JP5520676B2 - Reporting device - Google Patents

Description

  The present invention relates to a notification device for detecting and reporting the presence of a suspicious person who may impair the maintenance of a monitored object or the occurrence of an emergency, and in particular, a technique capable of reducing erroneous determination of a legitimate person as a suspicious person About.

Conventionally, as a reporting device for users in stores and offices to report the existence of suspicious persons such as robbery to the outside, remote monitoring of images captured by surveillance cameras along with emergency signals by operating so-called emergency buttons What is sent to the center is widely known.
Although this type of reporting device is based on the user's voluntary operation, it rarely reports an emergency situation accidentally, but when an emergency such as a burglary occurs, the operation of the emergency button is regulated by the burglary. The user may be upset and forget to operate the emergency button, and there is a problem that the certainty of the notification is lacking.

The present applicant has filed a patent application according to Patent Document 1 as a countermeasure to such a problem.
In this patent document 1, a phrase whose pronunciation is predicted when an emergency occurs and a sound pressure level corresponding to the danger level of the phrase are stored in association with each other and input to a microphone in a store or the like. An informing device is disclosed that determines whether or not an emergency has occurred based on a combination of a phrase and sound pressure by monitoring the phrase and sound pressure in the voice.

Japanese Patent Laid-Open No. 2006-11872

  According to the reporting device proposed in Patent Document 1, it is possible to report the occurrence of an emergency such as a burglary to the outside while eliminating the need for an emergency button operation by the user. Both convenience and certainty of reporting can be achieved. Can be improved.

By the way, in general, suspicious persons such as robbers aim to suppress the object to be monitored and steal money, and often appear aiming at a time zone in which the success probability is high.
On the other hand, since the reporting device of Patent Document 1 is configured to constantly collect the sound to be monitored and determine the presence of a suspicious person or the occurrence of an emergency, the busy time is low in the possibility of a suspicious person appearing. Even if it is a belt, it will be continuously monitored.

  However, in such a busy time period, the environmental sound due to the hustle is generally large, and there is a risk that the suspicious person may be erroneously determined even in a situation where only a legitimate person exists in the notification device of Patent Document 1. . For example, it may be erroneously determined as an emergency by a message that flows at a relatively large volume, such as a noise caused by a large number of visitors or a broadcast in a store.

  The present invention has been made in view of the above problems, and reduces the possibility of misjudging a legitimate person as a suspicious person when automatically detecting and reporting the presence of a suspicious person or the occurrence of an emergency. The purpose is to propose a reporting device with improved reliability.

  In order to achieve the above object, the reporting device according to the present invention is a reporting device that detects the presence of a suspicious person at least when the monitoring target is manned and remotely reports it, and a clock unit that outputs the current time, A time storage unit that stores a monitoring start time, a suspicious person detection unit that executes a suspicious person detection process for detecting a suspicious person existing in the monitoring target, a notification unit that reports when the suspicious person is detected, The suspicious person detection unit starts executing the suspicious person detection process when the current time becomes the monitoring start time.

  As a result, the reporting device starts executing the suspicious person detection process when the current time becomes the monitoring start time, so the suspicious person detection process detects the suspicious person due to a false detection factor occurring in the monitoring target before the monitoring start time. Can be prevented.

  In the reporting device according to the present invention, the monitoring target is a sales office, and further includes a time determination unit that determines the monitoring start time based on a business end time of the monitoring target (sales office).

  As a result, the monitoring start time is determined based on the business end time of the sales office, and the execution of the suspicious person detection process starts when the current time reaches the determined monitoring start time. It can prevent detecting a suspicious person accidentally by sound.

  Further, in the reporting device of the present invention, a statistical information storage unit that stores the number of visitors corresponding to the time as statistical information, and a time when the number of visitors is equal to or less than a threshold based on the statistical information is the monitoring start time. A time determination unit for determining

  Thereby, it is possible to prevent the suspicious person from being erroneously detected by the environmental sound caused by the hustle and the like in the busy time zone where the monitoring target is crowded with visitors.

  Further, in the notification device of the present invention, a mode setting unit for setting a monitoring mode set in an unmanned state or a non-monitoring mode set in a manned state, and an intruder in a monitoring target in which the monitoring mode is set are detected. An intruder detection unit that performs notification when the suspicious person is detected and when the intruder is detected, and the suspicious person detection unit is set to the monitoring mode. And the execution of the suspicious person detection process ends.

  As a result, when the monitoring mode in which the intruder detection unit detects the intruder in the monitoring target is set, the execution of the suspicious person detection process is terminated. Therefore, while maintaining the security of the monitoring target by the intruder detection unit, the suspicious person is detected. False detection due to person detection processing can be prevented.

  Further, in the notification device of the present invention, further comprising: a storage unit that stores information on a plurality of monitoring areas that divide the monitoring target and information on a specific monitoring area among the plurality of monitoring areas, and the mode setting unit includes: The monitoring mode or the non-monitoring mode is set for each monitoring area, the intruder detection unit detects an intruder for each monitoring area where the monitoring mode is set, and the suspicious person detection unit is When the specific monitoring area is set to the monitoring mode, the execution of the suspicious person detection process is terminated.

  Thus, if an important monitoring area where, for example, a safe or customer data is stored is stored as a specific monitoring area, the security of the specific monitoring area is maintained by the intruder detection unit. In this case, since the suspicious person detection process ends, erroneous detection due to the suspicious person detection process can be prevented as much as possible.

  According to the present invention, since the execution of the suspicious person detection process is started when the current time becomes the monitoring start time, the suspicious person detection process detects the suspicious person due to a false detection factor generated in the monitoring target before the monitoring start time. Can be prevented.

It is the schematic which shows the whole structure of the notification system by the notification apparatus of this invention. It is a block diagram which shows the structure of the notification apparatus of this invention. It is a flowchart which shows the monitoring process of the notification apparatus of this invention.

Embodiments of the present invention will be specifically described below with reference to the drawings.
In the present embodiment, a business office such as a financial institution or a store is set as a monitoring target, and a case where a store area and an office area are monitored as a monitoring area that divides the monitoring target is exemplified. The scope of the present invention is not limited to this.

FIG. 1 is a configuration diagram showing a notification system 1 using the notification device of the present invention.
FIG. 1 shows a monitoring object 2 including a store area 2a and an office area 2b having an entrance to the outside, a monitoring camera 3 installed in the monitoring object 2, a security sensor 7 such as a heat ray sensor and an open / close sensor, The relationship between the monitoring camera 3 and the alarm device 4 to which the security sensor 7 is connected is schematically shown on the plan view.

  Here, in the present embodiment, the store area 2a is a business area, and is an area where a salesclerk who is a user of the monitoring target 2 and a customer who is a visitor from the outside can exist together. The area 2b is a non-business division and can be an area where only a store clerk can exist. As shown in FIG. 1, in the store area 2a, a store entrance 21 is provided as an entrance to the outside, and a common entrance 22 is provided between the store area 2a and the office area 2b. In addition, the office area 2b is provided with an office entrance 23 as an entrance to the outside in addition to the above-described common port 22.

  In the example of FIG. 1, the monitoring camera 3 is installed at a position where the entire store area 2a including the entrances 21 and 22 of the store area 2a can be imaged, and the entire entrances 22 and 23 of the office area 2b can be imaged. A surveillance camera 3 is also installed. The monitoring camera 3 and the notification device 4 are connected by a LAN (not shown), and the notification device 4 is further connected to a remote monitoring center 5 via a communication line network 6.

  Moreover, in the example of FIG. 1, the opening / closing sensor is installed in the entrance / exit 21 of the store area 2a and the office entrance / exit 23 of the office area b, and the heat ray sensor is installed in the store area 2b and the office area b. These security sensors 7 are connected to a LAN connecting the reporting device 4 and the monitoring camera 3.

  The monitoring camera 3 is a monitoring unit that generates monitoring information of the monitoring target 2. The surveillance camera 3 stores a camera number for identifying each surveillance camera 3 in advance, and an image signal input from the image sensor is transmitted at a predetermined photographing interval (for example, a cycle of 0.2 seconds, that is, 5 fps (frame / second)). Then, the image data is converted into a digital signal, compression-encoded, and image data compliant with a predetermined standard (for example, JPEG standard) is generated. The generated image data is output to the LAN and transmitted to the notification device 4. The image data transmitted at this time includes a camera number. Note that the surveillance camera 3 may compress and encode the audio signal input from the microphone to generate audio data, multiplex the image data and audio data, and output the multiplexed audio data to the LAN.

  The security sensor 7 is a monitoring unit that detects an intruder entering the inside of the area. The security sensor 7 stores a sensor number for identifying each security sensor 7 in advance, and outputs a detection signal including the sensor number to the notification device 4 when an intruder is detected.

  The reporting device 4 monitors intruders entering each area based on the detection signal from the security sensor 7 and the security mode set in each area. The security mode includes a security set mode as a monitoring mode and a security release mode as a non-monitoring mode. The security set mode is a mode set in an unattended state in which no user exists in the area, and the reporting device 4 determines intrusion when receiving a detection signal from the security sensor 7 in the area where the security set mode is set. The intrusion detection signal is transmitted to the monitoring center 5. The security release mode is a mode that is set in a manned state where a user exists in the area, and the reporting device 4 intrudes even if a detection signal is received from the security sensor 7 in the area where the security release mode is set. The intrusion detection signal is not transmitted to the monitoring center 5.

  In addition, the notification device 4 receives image data input from the monitoring camera 3 and executes suspicious person detection processing for determining whether or not there is a suspicious person in the monitoring target 2 from the image data. As a result of the suspicious person detection process, when it is determined that there is a suspicious person in the monitoring target 2, a suspicious person detection signal is reported to the monitoring center 5 via the communication network 6 and received from the monitoring camera 3. The image data is transmitted to the monitoring center 5. The image data transmission process is continuously performed until a stop input is received from the user of the monitoring center 5 or the monitoring target 2.

  In particular, in the present embodiment, the notification device 4 stores the time when the number of persons in the monitoring target 2 is estimated to be small as the monitoring start time, and allows the suspicious person detection process to be executed when the current time becomes the monitoring start time. . In addition, when the reporting device 4 determines that the inside of the monitoring target 2 has become unattended, the reporting device 4 prohibits execution of the suspicious person detection process. As a result, the monitoring target 2 is predicted to be quiet and is operated to reliably detect a suspicious person in a time zone in which there is a high risk that a suspicious person such as a burglar will intrude. Therefore, it is possible to prevent erroneous determination that a suspicious person exists due to some noise factor.

  Here, in this embodiment, a suspicious person refers to a person who may impair the maintenance of the monitoring target 2, and specifically, a person whose appearance and behavior match a predetermined suspicious pattern. For example, people who are extremely depressed or wearing sunglasses or masks to hide part of their face and do not know the human phase, who stepped on or stayed in a specific area, who shouted loudly or others around them Someone who screams.

  The monitoring center 5 is a facility provided with a center device 51 operated by a security company or the like. The center device 51 is composed of one or a plurality of computers, and realizes the function of the monitoring center 5 related to the present invention. In the monitoring center 5, various devices are controlled by the center device 51, the suspicious person detection signal received from the reporting device 4 is recorded, and the image data transmitted from the reporting device 4 is displayed on the display 52, so that the monitoring staff Monitors a plurality of monitoring areas 2 to be monitored.

<Notification device>
Next, the configuration of the notification device 4 will be described with reference to FIG. FIG. 2 is a block diagram showing the configuration of the notification device 4.
The reporting device 4 is installed in the monitoring target 2 (in the present embodiment, the office area 2b) so as to be able to communicate with the monitoring camera 3, the security sensor 7, and the monitoring center 5.

  The reporting device 4 includes a monitoring information acquisition unit 41 as a communication I / F (interface) connected to the LAN, a communication unit 42 connected to the communication network 6, and an operation unit 43 on which a user performs an input operation. The storage unit 44 includes an HDD, a memory, and the like, and the control unit 45 includes an MPU, a microcomputer, and the like and controls each unit.

The monitoring information acquisition unit 41 is connected to the monitoring camera 3 and the security sensor 7 and receives the camera number and image data output from the monitoring camera 3 as the monitoring information of the monitoring target 2 and the detection signal output from the security sensor 7. The data is output to the control unit 45.
The communication unit 42 is connected to the center device 51 via the communication line network 6 and communicates with the monitoring center 5. When the control unit 45 determines that there is a suspicious person in the monitoring target 2, the communication unit 42 transmits a suspicious person detection signal including its own address information and image data captured by the monitoring camera 3 to the monitoring center 5. To do. In addition, when the communication unit 42 determines that there is an intruder in the area set in the security set mode by the control unit 45 (store area 2a, office area 2b), the intrusion detection signal including its own address information. Is transmitted to the monitoring center 5.
The operation unit 43 is a switch capable of inputting setting information such as a security mode setting operation.

  The storage unit 44 is configured by a ROM, a RAM, or an HDD, stores address information for identifying itself, various programs, and the like, and further stores various information for operating the reporting device 4. Specifically, the storage unit 44 includes reference data serving as background information for extracting a moving object, mode information indicating the current security mode, area information indicating information on an area constituting the monitoring target 2, and statistics. The number of visitors information that stores past number of visitors transition as information and the monitoring time information for performing suspicious person detection processing are stored. Further, the storage unit 44 stores image data for a past predetermined time output from the monitoring camera 3.

Here, the reference data stored in the storage unit 44 is comparison reference information used for extracting a moving object in the monitoring target 2 in comparison with the current image data in the visitor detection process described later. This is image data obtained by capturing an image of the monitoring target 2 in the unattended state in advance.
Moreover, the mode information has memorize | stored the security mode (security set mode or security cancellation | release mode) currently set for every area (shop area 2a, office area 2b). The security mode is set by the control unit 45 based on an operation input to the operation unit 43 by the user.
Further, the area information includes the positions of the monitoring cameras 3 and the entrances 21, 22, and 23 corresponding to the store area 2 a and the office area 2 b constituting the monitoring target 2, and information on various areas set in the image data, The information of the security sensor 7 installed in the area is information set in advance.

The number of visitors information is the number of visitors to the monitoring target 2 output from the control unit 45 stored in correspondence with the time, and the number of visitors per unit time (for example, 30 minutes) is predetermined in the past. I remember for days.
Furthermore, the monitoring time information is information that defines a monitoring start time for starting execution of the suspicious person detection process, and is a value set by the control unit 45. The monitoring time information may be directly input from the operation unit 43 and stored in the storage unit 44.

  The control unit 45 includes a microcomputer including a CPU, a ROM, a RAM, and the like and peripheral circuits thereof, and controls each unit described above. For this purpose, the control unit 45 includes an electronic calendar unit 450 as a clock means for acquiring the current date and time as a functional module realized by the microcomputer and a computer program executed on the microcomputer, and a security mode of the monitoring target 2. A mode setting unit 451 for setting / changing the intruder, an intruder detection unit 452 for detecting an intruder to the monitoring target 2, an entrance number detection unit 453 for detecting the number of visitors to the monitoring area 2, and a suspicious person detection A time determination unit 454 that determines a monitoring start time for starting the execution of processing, a suspicious person detection unit 455 that executes suspicious person detection processing, and a communication control unit 456 that controls communication processing by the communication unit 42 are provided.

  The mode setting unit 451 collates the information input from the operation unit 43 when the user sets the security mode, and if the verification is OK, the mode setting unit 451 sets the security mode for each area based on the input of the operation unit 43. Or set to security release mode. That is, if there is a security set mode setting operation for the store area 2a, the security mode of the store area 2a is set to the security set mode, and if there is a security set mode setting operation for the office area 2b, the security mode of the store area 2a is set. Set to security set mode. The security mode for each area set by the mode setting unit 451 is stored in the mode information of the storage unit 44.

  As described above, the security set mode is set when the monitoring area is unattended, such as at night or on holidays, and when the security sensor 7 detects a change in the event, the remote monitoring center 5 is connected via the communication unit 42. In this mode, an abnormality report is made using an intrusion detection signal. Further, the security release mode is a mode that is set when the monitoring area is manned and does not perform abnormality notification by detection of the security sensor 7.

  When an intruder detection unit 452 receives a detection signal from the security sensor 7 via the monitoring information acquisition unit 41, the intruder detection unit 452 refers to the area information and mode information stored in the storage unit 44, and the current security mode is the security. When the security sensor 7 in the area that is in the set mode outputs a detection signal, it is determined that an intruder exists in the area. On the other hand, if the security sensor 7 in the area where the current security mode is the security release mode outputs a detection signal, the presence of an intruder is not determined. Information on the area where the intruder detection unit 452 detects the intruder and information on the security sensor 7 that has output the detection signal are stored in the storage unit 44 and reported to the monitoring center 5 as an intrusion detection signal.

  The number-of-entrance detection unit 453 performs image processing on the image data acquired by the monitoring information acquisition unit 41 (image data input from the monitoring camera 3) to detect the number of visitors to the monitoring target 2. In the entrance number detection unit 453, position information of an area (entrance / exit area) on the image including the entrances 21 and 23 to the outside in the captured image data is set in advance for each monitoring camera 3. The number-of-entrance detection unit 453 detects a fluctuating region newly appearing on the image from the entrance / exit region, detects the presence of the visitor, and obtains the number of visitors.

  Specifically, the entrance number detection unit 453 compares the reference data (image data when nobody is present) stored in the storage unit 44 with the current image data input from the monitoring information acquisition unit 41, and determines the luminance value. The fluctuation pixels whose fluctuations are greater than or equal to a predetermined value are extracted, and a group of substantially continuous fluctuation pixels is grouped as one fluctuation area, and each fluctuation area is labeled with a unique label. Then, the label detected in the previous frame process is associated with the label of the current frame by the tracking process. The association is performed according to the distance and size between the labels of both frames. Then, when the label of the current frame that cannot be correlated by the tracking process, that is, the object that newly appears on the image data is located in the entrance / exit area, the entrance number detection unit 453 captures the object by the image data. It is determined as a new visitor in the area (store area or office area). The number-of-entrance detection unit 453 performs the above-described processing on the image data captured by each monitoring camera 3, and detects the visitors for each store area 2a and office area 2b based on the camera number, thereby entering the monitoring target 2. Detect visitors. That is, if an entrance person is detected in the entrance / exit area corresponding to the store entrance / exit 21, it is determined that the person enters the store area 2a, and if an entrance person is detected at the office entrance / exit 23, it is determined that the person enters the office area 2b. .

  The number-of-entrance detection unit 453 detects the number of visitors detected in each area (store area 2a and office area 2b) every preset unit time (for example, 30 minutes), and the number of visitors in each area. The number of visitors to the monitoring target 2 to which is added is output to the storage unit 44 and stored in association with the time. The unit time for detecting the number of visitors is at least a time when the number of visitors corresponding to the time zone can be identified, and is arbitrarily set depending on the frequency of visits to the store, the entrance area, the store area, etc. It's okay.

  The detection of the number of visitors is not limited to this, and any method may be used as long as the number of visitors to the monitoring target 2 can be detected. For example, a traffic detection sensor capable of detecting the direction in which the person has passed is installed at the entrances 21 and 23 to the outside of the monitoring target 2, and the notification device 4 sends a detection signal from the traffic detection sensor to the monitoring information acquisition unit 41. And the number of persons passing through each entrance is detected by the entrance number detection unit 453 to determine that there are visitors to the store area 2a and the office area 2b. You may ask for the number of visitors. As such a traffic detection sensor, various methods such as a method of providing a plurality of infrared sensors along the traffic direction and detecting the traffic direction according to the detection order are known.

The time determination unit 454 calculates a monitoring start time for starting execution of the suspicious person detection process based on the past number of visitors information stored in the storage unit 44, and stores it in the monitoring time information of the storage unit 44. Specifically, the time determination unit 454 reads the visitors in the same time zone or unit time of the past predetermined number of days (for example, one week) from the information on the number of visitors in the storage unit 44, and is monitored for each time zone. The average value of the number of visitors of 2 is calculated, and the start time of the time zone in which the average number of visitors is equal to or less than a predetermined threshold (for example, the number of salesclerks in the monitoring target 2) is set as the monitoring start time. Set.
The monitoring start time is a time reference value for determining whether or not to perform suspicious person detection processing, and it is not preferable from the viewpoint of preventing erroneous determination to perform suspicious person detection processing when a large number of legitimate visitors enter. It is necessary to execute the suspicious person determination process surely during a time period in which it is predicted that the store is quiet and there is a high risk that a suspicious person such as a burglar may intrude. Therefore, in the present embodiment, the suspicious person detection process is executed at the time when the number of visitors equal to or less than the number of store clerks enters from the transition of past visitors.

  The setting of the monitoring start time is not limited to this, and the monitoring start time may be set based on the closing time of the store area 2a, which is a business division, instead of or in addition to the above configuration. In this case, the time determination unit 454 monitors a time before a predetermined time (for example, one hour before) from the closing time input from the operation unit 43 when the reporting device 4 is installed or when the security planning of the monitoring area 2 is changed. Set as start time. Thereby, it is possible to start the suspicious person detection process from a time zone where the number of customers decreases when the business area is closed, and it is possible to monitor the suspicious person while preventing erroneous determination.

  In addition to the example of setting the start time for allowing the execution of the suspicious person detection process as described above, a period in which the number of the monitoring targets 2 is estimated to be small (for example, the past average number of visitors is a threshold value). The following period) may be set as the monitoring period, and the suspicious person detection process may be allowed within this period.

  The suspicious person detection unit 455 allows the suspicious person detection process to be executed when the current time becomes the monitoring start time stored in the storage unit 44. The execution of this suspicious person detection process is prohibited when the store area 2a and the office area 2b are set in the security set mode, that is, when it can be determined that the monitoring target 2 is unattended, and again the monitoring target 2 When the person becomes manned and the monitoring start time is reached, the state is allowed again.

  The detection method of the suspicious person by the suspicious person detection processing executed by the suspicious person detection unit 455 is not limited to the image, and any method may be used. However, in this embodiment, the monitoring information acquisition unit 41 is used as the image characteristic of the suspicious person. It is detected that there is a person who conceals each part (eyes, nose, mouth), which is a facial feature part whose human phase can be distinguished, in the image data acquired in (cannot detect each part of the face). The suspicious person detection unit 455 can use various known methods for detecting a facial feature portion in the face area.

  Specifically, the suspicious person detection unit 455 extracts, as suspicious person detection processing, the edge component of the fluctuation region labeled by the entrance number detection unit 453, and has an elliptical shape that approximates the contour shape of the face in the edge image data. When an edge distribution is detected and the color information in the elliptical area surrounded by the edge distribution includes a skin color (for example, a pixel whose hue (H) component is 0 to 30 in the HSV color system), the elliptical area As a face region. Then, it is determined whether or not an edge (for example, a horizontal edge such as an eye or a mouth) that becomes a facial feature portion appears in the facial region, and a facial region where such a facial feature portion cannot be detected by a suspicious person. Judge that there is.

  Further, the suspicious person detecting unit 455 individually detects a face area on which sunglasses and a mask are worn from the luminance distribution of the face area. In the face area where the sunglasses and the mask are worn, dark pixels concentrate on the upper side, so that the luminance center of gravity in the vertical direction is lower than the center. Further, the luminance value for each line viewed in the horizontal direction is small, whereas the variance of the luminance value for each line viewed in the vertical direction is large. Furthermore, there is a property that the luminance value is extremely low depending on the part of the sunglasses. Therefore, the Y coordinate of the luminance center of gravity of the face area is below the center of the face area, and the ratio between the standard deviation in the X direction and the standard deviation in the Y direction is larger than a predetermined threshold, and the pixel having a low luminance value Is equal to or greater than the threshold value, it is determined that the image in the face area is an image of a face wearing sunglasses and a mask, and the face area is determined to be a suspicious person.

The suspicious person detection process is not limited to this, and it is only necessary to determine that the appearance or behavior of a person matches a preset suspicious pattern.
For example, it may be determined whether the person is a suspicious person based on the position of the person. In this case, an important monitoring area is set in the image data, and the person existing in the important monitoring area is determined as the suspicious person. Further, it may be determined whether the person is a suspicious person based on the movement locus of the person. In this case, for example, the movement locus of the person (moving object) detected by the tracking processing of the labeled fluctuation region is set in the image data. The person may be determined as a suspicious person when it is linear from the entrance / exit area to an important monitoring area such as a cash register or a safe. Further, it may be determined whether the person is a suspicious person based on the residence time of the person. In this case, the person who exists in the important monitoring area set in the image data for a predetermined time is determined as the suspicious person. In addition, a person who matches the suspicious pattern can be extracted by various known methods.

The communication control unit 456 transmits a suspicious person detection signal to the monitoring center 5 when the suspicious person detection unit 455 determines that there is a suspicious person in the monitoring target 2. The suspicious person detection signal includes the address information of the reporting device 4. In addition, when the presence of a suspicious person is determined, the communication control unit 456 starts transmission of image data input from the monitoring camera 3 to the monitoring center 5. The camera number and the address information of the reporting device 4 are added as header information to the transmitted image data, and the current image data is continuously transmitted each time it is input from the monitoring camera 3. When the communication control unit 456 receives either a stop signal due to an image transmission stop input to the operation unit 43 or an image transmission stop signal transmitted from the monitoring center 5, the communication control unit 456 performs image data transmission processing to the monitoring center 5. To stop.
If the intruder detection unit 452 determines that an intruder exists in the area set in the guard set mode in the monitoring target 2, the communication control unit 456 transmits an intrusion detection signal to the monitoring center 5.

<Description of operation>
About the notification system 1 comprised as mentioned above, the operation | movement is demonstrated with reference to drawings. Here, the operation related to the reporting device 4 will be mainly described. FIG. 3 is a flowchart showing the operation of the monitoring program repeatedly executed by the notification device 4.

  The notification device 4 accepts input of image data captured by the monitoring camera 3 from the monitoring information acquisition unit 41 at a predetermined cycle (for example, a cycle of 0.2 seconds, that is, 5 fps (frames / second)), and stores it in the storage unit 44. . Further, the time determination unit 454 calculates the monitoring start time based on the past visitor number information at a predetermined timing such as before the business start of the monitoring target 2 and stores it in the storage unit 44.

  When the monitoring program shown in FIG. 3 is executed, first, the entrance number detection unit 453 detects the number of visitors in the monitoring target 2 by performing image processing on the image data acquired by the monitoring information acquisition unit 41, The number of visitors detected every unit time (for example, 30 minutes) is stored in the number of visitors information of the storage unit 44 (step ST1).

  Next, the control unit 45 of the reporting device 4 compares the current date and time acquired by the electronic calendar unit 450 with the monitoring start time stored in the monitoring time information of the storage unit 44, and the current date and time is the monitoring start time. Is determined (step ST2).

  If it is determined in step ST2 that the current date and time has passed the monitoring start time (step ST2-Yes), it is determined whether or not all areas are in the security set mode with reference to the mode information in the storage unit 44. (Step ST3). When all the areas are not in the security set mode (step ST3-No), the suspicious person detection unit 455 is caused to execute suspicious person detection processing (step ST4).

  In the suspicious person detection process executed by the suspicious person detection unit 455, it is determined that the appearance or behavior of the person in the monitoring target 2 matches a preset suspicious pattern, thereby determining the presence of the suspicious person. In the present embodiment, as image characteristics of a suspicious person, each part (eyes, nose, mouth), which is a facial feature part whose human phase can be identified, is concealed in the image data acquired by the monitoring information acquisition unit 41 (face A person is detected as a suspicious person.

  As a result of the suspicious person detection process, when it is determined that a suspicious person is present in the monitoring area 2 (step ST5-Yes), the communication control unit 456 transmits a suspicious person detection signal to the monitoring center 5 (step ST6). Transmission of image data input from the camera 3 is started to the monitoring center 5 (step ST7). The transmission of the image data is continuously performed until an image transmission stop signal is input from the operation unit 43 or the monitoring center 5. When an image transmission stop signal is input from the operation unit 43 or from the monitoring center 5 (step ST8—Yes), the transmission of image data to the monitoring center 5 is stopped and the process is terminated (step ST9).

  On the other hand, when it is determined in step ST2 that the current date and time has not passed the monitoring start time (step ST2-NO), the processing of step ST3 to step ST9 is skipped to execute the suspicious person detection processing. Is prohibited. Therefore, when the current date and time is before the monitoring start time, it is possible to prevent the determination that there is a suspicious person in the monitoring target 2 and suppress erroneous determination.

  If it is determined in step ST3 that all areas are in the security set mode (step ST-Yes), the execution of the suspicious person detection process is prohibited by skipping the processes in steps ST4 to ST9. ing. Therefore, when the entire monitoring target 2 is in the security set mode in which the intruder detection unit 452 monitors the intruder and the security of the monitoring target 2 is maintained, the execution of the suspicious person detection process is prohibited. Therefore, it is possible to prevent erroneous detection due to suspicious person detection processing while maintaining security.

  Note that the above-described determination in step ST2 may determine whether it is within a period in which it can be estimated that the number of persons in the monitoring target 2 is small, not whether or not it is after the monitoring start time. In this case, the time determination unit 454 sets the period during which the number of visitors in the past is equal to or less than the threshold as the monitoring period, and proceeds to step ST3 if the current date is within this period in the determination of step ST2. If it is outside the period, step ST3 to step ST9 may be skipped.

  The suspicious person detection process may be prohibited from being executed when the office area 2b, which is a non-business area as a specific monitoring area, is in the security set mode. In this case, in step ST3, it is determined whether or not the office area 2b is set in the security set mode. If the office area 2b is set in the security set mode, the processes in steps ST4 to ST9 are skipped, Execution of the suspicious person detection process may be prohibited. Accordingly, if an important monitoring area where, for example, a safe or customer data is stored is stored as a specific monitoring area, the security of the specific monitoring area is maintained by the intruder detection unit 452. In this case, since the suspicious person detection process is completed, erroneous detection due to the suspicious person detection process can be prevented as much as possible.

  The embodiments of the present invention have been described above by way of example, but the scope of the present invention is not limited to these embodiments, and can be changed or modified according to the purpose within the scope of the claims. is there.

  For example, in the present embodiment, an example in which the monitoring information acquisition unit 41 acquires image data as monitoring information of the monitoring target 2 and performs entrance detection and suspicious person detection using the image data has been described, but the present invention is not limited thereto. . That is, the monitoring information is not limited to image data, and may be information that can identify and recognize the moving object of the monitoring target 2. For example, instead of the monitoring camera 3 or in addition to the monitoring camera 3, reflected light reflected by an object on the optical path by performing spatial scanning at a predetermined period while irradiating the monitoring target 2 with laser light as the monitoring means A laser scanning distance sensor that detects the position of the object by obtaining the distance data to the object existing in the area and the irradiation direction by receiving the light may be used.

  In this case, the position (distance data and irradiation direction) of the object in the monitoring target 2 is input to the monitoring information acquisition unit 41 from the laser scanning distance sensor as monitoring information. As the reference data, the position of the existing object measured during unmanned operation is stored, and the variable object is extracted and labeled from the difference between the reference data and the position of the object in the current monitoring target 2, and the tracking process with the previous period is performed. It is determined whether or not it is a new appearance object. In the process of detecting the number of entrances, when a new appearance object is detected in the entrance / exit area set within the scanning range of the laser scanning distance sensor, it is detected as an entrance and the number of visitors is obtained.

  In the suspicious person detection process, it may be determined whether or not the person is a suspicious person based on the existence position, moving locus, and residence time of the labeled variable object (person) as in the above-described embodiment. That is, an important monitoring area is set within the scanning range of the laser scanning type distance sensor, and the entrance of a person into this area is monitored, and a predetermined suspicious pattern (entering into the important monitoring area, moving to the important monitoring area) A person who matches the trajectory and the residence time in the important monitoring area) is determined as a suspicious person.

In addition to the above-described embodiment, in the suspicious person detection process, a suspicious person may be detected based on voice data input from a microphone installed in the monitoring target 2 (the store area 2a and the office area 2b).
In this case, the monitoring information acquisition unit 41 also functions as a voice acquisition unit that acquires voice data collected by the microphone, and the suspicious person detection unit 455 performs voice recognition processing on the voice data as a suspicious person detection process. It is determined whether a suspicious person exists in the monitoring target based on the character string included in the data. Specifically, the suspicious person detecting unit 455 extracts a voice feature amount from the voice data, cuts out the voice by pattern matching and replaces it with a character string of a code, and an emergency has occurred in which the character string is stored in the storage unit in advance. It is determined that there is a suspicious person when it coincides with a dangerous phrase (eg, “help” or “make money”) whose pronunciation is sometimes predicted. In this case, the dangerous word / phrase is associated with the determination sound pressure, and the presence of the suspicious person is determined when the sound data of the monitoring target 2 includes the dangerous word / phrase and the sound pressure of the word / phrase is equal to or higher than the determination sound pressure. Is preferred.

DESCRIPTION OF SYMBOLS 1 Reporting system 2 Monitoring object 2a Store area 2b Office area 3 Monitoring camera 4 Notification apparatus 41 Monitoring information acquisition part 42 Communication part 43 Operation part 44 Storage part 45 Control part 450 Electronic calendar part 451 Mode setting part 452 Intruder detection part 453 Entrance number detection unit 454 Time determination unit 455 Suspicious person detection unit 456 Communication control unit 5 Monitoring center 51 Center device 52 Display 6 Communication line network 7 Security sensor

Claims (4)

A reporting device that detects the presence of a suspicious person at least when the monitoring target is manned and reports it remotely,
An operation unit for a user to set and operate a monitoring mode set in an unmanned state or a non-monitoring mode set in a manned state;
A mode setting unit for setting the monitoring mode or the non-monitoring mode set and operated in the operation unit;
An intruder detection unit for detecting an intruder in the monitoring target in which the monitoring mode is set;
A clock section that outputs the current time;
A time storage unit for storing the monitoring start time;
A suspicious person detection unit for executing a suspicious person detection process for detecting a suspicious person existing in the monitoring target in the manned state ;
A reporting unit for reporting when the suspicious person is detected and when the intruder is detected ;
The suspicious person detection unit starts executing the suspicious person detection process when the current time becomes the monitoring start time, and ends the execution of the suspicious person detection process when the monitoring mode is set. Reporting device.
The notification device according to claim 1, further comprising a time determination unit that determines the monitoring start time based on the monitoring end time of the monitoring target.
Furthermore, a statistical information storage unit that stores the number of visitors corresponding to the time as statistical information;
The notification device according to claim 1, further comprising a time determination unit that determines, as the monitoring start time, a time at which the number of visitors is equal to or less than a threshold based on the statistical information.
Furthermore, a storage unit that stores information on a plurality of monitoring areas that divide the monitoring target and information on a specific monitoring area among the plurality of monitoring areas,
The mode setting unit sets the monitoring mode or non-monitoring mode for each monitoring area,
The intruder detection unit detects an intruder for each monitoring area where the monitoring mode is set,
The said suspicious person detection part is a notification apparatus as described in any one of Claim 1 thru | or 3 which complete | finishes execution of the said suspicious person detection process, if the said specific monitoring area is set to the said monitoring mode.

Images