Intelligent monitoring method and system based on biometric recognition

The intelligent monitoring system uses biometric recognition to determine trustworthy individuals by analyzing shoe size, leg size, gait, and movement route, and assesses behavioral threat levels using vibration data, ensuring effective monitoring without privacy leakage.

CN118747867BActive Publication Date: 2024-12-06BEIJING YAOGUANG INTELLIGENT TECH CO LTD
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202411235572.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-04
Publication Date
2024-12-06
Estimated Expiration
2044-09-04

AI Technical Summary

Technical Problem

Existing monitoring systems installed on doors or entrances collect personal biometrics and privacy of surrounding residents without consent, leading to privacy leakage and reduced monitoring effectiveness when theft occurs.

Method used

An intelligent monitoring method and system based on biometric recognition that uses video information to determine shoe size, leg size, gait, and movement route to identify trustworthy individuals, and employs vibration data to assess behavioral threat levels, obtaining facial features only when necessary.

Benefits of technology

Facilitates monitoring without collecting sensitive personal biometrics, accurately identifying potential threats, and gathering evidence while preserving privacy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118747867B_ABST
    Figure CN118747867B_ABST
Patent Text Reader

Abstract

The present application relates to an intelligent monitoring method and system based on biometric identification, and to the field of intelligent monitoring. The method includes, when detecting the presence of a person in a preset area, obtaining first video information within a first preset monitoring range, determining the shoe size, leg size, gait and movement route of the person based on the first video information, judging whether the person is a trustworthy person based on the shoe size, leg size, gait and movement route, and if not, obtaining the distance from the person to the door, and if the distance is less than the preset distance, and the duration less than the preset distance reaches a preset duration, obtaining the vibration data of the door, determining the behavior threat level of the person based on the vibration data, and obtaining the second video information of the second preset monitoring range if the behavior threat level reaches the preset threat level. The present application facilitates monitoring without collecting and leaking key personal biometrics and privacy of surrounding residents.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of intelligent monitoring, and in particular to an intelligent monitoring method and system based on biometric recognition. Background Art

[0002] With the development and popularization of various monitoring products and the public's attention to property safety, monitoring products installed on various doors or entrances and exits have emerged, such as monitoring cameras, smart monitoring cat eyes, monitoring door locks, etc. However, when the above products are installed on doors or entrances and exits, if the permission of the surrounding residents is not obtained, the facial images of the surrounding residents will be collected when the surrounding residents pass by, resulting in the leakage of the personal biometrics and privacy of the surrounding residents. If the images in the environment are not collected, the monitoring effect will be reduced when theft occurs in one's own residence, and it will be inconvenient to collect the criminal's personal information and evidence afterwards. Therefore, how to monitor without collecting and leaking the key personal biometrics and privacy of the surrounding residents has become a problem. Summary of the invention

[0003] In order to facilitate monitoring without collecting and leaking key personal biometrics and privacy of surrounding residents, the present application provides an intelligent monitoring method and system based on biometric recognition.

[0004] In the first aspect, the present application provides an intelligent monitoring method based on biometric recognition, which adopts the following technical solutions:

[0005] An intelligent monitoring method based on biometric recognition, comprising:

[0006] When a person is detected in a preset area, first video information within a first preset monitoring range is obtained, where the first preset monitoring range includes an area that can cover the legs and feet of the person in the environment;

[0007] Determining the shoe size, leg size, gait, and movement route of the person based on the first video information;

[0008] Determining whether the person is a trustworthy person based on the shoe size, leg size, gait, and movement route;

[0009] If not, the distance from the person to the door is obtained. If the distance is less than a preset distance and the time duration less than the preset distance reaches a preset time duration, the vibration data of the door is obtained.

[0010] The behavior threat level of the person is determined based on the vibration data. If the behavior threat level reaches a preset threat level, second video information of a second preset monitoring range is obtained, where the second preset monitoring range includes an area above the first preset monitoring range.

[0011] By adopting the above technical solution, the first video information including the lower body of the current person, i.e., the legs and feet, is obtained, and the shoe size, leg size, gait and movement route of the current person are determined based on the first video information. Since each person's shoe size, leg size and gait are different, and different people have different movement routes in the area in front of the door, it is judged whether the current person is a trustworthy person based on the shoe size, leg size, gait and movement route without obtaining other sensitive personal identity features such as the current person's face. If it is judged that the current person is not a trustworthy person, it is judged whether the distance is small based on the distance between the current person and the door. Whether the time when the person is at a preset distance and less than the preset distance reaches a preset time, if so, it means that the current person is suspicious in the area in front of the door. At this time, it is necessary to obtain the vibration data of the door to judge the current person's behavioral threat level to the door according to the vibration data. If the behavioral threat level reaches the preset threat level, it means that the current person is attempting to commit a crime such as burglary. At this time, the second video information is obtained to obtain the facial features of the current person and behavioral evidence, so as to realize more convenient monitoring of the area in front of the door and criminal acts of attempting to break into the house without collecting and leaking the key personal biometric features and privacy of the surrounding residents.

[0012] In another possible implementation, judging whether the person is a trustworthy person based on the shoe size, leg size, gait, and movement route includes:

[0013] Determine the identity feature value of the person based on the shoe size and the leg size, and judge whether there is a target preset feature value consistent with the identity feature value among multiple preset identity feature values;

[0014] If there is a target preset characteristic value, obtaining multiple historical gaits and multiple historical movement routes corresponding to the target preset characteristic value;

[0015] Whether the person is a trustworthy person is determined based on a plurality of historical gaits, a plurality of historical moving routes, and the gaits and moving routes of the person corresponding to the preset characteristic values ​​of the target.

[0016] In another possible implementation, the leg size includes thigh length, calf length, thigh width, and calf width, and determining the identity feature value of the person based on the shoe size and leg length includes any one of the following:

[0017] Determine a first ratio of the calf length to the thigh length, and determine a second ratio of the first ratio to the shoe size, wherein the second ratio represents the identity feature value;

[0018] Determine a third ratio of the calf width to the thigh width, and determine a fourth ratio of the third ratio to the shoe size, wherein the fourth ratio represents the identity feature value;

[0019] Determine a first ratio of the calf length to the thigh length, determine a third ratio of the calf width to the thigh width, determine a leg feature value of the person based on the first ratio and the third ratio, determine a fifth ratio of the leg feature value to the shoe size, the fifth ratio representing the identity feature value;

[0020] Determine a sixth ratio of the calf length to the calf width, determine a seventh ratio of the thigh length to the thigh width, determine the leg characteristic value of the person based on the sixth ratio and the seventh ratio, determine an eighth ratio of the leg characteristic value to the shoe size, and the eighth ratio represents the identity characteristic value.

[0021] In another possible implementation, judging whether the person is a trustworthy person based on a plurality of historical gaits, a plurality of historical movement routes, and the gaits and movement routes of the person corresponding to the preset characteristic values ​​of the target includes:

[0022] Calculating a first similarity between the gait of the person and each historical gait, and calculating a second similarity between the movement route and each historical movement route;

[0023] Determining a first number at which the first similarity reaches a preset similarity threshold, and a second number at which the second similarity reaches a preset similarity threshold;

[0024] Determine a first ratio of the first number to the number of the plurality of historical gaits, and determine a second ratio of the second number to the plurality of historical movement routes;

[0025] If both the first proportion and the second proportion reach corresponding preset proportions, the person is determined to be a trustworthy person.

[0026] In another possible implementation, judging whether the person is a trustworthy person based on a plurality of historical gaits, a plurality of historical movement routes, and the gaits and movement routes of the person corresponding to the preset characteristic values ​​of the target includes:

[0027] Determine a frequently stepped point in a first preset area and a first posture of a foot and a leg at the frequently stepped point based on the multiple historical gaits and multiple historical movement routes;

[0028] Determining whether the person has hit a frequently visited spot based on the person's moving route;

[0029] If the hit is found, then based on the gait and movement route of the person, a second posture of the feet and legs of the person when the person hits the frequently stepped point is determined, and a third similarity between the first posture and the second posture is determined. If the third similarity reaches a preset similarity threshold, then the person is determined to be the trusted person; if the third similarity does not reach the preset similarity threshold, then the person is determined not to be the trusted person;

[0030] If there is no hit, it is determined that the person is not the trusted person.

[0031] In another possible implementation manner, determining the behavioral threat level of the person based on the vibration data includes:

[0032] determining from the vibration data the behavior of the vibration amplitude segments;

[0033] Determine the maximum amplitude and duration of each behavioral amplitude segment;

[0034] Determine the number of all behavioral amplitude segments, the average of the maximum amplitude values, and the total duration of all amplitude segments, and determine the behavioral score based on the number of behavioral amplitude segments, the average of the maximum amplitude values, and the total duration;

[0035] A target preset score interval where the behavior score is located is determined from a plurality of preset score intervals, each preset score interval corresponds to a preset threat level, and the preset threat level of the target preset score interval is determined as the behavior threat level.

[0036] In another possible implementation, the method further includes:

[0037] Determine the remaining time for the person to enter the room based on the behavior score;

[0038] And send the remaining time and the second video information to the target terminal device.

[0039] In the second aspect, the present application provides an intelligent monitoring system based on biometric recognition, which adopts the following technical solutions:

[0040] An intelligent monitoring system based on biometric recognition, comprising:

[0041] A first video acquisition module, configured to acquire first video information within a first preset monitoring range when a person is detected in a preset area, wherein the first preset monitoring range includes an area that can cover the legs and feet of the person in the environment;

[0042] a data determination module, configured to determine the shoe size, leg size, gait, and movement route of the person based on the first video information;

[0043] A judgment module, used for judging whether the person is a trustworthy person based on the shoe size, leg size, gait and movement route;

[0044] a data acquisition module, for acquiring the distance between the person and the door when the person is not in the state of being ...

[0045] The second video acquisition module is used to determine the behavioral threat level of the person based on the vibration data. If the behavioral threat level reaches a preset threat level, second video information of a second preset monitoring range is acquired, and the second preset monitoring range includes an area above the first preset monitoring range.

[0046] By adopting the above technical solution, the first video acquisition module acquires the first video information including the lower body of the current person, i.e., the legs and feet. The data determination module determines the shoe size, leg size, gait and movement route of the current person according to the first video information. Since each person's shoe size, leg size and gait are different, and different people have different movement routes in the area in front of the door, the judgment module determines whether the current person is a trustworthy person according to the shoe size, leg size, gait and movement route without acquiring other sensitive personal identity features such as the current person's face. If it is judged that the current person is not a trustworthy person, the data acquisition module determines the distance from the current person to the door. Whether the distance is less than the preset distance and whether the time less than the preset distance reaches the preset time, if so, it means that the current person is behaving suspiciously in the area in front of the door. At this time, the data acquisition module needs to obtain the vibration data of the door to judge the behavioral threat level of the current person to the door based on the vibration data. If the behavioral threat level reaches the preset threat level, it means that the current person is attempting to commit a crime such as burglary. At this time, the second video acquisition module obtains the second video information to obtain the facial features of the current person and behavioral evidence, so as to achieve more convenient monitoring of the area in front of the door and criminal acts attempting to break into the house without collecting and leaking the key personal biometrics and privacy of surrounding residents.

[0047] In another possible implementation, when the judgment module judges whether the person is a trustworthy person based on the shoe size, leg size, gait, and movement route, it is specifically used to:

[0048] Determine the identity feature value of the person based on the shoe size and the leg size, and judge whether there is a target preset feature value consistent with the identity feature value among multiple preset identity feature values;

[0049] If there is a target preset characteristic value, obtaining multiple historical gaits and multiple historical movement routes corresponding to the target preset characteristic value;

[0050] Whether the person is a trustworthy person is determined based on a plurality of historical gaits, a plurality of historical moving routes, and the gaits and moving routes of the person corresponding to the preset characteristic values ​​of the target.

[0051] In another possible implementation, the leg size includes thigh length, calf length, thigh width, and calf width. When the judgment module determines the identity feature value of a person based on the shoe size and the leg length, it is specifically used for any one of the following:

[0052] Determine a first ratio of the calf length to the thigh length, and determine a second ratio of the first ratio to the shoe size, wherein the second ratio represents the identity feature value;

[0053] Determine a third ratio of the calf width to the thigh width, and determine a fourth ratio of the third ratio to the shoe size, wherein the fourth ratio represents the identity feature value;

[0054] Determine a first ratio of the calf length to the thigh length, determine a third ratio of the calf width to the thigh width, determine a leg feature value of the person based on the first ratio and the third ratio, determine a fifth ratio of the leg feature value to the shoe size, the fifth ratio representing the identity feature value;

[0055] Determine a sixth ratio of the calf length to the calf width, determine a seventh ratio of the thigh length to the thigh width, determine the leg characteristic value of the person based on the sixth ratio and the seventh ratio, determine an eighth ratio of the leg characteristic value to the shoe size, and the eighth ratio represents the identity characteristic value.

[0056] In another possible implementation, when the judgment module judges whether the person is a trustworthy person based on a plurality of historical gaits, a plurality of historical movement routes, and the gait and movement route of the person corresponding to the preset characteristic value of the target, it is specifically used to:

[0057] Calculating a first similarity between the gait of the person and each historical gait, and calculating a second similarity between the movement route and each historical movement route;

[0058] Determining a first number at which the first similarity reaches a preset similarity threshold, and a second number at which the second similarity reaches a preset similarity threshold;

[0059] Determine a first ratio of the first number to the number of the plurality of historical gaits, and determine a second ratio of the second number to the plurality of historical movement routes;

[0060] If both the first proportion and the second proportion reach corresponding preset proportions, the person is determined to be a trustworthy person.

[0061] In another possible implementation, when the judgment module judges whether the person is a trustworthy person based on a plurality of historical gaits, a plurality of historical movement routes, and the gait and movement route of the person corresponding to the preset characteristic value of the target, it is specifically used to:

[0062] Determine a frequently stepped point in a first preset area and a first posture of a foot and a leg at the frequently stepped point based on the multiple historical gaits and multiple historical movement routes;

[0063] Determining whether the person has hit a frequently visited spot based on the person's moving route;

[0064] If the hit is found, then based on the gait and movement route of the person, a second posture of the feet and legs of the person when the person hits the frequently stepped point is determined, and a third similarity between the first posture and the second posture is determined. If the third similarity reaches a preset similarity threshold, then the person is determined to be the trusted person; if the third similarity does not reach the preset similarity threshold, then the person is determined not to be the trusted person;

[0065] If there is no hit, it is determined that the person is not the trusted person.

[0066] In another possible implementation, when determining the behavior threat level of the person based on the vibration data, the second video acquisition module is specifically configured to:

[0067] determining from the vibration data the behavior of the vibration amplitude segments;

[0068] Determine the maximum amplitude and duration of each behavioral amplitude segment;

[0069] Determine the number of all behavioral amplitude segments, the average of the maximum amplitude values, and the total duration of all amplitude segments, and determine the behavioral score based on the number of behavioral amplitude segments, the average of the maximum amplitude values, and the total duration;

[0070] A target preset score interval where the behavior score is located is determined from a plurality of preset score intervals, each preset score interval corresponds to a preset threat level, and the preset threat level of the target preset score interval is determined as the behavior threat level.

[0071] In another possible implementation, the system further includes:

[0072] A time determination module, used to determine the remaining time for the person to enter the room based on the behavior score;

[0073] The sending module is used to send the remaining time and the second video information to the target terminal device.

[0074] In a third aspect, the present application provides an electronic device, which adopts the following technical solution:

[0075] An electronic device, comprising:

[0076] at least one processor;

[0077] Memory;

[0078] At least one application, wherein at least one application is stored in a memory and configured to be executed by at least one processor, and at least one is configured to: execute an intelligent monitoring method based on biometric recognition as shown in any possible implementation of the first aspect.

[0079] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0080] A computer-readable storage medium, when the computer program is executed in a computer, enables the computer to execute the intelligent monitoring method based on biometric recognition as described in any one of the first aspects.

[0081] In summary, the present application includes at least one of the following beneficial technical effects:

[0082] The first video information including the lower body of the current person, i.e., the legs and feet, is obtained, and the shoe size, leg size, gait, and movement route of the current person are determined based on the first video information. Since each person's shoe size, leg size, and gait are different, and different people have different movement routes in the area in front of the door, it is judged whether the current person is a trustworthy person based on the shoe size, leg size, gait, and movement route without obtaining other sensitive personal identity features such as the current person's face. If it is judged that the current person is not a trustworthy person, it is judged whether the distance is less than the preset distance based on the distance from the current person to the door. And whether the time less than the preset distance reaches the preset time, if so, it means that the current person is acting suspiciously in the area in front of the door. At this time, it is necessary to obtain the vibration data of the door to judge the behavioral threat level of the current person to the door based on the vibration data. If the behavioral threat level reaches the preset threat level, it means that the current person is attempting to break into the house or other crimes. At this time, the second video information is obtained to obtain the facial features of the current person and behavioral evidence, so as to achieve more convenient monitoring of the area in front of the door and criminal acts attempting to break into the house without collecting and leaking the key personal biometric features and privacy of the surrounding residents. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] Figure 1 It is a flow chart of an intelligent monitoring method based on biometric recognition according to an embodiment of the present application.

[0084] Figure 2It is a flowchart of determining whether a person is a trustworthy person in an embodiment of the present application.

[0085] Figure 3 It is a structural diagram of an intelligent monitoring system based on biometric recognition in an embodiment of the present application.

[0086] Figure 4 It is a structural schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0087] The present application is further described in detail below in conjunction with the accompanying drawings.

[0088] After reading this specification, those skilled in the art may make non-creative modifications to this embodiment as needed, but such modifications are protected by patent law as long as they are within the scope of the claims of this application.

[0089] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0090] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0091] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0092] The embodiment of the present application provides an intelligent monitoring method based on biometric identification, which is executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited to this. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, and the embodiment of the present application does not limit this. Figure 1 As shown, the method includes step S101, step S102, step S103, step S104 and step S105, wherein:

[0093] S101, when it is detected that there is a person in a preset area, first video information within a first preset monitoring range is obtained.

[0094] The first preset monitoring range includes an area that can cover the legs and feet of people in the environment.

[0095] For the embodiments of the present application, the staff can install pyroelectric sensors, human sensors, and other sensors that can monitor whether there are people in the scene on the door, wall, or other locations that can monitor a certain area in front of the door. The sensor is connected to the electronic device via wired or wireless. When the sensor detects that there are people in the area in front of the door, it outputs a signal to let the electronic device know, and the electronic device obtains the first video information collected by the camera device. The camera device is set on the door or integrated in the door lock, and the viewing angle is facing the ground, so as to collect the first video information within the first preset monitoring range. When people are active in the first preset monitoring range, the camera can only collect images and videos of the legs and feet of the people, and thus cannot collect key personal biometric features of surrounding residents such as facial images.

[0096] S102, determining the shoe size, leg size, gait and movement route of the person based on the first video information.

[0097] For the embodiment of the present application, after the electronic device obtains the first video information, it can perform edge detection on each frame of the first video information, first perform denoising on each frame, then perform grayscale transformation to obtain a grayscale image, and finally determine the place where the grayscale steps occur as the edge, thereby obtaining the contour and features of the legs and feet. The electronic device can also input each frame into a trained network model for feature recognition, thereby obtaining the features of the person's legs and feet. Specifically, the network model can be a convolutional neural network model, a recurrent neural network model, or other types of network models.

[0098] After the electronic device determines the outline of the foot, it can determine the shoe size based on the number of pixels from the front to the back of the foot outline. After the electronic device determines the leg features, it determines the leg size of the person based on the leg feature outline and the coverage area of ​​the outline. The electronic device can determine feature points such as the thigh root, knee, ankle, heel and toe on the leg features and foot features, and then connect the feature points in each frame to obtain gait changes. To determine the moving position of a person, the electronic device can use the heel as a feature point and connect the heel feature points in each frame to obtain the moving route.

[0099] S103, judging whether the person is a trustworthy person based on the shoe size, leg size, gait and movement route.

[0100] For the embodiment of the present application, the trusted persons include surrounding residents, property staff and other set persons. The electronic device can determine the shoe size, leg size, gait and movement route of each trusted person based on the first video information within a period of time. Since there are differences between shoe size, leg size, gait and movement route, the shoe size, leg size, gait and movement route can be used as the identity identification and basis of each trusted person. The shoe size, leg size, gait and movement route are not important biological characteristics of people, and the possibility of privacy leakage is extremely small. Therefore, when a person appears in the area in front of the door, it can be accurately judged whether it is a trusted person based on the above factors.

[0101] S104, if not, obtain the distance from the person to the door, and if the distance is less than the preset distance and the duration less than the preset distance reaches the preset duration, obtain the vibration data of the door.

[0102] For the embodiment of the present application, if the electronic device determines that the person is not a trustworthy person, it means that the person is more likely to commit threatening acts such as theft to the residence, and when the person commits acts such as theft, he will perform certain operations on the door, thereby causing the door to vibrate. The staff can install distance sensors such as ultrasonic distance sensors and infrared distance sensors on the door to detect the distance between the person and the door. The preset distance is used as a demarcation point for judging whether the person is too close to the door. If the electronic device determines that the distance is less than the preset distance, it means that the person may want to perform certain destructive operations on the door. Therefore, the electronic device obtains vibration data on the door and determines whether to perform destructive operations based on the vibration data. Specifically, the electronic device can install a vibration sensor on the door to collect vibration data. Both the distance sensor and the vibration sensor are connected to the electronic device through wires or wirelessly to obtain distance and vibration data. If the distance reaches the preset distance and the duration less than the preset distance does not reach the preset duration, it means that the current person is not a big threat to the door, so the electronic device does not need to obtain vibration data of the door.

[0103] S105, determining a behavior threat level of the person based on the vibration data, and if the behavior threat level reaches a preset threat level, obtaining second video information of a second preset monitoring range.

[0104] The second preset monitoring range includes an area above the first preset monitoring range.

[0105] For the embodiment of the present application, the vibration data includes data such as amplitude and frequency. Therefore, the vibration data can characterize the behavior of the person against the door. The electronic device determines the current person's behavioral threat level based on the vibration data. The preset threat level is used as the dividing point of whether the current person's threat is too great. If the electronic device determines that the behavioral threat level reaches the preset threat level, it means that the current person is committing illegal acts such as burglary. The electronic device obtains the second video information of the second preset monitoring range. The second video information can be collected by another camera device. The other camera device is usually in a normally closed state, so it is impossible to collect personal biometric features and facial images of surrounding residents and other trusted persons. The camera device is set on the door, wall or other position that can cover the second preset monitoring range. By collecting the first video information within the first preset monitoring range and obtaining the current person's leg size, shoe size, gait and movement route, it is more accurate to comprehensively determine whether the current person is a trustworthy person based on the above four factors, and when it is determined that the current person is not a trustworthy person, the behavioral threat level of the current person's behavior to the residence is determined based on the vibration data on the door, and when the behavioral threat level reaches the preset threat level, the second video information of the second preset monitoring range is obtained, thereby collecting personal characteristics such as the current person's appearance and other evidence, thereby realizing the protection and monitoring of the residence without collecting and leaking the personal biometrics and privacy of surrounding residents.

[0106] In a possible implementation of the embodiment of the present application, in step S103, judging whether a person is a trustworthy person based on shoe size, leg size, gait, and movement route specifically includes step S1031, step S1032, and step S1033, wherein:

[0107] S1031, determining the identity feature value of the person based on the shoe size and the leg size, and determining whether there is a target preset feature value with the same identity feature value among multiple preset identity feature values.

[0108] For the embodiment of the present application, since the leg sizes of different people may be the same or different, and the shoe sizes of different people may be the same or different, the shoe size and leg size are merged to determine the identity feature value of the person, and the identity feature values ​​of different people are different, that is, the identity feature value is unique. The electronic device determines the shoe size and leg size of each trusted person based on the video information within a period of time in step S103, and then obtains the identity feature value of each trusted person, that is, the preset identity feature value. Therefore, after determining the identity feature value of the current person, the electronic device searches from multiple preset identity feature values ​​to determine whether there is a consistent target preset feature value.

[0109] S1032: If there is a target preset feature value, obtain multiple historical gaits and multiple historical movement routes corresponding to the target preset feature value.

[0110] For the embodiment of the present application, if there is a target preset characteristic value, it means that the current person may be a trusted person, or the current person may be disguised so that the identity characteristic value hits multiple preset identity characteristic values, and there is also a very small possibility that the current person is not a trusted person but hits the preset identity characteristic value. Therefore, it is necessary to further determine whether it is a trusted person. After determining the target preset characteristic value, the electronic device obtains the historical gait and historical movement route of the trusted person corresponding to the target preset characteristic value each time when moving in the area in front of the door.

[0111] S1033, judging whether the person is a trustworthy person based on multiple historical gaits, multiple historical moving routes, and the person's gaits and moving routes corresponding to the preset characteristic values ​​of the target.

[0112] For the embodiments of the present application, there are certain regularities in the movement of trusted persons in the area in front of the door, including differences in the gait of different people when walking, so the identity of the person can be judged based on the gait. Furthermore, if the trusted person is a nearby resident, the movement route of the nearby residents in front of the door is fixed due to people's subconsciousness and formed habits. In order to improve the accuracy of verifying whether the current person is a trusted person, the electronic device further determines whether the current person is a trusted person based on the determined gait and movement route of the current person in the area in front of the door, and the gait and movement route of the trusted person corresponding to the target preset characteristic value, thereby improving the accuracy of identity recognition.

[0113] In a possible implementation of the embodiment of the present application, the leg size includes thigh length, calf length, thigh width and calf width. In step S1033, determining the identity feature value of the person based on the shoe size and the leg length includes any one of step Sa (not shown in the figure), step Sb (not shown in the figure), step Sc (not shown in the figure) and step Sd (not shown in the figure).

[0114] Sa, determine a first ratio of the calf length and the thigh length, and determine a second ratio of the first ratio to the shoe size.

[0115] The second ratio represents the identity feature value.

[0116] For the embodiment of the present application, the ratio of the calf length to the thigh length varies from person to person. Therefore, the electronic device determines a feature point at the thigh root of the leg feature, determines a feature point at the knee position, and determines a feature point at the ankle position based on the determined leg feature. The electronic device connects the feature point at the thigh root with the feature point at the knee position to obtain the thigh length, and connects the feature point at the knee position with the feature point at the ankle to obtain the calf length. The electronic device can thereby determine a first ratio. Further, in order to improve the specificity of the identity feature value, the electronic device determines a second ratio of the first ratio to the shoe size in combination with the shoe size. The identity feature value of the current person represented by the second ratio is less likely to conflict with the identity feature value of the trusted person. The electronic device can determine the identity feature value of each trusted person in the same manner.

[0117] Sb, determine a third ratio of the calf width to the thigh width, and determine a fourth ratio of the third ratio to the shoe size.

[0118] Among them, the fourth ratio represents the identity feature value.

[0119] For the embodiment of the present application, the ratio of the calf width to the thigh width of different people is different. Therefore, the electronic device determines the position of the pants without wrinkles according to the determined leg features and leg contours, due to the modification effect of clothing on the leg shape, and the position without wrinkles represents the width of the calf or thigh more accurately. After the electronic device determines the area without wrinkles in the calf area, it determines the number of pixels with the largest horizontal area in the area, and uses the number of pixels to represent the calf width. After the electronic device determines the area without wrinkles in the thigh area, it determines the number of pixels with the largest horizontal area in the area, and uses the number to represent the thigh width. The specific electronic device can identify the area without wrinkles through a trained network model or identify the area without wrinkles through edge detection, which is not limited here. The electronic device can thus determine the third ratio, and further in order to improve the specificity of the identity feature value, the electronic device determines the fourth ratio of the third ratio and the shoe size in combination with the shoe size, and uses the fourth ratio to represent the identity feature value of the current person, which is less likely to conflict with the identity feature value of the trusted person. The electronic device can use the same method to determine the identity feature value of each trusted person.

[0120] Sc, determine a first ratio of calf length and thigh length, determine a third ratio of calf width and thigh width, determine the person's leg characteristic value based on the first ratio and the third ratio, and determine a fifth ratio of the leg characteristic value to the shoe size.

[0121] Among them, the fifth ratio represents the identity feature value.

[0122] For the embodiment of the present application, after the electronic device determines the first ratio and the third ratio in the manner disclosed in steps Sa and Sb, it determines the characteristic value of the current person's legs according to the first ratio and the third ratio, so that the characteristic value of the legs is more specific. Specifically, the electronic device can directly sum the second ratio and the third ratio to obtain the leg characteristic value, or perform weighted calculation on the second ratio and the third ratio to obtain the leg characteristic value. Then determine the fifth ratio of the leg characteristic value to the shoe size, and the fifth ratio represents the identity characteristic value so that it is more specific. The electronic device can use the same method to determine the identity characteristic value of each trusted person.

[0123] Sd, determine the sixth ratio of calf length to calf width, determine the seventh ratio of thigh length to thigh width, determine the leg characteristic value of the person based on the sixth ratio and the seventh ratio, and determine the eighth ratio of the leg characteristic value to the shoe size.

[0124] Among them, the eighth ratio represents the identity feature value.

[0125] For the embodiment of the present application, after the electronic device determines the calf length, calf width, thigh length and thigh width in the above manner, it can determine the sixth ratio of the calf length to the calf width, that is, the sixth ratio characterizes the characteristic value of the calf, and determine the seventh ratio of the thigh length to the thigh width, that is, the seventh ratio characterizes the characteristic value of the thigh. The electronic device further determines the leg characteristic value of the person according to the sixth ratio and the seventh ratio. Specifically, the electronic device can sum the sixth ratio and the seventh ratio to obtain the leg characteristic value, or perform weighted calculation on the sixth ratio and the seventh ratio to obtain the leg characteristic value, or obtain the leg characteristic value by other methods. Finally, the electronic device determines the eighth ratio of the leg characteristic value to the shoe size in combination with the shoe size, and uses the eighth ratio to characterize the identity characteristic value. The electronic device can use the same method to determine the identity characteristic value of each trusted person.

[0126] In other embodiments, the electronic device may also determine the width of the ankle, determine the ratio of the calf width to the ankle width, and use the ratio to characterize the calf characteristic value.

[0127] In a possible implementation of the embodiment of the present application, in step S1033, judging whether a person is a trustworthy person based on multiple historical gaits, multiple historical moving routes, and the gait and moving routes of the person corresponding to the preset characteristic values ​​of the target, specifically includes step S1 (not shown in the figure), step S2 (not shown in the figure), step S3 (not shown in the figure), and step S4 (not shown in the figure), wherein:

[0128] S1, calculating a first similarity between the gait of the person and each historical gait, and calculating a second similarity between the moving route and each historical moving route.

[0129] For the embodiment of the present application, the electronic device may input the gait of the current person and each historical gait into the trained network model to calculate the gait similarity, thereby obtaining a first similarity for each historical gait. Similarly, the electronic device may input the movement route of the current person and each historical movement route into the trained network model to calculate the route similarity, thereby obtaining a second similarity for each historical movement route. The electronic device may also calculate the gait of the feature points of each frame in the first video information of the current person, and perform the corresponding cosine distance calculation with each historical gait in the order of the frames to obtain the first similarity. Similarly, the electronic device may also calculate the cosine distance between the movement route of the current person and each historical movement route to obtain the second similarity.

[0130] S2, determining a first number of first similarities reaching a preset similarity threshold, and a second number of second similarities reaching a preset similarity threshold.

[0131] For the embodiment of the present application, the preset similarity threshold is used as the dividing point of whether the gait or movement route is close to the historical gait or movement route. The preset similarity thresholds for gait and movement route can be the same or different. After the electronic device obtains the first similarity, it determines the first number of the first similarity reaching the preset similarity threshold. The larger the first number, the more the gait of the current person is close to the historical gait of the trusted person with the target preset characteristic value, and the greater the possibility that the current person is a trusted person. Similarly, after the electronic device obtains the second similarity, it determines the second number of the second similarity reaching the preset similarity threshold. The larger the second number, the more the current person's movement route is close to the historical movement route of the trusted person with the target preset characteristic value, and the greater the possibility that the current person is a trusted person.

[0132] S3, determining a first ratio of the first number to the number of the plurality of historical gaits, and determining a second ratio of the second number to the plurality of historical movement routes.

[0133] For the embodiment of the present application, the electronic device determines a first ratio of the first number to the total number of historical gaits of the target preset characteristic value, and the larger the first ratio is, the greater the possibility that the current person is a trustworthy person of the target preset characteristic value in terms of gait. Similarly, the electronic device determines a second ratio of the second number to the historical moving routes of the target preset characteristic value, and the larger the second ratio is, the greater the possibility that the current person is a trustworthy person of the target preset characteristic value in terms of moving routes.

[0134] S4, if the first proportion and the second proportion both reach the corresponding preset proportions, the person is determined to be a trustworthy person.

[0135] For the embodiment of the present application, after the electronic device determines that the first proportion reaches its corresponding preset proportion, it can be said that the current person belongs to the trustworthy person corresponding to the target preset characteristic value in terms of gait. After the electronic device determines that the second proportion reaches its corresponding preset proportion, it can be said that the current person belongs to the trustworthy person corresponding to the target preset characteristic value in terms of movement route. Therefore, in combination with gait and movement route, the electronic device can determine that the current person is a trustworthy person when it determines that both meet the corresponding preset proportions. If one of the two does not reach the corresponding preset proportion or both do not reach the preset proportion, it is impossible to determine that the current person is a trustworthy person. Therefore, after determining the identity characteristic value of the current person, it is more accurate to further determine whether the current person is a trustworthy person based on gait and movement route.

[0136] In a possible implementation of the embodiment of the present application, in step S1033, judging whether a person is a trustworthy person based on multiple historical gaits, multiple historical moving routes, and the gait and moving routes of the person corresponding to the preset characteristic values ​​of the target, specifically includes step 1, step 2, step 3, and step 4, wherein:

[0137] Step 1: determine the frequently stepped points in the first preset area and the first postures of the feet and legs at the frequently stepped points based on multiple historical gaits and multiple historical movement routes.

[0138] For the embodiment of the present application, the electronic device performs overlapping mapping on multiple movement routes of the trusted person with the preset characteristic value of the target, so as to determine the overlapping points in the multiple movement routes, that is, the frequently stepped points in the area in front of the door. If there are multiple overlapping points, the position with the most overlaps can be determined as the frequently stepped point. After determining the frequently stepped point, the electronic device can determine the first posture of the foot and leg when each gait is at the frequently stepped point from multiple historical gaits. The first posture can be the angle between the foot and the leg, or the first posture can be represented by the line connecting the characteristic points of the foot and the leg.

[0139] Step 2: Determine whether the person has hit a frequently visited spot based on the person's movement route.

[0140] For the embodiment of the present application, the electronic device can set a coordinate system according to the area in front of the door, determine the coordinates of the frequently visited points and draw the current person's moving route on the coordinate system, so as to determine whether the coordinates of the frequently visited points are located on the moving route, and then determine whether the current person's moving route hits the frequently visited points.

[0141] Step three, if hit, then determine the second posture of the person's feet and legs when hitting the common stepping point based on the person's gait and movement route, determine the third similarity between the first posture and the second posture, if the third similarity reaches the preset similarity threshold, then determine that the person is a trustworthy person, if the third similarity does not reach the preset similarity threshold, then determine that the person is not a trustworthy person.

[0142] For the embodiment of the present application, after the electronic device determines that the current person's moving route hits the frequently stepped point, it means that the current person may be a trusted person, but the identity still needs to be further determined. The electronic device determines the gait of the current person when he is at the frequently stepped point based on the moving route and gait, and then determines the second posture of the foot and leg. The second posture can also be the angle between the foot and the leg, or the line connecting the characteristic points of the foot and the leg. After determining the first posture and the second posture, the electronic device calculates the similarity between the first posture and the second posture. Specifically, the cosine distance between the first posture and the second posture can be calculated to obtain the similarity, that is, the third similarity. The preset similarity threshold is used as the dividing point of whether the first posture and the second posture belong to the posture of the same person. The electronic device determines that the third similarity reaches the preset similarity threshold, which means that the posture of the foot and leg of the current person when he is at the frequently stepped point is the same as the posture of the person with the target preset characteristic value when he is at the frequently stepped point. The electronic device determines that the current person is a trusted person, otherwise he is not a trusted person.

[0143] Step 4: If there is no hit, it is determined that the person is not a trustworthy person.

[0144] For the embodiment of the present application, if the current person's moving route does not hit the frequently visited points, the electronic device can directly determine that the current person is not a trusted person corresponding to the target preset characteristic value. After determining the identity characteristic value of the current person, it is more accurate to further determine whether the current person is a trusted person based on the frequently visited points and the posture when located at the frequently visited points.

[0145] In a possible implementation of the embodiment of the present application, in step S105, determining the behavioral threat level of a person based on vibration data specifically includes step S1051 (not shown in the figure), step S1052 (not shown in the figure), step S1053 (not shown in the figure), and step S1054 (not shown in the figure), wherein:

[0146] S1051, determining the behavior as the amplitude segment from the vibration data.

[0147] For the embodiment of the present application, the electronic device analyzes and divides the collected vibration data to obtain multiple behavioral amplitude segments. The specific electronic device can map the vibration data to a coordinate system of amplitude with respect to time, filter out the amplitude segments with an amplitude of 0, and the remaining ones are the behavioral amplitude segments.

[0148] S1052, determining the maximum amplitude and duration of each behavior amplitude segment.

[0149] For the embodiment of the present application, after the electronic device determines each behavior amplitude segment, it determines the maximum amplitude of each behavior amplitude segment. The larger the maximum amplitude, the more violent the vibration of the door, the more serious the current person's vandalism to the door, the more serious the damage to the door, and the greater the possibility that the current person has entered the room. For example, the vibration when the door is damaged by a hammer or other tool is much greater than the vibration generated when the door is knocked. The longer the duration of each behavior amplitude segment, the longer the behavior on the door is, and the greater the possibility of vandalism to the door. For example, the vibration duration generated by knocking on the door is shorter than the vibration duration generated by damaging the door with a tool such as a saw.

[0150] S1053, determine the number of all behavior amplitude segments, the average value of the maximum amplitude, and the total duration of all amplitude segments, and determine the behavior score based on the number of behavior amplitude segments, the average value of the maximum amplitude, and the total duration.

[0151] For the embodiment of the present application, the greater the number of behavior amplitude segments, the more times the behavior is implemented on the door, the longer the time span, and the greater the possibility of vandalism on the door. The larger the maximum amplitude value, the greater the possibility of vandalism on the door. Similarly, the longer the duration of a single behavior amplitude segment, the greater the possibility of vandalism on the door. The electronic device can count the behavior amplitude segments to obtain the number of behavior amplitude segments, sum the maximum amplitude values ​​of each behavior amplitude segment and calculate the average amplitude value, and use the average value of the maximum amplitude value to characterize the overall vibration and shaking of the door. The larger the average value of the maximum amplitude value, the more violent the vibration of the door, and the more serious the damage to the door. The electronic device can sum the duration of each behavior amplitude segment to obtain the total duration. The larger the total duration, the longer the total duration of the door being subjected to the implementation behavior, and the more serious the damage to the door.

[0152] In summary, the number of behavioral amplitude segments, the average value of the maximum amplitude, and the total duration are all important factors that affect the degree of threat posed by the current person's behavior to the door, and the above three factors have different relevance to the threat posed by the current person's behavior. Therefore, the staff can set different coefficients for the number of behavioral amplitude segments, the average value of the maximum amplitude, and the total duration. The electronic device performs weighted calculations on the number of amplitude segments, the average value of the maximum amplitude, the duration, and the corresponding coefficients to obtain a behavior score, which characterizes the threat posed by the current person's behavior to the door. Assuming that the number of behavioral amplitude segments is 15, the average value of the maximum amplitude is 8 millimeters (mm), and the total duration is 20 seconds (s), the coefficient corresponding to the behavioral amplitude segment is 0.2, the coefficient corresponding to the maximum amplitude is 0.4, and the coefficient corresponding to the duration is 0.4, the electronic device determines that the current person's behavior score is 15×0.2+8×0.4+20×0.4=14.4. It should be noted that the coefficients of the three can be adaptively adjusted according to actual conditions and needs.

[0153] S1054, determining a target preset score interval where the behavior score is located from a plurality of preset score intervals, each preset score interval corresponding to a preset threat level, and determining the preset threat level of the target preset score interval as the behavior threat level.

[0154] For the embodiment of the present application, the staff can set a plurality of preset score intervals in advance according to experiments or calculations, and set a corresponding preset threat level for each preset score interval according to the actual possible situation. After the electronic device determines the behavior score, it determines the preset score interval where the behavior score is located, that is, the target preset score interval. The preset threat level corresponding to the target preset score interval is the threat level of the current person's behavior against the door. Therefore, the electronic device directly determines the preset threat level of the target preset score interval as the threat level of the current person's behavior against the door. Assume that there are five preset score intervals, namely preset score interval a (0, 4], preset score interval b (4, 8], preset score interval c (8, 12], preset score interval d (12, 16], preset score interval e (16, 20]. The corresponding threat levels are level one, level two, level three, level four and level five. Taking step S1053 as an example, the electronic device determines that the interval where the current person's behavior score is located is interval d, and the corresponding threat level is level four.

[0155] In a possible implementation of the embodiment of the present application, step S105 further includes step S106 (not shown in the figure) and step S107 (not shown in the figure), wherein:

[0156] S106, determining the remaining time for the person to enter the room based on the behavior score.

[0157] For the embodiment of the present application, the electronic device may multiply the behavior score by a preset coefficient to obtain a numerical value, and use the data to represent the remaining time. The electronic device may also set multiple score intervals, each score interval corresponds to the remaining time, and the score interval in which the behavior score is located is determined to determine the remaining time. The larger the behavior score, the smaller the corresponding remaining time.

[0158] S107. The remaining time and the second video information are sent to the target terminal device.

[0159] For the embodiment of the present application, the target terminal device can be the terminal device of the owner of the residence, or it can be a terminal device related to property or police affairs. The electronic device sends the remaining time and the second video information to the target terminal device so that the relevant personnel can know the degree of urgency and judge the tools carried by the current personnel based on the second video information so that the relevant personnel can make adequate preparations.

[0160] The above embodiment introduces an intelligent monitoring method based on biometric identification from the perspective of method flow, and the following embodiment introduces an intelligent monitoring system based on biometric identification from the perspective of a virtual module or a virtual unit. For details, please refer to the following embodiment.

[0161] The present application embodiment provides an intelligent monitoring system 20 based on biometric recognition, such as Figure 3 As shown, the intelligent monitoring system 20 based on biometric recognition may specifically include:

[0162] A first video acquisition module 201 is used to acquire first video information within a first preset monitoring range when a person is detected in a preset area, where the first preset monitoring range includes an area that can cover the legs and feet of the person in the environment;

[0163] A data determination module 202, for determining a person's shoe size, leg size, gait, and movement route based on the first video information;

[0164] A judgment module 203 is used to judge whether a person is a trustworthy person based on shoe size, leg size, gait and movement route;

[0165] The data acquisition module 204 is used to acquire the distance between the person and the door when the person is not in the state of being ...

[0166] The second video acquisition module 205 is used to determine the behavior threat level of the personnel based on the vibration data. If the behavior threat level reaches the preset threat level, the second video information of the second preset monitoring range is acquired. The second preset monitoring range includes the area above the first preset monitoring range.

[0167] The embodiment of the present application discloses an intelligent monitoring system 20 based on biometric identification, wherein a first video acquisition module 201 acquires first video information including the lower body of the current person, i.e., the legs and feet, and a data determination module 202 determines the shoe size, leg size, gait, and movement route of the current person based on the first video information. Since each person's shoe size, leg size, and gait are different, and different people have different movement routes in the doorfront area, the judgment module 203 judges whether the current person is a trustworthy person based on the shoe size, leg size, gait, and movement route without acquiring other sensitive personal identity features such as the current person's face. If it is judged that the current person is not a trustworthy person, the data acquisition module 204 determines the shoe size, leg size, gait, and movement route of the current person based on the shoe size, leg size, gait, and movement route. According to the distance between the current person and the door, it is determined whether the distance is less than the preset distance and whether the time period less than the preset distance reaches the preset time period. If so, it means that the current person is suspicious in the area in front of the door. At this time, the data acquisition module 204 needs to obtain the vibration data of the door to determine the behavioral threat level of the current person to the door based on the vibration data. If the behavioral threat level reaches the preset threat level, it means that the current person is committing a crime such as attempting to break into a house. At this time, the second video acquisition module 205 obtains the second video information to obtain the facial features of the current person and behavioral evidence, thereby realizing more convenient monitoring of the area in front of the door and criminal acts attempting to break into the house without collecting and leaking the key personal biometric features and privacy of surrounding residents.

[0168] In a possible implementation of the embodiment of the present application, when the judgment module 203 judges whether a person is a trustworthy person based on the shoe size, leg size, gait, and movement route, it is specifically used to:

[0169] Determine the identity feature value of the person based on the shoe size and the leg size, and determine whether there is a target preset feature value with the same identity feature value among the multiple preset identity feature values;

[0170] If there is a target preset characteristic value, obtaining multiple historical gaits and multiple historical movement routes corresponding to the target preset characteristic value;

[0171] Whether a person is a trustworthy person is determined based on multiple historical gaits, multiple historical moving routes, the person's gaits and moving routes corresponding to the preset characteristic values ​​of the target.

[0172] In a possible implementation of the embodiment of the present application, the leg size includes thigh length, calf length, thigh width and calf width. When the judgment module 203 determines the identity feature value of a person based on the shoe size and the leg length, it is specifically used for any one of the following:

[0173] Determine a first ratio of the calf length to the thigh length, and determine a second ratio of the first ratio to the shoe size, wherein the second ratio represents an identity feature value;

[0174] Determine a third ratio of the calf width to the thigh width, and determine a fourth ratio of the third ratio to the shoe size, wherein the fourth ratio represents an identity feature value;

[0175] Determine a first ratio of calf length to thigh length, determine a third ratio of calf width to thigh width, determine a leg feature value of the person based on the first ratio and the third ratio, determine a fifth ratio of the leg feature value to the shoe size, the fifth ratio representing the identity feature value;

[0176] Determine the sixth ratio of calf length to calf width, determine the seventh ratio of thigh length to thigh width, determine the leg characteristic value of the person based on the sixth ratio and the seventh ratio, determine the eighth ratio of the leg characteristic value to the shoe size, and the eighth ratio represents the identity characteristic value.

[0177] In a possible implementation of the embodiment of the present application, when the judgment module 203 judges whether a person is a trustworthy person based on a plurality of historical gaits, a plurality of historical moving routes, a person's gait and a moving route corresponding to a preset characteristic value of the target, it is specifically used to:

[0178] Calculating a first similarity between the gait of the person and each historical gait, and calculating a second similarity between the moving route and each historical moving route;

[0179] Determining a first number at which the first similarity reaches a preset similarity threshold, and a second number at which the second similarity reaches a preset similarity threshold;

[0180] Determine a first ratio of the first number to the number of the plurality of historical gaits, and determine a second ratio of the second number to the plurality of historical movement routes;

[0181] If both the first ratio and the second ratio reach the corresponding preset ratios, the person is determined to be a trustworthy person.

[0182] In a possible implementation of the embodiment of the present application, when the judgment module 203 judges whether a person is a trustworthy person based on a plurality of historical gaits, a plurality of historical moving routes, a person's gait and a moving route corresponding to a preset characteristic value of the target, it is specifically used to:

[0183] Determine a frequently stepped point in a first preset area and a first posture of a foot and a leg at the frequently stepped point based on a plurality of historical gaits and a plurality of historical movement routes;

[0184] Determine whether the personnel have hit the frequently visited spots based on their movement routes;

[0185] If the hit is found, then based on the gait and movement route of the person, the second posture of the person's feet and legs when hitting the frequently stepped point is determined, and the third similarity between the first posture and the second posture is determined. If the third similarity reaches a preset similarity threshold, the person is determined to be a trustworthy person. If the third similarity does not reach the preset similarity threshold, the person is determined to be not a trustworthy person.

[0186] If it does not hit, it is determined that the person is not a trustworthy person.

[0187] In a possible implementation of the embodiment of the present application, when the second video acquisition module 205 determines the behavioral threat level of a person based on the vibration data, it is specifically used to:

[0188] Determining the behavior as amplitude segments from the vibration data;

[0189] Determine the maximum amplitude and duration of each behavioral amplitude segment;

[0190] Determine the number of all behavioral amplitude segments, the average of the maximum amplitude values, and the total duration of all amplitude segments, and determine the behavioral score based on the number of behavioral amplitude segments, the average of the maximum amplitude values, and the total duration;

[0191] A target preset score interval where the behavior score is located is determined from a plurality of preset score intervals, each preset score interval corresponds to a preset threat level, and the preset threat level of the target preset score interval is determined as the behavior threat level.

[0192] In a possible implementation of the embodiment of the present application, the system 20 further includes:

[0193] A time determination module, used to determine the remaining time for a person to enter the room based on the behavior score;

[0194] The sending module is used to send the remaining time and the second video information to the target terminal device.

[0195] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described intelligent monitoring system 20 based on biometric recognition can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0196] An electronic device is provided in an embodiment of the present application, such as Figure 4 As shown, Figure 4 The electronic device 30 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 30 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 30 does not constitute a limitation on the embodiments of the present application.

[0197] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0198] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but it does not mean that there is only one bus or only one type of bus.

[0199] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0200] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0201] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 4 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0202] The embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment. Compared with the related art, the embodiment of the present application obtains first video information including the lower body of the current person, namely the legs and feet, and determines the shoe size, leg size, gait and movement route of the current person based on the first video information. Since each person's shoe size, leg size and gait are different, and for the area in front of the door, different people have different movement routes in the area in front of the door. Therefore, based on the shoe size, leg size, gait and movement route, it is judged whether the current person is a trustworthy person without obtaining other sensitive personal identity features such as the current person's face. If it is judged that the person is not a trustworthy person, the distance between the current person and the door is judged based on the distance. Whether the distance is less than the preset distance and whether the time period less than the preset distance reaches the preset time period, if so, it means that the current person is acting suspiciously in the area in front of the door. At this time, it is necessary to obtain the vibration data of the door to judge the threat level of the current person's behavior to the door according to the vibration data. If the threat level of the behavior reaches the preset threat level, it means that the current person is attempting to break into the house or other crimes. At this time, the second video information is obtained to obtain the facial features of the current person and behavioral evidence, so as to realize more convenient monitoring of the area in front of the door and criminal acts of attempting to break into the house without collecting and leaking the key personal biometric features and privacy of the surrounding residents.

[0203] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0204] The above description is only a partial implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. An intelligent monitoring method based on biometric recognition, characterized in that: include: When a person is detected in a preset area, first video information within a first preset monitoring range is obtained, where the first preset monitoring range includes an area that can cover the legs and feet of the person in the environment; Determining the shoe size, leg size, gait, and movement route of the person based on the first video information; Determining whether the person is a trustworthy person based on the shoe size, leg size, gait, and movement route; If not, the distance from the person to the door is obtained. If the distance is less than a preset distance and the time duration less than the preset distance reaches a preset time duration, the vibration data of the door is obtained. determining a behavior threat level of the person based on the vibration data, and if the behavior threat level reaches a preset threat level, acquiring second video information of a second preset monitoring range, where the second preset monitoring range includes an area above the first preset monitoring range; Wherein, judging whether the person is a trustworthy person based on the shoe size, leg size, gait and movement route includes: Determine the identity feature value of the person based on the shoe size and the leg size, and judge whether there is a target preset feature value consistent with the identity feature value among multiple preset identity feature values; If there is a target preset characteristic value, obtaining multiple historical gaits and multiple historical movement routes corresponding to the target preset characteristic value; Whether the person is a trustworthy person is determined based on a plurality of historical gaits, a plurality of historical moving routes, and the gaits and moving routes of the person corresponding to the preset characteristic values ​​of the target.

2. The intelligent monitoring method based on biometric recognition according to claim 1, characterized in that: The leg size includes thigh length, calf length, thigh width and calf width. The identification feature value of a person determined based on the shoe size and leg length includes any one of the following: Determine a first ratio of the calf length to the thigh length, and determine a second ratio of the first ratio to the shoe size, wherein the second ratio represents the identity feature value; Determine a third ratio of the calf width to the thigh width, and determine a fourth ratio of the third ratio to the shoe size, wherein the fourth ratio represents the identity feature value; Determine a first ratio of the calf length to the thigh length, determine a third ratio of the calf width to the thigh width, determine a leg feature value of the person based on the first ratio and the third ratio, determine a fifth ratio of the leg feature value to the shoe size, the fifth ratio representing the identity feature value; Determine a sixth ratio of the calf length to the calf width, determine a seventh ratio of the thigh length to the thigh width, determine the leg characteristic value of the person based on the sixth ratio and the seventh ratio, determine an eighth ratio of the leg characteristic value to the shoe size, and the eighth ratio represents the identity characteristic value.

3. The intelligent monitoring method based on biometric recognition according to claim 1, characterized in that: The determining whether the person is a trustworthy person based on a plurality of historical gaits, a plurality of historical moving routes, and the gaits and moving routes of the person corresponding to the preset characteristic values ​​of the target includes: Calculating a first similarity between the gait of the person and each historical gait, and calculating a second similarity between the movement route and each historical movement route; Determining a first number at which the first similarity reaches a preset similarity threshold, and a second number at which the second similarity reaches a preset similarity threshold; Determine a first ratio of the first number to the number of the plurality of historical gaits, and determine a second ratio of the second number to the plurality of historical movement routes; If both the first proportion and the second proportion reach corresponding preset proportions, the person is determined to be a trustworthy person.

4. The intelligent monitoring method based on biometric recognition according to claim 1, characterized in that: The determining whether the person is a trustworthy person based on a plurality of historical gaits, a plurality of historical moving routes, and the gaits and moving routes of the person corresponding to the preset characteristic values ​​of the target includes: Determine a frequently stepped point in a first preset area and a first posture of a foot and a leg at the frequently stepped point based on the multiple historical gaits and multiple historical movement routes; Determining whether the person has hit a frequently visited spot based on the person's moving route; If the hit is found, then based on the gait and movement route of the person, a second posture of the feet and legs of the person when the person hits the frequently stepped point is determined, and a third similarity between the first posture and the second posture is determined. If the third similarity reaches a preset similarity threshold, then the person is determined to be the trusted person. If the third similarity does not reach the preset similarity threshold, then the person is determined not to be the trusted person. If there is no hit, it is determined that the person is not the trusted person.

5. The intelligent monitoring method based on biometric recognition according to claim 1, characterized in that: The determining the behavioral threat level of the person based on the vibration data comprises: determining from the vibration data the behavior of the vibration amplitude segments; Determine the maximum amplitude and duration of each behavioral amplitude segment; Determine the number of all behavioral amplitude segments, the average of the maximum amplitude values, and the total duration of all amplitude segments, and determine the behavioral score based on the number of behavioral amplitude segments, the average of the maximum amplitude values, and the total duration; A target preset score interval where the behavior score is located is determined from a plurality of preset score intervals, each preset score interval corresponds to a preset threat level, and the preset threat level of the target preset score interval is determined as the behavior threat level.

6. The intelligent monitoring method based on biometric recognition according to claim 5, characterized in that: The method further comprises: Determine the remaining time for the person to enter the room based on the behavior score; And send the remaining time and the second video information to the target terminal device.

7. An intelligent monitoring system based on biometric recognition, characterized in that: include: A first video acquisition module is used to acquire first video information within a first preset monitoring range when a person is detected in a preset area, wherein the first preset monitoring range includes an area that can cover the legs and feet of the person in the environment; a data determination module, configured to determine the shoe size, leg size, gait, and movement route of the person based on the first video information; A judgment module, used for judging whether the person is a trustworthy person based on the shoe size, leg size, gait and movement route; A data acquisition module, for acquiring the distance from the person to the door when the person is not in the state of being ... A second video acquisition module is used to determine the behavior threat level of the person based on the vibration data, and if the behavior threat level reaches a preset threat level, obtain second video information of a second preset monitoring range, where the second preset monitoring range includes an area above the first preset monitoring range; Wherein, when the judgment module judges whether the person is a trustworthy person based on the shoe size, leg size, gait and movement route, it is specifically used to: Determine the identity feature value of the person based on the shoe size and the leg size, and judge whether there is a target preset feature value consistent with the identity feature value among multiple preset identity feature values; If there is a target preset characteristic value, obtaining multiple historical gaits and multiple historical movement routes corresponding to the target preset characteristic value; Whether the person is a trustworthy person is determined based on a plurality of historical gaits, a plurality of historical moving routes, and the gaits and moving routes of the person corresponding to the preset characteristic values ​​of the target.

8. An electronic device, characterized in that: It includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in the memory and is configured to be executed by the at least one processor, and the at least one application is used to execute the intelligent monitoring method based on biometric recognition according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the intelligent monitoring method based on biometric identification as described in any one of claims 1 to 6.

Citation Information

Patent Citations

  • Gait data acquisition and labeling method and application

    CN112784740A

  • Gait recognition based intelligent building monitoring system

    CN203120058U

  • Method, apparatus, and system for wireless tracking, scanning and monitoring

    EP3739356A1

  • Identity information determining method and apparatus, and storage medium

    WO2020249025A1