Monitoring and warning method and device for building visitors, terminal and medium

Abstract

The invention discloses a monitoring and warning method and device for building visitors, a terminal and a medium, and the method comprises the steps: obtaining image information and visitor work card information of a target area in a building, the image information being used for reflecting the identity recognition information of the visitors, the visitor work card information being used for reflecting the identity input information of the visitors, and the visitor work card information being used for reflecting the identity input information of the visitors; the identity recognition information comprises face feature information, clothing feature information and body shape feature information, and the identity input information comprises personal identity information and access area information; determining a visitor identity authentication result of a target area according to the identity recognition information and the identity input information; and according to the visitor identity authentication result and the sensitive threshold value of the target area, obtaining the security alarm level of the visitor in the target area. According to the invention, accurate recognition of visitors can be realized in combination with multiple features such as human faces, clothes, body types and the like, different safety alarm levels can be reasonably configured, and management and control of workers on buildings are facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of building personnel management and control, and in particular to a monitoring and alarm method, device, terminal and medium for building visitors. Background Art

[0002] The monitoring and alarm system of the smart building system is an important part of achieving building safety management. However, the existing smart building system can only confirm the identity information of visitors through facial recognition technology and visitor passes. When visitors wear masks or walk by with their heads down, the cameras installed high in the building cannot recognize the visitor's facial information, resulting in the inability of the existing smart building system to accurately identify the identity information of building personnel. When the smart building system cannot accurately determine the identity information of building personnel, it cannot effectively determine whether the current personnel have illegally accessed other building areas, causing the monitoring and alarm system to have alarm delays, affecting the management efficiency of the building.

[0003] Therefore, the prior art still needs to be improved and enhanced. Summary of the invention

[0004] The technical problem to be solved by the present invention is that, in view of the above-mentioned defects of the prior art, a monitoring and alarm method, device, terminal and medium for building visitors are provided, aiming to solve the problem in the prior art that the intelligent building system cannot accurately identify the identity information of building personnel and cannot effectively determine whether the current personnel have illegally accessed other building areas, thereby affecting the management efficiency of the building.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is as follows:

[0006] In a first aspect, the present invention provides a monitoring and alarm method for building visitors, wherein the method comprises:

[0007] Obtaining image information and visitor badge information of a target area in a building, wherein the image information is used to reflect the visitor's identity information, and the visitor badge information is used to reflect the visitor's identity entry information, wherein the identity information includes facial feature information, clothing feature information, and body feature information, and the identity entry information includes personal identity information and access area information;

[0008] Determine the visitor identity authentication result of the target area according to the identity recognition information and the identity entry information;

[0009] According to the visitor identity authentication result and the sensitivity threshold of the target area, the security warning level of the visitor in the target area is obtained.

[0010] In one implementation, before acquiring the image information of the target area in the building and the visitor badge information, the process includes:

[0011] When a visitor enters the building, facial feature information, clothing feature information and body feature information of the current visitor are collected, and the identity recognition information of the current visitor is obtained based on the facial feature information, clothing feature information and body feature information;

[0012] After the identity recognition information is collected, the personal identity information and the visited area information of the current visitor are collected, and the identity entry information of the current visitor is obtained based on the personal identity information and the visited area information;

[0013] The identity recognition information and the identity entry information are bound and sent to the edge super device controller of each target area for storage.

[0014] In one implementation, the collecting of facial feature information, clothing feature information, and body feature information of the current visitor includes:

[0015] By using face recognition technology, the facial features layout information of the current visitor is collected, and the facial feature information is determined according to the facial features layout information;

[0016] By using computer vision and image processing technology, the clothing style, clothing color and clothing pattern of the current visitor are collected, and the clothing feature information is determined based on the clothing style, clothing color and clothing pattern;

[0017] The static feature information and dynamic feature information of the current visitor are collected through computer vision, deep learning and three-dimensional modeling technology, and the body feature information is determined based on the static feature information and the dynamic feature information.

[0018] In one implementation, the collecting of static feature information and dynamic feature information of the current visitor through computer vision, deep learning and three-dimensional modeling technology, and determining the body shape feature information based on the static feature information and the dynamic feature information include:

[0019] Calculating the body proportion data of the current visitor, and determining static feature information based on the body proportion data;

[0020] Extracting and analyzing the walking posture data of the current visitor, and determining dynamic feature information based on the walking posture data;

[0021] The body shape feature information is determined based on the static feature information and the dynamic feature information.

[0022] In one implementation, determining the visitor identity authentication result of the target area according to the identity recognition information and the identity entry information includes:

[0023] Based on the edge super device controller of the target area, calculating the similarity scores of the facial feature information, clothing feature information and body feature information in the identity recognition information and the identity entry information;

[0024] Based on the similarity score and a preset weight ratio, a visitor identity authentication result of the target area is determined.

[0025] In one implementation, determining the visitor identity authentication result of the target area based on the similarity score and a preset weight ratio includes:

[0026] Calculating a visitor identity authentication score for the target area based on the similarity score and a preset weight ratio;

[0027] The visitor identity authentication score is compared with a preset score threshold to obtain a visitor identity authentication result of the target area, wherein the visitor identity authentication result includes authentication pass and authentication fail.

[0028] In one implementation, obtaining the security warning level of the visitor in the target area according to the visitor identity authentication result and the sensitivity threshold of the target area includes:

[0029] When the visitor identity authentication result is authentication passed and the visitor identity authentication score reaches the sensitivity threshold of the target area, determining that the security warning level of the visitor in the target area is the first level;

[0030] When the visitor identity authentication result is authentication passed and the visitor identity authentication score does not reach the sensitivity threshold of the target area, it is determined that the security warning level of the visitor in the target area is the second level.

[0031] In a second aspect, an embodiment of the present invention further provides a monitoring and alarm device for building visitors, wherein the device comprises:

[0032] The target area information acquisition module is used to obtain the image information and visitor badge information of the target area in the building, the image information is used to reflect the visitor's identity recognition information, the visitor badge information is used to reflect the visitor's identity entry information, the identity recognition information includes facial feature information, clothing feature information and body feature information, and the identity entry information includes personal identity information and access area information;

[0033] An identity authentication result determination module, used to determine the identity authentication result of the visitor in the target area according to the identity recognition information and the identity entry information;

[0034] The security alarm level determination module is used to obtain the security alarm level of the visitor in the target area according to the visitor identity authentication result and the sensitivity threshold of the target area.

[0035] In the third aspect, an embodiment of the present invention further provides a terminal, wherein the terminal includes a memory, a processor, and a monitoring and alarm program for building visitors stored in the memory and executable on the processor, and when the processor executes the monitoring and alarm program for building visitors, the steps of the monitoring and alarm method for building visitors of any one of the above-mentioned schemes are implemented.

[0036] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein a monitoring and alarm program for building visitors is stored on the computer-readable storage medium, and when the monitoring and alarm program for building visitors is executed by a processor, the steps of the monitoring and alarm method for building visitors described in any one of the above-mentioned schemes are implemented.

[0037] Beneficial effects: Compared with the prior art, the present invention provides a monitoring and alarm method, device, terminal and medium for building visitors. First, the image information and visitor badge information of the target area in the building are obtained. The image information is used to reflect the visitor's identity recognition information, and the visitor badge information is used to reflect the visitor's identity entry information. The identity recognition information includes facial feature information, clothing feature information and body feature information, and the identity entry information includes personal identity information and access area information. Then, based on the identity recognition information and the identity entry information, the visitor identity authentication result of the target area is determined. Finally, based on the visitor identity authentication result and the sensitive threshold of the target area, the security alarm level of the visitor in the target area is obtained. Therefore, the present invention can combine multiple features such as face, clothing, body shape, etc. to realize accurate identification of visitors, and can also configure different security alarm levels for areas with different sensitive thresholds, which facilitates the staff's management and control of buildings. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A flowchart of a specific implementation of the monitoring and alarm method for building visitors provided in an embodiment of the present invention.

[0039] Figure 2 A functional schematic diagram of a monitoring and alarm device for building visitors provided in an embodiment of the present invention.

[0040] Figure 3 A functional block diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solution and effect of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples.

[0042] Those skilled in the art will appreciate that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. Unless specifically stated, the singular forms "one", "said", and "the" used herein may also include plural forms, and the term "comprising" used in the specification of the present invention refers to the presence of the features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or their groups. It should be understood that when an element is "connected" or "coupled" to another element, it may be directly connected or coupled to other elements, or there may also be intermediate elements. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0043] It should be noted that the present invention does not involve infringement of personal privacy. The information involved (including but not limited to user device information, user personal information, etc.), data (including but not limited to user analysis data, user stored data, user displayed data, etc.) and signals are all information, data and signals authorized by the user or fully authorized by all parties; and the collection, use and processing of relevant information, data and signals comply with the laws, regulations and standards of relevant countries and regions.

[0044] It should be noted that the information, data or signals involved in the present invention are processed in compliance with the relevant national data protection laws and regulations and with full authorization.

[0045] This embodiment provides a monitoring and alarm method, device, terminal and medium for building visitors. In specific implementation, this embodiment first obtains the image information and visitor badge information of the target area in the building. The image information is used to reflect the visitor's identity recognition information, and the visitor badge information is used to reflect the visitor's identity entry information. The identity recognition information includes facial feature information, clothing feature information and body feature information, and the identity entry information includes personal identity information and access area information. Then, based on the identity recognition information and the identity entry information, the visitor identity authentication result of the target area is determined. Finally, based on the visitor identity authentication result and the sensitive threshold of the target area, the security alarm level of the visitor in the target area is obtained. Therefore, this embodiment can combine multiple features such as face, clothing, body shape, etc. to realize accurate identification of visitors, and can also configure different security alarm levels for areas with different sensitive thresholds, which facilitates the staff's management and control of buildings.

[0046] Exemplary Methods

[0047] The monitoring and alarm method for building visitors of this embodiment can be applied to a terminal, which can be a preset mobile terminal such as a mobile phone, a tablet, a computer, or an intelligent device such as a smart TV. In this embodiment, the terminal can be an external device connected to the monitoring and alarm device for building visitors, or it can be a device built into the monitoring and alarm device for building visitors. Figure 1 As shown in , the monitoring and alarm method for building visitors of this embodiment includes the following steps:

[0048] Step S100, obtaining image information and visitor badge information of a target area in a building, wherein the image information is used to reflect the visitor's identity recognition information, and the visitor badge information is used to reflect the visitor's identity entry information, wherein the identity recognition information includes facial feature information, clothing feature information, and body feature information, and the identity entry information includes personal identity information and access area information.

[0049] In order to achieve accurate identification and efficient control of visitors in the building, this embodiment will acquire and collect image information and visitor badge information in different target areas in the building in real time. Among them, the target area can be any door area of ​​each building floor, or a room area of ​​each building floor.

[0050] In this embodiment, the following modules are arranged in the building: visitor login module, visitor feature information extraction module, visitor information delivery module, access area and alarm level configuration module, edge closed-loop alarm processing module and visitor access termination module.

[0051] Specifically, the visitor login module is used to obtain the visit area information when the visitor enters the building and collect the visitor's facial feature information, and then enter the visit area information and facial feature information into the visitor's work card to bind the identity information, and give the visitor an exclusive visitor identification (Identity document, ID). The visitor feature information extraction module is used to collect the user's current clothing feature information and body feature information to supplement the visitor's other identity feature information to achieve more accurate visitor identification. The visitor information delivery module is used to send the visitor information collected by the visitor login module and the visitor feature information extraction module to the edge super device controller of each floor, so that when the edge super device collects visitor information on different floors, it can clarify the visitor's identity based on the information stored in the edge super device controller. The access area and alarm level configuration module is used to define the sensitive areas of the building at all levels, the sensitive behaviors of visitors, the alarm level and the alarm notification method. The edge closed-loop alarm processing module is used to obtain the appropriate alarm level and the alarm notification method corresponding to the alarm level according to the sensitivity score of the visitor in the sensitive areas at all levels for reporting. The visitor end access module is used to send a message to clear the visitor's whitelist when the visitor ends his / her visit, and each floor controller deletes the visitor's information from the whitelist.

[0052] In one implementation, before acquiring the image information of the target area in the building and the visitor badge information, the present embodiment includes the following steps:

[0053] Step S1: When a visitor enters a building, facial feature information, clothing feature information and body feature information of the current visitor are collected, and the identity recognition information of the current visitor is obtained based on the facial feature information, clothing feature information and body feature information;

[0054] Step S2: after the identity recognition information is collected, personal identity information and access area information of the current visitor are collected, and based on the personal identity information and the access area information, the identity entry information of the current visitor is obtained;

[0055] Step S3: Bind the identity recognition information and the identity entry information, and send them to the edge super device controller of each target area for storage.

[0056] Specifically, when a visitor enters a building, the visitor passes through the building gate, triggering the face recognition device on the gate to collect the visitor's identity information, such as collecting the visitor's identity information through the front camera and the camera above the gate. Among them, the visitor's identity information collected in this embodiment includes facial feature information, clothing feature information, and body feature information. Preferably, the visitor's identity feature information in this embodiment includes but is not limited to facial feature information, clothing feature information, and body feature information, and may also be other feature information set by the technician according to the scene requirements.

[0057] Next, this embodiment will also inquire and query the visitor's personal identity information and access area information, where the personal identity information can be the visitor's name, phone number and other information, and the access area information can be the visitor's specific access floor, the visitor's specific access room number and other information. Finally, the visitor's identity recognition information and identity entry information are bound and entered into the visitor's badge, giving the visitor a unique visitor ID. At the same time, this embodiment will also send the collected identity recognition information, identity entry information, visitor ID and other information to the edge super device controller of each target area for storage.

[0058] In one implementation, step S1 of this embodiment specifically includes the following steps:

[0059] Step S11, using face recognition technology to collect facial features layout information of the current visitor, and determining the facial feature information according to the facial features layout information;

[0060] Step S12: collecting the clothing style, clothing color and clothing pattern of the current visitor through computer vision and image processing technology, and determining the clothing feature information based on the clothing style, clothing color and clothing pattern;

[0061] Step S13: Collect static feature information and dynamic feature information of the current visitor through computer vision, deep learning and three-dimensional modeling technology, and determine the body feature information based on the static feature information and the dynamic feature information.

[0062] Specifically, the facial feature information collected by this embodiment may include the layout of the visitor's facial features, the visitor's facial contour, etc. Therefore, when the edge camera recognizes the visitor's facial feature information at a close distance, the identity information of the current visitor can be identified through operations such as facial recognition technology.

[0063] The clothing feature information collected in this embodiment may include information such as the visitor's clothing style features, clothing color features, and clothing pattern features. Among them, clothing style features can be specifically divided into long sleeves, short sleeves, trousers, shorts, high heels, and sneakers. Clothing color features can be specifically divided into black, white, red, yellow, and blue. Clothing pattern features can be specifically divided into solid color without pattern, floral pattern, and animal pattern. When the edge camera recognizes the visitor image, the current visitor's clothing feature information can be identified through operations such as computer vision and image processing technology.

[0064] Furthermore, the present embodiment can also use a convolutional neural network (CNN) to collect clothing feature information of visitors. CNN includes a convolution layer, a pooling layer and a fully connected layer. Specifically, in the convolution layer, a convolution layer can contain multiple different convolution kernels. Different convolution kernels can detect different features of different clothing images, such as color, texture, shape, etc. For example, a specific convolution kernel may be specifically used to detect stripe patterns, and another may be used to detect a specific color combination. The features output by a convolution layer are jointly determined by all the convolution kernels of the convolution layer. Therefore, the present embodiment can gradually extract more advanced and abstract clothing feature information by stacking multiple convolution layers. The pooling layer is used after the convolution layer. The pooling layer is used to reduce the size of the feature map, thereby reducing the amount of calculation and the number of parameters. In the feature extraction of clothing images, the pooling layer can help extract representative features, and at the same time has a certain invariance to changes such as translation and rotation of the image. Common pooling methods include maximum pooling and average pooling. After passing through multiple convolutional layers and pooling layers, it is finally connected to a fully connected layer, which is used to integrate the extracted features and output a feature vector of a fixed length for subsequent classification or similarity calculation tasks. In other words, this embodiment uses a convolutional neural network to identify the clothing feature information of visitors, which can ensure that the collected clothing feature information can be used to identify visitors more accurately and reliably.

[0065] In one implementation, step S13 of this embodiment specifically includes the following steps:

[0066] Step S131, calculating the body proportion data of the current visitor, and determining static feature information based on the body proportion data;

[0067] Step S132, extracting and analyzing the walking posture data of the current visitor, and determining dynamic feature information based on the walking posture data;

[0068] Step S133: Determine the body shape feature information based on the static feature information and the dynamic feature information.

[0069] The body feature information collected in this embodiment may include static feature information and dynamic feature information of the visitor. The static feature information may be determined by calculating the body proportion data of the current visitor, such as the visitor's hairstyle, the visitor's height, and the visitor's body proportion. The dynamic feature information may be determined by extracting and analyzing the walking posture data of the current visitor, such as the visitor's walking posture, the walking stride amplitude, etc. When the edge camera recognizes the visitor's image, the body feature information of the current visitor may be obtained through operations such as computer vision, deep learning, and three-dimensional modeling technology.

[0070] Furthermore, the present embodiment can also use a recurrent neural network (RNN) to extract and analyze the dynamic feature information in the visitor's body shape feature information. RNN has a loop structure and a memory unit. The loop structure is used to process sequence data. For the analysis of body shape dynamics, the body shape information of each frame can be regarded as the input of a time step. The RNN can capture the dynamic change process of the body shape by looping on the time step. For example, as the visitor walks, moves, etc., the visitor's body shape will change accordingly, and the RNN can learn the pattern of these cyclic changes. Then, the memory unit in the RNN can store the information learned in the past, and comprehensively process the input of the current time step and the past state, so as to better capture the continuity of the body shape dynamics. For example, the memory unit can remember the body shape state of the visitor in the previous frame, and combine the input of the current frame to better predict the body shape change of the next frame. That is to say, the present embodiment extracts and analyzes the dynamic feature information in the visitor's body shape feature information through a recurrent neural network, which can ensure that the collected dynamic feature information can be used to identify the visitor more accurately and reliably.

[0071] Next, after the visitor's identity feature information is collected in this embodiment, the identity feature information will be bound to the visitor ID card that triggers the gate, so that the visitor's access area information, identity feature information and the visitor ID card correspond to each other. At this time, this embodiment can realize multi-feature recognition of the visitor based on the above-collected facial feature information, clothing feature information and body feature information of the visitor, and more accurately identify the visitor's identity information by integrating multiple feature information, thereby improving the authenticity and credibility of the visitor's identity.

[0072] Finally, this embodiment will send the collected visitor badge (including visitor badge ID), access area information and identity feature information of each visitor to the edge super device controller on each floor. Specifically, the visitor badge, access area information and identity feature information of this embodiment can be sent to the edge super device controller on each floor through the MQTT communication protocol, and then the controller records the received data in the whitelist so that the edge super devices in each area of ​​each floor can collect and analyze the visitor's identity information. The edge super device controller is mainly designed to optimize and manage smart devices and sensors located at the edge of the network. Its characteristics are that they operate close to the source of data generation, can process data in real time, perform complex analysis and make decisions, thereby reducing dependence on the cloud, reducing latency and improving computing efficiency. Edge super device controllers are particularly important in application scenarios such as the Internet of Things, Industry 4.0, and smart cities. They usually have the following functions: Data processing and analysis: Instantly process large amounts of data at the edge, perform filtering, aggregation and other operations, and only transmit necessary data back to the cloud or data center. Device management: Monitor and control connected edge devices, including configuration, firmware update, and optimization of operating status. Intelligent decision-making: Make decisions locally based on preset rules or machine learning models to achieve automated control and response. Security protection: Implement security policies, detect and respond to potential network risks, and protect the security of edge devices and data. Resource optimization: Rationally allocate computing, storage, and network resources to ensure efficient collaboration among devices and reduce energy consumption.

[0073] Step S200: Determine the visitor identity authentication result of the target area according to the identity recognition information and the identity entry information.

[0074] When this embodiment obtains the real-time data (identity recognition information and identity entry information) of the camera and radio frequency identification (RFID) detection device of each target area based on the edge super device connected and controlled by the edge super device controller, the visitor identity authentication result of the target area can be further determined.

[0075] In one implementation, step S200 of this embodiment specifically includes the following steps:

[0076] Step S201: Based on the edge super device controller in the target area, calculate the similarity scores of the facial feature information, clothing feature information and body feature information in the identity recognition information and the identity entry information;

[0077] Step S202: Determine the visitor identity authentication result of the target area based on the similarity score and a preset weight ratio.

[0078] Specifically, the edge super device controller can perform similarity analysis on the visitor's feature information obtained through real-time monitoring to obtain a similarity score. For example, after comprehensive analysis by the edge super device controller, the similarity score of the visitor's facial feature information is 0.7, the similarity score of the clothing feature information is 0.8, the similarity score of the body feature information is 0.5, and the similarity score of the identity entry information is 1.

[0079] Next, the preset weight ratio in this embodiment can be pre-set by the technician according to the actual situation of the building scene. For example, in the scene where the visitor's identity information score is jointly determined based on the four factors of the visitor's facial feature information, clothing feature information, body feature information and identity entry information, since the face is usually one of the most recognizable features, it has unique features such as facial features layout and contour, and can provide more reliable identification information even under different lighting and angles, so the technician can give the facial feature information a higher weight ratio, such as 0.4. Since the style and color combination of a person's clothing can assist in identifying identity information to a certain extent, and considering the stability, uniqueness and possibility of change of clothing in different scenes, the technician will give the clothing feature information a weight ratio, such as 0.2. Of course, if the clothing style of different visitors is relatively fixed and has obvious characteristics in a building scene, a higher weight ratio can be appropriately given to the clothing feature information. If the clothing of different visitors is easy to change or similar to that of others in a building scene, the weight ratio of the clothing feature information is appropriately reduced. Since the body feature information of a person is relatively stable, but its recognition may be slightly inferior to that of a face, the technician will assign a weight ratio of 0.2 to the body feature information. Of course, this embodiment can also take into account the stability of the shape, body shape and height ratio of a person and the significance of individual differences, so as to assign different weight ratios to the body feature information. For example, in a building scene where the body shapes of different visitors are very different or the walking posture is easy to identify, the body feature information can be appropriately assigned a higher weight ratio. If the body features of different visitors are not much different in a building scene, the weight ratio of the body feature information should be appropriately reduced. Since the identity entry information in the visitor's badge has high accuracy and uniqueness, but considering the stability and reliability of RFID reading, and whether there is substitution, impersonation or damage, the technician will assign a weight ratio of 0.2 to the identity entry information. Of course, if in a building scenario where the RFID reading can be ensured to be normal and consistent with the system records, this embodiment can also appropriately give a higher weight ratio to the identity entry information. If in a building scenario where the RFID is prone to reading problems or may be used fraudulently, the weight ratio of the identity entry information can be appropriately reduced. Finally, the visitor identity authentication result of the target area can be determined based on the similarity score and the preset weight ratio.

[0080] In one implementation, step S202 of this embodiment specifically includes the following steps:

[0081] Step S2021: Calculate the visitor identity authentication score of the target area based on the similarity score and a preset weight ratio;

[0082] Step S2022: Compare the visitor identity authentication score with a preset score threshold to obtain a visitor identity authentication result of the target area, wherein the visitor identity authentication result includes authentication passed and authentication failed.

[0083] Specifically, the visitor identity authentication score of the target area is equal to the product sum of the similarity scores of each feature information of the visitor and the weight ratio of each feature information of the visitor. For example, in a scenario where the visitor's identity information score is determined based on the four factors of the visitor's facial feature information, clothing feature information, body feature information and identity entry information, the weight ratios of the visitor's facial feature information, clothing feature information, body feature information and identity entry information are: 0.4, 0.2, 0.2 and 0.2, respectively, and the similarity scores of the visitor's facial feature information, clothing feature information, body feature information and identity entry information are: 0.7, 0.8, 0.5 and 1, respectively, then the visitor identity authentication score is: 0.4×0.7+0.2×0.8+0.2×0.5+0.2×1=2.8+1.6+1+0.2=5.6. The visitor identity authentication score is used to reflect the accuracy of the identified visitor identity. The higher the visitor identity information score, the higher the accuracy of the identified visitor identity. Compared with the existing building system that only identifies the visitor's identity information through the visitor's facial feature information detected by the camera, this embodiment uses a variety of information features to comprehensively identify the visitor's identity information, including but not limited to facial feature information, clothing feature information, body feature information, and identity entry information. This can avoid the situation where the camera installed high in the building cannot recognize the visitor's facial information when the visitor wears a mask or walks with his head down, resulting in the existing intelligent building system being unable to effectively identify the facial feature information of the building personnel. Therefore, the technology of comprehensively identifying the visitor's identity information based on a variety of information features in this embodiment can improve the accuracy of visitor identity recognition.

[0084] Next, the visitor identity authentication score is compared with the preset score threshold to obtain the visitor identity authentication result of the target area, wherein, when the visitor identity authentication score is greater than or equal to the preset score threshold, it indicates that the visitor identity authentication result is authentication passed; when the visitor identity authentication score is less than the preset score threshold, it indicates that the visitor identity authentication result is authentication failed.

[0085] Step S300: Obtain the security warning level of the visitor in the target area according to the visitor identity authentication result and the sensitivity threshold of the target area.

[0086] Specifically, step S300 of this embodiment includes the following steps:

[0087] Step S301: When the visitor identity authentication result is authentication passed and the visitor identity authentication score reaches the sensitivity threshold of the target area, determining that the security warning level of the visitor in the target area is the first level;

[0088] Step S302: When the visitor identity authentication result is authentication passed and the visitor identity authentication score does not reach the sensitivity threshold of the target area, it is determined that the security warning level of the visitor in the target area is the second level.

[0089] Since the present embodiment first defines the sensitivity thresholds of each target area of ​​the building, for example, the reception hall, corridor, exercise room and other areas are set as low-sensitivity areas with a sensitivity threshold of 0.5, the general office area is set as a medium-sensitivity area, and the archive room, leadership office and other areas are set as high-sensitivity areas with a sensitivity threshold of 0.8. Therefore, after the intelligent building system recognizes the visitor identity authentication result, the present embodiment will further combine the sensitivity threshold of the current target area to obtain different security alarm levels to improve the management efficiency of the building.

[0090] Optionally, the sensitivity threshold of the target area in this embodiment is set according to the actual needs of the building scene. When the building is used as a high-confidentiality office scene or a high-security residential scene, the sensitivity threshold of the building scene will be appropriately lowered so that the system can trigger and generate an alarm prompt to improve the safety of the building. When the scene provided by the building has low security and confidentiality, or there are fewer security personnel in the current building, the sensitivity threshold can be appropriately increased to reduce the number of alarm prompts generated by the system and reduce the misjudgment of visitors.

[0091] On the premise that the visitor identity authentication result is authentication passed, when the visitor identity authentication score reaches the sensitive threshold of the target area, the security alarm level of the visitor in the target area is determined to be the first level. When the visitor identity authentication score does not reach the sensitive threshold of the target area, the security alarm level of the visitor in the target area is determined to be the second level. Among them, the first level of alarm prompt can be expressed as displaying a reminder message on the security personnel monitoring screen, adding an obvious alarm sound, flashing lights, or informing the security personnel in the form of SMS notification. The second level of alarm prompt can only be expressed as displaying a reminder message on the security personnel monitoring screen. At the same time, because the alarm behavior is closed on the edge side, compared with the detection path of the central server, it can detect illegal entry of personnel into the access area faster and generate sensitive behavior alarms.

[0092] Optionally, the present embodiment can also set the sensitive behaviors of visitors in advance. For example, the visitor's photo taking behavior, the visitor's carrying of suspicious objects (such as knives or sticks) and other behaviors can be set as sensitive behaviors. Then, when the camera in a target area in the building recognizes that the degree of consistency between the visitor's behavior and the sensitive behavior is equal to or higher than a threshold, the present embodiment will also generate an alarm prompt and feed the alarm prompt back to the security personnel, thereby improving the safety of the building.

[0093] In summary, this embodiment provides a monitoring and alarm method, device, terminal and medium for building visitors. When implemented specifically, this embodiment first obtains the image information and visitor badge information of the target area in the building. The image information is used to reflect the visitor's identity recognition information, and the visitor badge information is used to reflect the visitor's identity entry information. The identity recognition information includes facial feature information, clothing feature information and body feature information, and the identity entry information includes personal identity information and access area information. Then, based on the identity recognition information and the identity entry information, the visitor identity authentication result of the target area is determined. Finally, based on the visitor identity authentication result and the sensitive threshold of the target area, the security alarm level of the visitor in the target area is obtained. Therefore, this embodiment can combine multiple features such as face, clothing, body shape, etc. to realize accurate identification of visitors, and can also configure different security alarm levels for areas with different sensitive thresholds, which facilitates the staff's management and control of buildings.

[0094] Exemplary Devices

[0095] Based on the above embodiments, the present invention also provides a monitoring and alarm device for building visitors, such as Figure 2 As shown in , the device includes: a target area information acquisition module 10, an identity authentication result determination module 20 and a security alarm level determination module 30. Specifically, the target area information acquisition module 10 is used to obtain image information and visitor badge information of the target area in the building, the image information is used to reflect the visitor's identity recognition information, the visitor badge information is used to reflect the visitor's identity entry information, the identity recognition information includes facial feature information, clothing feature information and body feature information, and the identity entry information includes personal identity information and access area information. The identity authentication result determination module 20 is used to determine the visitor identity authentication result of the target area according to the identity recognition information and the identity entry information. The security alarm level determination module 30 is used to obtain the security alarm level of the visitor in the target area according to the visitor identity authentication result and the sensitivity threshold of the target area.

[0096] In one implementation, before acquiring the image information of the target area in the building and the visitor badge information, the process includes:

[0097] An identity recognition information determination unit, used to collect facial feature information, clothing feature information and body feature information of the current visitor when the visitor enters the building, and obtain the identity recognition information of the current visitor based on the facial feature information, clothing feature information and body feature information;

[0098] An identity entry information determination unit, configured to collect the personal identity information and the visited area information of the current visitor after the identity recognition information is collected, and obtain the identity entry information of the current visitor based on the personal identity information and the visited area information;

[0099] The information storage unit is used to bind the identity recognition information and the identity entry information, and send them to the edge super device controller of each target area for storage.

[0100] In one implementation, the identity information determining unit includes:

[0101] A facial feature information determination subunit, used to collect facial features layout information of the current visitor through facial recognition technology, and determine the facial feature information according to the facial features layout information;

[0102] A clothing feature information determination subunit, used to collect the clothing style, clothing color and clothing pattern of the current visitor through computer vision and image processing technology, and determine the clothing feature information based on the clothing style, clothing color and clothing pattern;

[0103] The body shape feature information determination subunit is used to collect static feature information and dynamic feature information of the current visitor through computer vision, deep learning and three-dimensional modeling technology, and determine the body shape feature information based on the static feature information and the dynamic feature information.

[0104] In one implementation, the body shape feature information determination subunit includes:

[0105] A static feature information determination subunit, used to calculate the body proportion data of the current visitor, and determine the static feature information based on the body proportion data;

[0106] A dynamic feature information determination subunit, used to extract and analyze the walking posture data of the current visitor, and determine the dynamic feature information based on the walking posture data;

[0107] The body shape feature information determining second subunit is used to determine the body shape feature information based on the static feature information and the dynamic feature information.

[0108] In one implementation, the identity authentication result determination module 20 includes:

[0109] A similarity score determination unit, configured to calculate, based on the edge super device controller of the target area, the similarity scores of the facial feature information, the clothing feature information and the body feature information in the identity recognition information and the identity entry information;

[0110] The visitor identity authentication result determination unit is used to determine the visitor identity authentication result of the target area based on the similarity score and a preset weight ratio.

[0111] In one implementation, the visitor identity authentication result determination unit includes:

[0112] a visitor identity authentication score determination subunit, configured to calculate a visitor identity authentication score of a target area based on the similarity score and a preset weight ratio;

[0113] The visitor identity authentication result determination subunit is used to compare the visitor identity authentication score with a preset score threshold to obtain the visitor identity authentication result of the target area, wherein the visitor identity authentication result includes authentication pass and authentication fail.

[0114] In one implementation, the security alert level determination module 30 includes:

[0115] A first level determination unit, configured to determine that the security warning level of the visitor in the target area is the first level when the visitor identity authentication result is authentication passed and the visitor identity authentication score reaches the sensitivity threshold of the target area;

[0116] The second level determination unit is used to determine that the security warning level of the visitor in the target area is the second level when the visitor identity authentication result is authentication passed and the visitor identity authentication score does not reach the sensitivity threshold of the target area.

[0117] The working principles of each module in the monitoring and alarm device for building visitors in this embodiment are the same as the principles of each step in the above method embodiment, and will not be repeated here.

[0118] Based on the above embodiment, the present invention further provides a terminal, the principle block diagram of the terminal can be as follows: Figure 3 The terminal may include one or more processors 100 ( Figure 3Only one is shown in the figure), a memory 101 and a computer program 102 stored in the memory 101 and executable on one or more processors 100, for example, a monitoring and alarm program for building visitors. When one or more processors 100 execute the computer program 102, the various steps in the embodiment of the monitoring and alarm method for building visitors can be implemented. Alternatively, when one or more processors 100 execute the computer program 102, the functions of the various modules / units in the embodiment of the monitoring and alarm device for building visitors can be implemented, which is not limited here.

[0119] In one embodiment, the processor 100 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0120] In one embodiment, the memory 101 may be an internal storage unit of an electronic device, such as a hard disk or memory of the electronic device. The memory 101 may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device. Further, the memory 101 may also include both an internal storage unit of the electronic device and an external storage device. The memory 101 is used to store computer programs and other programs and data required by the terminal. The memory 101 may also be used to temporarily store data that has been output or is to be output.

[0121] Those skilled in the art will understand that Figure 3 The principle block diagram shown in the figure is only a block diagram of a partial structure related to the scheme of the present invention, and does not constitute a limitation on the terminal to which the scheme of the present invention is applied. The specific terminal may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0122] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, operating database or other media used in the embodiments provided by the present invention may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double operational data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0123] In summary, the present invention discloses a monitoring and alarm method, device, terminal and medium for building visitors, the method comprising: obtaining image information and visitor badge information of a target area in a building, the image information is used to reflect the visitor's identity recognition information, the visitor badge information is used to reflect the visitor's identity entry information, the identity recognition information includes facial feature information, clothing feature information and body feature information, the identity entry information includes personal identity information and access area information; according to the identity recognition information and the identity entry information, determining the visitor identity authentication result of the target area; according to the visitor identity authentication result and the sensitive threshold of the target area, obtaining the security alarm level of the visitor in the target area. The present invention can realize accurate identification of visitors by combining multiple features such as face, clothing, body shape, etc., and can also reasonably configure different security alarm levels, which facilitates the staff's management and control of buildings.

[0124] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A monitoring and alarm method for building visitors, characterized in that: The method comprises: Obtaining image information and visitor badge information of a target area in a building, wherein the image information is used to reflect the visitor's identity information, and the visitor badge information is used to reflect the visitor's identity entry information, wherein the identity information includes facial feature information, clothing feature information, and body feature information, and the identity entry information includes personal identity information and access area information; Determine the visitor identity authentication result of the target area according to the identity recognition information and the identity entry information; According to the visitor identity authentication result and the sensitivity threshold of the target area, the security warning level of the visitor in the target area is obtained.

2. The monitoring and alarm method for building visitors according to claim 1 is characterized in that: Before obtaining the image information of the target area in the building and the visitor badge information, the following steps are included: When a visitor enters the building, facial feature information, clothing feature information and body feature information of the current visitor are collected, and the identity recognition information of the current visitor is obtained based on the facial feature information, clothing feature information and body feature information; After the identity recognition information is collected, the personal identity information and the visited area information of the current visitor are collected, and the identity entry information of the current visitor is obtained based on the personal identity information and the visited area information; The identity recognition information and the identity entry information are bound and sent to the edge super device controller of each target area for storage.

3. The monitoring and alarm method for building visitors according to claim 2 is characterized in that: The collection of the current visitor's facial feature information, clothing feature information and body feature information includes: By using face recognition technology, the facial features layout information of the current visitor is collected, and the facial feature information is determined according to the facial features layout information; By using computer vision and image processing technology, the clothing style, clothing color and clothing pattern of the current visitor are collected, and the clothing feature information is determined based on the clothing style, clothing color and clothing pattern; The static feature information and dynamic feature information of the current visitor are collected through computer vision, deep learning and three-dimensional modeling technology, and the body feature information is determined based on the static feature information and the dynamic feature information.

4. The monitoring and alarm method for building visitors according to claim 3 is characterized in that: The collecting of static feature information and dynamic feature information of the current visitor through computer vision, deep learning and three-dimensional modeling technology, and determining the body shape feature information based on the static feature information and the dynamic feature information, includes: Calculating the body proportion data of the current visitor, and determining static feature information based on the body proportion data; Extracting and analyzing the walking posture data of the current visitor, and determining dynamic feature information based on the walking posture data; The body shape feature information is determined based on the static feature information and the dynamic feature information.

5. The monitoring and alarm method for building visitors according to claim 1 or 2, characterized in that: The step of determining the visitor identity authentication result of the target area according to the identity recognition information and the identity entry information includes: Based on the edge super device controller of the target area, calculating the similarity scores of the facial feature information, clothing feature information and body feature information in the identity recognition information and the identity entry information; Based on the similarity score and a preset weight ratio, a visitor identity authentication result of the target area is determined.

6. The monitoring and alarm method for building visitors according to claim 5, characterized in that: The step of determining the visitor identity authentication result of the target area based on the similarity score and a preset weight ratio includes: Calculating a visitor identity authentication score for the target area based on the similarity score and a preset weight ratio; The visitor identity authentication score is compared with a preset score threshold to obtain a visitor identity authentication result of the target area, wherein the visitor identity authentication result includes authentication pass and authentication fail.

7. The monitoring and alarm method for building visitors according to claim 6, characterized in that: The obtaining, according to the visitor identity authentication result and the sensitivity threshold of the target area, a security warning level of the visitor in the target area includes: When the visitor identity authentication result is authentication passed and the visitor identity authentication score reaches the sensitivity threshold of the target area, determining that the security warning level of the visitor in the target area is the first level; When the visitor identity authentication result is authentication passed and the visitor identity authentication score does not reach the sensitivity threshold of the target area, it is determined that the security warning level of the visitor in the target area is the second level.

8. A monitoring and alarm device for building visitors, characterized in that: The device comprises: The target area information acquisition module is used to obtain the image information and visitor badge information of the target area in the building, the image information is used to reflect the visitor's identity recognition information, the visitor badge information is used to reflect the visitor's identity entry information, the identity recognition information includes facial feature information, clothing feature information and body feature information, and the identity entry information includes personal identity information and access area information; An identity authentication result determination module, used to determine the identity authentication result of the visitor in the target area according to the identity recognition information and the identity entry information; The security alarm level determination module is used to obtain the security alarm level of the visitor in the target area according to the visitor identity authentication result and the sensitivity threshold of the target area.

9. A terminal, characterized in that: The terminal includes a memory, a processor, and a monitoring and alarm program for building visitors stored in the memory and executable on the processor. When the processor executes the monitoring and alarm program for building visitors, the steps of the monitoring and alarm method for building visitors as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a monitoring and alarm program for building visitors. When the monitoring and alarm program for building visitors is executed by the processor, the steps of the monitoring and alarm method for building visitors as described in any one of claims 1-7 are implemented.

Images