WO2021029086A1

WO2021029086A1 - Digital smart guide security system, method, and program

Info

Publication number: WO2021029086A1
Application number: PCT/JP2019/032278
Authority: WO
Inventors: 和夫三輪
Original assignee: 株式会社テクノミライ
Priority date: 2019-08-14
Filing date: 2019-08-19
Publication date: 2021-02-18
Also published as: JPWO2021029086A1; WO2021029035A1

Abstract

Provided is a digital smart guide security system, a method, and a program with which unlawful entry by suspicious persons or the like can be prevented, and with which a user can be guided to a target location without placing a burden on the user. A digital smart guide security system (1000) comprises, at an entrance to or inside a security area: a destination acquisition unit (111) that acquires information related to a target location to which a person or a vehicle will travel, and that acquires a video of such person or vehicle; an identification unit (112) that identifies, by means of the video, the person or the vehicle within the security area; and a guide unit (113) that guides the person or the vehicle identified by the identification unit (112) to the target location.

Description

Digital smart guide security systems, methods and programs

The present invention relates to a digital smart guide security system, a method and a program for taking a picture of a security area with a surveillance camera to prevent crime.

Patent Document 1 states, "In-building guidance system (claim 1) that transmits guidance information including a destination location and a user's current location to a mobile phone based on the sent destination location information and the location information of the mobile phone. "Is described. The technology of Patent Document 1 provides in-building guidance services such as automatic call registration of elevators, guidance to destinations, and contact with companions at meeting places by acquiring human location information using mobile phones and the like. It is related to the guidance system in the building to be provided.

JP-A-2002-117173

Since the guidance information in the building described in Patent Document 1 transmits guidance information to any user, it is not possible to prevent unauthorized entry by a suspicious person or the like.
In addition, the user must have a mobile phone.
In addition, the user must send the destination to the system.
An object of the present invention is to provide a digital smart guide security system, method and program that can prevent unauthorized entry by a suspicious person and guide the user to a destination without imposing a burden on the user. is there.

The digital smart guide security system according to the present invention acquires information on a destination where a person or a vehicle goes at the entrance or inside of a security area, and a destination acquisition means for acquiring an image of the person or the vehicle, and security. It is characterized by including an identification means for identifying a person or a vehicle in the area by an image, and a guide means for guiding the person or the vehicle identified by the identification means to the destination.

With this configuration, it is possible to prevent unauthorized entry by suspicious persons. In addition, since the user does not have to carry a mobile phone to receive the guidance or send the destination to the system side, the user can be guided to the destination without imposing a burden on the user.

The guidance means is adjusted to the distance between the position of the destination acquisition means and the position of the elevator and the time corresponding to the walking speed of the person from the time when the destination acquisition means acquires the information about the destination where the person goes. By calling the elevator to the entrance floor, it is possible to provide efficient and highly workable guidance without causing trouble to other elevator users.

The destination acquisition means aims at collating the face information and / or body feature information of a person in the video with the face information and / or body feature information accumulated in association with the section identification information of the section to which the person belongs. By acquiring the location, the destination location can be acquired based on highly accurate face recognition and / or recognition of body feature information.

Since the destination acquisition means acquires the destination location in response to the unlocking of the auto lock, the acquisition of the destination location can be automated, and prompt processing (prevention of unauthorized entry and guidance of the destination location) can be performed. It can be carried out. Especially in offices where many people come and go at the same time, it is possible to support multiple auto-lock devices. For example, 1 to n units.

The destination acquisition means acquires the destination location by photographing the display of the auto-lock device, so that a system can be retrofitted to the existing auto-lock device.

Since the unlocking is from the dwelling unit, the visitor can be selected and guided to the destination.

Since the unlocking is performed at the entrance or the entrance of the site, unwanted visitors can be refused at the entrance or the entrance of the site, and regular visitors can be sequentially guided to the destination.

The above guidance is an alarm that tells that the area is off limits, so that a suspicious person (intruder) can be effectively repelled.

The identification means recognizes a fire or a sign thereof by a camera that captures an image of a person or a vehicle in the security area, and the guidance means gives a fire warning based on the recognition result of the identification means. Fire alerts are also issued at any time during the digital smart guide security operation, so fire alerts can be multiplexed to further enhance the safety of residents and visitors. Moreover, since no new member is added, it can be carried out at low cost.

The digital smart guide security method according to the present invention includes a destination acquisition step of acquiring information about a destination where a person or a vehicle goes at the entrance or inside of a security area, and a destination acquisition step of acquiring an image of the person or the vehicle, and security. It is characterized by including an identification step for identifying a person or a vehicle in the area by an image, and a guidance step for guiding the person or the vehicle identified by the identification step to the destination.

The present invention uses a computer as a destination acquisition means for acquiring information about a destination where a person or a vehicle goes at the entrance or inside of a security area, and for acquiring an image of the person or the vehicle, and a person or a person in the security area. It functions as a digital smart guide security system characterized by comprising an identification means for identifying a vehicle by an image and a guidance means for guiding a person or a vehicle identified by the identification means to the destination. It is a program for.

According to the present invention, it is possible to prevent unauthorized entry by a suspicious person and to guide the user to a destination without imposing a burden on the user.

It is a block diagram which shows the structure of the digital smart guide security system which concerns on 1st Embodiment of this invention. It is a block diagram of the control part of the digital smart guide security system which concerns on 1st Embodiment of this invention. It is a block diagram which shows the whole using the digital smart guide security system which concerns on 1st Embodiment of this invention. It is a figure which shows the security application operation of the digital smart guide security system which concerns on 1st Embodiment of this invention. It is a flowchart which shows the digital smart guide security processing of the digital smart guide security system which concerns on 1st Embodiment of this invention. It is a flowchart which shows the digital smart guide security processing of the digital smart guide security system which concerns on 1st Embodiment of this invention. Three types of security belts that set people and vehicles to enter the site, building, private area in the facility, high security area, and high risk area of the digital smart guide security system according to the first embodiment of the present invention. It is a figure explaining. It is a subroutine which shows the identification process which identifies the suspicious person of the digital smart guide security system which concerns on 1st Embodiment of this invention. It is a figure which shows the structure of the high-rise apartment, the office, the hotel, and the parking lot of the skyscraper of the digital smart guide security system which concerns on 1st Embodiment of this invention. It is a figure explaining the security of the condominium (1F) of the skyscraper of FIG. It is a figure explaining the security of the condominium purpose floor of the skyscraper of FIG. It is a figure explaining the security of the office (1F) of the skyscraper of FIG. It is a figure explaining the security of the office objective floor (9F) of the skyscraper of FIG. It is a flowchart which shows the procedure of admission of a visitor and a resident to the skyscraper of FIG. It is a flowchart which shows the digital smart guide security processing of the digital smart guide security system applied to the skyscraper of FIG. It is a flowchart which shows the digital smart guide security processing of the digital smart guide security system applied to the site under the control of a company. It is a flowchart which shows the digital smart guide security processing of the digital smart guide security system applied to the site of a private house or an apartment house. It is a figure explaining the defense guide function of the digital smart guide security system which concerns on 1st Embodiment of this invention. It is a flowchart which shows the operation of the defense guide function by an image and sound in the explanatory view of FIG. It is a figure explaining the destination detection / registration function by the doorphone monitoring of the digital smart guide security system which concerns on 1st Embodiment of this invention. It is a flowchart which shows the operation of the destination detection / registration function by the doorphone monitoring of FIG. It is a flowchart which shows the operation of the face recognition function at the entrance of a building / dwelling unit in the digital smart guide security system which concerns on 1st Embodiment of this invention. It is a flowchart which shows the operation of the person tracking function by the AI accelerator of the digital smart guide security system which concerns on 1st Embodiment of this invention. It is a flowchart which shows the operation of the function which prevents a visitor or the like from entering an unauthorized place in the digital smart guide security system which concerns on 1st Embodiment of this invention. It is a flowchart which shows the operation of the function which prevents a visitor or the like from entering an unauthorized place in the digital smart guide security system which concerns on 1st Embodiment of this invention. It is a flowchart which shows the operation of the function which prevents a visitor or the like from entering an unauthorized place in the digital smart guide security system which concerns on 1st Embodiment of this invention. It is a flowchart which shows the operation of the function which notifies a person concerned about the history of a visitor and the like in the digital smart guide security system which concerns on 1st Embodiment of this invention. It is a figure explaining the piggybacking detection function of the digital smart guide security system which concerns on 1st Embodiment of this invention. It is a flowchart which shows the operation of the tailgating detection function of the digital smart guide security system which concerns on 1st Embodiment of this invention. It is a flowchart which shows the operation of the function which detects and cancels the registration that the visitor of the digital smart guide security system which concerns on 1st Embodiment of this invention has moved out. It is a figure explaining the digital smart guide security operation of the digital smart guide security system which concerns on 2nd Embodiment of this invention. It is a figure explaining the function of destination detection / deregistration at the entrance of the digital smart guide security system which concerns on the modification of this invention. It is a figure explaining the destination guidance function around the elevator of the digital smart guide security system which concerns on the modification of this invention. It is a figure which shows the application example to the international terminal of the digital smart guide security system which concerns on the modification of this invention. It is a flowchart which shows the operation of the destination detection / registration function by the entrance / exit management gate monitoring of the digital smart guide security system which concerns on the modification of this invention.

Hereinafter, embodiments for carrying out the present invention will be described in detail with reference to the accompanying drawings.
(First Embodiment)
FIG. 1 is a block diagram showing a configuration of a digital smart guide security system according to a first embodiment of the present invention.
The first embodiment is an example applied to a residence, a condominium and an office.
This digital smart guide security system is suitable for application to business establishments that require a high degree of management, such as residences, corporate offices, factories, research institutes, information processing rooms, and money collection rooms.

As shown in FIG. 1, the digital smart guide security system 1000 includes surveillance cameras 11 (photographing means) installed in various places in the security area, human sensor 20 and Wi-Fi installed in the security area. Controls the entire system, including the (Wireless Fidelity) terminal (hereinafter referred to as "Wi-Fi master unit") 30, the beacon master unit 40, and the mobile terminal device 50 (ID (Identification) terminal) carried by related parties (family members). The monitoring device 100 and the AI (Artificial Intelligence) accelerator (Accelerator) 200 (recognition means) are provided. The security area is a security area (security target area), and includes, for example, a site, a front door and a balcony for a residence, and an elevator hall, a balcony and a window for an office.

Although the monitoring device 100 is installed in the security area, it may be installed outside via a network (not shown). When the monitoring device 100 is installed on a server on the network, a plurality of security areas can be monitored.

<Surveillance camera 11>
The surveillance camera 11 captures an image (two-dimensional) of the security area specified in two dimensions or three dimensions.
A part or all of the surveillance camera 11 is a PTZ camera having a PTZ (pan / tilt / zoom) function, and is remotely controlled by the surveillance device 100. The surveillance cameras 11 are installed around the outer wall of the security target building, for example, at the entrance / exit where an intruder can enter / exit, the window opening, the outer periphery of the site boundary, and the corresponding site area. The image taken by the surveillance camera 11 is output to the surveillance device 100 and recorded in the recording unit 160.

<Human sensor 20>
The motion sensor 20 is a thermo camera, an infrared camera, or the like, and detects the temperature of a sensing object in the security area to detect a suspicious person in the security area.

<Wi-Fi master unit 30>
The Wi-Fi master unit 30 exchanges information with the Wi-Fi slave unit 51 of the mobile terminal device 50 using Wi-Fi. Further, the Wi-Fi master unit 30 can acquire position information by Wi-Fi positioning, that is, can acquire the position information of the Wi-Fi slave unit 51 by using the Wi-Fi access point and a predetermined position information service.

<Beacon master unit 40>
The beacon master unit 40 is a BLE transmitter installed at a front door or the like and transmits a beacon signal containing an individual identification code by BLE (Bluetooth Low Energy).
BLE is a wireless technology that detects proximity. The BLE is composed of a combination of a beacon master unit 40, which is a beacon device on the transmitting side, and an application of a mobile terminal device 50 (corresponding to the beacon slave unit 52 described later) that supports reception of radio waves from the beacon master unit 40. The BLE transmits unique ID information necessary for identification and reacts only to the application associated with the ID information of the mobile terminal device 50. The application of the mobile terminal device 50 registers the same identifier as the beacon master unit 40. The application (beacon slave unit 52) of the mobile terminal device 50 stands by in the background by executing an application equipped with a BLE function, and excites a predetermined action when approaching the beacon of the beacon master unit 40.

[Mobile terminal device 50]
The mobile terminal device 50 is carried by a family member or the like. The mobile terminal device 50 is, for example, a smartphone 50a, a tablet 50b, a notebook computer 50c, or the like. The mobile terminal device 50 is also a mobile phone, a PHS (Personal Handy-Phone System), a PDA (Personal Digital Assistants), a dedicated terminal, or the like. In the present embodiment, the mobile terminal device 50 can be used by a family member or the like in various places (that is, the current position), and can receive an e-mail or a video including a moving image from the monitoring device 100 via a telephone line (not shown). Is.

In the present embodiment, the mobile terminal device 50 assumes the use of a smartphone 50a (ID terminal), and each individual can use it in various places (that is, the current position). One of the mobile terminal devices 50 is located at a security company (not shown).

The smartphone 50a has a digital smart guide security application (hereinafter referred to as "security application"). When the security application is started by the background processing of each application, for example, the communication carrier network (fixed network and mobile phone communication network), the web service cloud 300 (see FIG. 3 below), or the Internet 303 (see FIG. 3 below). ) Can be connected to the cloud server 301 (see FIG. 3 below) on the web service cloud 300, and the telop about the suspicious person can be received from the cloud server 301. The smartphone 50a can notify a telop in which a suspicious person is detected on a standby screen or the like.

The smartphone 50a includes a Wi-Fi individual identification device (hereinafter referred to as a "Wi-Fi slave unit") 51, and a GPS 53 that captures the position thereof.
The smartphone 50a may be provided with the beacon slave unit 52. Alternatively, the smartphone 50a may include any one of the Wi-Fi slave unit 51, the beacon slave unit 52, and the GPS 53.

<Wi-Fi handset 51>
The Wi-Fi slave unit 51 receives and individually identifies the radio waves of the Wi-Fi master unit 30 installed in the business facility. The monitoring device 100 stores the arrangement information of the Wi-Fi master unit 30 installed in the facility as safety-related information. When the Wi-Fi slave unit 51 approaches the Wi-Fi master unit 30, it is possible to determine the ID and position of the person who carries the mobile terminal device 50.

<Beacon slave unit 52>
The beacon slave unit 52 is an application of the mobile terminal device 50 that supports reception of radio waves from the beacon master unit 40. The beacon master unit 40 transmits a beacon (unique ID information necessary for identification), and the application (beacon slave unit 52) of the mobile terminal device 50 excites a predetermined action when approaching the beacon of the beacon master unit 40. To do.

<GPS53>
The GPS 53 receives radio waves of position information from GPS satellites and the like. The GPS 53 acquires the position information by calculating the current position information as three parameters of latitude, longitude and altitude from the information received via the GPS antenna. The acquired position information is timely transmitted to the monitoring device 100.

In the present embodiment, an example using GPS satellites is shown as a means for acquiring position information, but a method using a positional relationship with a base station other than GPS may also be used. For example, when an Android (registered trademark) smartphone or a high-performance mobile phone with a camera is used as the mobile terminal device 50, which is a mobile terminal, a base station and a mobile phone communication network (not shown) are used in place of or in combination with GPS53. It is also possible to send and receive information to and from the mobile phone company server via the mobile phone company and acquire the current location information of the own terminal from the proximity confirmation.

Further, location information acquisition by Wi-Fi positioning, that is, location information acquisition using a Wi-Fi access point and a predetermined location information service may be used.

[Monitoring device 100]
The monitoring device 100 is installed in a residence or a building common area of a person concerned (for example, a family member) and centrally manages the security area. The monitoring device 100 may be a general server computer, a personal computer (PC), or the like.

The monitoring device 100 includes a control unit 110, an input unit 120, a storage unit 130, a display unit 140, an output unit 150, a recording unit 160 (recording means), and a registrant information / suspicious person information DB (database). It includes 165, a tracking DB 166, an image processing unit 170, an interface (I / F) unit 180, and a communication unit 190, and each unit is connected by a bus 195.

After that, when the subject is described as "○○ part is", the control unit 110 shall read each program from the ROM as necessary, load it into the RAM, and execute each function (described later). Each program may be stored in the storage unit 130 in advance, or may be incorporated into the monitoring device 100 when necessary via another storage medium or communication medium.

The control unit 110 is composed of a CPU (Central Processing Unit) and the like, controls the entire monitoring device 100, executes a control program, and functions as a digital smart guide security system. The detailed configuration of the control unit 110 will be described later.

The input unit 120 is an input device for the user of the monitoring device 100 to input instructions and the like, such as a keyboard, a mouse, a touch panel and a microphone provided on the screen of the display unit 140.

The storage unit 130 includes memories such as ROM (Read Only Memory), RAM (Random Access Memory), and EEPROM (Electrically Erasable Programmable Read-Only Memory), and stores various data and programs used by the control unit 110. The storage unit 130 stores still images or moving images received from the surveillance camera 11, various data and programs used by the control unit 110, and the like.

The display unit 140 displays the operating status of the monitoring device 100, the image received from the monitoring camera 11, the GUI (Graphical User Interface) for operating the monitoring device 100, and the like.

The output unit 150 is, for example, an interface, which outputs an audio signal from the monitoring device 100 to the acoustic system 155 (guidance means) in the security area, and also outputs a voice signal to the guide monitor 156 (guidance means). The image signal from 100 is output. As the audio signal output from the monitoring device 100 to the acoustic system 155, for example, an audio signal input from an audio input device such as a microphone provided in the input unit 120, or music data stored in the storage unit 130 is controlled by the control unit. 110 may be the reproduced audio signal. The sound system 155 includes an amplifier and a plurality of speakers arranged on the premises, and emits a signal input from the monitoring device 100 into the security area. The guide monitor 156 may be a TV or a movable tablet.

The recording unit 160 is composed of an external storage device such as an HDD (Hard Disk Drive), and records an image in the security area taken by the surveillance camera 11. The recording unit 160 records high image quality for a predetermined short time after shooting, converts it to low image quality after the predetermined short time elapses, and records for a predetermined long time.

The registrant information / suspicious person information DB 165 stores registrant information such as family members, guardians, and visitors, and suspicious person information. The registrant information / suspicious person information DB 165 accumulates face images (face information) of the registrant and the suspicious person as a face information DB (not shown). The face information of the registrant is accumulated in association with the lot identification information (for example, the house number in the case of an apartment, the room number in the case of a research institute, etc.). The registrant information / suspicious person information DB 165 may accumulate the accident history and the action history in association with the face information of the suspicious person as the accident history / action history DB. Basic data such as the face of a person registered in the face information DB and the accident history / action history DB is obtained from the headquarters, the head office, a security company, etc., which are not shown, via the I / F section 180, and the face. An information DB is constructed. In addition, mutual face information DB can be updated to the latest face image (face information) by exchanging information with the headquarters, head office, security company, etc. (not shown).

The tracking DB166 accumulates tracking facial / physical features such as a human face and physical features used in the AI accelerator 200. Moreover, in the case of a vehicle, the appearance is accumulated.

Further, it is provided with an image correspondence DB (not shown) that stores each position in two dimensions of the image taken by the surveillance camera 11 and each position in the three-dimensional space taken by the surveillance camera 11 in association with each other. The control unit 110 stores the shape defined in the three-dimensional space in the image correspondence DB in association with it by a projection transformation that projects it on a two-dimensional surface. The image correspondence DB may use a part of the memory area of the storage unit 130.

The image processing unit 170 is composed of a DSP (Digital Signal Processor) or the like, and performs predetermined processing on the received image. Predetermined processing includes contour extraction, image resizing, resolution conversion processing, and the like.

When the image captured by the surveillance camera 11 in 1 second is, for example, a 5-frame image, the 1/5 second image, the 2/5 second image, the 3/5 second image, the 4/5 second image, and the 5/5 second image. In the case of 10 frames of images per second in motion, the size of the moving object can be known by inputting the outer shape line of the object in the motion of 10 images.
The image processing unit 170 processes the image data taken by the surveillance camera 11 and outputs the image in the security area.

The I / F unit 180 connects each surveillance camera 11 arranged in the security area with the surveillance device 100. Further, the I / F unit 180 is connected to a headquarters, a head office, a security company, etc. (not shown) by a network or a dedicated line.
The communication unit 190 transmits / receives data to / from the mobile terminal device 50 via the base station. The communication unit 190 has a wireless communication function, and is connected to a control board using, for example, a UART (Universal Asynchronous Receiver Transmitter).

[Control unit 110]
FIG. 2 is a block diagram of the control unit 110 of the digital smart guide security system 1000 according to the first embodiment of the present invention.
The control unit 110 shown in FIG. 2 is composed of a CPU (Central Processing Unit) or the like, controls the entire monitoring device 100, executes a control program, and functions as a digital smart guide security system.
The control unit 110 includes a destination acquisition unit 111 (destination acquisition means), an identification unit 112 (recognition means), a guidance unit 113 (guidance means), an ID terminal detection unit 114 (ID terminal detection means), and an ID terminal registration. A unit 115 (ID terminal registration means) and a reporting unit 116 (reporting means) are provided.

<Control unit 110>
The control unit 110 determines whether or not the person has the ID terminal (mobile terminal device 50; smartphone 50a) detected by the ID terminal detection unit 114 (a person who has a predetermined ID such as a family member). ..

The control unit 110 excludes the person who possesses the ID terminal detected by the ID terminal detection unit 114 from the suspicious person.

The control unit 110 refers to the registrant information DB 165 to determine whether or not the person has the ID terminal (ID of the visitor or the like) registered by the ID terminal registration unit 115, and determines whether or not the person has the ID terminal (ID of the visitor or the like). ) Is excluded from suspicious persons.

The control unit 110 determines the risk of intrusion based on the position of a person or vehicle in the security area. For example, the risk of intrusion is determined based on where the intruder is on the security belts, the yellow belt Y, the orange belt O, and the red belt R (see FIGS. 6, 9 to 12).

The control unit 110 performs an image or voice dialogue or a voice warning according to the degree of danger.

The control unit 110 is based on the two-dimensional position of the person and the size of the person (particularly the size of the head of the person) identified by the person detection, and the three-dimensional space of the person by the image correspondence DB (not shown). Detect the position inside. Specifically, the control unit 110 reads out the projected shape that has been defined and stored in advance as the shape projected in the three-dimensional space from the image correspondence DB. The control unit 110 back-projects the shape defined in the three-dimensional space onto the two-dimensional plane based on the two-dimensional image of the person detected in the security area and the size of the person. The control unit 110 detects the three-dimensional position by performing a back-projection transformation from the image of one surveillance camera 11. In principle, it should not be possible to detect a 3D position in a 2D image, but it is assumed that the size of the person is known (assuming that there is almost no difference in the size of the head between people). The three-dimensional position can be detected based on the two-dimensional image taken by one surveillance camera 11 and the size information of the detected person.

<Destination acquisition unit 111>
At the entrance of the security area, the destination acquisition unit 111 acquires information on the destination where a person or a vehicle goes, and acquires the video. If it is a person, specifically, the destination acquisition unit 111 acquires the destination location based on the unlocking of the auto lock (for example, unlocking from the dwelling unit, unlocking at the entrance). By the way, the auto-lock system of the condominium automatically locks the door at the entrance (shared entrance) of the building, and the resident can enter the building after confirming the visitor by calling and video of the intercom.

<Identification unit 112>
The identification unit 112 identifies a person or a vehicle in the security area by video. In addition, the identification unit 112 detects a fire or a sign of fire from the image taken by the surveillance camera 11.
The identification unit 112 detects a person or a vehicle from the image taken by the surveillance camera 11 and detects the size thereof. Specifically, the identification unit 112 uses the AI accelerator 200 (described later) to identify a person or vehicle in the security area. The identification unit 112 issues a person or vehicle identification request to the AI accelerator 200, and the AI accelerator 200 executes an AI calculation other than the CPU and transmits the identification result of the person or vehicle to the identification unit 112. Since accuracy and high speed are required for identifying a person or a vehicle, the AI accelerator 200 is used for identifying a person or a vehicle.

In deep learning by the AI accelerator 200, the digital smart guide security system 1000 monitors only people or vehicles, as compared with image recognition by a conventional motion detection type surveillance camera using image difference. It is possible to detect an intruder with extremely high accuracy.

The digital smart guide security system 1000 detects an intruder in the security area by the tracking function (described later) of a person or a vehicle by the AI accelerator 200.

In the present embodiment, the identification unit 112 identifies a person or a vehicle by using the AI accelerator 200, but the thermo camera (or the motion sensor 20) may detect the person. That is, the motion sensor 20 detects the temperature in the security area. Then, the identification unit 112 detects the presence of a person (suspicious person candidate) by detecting the body temperature of the person by the motion sensor 20 and detecting the change in the captured image by the surveillance camera 11.

Note that the identification unit 112 may combine person identification using the AI accelerator 200 and person detection using a thermo camera (or motion sensor). For example, in the security area, AI accelerator 200 is used for the entrance, veranda, and windows where high speed of person detection is required, and the site of the boundary between the site and the outside where high speed of person identification is not required is a thermo. Use a camera (or motion sensor).

<Information unit 113>
The guide unit 113 guides the person or vehicle identified by the identification unit 112 to the destination. The guide unit 113 guides a person or a vehicle to a destination by, for example, voice guidance by an acoustic system 155 (see FIG. 2) or display by a guide monitor 156 (see FIG. 2).

<ID terminal detection unit 114 and ID terminal registration unit 115>
The ID terminal detection unit 114 detects an ID (Identification) terminal possessed by a non-intruder.
The ID terminal registration unit 115 registers the ID terminal possessed by the visitor or the like in the registrant information DB 165.

<Report section 116>
The reporting unit 116 warns the person or vehicle identified by the identification unit 112 with a voice corresponding to the area, and notifies the related persons of the existence of a suspicious person. The reporting unit 116 makes a report according to the degree of danger (degree of caution, degree of urgency).

The reporting unit 116 does not report the person who possesses the ID terminal detected by the ID terminal detecting unit 114.

[AI Accelerator 200]
The AI accelerator 200 is a dedicated processor that identifies a person or a vehicle, and uses a computing resource other than a CPU. The AI accelerator 200 is, for example, an accelerator for image processing by a processor enhanced with a GPU (Graphics Processing Unit) and signal processing using an FPGA (Field Programmable Gate Array). Further, the AI accelerator 200 executes the calculation of AI (Artificial Intelligence) on a dedicated hardware (for example, GPU).
The AI accelerator 200 tracks a person or a vehicle (described later) using the tracking DB166.

[Digital Smart Guide Security System]
FIG. 3 is a configuration diagram showing the whole using the digital smart guide security system 1000 according to the first embodiment of the present invention.
As shown in FIG. 3, the digital smart guide security system 1000 is active on the web service cloud 300 in cooperation with the cloud server (commercial server) 301 and the cloud server 301 that provide the digital smart guide security service. It has a Push notification server 302 that acquires information and notifies the user's smartphone 50a (mobile terminal device; ID terminal). The web service cloud 300 is connected to the Internet 303. The smartphone 50a can transmit texts and images to the cloud server 301 on the web service cloud 300 via the Internet 303. Further, the smartphone 50a receives the push notification from the push notification server 302 via the Internet 303. Further, the cloud server 301 and the push notification server 302 are connected to the smartphone 50a equipped with the security application via a communication carrier network (fixed network) (not shown) such as an LTE / 3G network.

As shown in FIG. 3, the digital smart guide security system 1000 detects intrusion of a suspicious person into an exclusion zone and push-notifies the smartphone 50a possessed by a person concerned (a condominium manager, a resident, etc.). ..
When the user taps the notification that comes to the smartphone 50a, the security application is activated and the zoom screen of the suspicious person is displayed, and the telop "A suspicious person has been detected at the entrance on the 1st floor" is played. At the same time, the content is read aloud. In this way, the suspicious person is notified by the telop and voice on the screen of the smartphone 50a. Further, by the operation of the user of the smartphone 50a, for example, in an emergency, the related organizations (police, fire department) are notified. In this case, the security company and the head office of the affiliated company are also automatically notified. Also, if there is no urgency or if you want to confirm, only the security company will be notified.

[Security app operation]
FIG. 4 is a diagram showing the operation of the security application of the digital smart guide security system 1000 according to the first embodiment of the present invention.
As shown on the left side of FIG. 4, a telop that detects a suspicious person is notified on the standby screen or the like of the smartphone 50a. By tapping the user, as shown in FIG. 4, the display of the smartphone 50a is switched to the security application operation display, the zoom screen of the suspicious person is displayed, and the position and situation of the suspicious person "suspicious person at the entrance on the 1st floor" is displayed. .. In addition, this telop is read aloud by automatic voice. Further, by tapping the user, the display of the smartphone 50a is displayed on four time-series screens as shown on the right side of FIG.

The operation of the digital smart guide security system configured as described above will be described below.
[Digital smart guide security processing]
5A and 5B are flowcharts showing digital smart guide security processing. This flow is executed by the control unit 110 (see FIG. 2) of the monitoring device 100. This flow takes the case of a high-rise condominium in a high-rise building as an example.

In step S11, an image in the security area (specific area) specified in three dimensions is taken. The surveillance camera 11 is, for example, a PTZ camera and is remotely controlled by the surveillance device 100. The image taken by the surveillance camera 11 is output to the surveillance device 100.

In step S12, the identification unit 112 of the control unit 110 detects a fire or a sign thereof from the image taken by the surveillance camera 11. In the present embodiment, a fire or a sign thereof (for example, generation of smoke) is detected by a surveillance camera 11 installed for guidance.
When a fire or a sign thereof is detected (step S12: Yes), a fire alarm is issued in step S13 and the process proceeds to step S14. If no fire or sign thereof is detected (step S12: No), the process proceeds to step S14.
Similar to the "defense guide function", the fire alarm is a voice guidance by the sound system 155 (see FIG. 2) and a display by the guide monitor 156 (see FIG. 2). Further, in the fire alarm, the fire occurrence area, the house number, the site camera image, and the like are transmitted to the PC or smartphone 50a of the person concerned.
When the digital smart guide security system 1000 detects a sign of fire such as fire or smoke as a defense guide function in the event of a fire, power outage, or electric leakage, the alarm occurrence information is promptly sent to the related personal computer and related parties. It is sent to the senior manager's smartphone 50a, a security company or related public institutions, and guides the residents, employees, visitors, etc. in the building with images and sounds of appropriate evacuation routes.

In particular, the digital smart guide security system 1000 gives a double alarm with a normal fire alarm. That is, the digital smart guide security system 1000 issues a fire alarm in addition to a normal fire alarm. As a result, fire alerts are also issued at any time while the digital smart guide security operation is being performed, so that fire alerts can be multiplexed and the safety of residents and visitors can be further enhanced. it can. Moreover, since no new member is added, it can be carried out at low cost.

In the present embodiment, the fire alarm and the guidance related to the "defense guide function" are processed in parallel, but when the fire alarm is executed, the processing of this flow may be terminated. ..

In step S14, the destination acquisition unit 111 of the control unit 110 acquires information about the destination where a person goes at the entrance of the security area. Here, the destination acquisition unit 111 acquires the destination location according to the unlocking of the auto-lock of the door at the entrance (common entrance).
In step S15, the destination acquisition unit 111 acquires a photographed image of the face by the auto-lock system and / or an image (video) of a person photographed by the surveillance camera 11 installed at the entrance (common entrance).

In step S16, the control unit 110 unlocks the auto lock of the door at the entrance from the dwelling unit.
In step S17, the identification unit 112 of the control unit 110 identifies whether or not the person who has acquired the information about the destination is a suspicious person (“FIG. 7 identification subroutine”). In the present embodiment, the identification unit 112 requests the AI accelerator 200 to track a person by AI, and the identification unit 112 waits for the result of tracking a person from the AI accelerator 200. Further, the identification unit 112 determines that the person is a suspicious person based on the face information of the person registered in the registrant information / suspicious person information DB 165. Alternatively, the identification unit 112 identifies a person who does not have the ID terminal or identification number card registered in advance in the registrant information / suspicious person information DB 165 as a suspicious person. In the present embodiment, the suspicious person is registered in the registrant information / suspicious person information DB 165, recognized and eliminated.

When the identified person is not a suspicious person (step S17: No), the guide unit 113 of the control unit 110 in step S18 associates the image of the person who has acquired the information about the destination location with the destination, and sequentially guides the destination to the destination. ..

If the identified person is a suspicious person in step S17 (step S17: Yes), the control unit 110 gives an alarm to the suspicious person by an announcement (guidance) informing the suspicious person that the area is off limits. Emit. An "exclusion zone" is a place that is not a route from the person's entrance to the destination.

In step S20, the control unit 110 acquires detailed information on the suspicious person (intruder). The suspicious person detailed information is the history information of the suspicious person registered in the registrant information / suspicious person information DB 165 and the image (including moving image) information of the suspicious person taken by the surveillance camera 11.

In step S21, the control unit 110 detects the intrusion direction of the suspicious person and the traveling speed of the suspicious person. The direction of the suspicious person's invasion and the traveling speed of the suspicious person can be obtained by collating the difference (change) of the images taken by the plurality of surveillance cameras 11.
In step S22, the control unit 110 determines the risk of intrusion based on the position of a person in the security area.

FIG. 6 is a diagram illustrating three types of security belts that set people and vehicles to enter a site, a building, a private area in a facility, a high security area, and a high risk area.
(1) Yellow belt Y
Set the yellow belt Y inward from the boundary of the site within a range of 30 cm to 4 m.
(2) Orange belt O
Set orange belt O between (1) and (3) (conditional alarm area)
(3) Red belt R
Red belt R is set in the range of 1m to 4m outward from the outer wall of the building (immediate notification area)

For example, the risk of intrusion is determined based on where the intruder is in the yellow belt Y (see FIG. 6), the orange belt O, or the red belt R. Specifically, the risk of intrusion is determined as follows.

(1) When a person or vehicle is detected in the yellow belt Y as shown in FIG. 6, the risk is low. When a person or vehicle is detected in the orange belt O, the risk is medium and the red belt. If a person or vehicle is detected in R, it can be determined that the risk is high. Further, when a person or a vehicle is detected outside the yellow belt Y, it can be determined that there is no risk.

(2) The degree of danger (degree of caution, degree of urgency) can be determined by the movement of a suspicious person. The movements of the suspicious person are, for example, the movement of the eyes and the movement of the neck (detailed later) and the movement of the arm (detailed later). If the movement of the suspicious person is unnatural, it can be determined that the degree of danger (degree of caution, degree of urgency) is high.

In step S23, the reporting unit 116 reports the above-mentioned detailed information on the suspicious person and emergency information according to the progress speed and the degree of danger (degree of caution, degree of urgency) of the suspicious person. The report transmits information about the suspicious person to, for example, the smartphone 50a of the person concerned. This report should be given a message, mark, highlighted letters, and color coding indicating the degree of danger according to the degree of risk of intrusion crime (classification of the degree of danger). Also, change the report destination according to the degree of danger or urgency. For example, when the suspicious person progresses quickly, the intruder determines that the intruder is dangerous and has a high degree of urgency, and notifies the intruder of the most urgent telop. In addition, the police will be included in the relevant organizations to be reported. And this report is given priority over the automatic registration process of the suspicious person. In addition, when a person is detected inside the red belt R, a telop with a high urgency of intrusion is notified (see FIG. 4), and when a person is detected outside the yellow belt Y, it is considered that there is no urgency of intrusion. Do not notify.

As described above, a telop for notifying the existence of a suspicious person is transmitted to the standby screen or the like of the smartphone 50a shown on the left side of FIG. By tapping the person concerned (apartment manager, etc.), as shown in Fig. 4, the zoom screen of the suspicious person is displayed, the position and situation of the suspicious person "suspicious person at the entrance on the 1st floor" is displayed, and this telop is displayed. Read aloud with automatic voice.

In step S24, the control unit 110 registers the information of the suspicious person in the security area in the registrant information / suspicious person information DB 165, and ends the process of this flow. As a result, intrusion information of a suspicious person is recorded, which is useful information for crime prevention.

FIG. 7 is a subroutine showing an identification process for identifying whether or not the person is a suspicious person. This subroutine is executed by the subroutine call in step S17 of FIG. 5A. FIG. 7 shows the first processing at the entrance (entrance).
In step S31, the control unit 110 determines whether or not the face of the person who has acquired the information about the destination by receiving the subroutine call matches the face of the suspicious person registered in the registrant information / suspicious person information DB 165. Determine. If the face of the person who acquired the information about the destination matches the face of the suspicious person registered in the registrant information / suspicious person information DB165 (step S31: Yes), it is determined in step S35 that the person is a suspicious person. Then, the process returns to step S17 of FIG. 5A.

When the face of the person who acquired the information about the destination does not match the face of the suspicious person registered in the registrant information / suspicious person information DB165 (step S31: No), the control unit 110 in step S32 sets the ID terminal. It is determined whether or not the person has the ID terminal (portable terminal device 50; smartphone 50a) detected by the detection unit 114 (a person who has a predetermined ID such as a family member).
In the case of a person who possesses the ID terminal detected by the ID terminal detection unit 114 (step S32: Yes), the control unit 110 in step S33 determines the person who possesses the ID terminal detected by the ID terminal detection unit 114. Exclude from suspicious persons and return to step S17 of FIG. 5A.

When the person does not have the ID terminal (step S32: No), the control unit 110 refers to the registrant information / suspicious person information DB 165 in step S34, and the ID terminal registered by the ID terminal registration unit 115 (step S32: No). It is determined whether or not the person has an ID) such as a visitor.
In the case of a person who has an ID terminal registered by the ID terminal registration unit 115 (step S34: Yes), the control unit 110 excludes the person who has registered the ID terminal (ID of a visitor or the like) from the suspicious person. Then, the process returns to step S17 of FIG. 5A.

If the ID terminal registration unit 115 is not the person who possesses the registered ID terminal (step S34: No), the control unit 110 determines in step S35 that the person is a suspicious person, and returns to step S18 in FIG. 5A. ..
In this way, when suspicious person information is registered in the registrant information / suspicious person information DB 165, when a family member or the like has an ID terminal, or when an ID terminal such as a visitor is registered in advance, the subsequent processing is performed. Skip to speed up processing.

[Application example of digital smart guide security system]
An application example of the digital smart guide security system will be described.
<High-rise apartment>
FIG. 8 is a diagram showing the configuration of a high-rise condominium (20F to 40F), an office (1F to 9F), a hotel (10F to 19F), and a parking lot (B1F to B3F) of a skyscraper. Hereinafter, an example in which the digital smart guide security system 1000 is applied to the high-rise condominium and office shown in FIG. 8 will be described. The hotel shown in FIG. 8 can be applied in the same manner as the office shown in FIG. The parking lot will be described later in the second embodiment of FIG.

FIG. 9 is a diagram illustrating security of the condominium (1F) (outer periphery of the building) of the skyscraper of FIG.
As shown in FIG. 9, a surveillance camera, a tablet, a monitor TV, a door phone, an auto-unlock device, a speaker, a BLE (Bluetooth Low Energy) beacon, a laser, and a Wi-Fi master unit are installed in the condominium (1F). There is. Further, a yellow belt Y, an orange belt O, and a red belt R are set. The inside of the red belt R on the outer wall of the building is a security inside the building. The visitor moves along the arrow in FIG.
Successful face recognition at the entrance shown in Fig. 9, doorphone, BLE beacon, smartphone 50a, weak radio wave of electric lock, contactless IC card, tablet, QR code, etc., allows passage to the target dwelling unit. To. The visitor moves along the arrow in FIG. By registering at the entrance shown in FIG. 9, passage to the target area is permitted.

Here, the security release by the above BLE will be described.
BLE is a technology for detecting close proximity. The digital smart guide security system 1000 has a function of allowing the user and his / her family to invade the caution range by installing an application dedicated to the digital smart guide security system on the smartphone. The user has a predetermined unlock code (installed in the app), and when it detects proximity, this unlock code is sent by BLE to the digital smart guide security system 1000, and it is temporarily in alert mode. To cancel. As a result, it becomes possible to exclude the behaviors of the user and his / her family from the detection target, and it is possible to perform highly accurate intrusion detection.

FIG. 10 is a diagram illustrating security on the condominium destination floor (26F) of the skyscraper of FIG.
As shown in FIG. 10, there is a living area on the condominium purpose floor (26F), one of which is the target dwelling unit. Red belt R is set as the target dwelling unit. A visitor who gets off the elevator moves to the target dwelling unit along the arrow in FIG.

<Office>
FIG. 11 is a diagram illustrating security of the office (1F) (outer periphery of the building) of the skyscraper of FIG.
As shown in FIG. 11, a surveillance camera, a tablet, a monitor TV, a door phone, an auto-lock release device, a speaker, a BLE beacon, a laser, and a Wi-Fi master unit are installed in the office (1F). Further, a yellow belt Y, an orange belt O, and a red belt R are set. The inside of the red belt R on the outer wall of the building is a security inside the building. The visitor moves along the arrow in FIG.
Successful face recognition at the entrance shown in FIG. 11, doorphone, BLE beacon, smartphone 50a, weak radio wave of electric lock, contactless IC card, tablet, QR code, etc., allow passage to the target dwelling unit. To. The visitor moves along the arrow in FIG. By registering at the reception shown in FIG. 11, passage to the target area is permitted.

FIG. 12 is a diagram illustrating security on the office destination floor (9F) of the skyscraper of FIG.
As shown in FIG. 12, there is an office area on the office purpose floor (9F), one of which is the target office. Red belt R is set for the target office. A visitor who gets off the elevator moves to the target office along the arrow in FIG.

<Visitors and residents>
FIG. 13 is a flowchart showing a procedure for admission of visitors and residents to the skyscraper of FIG. The flow of visitors and residents in FIG. 13 is not CPU processing, but will be described with step numbers for convenience.

i) Case of irregular visitor In step S51a, irregular visitor A visits resident S.
Mr. S's dwelling unit will be Room 602 on the 6th floor (see Fig. 10).
In step S52a, the visitor A calls the resident S with the 1st floor entrance doorphone (see FIG. 9).
In step S53a, the visitor A is allowed to enter the building through a doorphone dialogue with Mr. S, and the auto-lock is released by Mr. S (see FIG. 10).
In step S54a, the visitor A goes to the target dwelling unit.

ii) Case of regular visitor In step S51b, the regular visitor B pre-registers the face information. Also, pre-register your visit reservations.
In step S52b, a regular visitor B visits the resident S and tries to enter the building from the 1st floor entrance (see FIG. 9).
In step S53b, the visitor B enters the building after the auto-lock is released by face authentication, a door phone, a BLE beacon, a smartphone 50a, a tablet, a QR (Quick Response) code, or the like (see FIG. 10).
In step S54b, the visitor B goes to the target dwelling unit.

iii) Resident Case In step S51c, Resident R pre-registers face information in association with the house number.
In step S52c, resident R tries to enter the building from the 1st floor entrance (see FIG. 9).
In step S53c, resident R is automatically unlocked by face recognition, BLE beacon, smartphone 50a, weak radio waves of electric lock, contactless IC card, tablet, etc., and enters the building (see FIG. 10). .. In the case of face recognition or the like, if a dwelling unit number is input, it is possible to authenticate more reliably by collating with the face information or the like accumulated in association with the dwelling unit number.
In step S54c, the resident R goes to the target dwelling unit.

<Security inside the building>
FIG. 14 is a flowchart showing a digital smart guide security process of the digital smart guide security system 1000 applied to the skyscraper of FIG. FIG. 14 corresponds to a process of guarding the inside of a building. The process of guarding the outer periphery of the building will be described later with reference to FIG.
This flow is executed in the "always-on security mode" by the control unit 110 (see FIG. 2) of the monitoring device 100. In the "always-on security mode", the digital smart guide security system 1000 constantly monitors the status of the security area and prompts people to take appropriate measures. In addition, there is another "outing / home security mode" in the security mode. The "outing / home security mode" has an outing security mode and a home security mode, and the home security mode is automatically turned on / off from 23:00 to 5:00, for example. The outing security mode is turned on when going out and turned off when returning home.

Face recognition is performed at the building entrance in step S101.
In step S102, it is determined whether or not the person is permitted to enter the building by face recognition.
If it is not permitted to enter the building by face recognition (step S102: No), the process proceeds to step S103. For example, if the person is not allowed to enter the building by face recognition, it may be “i) an irregular visitor” (see FIG. 13).
In step S103, the destination is detected by the doorphone monitoring and registration is performed.
In step S104, it is determined whether or not the resident is permitted to enter the building.
If the resident is not allowed to enter the building (step S104: No), the door lock is not released in step S105. If the resident permits entry into the building (step S104: Yes), the process proceeds from step S111a to step S111d.

On the other hand, when it is permitted to enter the building by face recognition in step S102 (step S102: Yes), it is determined in step S106 whether or not the person is a resident.
If the person is allowed to enter the building by face recognition and is not a resident, it is judged as "ii) a regular visitor" (see FIG. 13) and registered in the registrant information / suspicious person information DB 165 in step S107. The destination of the visitor is acquired from the reservation of the visit, and the process proceeds to step S111a to step S111d.

When it is determined to be a resident in step S102 (step S106: Yes), it is determined that "iii) is a resident (see FIG. 13), and in step S107, the BLE beacon, the smartphone 50a, the weak radio wave of the electric lock, and the non-resident are determined. A person is authenticated by a contact type IC card or the like, and the process proceeds from step S111a to step S111d.

Hereinafter, the same processing is executed for each of the floors B3F to 40F of the skyscraper of FIG. 8 (see the dashed line box of FIG. 14). Since the processing is the same, the processing on the floor B3F will be described as a representative.
In step S111a, the human body is detected by the image of the surveillance camera installed in front of the elevator on the floor B3F.
In step S112a, a person is tracked by the AI accelerator 200 (see FIG. 1).
Piggybacking (described later) is detected in step S113a.
Step S114a prevents access to unauthorized locations.
In step S115a, the history of visitors and the like is notified to the persons concerned.
In step S116a, a defense guide using a tablet or the like is performed, and the process proceeds to step S117.
In step S117, it is detected that the visitor or the like has moved out and the registration is canceled.

In this way, (1) in front of the elevator on each floor in the building, around the stairs, at key points in the corridor, for example, a surveillance camera 11 is installed in units of 30 to 40 m to photograph visitors and the like. Then, the AI accelerator 200 is used to track a person, and to identify and track a visitor or the like. In addition, it is determined whether or not the person is heading for the target place, and entry to a place other than the target place is blocked.

(2) In front of the elevator on each floor in the building, around the stairs, at key locations in the corridor, for example, a tablet or monitor installed in units of 30 to 40 m and a voice function are used to perform defense guides using images and voice.

(3) When a visitor enters an unauthorized area or an important area such as a laboratory, the current image, the flow line at the time of this visit, the route, and the past history image of the person are notified to the smartphone 50a, etc. of the person concerned. To do.

(4) Detects intrusion into yellow belt Y, orange belt O, red belt R, etc., or intrusion into the site and the floor outside the permitted purpose in the building. If the intruder is moving, the position of the intruder is accurately determined by the image correspondence DB (not shown) and the back projection conversion, and it is detected that the intruder is in the site or the building.
This completes the security process inside the building.

<Security around the building>
FIG. 15 is a flowchart showing the digital smart guide security process of the digital smart guide security system 1000 applied to the site under the control of the company. FIG. 15 corresponds to a process of guarding the outer periphery of the building.
In step S121, an image of a surveillance camera with a microphone on the outer periphery of the building is acquired.
In step S122, the intrusion of a person into the yellow belt Y is detected.
In step S123, it is determined whether or not the BLE and the smartphone 50a have been authenticated.

If it has not been authenticated (step S123: No), in step S124, an automatic voice message such as "Please show the QR code to the surveillance camera" is given. If the authentication has been completed (step S123: Yes), the resident or the visitor is notified that the authentication has been performed by automatic voice in step S125, and the processing of this flow is terminated.

In step S126, it is determined whether or not the QR code has been authenticated, and if it has not been authenticated (step S126: No), the visit of an unregistered person is notified to the smartphone 50a of the person concerned, and the process proceeds to step S129. If the authentication has been completed (step S126: Yes), the visitor is notified by automatic voice that the authentication has been performed in step S128, and the processing of this flow ends.

In step S129, it is detected that the visitor has invaded the orange belt O.
In step S130, a conditional alert is issued, an automatic voice warning is given, a request for eviction is made, and the smartphone 50a of the person concerned is notified. Further, the person concerned may give a voice warning from the smartphone 50a.

In step S131, it is detected that the visitor has invaded the Red Belt R.
In step S132, an immediate alert is issued, threatening with an automatic voice, further requesting to move out, notifying the smartphone 50a of the person concerned, and ending the processing of this flow. Further, the person concerned may intimidate with a real voice from the smartphone 50a.

<Security around the building>
FIG. 16 is a flowchart showing a digital smart guide security process of the digital smart guide security system 1000 applied to the site of an individual house or an apartment house. FIG. 16 corresponds to a process of guarding the outer periphery of the building.
In step S141, an image of a surveillance camera with a microphone on the outer periphery of the building is acquired.
In step S142, the intrusion of a person into the yellow belt Y is detected.
In step S143, it is determined whether or not the BLE and the smartphone 50a have been authenticated.

If it has not been authenticated (step S143: No), it outputs a voice by operating from a smartphone in step S144 and tells "If you want to use it, please show the QR code to the surveillance camera". If the authentication has been completed (step S143: Yes), the resident or the visitor is notified by voice output by the operation from the smartphone in step S145 to end the process of this flow.

In step S146, it is determined whether or not the QR code has been authenticated, and if it has not been authenticated (step S146: No), the visit of the unregistered person is notified to the smartphone 50a of the person concerned, and the process proceeds to step S149. If the authentication has been completed (step S146: Yes), the visitor is notified that the authentication has been completed by outputting voice by operating from the smartphone in step S148, and the process of this flow is terminated.

In step S149, it is detected that the visitor has invaded the orange belt O.
In step S150, a conditional alert is issued, and a voice is output by an operation from the smartphone to warn and request to move out, and the related smartphones 50a are notified.

In step S151, it is detected that the visitor has invaded the red belt R.
In step S152, an immediate alarm is issued, a voice is output by an operation from the smartphone to intimidate the user, a request for evacuation is made, and the smartphone 50a of the person concerned is notified to end the processing of this flow.

<Outline of defense guide function>
The defense guide function using a tablet or the like will be described.
FIG. 17 is a diagram for explaining the defense guide function. The upper part of FIG. 17 shows the entrance on the 1st floor, the middle of FIG. 17 shows the floor that is not the destination of the visitor (for example, the 20th floor of FIG. 8), and the lower part of FIG. The floor of the visitor's destination (for example, 26F in FIG. 8) is shown.

The defense guide function using tablets, etc. provides appropriate communication guides to visitors and third parties by using images of tablets, speakers, and sound collection microphones installed in areas and passages in the facility. provide. It also protects the area inside the facility from unauthorized intruders.

As shown in the upper part of FIG. 17, the defense guide function uses images of monitors, tablets, etc. installed in the area of the facility, passages, etc., and voices of speakers, microphones for collecting sound, etc., to display the floor of the destination of visitor A. We will guide you to the directions according to the house number.

As shown in FIG. 17, the defense guide function warns that visitor A is in an area where entry is not permitted, displays a zoomed image of the person himself, and requests that he / she move out.

As shown in the lower part of Fig. 17, the defense guide function guides the directions according to the destination floor / house number of the visitor A.

<Defense guide function operation flow>
FIG. 18 is a flowchart showing the operation of the defense guide function by the image and the sound in the explanatory view of FIG. In explaining the flow of FIG. 18, the visitor shall take the following actions.
・ Premise The destination of visitor A is room 602 on the 26th floor. Mr. A shall be granted permission from the system to enter the public areas, elevators and room 602 (private area) on the 1st and 26th floors.
・ Behavior on Fig. 17 Mr. A enters the building from the entrance of the building on the 1st floor.
Mr. A moves in the 1st floor common corridor to get on the elevator.
Mr. A gets on the elevator on the 1st floor.
・ Behavior in Fig. 17 Mr. A gets off the elevator on the 20th floor, which is not the destination floor.
Mr. A moves in the common corridor on the 20th floor.
・ Behavior in the lower part of Fig. 17 Mr. A gets off the elevator on the 26th floor of the destination.
Mr. A moves in the common corridor on the 26th floor to go to Room 602.

As shown in FIG. 18, in step S201, monitoring of the entire building by the surveillance cameras 11 at various locations in the building is started.
In step S202, the destination (destination) of the visitor A is acquired according to the unlocking of the auto lock of the door at the entrance (shared entrance).
In step S203, an image is acquired from the surveillance camera 11 at the entrance of the building on the 1st floor (see FIG. 8).
In step S204, the tracking face / body characteristics of the visitor A are registered in the tracking DB 166.
In step S205, an image is acquired from the surveillance camera 11 in front of the 1st floor elevator.
In step S206, the person tracking function by the AI accelerator 200 is executed.
In step S207, the visitor A is detected.

In step S208, it is determined whether the visitor A is on a floor and a position (“no entry area”) outside the purpose permission. Here, even within the permitted floor, it is prohibited to move to an unauthorized place.

In step S209, it is confirmed whether the visitor A has permission to visit the destination.
If there is permission to visit, in step S210, the directions will be guided according to the floor and house number of the visitor's destination. For example, the voice guidance by the sound system 155 (see FIG. 1) and the display by the guide monitor 156 (see FIG. 1) guide the visitor A to the destination.

When the visit is prohibited in step S211 above, the position of the intruder is accurately determined by the image correspondence DB (not shown) and the back projection conversion, and it is detected that the intruder is in the prohibited area. That is, as described above, the monitoring device 110 (see FIG. 2) has a two-dimensional position of the image captured by the surveillance camera 11 (see FIG. 1) and each position in the three-dimensional space captured by the surveillance camera 11. An image-corresponding DB that stores the position in association with the position is provided. The control unit 110 stores the shape defined in the three-dimensional space in the image correspondence DB in association with each other by a projection transformation that projects the shape on the two-dimensional surface. Then, the control unit 110 accurately detects the position of the intruder by performing back-projection conversion based on the position information stored in the image correspondence DB.
In step S212, the user is warned that he / she is in an area where entry is not permitted, the zoom image of the person is displayed on the guide monitor 156 (see FIG. 1), the evacuation is requested, and the processing of this flow is terminated.

Similarly, in step S213, an image is acquired from the surveillance camera 11 on the floor (see FIG. 17) that is not the destination of the visitor.
In step S214, the person tracking function by the AI accelerator 200 is executed.
In step S215, the visitor A is detected.

In step S216, it is determined whether the visitor A is on a floor and a position (“no entry area”) outside the purpose permission. Here, even within the permitted floor, it is prohibited to move to an unauthorized place.

In step S217, it is confirmed whether the visitor A has permission to visit the destination.
If there is permission to visit, step S218 will guide the visitor according to the destination floor and house number (see the top of FIG. 17). For example, the voice guidance by the sound system 155 (see FIG. 1) and the display by the guide monitor 156 (see FIG. 1) guide the visitor A to the destination.

When the visit is prohibited in step S219, the position of the intruder is accurately determined by the image correspondence DB (not shown) and the back-projection conversion, and it is detected that the intruder is in the prohibited area.
In step S220, the user is warned that he / she is in an area where entry is not permitted, the zoom image of the person is displayed on the guide monitor 156 (see FIG. 1), the move-out is requested, and the processing of this flow is terminated.

Similarly, in step S221, an image is acquired from the surveillance camera 11 on the floor of the visitor's destination (see the bottom of FIG. 17).
In step S222, the person tracking function by the AI accelerator 200 is executed.
In step S223, the visitor A is detected.
In step S224, it is determined whether or not the visitor A is on a floor and a position (“exclusion zone”) outside the purpose permission. Here, even within the permitted floor, it is prohibited to move to an unauthorized place.

In step S225, it is confirmed whether the visitor A has permission to visit the destination.
If there is permission to visit, step S226 will guide the visitor according to the destination floor and house number. For example, the voice guidance by the sound system 155 (see FIG. 1) and the display by the guide monitor 156 (see FIG. 1) guide the visitor A to the destination.

When the visit is prohibited in step S227, the position of the intruder is accurately determined by the image correspondence DB (not shown) and the back projection conversion, and it is detected that the intruder is in the prohibited area.
In step S228, the user is warned that he / she is in an area where entry is not permitted, the zoom image of the person is displayed on the guide monitor 156 (see FIG. 1), the move-out is requested, and the process of this flow is terminated.

In this way, the digital smart guide security system 1000 sets the yellow belt Y, the orange belt O, and the red belt R in the building / site to be guarded.
For example, if visitor A gets permission from the doorphone at the entrance of the condominium and goes to room 602 on the 26th floor, visitor A gives permission to enter the public area, elevator and room 602 (private area) on the 1st and 26th floors. Granted.
If visitor A enters a place without permission, the regular route will be guided by the voice guidance by the sound system 155 (see Fig. 1) and the defense guide function by the guide monitor 156 (see Fig. 1). .. If a suspicious person enters an unauthorized location, the Defense Guide feature will warn them to leave. In this case, the person concerned is notified of entry into a place without the permission of the suspicious person.

<Destination detection / registration function by doorphone monitoring>
The destination detection / registration function by doorphone monitoring monitors the interaction between the visitor and the resident at the entrance doorphone, detects the visitor's destination (floor, house number, etc.), and associates it with the destination of the visitor. Face information is automatically registered in the tracking DB 166.

FIG. 19 is a diagram illustrating a destination detection / registration function by doorphone monitoring. FIG. 20 is a flowchart showing the operation of the destination detection / registration function by the doorphone monitoring of FIG. FIG. 19 shows the 1st floor entrance and the destination room. The flow of visitors and residents in FIG. 20 is not CPU processing, but will be described with step numbers for convenience. Visitors have step V, and residents (family) have step F.

The upper part of FIG. 19 shows the dwelling unit of the visitor's destination (for example, room 602 on the 38th floor).
As shown in the flow of FIG. 20, the visitor calls the resident of the destination dwelling unit with the door phone. For example, suppose that the visitor A calls the resident S of the room 602 with the door phone at the entrance on the 1st floor shown in the lower part of FIG. 19 (step V11). Visitor A gives his name, company name, etc. and tells the matter (step V12).

Resident S receives the doorphone contact of visitor A (step F11).
The doorphone master unit rings, and the resident S confirms the image of the visitor A in front of the doorphone and talks by voice (step F11). For example, Mr. S, a resident of Room 602 on the 38th floor, confirms the image of Mr. A and has a voice dialogue with Mr. A (step F11).
Resident S determines whether to release the auto lock and allow the visitor to enter the building (step F12).
When the resident S puts the visitor A inside, the resident S releases the auto lock (step F13).
If the resident S does not allow the visitor A to enter, the resident S refuses the visit (step F14).

In such a situation, the digital smart guide security system 1000 executes the destination detection / registration function by the following doorphone monitoring.
In step S301, the door phone is monitored by the face recognition camera (surveillance camera 11).
In step S302, the number of the destination house number entered by the visitor into the doorphone is read from the doorphone display by the face recognition camera.
Further, in parallel with S301, the data signal line of the doorphone is monitored in step S303.
In step S304, the number of the destination house number input by the visitor to the door phone is read from the data signal line and detected.
In step S305, information on which dwelling unit was called by the entrance door phone is acquired.
In step S306, an image of the visitor is acquired from the surveillance camera in front of the entrance.
In step S307, the face and body features of the visitor A are extracted from the acquired image.
In step S308, information on whether or not the resident S has released the auto lock is acquired.
In step S309, it is determined whether or not the resident S has released the auto lock.
When the resident S releases the auto lock (step S309: Yes), in step S310, the face and physical characteristics of the visitor extracted from the image of the surveillance camera 11 are tracked in association with the visitor's destination (house number, etc.). Register in DB166 for ending the processing of this flow. If the resident S does not release the auto lock (step S309: No), the process of this flow ends as it is. The visitor is guided to the destination based on the face and body characteristics and the destination registered in step S310.

<Face recognition and tracking function>
The face recognition and tracking functions in the digital smart guide security system 1000 will be described.
The face recognition and tracking functions in the digital smart guide security system 1000 include the following (1) to (3).
(1) Face recognition function at the entrance of a building / dwelling unit (see the flow in Fig. 21)
-Install a surveillance camera 11 for face recognition at the entrance of the building, the entrance to the dwelling unit of the resident, the entrance of the laboratory, and the like. The face recognition function may be an option at the hotel in consideration of privacy.
・ Residents, tenant employees, or regular visitors should pre-register face information and perform face recognition at the entrance. If the identity is confirmed, permission to enter the area from the entrance is automatically granted and the auto lock is released. However, whether or not to cancel automatically depends on the setting.

(2) Human tracking function by AI accelerator 200 (see FIG. 1) (see flow in FIG. 22)
-A surveillance camera 11 for face recognition is installed in front of the entrance, and an image of a visitor or the like is taken by this surveillance camera 11. Then, the tracking face and body characteristics of the person, the number of people, and the like are automatically registered in the tracking DB 166 (see FIG. 1).
-Install surveillance cameras 11 in front of the elevator, inside the elevator, at key points in the common corridor (for example, in units of 30 to 40 m), around the stairs, at the entrance to the emergency stairs, and at the boundary between the public area and the private area. Visitors and the like are identified from the images taken by the surveillance cameras 11 and the visitors are tracked. Visitors are identified by looking at the degree of matching between the captured image of the surveillance camera 11 for face authentication in front of the entrance and the features (particularly face registration information) automatically registered in the registrant information / suspicious person information DB165. ..
・ If it is determined that the person is a regular resident or a regular visitor, the auto lock in front of the elevator will be automatically released. However, whether or not to cancel automatically depends on the setting.

(3) Function to prevent visitors from entering unauthorized places (see the flow in FIGS. 23 to 25)
A visitor is identified using the person tracking function of the AI accelerator 200. In addition, if the movement of a visitor is tracked and a visitor is detected in an illegal area such as the floor other than the floor where the target dwelling unit is registered at the entrance or the entrance of an emergency staircase, the correct route is immediately transmitted by automatic voice. If the detected visitor is not registered as a legitimate visitor, it will be detected and registered as a suspicious person, immediately requested to move out by automatic voice, and the image of the suspicious person will be notified to the smartphone 50a of the person concerned. ..
When an intruder enters the yellow belt Y, the image of the surveillance camera 11 is analyzed on the three-dimensional space axis and the fourth-dimensional time axis. As a result, the position is accurately determined. A conditional alert is issued when the orange belt O is invaded, and an immediate alert is issued when the red belt R is invaded.
In addition, yellow belt Y, red belt R, etc. are defined in front of the outer periphery of the building and the exit of the emergency stairs on the roof to monitor intruders. At the outer periphery of the building, intrusion by people and vehicles is monitored.

FIG. 21 is a flowchart showing the operation of the face recognition function at the entrance of the building / dwelling unit (1).
In step S401, an image is acquired from the surveillance camera 11 for face authentication in front of the entrance.
In step S402, the face authentication process is performed and collated with the face registration information in the registrant information / suspicious person information DB 165.
In step S403, classification is performed based on face registration information, and the process branches to the following step.
In step S404, the related parties are notified of the history of visitors and the like.
In step S405, security / recording is continued.
In step S406, the auto lock at the entrance is released.

In step S408, the visitor is searched by referring to the registrant information / suspicious person information DB165.
In the case of a regular visitor, the regular visitor (acquaintance or the like) is set in step S409, and the regular visitor is processed in step S410 to proceed to step S413.
If the visitor is not a regular visitor, the visitor is treated as an irregular visitor (mail delivery, etc.) in step S411, and the irregular visitor is processed (identification required) in step S412, and the process proceeds to step S413.

In step S413, the registrant information / suspicious person information DB 165 is searched for the visit reservation, and it is confirmed whether the visit is reserved in advance.
In step S414, it is determined whether or not the visit is reserved.
If the visit is not reserved, the history of the visitor and the like is notified to the persons concerned in step S415, and the process of this flow is terminated.
If the visit is reserved, the auto-lock at the entrance is released in step S416 to end the processing of this flow.

FIG. 22 is a flowchart showing the operation of the person tracking function by the AI accelerator 200 (2).
In step S501, images are acquired from the surveillance cameras 11 in front of the entrance and in front of the elevator.
In step S502, the image taken by the surveillance camera 11 is analyzed by using the AI accelerator 200, and the face and body features for tracking of a person are detected.
In step S503, the person is identified.
In step S504, the image taken by the surveillance camera 11 is analyzed by using the AI accelerator 200, and the number of people in the group is detected. The reason for detecting the number of people in a group is that the tailgating detection function (see step S509 below) detects the tailgating.
In step S505, the group is identified.

In step S506, it is determined whether or not the entry of the place without permission is detected.
When it is detected that the place has entered the unauthorized area, it is determined in step S507 that the entry is an unauthorized area, and the process proceeds to step S509.
If the entry of the place without permission is not detected, it is determined in step S508 that it is normal, and the process proceeds to step S509.

In step S509, the tailgating detection function (see FIG. 27) is executed. Piggybacking means that multiple people pass through the door unlocked by one person's ID authentication. If you have tailgating, you will not be able to accurately record entry and exit, so you need to detect piggybacking.
In step S510, it is determined whether or not piggybacking is detected.
When a piggybacking is detected, in step S511, it is determined that the piggybacking (suspicious person) is made, and the processing of this flow ends.
If no piggybacking is detected, it is determined in step S512 that the process is normal, and the processing of this flow ends.

23 to 25 are flowcharts showing the operation of the function (3) of preventing a visitor or the like from entering an unauthorized place. FIG. 23 is a flowchart showing the “security of the public area in the floor”.
Public areas on the floor are, for example, 1st floor entrance, 1st floor lobby, lounge, elevator, aisle and stairs.
As shown in FIG. 23, in step S601, the constant security mode is started.
In step S602n (n is an arbitrary natural number), images are acquired from surveillance cameras 11 installed in various places such as in front of the elevator and in the common corridor.
In step S603n, a person is detected from the captured images of the surveillance cameras 11 installed at various places.
In step S604n, the person tracking function by the AI accelerator 200 is executed. That is, the human tracking function analyzes the image taken by the surveillance camera 11 using the AI accelerator 200, and detects the human tracking face and body features.

In step S605, it is determined whether or not the person is a resident or the like based on the detection result of the face and body characteristics for tracking of the person.
In the case of a resident or the like, monitoring is continued in step S606.
If the person is not a resident or the like, the permission to the area is determined in step S607, and the process proceeds to step S108.
In step S608, it is determined whether or not the area is permitted.
In the case of the permitted area, monitoring is continued in step S609.

If the area is not permitted, step S610 determines whether or not the visitor is a legitimate visitor.
In the case of a regular visitor, in step S611, the history of the visitor and the like is notified to the persons concerned.
In step S612, the "defense guide function" by the tablet or the like is executed to end the processing of this flow. The "defense guide function" is a function of guiding a person to a destination by voice guidance by an acoustic system 155 (see FIG. 2) and display by a guide monitor 156 (see FIG. 2).

If the visitor is not a regular visitor, the history of the visitor or the like is notified to the persons concerned in step S613.
In step S614, the "defense guide function" by the tablet or the like is executed to end the processing of this flow. The "defense guide function" in step S614 is a threat to a suspicious person (intruder). For example, an intrusion is warned by a voice warning by the sound system 155 (see FIG. 2) and a display by the guide monitor 156 (see FIG. 2). In addition, the guide monitor 156 displays the face and appearance of the intruder to warn the user.

FIG. 24 is a flowchart showing the above-mentioned (3) "security of the entrance / veranda of the resident's dwelling unit", which is a function of preventing visitors and the like from entering an unauthorized place.
In step S701, the constant security mode is started.
In step S702, the image of the surveillance camera 11 for face authentication in front of the entrance is acquired.
In step S703, it is confirmed whether or not a person has invaded the yellow belt Y at the entrance, and the process proceeds to step S706.
In step S704, the image of the surveillance camera 11 installed on the balcony is acquired.
In step S705, it is confirmed whether or not a person has invaded the red belt R of the balcony, and the process proceeds to step S706.

In step S706, the person tracking function by the AI accelerator 200 is executed.
In step S707, it is determined whether or not the person is a resident or the like.
In the case of a resident or the like, monitoring is continued in step S708.
If it is not a resident or the like, the exact position is specified in step S709. "Accurate position identification" can be realized by the following. That is, when an intruder invades the yellow belt Y, the orange belt O, the red belt R, etc. and moves on the floor outside the permission purpose in the site and the building, the position of the intruder is displayed in the image correspondence DB. Accurate detection is performed by performing back-projection conversion based on the stored position information.

In step S710, it is determined whether or not a person has invaded the orange belt O.
If no person has invaded the orange belt O, in step S711, monitoring is continued and the process proceeds to step S713.
When a person has invaded the orange belt O in step S710, the history of visitors and the like is notified to the persons concerned in step S712, and the process proceeds to step S713.

In step S713, it is determined whether or not a person has invaded the red belt R.
If no person has invaded the red belt R, in step S714, monitoring is continued and the processing of this flow ends. Since this flow is repeatedly executed at a predetermined cycle, monitoring will be continued.
When a person has invaded Red Gibert R in step S713, the process of this flow is terminated in step S715 by notifying the concerned parties of the history of visitors and the like.

FIG. 25 is a flowchart showing “security of the outer periphery of the building and emergency stairs” of the function (3) of preventing visitors and the like from entering unauthorized places.
In step S801, the constant security mode is started.
In step S802, the image of the surveillance camera 11 on the outer periphery of the building is acquired.
In step S803, it is confirmed whether or not a person has invaded the yellow belt Y on the outer periphery of the building, and the process proceeds to step S806.
In step S804, the image of the surveillance camera 11 installed at the rooftop exit is acquired.
In step S805, it is confirmed whether or not a person has invaded the red belt R at the rooftop exit, and the process proceeds to step S806.

In step S806, the person tracking function by the AI accelerator 200 is executed.
In step S807, it is determined whether or not the person is a resident or the like.
In the case of a resident or the like, monitoring is continued in step S808.
If it is not a resident or the like, the exact position is specified in step S809. That is, when an intruder invades the yellow belt Y, the orange belt O, the red belt R, etc. and moves on the floor outside the permission purpose in the site and the building, the position of the intruder is displayed in the image correspondence DB. Accurate detection is performed by performing back-projection conversion based on the stored position information.

In step S810, it is determined whether or not a person has invaded the orange belt O.
If no person has invaded the orange belt O, the monitoring is continued in step S811 and the process proceeds to step S813.
When a person has invaded the orange belt O in step S810, the history of visitors and the like is notified to the persons concerned in step S812, and the process proceeds to step S813.

In step S813, it is determined whether or not a person has invaded the red belt R.
If no person has invaded the red belt R, in step S814, monitoring is continued and the processing of this flow ends.

If a person has invaded Red Gibert R in step S813, the history of visitors and the like is notified to related parties in step S815, and the processing of this flow ends.

<History notification, tailgating detection, cancellation of registration when moving out>
The history notification, tailgating detection, and registration cancellation functions at the time of moving out in the digital smart guide security system 1000 include the following (4) to (6).
(4) A function to notify related parties of the history of visitors, etc. (detailed in FIG. 26)
・ When a visitor enters an unauthorized area or an important area, the current position and image, and the flow line and route from the time of entering the site / building at the time of this visit to the time of reaching the current position are shown by the persons concerned. Notify the PC, smartphone 50a, etc.
-Search the registrant information / suspicious person information DB165, and if there is a record of the person's past visits, add the history to the above notification.

-When the registrant information / suspicious person information DB 165 has an accident history / behavior history DB (including a case where an external accident history / behavior history DB can be accessed), the accident history / behavior history DB is searched and the accident history is searched. , If there is an action history, add the accident history and action history to the above notification.

(5) Piggybacking detection function (detailed in FIG. 27)
・ When automatically registering a visitor, if the visitor has a companion, make a group with the visitor as the group representative and the companion as a member, and set the number of people, representatives, and members of the group. Automatically register in registrant information / suspicious person information DB165.
・ Take pictures of visitors with surveillance cameras in various parts of the building. If the person is registered as a member of the group, there is no problem if he / she takes the same action as the member of the group, and if he / she takes another action, he / she is detected as a tailgating.

(6) Function to detect and cancel registration of visitors moving out (detailed in FIG. 28)
The digital smart guide security system 1000 monitors whether or not a visitor has moved out of the building, and if the visitor does not move out after a certain period of time, the visitor is detected as a suspicious person, registered, and related. Notify the image of the visitor to the smartphone 50a of the person or the like.

FIG. 26 is a flowchart showing the operation of the function of notifying related parties of the history of (4) visitors and the like.
In step S901, the current position and image of the person concerned are acquired.
In step S902, the movement route and the image sequence from the time when the person concerned enters the site and the building to reach the current position are acquired from the registrant information / suspicious person information DB 165, and the notification at the time of this visit is created.
In step S903, the registrant information / suspicious person information DB 165 is searched further retroactively, for example, the data up to 3 months ago is searched, and it is checked whether or not there is a history of the person concerned at the time of past visit.

In step S904, it is determined whether or not the past image of the relevant person has been found. If the past image of the person concerned is not found, the process proceeds to step S906.
When the past image of the person concerned is found, the past image history of the person concerned is added to the notification information, and the process proceeds to step S906.

In step S906, the accident history / action history DB (registrant information / suspicious person information DB 165) is referred to, and the face photo of the relevant person is used as a key to search for an accident history / action history.
In step S907, it is determined whether or not the accident history and behavior history of the relevant person have been found.
When the accident history and action history of the relevant person are found, the accident history and action history of the relevant person are added as notification information, and the process proceeds to step S909. If the accident history and action history of the relevant person are not found, the process proceeds to step S909 as it is.
In step S909, the created notification information is transmitted to the administrator, the visitor's visited resident's PC, smartphone 50a, or the like, and the processing of this flow is completed.

FIG. 27 is a diagram illustrating the above (5) tailgating detection function. The problem with conventional auto-locking is that when a regular visitor enters the building, a suspicious person can enter the building before the door closes. Therefore, in this embodiment, the tailgating is recognized and prevented by the image taken by the surveillance camera 11 or the like.
For example, the windbreak room at the entrance of an apartment, office, research institute, factory, money counting room, information center, etc. is set to yellow belt Y, and a person who enters the inside through the door outside the windbreak room is detected by a surveillance camera. To do. In addition, whether or not to set a green area G with a radius of 1.3 to 2 m around the doorphone device with an auto-lock release function, monitor a person who has entered the green area G with a surveillance camera, and perform an auto-lock release operation. Is determined.
After the auto-lock is released, the door on the side of the windbreak room is monitored by a surveillance camera, and the person who enters the building through the opened door and the accompanying person are judged to be regular visitors. Continue to monitor the inner door, detect people and companions entering the building before the door closes, determine that there is a possibility of tailgating, and say "Please perform auto-unlock operation one by one." Etc. to deter friends.
Further, a person who stays in the yellow belt Y for a long time, for example, 10 minutes or more, records an image as a suspicious person. It also counts the number of times a suspicious person or tailgating is recorded, and notifies the parties concerned, for example, when the same person is detected multiple times.

This will be described in more detail. First, in the case of a person who has completed normal entrance procedures in the hall in Green Area G, the authentication camera and surveillance camera 11 installed in front of the entrance / exit of the hall take pictures of the person and his / her companion, and as that person and his / her companion. Recognize, approve and remember as a normal visitor.
In addition, when the inside door is opened by a normal entrance auto-unlock operation, before the door is closed, the person does not enter the green area G, but enters the windbreak room at the entrance / exit away from the green area G and stops. When you try to enter the hall, you enter the green area G, recognize that you are not operating by the images of the authentication camera, surveillance camera 11, etc., and judge as a suspicious person who has not performed the formal admission procedure (suspicious person judgment part 1). Then, for example, the auto-unlock operation is guided by saying, "Please perform the auto-unlock operation one by one."
Nevertheless, if a friend enters the hall, the image of the suspicious person taken by the authentication camera, the surveillance camera 11, etc. is stored as the image of the caution person.

Furthermore, if a friend enters the building multiple times, it is judged to be an intruder and the image is stored as an image of the intruder.
Also, if you do not enter the green area G and do the auto-unlock operation as it is, it will be judged as a piggybacker (suspicious person judgment part 2), and "Please perform the auto-unlock operation one by one." Guide the unlocking operation.

In addition, since this system determines whether or not it is a legitimate companion based on the image, for families, by entering the outer door at the same time and entering the hall at the same time from the inner door after the auto unlock operation, it is legitimate. It is judged to be a companion of the family, etc.
For children, if the height is arbitrarily set, for example, 130 cm or less, it may be determined that the child is accompanied by a family member and the auto-lock operation guide may not be spoken.

Regular visitors such as residents and workers can unlock the auto-lock by using the auto-lock release key and the auto-lock release operation from inside the building.
In addition, for related persons such as residents and workers, the face image is stored in advance in association with the house number, etc., and even if the related person does not have the auto-lock release key, the input operation of the house number, etc. If you do, the face image stored in advance in association with the entered house number etc. will be compared with the face image of the visitor taken by the authentication camera, and if they match, the auto lock will be released. Good.
If there are multiple auto-lock doors, each has the same configuration.

FIG. 28 is a flowchart showing the operation of the above (5) tailgating detection function.
In step S1001, an image is acquired from the surveillance camera 11 in the windbreak room.
In step S1002, a person who has entered the yellow belt Y is detected from the image.
In step S1003, it is determined whether the person has entered the green area.
When entering the green area (step S1003: Yes), the green area is monitored by a surveillance camera for several seconds to several tens of seconds in step S1004, and it is determined whether or not the unlock operation is performed.

If the person is not in the green area (step S1003: No), in step S1005, a surveillance camera 11 monitors a person outside the green area, measures the number of people and the staying time, and proceeds to step S1011.
When the person performs the unlock operation in step S1006 (step S1006: Yes), the inner door opens in step S1007, and the inside door is monitored and detected by the surveillance camera 11 in step S1008. Is determined to be a regular visitor, and the process proceeds to step S1011.
If the person did not perform the unlock operation in step S1006 (step S1006: No), the inner door was closed in step S1009, and in step S1010 the door was opened by a person going out from inside and intruding at that time. The monitoring is continued and the process proceeds to step S1011.

In step S1011, the inner door is monitored by the surveillance camera, and it is determined that the visitor and the accompanying person detected immediately before the door is closed may be accompanied by a friend.
If there is a person who entered the museum with a friend in step S1012 (step S1012: Yes), in step S1013, it is detected that there is a possibility of a friend, and the image is urged to unlock one by one by voice. Record and proceed to step S1014.
If no person has entered the museum with a friend in step S1012 (step S1012: No), the process proceeds to step S1014.

In step S1014, it is determined whether or not there is a person who has stayed in the yellow belt Y for, for example, 10 minutes or more.
If there is a person staying in the yellow belt Y (step S1014: Yes), in step S1015, an image is recorded with that person as a suspicious person, and the process proceeds to step S1016.
If no one is staying in the yellow belt Y (step S1014: No), the process proceeds to step S1016.

In step S1016, it is determined whether the piggybacking or suspicious person is detected multiple times.
When it is detected as a piggybacking or a suspicious person multiple times (step S1016: Yes), in step S1017, the person is regarded as an intruder and the related person is notified of the image, and the process of this flow is terminated.
If it is not detected as a piggybacking or a suspicious person multiple times (step S1016: No), the process of this flow ends.

FIG. 29 is a flowchart showing the operation of the function (6) of detecting / canceling registration that a visitor or the like has moved out.
In step S1101, images are acquired from the surveillance cameras 11 in front of the entrance and in front of the elevator.
In step S1102, the person tracking function by the AI accelerator 200 is executed.
In step S1103, it is determined whether or not the person is a resident.
If it is determined to be a resident, it is determined to be a resident in step S1104, and the process of this flow is terminated without performing security in step S1105.
If it is not a resident, it is determined in step S1106 that it is a visitor, and in step S1107 it is determined whether or not the visitor is about to leave.

If the visitor is about to leave, step S1108 determines whether the visitor has returned from the destination.
When the visitor returns from the target place, the monitoring is canceled in step S1109, and the registration made when the visitor enters the building is canceled in step S1110 to end the processing of this flow.

If the visitor is not leaving in step S1107, or if the visitor does not return from the target location in step S1108, the "defense guide function" described above is executed in step S1111.
In step S1112, the image of the visitor is transmitted to the resident's smartphone 50a, and in step S113, the visitor is registered as a suspicious person in the registrant information / suspicious person information DB 165, and the process of this flow is completed.

As described in detail above, according to the present embodiment, the digital smart guide security system 1000 (see FIG. 1) acquires information on the destination where a person or a vehicle goes at the entrance of the security area, and also obtains information about the destination. The destination acquisition unit 111 that acquires the image, the identification unit 112 that identifies the person or vehicle in the security area by the image, and the guidance unit that guides the person or vehicle identified by the identification unit 112 to the destination. It is provided with 113.

For example, when the digital smart guide security system 1000 is applied to a house, condominium, office, or hotel, a dwelling unit (in the case of a house or office), a guest room, or a facility (in the case of a hotel) intended for a person by voice or display. In case). In the case of houses, condominiums, and offices, the destinations of visitors and the like are known because information on the destinations where people go is obtained at the entrance of the security area. The Digital Smart Guide Security System 1000, for example, informs the relevant visitor, "The place of visit is the 5th floor on the elevator on the right, and the dwelling unit at the end of the turn to the left." In addition, if a visitor is detected in an illegal area such as the entrance of an emergency staircase or on a floor other than the floor where the intended dwelling unit is registered at the entrance, the correct route will be immediately transmitted by automatic voice and the visitor will enter an unauthorized place. You can prevent that.

More specifically, the visitor presses the numeric keypad of the auto-lock device (enters the house number), the house number is displayed on the display of the auto-lock device, and the visitor confirms the displayed display number and makes a call. Do (press the call button).

The digital smart guide security system 1000 has an authentication camera installed in the green area G of the area where the auto-lock device is operated at a position where the display number and the face of the visitor who operates it can be photographed, and the auto-lock is performed by the resident. When is released, the face information of the visitor is stored in association with the entered dwelling unit number taken by the authentication camera, and for example, the visitor in room 306 on the 12th floor is guided to No. 306 on the 12th floor via the elevator. If the guide function is activated and you move off the elevator on the 12th floor, this system will guide you to No. 306 on the 12th floor.

In addition, in the digital smart guide security system 1000, when a visitor inputs a house number into the auto-lock device, an authentication camera installed in the green area G photographs the visitor's face and is registered in advance as a regular visitor. Judge whether it is a person or a suspicious person. It is also possible to determine that the person is a resident by holding the unlock key over.

If a visitor's companion tries to enter the same floor of No. 306 on the 12th floor, No. 309, the companion will automatically be told "It is different from Room 306." It sounds automatically and the security function is activated.

In the digital smart guide security system 1000, the authentication camera captures and recognizes the number displayed on the display of the auto-lock device, and the authentication camera photographs and inputs the visitor's face to recognize the visitor. Accurately guide you to the destination of the number and prevent suspicious persons such as piggybackers from entering the museum illegally or entering the restricted area.

Also, even inside the security area, at the gate from one area to another, the destination where a person or vehicle goes can be obtained, so the destination is not limited to the entrance, but the security area. It may be internal.

The destination acquisition means 111 acquires the destination location according to the collation between the face information of the person in the video and the face information accumulated in association with the section identification information of the section to which the person belongs. The destination can be obtained based on the recognition of high face recognition. This face information may be face information and / or body feature information.

Since the destination acquisition unit 111 acquires the destination location in response to the unlocking of the auto lock, the acquisition of the destination location can be automated, and rapid processing (prevention of unauthorized entry and guidance of the destination location) can be performed. It can be carried out. Especially in offices where many people come and go at the same time, it is possible to support multiple auto-lock devices. For example, 1 to n units.

Since the unlocking is from the dwelling unit, it is possible to select the visitor and guide him to the destination.

By unlocking at the entrance or the entrance of the site, unwanted visitors can be refused at the entrance or the entrance of the site, and regular visitors can be guided to the destination in sequence.

The guidance is an alarm that tells you that the area is off limits, so you can effectively repel suspicious persons (intruders).

The identification unit 112 recognizes a fire or a sign thereof by a camera that captures an image of a person or a vehicle in the security area, and the guide unit 113 digitally gives a fire warning based on the recognition result of the identification unit 112. -While the smart guide security operation is being executed, a fire alarm is also issued at any time, so fire alarms can be multiplexed and the safety of residents and visitors can be further improved. Moreover, since no new member is added, it can be carried out at low cost.

The present invention can be applied to an information processing center, a vault, a research institute, an elderly housing with a high degree of security, and the like. In addition, since the face recognition of the registered specific person is performed, if the specific person is a related person, it is possible to support unlocking, and if the specific person is a suspicious person, the suspicious person is in a building or the like. It can be prevented from entering.

(Second Embodiment)
FIG. 30 is a diagram illustrating a digital smart guide security operation of the digital smart guide security system 1000 according to the second embodiment of the present invention. FIG. 30 is a diagram showing a parking lot 60 in a security area. The first embodiment is an example applied to the parking lot 60. The parking lot can be similarly applied to the parking lots (B1F to B3F) in the public area of the skyscraper shown in FIG.
Since the configuration of the digital smart guide security system 1000 according to the second embodiment is the same as that in FIGS. 1 and 2, the description thereof will be omitted. However, the destination acquisition unit 111 of the control unit 110 shown in FIG. 2 acquires information on the destination where the vehicle (general vehicle, including motorcycles and bicycles) goes at the entrance of the parking lot 60 (security area), and obtains information on the destination. Get the video. Here, the destination (destination location) of the approaching vehicle is acquired from the availability of the parking lot 60.

As shown in FIG. 30, a surveillance camera 11, a sound system 155 such as a speaker, a charge settlement machine 61, and a flap plate (locking device) 62 are installed in the parking lot 60. The surveillance camera 11 is connected to the surveillance device 100 (see FIG. 1). In the example of FIG. 30, the parking lot 60 has the parking spaces of the numbers 1 to 17, the parking space of the number 9 is monthly, and the vehicles are stopped at the numbers 1 to 8, 10 to 14. .. Vehicle M is about to enter the parking lot 60 by turning left.
The control unit 110 shown in FIG. 2 detects the vehicle M from the image taken by the surveillance camera 11 installed at the entrance (inside the security area) of the parking lot.

The destination acquisition unit 111 of the control unit 110 shown in FIG. 2 acquires the destination of the approaching vehicle from the availability of the parking lot. The vehicle that has entered acquires an empty space in the parking lot 60 (parking space numbers 15 to 17 in FIG. 30) as a destination.
The identification unit 112 of the control unit 110 shown in FIG. 2 identifies the vehicle M entering the parking lot 60 based on the image taken by the surveillance camera 11. It is desirable to identify the vehicle number on the license plate.
The guide unit 113 of the control unit 110 shown in FIG. 2 sequentially guides the approaching vehicle M to the acquired parking space (destination place) of the destination. The guidance is a voice announcement by an acoustic system 155 such as a speaker, and a display by a guide monitor 156 (see FIG. 2).

When the digital smart guide security system 1000 is applied to the digital smart guide security of the parking lot 60 shown in FIG. 30, the control unit 110 (see FIG. 2) is a vehicle M entering the parking lot 60. In response to the notification of the sound system 155 such as a speaker, "there is a vacancy in the numbers 15 to 17 on the right hand side after turning right and proceeding, then turning left." This eliminates the need to search for empty spaces in the parking lot.

[Modification example]
The present invention can be applied to offices, laboratories, information processing centers, financial relations, factories, and the like. It can also be applied to air terminals, passenger planes, ultra-high-speed railways, passenger ships, hotels, elevators, and the like.
FIG. 31 is a diagram illustrating a destination detection and registration function at the entrance. Visitor A or user A scans the contactless IC card, magnetic card, QR code, etc. or smartphones equipped with these at the entry / exit management gate to enter / exit, and the system at that time Input the signal.
For example, a green area G having a radius of 2 to 3 m is set around the entrance / exit control gate, and a person who has entered the green area G is monitored by a surveillance camera.

When a visitor or user who enters or exits the entrance / exit control gate scans an IC chip, etc., the system collates with the registered IC chip, etc., and if it conforms, a conforming signal is emitted, and the gate emits a conforming signal. When opened, a surveillance camera installed in the green area G photographs the face and body of a gate passerby and stores the image.

For example, if the destination (destination) of the visitor is the information processing center No. 30 on the 38th floor, the system sends the information to the elevator with the 38th floor of the corresponding super high floor as the stop floor, and the area around the elevator on the 38th floor and around the elevator. The image taken by the surveillance camera installed in the corridor is compared with the image of the person in question captured and stored at the gate, and if it is determined that the visitor is the visitor, the monitor TV and tablet installed on the 38th floor 30 Guide the visitor along the route to Room No.

If the visitor mistakenly descends on the 36th floor of another stop floor, the system determines that the visitor has descended to an unintended floor, and the installed monitor TV, tablet, etc., is 36 on the relevant floor. Guiding the visitor on the floor and the route to room 30 on the 38th floor, and sending an image to the guard's PC, tablet or smartphone, the guard is moving incorrectly in real time. Visitors can be confirmed and the accuracy of security can be improved.

FIG. 32 is a diagram illustrating a destination guidance function around the elevator. For example, if the elevator area is set to a radius of 3 to 6 m, a surveillance camera is installed in front of the elevator where the elevator area is photographed, and the visitor moves to the elevator area, the visitor has moved to the elevator area. Judging that, the 38th floor, which is the destination floor, is controlled to be the stop floor of the elevator. This prevents visitors from going to different floors for improper purposes. In addition, by calling the elevator to the entrance floor (mostly on the 1st floor) according to the distance between the entrance and the elevator area and the time required to move between them, it does not bother other elevator users. It is possible to provide efficient and highly workable guidance. The time required for the movement should be adjusted to those who walk fast. If you are a user, if you know the users of the same destination in advance (such as office employees), you should match the users of that destination who walk fast. When an individual can be identified by a user's IC chip or the like at the entrance / exit management gate, it is preferable to match the walking speed of the user.

In addition, for example, the 30th to 36th floors of important floors are set as Z zones, and if an unauthorized person invades the area using an emergency staircase or the like, they are installed around the elevator boarding / alighting area and in the corridor. The system collates the image taken by the surveillance camera with the image in the DB that stores the image of the person permitted in advance, and the person concerned has moved to a floor number other than the permission. The floor corresponding to the monitor TV and tablet installed is the important floor Z zone, so you should move out immediately, guide the visitor to the movement route, and further, the guard's PC, tablet, etc. Alternatively, by sending an image to a smartphone and storing it, the guard can confirm the person who has moved incorrectly in real time, and the system can remember the person who moved into the important facility. it can.

FIG. 33 is a diagram showing an example of application to an international terminal.
Boarding tickets possessed by users at check-in counters such as air terminals, passenger planes, ultra-high-speed railways, passenger ships, hotels or elevators, security checkpoints, customs gates, immigration checkpoints or boarding gates. By scanning the QR code, etc., the user can check the reserved seat, room name, time, flight name, destination, boarding / alighting, etc. with the reservation details of the server, and the user will pass through the gate. , The system inputs and stores signals such as reserved seats. For example, in the case of a hotel, when a guest checks in, the guest room number is entered and memorized.

For example, a green area G having a radius of 2 to 3 m is set around the entrance / exit control gate, and users who have entered the green area G are monitored by a surveillance camera.
When a user entering or exiting the entry / exit control gate scans the QR code of the boarding ticket, the system collates with the registered QR code, etc., and if it matches, issues a conforming signal, the gate opens, and the gate opens. A surveillance camera installed in the green area G photographs the face and body of a gate passerby and stores the image.

For example, if the user's destination (destination) is Company A's flight A111 bound for Sapporo at 12:30 and the boarding gate 30 in the north wing, the system was photographed by a surveillance camera installed in the corridor. If the image is compared with the image of the relevant person taken and stored at the gate and the user is determined to be the user, the user is determined to be the user along the movement route to the boarding gate 30 by the installed monitor TV, tablet, or the like. To guide you. The system will guide you, for example, "Please proceed as it is. At the corner of the destination, if you are going to Sapporo, please turn left."

If the user mistakenly tries to go to boarding gate 20 in the North Wing on B222 flight from another company B at 12:50 to Kagoshima, the system determines that he is going in the wrong direction. However, the installed monitor TV, tablet, etc. guide the user of the movement route from that position to the boarding gate 30.

In the case of ultra-high-speed rail, passenger ships or passenger planes, when the QR code of the boarding ticket is scanned at the boarding gate, the system collates with the registered QR code, and if it is compatible, it issues a conforming signal. The user passes through the gate, and a surveillance camera installed in, for example, a green area G having a radius of 2 to 3 m around the boarding gate photographs the user's face and body, and stores the image. Further, the system inputs and stores a user's destination, such as a flight number, time, direction, number of floors, room number, car number, seat name, etc., in association with the image.

Then, the system collates the image taken by the surveillance camera installed at the elevator entrance / exit, the passage, etc. with the image of the user photographed and stored at the gate, and determines that the user is the user. , Guide the user along the movement route to the target seat by the installed monitor TV and tablet.

If the user tries to use a different floor number, room number, seat, etc., the system will determine that the user is going to the wrong seat, and the installed monitor TV, tablet, etc. will be in that position. Guide the user on the route from to the desired seat.
If the user still does not follow the guided travel route, the image can be transmitted to the PC, tablet or smartphone of the person concerned, and the person concerned can be guided by the broadcasting equipment or rush to the site.

FIG. 34 is a flowchart showing the operation of the destination detection / registration function by the entry / exit management gate monitoring. As shown in the flow of FIG. 34, it is assumed that the destination of the visitor is Room 30 on the 38th floor (step V21). Further, it is assumed that the destination of the user is N30 in the north wing, and the target flight is A111 flight departing from A airline company at 12:30 (step V22).

The entry / exit control gate reads a contactless IC card, a magnetic card, a QR code, etc., or a smartphone or the like equipped with these with a contactless reader or the like (step F21).
Following the decision by the system to allow the visitor or user to enter (step F22), if the visitor or user is allowed to enter, the gate is opened (step F23). If no visitors or users are allowed inside, the gate is closed (step F24).

In such a situation, the digital smart guide security system 1000 executes the destination detection / registration function by the following entry / exit management gate monitoring.
In step S1201, the data signal line of the entry / exit control gate is monitored.
In step S1202, the visitor's user ID and the like are acquired from the gate.
In step S1203, the DB is searched and the target floor / room number and the like are acquired from the user ID.
Further, in parallel with S1202, in step S1204, the user's ticket No. and the like are acquired from the gate.
In step S1205, the DB is searched and the target boarding gate of the aircraft is acquired from the ticket number of the user.
In step S1206, an image of a visitor or a user is acquired from a surveillance camera in front of the entrance.
In step S1207, the face and physical features of the visitor or user are extracted from the acquired image.
In step S1208, information on the open / closed state of the gate is acquired.
In step S1209, it is determined whether the gate is in the open state.
When the gate is open (step S1209: Yes), in step S1210, the face and physical characteristics of the visitor extracted from the image of the surveillance camera are associated with the destination (room number, etc.) of the visitor or the user for tracking. Register in DB166 and end the processing of this flow. If the gate is not in the open state (step S1209: No), the processing of this flow ends as it is. The visitor or user is guided to the destination based on the face and physical characteristics and the destination registered in step S1210.

The above description is an example of a preferred embodiment of the present invention, and the scope of the present invention is not limited thereto.
For example, each function of the digital smart guide security system 1000 may be executed independently or in combination.

Further, in each of the above embodiments, the names of digital smart guide security system and method are used, but this is for convenience of explanation, and includes digital smart defense guide security system, guide security method, and the like. May be good.

The digital smart guide security system and method of the present invention are also realized by a program for making a computer function as the digital smart guide security system or method of the present invention. The program may be stored on a computer-readable recording medium.

The recording medium on which this program is recorded may be the ROM itself of the digital smart guide security system, or a program reading device such as a CD-ROM drive is provided as an external storage device, and the recording medium is provided therein. It may be a CD-ROM or the like that can be read by inserting.

Further, each of the above configurations, functions, processing units, processing means, etc. may be realized by hardware by designing a part or all of them by, for example, an integrated circuit. In addition, each of the above configurations, functions, and the like may be realized by software for the processor to interpret and execute a program that realizes each function. Information such as programs, tables, and files that realize each function can be stored in memory, hard disks, recording devices such as SSDs (Solid State Drives), IC (Integrated Circuit) cards, SD (Secure Digital) cards, optical disks, etc. It can be held on a recording medium.

The present invention relates to a large capacity memory, 5G (5th generation mobile communication system), 4K8K broadcasting standard, infrared camera, PTZ camera, laser, radar, infrared sensor, motion sensor, BLE beacon, QR code reader, IoT (Internet of). Things) It can be realized by effectively using the latest technologies such as devices, Wi-Fi devices, GPS receivers, tablets, drones, helicopters, and artificial satellites.

All publications, patents and patent applications cited herein are incorporated herein by reference only.

The digital smart guide security system, method and program according to the present invention can be installed in a residence, a corporate office, a factory, a research institute, an information processing room, a money collection room, or any other business establishment requiring a high degree of management. Be expected. In addition, residential, commercial facilities, offices, hospitals, hotels, financial institutions, factories, laboratories, power plants, air terminals, meeting places, stadiums, museums and other buildings indoors and outdoors, transportation trains, ferries, airplanes The inside of the car is also covered.

11 Surveillance camera (shooting means)
20 Motion sensor 30 Wi-Fi master unit 40 Beacon master unit 50 Mobile terminal device (ID terminal)
50a Smartphone (mobile terminal device; ID terminal)
51 Wi-Fi handset 52 Beacon handset 53 GPS
60 Parking lot (security area)
100 Monitoring device 110 Control unit 111 Destination acquisition unit (destination acquisition means)
112 Identification unit (recognition means)
113 Information section (guidance means)
114 ID terminal detection unit (ID terminal detection means)
115 ID terminal registration unit (ID terminal registration means)
116 Reporting section (reporting means)
120 Input unit 130 Storage unit 140 Display unit 150 Output unit 155 Sound system (guidance means)
156 Guide monitor (guidance means)
160 Recording unit 165 Registrant information / Suspicious person information DB
166 Tracking DB
170 Image processing unit 180 Interface (I / F) unit 190 Communication unit 200 AI accelerator (recognition means)
1000 Digital Smart Guide Security System Y, O, R Security Belt M Vehicle

Claims

At the entrance or inside of the security area, a destination acquisition means for acquiring information on the destination where the person or vehicle goes and an image of the person or vehicle, and
Identification means to identify people or vehicles in the security area by video,
A digital smart guide security system including a guide means for guiding a person or a vehicle identified by the identification means to the destination.
The guidance means is adjusted to the distance between the position of the destination acquisition means and the position of the elevator and the time corresponding to the walking speed of the person from the time when the destination acquisition means acquires the information about the destination where the person goes. The digital smart guide security system according to invoice 1, wherein the elevator is called to the entrance floor.
The purpose of the destination acquisition means is to collate the human face information and / or body feature information in the video with the face information and / or body feature information accumulated in association with the section identification information of the section to which the person belongs. The digital smart guide security system according to claim 1, wherein the location is acquired.
The digital smart guide security system according to claim 1, wherein the destination acquisition means acquires a destination location in response to unlocking of an auto lock.
The digital smart guide security system according to claim 1, wherein the destination acquisition means acquires a destination location by photographing the display of the auto-lock device.
The digital smart guide security system according to claim 3, wherein the unlocking is from a dwelling unit.
The digital smart guide security system according to claim 3, wherein the unlocking is performed at the entrance or the entrance of the site.
The digital smart guide security system according to claim 1, wherein the guidance is an alarm indicating that the area is off limits.
The identification means recognizes a fire or a sign thereof by a camera that captures an image of a person or a vehicle in the security area.
The digital smart guide security system according to claim 1, wherein the guidance means gives a fire alarm based on the recognition result of the identification means.
At the entrance or inside of the security area, the destination acquisition step of acquiring information about the destination where the person or vehicle goes and acquiring the image of the person or vehicle,
An identification step that identifies a person or vehicle in the security area by video,
A digital smart guide security method comprising a guide step for guiding a person or a vehicle identified by the identification step to the destination.
Computer,
At the entrance or inside of the security area, information on the destination where the person or vehicle goes is acquired, and the destination acquisition means for acquiring the image of the person or vehicle and the identification of the person or vehicle in the security area by the image. A program for allowing a person or a vehicle identified by the identification means to function as a digital smart guide security system including means for guiding the person or vehicle to the destination.