Apparatus and method for controlling unmanned access based on video analysis to verify the reality and suitability of access requests

Abstract

An unmanned access control management device is disclosed, comprising: a shooting module that captures an area including the entrance door of a store to acquire an access image; and a processor that performs a process for authenticating an access request to the store via a phone call based on the access image; wherein, when the phone call is confirmed, the processor recognizes the occurrence of an object or movement in a preset area within the access image and determines whether to approve the access request based on the recognition result.

Description

Technology Field

[0001] The present disclosure relates to an unmanned access control management device and method, and more specifically, to a telephone number-based unmanned access control management device and method through access video analysis. Background Technology

[0002] With the recent surge in demand for unmanned store services, the need for efficient and secure unmanned access control systems is emerging. In particular, small business owners and small and medium-sized stores are in urgent need of access management solutions that can be easily implemented without complex installation or high costs.

[0003] In response to these demands, unmanned access control systems utilizing phone numbers have been developed. These systems operate by automatically opening the entrance door after a user calls a specific number installed in the store and the system records the caller's number. This provided the convenience of allowing entry using only an existing mobile phone, without the need for a separate physical key or card.

[0004] However, these conventional phone number-based unmanned access control systems may have the following serious security limitations.

[0005] First, there may be vulnerability issues with remote proxy authentication. Since conventional systems perform authentication by simply verifying a phone number, the entrance door can be opened even if a user who is not actually in front of the store makes a call from a remote location. For example, a situation could arise where the door is opened remotely for someone else while the user is not present in the store, which can pose a serious threat to store security.

[0006] Second, there may be an issue regarding the lack of a real-time situation verification function. Since existing phone authentication methods do not take into account the actual surroundings of the store at the time of incoming call, they cannot detect suspicious activity or abnormal access attempts. Consequently, there may be a problem in that malicious users attempting to infiltrate the store using legitimate phone numbers cannot be blocked in advance.

[0007] Due to these limitations, there is an urgent need to develop a more intelligent and secure unmanned access control system that can verify whether a user is actually in front of a store while maintaining phone number-based convenience, detect suspicious situations in real time through video analysis, and respond to various security threats. Prior art literature

[0008] Registered Patent 10-2463494 (November 04, 2022) The problem to be solved

[0009] The embodiments disclosed in this disclosure disclose a device and method for determining authenticity and suitability through entry video analysis during a phone number-based entry authentication attempt, and allowing the opening and closing of an entry door according to the determination result.

[0010] The problems that this disclosure aims to solve are not limited to those mentioned above, and other unmentioned problems will be clearly understood by a person skilled in the art from the description below. means of solving the problem

[0011] An apparatus according to the present disclosure for achieving the aforementioned technical problem comprises: a shooting module that captures an area including the entrance door of a store to acquire an entry image; and a processor that performs a process for authenticating an entry request to the store via telephone reception based on the entry image, wherein, when the telephone reception is confirmed, the processor recognizes the occurrence of an object or movement in an area set within the entry image and determines whether to approve the entry request based on the recognition result.

[0012] Meanwhile, the processor may approve the access request if it recognizes the occurrence of the object or movement, and reject the access request if it does not recognize the occurrence of the object or movement.

[0013] Additionally, when the processor recognizes the occurrence of the object or movement, it identifies the user in the entry / exit video, determines whether the identified user matches the recipient of the phone, and determines whether to approve the entry request based on the result of the determination.

[0014] Additionally, if the identified user matches the recipient of the phone call, the processor may extract feature information about the identified user from the entry / exit video, compare the extracted feature information with feature information about a previously stored blacklist, and determine whether to approve the entry request based on the comparison result.

[0015] In addition, when the occurrence of the movement is confirmed, the processor may determine whether to approve the access request by checking whether the phone number that attempted to receive the call is included in a stored blacklist or whitelist.

[0016] In addition, the processor can determine whether to approve the access request by checking whether the incoming call to the same phone number has been repeated more than a preset number of times.

[0017] In addition, when the incoming call is confirmed, the processor can acquire the entry and exit video for a preset time period before and after the time of the incoming call.

[0018] Additionally, when the processor recognizes the occurrence of the object or movement, it approves the entry request, stores the phone number that attempted to receive the call, and controls the door to open; when the object or movement is not recognized, it rejects the entry request, provides an alarm message regarding the entry request to the administrator terminal, and records a log regarding the entry request.

[0019] Meanwhile, the method according to the present disclosure is a telephone number-based unmanned access control management method through access video analysis performed by a device, comprising: a step of confirming an incoming call for an access request to a store; a step of acquiring an access video that captures an area including the entrance door of the store; a step of recognizing the occurrence of an object or movement in a pre-set area within the access video; and a step of determining whether to approve the access request based on the recognition result.

[0020] Additionally, the step of determining whether to approve the access request may include: a step of identifying a user within the access video; a step of extracting feature information for the identified user; a step of verifying the user using the extracted feature information and the phone number; and a step of determining whether to approve the access request based on the verification result.

[0021] In addition to this, a computer program stored on a computer-readable recording medium for executing the present disclosure may be further provided.

[0022] In addition, a computer-readable recording medium for recording a computer program for executing a method for implementing the present disclosure may be further provided. Effects of the invention

[0023] According to the aforementioned means for solving the problem of the present disclosure, by integrating real-time video analysis technology into a phone number-based unmanned access control system, it is possible to provide an innovative technology that resolves security vulnerabilities of existing systems and simultaneously ensures user convenience. In particular, remote proxy authentication can be prevented through video analysis performed simultaneously with the incoming call, and high security can be achieved through a multi-verification system.

[0024] The effects of the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by a person skilled in the art from the description below. Brief explanation of the drawing

[0025] FIG. 1 is a conceptual diagram of a system according to one embodiment of the present disclosure. Figure 2 is a diagram briefly illustrating the data flow for providing unmanned access control management services in the system illustrated in Figure 1. Figure 3 is a control block diagram of the device shown in Figure 1. FIG. 4 is a flowchart of an unmanned access control management method according to one embodiment of the present disclosure. FIG. 5 is a drawing showing the state in which a shooting module according to one embodiment of the present disclosure is installed, and FIG. 6 is an example of an entry / exit image obtained from the shooting module shown in FIG. 5. Figure 7 is a detailed flowchart of step S300 shown in Figure 4. Figure 8 is an example of an entry / exit image obtained from the shooting module shown in Figure 5. Specific details for implementing the invention

[0026] Throughout this disclosure, the same reference numerals denote the same components. This disclosure does not describe all elements of the embodiments, and general content in the art to which this disclosure pertains or content that overlaps between embodiments is omitted. The terms 'part, module, component, block' as used in the specification may be implemented in software or hardware, and depending on the embodiments, a plurality of 'parts, modules, components, blocks' may be implemented as a single component, or a single 'part, module, component, block' may include a plurality of components.

[0027] Throughout the specification, when a part is described as being "connected" to another part, this includes not only cases where they are directly connected but also cases where they are indirectly connected, and indirect connections include connections made via a wireless communication network.

[0028] Furthermore, when it is stated that a part "includes" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0029] Throughout the specification, when it is stated that a component is located "on" another component, this includes not only cases where a component is in contact with another component, but also cases where another component exists between the two components.

[0030] The terms first, second, etc. are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

[0031] Singular expressions include plural expressions unless there is an obvious exception in the context.

[0032] In each step, identification codes are used for convenience of explanation and do not describe the order of the steps; the steps may be performed differently from the specified order unless a specific order is clearly indicated in the context.

[0033] The operating principles and embodiments of the present disclosure will be described below with reference to the attached drawings.

[0034] In this specification, the term "device according to the present disclosure" includes all various devices capable of performing computational processing and providing results to a user. For example, the device according to the present disclosure may include all of a computer, a server device, and a portable terminal, or may be in the form of any one of these.

[0035] Here, the computer may include, for example, a notebook, desktop, laptop, tablet PC, slate PC, etc. equipped with a web browser.

[0036] The above server device is a server that processes information by communicating with an external device, and may include an application server, a computing server, a database server, a file server, a game server, a mail server, a proxy server, and a web server.

[0037] The above portable terminal may include, for example, all types of handheld-based wireless communication devices such as PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), WiBro (Wireless Broadband Internet) terminals, smartphones, etc., as well as wearable devices such as watches, rings, bracelets, anklets, necklaces, glasses, contact lenses, or head-mounted devices (HMDs).

[0038] Functions related to artificial intelligence according to the present disclosure are operated through a processor and memory. The processor may be composed of one or more processors. In this case, the one or more processors may be general-purpose processors such as CPUs, APs, and DSPs (Digital Signal Processors), graphics-dedicated processors such as GPUs and VPUs (Vision Processing Units), or artificial intelligence-dedicated processors such as NPUs. The one or more processors control the processing of input data according to predefined operation rules or artificial intelligence models stored in memory. Alternatively, if the one or more processors are artificial intelligence-dedicated processors, the artificial intelligence-dedicated processors may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

[0040] FIG. 1 is a conceptual diagram of a system according to one embodiment of the present disclosure.

[0041] Referring to FIG. 1, a system (1) according to one embodiment of the present disclosure may include a device (100) and a user terminal (200).

[0042] The device (100) can provide an unmanned access control management service according to the present disclosure.

[0043] The unmanned access control management service according to the present disclosure can determine whether to open or close the door after analyzing the access video to identify the caller upon receiving an unmanned access request via telephone. A detailed explanation regarding this will be provided later with reference to FIG. 2.

[0044] The user terminal (200) can be connected to the device (100) via a network and can receive an unmanned access control management service according to the present disclosure through the device (100).

[0045] For example, the user terminal (200) is a terminal possessed by the manager of the store, and may access a website or install an application to receive the service according to the present disclosure. The user terminal (200) may exchange data through the website or the application.

[0046] The system (1) according to one embodiment of the present disclosure can expect the effect of improving security by adding a video verification step in an unmanned access control method through phone number recording based on incoming calls.

[0048] Figure 2 is a diagram briefly illustrating the data flow for providing unmanned access control management services in the system illustrated in Figure 1.

[0049] Referring to FIG. 2, the device (100) may be provided within a store and may receive entry request information based on a phone call received from an external phone server (10) to a phone number designated in the store.

[0050] For example, the telephone server (10) may include a CID transmission and reception module, and when a call is received at a phone number designated in the store, it may transmit access request information including the phone number to the device (100).

[0051] The device (100) may be linked with the locking system and door CCTV system installed in the store, or may be implemented as a unit with at least a part of each system.

[0052] When the device (100) confirms a request for entry into a store upon receiving entry request information from a telephone server (10), it can acquire an entry video through an entry door CCTV system and analyze the entry video to verify whether the entry request is a legitimate entry request. For example, the device (100) can verify the entry request based on whether the user appearing in the entry video matches the recipient of the telephone call.

[0053] The device (100) determines whether to approve the access request based on the verification result of the access request, and if the access request is approved, it can store the phone number included in the access request information and control the door to be opened through the locking device system.

[0055] Figure 3 is a control block diagram of the device shown in Figure 1.

[0056] Referring to FIG. 3, a device (100) according to one embodiment of the present disclosure may include a processor (110), a communication module (120), a memory (130), a driving module (140), and a shooting module (150).

[0057] The components illustrated in FIG. 3 are not essential for implementing the device (100) according to the present disclosure, so the device (100) described in this specification may have more or fewer components than the components listed above.

[0058] The processor (110) can perform a process for providing an unmanned access control management service according to the present disclosure.

[0059] The processor (110) may be implemented with a memory that stores data for an algorithm or a program that reproduces the algorithm for controlling the operation of components within the device, and at least one processor (not shown) that performs the aforementioned operation using the data stored in the memory. In this case, the memory and the processor may each be implemented as separate chips. Alternatively, the memory and the processor may be implemented as a single chip.

[0060] In addition, the processor (110) may control one or more of the components described above in combination to implement various embodiments according to the present disclosure described in the drawings below on the device.

[0061] For example, when a call is received, the processor (110) can analyze the entry / exit video to check whether movement has occurred in a pre-set area and determine whether to approve the entry / exit request based on whether movement has occurred.

[0062] Additionally, the processor (110) may approve the access request when the occurrence of the movement is confirmed, and reject the access request when the occurrence of the movement is not confirmed.

[0063] Additionally, when the movement is detected, the processor (110) identifies the user in the entry / exit video, determines whether the identified user matches the recipient of the phone, and determines whether to approve the entry request based on the result of the determination.

[0064] Additionally, the processor (110) can extract feature information about the identified user from the entry / exit video when the identified user and the recipient of the phone match, compare the extracted feature information with feature information about a previously stored blacklist, and determine whether to approve the entry / exit request based on the comparison result.

[0065] Additionally, when the above processor (110) confirms the occurrence of the above movement, it can determine whether to approve the above entry request by checking whether the phone number that attempted to receive the call is included in a stored blacklist or whitelist.

[0066] Additionally, the processor (110) can determine whether to approve the entry request by checking whether the phone call received by the same phone number has been repeated more than a preset number of times.

[0067] Additionally, the processor (110) can acquire the entry and exit video for a preset time period before and after the time of the phone call when the phone call is confirmed.

[0068] Additionally, the processor (110) may, when the occurrence of the movement is confirmed, approve the entry request, store the phone number that attempted to receive the call, and control the door to open, and when the occurrence of the movement is not confirmed, reject the entry request, provide an alarm message regarding the entry request to the administrator terminal, and record a log regarding the entry request.

[0069] The communication module (120) may include one or more components that enable communication with an external device, and may include, for example, at least one of a wired communication module, a wireless communication module, a short-range communication module, and a location information module.

[0070] The wired communication module may include various wired communication modules such as a Local Area Network (LAN) module, a Wide Area Network (WAN) module, or a Value Added Network (VAN) module, as well as various cable communication modules such as USB (Universal Serial Bus), HDMI (High Definition Multimedia Interface), DVI (Digital Visual Interface), RS-232 (recommended standard 232), power line communication, or POTS (plain old telephone service).

[0071] In addition to Wi-Fi modules and WiBro (Wireless broadband) modules, the wireless communication module may include wireless communication modules that support various wireless communication methods such as GSM (global System for Mobile Communication), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), UMTS (universal mobile telecommunications system), TDMA (Time Division Multiple Access), LTE (Long Term Evolution), 4G, 5G, and 6G.

[0072] The wireless communication module may include a wireless communication interface comprising an antenna and a transmitter that transmit a mobile communication signal. Additionally, the wireless communication module may further include a signal conversion module that modulates a digital control signal output from the processor (110) through the wireless communication interface into an analog wireless signal under the control of the processor (110).

[0073] A short-range communication module is for short-range communication and can support short-range communication by using at least one of Bluetooth™, RFID (Radio Frequency Identification), Infrared Data Association (IrDA), UWB (Ultra Wideband), ZigBee, NFC (Near Field Communication), Wi-Fi (Wireless-Fidelity), Wi-Fi Direct, and Wireless USB (Wireless Universal Serial Bus) technologies.

[0074] The location information module is a module for obtaining the location (or current location) of the device according to the present disclosure, and representative examples thereof include a Global Positioning System (GPS) module or a Wireless Fidelity (WiFi) module. For example, if a GPS module is utilized, the location of the device can be obtained using signals sent from GPS satellites. As another example, if a Wi-Fi module is utilized, the location of the device can be obtained based on information from a Wireless Access Point (AP) that transmits or receives wireless signals from the Wi-Fi module. If necessary, the location information module may perform any of the functions of other modules of the communication unit to obtain data regarding the location of the device, either substituted or additionally. The location information module is a module used to obtain the location (or current location) of the device, and is not limited to a module that directly calculates or obtains the location of the device.

[0075] The memory (130) can store data supporting various functions of the device and programs for the operation of the processor (110), and can store input / output data, and can store a number of application programs (or applications) running on the device, data for the operation of the device, and instructions. At least some of these application programs can be downloaded from an external server via wireless communication.

[0076] Such memory (130) may include at least one type of storage medium among flash memory type, hard disk type, SSD type (Solid State Disk type), SSD type (Silicon Disk Drive type), multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), RAM (random access memory; RAM), SRAM (static random access memory), ROM (read-only memory; ROM), EEPROM (electrically erasable programmable read-only memory), PROM (programmable read-only memory), magnetic memory, magnetic disk, and optical disk. Additionally, the memory (130) may be a database that is separated from the device but connected via wired or wireless connection.

[0077] The drive module (140) is for physical control of the entrance door of a store and can operate in conjunction with a locking device system such as an electronic door lock, an automatic door system, or an alarm device.

[0078] For example, the drive module (140) may include, but is not limited to, a relay circuit, a motor driver, a power supply, a safety sensor, etc., and may have various configurations depending on the type of locking device system to which it is linked.

[0079] The driving module (140) can operate according to a control signal provided by the processor (110).

[0080] For example, the processor (110) may provide a control signal to the drive module (140) to open the door when it approves the entry request, and provide a control signal to the drive module (140) to close the door when it rejects the entry request. The drive module (140) may control the door to open or lock according to these control signals, and the processor (110) may automatically return the door to a locked state after the opening control.

[0081] The shooting module (150) can capture an area including the entrance door of the store and obtain an entry video in real time.

[0082] For example, the shooting module (150) may include a high-resolution digital camera, a lens system, an image sensor, and an image processing circuit.

[0083] At least one component may be added or removed in response to the performance of the components illustrated in FIG. 3. Additionally, it will be readily understood by those skilled in the art that the relative positions of the components may be changed in response to the performance or structure of the system.

[0084] Meanwhile, each component illustrated in Fig. 3 refers to a software and / or hardware component such as a Field Programmable Gate Array (FPGA) and an Application Specific Integrated Circuit (ASIC).

[0086] FIG. 4 is a flowchart of an unmanned access control management method according to one embodiment of the present disclosure.

[0087] A method according to one embodiment of the present disclosure can be performed by the device (100) shown in FIG. 3.

[0088] Referring to FIG. 4, a method according to one embodiment of the present disclosure may include a step (S100) in which a processor (110) confirms the reception of an entry request call, a step (S200) in which, if the reception of an entry request call is confirmed, an entry video is analyzed, a step (S300) in which, if movement is confirmed as a result of the entry video analysis, an entry request is approved (S400), and a step (S500) in which, if movement is not confirmed as a result of the entry video analysis, an entry request is rejected.

[0089] The processor (110) can confirm the incoming call for the entry request by receiving information regarding the entry request to the store through the incoming call from the telephone server (10) via the communication module (120) (S100).

[0090] Access request information may include a phone number, time of incoming call, and duration.

[0091] Meanwhile, when the processor (110) confirms the incoming call for an access request (S100), it can filter the access request.

[0092] For example, the processor (110) can automatically filter access requests by checking whether the access request information meets preset criteria. The preset criteria may include the form of the phone number and the minimum call duration.

[0093] When the processor (110) confirms that a phone call for an access request has been received (S100), it may perform a process to authenticate the access request, for example, first verify the existence of the access request to verify whether the access request is authenticated, or secondly verify the suitability of the access request to finally determine whether the access request is authenticated.

[0094] In this embodiment, the processor (110) can verify whether the caller who made the call requesting entry is actually in front of the store by detecting an object or motion in the entry video. For example, the processor (110) may verify the existence based on whether an object is recognized, verify the existence based on whether motion is detected, or verify the existence when both an object and motion are detected. At this time, the processor (110) can recognize a person in the entry video by applying a deep learning-based object recognition algorithm. In the following description, the processor (110) will be described as performing the process of verifying the existence of the entry request through motion detection.

[0095] First, the processor (110) can acquire an entry / exit image through a shooting module (150) to verify the authenticity of the entry / exit request and analyze whether movement occurs within the image (S200). This will be explained with reference to FIGS. 5 and FIGS. 6.

[0096] FIG. 5 is a drawing showing the state in which a shooting module according to one embodiment of the present disclosure is installed, and FIG. 6 is an example of an entry / exit image obtained from the shooting module shown in FIG. 5.

[0097] Referring to FIG. 5, the shooting module (150) can be installed to capture an area (A) including a door (D) to obtain real-time entry / exit images, and preferably, it can be installed at a height that can effectively capture the user's face and full body.

[0098] The processor (110) can acquire an entry / exit image through this shooting module (150).

[0099] For example, the processor (110) can acquire entry and exit footage captured during a preset time period around the time of the phone call. At this time, the real-time entry and exit footage can be stored cyclically by segment according to a preset buffer time interval. The processor (110) can extract and acquire a certain segment around the time of the phone call from the real-time entry and exit footage.

[0100] The processor (110) can perform preprocessing on the acquired entry / exit image to improve analysis accuracy.

[0101] For example, the processor (110) may perform noise removal by applying a Gaussian filter or a median filter, and may also perform downscaling to improve processing speed.

[0102] The processor (110) can analyze whether movement occurs in a pre-set motion detection area of ​​the pre-processed entry / exit video.

[0103] Referring to FIG. 6, the processor (110) can set a motion detection area (A) in the entry / exit video. For example, the processor (110) can set the motion detection area (A) as a region of interest (ROI) based on the door (D) in the entry / exit video. For example, in this embodiment, the motion detection area (A) may be a circular or rectangular area with a radius of 4 meters centered on the door (D), but is not limited thereto and can be set in various forms depending on the structure of the store or the location of the door.

[0104] The processor (110) can determine whether motion occurs in the motion detection area (A) set in the entry / exit video. For example, the processor (110) can determine whether motion occurs in the entry / exit video by applying a motion detection algorithm based on at least one of background subtraction, optical flow, frame differencing, and deep learning-based object detection algorithms.

[0105] The processor (110) can verify whether the caller who made the call for entry request is actually in front of the store by checking whether movement has occurred in the area adjacent to the door (D) for a preset time based on the time of the call reception. This can be considered an effective method that can relatively briefly supplement the lack of verification of reality in a simple call reception-based unmanned entry control method. If the processor (110) confirms that movement has occurred in the entry video (S300), it may approve the entry request (S400), and if no movement has occurred (S300), it may reject the entry request (S500).

[0106] When the processor (110) detects movement in the entry / exit video, it may consider the user to actually be present in front of the store and approve the entry request as valid, and may provide a control signal to the drive module (140) so that the door can be opened.

[0107] At this time, the processor (110) can control the opening of the door after storing the phone number included in the access request information as it approves the access request.

[0108] Meanwhile, if the processor (110) detects movement in the entry / exit video, it may verify whether the user in front of the store is a normal user as described above and then finally approve the entry request. A detailed explanation regarding this will be provided later with reference to FIG. 7.

[0109] If no movement is detected in the entry video, the processor (110) may reject the entry request by determining that the entry request is invalid, such as being made from a remote location, by assuming that the user is not actually present in front of the store, and may provide a control signal to the drive module (140) so that the door can be kept locked.

[0110] At this time, the processor (110) can provide an alarm message regarding the access request to the user terminal (200) as it rejects the access request, and can record a log regarding the access request.

[0111] For example, alarm messages may include the time of refusal, phone number, reason for refusal, and relevant entry / exit footage, and can be provided in various forms such as push notifications and SMS. Additionally, log records may store structured data related to the access request authentication process.

[0113] Figure 7 is a detailed flowchart of step S300 shown in Figure 4.

[0114] Referring to FIG. 7, a method according to one embodiment of the present disclosure may further include, when a processor (110) confirms that movement has occurred in an entry / exit video (S300), a step of identifying a user (S310), a step of verifying the identified user (S320), and a step of verifying a phone number (S330).

[0115] When the processor (110) detects movement in the entry / exit video (S300), it can identify the user appearing in the entry / exit video (S310).

[0116] For example, the processor (110) can apply a deep learning-based object verification algorithm to identify human objects in an entry / exit video.

[0117] The processor (110) can verify the identified user by extracting characteristic information of the identified user (S320).

[0118] The processor (110) can extract feature information including at least one of the user's pose, position, body shape, face, and clothing from the entry / exit video.

[0119] The processor (110) can determine whether there is a match between the user identified in the entry / exit video and the actual caller who made the call by using the extracted user feature information.

[0120] For example, the processor (110) may determine whether there is a match between the user identified in the entry / exit video and the recipient of the phone call by using pose information included in the user's feature information. This will be explained with reference to FIG. 8.

[0121] Figure 8 is an example of an entry / exit image obtained from the shooting module shown in Figure 5.

[0122] Referring to FIG. 8, the processor (110) can apply a pose detection algorithm to estimate the joint positions of the identified user within the entry / exit image and obtain pose information (p) based on the estimated joint positions.

[0123] The processor (110) can determine whether the pose information (p) of the user identified in the entry / exit video corresponds to a stored call pose. The stored call pose may define the relative position of the hand and head, the tilt of the head, etc., and the processor (110) can determine whether the user identified in the entry / exit video is in a call pose by comparing the pose information (p) with the stored call pose.

[0124] If the processor (110) determines that the user identified in the entry / exit video is in a calling posture, it can determine that the user matches the recipient of the call.

[0125] If the processor (110) determines that the user identified in the entry / exit video matches the actual caller, it can verify whether the user identified in the entry / exit video is a normal user.

[0126] For example, the processor (110) may include a blacklist database. The blacklist database includes information about persons banned from entering the store and may consist of fields such as phone number, facial feature information, pose feature information, body shape feature information, clothing feature information and reason for ban.

[0127] The processor (110) can determine whether the user identified in the entry video is a prohibited entry subject by comparing the feature information of the user identified in the entry video with the feature information of the blacklist.

[0128] The processor (110) can convert feature information such as face, pose, body shape and clothing into a vector, calculate the similarity between the vector of feature information of a user identified in an entry / exit video and the vector of feature information of users registered in a blacklist, and if the similarity is greater than or equal to a threshold value, determine that the user identified in the entry / exit video is the same person as the user registered in the blacklist.

[0129] In this way, the processor (110) can determine whether there is a match between the user identified in the entry / exit video and the recipient of the phone call, and can finally verify the user by checking whether the user identified in the entry / exit video belongs to a blacklist.

[0130] The processor (110) may refuse an entry request if it determines that the user identified in the entry video does not match the recipient of the phone call, or that the user identified in the entry video belongs to a blacklist.

[0131] The processor (110) can approve an entry request if it determines that the user identified in the entry video and the recipient of the phone call are the same and are not included in the blacklist.

[0132] Meanwhile, if the processor (110) determines that the user identified in the entry video and the recipient of the phone call are the same and are not included in the blacklist, it can verify the phone number to determine whether to finally approve the entry request (S330).

[0133] For example, the processor (110) can verify the phone number by checking whether the phone number that attempted to receive the call for the entry request corresponds to a phone number included in the blacklist database. The processor (110) may finally approve the entry request only if the phone number is not included in the blacklist database, and may finally reject the entry request if the phone number is included in the blacklist database.

[0134] Additionally, the processor (110) can verify the phone number by checking whether a call received by the same phone number has been repeated more than a preset number of times. If a call received by the same phone number has been repeated more than a preset number of times, the processor (110) may consider the user to be abnormal and ultimately refuse the request for entry.

[0135] Additionally, the processor (110) may include a whitelist database. The whitelist database may include phone numbers of persons allowed to enter the store. The processor (110) may finally approve an entry request only if the phone number of the incoming call is included in the whitelist database.

[0136] Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium that stores instructions executable by a computer. The instructions may be stored in the form of program code and, when executed by a processor, may generate a program module to perform the operation of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

[0137] Computer-readable recording media include all types of recording media that store instructions that can be decoded by a computer. Examples include ROM (Read Only Memory), RAM (Random Access Memory), magnetic tape, magnetic disk, flash memory, optical data storage devices, etc.

[0138] As described above, the disclosed embodiments have been explained with reference to the attached drawings. Those skilled in the art will understand that the present disclosure may be practiced in forms different from the disclosed embodiments without changing the technical spirit or essential features of the present disclosure. The disclosed embodiments are illustrative and should not be interpreted restrictively. Explanation of the symbols

[0140] 1: Unmanned access control management system 10: Telephone server 100: Device 200: User terminal

Claims

Claim 1 A shooting module that captures an area including the entrance door of a store to acquire an entry video in real time; and a processor that performs a process for authenticating an entry request to the store via a phone call based on the entry video; wherein the processor cyclically stores the entry video according to a preset buffer time interval, and when the phone call is confirmed, extracts video for a preset time period before and after the phone call to acquire an entry video to be analyzed, recognizes the occurrence of an object or movement in a preset area within the entry video to be analyzed, and when the occurrence of the object or movement is recognized, identifies a user in the entry video to be analyzed, estimates the joint position of the identified user to acquire pose information, compares the acquired pose information with a preset call pose to determine whether the identified user is in a call posture to perform a first verification of the entry request, and when the first verification of the entry request is completed, extracts feature information of the identified user from the entry video to be analyzed, compares the extracted feature information with feature information of a preset blacklist to perform a second verification of the entry request, and according to the second verification of the entry request An unmanned access control management device that makes the final decision on whether to approve the above access request. Claim 2 An unmanned access control management device according to claim 1, wherein the processor approves the access request when the occurrence of the object or movement is recognized, and rejects the access request when the occurrence of the object or movement is not recognized. Claim 3 delete Claim 4 delete Claim 5 An unmanned access control management device according to claim 1, wherein the processor, upon recognizing the occurrence of the object or movement, determines whether to approve the access request by checking whether the phone number attempting to receive the call is included in a stored blacklist or whitelist. Claim 6 An unmanned access control management device according to claim 1, wherein the processor determines whether to approve the access request by checking whether the incoming call by the same phone number has been repeated more than a preset number of times. Claim 7 delete Claim 8 An unmanned access control management device according to claim 1, wherein the processor, when the occurrence of the object or movement is recognized, approves the access request, stores the phone number that attempted to receive the call, and controls the opening of the access door, and when the occurrence of the object or movement is not recognized, rejects the access request, provides an alarm message regarding the access request to a manager terminal, and records a log regarding the access request. Claim 9 A method for managing unmanned access control based on a phone number through access video analysis performed by a device, comprising: a step of confirming an incoming call for an access request to a store; a step of acquiring an access video in real time that captures an area including the entrance door of the store and cyclically storing the access video according to a preset buffer time interval, and, when the incoming call is confirmed, extracting video for a preset time period before and after the incoming call to acquire an access video to be analyzed; a step of recognizing the occurrence of an object or movement in a preset area within the access video to be analyzed; a step of identifying a user in the access video to be analyzed when the object or movement is recognized; a step of acquiring pose information by estimating the joint position of the identified user; a step of verifying the access request in a first step by comparing the acquired pose information with a preset call pose to determine whether the identified user is in a call posture; a step of extracting feature information of the identified user from the access video to be analyzed when the first verification of the access request is completed; a step of verifying the access request in a second step by comparing the extracted feature information with feature information of a preset blacklist; and according to the second verification of the access request An unmanned access control management method comprising: a step of finally determining whether to approve the above access request. Claim 10 delete

Images