JP5202419B2 - Security system and security method - Google Patents

Description

  The present invention relates to a security system and a security method.

  In a security system in which a plurality of security devices and a monitoring center are connected via a network, the monitoring center can access the security device and check images according to the purpose of use, or can store images inside the monitoring center. Etc.

  Patent Document 1 proposes a monitoring camera system that tracks the same moving object (monitoring target) with a plurality of monitoring cameras connected via a network by a monitor device. In the method of Patent Document 1, feature information that is a feature (shape, color, size, face information, etc.) of a moving body is extracted from video data captured by a plurality of surveillance cameras, and feature information is exchanged with each other. The video of the surveillance camera in which the moving body that matches the feature information is picked up is selected (screen display or the like).

Japanese Patent No. 3999561

  However, the method of Patent Document 1 is inefficient because (1) it is necessary to store the feature information in each monitoring camera device, and (2) it is difficult to check the action history of the monitoring target. (3) It is difficult to exchange characteristic information of a large number of monitoring destinations, and (4) high processing capability is required for a large number of monitoring camera devices installed at the monitoring destinations, which is a factor of high cost. There were problems such as becoming.

  In addition, in a security system that accumulates images inside the monitoring center, the amount of data stored in the image storage device of the monitoring center increases as the number of monitoring destinations (security devices) increases and the performance of surveillance cameras increases (higher resolution). There was a problem that the (necessary storage capacity) was enormous. Further, when the amount of stored image data increases, there is a problem that the efficiency of the operation of extracting only specific data in the image storage device of the monitoring center is lowered. This work corresponds to, for example, a work of tracking and monitoring a specific monitoring target (for example, the same person) across a plurality of monitoring destinations. Due to such a problem, it is difficult to track and monitor a specific monitoring target at a plurality of monitoring destinations.

  The present invention has been made in view of the above, and an object of the present invention is to provide a security system and a security method capable of reducing the data amount of data stored in a monitoring center for tracking a monitoring target and the like. To do.

In order to solve the above-mentioned problems and achieve the object, the present invention is a security system comprising a security device and a monitoring center connected to the security device via a network, the security device comprising: A feature extracting unit that extracts a feature amount representing a feature of a monitoring target from image information captured by an imaging unit that images the monitoring region; and a transmission unit that transmits the feature amount to the monitoring center. The center includes a reception unit that receives the feature amount from the security device, a feature amount storage unit that stores the received feature amount and identification information of the monitoring area in association with each other, and the feature of the monitoring target. An input receiving unit that receives an input of a monitoring request for requesting monitoring of the monitoring target, and when the monitoring request is received, the similarity between the feature amount included in the monitoring request is Characterized in that it comprises a retrieval means for retrieving the characteristic amount of the threshold is larger than the feature value memory defined because, and output means for outputting the feature quantity retrieved, the.

The present invention is also a security method executed in a security system comprising a security device and a monitoring center connected to the security device via a network, wherein the security device images a monitoring area. A feature extraction step of extracting a feature amount representing a feature of a monitoring target from image information captured by the means; a transmission step in which the security device transmits the feature amount to the monitoring center; and the monitoring center, A reception step of receiving the feature amount from a security device; a storing step in which the monitoring center associates the received feature amount with the identification information of the monitoring area and stores the same in a feature amount storage unit; and the monitoring An input receiving step for receiving an input of a monitoring request for requesting monitoring of the monitoring target, the center including the feature quantity of the monitoring target; A search step of searching for the feature quantity of the feature quantity storage means having a similarity with the feature quantity included in the monitoring request greater than a predetermined threshold when a viewing request is received; And an output step of outputting the searched feature quantity .

  According to the present invention, the security device extracts the feature quantity of the monitoring target from the image information and transmits it to the monitoring center. The monitoring center stores the feature quantity as information used for tracking the monitoring target instead of the image information. The amount of information stored in the monitoring center for tracking the monitoring target can be reduced.

FIG. 1 is a diagram for explaining an overview of a security system according to the present embodiment. FIG. 2 is a diagram for explaining the outline of the security system according to the present embodiment. FIG. 3 is a block diagram showing an example of the configuration of each device of the security system according to the present embodiment. FIG. 4 is a diagram illustrating an example of a data structure of data stored in the feature amount storage unit. FIG. 5 is a sequence diagram showing an overall flow of the feature amount storing process in the present embodiment. FIG. 6 is a flowchart showing the overall flow of the monitoring request process. FIG. 7 is a flowchart showing the overall flow of the monitoring process. FIG. 8 is a diagram illustrating a display example of displayed data. FIG. 9 is a flowchart showing the overall flow of the alarm notification process. FIG. 10 is a diagram illustrating an example of the displayed departure warning.

  Exemplary embodiments of a security system and a security method according to the present invention will be explained below in detail with reference to the accompanying drawings.

  1 and 2 are diagrams for explaining an outline of a security system according to the present embodiment. As shown in FIG. 1, a security system 10 according to the present embodiment includes a monitoring center 100 and a security device 200 installed in each monitoring destination A to C via a communication line (network) 50 such as the Internet. It is a connected configuration. The security device 200 is connected to a monitoring camera that captures an image of the monitoring area, a sensor (not shown) that detects an abnormality in the monitoring area, an emergency push button (not shown), and the like.

  Note that the number of monitoring destinations is not limited to three. Further, the communication line 50 is not limited to the Internet, and can be configured by any network that has been used conventionally.

  As shown in FIG. 1, in this embodiment, each monitoring destination security device 200 executes a feature amount extraction process for extracting a feature amount from image information captured by a monitoring camera. The extracted feature amount is transmitted from the monitoring destination to the monitoring center 100 and stored in the feature amount storage unit 121 of the monitoring center 100. Then, a feature amount tracking process for tracking the monitoring target is executed by the monitoring center 100.

  FIG. 2 shows processing when an abnormality is detected by a sensor or the like at the monitoring destination A. In this case, the security device 200 of the monitoring destination A includes the feature amount extracted from the image information when an abnormality is detected, and sends a monitoring request for requesting monitoring of the monitoring target represented by the feature amount to the monitoring center 100. Send. At this time, the security device 200 transmits the extracted feature quantity to the monitoring center 100 together with the face image to be monitored captured by the monitoring camera.

  Thereby, the monitoring center 100 can search the feature amount storage unit 121 for a feature amount that matches (similar) the received feature amount, and can output a face image together with the search result. That is, the monitoring staff of the monitoring center 100 can track the movement history of the monitoring target from the information retrieved based on the feature amount, and determine the monitoring target from the image of the monitoring destination by referring to the face image. It becomes possible.

  Next, the detail of the function of each apparatus which comprises the security system 10 is demonstrated. FIG. 3 is a block diagram showing an example of the configuration of each device of the security system 10 according to the present embodiment.

  As shown in FIG. 3, the security device 200 is connected to a monitoring camera 320 that images a monitoring area and a sensor 310.

  The sensor 310 is a human sensor that is installed in a monitoring area that is a security target and is mainly installed for the purpose of detecting an abnormality such as an intruder. The sensor 310 outputs a detection signal when the presence of a person or the opening / closing of a door is detected. The sensor 310 is, for example, an infrared sensor that detects the presence of a person based on a change in the amount of received infrared light, a blocking sensor that detects the presence of a person by blocking reception of infrared light, and the presence of a person due to disturbance of electromagnetic waves. Can be configured by various sensors that detect abnormalities in the monitoring area, such as a radio wave sensor that detects the opening and closing of the door with a magnet.

  Note that the monitoring camera 320 and the sensor 310 are not limited to one, and a plurality of monitoring cameras and sensors may be provided. In FIG. 3, only one security device 200 is shown, but any number of security devices 200 can be included as described above.

  First, the configuration of the security device 200 will be described. As illustrated in FIG. 3, the security device 200 includes an image information reception unit 201, a detection information reception unit 202, a feature extraction unit 203, a transmission / reception unit 204, and an image storage unit 221.

  The image information reception unit 201 receives image information captured by the monitoring camera 320. The detection information receiving unit 202 receives detection information that is transmitted when an abnormality is detected by the sensor 310. The detection information is a detection signal sent from the sensor 310. When a plurality of sensors 310 are installed, the detection information includes a detection signal and a sensor ID that identifies each sensor 310. Information indicating that the emergency push button has been pressed can also be handled in the same manner as the detection information.

  The feature extraction unit 203 extracts a feature amount representing a feature to be monitored from the captured image information. For example, the feature extraction unit 203 extracts the relative position information of the eyes and nose and mouth with respect to the outline of the face as a feature amount from the face image detected by collation with the face area pattern. As a method of extracting feature points such as the eyes and nose and mouth, a face image is binarized (black and white) as in Japanese Patent Laid-Open No. 08-77334 to obtain main feature points, and other feature points are face images. Can be applied by edge processing. Further, as in the method of Japanese Patent No. 3735893, when extracting a region of a facial feature portion, a search range may be set for each feature portion so as to increase search efficiency.

  Note that the feature amount to be extracted is not limited to the above, and any information that represents the feature to be monitored can be extracted as the feature amount. Also, the feature quantity extraction method is not limited to the above, and any conventionally used method can be applied according to the feature quantity to be applied.

  The transmission / reception unit 204 transmits / receives various information to / from the monitoring center 100 via the communication line 50. For example, the transmission / reception unit 204 functions as a transmission unit that transmits the extracted feature amount. The transmission / reception unit 204 transmits the alarm information to the monitoring center 100 when the detection information is received from the sensor 310 and the security mode is stored as the current security state.

  The security state is information representing the current security state of the security device 200 and is stored in a security state storage unit (not shown). As the security state, for example, either the security mode or the security release mode is stored. The security mode refers to a state in which alarm information notifying the abnormality in the security area is transmitted to the monitoring center 100 when the sensor 310 detects the abnormality and acquires the detection information. The security release mode refers to a state in which alarm information notifying the abnormality is not transmitted to the monitoring center 100 even when the detection information is acquired. The security state can be configured to be specified from an operation panel (not shown) for displaying information about the security device 200 and inputting information to the security device 200, for example.

  The image storage unit 221 stores image information captured by the monitoring camera 320 and received by the image information receiving unit 201. The image storage unit 221 may be provided outside the security device 200, and the security device 200 may be configured to read and use image information stored in the image storage unit 221 as necessary.

  Next, the configuration of the monitoring center 100 will be described. As shown in FIG. 3, the monitoring center 100 includes a transmission / reception unit 101, a storage unit 102, a search unit 103, a display control unit 104, a condition extraction unit 105, a determination unit 106, an input reception unit 107, A display unit 110, a feature amount storage unit 121, and an image storage unit 122 are provided.

  The feature amount storage unit 121 stores the feature amount transmitted from the security device 200. FIG. 4 is a diagram illustrating an example of a data structure of data stored in the feature amount storage unit 121. As illustrated in FIG. 4, the feature amount storage unit 121 stores a date and time, a location, and a feature amount value in association with each other. The date / time is, for example, the date / time (image date / time) when the monitoring camera 320 captured the image information from which the feature amount was extracted. In this case, the imaging date / time is received from the security device 200 together with the feature amount, and the received imaging date / time is stored in the date / time field.

  The location stores, for example, identification information for identifying the monitoring area. In the example of FIG. 4, an example is shown in which the monitoring area is identified by the monitoring destination identification information (monitoring destination A or the like) and the identification information (camera 1 or the like) of the monitoring camera 320 installed at the monitoring destination. . This identification information is received together with the feature amount from the security device 200, for example, and the received identification information is stored in the place field. This identification information is merely an example, and any information can be used as long as the information can identify the monitoring area.

  Returning to FIG. 3, the image storage unit 122 stores image information such as a face image transmitted from the security device 200 together with the feature amount.

  Note that the image storage unit 221 of the security device 200, the feature amount storage unit 121 of the monitoring center 100, and the image storage unit 122 are general such as an HDD (Hard Disk Drive), an optical disk, a memory card, and a RAM (Random Access Memory). It can be configured by any storage medium used for the above.

  The transmission / reception unit 101 transmits / receives various types of information to / from external devices including the monitoring device 200 as a monitoring destination via the communication line 50. For example, the transmission / reception unit 101 functions as a reception unit that receives a feature amount transmitted from the security device 200. The transmission / reception unit 101 receives a monitoring request to be monitored from the security device 200 or an external device (not shown) other than the security device 200.

  The storage unit 102 stores the feature amount received by the transmission / reception unit 101 in the feature amount storage unit 121.

  When the monitoring request is received by the transmission / reception unit 101, the search unit 103 searches the feature amount storage unit 121 for a feature amount that matches or is similar to the feature amount included in the monitoring request. For example, the search unit 103 calculates a similarity indicating a degree of similarity between the feature amount included in the monitoring request and the feature amount stored in the feature amount storage unit 121, and the similarity is larger than a predetermined threshold. Search for quantity. Note that, as a method for calculating the similarity, any conventionally used method can be applied according to the feature amount to be applied.

  The display unit 110 is a display device such as a display for displaying the searched feature amount. That is, the display unit 110 functions as an output unit that outputs the searched feature amount. It should be noted that the feature amount output method is not limited to the method of displaying on the display device.

  The display control unit 104 controls output processing of various types of information such as feature amounts for the display unit 110.

  The condition extraction unit 105 extracts a condition indicating a pattern of a monitoring area where the monitoring target is imaged by analyzing the feature amount stored in the feature amount storage unit 121. For example, when the feature quantity corresponding to a certain monitoring target (person or the like) is extracted only by the monitoring destinations A and B, the condition extraction unit 105 sets “confirmed by the monitoring destinations A and B as conditions for this feature quantity. Is extracted.

  The determination unit 106 determines whether or not the received feature amount satisfies the condition extracted by the condition extraction unit 105. Then, when the condition is not satisfied, the determination unit 106 determines that an action deviating from the condition has occurred, that is, an abnormality has occurred. In this case, for example, the display control unit 104 outputs a departure warning indicating that an action deviating from the condition has occurred on the display unit 110.

  The input receiving unit 107 functions as an input receiving unit that receives input of various information used for various processes in the monitoring center 100. For example, the input reception unit 107 receives a monitoring request for requesting monitoring of a desired monitoring target. More specifically, the input reception unit 107 receives a monitoring request received from the security device 200 or the like by the transmission / reception unit 101. The input receiving unit 107 may be configured to receive a monitoring request designated by a monitor of the monitoring center 100 through an input interface (not shown) such as a keyboard and a mouse.

  Next, the feature amount storage processing by the security system 10 according to the present embodiment configured as described above will be described with reference to FIG. FIG. 5 is a sequence diagram showing an overall flow of the feature amount storing process in the present embodiment.

  First, the image information receiving unit 201 of the security device 200 receives image information captured by the monitoring camera 320 (step S501). Next, the feature extraction unit 203 of the security device 200 extracts the feature quantity to be monitored from the image information (step S502). And the transmission / reception part 204 of the security apparatus 200 transmits the extracted feature-value to the monitoring center 100 (step S503).

  In the monitoring center 100, the transmission / reception unit 101 receives the feature amount (step S504). Then, the storage unit 102 stores the received feature amount in the feature amount storage unit 121 (step S505), and ends the feature amount storage process.

  Note that although one security device 200 is illustrated in FIG. 5, the feature amount is received from each of the monitoring destination security devices 200 by the above processing and stored in the feature amount storage unit 121. In this way, only the feature amount having a smaller data amount than the image information can be stored in the monitoring center 100. The stored feature amount can be used for tracking the monitoring target as follows.

  Next, processing for tracking the monitoring target will be described with reference to FIGS. FIG. 6 is a flowchart showing the overall flow of the monitoring request process for requesting that the security device 200 track and monitor the monitoring target.

  First, the feature extraction unit 203 determines whether detection information is received from the sensor 310 by the detection information receiving unit 202 (step S601). If the detection information is not received (step S601: No), the process is repeated until it is received. When the detection information is received (step S601: Yes), the feature extraction unit 203 acquires a face image from the image information captured by the monitoring camera 320 (step S602).

  Next, the feature extraction unit 203 extracts a feature amount from the image information (step S603). Then, the transmission / reception unit 204 transmits an alarm signal including the acquired face image and the extracted feature quantity as a monitoring request to the monitoring center 100 (step S604), and the monitoring request process ends.

  FIG. 7 is a flowchart showing an overall flow of a monitoring process for tracking and monitoring a monitoring target in response to a monitoring request from the security device 200. Note that, for example, when the monitoring request designated by the monitor is received by the input receiving unit 107, the monitoring process can be executed in the same procedure.

  First, the input receiving unit 107 determines whether or not an alarm signal, which is a monitoring request from the security device 200, has been received by the transmission / reception unit 101 (step S701). If not received (step S701: No), the process is repeated until received.

  When the alarm signal is received (step S701: Yes), the search unit 103 searches the feature amount storage unit 121 for a feature amount that matches or is similar to the feature amount in the alarm signal (step S702). Specifically, the search unit 103 calculates the similarity between the feature amount included in the warning signal and each feature amount stored in the feature amount storage unit 121, and selects a feature amount whose similarity is greater than a predetermined threshold. Search for.

  Next, the search unit 103 determines whether or not a feature value that matches or is similar to the feature value in the alarm signal has been searched (step S703). If a search is made (step S703: Yes), the display control unit 104 arranges the searched feature amounts in chronological order and outputs them to the display unit 110 together with the face image included in the alarm signal (step S704).

  FIG. 8 is a diagram showing a display example of data displayed at this time. FIG. 8 shows an example in which the date / time, the location, and the feature amount read from the feature amount storage unit 121 are displayed in association with the presence / absence of an alarm and the similarity. The presence / absence of an alarm sets whether or not it is a feature quantity accompanied by an alarm. That is, in the presence / absence of an alarm, “present” is set in the case of a feature quantity transmitted as a monitoring target to be tracked and included in the alarm signal, and “none” is set for other feature quantities. As the similarity, a value calculated as the similarity to the feature amount included in the alarm signal is set. As the feature amount, binary data of the feature amount stored in the feature amount storage unit 121 is displayed. In addition, you may comprise so that a feature-value may not be displayed.

  Thus, by searching for feature quantities similar to the feature quantity designated as the monitoring target and displaying them in time series, the monitor of the monitoring center 100 can track the movement history of the monitoring target. The monitoring center 100 can track and monitor the monitoring target using the image information, for example, by acquiring the image information from the displayed monitoring device 200 as a monitoring destination in real time. Although not shown in FIG. 8, since the face image transmitted in the alarm signal is also displayed, the monitor of the monitoring center 100 determines the monitoring target from the targets included in the image information acquired in real time. be able to.

  Returning to FIG. 7, when a feature amount that matches or is similar to the feature amount in the alarm signal is not found (step S703: No), the display control unit 104 displays the face image and the feature amount included in the alarm signal. It outputs to the display part 110 (step S705).

  Next, alarm notification processing for extracting a condition of a monitoring area where the monitoring target represented by the feature quantity is monitored and notifying the alarm when the condition deviates from the condition will be described with reference to FIG. FIG. 9 is a flowchart showing an overall flow of the alarm notification processing according to the present embodiment.

  First, the condition extraction unit 105 analyzes the feature quantity stored in the feature quantity storage unit 121, and for each feature quantity that matches or is similar, a normal pattern that represents the pattern of the monitoring area in which the monitoring target represented by the feature quantity is imaged Is extracted (step S901). For example, as described above, the condition extraction unit 105, when feature quantities having similarities or similarities to each other are extracted only by the monitoring destinations A and B, the feature extraction unit 105 selects “with monitoring destinations A and B”. The condition “confirmed” is extracted as a normal pattern. The extracted normal pattern (condition) is stored in a storage unit (not shown) or the like so as to be associated with the feature amount as the extraction source so that it can be referred to in the processing described later.

  The condition extraction process by the condition extraction unit 105 is executed at an arbitrary timing. For example, the condition extraction process can be executed every time a predetermined period elapses.

  The determination unit 106 determines whether or not the received feature value satisfies the extracted normal pattern when the feature value is received by the transmission / reception unit 101 (step S902). If the normal pattern is satisfied (step S902: Yes), the process returns to step S901 and the process is repeated.

  When the normal pattern is not satisfied (step S902: No), the determination unit 106 determines that a departure act has occurred, and the display control unit 104 outputs a departure warning to the display unit 110 (step S903). For example, the display control unit 104 displays the deviation warning and the received feature amount on the display unit 110 in association with each other. Thereby, the monitor can continuously monitor the monitoring target represented by the displayed feature amount.

  FIG. 10 is a diagram illustrating an example of the displayed departure warning. FIG. 10 shows an example in which a deviation field indicating whether or not a deviation has occurred, date and time, location, presence / absence of an alarm, similarity, and feature amount are displayed in association with each other. In the deviation field, “Yes” indicating that a deviation has occurred or “No” indicating that no deviation has occurred is displayed. FIG. 10 shows an example in which a departure warning is displayed when the feature amount normally confirmed by the monitoring destinations A and B is confirmed by the monitoring destination C.

  Note that the processing at the time of departure warning is not limited to this. For example, a deviation warning may be notified to a predetermined person (contractee's manager, etc.) and alerted. At this time, a face image or the like may be provided together with the departure warning.

  It has been clarified that burglars and others conduct a number of preliminary checks in advance. The departure alarm is used as a pre-alarm for detecting and notifying such an action in advance.

  As described above, in the security system according to the present embodiment, the feature amount is extracted by the security device of each monitoring destination from the image information acquired by a large number of monitoring cameras installed at a large number of monitoring destinations. The monitoring device at each monitoring destination transmits the feature amount to the monitoring center via the communication line, and the feature amount is centrally managed by the monitoring center. With such a configuration, for example, the following effects can be obtained.

(1) Since the information recorded and saved at the monitoring center is not image information but a feature amount, the necessary storage capacity for recording and saving can be reduced, and management can be efficiently performed.
(2) Since only the feature amount is transmitted instead of the image information and stored in the monitoring center, personal information protection (privacy protection) is possible. This reduces the administrative burden.
(3) The feature amount comparison and collation processing is complicated, and the price of the collation apparatus is expensive. For this reason, as in the present embodiment, the comparison and collation processing can be efficiently executed by carrying out collectively at the monitoring center or the like instead of the security device of each monitoring destination.
(4) Since the information transmitted to the monitoring center is not the image information but the feature amount data, the amount of data to be transmitted can be reduced. For this reason, it is possible to prevent congestion of the communication line even when feature quantities are simultaneously transmitted from a large number of monitoring devices.

  Further, in the security system according to the present embodiment, when abnormality detection information is notified from a sensor or the like, it is the same as the feature amount of a specific monitoring target (person or the like) from among the centrally managed feature amounts. By extracting only the feature quantities of and arranging them in time series, it is possible to track and monitor the behavior of this specific monitoring target.

  That is, when the security device detects an alarm (detection information) from a sensor or the like, the security device associates the face image acquired by the monitoring camera with the feature amount and transmits the result to the monitoring center. The monitoring center searches for the same (or similar) feature value from the feature value storage unit based on the transmitted feature value, and performs a feature value tracking process for managing the movement history in time series.

  As described above, since the face image or the like (personal identification information) is simultaneously transmitted together with the feature amount, the monitor who performs monitoring at the monitoring center can use the face image or the like as auxiliary information when confirming the image information of the monitoring destination. . Further, the face image or the like serves as auxiliary information for visualizing the feature amount to humans. Further, according to the method of the present embodiment, personal information such as a face image is transmitted to the monitoring center after detecting an alarm, and tracking monitoring is started, so that personal information can be protected. For this reason, the administrative burden can be reduced.

DESCRIPTION OF SYMBOLS 10 Security system 50 Communication line 100 Monitoring center 101 Transmission / reception part 102 Storage part 103 Search part 104 Display control part 105 Condition extraction part 106 Judgment part 107 Input reception part 110 Display part 121 Feature-value memory | storage part 122 Image storage part 200 Security apparatus 201 Image Information reception unit 202 Detection information reception unit 203 Feature extraction unit 204 Transmission / reception unit 221 Image storage unit 310 Sensor 320 Monitoring camera

Claims (6)

A security system comprising a security device and a monitoring center connected to the security device via a network,
The security device
A feature extraction unit that extracts a feature amount representing a feature of a monitoring target from image information captured by an imaging unit that captures the monitoring region;
Transmission means for transmitting the feature quantity to the monitoring center,
The monitoring center is
Receiving means for receiving the feature quantity from the security device;
Feature quantity storage means for storing the received feature quantity and identification information of the monitoring area in association with each other;
Input receiving means for receiving an input of a monitoring request that includes the feature quantity of the monitoring target and that requests monitoring of the monitoring target;
When the monitoring request is accepted, search means for searching for the feature quantity in the feature quantity storage means whose similarity to the feature quantity included in the monitoring request is greater than a predetermined threshold;
An output means for outputting the searched feature quantity;
A security system comprising: The receiving means further receives the monitoring request from the security device,
The input receiving means receives the received monitoring request;
The security system according to claim 1 . The transmission means transmits the feature quantity associated with the imaging date and time of the image information from which the feature quantity has been extracted to the monitoring center,
The input receiving means receives the feature amount associated with the imaging date and time,
The feature amount storage means stores the imaging date and time associated with the received feature amount, the feature amount, and the identification information in association with each other,
The output means outputs the searched feature quantities in the order of the imaging date and time;
The security system according to claim 1 . The input receiving means receives the monitoring request further including the image information to be monitored,
The output means outputs the image information included in the monitoring request in association with the searched feature quantity;
The security system according to claim 1 . The monitoring center is
Condition extracting means for extracting, from the feature quantity stored in the feature quantity storage means and the identification information, a condition that is satisfied by the monitoring area where the monitoring target represented by the feature quantity is imaged;
Determination means for determining whether or not the feature amount received by the reception means satisfies the extracted condition, and determining that an abnormality has occurred when the condition is not satisfied;
The security system according to claim 1. A security method executed by a security system comprising a security device and a monitoring center connected to the security device via a network,
A feature extraction step in which the security device extracts a feature amount representing a feature of a monitoring target from image information captured by an imaging unit that images a monitoring region;
A transmission step in which the security device transmits the feature quantity to the monitoring center;
A receiving step in which the monitoring center receives the feature quantity from the security device;
The monitoring center stores the received feature quantity and the identification information of the monitoring area in association with each other in a feature quantity storage unit;
An input receiving step for receiving an input of a monitoring request, the monitoring center including the feature quantity of the monitoring target and requesting monitoring of the monitoring target;
A search step of searching for the feature quantity in the feature quantity storage means when the monitoring center accepts the monitoring request, and the similarity to the feature quantity included in the monitoring request is greater than a predetermined threshold. When,
An output step in which the monitoring center outputs the searched feature quantity;
Security method characterized by including .

Images