JP2020077330A - Shop device - Google Patents

Abstract

To provide a shop device capable of transmitting a message to an important monitoring area and other monitoring areas with different criteria.SOLUTION: A shop device 10 includes: a first storage unit 13 that stores an arrangement position of each of a plurality of commodities in a shop and a monitoring area in the shop; an image acquisition unit 141 that acquires a captured image obtained by capturing an image of the monitoring area; a suspicious person detection unit 142 that detects a suspicious person from the captured image; a notification unit 143 that transmits a massage to a monitoring device 30 in the case where a suspicious person has been detected; an acceptance unit 144 that accepts one of the commodities among the plurality of commodities and a designation of an importance level for the commodity by a user; and an important monitoring area setting unit 145 that sets an important monitoring area on the basis of the arrangement position of the designated commodity and the designated importance level. The suspicious person detection unit 142 changes a reference for detecting a suspicious person from the captured image in accordance with whether or not the monitoring area includes the importance monitoring area.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a store device that monitors a store.

  Conventionally, an image that a store device installed in a store analyzes a captured image of the inside of the store and notifies a monitoring device installed in a monitoring center when a person detected from the captured image needs to be dealt with Surveillance system is used.

  For example, Patent Document 1 discloses an image monitoring system that monitors the status of a monitoring target with an image at a monitoring center. In this image monitoring system, the image monitoring device sends an emergency notification to the monitoring center and sends out the current image when the user performs an emergency notification operation.

  Further, Patent Document 2 discloses a device that acquires an image in a predetermined area around an important monitored object when a person's approach to the important monitored object is detected. When a person who satisfies a predetermined condition is detected from the image, this device notifies the monitoring center and transmits the monitoring image.

JP 2001-109973 A JP 2012-50031 A

  Generally, in a store apparatus that monitors a store using a captured image of the inside of the store, special skill is required to set an area to be monitored intensively. Therefore, in such a store apparatus, it is desired to be able to easily set the area to be monitored intensively.

  An object of the present invention is to provide a store apparatus that can easily set an area to be focused on in a store.

  In order to solve such a problem, the present invention is a store apparatus for monitoring a store, and a storage unit that stores each arrangement position of a plurality of products in the store and a monitor area in the store, and shoots the monitor area. An image acquisition unit that acquires the captured image, a suspicious person detection unit that detects a suspicious person from the captured image, a notification unit that sends a notification to the monitoring device when a suspicious person is detected, and multiple products by the user A receiving unit that receives designation of any of the products and the degree of importance of the product, and a focused monitoring area setting unit that sets a focused monitoring area based on the arrangement position of the designated product and the designated importance. And the suspicious person detection unit provides a store apparatus that changes a reference for detecting a suspicious person from a captured image according to whether or not the monitoring area includes a priority monitoring area.

  In this store apparatus, it is preferable that the reception unit further receives the setting of the number of each of the plurality of products, and the priority monitoring area setting unit further sets the priority monitoring area based on the number of each of the plurality of products. Is.

  It is preferable that the store apparatus further includes a store clerk detection unit that detects a store clerk of the store from the captured image, and the suspicious person detection unit changes the reference depending on whether the store clerk is detected.

  It is preferable that the store device further includes a congestion determination unit that determines whether or not the store is crowded, and the suspicious person detection unit changes the reference depending on whether or not the store is crowded. .

  With the store apparatus according to the present invention, it is possible to easily set an area to be focused on and monitored in the store.

It is a figure which shows the whole system structure of the image monitoring system 1. It is a top view which shows an example of the arrangement | positioning position of the goods in a store, a monitoring area, and the position of an imaging device. It is a figure which shows an example of the flowchart which shows operation | movement of a setting process. It is a figure which shows an example of the flowchart which shows operation | movement of a monitoring process. It is a figure which shows an example of the flowchart which shows operation | movement of notification determination processing. It is a figure which shows an example of the operation sequence of the image monitoring system 1. 6 is an example of a display screen displayed on the monitoring device 30.

  The image monitoring system according to the embodiment will be described below with reference to the drawings.

  FIG. 1 is a diagram showing an overall system configuration of an image monitoring system 1 according to the embodiment. As shown in FIG. 1, the image monitoring system 1 is connected to one or a plurality of store devices 10 installed in each of one or a plurality of stores and each store device 10 via a communication network such as a local area LAN or the Internet. And the monitoring device 30. In addition, one or more imaging devices 21, a sound output device 22, and one or more terminal devices 23 are connected to each store device 10.

  The store device 10 is, for example, a personal computer or the like, and includes an interface unit 11, a first communication unit 12, a first storage unit 13, and a first control unit 14.

  The interface unit 11 has an interface circuit conforming to a serial bus standard such as USB, and is connected to the image pickup device 21, the sound output device 22, and / or the terminal device 23 to transmit and receive various information. The interface unit 11 may have an interface circuit conforming to the short-distance wireless communication standard such as WiFi, Bluetooth (registered trademark), NFC, etc., instead of the interface circuit conforming to the serial bus standard.

  The first communication unit 12 has various communication interface circuits such as Ethernet (registered trademark), and transmits and receives various signals to and from the monitoring device 30 via a communication network.

The first storage unit 13 has a semiconductor memory such as ROM and RAM, a magnetic disk (HDD), or an optical disk drive such as CD-ROM and DVD-RAM, and its recording medium. The first storage unit 13 stores a computer program for controlling the store apparatus 10 and various data, and inputs / outputs these pieces of information to / from the first control unit 14. The computer program may be installed in the first storage unit 13 from a computer-readable portable recording medium such as a CD-ROM or a DVD-ROM using a known setup program or the like. Further, the storage unit 15 stores, as data, a background image 131, product arrangement information 132, monitoring area information 133, imaging device information 134, clerk information 135, and the like.
The background image 131 is an image captured by the imaging device 21 inside the store when there is no moving object. The product placement information 132 is information indicating the placement position of each of the plurality of products in the store. The monitoring area information 133 is information indicating the correspondence relationship between the arrangement position of each product and the monitoring area in the store. The imaging device information 134 is information indicating the correspondence between the surveillance area and the imaging device 21 that photographs the surveillance area. The clerk information 135 is information including a face photograph for each clerk.

  The first control unit 14 includes a processor such as a CPU and an MPU, a memory such as a ROM and a RAM, and peripheral circuits thereof, and executes various signal processes of the store apparatus 10. The first control unit 14 is an image acquisition unit 141, a suspicious person detection unit 142, a notification unit 143, a reception unit 144, an emphasis monitoring area setting unit 145, and a person detection unit 146, which are implemented as a functional module of a program operating on the processor. , A clerk detection unit 147, a congestion determination unit 148, an image transmission unit 149, and the like. A DSP, LSI, ASIC, FPGA or the like may be used as the first control unit 14.

  The imaging device 21 is a camera that is fixedly installed in the store where the store device 10 is installed and that captures an image of the inside of the store. The image pickup device 21 includes a photoelectric conversion element having a sensitivity to visible light, such as a CCD element or a C-MOS element, an imaging optical system that forms an image on the photoelectric conversion element, and an electrical output from the photoelectric conversion element. And an A / D converter that amplifies the signal and converts it into analog / digital (A / D). The imaging device 21 converts the captured image of each RGB color into a digital captured image in which each pixel has a brightness value in the range of 0 to 255, and outputs the digital captured image to the store device 10.

  The sound output device 22 is a speaker that is installed in the store where the store device 10 is installed and that outputs a sound in the store. The sound output device 22 receives a voice signal from the store device 10 and outputs a voice to a person in the store such as a clerk or a customer according to the received voice signal.

  The terminal device 23 is a terminal carried by a store clerk of the store device 10, and is, for example, an intercom (intercom) or a smartphone. The terminal device 23 has an interface for connecting to the store apparatus 10, a notification unit such as a display device and / or a voice output device for notifying a store clerk, and a processor for controlling them. The terminal device 23 receives the notification signal from the store device 10, and notifies the store clerk by image or voice according to the received notification signal.

  The imaging device 21, the sound output device 22, and / or the terminal device 23 may be provided integrally with the store device 10 instead of being provided separately from the store device 10.

  The monitoring device 30 is, for example, a server, and includes a second communication unit 31, an operation unit 32, a display unit 33, a second storage unit 34, and a second control unit 35.

  The second communication unit 31 has the same communication interface circuit as the first communication unit 12, and transmits and receives various signals to and from the store apparatus 10 via the communication network.

  The operation unit 32 is, for example, a touch panel, a mouse, a keyboard, or the like, receives an operation by a monitoring staff member of the monitoring center, and sends a signal according to the received operation to the second control unit 35.

  The display unit 33 is, for example, a liquid crystal display, an organic EL display, or the like, and displays a notification, a captured image, or the like received from the store apparatus 10 according to an instruction from the second control unit 35.

  The second storage unit 34 has the same semiconductor memory as the first storage unit 13, a magnetic disk or an optical disk drive, and its recording medium. The second storage unit 34 stores a computer program for controlling the monitoring device 30 and various data, and inputs / outputs these pieces of information from / to the second control unit 35. The computer program may be installed in the second storage unit 34 from a computer-readable portable recording medium such as a CD-ROM or a DVD-ROM using a known setup program or the like.

  The second control unit 35 has the same processor, memory, and peripheral circuits as the first control unit 14, and executes various signal processing of the monitoring device 30. The second control unit 35 has a monitoring unit 351 mounted as a functional module of a program operating on the processor.

FIG. 2 is a plan view showing an example of the arrangement positions of the products in the store, the monitoring areas, and the positions of the image pickup apparatus.
As shown in FIG. 2, a plurality of shelves S1 to S9 are arranged in the store, and the products are arranged on any of the shelves S1 to S9. A plurality of monitoring areas A1 to A9 including shelves S1 to S9 and their surroundings are set in the store. Note that a part of each monitoring area may be set so as to overlap with another monitoring area. Further, the imaging devices 21a to 21c capture at least one of the monitoring areas A1 to A9. In the present embodiment, the imaging device 21a is set to shoot the monitoring area A1, the imaging device 21b is set to shoot monitoring areas A2 to A5, and the imaging device 21c is set to shoot monitoring areas A6 to A9.

  FIG. 3 is a diagram showing an example of a flowchart showing the operation of the setting process by the store apparatus 10. The operation of the registration process according to this embodiment will be described below with reference to the flowchart shown in FIG. The operation flow described below is executed mainly by the first control unit 14 in cooperation with each unit of the store apparatus 10 based on a program stored in advance in the first storage unit 13. The setting process is executed by the store apparatus 10 before the monitoring process described below is executed or in parallel with the monitoring process.

  First, the reception unit 144 receives the importance setting instruction from the terminal device 23 via the interface unit 11 (step S101). The importance setting instruction is not limited to being received from the terminal device 23, but the instruction content input from a personal computer or the like installed in the store may be received via the interface unit 11. The degree-of-importance setting instruction includes any one or more of a plurality of items designated by the user of the image monitoring system 1, such as a store clerk, and a set of the degree of importance for the item. Next, the accepting unit 144 accepts the designation of the product and the importance included in the received importance setting instruction (step S102).

Next, the priority monitoring area setting means 145 sets a priority monitoring area based on the arrangement position of the designated product and the designated importance (step S103).
The priority monitoring area setting means 145 extracts, from the products included in the importance setting instruction, the products having the importance of a predetermined value or more. The priority monitoring area setting unit 145 specifies the arrangement position of the extracted product by referring to the product arrangement information 132, and specifies the monitoring area associated with the specified arrangement position by referring to the monitoring area information 133. The priority monitoring area setting means 145 sets the specified monitoring area as a priority monitoring area.

On the other hand, the priority monitoring area setting means 145 sets the monitoring area not set as the priority monitoring area to the normal monitoring area.
With the above, the operation of the setting process ends.
The priority monitoring area setting means 145 calculates the total value of the importance levels of the monitoring areas in which the products having the highest importance are placed, or the importance values of the products in each of the monitoring areas, and calculates the total value. The monitoring area with the maximum value may be set as the priority monitoring area.

  FIG. 4 is a diagram showing an example of a flowchart showing the operation of the monitoring process by the store apparatus 10. Hereinafter, the operation of the monitoring process according to the present embodiment will be described with reference to the flowchart shown in FIG. The operation flow described below is executed mainly by the first control unit 14 in cooperation with each unit of the store apparatus 10 based on a program stored in advance in the first storage unit 13. The monitoring process is executed for each imaging device 21.

First, the suspicious person detection unit 142 determines whether or not the surveillance area shown in the photographed image includes the priority surveillance area (step S201). The suspicious person detection means 142 identifies the monitoring area imaged by the imaging device 21 with reference to the imaging device information 134, and determines whether the identified monitoring area includes the priority monitoring area set in step S103 of FIG. judge.
When the monitoring area shown in the captured image includes the important monitoring area, the suspicious person detection unit 142 sets the reference for detecting the suspicious person as the reference for the important monitoring area (step S202).
When the surveillance area shown in the captured image does not include the priority surveillance area, the suspicious person detection unit 142 sets the standard for detecting the suspicious person to the standard for the normal surveillance area (step S203).

The criteria for detecting a suspicious person are the first criterion in which there are a predetermined number or more of people who have stayed in the surveillance area for the first hour or longer, and at least one person has stayed in the surveillance area for the second hour or longer. A second criterion is included. The second time is longer than the first time. When the photographed image includes a person who satisfies at least one of the first criterion and the second criterion, the shop device 10 detects the person as a suspicious person.
The first time and the second time in the standard for the priority monitoring area are shorter than the first time and the second time in the standard for the normal monitoring area, and the predetermined number of people in the standard for the priority monitoring area is the standard for the normal monitoring area. Less than the prescribed number in. That is, the store apparatus 10 detects a person with a short residence time or a person who is staying with a small number as a suspicious person when determining according to the criterion for the priority monitoring area, compared to determining according to the criterion for the normal monitoring area. It will be easier. However, in the reference for the priority monitoring area and the reference for the normal monitoring area, one or two of the first time, the second time, and the predetermined number of people may have the same value.

  Next, the store apparatus 10 applies the criterion set by the suspicious person detection unit 142 to execute the notification determination process (step S204), and returns the process to step S201.

  FIG. 5 is a diagram showing an example of a flowchart showing the operation of the notification determination process by the store apparatus 10. The operation of the notification determination process according to this embodiment will be described below with reference to the flowchart shown in FIG.

  First, the image acquisition unit 141 acquires, from the imaging device 21 via the interface unit 11, a captured image in which the imaging device 21 has captured the surveillance area in the store (step S301).

Next, the person detecting unit 146 detects a person from the captured image (step S302). The person detecting unit 146 obtains the brightness difference between corresponding pixels between the captured image and the background image 131 captured by the imaging device 21 that captured the captured image, and the pixel value of each pixel is the absolute brightness difference. A difference image represented by a value is generated. The person detecting unit 146 detects, in the captured image, a region in which the pixel value in the corresponding difference image is equal to or larger than a predetermined threshold as a moving body region. For example, the predetermined threshold can be an average value of the pixel values of the difference image. When the detected moving object region has a size within a predetermined range corresponding to a person, the person detecting unit 146 detects the moving object region as a person region in which the person is shown.
In addition, the person detecting unit 146 performs a tracking process on each of the detected person regions in the captured images sequentially acquired by the image acquiring unit 141 using a known tracking technique. For example, for each of the person areas in the latest captured image, the person detection unit 146 calculates the distance between the center of gravity position of the person area and the center of gravity position of the person area detected from the immediately preceding captured image, and the distance is calculated. Person areas that are equal to or less than a predetermined threshold are associated as person areas by the same person. The person detecting unit 146 may execute the tracking process using a method such as an optical flow or a particle filter. The person detection unit 146 stores, for each person area of the same person, the time when the person area is first detected.
If no person is detected from the captured image, the operation of the notification determination process ends.

On the other hand, when a person is detected from the captured image, the salesclerk detection unit 147 detects the salesclerk of the store from the detected person area (step S303). The store clerk detection unit 147 executes known face recognition processing on the person area detected by the person detection unit 146. The clerk detection unit 147 extracts a face from the person area, and determines that the similarity between the extracted face and the clerk's face stored in the clerk information 135 (for example, a normalized cross-correlation value) is equal to or greater than a predetermined threshold. In this case, the person reflected in the person area is detected as a clerk. When the store area detecting unit 147 determines that the person area detected by the person detecting unit 146 includes the color of the store employee uniform stored in the first storage unit 13 in advance at a predetermined ratio or more, the store area detecting unit 147 reflects the person area. The person present may be detected as a clerk.
When a clerk is detected, the suspicious person detection unit 142 changes the standard set in step S202 or S203 of FIG. 4 (step S304). The suspicious person detection unit 142 lengthens the first time or the second time with respect to the reference. Alternatively, the suspicious person detection unit 142 increases the predetermined number of people with respect to the reference.
When a clerk is detected in the captured image, the surveillance area is likely to be directly seen by the clerk's eyes. The store apparatus 10 can reduce the number of notifications to the monitoring device 30 by changing the reference when a salesclerk is detected in the captured image, and reduce the response load of the monitoring staff to the notification.
On the other hand, when the clerk is not detected in the captured image, the suspicious person detection unit 142 does not execute the process of step S304.

Next, the congestion determination unit 148 calculates the congestion degree indicating the degree of congestion in the store from the captured image (step S305). For example, the congestion determination unit 148 calculates the number of people detected from the captured image by the person detection unit 146 as the congestion degree. The congestion determination unit 148 may calculate, as the congestion degree, the number of persons who are located within a predetermined range, such as before the cash register, among the persons detected from the captured image. Further, the congestion determination unit 148 may calculate the congestion degree by weighting each person detected from the photographed image so that the weight of the person located within the predetermined range becomes large.
Next, the congestion determination unit 148 determines whether or not the store is crowded based on the calculated congestion degree (step S306). The congestion determination unit 148 determines that the store is busy when the congestion degree is equal to or higher than a predetermined threshold value, and determines that the store is not crowded when the congestion degree is lower than the predetermined threshold value.

When it is determined that the store is crowded, the suspicious person detection unit 142 changes the standard set in step S202 or S203 (step S307). The suspicious person detection unit 142 shortens the first time or the second time with respect to the reference. Alternatively, the suspicious person detection unit 142 reduces the predetermined number of people with respect to the reference.
When the store is crowded, many customers are obstructed and it is difficult for the clerk to reach the surveillance area. By changing the standard when the store is crowded, the store device 10 can increase the number of notifications to the monitoring device 30 and allow the monitoring staff to share the monitoring.
On the other hand, if the store is not determined to be crowded, the suspicious person detection unit 142 does not execute the process of step S307.
When it is determined that the store is crowded, the suspicious person detection unit 142 may increase the first time or the second time with respect to the reference, or may increase the predetermined number of people. If the store is crowded, the surveillance area is likely to be seen directly by the general public. This acts on the person who is going to commit a crime such as shoplifting to prevent the crime. Therefore, the store device 10 may reduce the number of notifications to the monitoring device 30 and reduce the response load of the monitoring staff by changing the standard when the store is crowded.

Next, the suspicious person detection unit 142 detects a suspicious person from the captured image according to the standard set in step S202, S203, S304, or S307 (step S308). The suspicious person detection unit 142 calculates the elapsed time from the time of the first detection to the current time for each person region of the same person detected by the person detection unit 146. The suspicious person detection unit 142 uses the number of each person area and the elapsed time calculated for each person area to determine whether the captured image satisfies the first criterion and the second criterion. The suspicious person detection unit 142 detects, as a suspicious person, a person in the person area determined to be staying in the monitoring area when the captured image satisfies at least one of the first criterion and the second criterion. ..
When a suspicious person is detected from the captured image, the notification unit 143 determines to send the notification to the monitoring device 30 (step S309), and ends the operation of the notification determination process.

  On the other hand, when the suspicious person is not detected from the captured image, the notification unit 143 does not execute the process of step S309 and ends the operation of the notification determination process.

  FIG. 6 is a diagram showing an example of an operation sequence of the image monitoring system 1. This operation sequence is executed based on a program stored in advance in each storage unit of each device, mainly by each control unit of each device, in cooperation with each element of the store device 10 and the monitoring device 30. .. This operation sequence is executed when the store device 10 detects a suspicious person in the notification determination process and determines to send a notification to the monitoring device 30.

  First, the notification unit 143 of the store apparatus 10 transmits the notification and the captured image used when the notification is determined to be transmitted to the monitoring apparatus 30 via the first communication unit 12 (step S401). The notification includes identification information of the store in which the store device 10 that has transmitted the notification is installed.

  Next, when the monitoring unit 351 of the monitoring device 30 receives the notification and the captured image from the store apparatus 10 via the second communication unit 31, the display unit 33 displays the identification information of the store included in the notification and the captured image. Is displayed (step S402).

FIG. 7 is an example of a display screen displayed on the monitoring device 30.
As shown in FIG. 7, on the display screen 400, the identification information 401 of the store that has transmitted the notification, the captured image 402 when a suspicious person is detected, the live image 403 displaying the live video, the voice notification button 404, the notification button 405, and An end button 406 or the like is displayed.
When the voice notification button 404 is pressed by the monitor, the monitoring device 30 transmits a voice output request for requesting output of a predetermined voice such as a warning to the store device 10 via the second communication unit 31. .. Upon receiving the voice output request, the store device 10 causes the sound output device 22 to output a predetermined voice through the interface unit 11. The monitoring device 30 may include a voice input unit (not shown) such as a microphone, accept voice input by a monitor, and transmit the received voice to the store device 10.
When the report button 405 is pressed by the monitoring staff, the monitoring device 30 transmits a report to another device (not shown) installed in the police or the like via the second communication unit 31.
When the monitor pushes the end button 406, the monitoring device 30 ends the display of the display screen 400.

  Next, the image transmission means 149 of the store apparatus 10 acquires the captured image newly captured by the imaging device 21 and transmits it to the monitoring device 30 via the first communication unit 12 (step S403). The image transmitting unit 149 transmits the acquired captured image to the monitoring device 30 every time the image capturing device 21 acquires a captured image newly captured.

Next, the monitoring unit 351 of the monitoring device 30 displays the new captured image acquired from the store apparatus 10 via the second communication unit 31 on the display unit 33 (step S404). Every time the monitoring unit 351 acquires a new captured image from the store apparatus 10, the monitoring unit 351 displays the acquired captured image on the display unit 33.
With the above, the operation sequence of the image monitoring system 1 ends.

  As described above, the store apparatus 10 according to the present invention sets the priority monitoring area based on the arrangement position and importance of the product designated by the user. As a result, the store apparatus 10 can easily set the area to be focused on and monitored in the store.

Although the preferred embodiments of the present invention have been described above, the present invention is not limited to these embodiments. For example, the accepting unit 144 may further accept the setting of the number of each of the plurality of products from the inventory management server that manages the number of products in stock via the first communication unit 12. The inventory management server can use an existing inventory management system such as a POS (point of sales system) system. In that case, the priority monitoring area setting unit 145 sets the priority monitoring area based on the number of each of the plurality of products in addition to the specified product, the specified importance, and the arrangement position of the product.
For example, the store apparatus 10 stores, in the product placement information 132, a product and a set of product placement positions in association with the number of products placed at the placement position. After step S103 in FIG. 3, the priority monitoring area setting unit 145 refers to the product placement information 132 and acquires the number of products received in step S102 for each placement position of the product. The priority monitoring area setting unit 145 sets the monitoring area in which the product is placed as the priority monitoring area only when the number of products whose importance is equal to or higher than a predetermined value is a predetermined number (for example, 1) or more. As a result, the store apparatus 10 can intensively monitor the area where the products that are not placed due to sold-out or the like are placed, and prevent unnecessary load on the surveillance staff. The number of stocks managed by the inventory management server may include the number stored in the warehouse instead of being placed in the store. Therefore, in addition to the information managed by the inventory management server, the area where the products are located is captured. The calculation may be performed by adding the information on the number of arrangements acquired from the camera image. By storing the image information, size, height information, and the like of the product in advance, the quantity placed in the store can be calculated from the captured image. Alternatively, it is possible to store an image in the absence of a product and determine that the product is out of stock if the image in the absence of the product matches the current image.
When the calculated quantity is equal to or larger than the predetermined quantity, the area is set as the priority monitoring area. The inventory management method is not limited to the above.

Further, the criterion for detecting the suspicious person may be only one of the first criterion and the second criterion, or may be another criterion different from both the first criterion and the second criterion. For example, the presence of a person whose face is covered with sunglasses or a mask may be used as a reference for detecting a suspicious person.
In this case, the first storage unit 13 stores in advance a head contour pattern such as an elliptical pattern, a sunglasses determination template image, and a mask determination template image. In step S308 of FIG. 5, the suspicious person detection unit 142 extracts a head candidate area from each person area detected by the person detection unit 146, and determines whether or not there is face concealment in the extracted head candidate area. Thus, a suspicious person is detected from the captured image. The suspicious person detection unit 142 extracts a region having a high similarity (for example, a normalized cross-correlation value) with the template image in each human region as a head candidate region using the head contour pattern as a template image. The suspicious person detection unit 142 respectively calculates the degrees of similarity between the extracted head candidate area and the sunglasses determination template image and the mask determination template image. The suspicious person detection unit 142 determines that the face is hidden when any of the calculated similarities is equal to or higher than a predetermined threshold, and the suspicious person is included in the person area corresponding to the similarity equal to or higher than the threshold. It is detected as a person area.

  Further, in the notification determination process of FIG. 5, the store apparatus 10 may omit one of the processes related to the detection of the clerk in steps S303 to S304 and the processes related to the calculation of the congestion degree in steps S305 to S307. Well, both processes may be omitted.

  As described above, various modifications can be made within the scope of the present invention in accordance with the embodiment.

  10 store device, 13 first storage unit, 141 image acquisition unit, 142 suspicious person detection unit, 143 notification unit, 144 reception unit, 145 focused monitoring area setting unit, 147 store clerk detection unit, 148 congestion determination unit, 30 monitoring device

Claims (4)

A store device for monitoring a store,
A storage unit that stores each arrangement position of a plurality of products in the store and a monitoring area in the store,
An image acquisition unit that acquires a captured image of the surveillance area,
A suspicious person detection unit that detects a suspicious person from the captured image,
If a suspicious person is detected, a notification unit that sends a notification to the monitoring device,
A receiving unit that receives designation of any one of the plurality of products by the user and importance of the product,
Based on the placement position of the designated product and the designated importance, a focused monitoring area setting unit for setting a focused monitoring area, and
The suspicious person detection unit changes a reference for detecting a suspicious person from the captured image according to whether the monitoring area includes the priority monitoring area,
A store device characterized by the above. The reception unit further receives the setting of the number of each of the plurality of products,
The store apparatus according to claim 1, wherein the priority monitoring area setting unit further sets the priority monitoring area based on the number of each of the plurality of products. Further comprising a clerk detection unit for detecting a clerk of the store from the captured image,
The store apparatus according to claim 1, wherein the suspicious person detection unit changes the reference according to whether a clerk is detected. Further having a congestion determination unit for determining whether the store is crowded,
The said suspicious person detection part is a store apparatus as described in any one of Claims 1-3 which changes the said reference according to whether the store is crowded.

Images