 shows the configuration of the main parts of this embodiment.

The detection area memory 34 and the image processing section 22 are the same as those in the previous embodiment. In this example, due to abnormal changes in the detection area,
Information about what kind of change would be considered abnormal is set in advance in the change pattern storage means 35. The abnormality determination means 3 uses the change pattern storage means 35 in addition to the detection area setting memory 34 and the image processing section 22 to detect a preset change pattern when an abnormal change in the detection area matches a preset change pattern. Output the degree of risk.

With the above configuration, it is possible to determine the degree of risk based on the abnormality change pattern in the detection area as described above.

Next, the @3 embodiment of the present invention will be described based on FIG. This embodiment is an example that is particularly effective for intrusion monitoring among abnormality monitoring. As shown in FIG. 8, it is assumed that an intrusion into a house 71 is to be monitored. At this time, a detection area 74 that remotely surrounds the house 71 is defined as a detection area with a risk level of 1, and a detection area 75 including the vicinity of the house 71 and the house 71 itself is defined as a detection area with a risk level of 2.
The detection area is set as the detection area, and the other area is set as the detection area with a risk level of 0. At this time, when an object is detected, the object moves from a detection area with a danger level of O to a detection area with a danger level of 1, and then passes through a detection area with a danger level of 2.
If the object moves into the detection area, it is determined that an abnormality has occurred (an intruder is present). If such an abnormality determination means is used, the number of occurrences of false alarms will be reduced.

Conventional devices of this type focus only on changes in brightness within the detection area, so for example, changes in brightness due to light leaking from the window 76 or shaking of the tree 77 are also judged as abnormal occurrences, resulting in false alarms. However, according to the abnormality determination method of the present invention, a change in brightness only in a detection area with a risk level of 1 or a change in brightness only in a detection area with a risk level of 2 does not indicate an abnormality has occurred. Since no determination is made, the occurrence of false alarms is suppressed. Furthermore, a particularly effective means for intrusion monitoring is to use the movement of objects as information for determination. In other words, as in the past, it is possible to detect not only the abnormality in a certain area, but also the object that actually intruded by remembering which object caused the abnormality in a certain area and determining intrusion from that information. can only be detected.

Furthermore, a fourth embodiment of the present invention will be described based on FIGS. 9 and 10. Let us consider a case where a picture 81 in a museum or the like is to be monitored, as shown in Figure fjS10. In this case, while the museum is open, it is only necessary to detect abnormalities in the detection area 83 of risk level 1, but after the museum is closed, it is necessary to also detect intrusions into the museum itself. Passageway 82 must also be a sensing area. FIG. 9 shows the configuration of the main parts of this embodiment. By the detection area setting means 33,
The contents of the plurality of detection area memories 34 are set. Switcher 3
6 selects which detection area memory 34 to use using an external signal such as a tarok signal from a digital clock or an illuminance signal from an illuminance meter that measures external brightness, and selects one of them. The detection area memory 34 is connected to the abnormality determination means.

Next, a fifth embodiment of the present invention will be described based on FIGS. 11 and 12. In this embodiment, an abnormality is detected not only by the troublesome change in brightness of the input image but also by using the pattern of the change in brightness. The configuration of this embodiment is shown in FIG. As in each of the embodiments described above, only the changes in the image are extracted by the imaging device 11, the reference image memory 24, the input image memory 21', and the image processing section 22.

As mentioned above, in the conventional example, the occurrence of an abnormality was determined based on whether this change exceeded a certain threshold value, but in this embodiment, the normal image change pattern when no abnormality occurs and the normal image change pattern when an abnormality occurs The abnormality determining means 3 determines the presence or absence of an abnormality by using the change pattern storage means 35 that stores the change pattern of the image and the change amount of the image obtained by the image processing section 22. If an abnormality is determined, the output means 4 generates an alarm.

FIG. 12 shows an example of a monitoring target, in which a door 92 is included in an image 91 captured by the imaging device 11, and an abnormality of this door 92 (for example, presence of an intruder) is monitored. It is something that exists. In such a case, in the conventional example, the detection area 93
If there was a change in brightness, an alarm would be issued indicating that an abnormality had occurred. However, especially in a factory or the like, there may be a lamp 94 above the door 92 that is the object of monitoring that is constantly blinking. In this case, even if there is no abnormality, a change in brightness occurs within the detection area 93, so the conventional example cannot detect an intruder in such a case. In this embodiment, it is possible to detect an intruder in such a case, and the pattern of brightness change due to blinking of the lamp 94 is stored in advance in the change pattern storage means 35, and the image processing unit 22 Even if there is a change in brightness in the output of the lamp 94, if it is determined that the change in brightness is due to the blinking of the lamp 94, it will not be determined that an abnormality has occurred. Only when it is determined that this is not due to blinking, it is determined that an abnormality has occurred (an intruder is present).

Next, a sixth embodiment of the present invention will be described based on FIGS. 13 and 14. This embodiment is an apparatus for detecting an abnormality in a region where the image when there is no abnormality repeats a certain change as in the previous embodiment, and is further configured to be able to store a plurality of change patterns. Image processing section 2
The steps up to obtaining the change in the image from 2 are the same as in the previous embodiment. This image and the change pattern storage means 3
The similarity calculating means compares the N change patterns given in 5 with the non-abnormal time and calculates the degree of similarity with the pattern that is most similar to the current t minute among the N change patterns. 3
Find it in 7. The comparison means 38 compares this similarity value with a certain threshold value, and if the similarity is small, it is determined that some kind of abnormality has occurred since it is not similar to any change pattern. By adopting such a configuration, for example, the 14th
As shown in the figure, it is possible to monitor a machine 97 that is constantly reciprocating on a rail 96 within a detection area 95.

As described above, when the change pattern when there is no abnormality is a certain fixed change pattern, the abnormality can be detected by the methods of the fifth and sixth embodiments.

Next, a seventh embodiment of the present invention will be described based on FIGS. 15 and 16. For example, assume that a right turn prohibited area is to be monitored at a crossroads 81 as shown in FIG. In such a case, it is not possible to identify from the current image alone whether a certain car is turning right like the right-turning car 82 or going straight and stopping like the straight-going car 83. FIG. 15 shows the main parts of a device that determines an abnormality from a time-series change pattern in this way. The process up to the point where the image change amount is obtained from the image processing section 22 is the same as in each of the embodiments described above. In this embodiment, this is stored in N image memories 39.

The memory contents of this image memory 39 are compared with the memory contents of the change pattern memory y, 35 which stores change patterns in normal cases and change patterns in abnormal cases, and the abnormality determining means 3 determines the abnormality. It is something to judge.

In the seventh embodiment, the image processing means uses the absolute difference
Although the image processing means includes a value circuit and a binarization circuit, if the image processing means is more advanced and can obtain information such as the position, size, and velocity of an object, this information Abnormalities can be detected accurately based on the change pattern.

Furthermore, if a change pattern is set that allows the behavioral patterns of the householder and the intruder to be distinguished, it is possible to distinguish between the householder and the intruder.゛Next, an eighth embodiment of the present invention will be described based on FIGS. 17 and 18. The present invention divides the detection area into a plurality of areas independently of the detection area, sets attributes for each area, and takes into account not only brightness changes but also attribute information when determining abnormalities. , which attempts to accommodate the diversity of monitoring areas. FIG. 17 shows the configuration of this embodiment. Imaging device 11, reference image memory 24, input image memo +721', image processing section 22) Output child y, 4 is the same as in each of the above embodiments.2 In this embodiment, the first
Consider a case where intrusion into the garden of a house is detected by abnormal occurrence as shown in Figure 8. A site including a house 71, a fence 72) and a tree 77 is set as a detection area 78, and an intrusion into this area is detected. This detection area 78 is set in the detection area memory 302 using the area setting means 301. In the conventional method, abnormalities are detected only by changes in brightness within the detection area, so changes in brightness due to blinking lights inside the house 71 or changes in the brightness caused by blinking lights in the house 71 or trees 77
There were cases where malfunctions occurred due to changes in brightness due to shaking. Further, if an intruder hides behind a tree 77, there is a problem that the alarm is canceled at that point. This embodiment improves this point by providing an attribute area separately from the detection area, describing the properties of each area as an attribute, and
By using this attribute information, false alarms and missed alarms are reduced.

For example, in the example of diagram f518, house 71. and trees 77, an attribute area 79 that is different from other sites.
a, attribute area 79b, and so on, the area setting means 301
is set and stored in the attribute area memory 303.

The attributes of each attribute area are stored in the attribute database 304 in one-to-one correspondence with the attribute area.

By making the above settings, during actual monitoring, for example, when the tree 77 shakes, the resulting brightness change and the attribute database 30
From the information No. 4, it can be determined that this brightness change is caused by the shaking of the tree 77, and it is possible to prevent the occurrence of false alarms. Furthermore, even if the intruder moves in the direction of the tree 77 and eventually disappears from the screen, it is determined that the intruder has simply hidden behind the tree 77 on the table, and the alarm continues. be able to.

Next, a ninth embodiment of the present invention will be described based on FIG. 19. In the present embodiment, an auxiliary sensor 5 is provided in the abnormality determination hand Fi3 in the abnormality monitoring device having the image input means 1, the image processing means 2, the abnormality determination means 3, and the output means 4.
The auxiliary sensor 5 is connected to the blind spot of the image input means 1.
By arranging this, information that cannot be obtained through image processing can be provided to the abnormality determining means 3. For example, consider an example in which a human body detection sensor is used as the auxiliary sensor 5 in this embodiment. A human body existing in a blind spot of the il image input means 1 does not appear on the input image.

Therefore, it is not possible to determine that an abnormality has occurred based only on the image processing results. If a human body detection sensor is placed in this blind spot, the presence or absence of a human body can be determined by the operation of this sensor. In addition, in this embodiment, the auxiliary sensor 5
Consider an example in which an infrared sensor is used. In this way, the human body existing in the blind spot of the image input means 1 and
Even a fire that occurs in a blind spot can be determined to be an abnormal occurrence.

FIG. 20 is a block diagram of a main part of a tenth embodiment of the present invention. This embodiment is particularly designed to update the reference image in the image (1 process-f?,!?2). 20
The image processing means 2 shown in the figure has a current image memory 21 and a reference image memory 24. The image processing unit 22
For example, it includes a subtraction circuit and a binarization circuit, and both memories 21.
After subtracting 24 luminance data between pixels, the data is binarized using an appropriate threshold value. The abnormality determining means 3 is a means for receiving the output of the image processing means 2 and determining an abnormality, as shown in the double series. The output of the abnormality determining means 3 is input to the AND circuit 27 via the NOT circuit 25. The output of the timer 26 is input to the other input of the AND circuit 27,
This timer 26 defines the update cycle of the reference image. The memory transfer circuit 23 is a circuit that transfers the stored contents of the current image memory 21 to the reference image memo +724, and the 6-AND circuit 27, which uses the output of the AND circuit 27 as a memory transfer command signal, outputs the output to the NOT circuit 25. , that is, when the abnormality determination means 3 does not determine that an abnormality has occurred, the memory transfer circuit 23
The device operates by sending a transfer command signal to.

FIG. 121 is a time chart for explaining the operation of the embodiment shown in FIG. The period is timer 2
6 shows the update cycle. When there is no abnormality detection signal, the reference image is updated according to the update cycle of the timer 26, but when an abnormality detection signal is generated, as in the case of L"n, the reference image is not updated. In this way, in this embodiment, the reference image is imported only when it is confirmed that no abnormality is observed on the image, so when images taken at regular intervals are automatically used as the reference image. Compared to , it is possible to effectively detect abnormalities without overlooking abnormalities, especially abnormalities that change slowly over time.

FIG. 22 is a block diagram of a main part of an eleventh embodiment of the present invention, in which reference image updating is further improved to further improve detection reliability.

In this embodiment, compared to the previous embodiment, the monostable multi-circuit 28
The configuration is the same as that of the previous embodiment except that an inter-pixel average value calculation circuit 29 is added. The monostable multi-circuit 28 extends the output pulse of the timer 26 and generates a pulse having a certain time width at a constant period. The time width of this pulse is usually set to an integral multiple of the current image capture cycle.

The inter-pixel average value calculation circuit 29 is activated by the output signal of the AND circuit 27, and is a calculation circuit that adds a plurality of consecutive current images and then averages them. For example, if no abnormal signal is found in five consecutive current images, the average value between each pixel of the five current images is calculated, and the result is updated as a reference image. This update typically occurs every few minutes, depending on the use of this type of device.

With the above configuration, in this embodiment, there is no possibility of missing an alarm for abnormalities that change slowly over time, and at the same time, fine brightness changes due to shaking of trees, etc. can be averaged over time. Since the image is used as a reference image, malfunctions caused by these factors can be extremely reduced.

FIG. 23 is a chart of a main part 70 of the twelfth embodiment of the present invention, in which the image processing element Pi2 is provided with an area determination function. After the image signal of the monitoring target captured by the image input means 1 such as a television camera is A/D converted,
Stored in current image memory. At this time, the data is also input to the reference image memory at regular intervals, and a luminance comparison between pixels (inter-pixel area g) is performed with the current image memory. Next, after binarization is performed depending on whether the brightness difference exceeds a certain set level, a known labeling algorithm is used to label the changing part of the image (i = 1 to 'rt), and each labeled cluster is The area, that is, the number of pixels, is determined. After that, area comparison is performed for each cluster with a preset area threshold, and a certain range SL≦Si≦S, H(
Here, i is the cluster number, Si is the first cluster area, S,,S.

are the minimum and maximum values of the set area, respectively), and only those clusters that fall within the set area values are output as abnormal signals.

This makes it possible to prevent malfunctions caused by changes in brightness over a small area such as swaying trees, rain, electrical noise, etc. that are widely distributed within the screen.

Next, Figure $24 is a 70-chart of the thirteenth embodiment of the present invention, and in this embodiment, the area determination function in the image processing means 2 is further improved. In this embodiment, instead of comparing the areas of the clusters whose areas were determined using the same threshold value as in the previous embodiment, the threshold value is changed according to the barycentric coordinates of each cluster. Generally, when carrying out the technique of the present invention, the image input means 1, such as a television camera, is tilted diagonally downward from a high place, as shown in FIG. 25, in order to monitor a wide field of view. It is set up so that you can see it. At this time, of the ground (floor surface) in the field of view of the camera, the near side is displayed at the bottom of the screen, and the far side is displayed at the top of the screen, but the distance between the near side and the far side is
Because the distance between the ground and the camera is different, even if the object is the same, the one in the foreground will be larger and the one further away will be smaller on the screen. Therefore, it is not preferable to compare the areas of clusters generated on the entire screen using the same threshold value. In this embodiment, in view of this point, the detection sensitivity is made constant regardless of the position of the object to be monitored within the warning area, and the influence of various malfunction factors is reduced.

below,? A method for setting a variable threshold value will be described according to FIG. 1S25 and FIG. fIIJ26. In the fjS25 diagram, the distance R0 between the camera and the point where the optical axis of the camera intersects with the ground is determined by the following equation.

Ro= H* cosecθ Where, H: Height of the camera θ: Angle between the camera light pongee and the ground Also, the actual distance of the upper limit of the screen 11 R)l and the actual distance RL of the lower limit of the screen are calculated by the following formula. Given.

RH==H11cosec(θ-α/2)RL=H
-cosec (θ ten α/2) where α: Viewing angle of the camera Next, take the X axis as shown in Figure 26, and the lower part of the screen is X =
0, and when X=A, the actual distance R of a point on the screen is generally given by R=H-coscc(θ-α(X/A--5-)). Since the size of an object on the ground that appears on the screen is inversely proportional to the square of the distance, the center of gravity position determined for each cluster is The area of each cluster may be compared using the new set upper limit value 3Hl and lower limit value S% obtained by performing the determined correction, that is, by multiplying by 1/R2. in fact,
A coordinate-distance correction coefficient conversion table may be prepared in memory without performing calculations such as calculating 1/R2.

This makes it possible to finely set the upper and lower limits of the area when determining whether or not it is an abnormal signal, for example, whether it is an intruder or a small animal such as a dog or cat.
This greatly improves detection reliability.

FIG. 27 is a block diagram showing a fourteenth embodiment of the present invention. This embodiment has an automatic setting function for the binarization level. The image of the monitoring area is captured by the imaging device rIi11.
The image is captured by the input image memory 21' and input to the input image memory 21'. The reference image memory 24 stores in advance an image of the monitoring area when there is no abnormality. The absolute difference value circuit 201 calculates the absolute difference value between pixels between the reference image memory 24 and the input image memory 21'. This absolute difference value is input to the binarization circuit 203, compared with a predetermined threshold value, and binarized. The threshold value for binarization in the binarization circuit 203 is input from the threshold memory 202. The abnormality determination means 3 receives the binarized signal obtained by the binarization circuit 203 and detects an abnormality from this signal. For y4 normal detection, for example, a means can be used that counts the signal obtained from the binarization circuit 203 and determines that an abnormality has occurred if the count exceeds a certain value. Output means 4
is to output a message to that effect when an abnormality is detected.

In such a device, setting a threshold for binarization is important. In this embodiment, the threshold value is determined by utilizing the fact that the change in the image when an abnormality occurs is larger than the change in the image when no abnormality occurs. in particular,
Images of the monitoring area when there is no abnormality are input N times, and a threshold value is determined based on the images. Let fip be the brightness at a certain coordinate P at the time of the i-th image input. If the change in the image when there is no abnormality follows a normal distribution and N is sufficiently large, μp = (1/N) white fip ...■σp2
= (1/N) eclipse fip2 - μp2...■ By the formula, the brightness of a pixel when there is no abnormality at any point in time is r
If p, − +rp−μp+ <kσp ...■ becomes (
It is well known that k can be found with a probability of 1-ψ). From these facts, input the image N times when there is no abnormality, calculate μp and σp from formulas ■ and ■, and create a reference image such that the brightness at coordinate P is μp.
If kσp is a threshold value, then the probability that a change at point Q which has caused a change exceeding the threshold value is not caused by 'A constant' is ψ from equation (2).

From the above, for example, N=100. If = 3, then
A sufficiently reliable reference image and threshold value can be obtained as an abnormality monitoring device. Specifically, it can be calculated using a microcomputer, and a 70-chart for this purpose is shown in FIG. In this 70-chart, r
p is the brightness of the input image of the locus Pj, p, and S+pySzp is
These are variables for determining μp and σp.

Next, a fifteenth embodiment of the present invention will be described based on FIG. 29. In the previous embodiment, the output from the binarization circuit 203 was directly input to the abnormality determination means 3, but in this embodiment, in order to perform more advanced image processing, the output from the binarization circuit 203 is input into the abnormality determining means 3. It creates a valued image and performs image processing such as noise processing. Imaging device 11, reference image memory 24, input image memory 21'', absolute difference circuit 20
1. The threshold memory 202 and the binarization circuit 203 are the same as those in the previous embodiment. In this embodiment, a binarized image created from the output of the binarization circuit 203 is input to the binarized image memory 204. The image obtained at this time is an image containing errors with a probability of ψ at each point. The image processing circuit 2 () 5 performs appropriate image processing on this image as exemplified below. For example, in the case of intrusion monitoring, when an abnormality occurs, the brightness changes at all points within a certain area. If the process is generally called isolated point removal, the error rate ψ can be further reduced. It can be lowered. Using this image processing result, an abnormality is determined by the abnormality determination means 3 as in the previous embodiment, and the determination result is outputted by the output means 4.

Next, a sixteenth embodiment of the present invention will be described based on FIG. 30. In this embodiment, the image processing means 2 is provided with a function of counting objects. In the apparatus shown in FIG. 30, first, the difference image between the reference image and the input image is
Binarization is performed in the digitization device 211 using a preset threshold value a.

Next, a labeling device 211 applies a well-known labeling method to this binarized image to label it to identify the object, and a comparing device 213 applies a label whose area is a predetermined threshold value. The number of objects whose number is greater than or equal to 1 is counted, and the number is compared with a predetermined threshold value C. If the number of objects is equal to or greater than the threshold C, the binarization threshold a is changed to an even larger value, and the binarization process and labeling process are performed again. As a result, objects such as rain that have a small difference in brightness from the background are removed.
Therefore, the abnormal portion can be extracted accurately, and more accurate information can be provided to the abnormality determining means 3.

Furthermore, what about the 17th embodiment of the present invention? This will be explained based on FIG. 1S31. In this embodiment, the number of objects is the threshold C
The process is the same as the previous example except that when the above is the case, the area threshold value is changed to a larger value and the labeling process is performed again. As a result, objects with small areas such as rain and snow are removed, and more accurate information can be supplied to the abnormality determining means.

FIG. 32 is a block diagram showing an 18th embodiment of the present invention. This embodiment has an image input means 1 using a multi-channel system.

In the figure, the abnormality monitoring device main body 234 is ? It includes an image processing means 2, an abnormality determination means 3, and an output means 4 in the lSi diagram. A pair of a reference image memory 12 and a comparison circuit 13 is arranged after each of the n imaging devices 11. Reference images of each monitoring area are recorded in advance in the reference image memory 12! has been done. The comparison circuit 13 compares the input image and the reference image, and if there is a change in brightness in the input image, outputs a change detection signal to the channel switching control circuit 14, and also outputs a change detection signal to the comparison result image (generally, the difference absolute value image) is output to the multiplexer 15.

Next, these operations will be explained. Imaging Apparatus] 1. Reference image memory 12) The blocks including the comparison circuit 13 are collectively called channels. Each channel from 1 to n operates at all times,
Suppose that an abnormality has now occurred on channel i. At this time, a change detection signal is transmitted from the channel i comparison circuit 13 to the channel switching control circuit 14, and the channel switching control circuit 14 selects the channel to the multiplexer 15 so as to connect channel 1 to the abnormality monitoring device main body 234. It outputs a signal and notifies that the image of channel i has been input to the abnormality monitoring device main body 234. The channel switching control circuit 14 is thereafter controlled by the abnormality monitoring device main body 234.

The abnormality monitoring device main body 234 instructs the channel switching control circuit 14 to input channel 1 until the abnormality processing of channel i is completed, and after the abnormality processing of channel i is completed, the control of the channel switching control circuit 14 is performed. Release. If the anomaly does not exist on any channel,
There is no need to enter any images. If brightness changes occur in two or more channels simultaneously, the abnormality monitoring device main body 234 selects only those channels and processes them while switching.

As described above, by processing only channels with brightness changes, the time during which processing cannot be performed for each channel (dead time) can be dramatically reduced compared to monitoring by time sharing method while constantly switching n channels. This can prevent the inconvenience of overlooking an abnormality that occurs in another channel while monitoring one channel.

FIG. 33 is a diagram showing a nineteenth embodiment of the present invention. This embodiment has an image input means l having an impulse light detection function.

The apparatus shown in FIG. 33 is a plurality of (n units) imaging apparatus
1, a multiplexer 15 that selects the image signal of the imaging device 11, an A/D converter 16 that quantizes the analog image signal output from the multiplexer 15, and an overflow signal (OV F ) of the A/D converter 16. A counter 18 that counts the clock (CL K ) dated at
Contains. Preferably, the A/D converter 16 is equipped with an overflow terminal that generates an overflow signal when the input signal exceeds a predetermined range. No A/
Even when a D converter is used, the digital output may be digitally compared with the full range value of the input signal, and the comparison output may be used as an overflow signal. The abnormality monitoring device main body 234 (hereinafter referred to as "main body 234J") includes the image processing means 2, the abnormality determination means 3, and the output means 4 shown in FIG.

The operation of this embodiment will be explained. Input images from the n imaging devices 11 are normally selected sequentially by the multiplexer 15 in response to a command from the main body 234, and are sent to the A/D converter 1.
6, the signal is A/D converted and input to the main body 234. Suppose now that channel i receives abnormal impulse light due to lightning, flash, or the like. With this impulse light,
The A/D converter 16 receives an overflow signal (OV F )
occurs. This overflow signal causes the date 1"t to rMp and the counter 7 (CL, K) to
1m is input, and the counter 18 starts counting clocks. This clock may be the same as the image sampling clock supplied to the A/D converter 16. Now, an overflow signal is output when an abnormal impulse light is included, but if it continues for more than one horizontal period, this image becomes an "abnormal image", that is, an unnecessary image that should not be processed by the main body 234. It should be rejected as an image. The counter 18 described above is provided to measure time to determine whether or not it continues for one horizontal period or more. The overflow signal (OVF') of this counter 18 is transmitted to the main body 234.
The main body 234 detects that the image is an "abnormal image" based on this overflow signal. If the image to be processed has, for example, 512×512 pixels, the counter 18 only needs to have 9 bits (IFFII). Note that the counter 18 is reset by a horizontal synchronization signal.

Now, the overflow signal (OV
The main body 234 that detected the "abnormal image" by F')
Processing/judgment of that image is canceled. Then, the multiplexer 15 is controlled so as to input this canceled channel 1 again. With this configuration, it is possible to monitor a channel in which an ``abnormal image'' has occurred without skipping it, and it is possible to reduce the occurrence of dead time.

Figure @34 is a block diagram of the main parts of the @20 embodiment of the present invention. This embodiment has an image input means 1 equipped with a gain setting function. The device shown in FIG. 34 includes a plurality of reference voltage sources V r + * V r 21 . . . and corresponding analog switches sw, , sw7 .・
...and gain setting memory 1 to control them.
01 and a decoder 102 that decodes the output of this memory 101. The gain setting memory 101 has a one-to-one correspondence with pixels like a graphic memory, and if the image is, for example, 512X512 pixels, this memory is 512X512X? It becomes 71 bits. This initial bit depends on the number of areas set; for example, if eight areas are required, it will be 3 bits. Since this memory is set in advance by a graphic tablet or light ben, the shape of the area can be set to any shape.

Suppose that we are monitoring a scene including a street light in front of a building at night, as shown in Figure 35. The area within the dotted line near the street light is a bright area. For this scene, an area "1" is set in advance according to the image as shown in FIG. 36. When inputting an image of the scene, the gain setting memory 101 shown in FIG. 34 is read out. The read data is input to the decoder 1021m input Za, 7': I-G 10
Only one of the 2" outputs of 2 is turned on, the analog switch S Wi corresponding to that output line becomes conductive, and the reference voltage source Vri is input to the A/D converter 16. The gain is set. In the case of the scene shown in Fig. 35, the area of "0" in Fig. 36 is emphasized with a high gain, and the area of 01'' is suppressed with a low gain, so that the entire image is This makes it possible to detect with uniform sensitivity. In this embodiment, the brightness level is adjusted by changing the reference voltage of the A/D converter 16, but it is also possible to adjust the gain by changing the gain of the analog amplifier.

FIG. 37 is a block diagram of essential parts of a tjfJ21 embodiment of the present invention. In this embodiment, the gain setting function in the image input means 1 is further improved.

In this embodiment, a plurality of A/D converters 16 with different reference voltages are provided, and the outputs of the A/D converters 16 are analyzed. Switch SW 1. This is a method of switching with S W 2 t..., and if this method is adopted, the digital signal will be switched instead of the analog voltage signal as in the previous embodiment, so the switching time will be reduced. This has the advantage that noise generation is suppressed.

FIG. 38 is a block diagram showing a twenty-second embodiment of the present invention. In this embodiment, the image input means 1 is provided with a warning function for areas where the illuminance rapidly changes. Input images from the imaging device 11 are input to a plurality of A/D converters 16.
(assumed to be 'rL). These n A/D converters 16 each have different reference voltage sources Vrl and Vr2.
．． ..., Vriw-tVrn, and are set to different gains. Here, if the i-th A/D converter 16 (hereinafter referred to as A/D converter 16i) is set to an intermediate gain, normally this A/D converter 16i and the reference image The absolute value of the difference between the two is used for subsequent abnormality monitoring. Now, if a high-luminance area caused by car headlights or the like suddenly appears on the screen, the difference between the input image and the reference image will rapidly increase. This difference data is obtained by the subtraction circuit 114, and the multi-stage comparator 1
13, and the gain A/D according to the difference data.
The converter 16 is selected by the multiplexer 111 and input to the differential absolute value circuit 117 at the subsequent stage. The multi-stage comparator 113 has a plurality of reference voltages VS++VS2t...t v
It has n threshold values based on sn, determines which gain correction is to be performed on the input difference data, and controls the multiplexer 111 for gain selection and the multiplexer 112 for reference image correction. The reference image correction circuit 116 corrects the reference image by multiplying the reference image data by a coefficient (Crt, . . . , Crn) that is the same as the gain change ratio as the gain of the input image is changed. If the A/D converter 16 with a low gain is selected due to the light from the headlights of a car and the gain is 0.8 times, a gain correction of 0°8 times is also applied to the reference image. conduct.

On the contrary, there may be cases where gain correction of 1 or more is performed. For example, when a nighttime light suddenly goes out, this applies to increasing the gain in a darkened area.

With the above configuration, the gain is adjusted in real time even if the brightness at any location within the screen changes rapidly, so that the sensitivity within the screen becomes uniform and the detection reliability of the device is improved.

FIG. 39 shows an example of the external appearance of the system when the present invention is embodied as an intrusion warning device, and FIG.
The figure shows an overview of information processing in the system. As shown in the figures above, this system photographs the surveillance area with a television camera, compares the input image with a reference image, and calculates and outputs the difference image, thereby extracting images of intruders. The monitoring area is divided into multiple detection areas using an image processing unit that obtains information such as the location, size, and speed of the person, and a pointing device such as a graphic tablet, and each detection area has a different degree of risk R15k.
(0), R15k(1), R15k(2), .= are assigned by the area setting unit, and information such as the intruder's position, size, speed, etc. obtained by the image processing unit and set by the area setting unit. Input information on the degree of risk of each detection area as "facts" and compare this with "rules" stored in advance in a library of risk assessment rules, and make inferences in the form of questions and answers. It has an intruder determination unit that determines the presence or absence of an intruder through processing, and an additional 8
! Functions include recording images on a VTR, printing out monitoring results on a printer, displaying the intruder's location and intrusion trajectory on a CRT, and emitting an alarm sound from a speaker and turning off a lamp when there is an intruder. arouse attention,
Transmit images containing intruders via optical fibers or telephone lines 8! It is something that has the ability.

Figures 41 to 48 are explanatory diagrams illustrating the range of application of the abnormality monitoring device according to the present invention for reference. Figure 43 shows night theft monitoring for self-employed people, Figure 44 shows theft and crime prevention of museum exhibits, Figure 45 shows crime prevention at airports, and Figure 46 shows fire detection. , $47 shows an example in which the abnormality monitoring device of the present invention is applied to the monitoring of robots and automatic guided vehicles in factories and warehouses, and FIG. 48 shows the application of the abnormality monitoring device of the present invention to the safety monitoring of children.

In each of the above figures, the frame-enclosed figure is an example of an image of the monitoring area shaded by a television camera. Furthermore, symbols such as R(0), R(1), and R(2) exemplify the degree of risk set in each area.

(Effects of the Invention) As described above, in the present invention, the image processing means mainly prevents malfunctions caused by various environmental factors, and the abnormality determination means can reduce malfunctions caused by ve-like targets. This has the effect of dramatically improving reliability compared to conventional devices.

[Brief explanation of drawings]

FIG. 1 is a claim correspondence diagram showing the basic configuration of the present invention, fj
Figure S2 is a flowchart showing the image processing algorithm as above, Figure t53 is an explanatory diagram for explaining the abnormality determination algorithm, Figure 14 is a block diagram of the ttSi embodiment of the present invention, and Figure vJ5 is a diagram for explaining the operation of the same as above. Explanatory diagram, 1
Figure 6 is a block diagram of the main part of the second embodiment of the present invention, Figure t5T is an explanatory diagram for explaining the operation of the same as above, and Figure 8 is an explanatory diagram for explaining the operation of the third embodiment of the invention. , FIG. 9 is a block diagram of the main part of the fourth embodiment of the present invention, FIG. 10 is an explanatory diagram for explaining the same operation as above, FIG. 11 is a block diagram of the fifth embodiment of the present invention, and FIG. The figure is an explanatory diagram for explaining the same operation as above, FIG. 13 is a block diagram of the main part of the sixth embodiment of the present invention, FIG. A main part block diagram of the fjS7 embodiment of the invention, FIG. 16 is an explanatory diagram for explaining the operation of the same as above,
FIG. 17 is a block diagram of the eighth embodiment of the present invention, FIG. 18 is an explanatory diagram for explaining the same operation as above, FIG. f519 is a block diagram of the ninth embodiment of the present invention, and FIG. FIG. 521 is a time chart for explaining the operation of the same as above, FIG. 24 is a main part flowchart of the embodiment, FIG. 24 is a flowchart of main part 7 of the 13th embodiment of the present invention, FIG. 25 is a side view for explaining the camera mounting state in the same embodiment, and FIG. 26 is the same as above. FIG. 27 is a diagram showing the correspondence relationship between on-screen coordinates and actual distance in the embodiment of fpJ of the present invention.
28 is a block diagram of the 14th embodiment of the present invention, FIG. 28 is a 70-chart for determining the threshold value in the same embodiment, FIG. 29 is a block diagram of the 15th embodiment of the present invention, and FIG. 30 is a 16th embodiment of the present invention. The main part block diagram of the example, FIG.
jS17 embodiment, FIG. 32 is a block diagram of the 18th embodiment of the present invention, and FIG. 33 is the 19th embodiment of the present invention.
FIG. 34 is a block diagram of a main part of the 20th embodiment of the present invention, FIG. 35 is a diagram showing an example of an input image in the above embodiment, and FIG. 36 is a gain diagram in the above embodiment. Diagram showing an example of the memory contents of the setting memory, @3
FIG. 7 is a block diagram of main parts of the 21st embodiment of the present invention, and the 38th embodiment
The figure is a block diagram of main parts of the twenty-second embodiment of the present invention, FIG. 39 is a schematic configuration diagram when the present invention is embodied as an intrusion warning device, FIG. 4
1 to 48 are explanatory diagrams illustrating different uses of the present invention, respectively. 1 is an image input means, 2 is an image processing means, 3 is an abnormality determination means, and 4 is an output means.

Claims (28)

[Claims] (1) An image input means that images the monitoring area and quantizes the image signal; an image processing means that compares the image obtained by the image input means with a reference image and obtains the information necessary for abnormality determination; The apparatus is characterized by comprising an abnormality determining means for determining the presence or absence of an abnormality based on the information obtained by the image processing means based on the knowledge for determining the abnormality, and an output means for outputting the determination result. Abnormality monitoring device. (2) In the device according to claim 1, the knowledge for abnormality determination is based on the temporal information of extraction targets after image processing in multiple levels of warning areas preset on the screen for each monitoring area. An abnormality monitoring device characterized in that the abnormality monitoring device is written in the form of a rule for determining the presence or absence of an abnormality from transition characteristics. (3) In the device according to claim 1, the knowledge for determining an abnormality is described including a rule for determining the presence or absence of an abnormality based on information from other sensors installed externally. An anomaly monitoring device characterized by: (4) In the device according to claim 1, the abnormality determining means includes a risk level setting means for dividing the monitoring area into a plurality of detection areas and setting a unique risk level for each detection area; and a risk determination means for determining a plurality of danger degrees based on the settings of the degree setting means and the information obtained by the image processing means, and the output means is adapted to determine a plurality of danger degrees determined by the abnormality determination means. An abnormality monitoring device characterized in that it is a means for outputting a plurality of alarm levels. (5) The apparatus according to claim 4, wherein the risk level determining means is a determining unit that determines the level of risk based on a pattern of changes in the occurrence of abnormalities in a plurality of detection areas. Device. (6) In the device according to claim 5, the change pattern of abnormality occurrence in the plurality of detection areas is a change pattern in which the detected object moves from a detection area with a low risk to a detection area with a higher risk. An abnormality monitoring device characterized in that the risk level determining means is a determining means that determines that there is an intruder when the change pattern occurs. (7) In the device according to claim 4, the risk level setting means is a setting unit that sets a plurality of detection areas of arbitrary shapes while looking at the screen, and assigns a unique risk level to each detection area. An abnormality monitoring device characterized by: (8) The device according to claim 4, characterized in that the risk level setting means includes a risk level switching unit that switches between a plurality of risk levels set for each detection area in accordance with an external signal. Abnormality monitoring device. (9) The apparatus according to claim 1, characterized in that the abnormality determining means includes change pattern identifying means for identifying a normal change pattern of the image and a change pattern when an abnormality occurs. Abnormality monitoring device. (10) In the apparatus according to claim 9, the change pattern identifying means identifies a normal change pattern of the image;
a change pattern storage means for storing a change pattern when an abnormality occurs; and a pattern matching means for comparing a change pattern of the current input image obtained from the image processing means with the change pattern to determine the presence or absence of an abnormality. An abnormality monitoring device comprising: (11) In the device according to claim 10,
The pattern matching means is characterized in that it includes means for storing a plurality of input images obtained from the image processing means in chronological order, and means for determining the presence or absence of an abnormality from a change pattern of the plurality of input images. Abnormality monitoring device. (12) In the apparatus according to claim 1, the abnormality determining means includes a setting means for setting an attribute area having an attribute different from a detection area in which an abnormality is to be detected, and using information on the attribute area. An abnormality monitoring device comprising: determination means for determining an abnormality. (13) In the device according to claim 12,
The setting means is characterized in that it includes a detection area setting means for setting a detection area in which an abnormality is to be detected, an attribute area setting means for setting an attribute area, and an area storage means for storing the detection area and the attribute area. Abnormality monitoring device. (14) In the device according to claim 1, the abnormality determining means includes an auxiliary sensor provided in a blind spot of the imaging device, and a means for determining an abnormality from detection information from the auxiliary sensor. An abnormality monitoring device characterized by: (15) In the apparatus according to claim 1, the image processing means detects a new reference image that is to be updated at a constant cycle, when a significant change from the previous reference image is detected. An abnormality monitoring device comprising means for prohibiting image updating. (16) In the device according to claim 15,
When a new reference image that is to be updated at a constant cycle has no significant change signal from the previous reference image, the image processing means calculates a new reference image by averaging a plurality of consecutive image signals between pixels. An abnormality monitoring device comprising means for updating as a reference image. (17) An abnormality monitoring device according to claim 1, wherein the image processing means includes area determination means having a predetermined threshold value. (18) In the device according to claim 17,
An abnormality monitoring device characterized in that the area determination means is an area determination means in which a threshold value for area determination is set to a different value depending on the position on the screen. (19) An abnormality monitoring device according to claim 1, wherein the image processing means includes automatic threshold setting means for automatically setting a threshold for binarizing the image. (20) In the device according to claim 19,
The automatic threshold setting means includes a means for obtaining a difference image between an input image and a reference image, a means for obtaining an average value and a standard deviation of brightness for each pixel from a plurality of difference images, and a means for calculating an average value and standard deviation of brightness for each pixel from a plurality of difference images. An abnormality monitoring device characterized by comprising: threshold value determining means for determining a threshold value for each pixel from the value and standard deviation. (21) An abnormality monitoring device according to claim 1, wherein the image processing means includes means for counting objects. (22) In the apparatus according to claim 1, the image input means includes a plurality of television cameras, an image preprocessing circuit corresponding to each television camera, and an output of the image preprocessing circuit after the image processing means. a channel switching control circuit that provides a channel selection signal to the multiplexer based on a change detection signal from the image preprocessing circuit; each image preprocessing circuit connects a reference image corresponding to each television camera; and a comparison circuit that compares the reference image and the input image and provides a change detection signal to the channel switching control circuit when a luminance change of more than a predetermined level occurs. Characteristic abnormality monitoring device. (23) In the device according to claim 22,
The channel switching control circuit does not input an image after the image processing means when there is no change detection signal, inputs the image after the image processing means when there is a change detection signal, and performs subsequent channel switching according to a command from the image processing means after that. An abnormality monitoring device characterized in that it is a circuit that controls a multiplexer as performed below. (24) In the device according to claim 23,
When there are two or more change detection signals, the channel switching control circuit notifies the image processing means and thereafter, and switches the multiplexer so that image processing can be performed while switching a plurality of channels under a command from the image processing means and thereafter. An abnormality monitoring device characterized by being a control circuit. (25) In the apparatus according to claim 1, the image input means includes an A/
Counts the clocks dated by the overflow signals from the D conversion means and the A/D conversion means, and outputs an impulse light detection signal to the main body of the abnormality monitoring device when the counted value exceeds a preset value. An abnormality monitoring device comprising: a counter. (26) In the device according to claim 25,
The image input means is a multi-channel image input means that includes a multiplexer that sequentially switches outputs from a plurality of imaging devices so that a plurality of monitoring areas can be monitored by one abnormality monitoring device main body, and the multiplexer is a multiplexer that interrupts sequential scanning of channels when an impulse light detection signal is generated, and switches channels so that image processing of the channel in which the impulse light detection signal is generated is performed immediately after the impulse light detection signal disappears. An abnormality monitoring device characterized by: (27) In the device according to claim 1, the image input means includes an A/
In order to be able to determine an abnormality with approximately equal sensitivity to a plurality of regions having different brightness levels in an input image,
There is a gain setting memory that stores in advance data for changing the reference voltage of the A/D conversion means in accordance with the brightness level of each part, and a gain setting memory that is selected according to the output of the gain setting memory and applied to the A/D conversion means. An abnormality monitoring device comprising: a plurality of reference voltage sources supplying different reference voltages. (28) In the apparatus according to claim 1, the image input means includes a plurality of A/D conversion means having different gains, a multiplexer for selecting the output of any one of the A/D conversion means; a multi-step comparison means for generating a multi-step comparison output for comparing the difference between the output of the two A/D conversion means and a reference image with a plurality of preset threshold values and controlling the switching of the multiplexer so that automatic gain adjustment is performed; , a reference image correction circuit that selectively multiplies a reference image by a plurality of correction coefficients so that automatic gain adjustment substantially the same as that of the input image is performed according to the multi-stage comparison output; An abnormality monitoring device comprising: a difference absolute value circuit that calculates a difference absolute value from an output of an image correction circuit.