JP2004236088A - Security system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a security system for detecting opening/closing of doors, locking of the doors, entrance/exit of people, lighting/extinction of illumination or the like by using an image photographed by a camera without the need of providing respective sensors. <P>SOLUTION: The security system displays an image photographed by a camera 1 on a screen of a monitor 4 and sets areas 7, 8 or the like to be monitored on the displayed image by an optional size and an optional number. The security system extracts present data corresponding to the areas 7, 8 from the image data photographed by the camera 1 at a prescribed time interval and compares the present data with reference data stored in advance. When a ratio of a change in the present data from the reference data is a prescribed value or over, the security system discriminates that an operation corresponding to the concerned area is executed, for example, a door 2 is opened/closed. <P>COPYRIGHT: (C)2004,JPO&NCIPI

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to a security system that detects opening / closing of a door, locking of a door, entry / exit of a person, turning on / off of a light, and the like, using an image captured by a camera.
[0002]
[Prior art]
2. Description of the Related Art Conventionally, a security system that monitors opening and closing of a door, locking of a door, entry and exit of a person, turning on / off of a light, and the like for each room has been put to practical use. In a conventional security system, a sensor is provided on each door or lighting switch to detect opening / closing of a door, locking of a door, turning on / off of a light, and the like. In addition, the entry and exit of a person is detected based on a change in luminance of an image captured by the camera, using a phenomenon that a screen becomes dark when a person passes in front of the camera.
[0003]
In addition, as a security system using an image captured by a camera, for example, as disclosed in Patent Document 1, in order to monitor for illegal acts on a gaming machine installed in a game arcade, an image captured by the camera is monitored. A monitoring device that detects a change in an image in a specific area has been proposed.
[0004]
[Patent Document 1]
JP 2001-218191 A (refer to claim 3)
[0005]
[Problems to be solved by the invention]
In a conventional security system, since sensors are individually provided for doors, lighting switches, and the like, wiring for connecting each sensor to the security room is complicated, and the installation cost of the sensors increases. Further, although an image taken by a camera contains various information, it is merely used to detect the entrance of a person, and the image data cannot be used effectively. Furthermore, since the position, size, sensitivity, etc. of the area to be monitored could not be set arbitrarily, it would react to changes in brightness due to turning on or off the lights, and the passage of small animals such as cats. However, there is a problem that there are many malfunctions.
[0006]
On the other hand, in the monitoring device disclosed in Patent Document 1, if an image in a specific area changes outside business hours such as at night, it can be inferred that the gaming machine may have been tampered with. Therefore, it is not possible to specifically detect what kind of operation has been performed. Further, similarly to the above-described conventional security system, there is a problem that the system reacts to turning on / off of a light, passing of a small animal, and the like, resulting in many malfunctions.
[0007]
The present invention has been made in order to solve the problems of the above-described conventional example, and without providing a sensor separately for a door or an illumination switch, using an image captured by a camera, opening and closing a door, and opening and closing a door. To provide a security system that can detect the locking, entry / exit of lights, turning on / off lights, etc., and can arbitrarily set the position, size, sensitivity, etc. of the area to be monitored, and reduce the occurrence of malfunctions. The purpose is.
[0008]
[Means for Solving the Problems]
In order to achieve the above object, an invention according to claim 1 is a security system for detecting a predetermined operation from a change in an image captured by a camera, wherein the camera is driven to generate reference image data and the reference image data at a predetermined cycle. An image data capturing unit that captures the current image data to be compared, and an arbitrary number of regions of any position and any size can be overlapped on the image displayed on the monitor screen using the reference image data. An area setting unit for setting, for each area set by the area setting unit, a sensitivity setting unit for setting a sensitivity for detecting a predetermined operation corresponding to each area, and the sensitivity setting unit A sensitivity storage section for storing the set sensitivity, and the area from the reference image data and the current image data captured by the image data capturing section. A data extraction unit that extracts reference data and current data corresponding to each area set by the setting unit; a reference data storage unit that stores reference data corresponding to each area extracted by the data extraction unit; A data comparison unit for comparing the current data extracted by the data extraction unit with reference data stored in the reference data storage unit in order for each area set by the setting unit; It is determined whether the data change amount with respect to the reference data exceeds a predetermined change amount corresponding to the sensitivity of each region set by the sensitivity setting unit, and the data change amount exceeds the predetermined change amount. When the predetermined operation is performed, it is determined that the predetermined operation corresponding to each of the regions has been performed, and a predetermined signal indicating that the predetermined operation has been performed and the predetermined operation are performed. An operation determining unit that outputs the time data obtained by the operation, an operation / time storage unit that stores a predetermined signal and time data output by the operation determining unit, and the predetermined operation when the predetermined operation requires an alarm. And an alarm output unit for outputting an alarm in response to the signal.
[0009]
According to such a configuration, the position, size, number, and sensitivity of the area to be monitored can be arbitrarily set, so that the opening / closing of the door, the locking of the door, the It is possible to detect whether or not a plurality of predetermined operations such as going in and out, turning on / off the lighting, and the like are performed, and an individual sensor for detecting each predetermined operation and its wiring are not required. As a result, the installation cost of the security system can be reduced. Furthermore, since the sensitivity can be set arbitrarily according to the predetermined operation to be detected, occurrence of malfunction can be reduced. As a result, the number of times security personnel are dispatched due to malfunctions is reduced, so that security system maintenance costs can be reduced. Furthermore, when it is determined that the predetermined operation has been performed, the predetermined operation and the time at which the operation was performed are recorded, so that the recording can be used for various purposes at a later date. Further, since it is determined whether the predetermined operation requires an alarm, an alarm is output only when the predetermined operation requires an alarm, and a predetermined operation requiring an alarm and a predetermined operation not requiring an alarm are performed. Can be monitored by the same security system.
[0010]
According to the second aspect of the present invention, it is possible to set an arbitrary number of areas of an arbitrary position and an arbitrary size on an image captured by a camera so as to be overlapped by an arbitrary number. A security system detects a corresponding predetermined operation.
[0011]
According to such a configuration, one camera can be used as a sensor for detecting a plurality of predetermined operations, and an individual sensor for detecting each predetermined operation and its wiring are not required. Therefore, the installation cost of the security system can be reduced.
[0012]
According to a third aspect of the present invention, in the security system of the second aspect, the sensitivity can be arbitrarily set for each of the areas.
[0013]
According to such a configuration, since the sensitivity can be arbitrarily set according to the predetermined operation to be detected, occurrence of a malfunction can be reduced. As a result, the number of times security personnel are dispatched due to malfunctions is reduced, so that security system maintenance costs can be reduced.
[0014]
According to a fourth aspect of the present invention, in the security system according to the second or third aspect, a time when the predetermined operation is performed is detected, and the time is output.
[0015]
According to such a configuration, when it is determined that the predetermined operation has been performed, the predetermined operation and the time at which the operation was performed are recorded, so that the recording can be used for various purposes at a later date. is there.
[0016]
According to a fifth aspect of the present invention, in the security system according to any one of the second to fourth aspects, when the predetermined operation requires an alarm, an alarm is output in response to the detection of the predetermined operation. I do.
[0017]
According to such a configuration, since it is determined whether the predetermined operation requires an alarm, an alarm is output only when the predetermined operation requires an alarm, and the predetermined operation and the alarm that require the alarm are output. Unnecessary predetermined operations can be monitored by the same security system.
[0018]
BEST MODE FOR CARRYING OUT THE INVENTION
An embodiment of a security system according to the present invention will be described with reference to the drawings. FIG. 1 shows a hardware configuration of a security system according to the present embodiment. A surveillance camera (hereinafter simply referred to as a “camera”) 1 using an imaging device such as a CCD is arranged so as to photograph, for example, the vicinity of a door 2 in a certain room. The output of the camera 1 is input to an image processing device 3 installed in a security room or the like, and an image captured by the camera 1 is displayed on a screen of a monitor device 4. The image processing device 3 uses, for example, a personal computer, and is connected to an input device 5 such as a keyboard and a mouse. Although FIG. 1 shows only one camera 1 and one monitor device 4, the cameras 1 are provided at various places in the building as needed. In addition, one monitor device 4 may be assigned to one camera 1, or one monitor device 4 may be assigned to a plurality of cameras 1 so that images displayed on the monitor device 4 are switched at regular intervals. It may be.
[0019]
Next, FIG. 2 shows a block configuration of the security system according to the present embodiment. The image processing device 3 drives the camera 1 and captures image data output from the camera 1, an image data capturing unit 31, an area setting unit 32 for setting an area to be monitored, and a sensitivity of the set area. A sensitivity setting unit 33 for setting, a sensitivity storage unit 41 for storing the set sensitivity, an image processing unit 34 for performing predetermined image processing on the captured image data, and a region set based on the captured image data. A data extraction unit 35 for extracting the extracted data, a reference data storage unit 42 for storing reference data used as a reference for operation determination, and a reference for comparing data of a current image to be subjected to operation determination with reference data. A data comparing unit 36, an operation determining unit 37 for determining whether a predetermined operation has been performed based on a comparison result by the data comparing unit 36, When it is determined that the operation has been performed, an operation / time storage unit 43 for storing the contents of the operation and the operation time, and an alarm output unit 40 for generating an alarm when a predetermined operation requires an alarm are provided. It is configured.
[0020]
The image data capturing unit 31, the area setting unit 32, the sensitivity setting unit 33, the image processing unit 34, the data extracting unit 35, the data comparing unit 36, and the operation determining unit 37 store a predetermined arithmetic processing program such as a ROM or a hard disk. It comprises a medium, a CPU for executing the arithmetic processing program, a RAM for temporarily storing read image data, and the like. In addition, the sensitivity storage unit 41, the reference data storage unit 42, and the operation / time storage unit 43 are configured by a storage medium such as a hard disk.
[0021]
Next, the operation of the security system according to the present embodiment will be described with reference to the block configuration shown in FIG. 2 and the flowchart shown in FIG.
[0022]
At the time of the initial setting, the image data capturing unit 31 captures reference image data serving as a reference for operation determination, for example, image data of an image in which the door 2 is closed and the illumination is turned on as shown in FIG. 1 (# 1). ). The image data captured by the image data capturing unit 31 is temporarily stored in a RAM or the like. Next, the image processing unit 34 displays the image 6 captured by the camera 1 on the screen of the monitor device 4 using the captured image data (# 2). The operator operates the input device 5 such as a mouse, for example, to set rectangular regions 7, 8,... Of an arbitrary size at an arbitrary position on the screen of the monitor device 4 (# 3).
[0023]
As a method for setting the regions 7, 8,..., The input device 5 is operated to move the cursor to a desired position on the screen, and, for example, the upper left starting point of the regions 7, 8,. Then, the size of the areas 7, 8,... Is set by moving the cursor while clicking a predetermined button (for example, a right button of a mouse) of the input device 5. The image processing unit 34 displays the setting operation of the areas 7, 8,... On the screen of the monitor device 4 according to the signal from the input device 5.
[0024]
When the areas 7, 8,... Set by operating the predetermined buttons of the input device 5 are determined, the data extracting unit 35 corresponds to the designated areas 7, 8,. The reference data is extracted and stored in the reference data storage unit 42 (# 4).
[0025]
After extracting and storing the reference data corresponding to the areas 7, 8,..., The input device 5 is operated to arbitrarily set the motion detection sensitivity for each of the set areas 7, 8,. (# 5). The sensitivity is set by operating a numeric keypad or the like of the keyboard, and the set sensitivity is stored in the sensitivity storage unit 41.
[0026]
For example, when detecting turning on / off of the lighting, if the area 8 is set at a position (for example, a ceiling) where a shadow cannot be formed due to a person entering or exiting, the image in the area 8 is either bright or dark. The intermediate brightness need not be considered. Then, in order to prevent erroneous determination, the sensitivity of the area 8 is set low. Further, since whether the door is opened or closed or locked is an important matter, the sensitivity of the area 7 set in the knob portion of the door 2 is set high.
[0027]
As an example of the sensitivity setting, consider the number of pixels in the imaging device of the camera 1. By setting the position and size of the regions 7, 8,..., The pixels on the image sensor that output data corresponding to the regions 7, 8,. Therefore, the ratio of the number of pixels whose data has changed to the total number of pixels corresponding to the regions 7, 8,... Can be set as the sensitivity.
[0028]
As an example, if the lighting on / off state of the illumination is detected, the illumination is turned off when the luminance changes from “bright” to “dark” for 80% or more of the total number of pixels corresponding to the area 8. It is determined that it has been performed. In addition, when the luminance of 80% or more of all pixels changes from “dark” to “bright”, it is determined that the illumination is turned on. Further, when the opening / closing of the door 2 is detected, when the luminance of the pixels corresponding to the area 7 that is 30% or more of the total number of pixels changes from “bright” to “dark” or from “dark” to “bright”, Is determined to be opened and closed.
[0029]
By repeating the above operations (# 3 to # 5), a plurality of areas 7, 8,... Can be set (# 6). When the reference data is stored in the reference data storage unit 42, the image data is copied, so that the areas A to D can be set to overlap as shown in FIG. 4, for example.
[0030]
When the setting of the areas 7, 8,... And the setting of the sensitivity of each area 7, 8,... Are completed (YES in # 6), as a normal security system, opening and closing the door, locking the door, entering and exiting the person, Detects lighting on / off. The image data capturing unit 31 drives the camera 1 at regular time intervals to capture current image data to be subjected to operation determination (# 7). The image processing unit 34 displays the current image captured by the camera 1 on the screen of the monitor device 4 using the captured current image data. In parallel with this, the data extraction unit 35 extracts the current data to be compared with the reference data from the current image data for each of the regions 7, 8,... Set by the region setting unit 32 (# 8). .
[0031]
When the current data is extracted, the data comparison unit 36 sequentially compares the current data with the reference data stored in the reference data storage unit 42 for each of the set areas 7, 8,... (# 9). . Here, when no movement such as opening / closing of the door or turning on / off of the lighting is performed, the current data and the reference data should be originally the same. Further, when an operation such as opening and closing of a door and turning on / off of a light is actually performed, the current data has changed from the reference data in a considerable number of pixels. Therefore, the data comparison unit 36 compares the current data with the reference data, and counts the number of pixels where the data has changed. Note that even when the operation of opening and closing the door and turning on / off the lighting is not performed, the current data is actually slightly different from the reference data due to noise, flickering of the lighting, and the like. Therefore, a threshold value is set for the data change amount, and it is determined that the data has changed only when the brightness has changed to a certain value or more.
[0032]
When the current data is compared with the reference data, the data comparison unit 36 outputs the comparison result, for example, the number of pixels (data change amount) whose luminance has changed to a certain value or more to the operation determination unit 37. The operation determination unit reads the sensitivity of the area to be determined from the sensitivity storage unit 41, and determines whether the number of changed pixels (data change amount) is the same as the predetermined number of pixels (predetermined change amount) corresponding to the read sensitivity. It is determined whether it is more than that (# 10). As described above, the sensitivity is set, for example, as a ratio of the number of changed pixels to the total number of pixels of the image sensor corresponding to the region. It is determined whether or not the luminance has changed for 80% or more of the total number of pixels. In addition, depending on the type of operation, it is also determined whether the direction of data change, for example, whether the luminance has changed from “bright” to “dark” or whether it has changed from “dark” to “bright”.
[0033]
If the number of changed pixels (data change amount) is equal to or larger than the predetermined number of pixels (predetermined change amount) corresponding to the sensitivity (YES in # 10), the operation determining unit 37 corresponds to the region. It is determined that the predetermined operation, for example, turning on or off the illumination, has been performed (# 11), and a signal corresponding to the performed predetermined operation and data on the time when the operation was performed are output. (# 12). The operation determining unit 36 determines whether the predetermined operation requires an alarm (# 13). For example, in the case of turning on or off lights or opening and closing a door in an unmanned state at night, it is necessary to output an alarm because there is a high possibility that a suspicious person may enter. Also, even if lighting is turned on and off, doors are repeatedly opened and closed, etc. during working hours, it is considered normal business, and there is no need to output an alarm. Therefore, only when an alarm is required (YES in # 13), the operation determination unit 37 outputs a predetermined alarm signal to the alarm output unit 40, and the alarm output unit 40 outputs an alarm such as a siren (# 14).
[0034]
Further, the above processing (# 9 to # 14) is repeated for all the areas 7, 8,... (# 15). When the operation determination is completed for all the regions 7, 8,..., The image data capturing unit 31 drives the camera 1 at predetermined time intervals to capture new current image data, and The above processing (# 9 to # 15) is repeated for.
[0035]
Next, setting of an area, comparison of data, operation determination, and the like in the present embodiment will be described in more detail with reference to FIG.
[0036]
As shown in the upper left of FIG. 4, it is assumed that an arbitrary number of areas A to D (not limited to four places) are set at an arbitrary position and an arbitrary size. A part may be overlapped like the area A and the area C and a part B and the area C, or may be completely overlapped like the area C and the area D.
[0037]
At the time of initial setting, the data extraction unit 35 extracts reference data corresponding to each of the areas A to D from the reference image data, and stores the reference data in the reference data storage unit 42. When the areas overlap as described above, the data of the overlapping part is copied and used as the reference data for the respective areas A to D. At the time of the operation determination, the data extraction unit 35 extracts the current data corresponding to each of the regions A to D from the current image data captured at regular intervals.
[0038]
The extracted current data of the area A, for example, is sent to the data comparison unit 36 and compared with the reference data of the area A stored in the reference data storage unit 42. The current data and the reference data in the area A are output from the same pixel group in the image sensor of the camera 1. The data comparing unit 36 compares the luminance of the current data with the luminance of the reference data for each pixel, and regards a pixel whose luminance has changed to a certain value or more as a pixel whose data has changed. The luminance of the current data and the luminance of the reference data are compared for all the pixels corresponding to the area A, and the number of pixels whose luminance has changed to a certain value or more is counted. Then, the counted number of pixels is output to the operation determining unit 37 as a data change amount. The same applies to the regions B to D. Note that for each of the regions A to D, the amount of change in the average value of the luminance of all pixel data may be used as the data change amount.
[0039]
The operation determination unit 37 compares the data change amount of the area A sent from the data comparison unit 36 with a predetermined change amount corresponding to the sensitivity of the area A stored in the sensitivity storage unit 41. When the number of pixels whose luminance has changed to a certain value or more is used as the data change amount, the number of pixels is used as the predetermined change amount corresponding to the sensitivity, and the data of the total number of pixels corresponding to the area A changes as the sensitivity. The ratio of the number of pixels is used. Also, when using the change amount of the average value of the brightness of all pixel data in each area as the data change amount, the change amount of the brightness is used as the predetermined change amount corresponding to the sensitivity, and the ratio of the brightness change or the absolute value is used as the sensitivity. Is used.
[0040]
When the data change amount is equal to or larger than the predetermined change amount corresponding to the sensitivity, the operation determining unit performs a predetermined operation corresponding to each of the areas A to D, for example, opening and closing a door, locking a door, entering and exiting a person, and lighting. It is determined that a predetermined operation such as turning on / off of is performed, and a predetermined signal corresponding to each predetermined operation is output.
[0041]
Next, a specific example of the operation determination according to the present embodiment will be described with reference to FIGS. FIG. 5 is a reference image obtained by photographing the room shown in FIG. 1 with the camera 1 and displayed on the screen of the monitor device 4, and FIG. 6 is a current image thereof. In addition to the region 7 of the knob portion of the door 2 and the region 8 of the ceiling portion, an upper region 9 of the door 2, a region 10 for locking the wall, and a region 11 at the center of the room including the door 2 are set. It is assumed that
[0042]
FIG. 6 shows a state in which a person X takes the key 23 hung on the wall, opens the door 2, turns off the light 24, and goes out of the room. Before turning off the light 24, first, focusing on the area 10, since the key 23 is missing, the current data has changed from the reference data by the number of pixels corresponding to the key 23. Depending on the size of the key 23 and the size of the area 10 and the relationship between the color of the wall and the color of the key 23, the presence or absence of the key 23 is an important matter. 23 can be detected as being removed.
[0043]
Next, paying attention to the area 9, since the outside such as a corridor can be seen at least in a part of the area 9 by opening the door 2, the current data is changed from the reference data by the number of pixels corresponding to the opening of the door 2. Change. Therefore, it can be detected that the door 2 has been opened. When the color of the wall of the corridor is similar to the color of the wall of the room, the change in data is small and it is difficult to determine whether the door is open or closed. Therefore, in order to easily detect the opening and closing of the door, for example, a mark 21 having an extremely higher or lower reflectance than other portions may be provided on the upper part of the door 2.
[0044]
Furthermore, focusing on the area 11, when the person X stands in front of the door 2, the current data of a considerable number of pixels in the area 11 changes from the reference data. Therefore, it is possible to detect the movement of the person or the ingress and egress of the person. In some cases, the person X may simply move around in the room. Therefore, it may be determined whether a person has entered or exited in accordance with the opening / closing operation of the door.
[0045]
Lastly, paying attention to the region 8, since the luminance of the current data is greatly reduced from the luminance of the reference data for all the pixels when the illumination 24 is turned off, it can be determined that the illumination 24 has been turned off.
[0046]
In addition, since the area 7 completely overlaps with the area 8, the sensitivity is set higher than the sensitivity of the area 8 and the direction of the lock knob provided on the knob 22 of the door 2 (vertical or horizontal) Is determined, it is possible to determine whether or not the door 2 is locked.
[0047]
FIG. 7 shows an image taken by a camera installed in, for example, a corridor. As shown in the figure, the area 12 to be monitored is set to include at least the entire width of the corridor at the center of the corridor. The sensitivity of the region 12 is set to be relatively low, that is, the ratio of the number of pixels whose data has changed to the total number of pixels corresponding to the region is increased. By setting the sensitivity low in this way, when a small animal 25 such as a cat passes, the number of pixels whose data has changed becomes smaller than the number of pixels corresponding to the sensitivity, so that it is not determined that a person has passed. . Conversely, when the person 26 passes, the number of pixels whose data has changed becomes larger than the number of pixels corresponding to the sensitivity, so it is determined that the person has passed. As a result, it is possible to reduce the possibility that a malfunction occurs.
[0048]
As described above, in the conventional security system, it is possible to detect the entrance and exit of a person from an image captured by a camera, but the position, size, and sensitivity of the area to be monitored cannot be set arbitrarily. It also responds to changes in brightness due to lighting or extinguishing of lights, and when small animals such as cats pass, and the likelihood of malfunctioning is high. According to the security system in the present embodiment, the position, size, number, and sensitivity of the area to be monitored can be arbitrarily set. By setting the ratio of the numbers high, the possibility of malfunction can be reduced. Also, by setting the area to be monitored at a high position, it is possible to reduce malfunctions due to passing of small animals. Further, it is also possible to set a plurality of areas to be monitored, and to judge whether a person enters or exits from a combination of the operation detection results in the plurality of areas.
[0049]
Note that the position, size, number and sensitivity of the reference screen and each area to be monitored can be determined based on an image actually taken by using a camera with the camera installed. It is needless to say that the use of the system is not limited to the above embodiment, but can be used for various uses.
[0050]
【The invention's effect】
As described above, according to the security system of the present invention, the position, size, number, and sensitivity of the area to be monitored can be arbitrarily set. Can detect whether or not a plurality of predetermined operations such as locking of doors, entering / exiting of a person, turning on / off of lighting, etc. are performed, and an individual sensor for detecting each predetermined operation and its wiring are unnecessary. Become. Further, since the sensitivity can be set arbitrarily according to the predetermined operation to be detected, occurrence of malfunction can be reduced. Furthermore, when it is determined that the predetermined operation has been performed, the predetermined operation and the time at which the operation was performed are recorded, so that the recording can be used for various purposes at a later date. Further, since it is determined whether the predetermined operation requires an alarm, an alarm is output only when the predetermined operation requires an alarm, and a predetermined operation requiring an alarm and a predetermined operation not requiring an alarm are performed. Can be monitored by the same security system.
[Brief description of the drawings]
FIG. 1 is a perspective view illustrating a hardware configuration of a security system according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating a configuration of the security system according to the embodiment.
FIG. 3 is a flowchart showing an operation of the security system according to the embodiment.
FIG. 4 is a conceptual diagram for explaining area setting, data comparison, and operation determination in the embodiment.
FIG. 5 is a diagram showing a reference image in a specific example of the operation determination in the embodiment.
FIG. 6 is a diagram showing a current image in a specific example of the operation determination in the embodiment.
FIG. 7 is a diagram showing a current image in another specific example of the operation determination according to the embodiment.
[Explanation of symbols]
1 camera
2 door
3 Image processing device
4 Monitor device
5 Input device
6 Images taken
7-12 Area to be monitored

Claims (5)

In a security system that detects a predetermined operation from a change in an image taken by a camera,
An image data capturing unit that drives the camera and captures current image data to be compared with the reference image data and the reference image data in a predetermined cycle.
On the image displayed on the monitor screen using the reference image data, an arbitrary number of areas of any position and any size, an area setting unit for setting the area to be overlappable,
For each region set by the region setting unit, a sensitivity setting unit for setting a sensitivity for detecting a predetermined operation corresponding to each region,
A sensitivity storage unit that stores the sensitivity set by the sensitivity setting unit,
A data extraction unit that extracts reference data and current data corresponding to each area set by the area setting unit from the reference image data and current image data captured by the image data capture unit;
A reference data storage unit that stores reference data corresponding to each area extracted by the data extraction unit;
For each area set by the area setting unit, in order, a data comparison unit that compares the current data extracted by the data extraction unit with reference data stored in the reference data storage unit.
It is determined whether the data change amount of the current data with respect to the reference data by the data comparison unit exceeds a predetermined change amount corresponding to the sensitivity for each region set by the sensitivity setting unit, and the data change amount is determined. If the predetermined amount of change has been exceeded, it is determined that the predetermined operation corresponding to each of the regions has been performed, and a predetermined signal indicating that the predetermined operation has been performed and data on the time during which the predetermined operation has been performed are output. An operation determining unit that performs
An operation / time storage unit that stores a predetermined signal and time data output by the operation determination unit,
A security system comprising: an alarm output unit that outputs an alarm according to the predetermined signal when the predetermined operation requires an alarm. An arbitrary number of areas and an arbitrary size of an area at an arbitrary position and an arbitrary size can be set to be overlapped on an image taken by a camera, and a predetermined operation corresponding to each area is detected from a change in the image of each set area. A security system characterized by that: The security system according to claim 2, wherein the sensitivity can be arbitrarily set for each of the areas. 4. The security system according to claim 2, wherein a time at which the predetermined operation is performed is detected and the time is output. The security system according to any one of claims 2 to 4, wherein when the predetermined operation requires an alarm, an alarm is output in response to detection of the predetermined operation.

Images