Anti-lost method and system, readable storage medium, cloud server and mobile terminal

Abstract

A method, a computer readable storage medium, a cloud server, a mobile terminal and a system for preventing a person from getting lost are disclosed. The method comprises: obtaining a reference face image of a ward and reference face images of at least one guardian associated with the ward; obtaining an image of a monitoring area; determining physical positions of the ward and each of the guardians in the monitoring area based on the image of the monitoring area, the reference face image of the ward and the reference face images of each of the guardians; determining physical distances between the ward and each of the guardians according to the physical positions of the ward and each of the guardians in the monitoring area, and judging whether a minimum value of all the physical distances is greater than a preset threshold; and issuing a warning signal when the minimum value of all the physical distances is greater than the preset threshold.

Description

Technical Field

[0001] This disclosure relates to the field of display technology, specifically to an anti-wandering method, a computer-readable storage medium, a cloud server, a mobile terminal, and an anti-wandering system. Background Technology

[0002] In crowded places such as parks, squares, and shopping malls, it is easy for children, the elderly, and other wards to get lost, which makes it necessary to find them in a timely manner. Summary of the Invention

[0003] This disclosure presents an anti-wandering method, a computer-readable storage medium, a cloud server, a mobile terminal, and an anti-wandering system.

[0004] Firstly, this disclosure provides a method for preventing people from getting lost, including:

[0005] Obtain a reference facial image of the ward, and a reference facial image of at least one guardian associated with the ward;

[0006] Acquire images of the monitored area;

[0007] Based on the images of the monitored area, the reference facial images of the ward, and the associated reference facial images of each of the guardians, the physical locations of the ward and each of the guardians in the monitored area are determined.

[0008] Based on the physical locations of the ward and each of the guardians in the monitoring area, the physical distance between the ward and each of the guardians is determined, and it is determined whether the minimum value among all physical distances is greater than a preset threshold; when the minimum value among all physical distances is greater than the preset threshold, an early warning signal is issued.

[0009] In some embodiments, the physical location of the ward and each guardian in the monitored area is determined based on images of the monitored area, reference facial images of the ward, and associated reference facial images of each guardian, specifically including:

[0010] Face detection is performed on the images of the monitored area to obtain individual face images in the monitored area;

[0011] Based on the facial images of each person in the monitoring area, the reference facial image of the person under guardianship, and the reference facial image of each guardian, it is determined whether the person under guardianship and the guardian exist in the monitoring area;

[0012] When the ward and the guardian are present in the monitoring area, obtain the external frame of the ward and each of the guardians;

[0013] The physical location of each guardian and ward in the monitoring area is determined based on the image position of their external frames in the image of the monitoring area.

[0014] In some embodiments, obtaining the external frame of the ward and each of the guardians includes:

[0015] Human detection is performed on the images of the monitored area to obtain the bounding boxes of each person in the monitored area;

[0016] The outer frame of the person whose face frame overlaps with the person under guardianship is taken as the outer frame of the person under guardianship; for any guardian, the outer frame of the person whose face frame overlaps with the person under guardianship is taken as the outer frame of the person under guardianship.

[0017] In some embodiments, obtaining a reference facial image of the ward and reference facial images of at least one guardian associated with the ward specifically includes:

[0018] Acquire human images of multiple individuals at the entrance of the monitored area;

[0019] From the human body images of the multiple individuals, obtain a reference facial image of the ward and a reference facial image of at least one guardian associated with the ward.

[0020] In some embodiments, obtaining a reference facial image of the ward and a reference facial image of at least one guardian associated with the ward from the human body images of the plurality of persons specifically includes:

[0021] Based on the human images of the plurality of individuals, the feature information of each individual among the plurality of individuals is determined, the feature information including posture information and / or clothing information;

[0022] Based on the characteristic information of each of the multiple individuals, determine whether there is a group of related individuals among the multiple individuals;

[0023] When there is a group of related individuals among the multiple individuals, determine whether the ward and the guardian are in the group of related individuals.

[0024] When the ward and the guardian are present in the associated person group, face detection is performed on the ward and the guardian to obtain reference face images of the ward and the guardian.

[0025] In some embodiments, acquiring a reference facial image of the ward and a reference facial image of at least one guardian associated with the ward may further include: receiving and storing registration information uploaded by a mobile terminal, wherein the registration information includes: reference facial images of multiple individuals;

[0026] Obtaining a reference facial image of the ward and a reference facial image of at least one guardian associated with the ward specifically includes: in response to a first selection instruction, selecting the corresponding reference facial images of the ward and the guardian from pre-stored registration information.

[0027] In some embodiments, the warning signal is sent to the mobile terminal.

[0028] In some embodiments, after issuing a warning signal, the anti-lost method further includes:

[0029] Send an instruction input request to the mobile terminal so that the mobile terminal outputs instruction request information, the instruction request information being used to request the user to input navigation instructions or abandon instructions;

[0030] When the navigation instruction is received, navigation information is sent to the mobile terminal; the navigation information includes route information between the ward and the guardian.

[0031] In some embodiments, acquiring a reference facial image of the ward and a reference facial image of at least one guardian associated with the ward may further include: receiving and storing registration information uploaded by a mobile terminal, wherein the registration information includes: reference facial images of multiple individuals;

[0032] Obtaining a reference facial image of the ward and a reference facial image of at least one guardian associated with the ward, specifically including:

[0033] In response to the second selection instruction, at least the reference face image of the corresponding ward is selected from the pre-stored registration information;

[0034] Acquire human images of multiple individuals at the entrance of the monitored area;

[0035] Based on the reference facial image of the ward, the reference facial image of at least one guardian associated with the ward is obtained from the human images of multiple people at the entrance of the monitored area.

[0036] In some embodiments, based on the reference facial image of the ward, obtaining the reference facial image of at least one guardian associated with the ward from the human images of multiple individuals at the entrance of the monitored area, specifically includes:

[0037] Based on the reference facial image of the ward and the human body images of the multiple individuals, determine the characteristic information of the ward and the characteristic information of each of the multiple individuals, wherein the characteristic information includes posture information and / or clothing information;

[0038] Based on the characteristic information of the ward and the characteristic information of each of the multiple individuals, obtain the associated group of individuals at the entrance of the monitoring area, wherein the associated group of individuals includes the ward and the guardian;

[0039] Obtain the facial images of all guardians in the associated group, and use them as reference facial images for each guardian.

[0040] In some embodiments, the preset threshold is related to the population density in the monitored area.

[0041] Secondly, embodiments of this disclosure also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method for preventing people from getting lost.

[0042] Thirdly, this disclosure also provides a cloud server, which includes a memory and a processor, wherein a computer program is stored in the memory, and the computer program, when executed by the processor, implements the above-described method for preventing people from getting lost.

[0043] Fourthly, embodiments of this disclosure also provide a mobile terminal, which includes a memory and a processor, wherein a computer program is stored on the memory, and the computer program, when executed by the processor, performs the following steps:

[0044] In response to the warning activation command, a start signal is sent to the cloud server, so that the cloud server responds to the start signal and implements the above-mentioned anti-lost method;

[0045] In response to the warning signal, corresponding warning information is output.

[0046] In some embodiments, when the computer program is executed by the processor, it further performs the following steps:

[0047] The registration information is obtained and uploaded to the cloud server; wherein, the registration information includes: reference facial images of multiple individuals.

[0048] In some embodiments, when the computer program is executed by the processor, it further performs the following steps:

[0049] In response to the instruction input request sent by the cloud server, an instruction request message is output to request the user to input navigation instructions or abandon instructions;

[0050] When the navigation instruction is received, the navigation instruction is sent to the cloud server so that the cloud server generates navigation information in response to the navigation instruction;

[0051] Receive and display the navigation information.

[0052] Fifthly, this disclosure also provides an anti-lost system, which includes the aforementioned cloud server and the aforementioned mobile terminal. Attached Figure Description

[0053] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation thereof. In the drawings:

[0054] Figure 1 This is a flowchart of an anti-wandering method provided in some embodiments of this disclosure.

[0055] Figure 2 This is a schematic diagram of an anti-wandering method provided in some other embodiments of this disclosure.

[0056] Figure 3 This is a schematic diagram of an anti-wandering method provided in some other embodiments of this disclosure.

[0057] Figure 4 This is a flowchart illustrating an optional implementation of step S12 provided in some embodiments of this disclosure.

[0058] Figure 5 This is a flowchart of an anti-wandering method provided in some further embodiments of this disclosure.

[0059] Figure 6 This diagram illustrates the steps involved when a computer program on a mobile terminal is executed by a processor.

[0060] Figure 7 This is a schematic diagram of an anti-lost system provided in some embodiments of this disclosure. Detailed Implementation

[0061] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this disclosure. All other embodiments obtained by those skilled in the art based on the described embodiments of this disclosure without creative effort are within the scope of protection of this disclosure.

[0062] Figure 1 This is a flowchart of an anti-lost method provided in some embodiments of this disclosure, wherein the anti-lost method can be applied to a cloud server, such as... Figure 1 As shown, the method for preventing people from getting lost includes the following steps S10 to S41:

[0063] S10. Obtain a reference facial image of the ward and a reference facial image of at least one guardian associated with the ward.

[0064] The ward can refer to children, the elderly, people with intellectual disabilities, or other persons who require guardianship. The guardian associated with the ward refers to the person who enters the monitored area with the ward and is capable of caring for the ward. The monitored area can be a park, square, shopping mall, or similar location.

[0065] The reference facial image of the ward (or guardian) refers to the facial image of the ward (or guardian) before entering the monitored area. The reference facial image can be captured by an image acquisition device at the entrance of the monitored area and uploaded to a cloud server; it can also be captured by a mobile terminal (e.g., a mobile phone) and uploaded to the cloud server; or it can be obtained from a database. For example, if an application is installed on the mobile terminal and its associated database stores reference facial images of multiple individuals, the application on the mobile terminal can obtain the identity information of the ward (or guardian), and the database can then send the reference facial image corresponding to that identity information to the cloud server. There can be one or multiple guardians.

[0066] S20. Acquire images of the monitored area.

[0067] The images of the monitored area can be acquired by image acquisition devices within the monitored area and then uploaded to the cloud server. These image acquisition devices may include multiple cameras, each with a specific monitoring range. The images captured by these multiple cameras collectively form the image of the entire monitored area.

[0068] The image acquisition device in the monitoring area can acquire images of the monitoring area in real time, and the cloud server can acquire these images in real time or at a certain frequency. In one example, the cloud server receives one image of the monitoring area every five frames acquired by the image acquisition device. Each time the cloud server acquires an image, it executes subsequent steps S30 to S41.

[0069] S30. Based on the images of the monitored area, the reference facial image of the ward, and the associated reference facial image of each guardian, determine the physical location of the ward in the monitored area and the physical location of each guardian in the monitored area.

[0070] The cloud server can perform face detection on the images of the monitored area to obtain all the face images appearing in the monitored area, and compare them with the reference face image of the ward and the face image of the guardian to determine which person in the monitored area is the ward and which person is the ward.

[0071] S40. Determine the physical distance between the ward and each guardian based on the physical location of the ward in the monitoring area and the physical location of each guardian in the monitoring area.

[0072] The "physical distance" between the ward and the guardian refers to the distance between the ward's physical location in the monitored area and the guardian's physical location in the monitored area.

[0073] S41. Determine if the minimum value among all physical distances is greater than a preset threshold; if so, issue an early warning signal. The minimum value among all physical distances is the distance between the physical location of the ward and the physical location of the guardian closest to the ward.

[0074] The cloud server can obtain a preset threshold before step S30. Optionally, the preset threshold is related to the population density in the monitored area; for example, the preset threshold is roughly positively correlated with the population density in the monitored area. In some examples, the preset threshold can be input by the user into a mobile terminal and then sent to the cloud server by the mobile terminal. For example, when the population density in the monitored area is high, the user can set the preset threshold to a smaller value, such as 5m; when the population density in the monitored area is low, the user can set the preset threshold to a larger value, such as 10m or 20m. In other examples, the preset threshold can be determined by the cloud server. For example, the cloud server can determine the population density in the monitored area based on the image of the monitored area and set the preset threshold based on the population density in the monitored area. For example, when the detected population density in the monitored area is greater than or equal to 1 person / 2m, the preset threshold can be set accordingly. 2 When the pedestrian density in the monitored area is less than 1 person / 2m, the preset threshold is set to 5m; 2 And greater than 1 person / 10m 2 When the population density in the monitored area is between 1 and 10m, set the preset threshold to 10m; ensure the population density in the monitored area is less than or equal to 1 person / 10m. 2 When that happens, set the preset threshold to 15m.

[0075] For example, if the ward is child A, and the guardian associated with child A is adult B, then if the physical distance between child A and adult B is greater than a preset threshold, an early warning signal will be issued. As another example, if the ward is child A, and the guardians associated with child A are adults B and C, then if the physical distance between child A and adult B is greater than the physical distance between child A and adult C, and the physical distance between child A and adult C is also greater than a preset threshold, an early warning signal will be issued.

[0076] The alarm signal can be sent from the cloud server to the guardian's mobile terminal, or it can be sent in other forms, such as by broadcasting.

[0077] In the anti-lost method provided in this embodiment, the physical location of the ward and the physical location of the guardian in the monitoring area are determined based on the image of the monitoring area, the reference face image of the ward, and the reference face image of the associated guardian. Furthermore, when the physical distance between the ward and the nearest guardian exceeds a preset threshold, an early warning signal is issued to remind the guardian, thereby reducing the probability of the ward getting lost, and without requiring the ward to wear a device.

[0078] Figure 2 This is a schematic diagram of an anti-wandering method provided in some other embodiments of this disclosure. Figure 2 for Figure 1 This is a specific implementation scheme of the anti-lost method shown. For example... Figure 2 As shown, methods to prevent people from getting lost include:

[0079] S01. Receive and store the registration information uploaded by the mobile terminal. The registration information includes: reference facial images of multiple individuals. These multiple individuals may include guardians and wards. The reference facial image for each individual in the registration information can be: a recently taken facial image of each individual.

[0080] For example, a user (who can be the owner of the mobile device and also a guardian) first registers as an administrator on the mobile device. During registration, the user can add their own identity information, such as name, ID number, phone number, and a reference facial image. The user can also bind the identity information of the person under their guardianship to the mobile device, such as name, ID number, and a reference facial image. The mobile device then uploads this registration information (i.e., the identity information of the guardian and the person under their guardianship) to the storage module of the cloud server for storage.

[0081] It should be noted that the registration information can include reference facial images of multiple guardians. For example, after registering as an administrator on a mobile device, a user can add the identity information of not only the ward but also other guardians. Furthermore, the administrator can manage the added identity information, such as deleting it.

[0082] S10. Obtain a reference facial image of the ward and a reference facial image of at least one guardian associated with the ward.

[0083] In some embodiments, step S10 may specifically include: S10a, in response to a first selection instruction, selecting the corresponding reference face images of the ward and the guardian from the registration information pre-stored in the storage module.

[0084] Users can select the guardian and ward they wish to monitor on their mobile devices. The mobile device then generates a first selection command based on the user's selection and uploads it to the cloud server. The cloud server, based on the first selection command, selects the corresponding reference facial images of the guardian and ward from its storage module.

[0085] S20. Acquire images of the monitored area.

[0086] S30. Based on the images of the monitored area, the reference facial image of the ward, and the associated reference facial image of each guardian, determine the physical location of the ward in the monitored area and the physical location of each guardian in the monitored area.

[0087] Specifically, step S30 may include:

[0088] S31. Perform face detection on the image of the monitored area to obtain the face bounding boxes of each face in the monitored area, thereby obtaining the face image of each face.

[0089] The embodiments disclosed herein do not specify the specific method of face detection, as long as it is possible to acquire each face image.

[0090] S32. Based on the facial images of each person in the monitoring area, the reference facial image of the ward, and the reference facial image of each guardian, determine whether the ward and guardian exist in the monitoring area. If the ward and guardian exist in the monitoring area, proceed to step S33.

[0091] S33. Obtain the external frame of the ward and each guardian. In some embodiments, step S33 may specifically include:

[0092] S331. Perform human detection on the image of the monitored area to obtain the bounding box of each person in the monitored area.

[0093] In this embodiment, the specific method of human body detection is not limited, as long as the bounding box of each person can be detected. The bounding box refers to a rectangular frame that can enclose the image of a human body.

[0094] S332. The outer frame of the person whose face frame overlaps with the person under guardianship with the largest area is taken as the outer frame of the person under guardianship; for any guardian, the outer frame of the person whose face frame overlaps with the person under guardianship with the largest area is taken as the outer frame of the person under guardianship.

[0095] It is understandable that for the same person, their face frame is located within the body frame. Therefore, by detecting the overlap area between each person's body frame and the face frame of the person under guardianship, as well as the overlap area between each person's body frame and the face frame of the guardian, the body frame of the person under guardianship and the body frame of the guardian can be determined.

[0096] S34. Determine the physical location of the guardian and the ward in the monitoring area based on the image position of the external frame of the guardian and the ward in the image of the monitoring area.

[0097] The image position of the human body bounding box in the image of the monitored area can be the image position of the reference point in the human body bounding box in the image of the monitored area. The reference point in the human body bounding box can be the lower left corner of the human body bounding box.

[0098] In some embodiments, step S34 specifically includes: determining the physical location of the guardian based on a preset location mapping relationship and the image location of the guardian; and determining the physical location of the ward based on the location mapping relationship and the image location of the ward.

[0099] The location mapping relationship is the mapping relationship between the image location of the sample point in the image of the monitoring area and the physical location of the sample point in the monitoring area.

[0100] S40. Determine the physical distance between the ward and each guardian based on the physical location of the ward in the monitoring area and the physical location of each guardian in the monitoring area.

[0101] S41. Determine whether the minimum value among all physical distances is greater than a preset threshold. If so, issue a warning signal.

[0102] The cloud server can send warning signals to mobile terminals. In one example, the warning signal can be a signal that includes warning information and the location information of the person being monitored. After receiving the warning signal, the mobile terminal can output the corresponding warning information and location information. For example, the warning information and location information are displayed in text format.

[0103] In some embodiments, after step S41, the following steps are further included:

[0104] S50. The cloud server sends a command input request to the mobile terminal, causing the mobile terminal to output command request information. This command request information is used to request the user to input navigation commands or abandon commands. For example, the command request information is output in text and / or voice form, such as "Do you need navigation?". When the user inputs a navigation command or abandon command to the mobile terminal, the mobile terminal sends the received navigation command or abandon command to the cloud server.

[0105] S60. When the cloud server receives a navigation instruction from the mobile terminal, it sends navigation information to the mobile terminal. The navigation information includes route information between the ward and the guardian, enabling the user to quickly find the ward based on the navigation information. When the cloud server receives an abandonment instruction from the mobile terminal, it does not need to send navigation information.

[0106] Figure 3 This is a schematic diagram of an anti-wandering method provided in some other embodiments of this disclosure, such as... Figure 3 As shown, methods to prevent people from getting lost include:

[0107] S10. Obtain a reference facial image of the ward and a reference facial image of at least one guardian associated with the ward.

[0108] Optionally, step S10 may specifically include:

[0109] S11. Obtain human images of multiple individuals at the entrance of the monitored area. These human images can be acquired by the image acquisition device at the entrance and then uploaded to the cloud server.

[0110] S12. From the human body images of multiple people, obtain a reference face image of the ward and a reference face image of at least one guardian associated with the ward.

[0111] Figure 4 This is a flowchart illustrating an optional implementation of step S12 provided in some embodiments of this disclosure, such as... Figure 4 As shown, step S12 may specifically include steps S121 to S124:

[0112] S121. Based on the human body images of multiple people, determine the feature information of each person among the multiple people. The feature information includes posture information and / or clothing information.

[0113] S122. Based on the characteristic information of each of the multiple characters, determine whether there is a related group of characters among the multiple characters.

[0114] For example, when at least two people who are close to each other (e.g., less than 1 meter apart) are dressed similarly (e.g., in matching outfits), they are identified as a group of related people. Similarly, when at least two people who are close to each other are in a specific pose (e.g., holding hands or carrying a child), they are identified as a group of related people.

[0115] S123. When there is a group of related persons among multiple persons, determine whether there is a ward and a guardian in the group of related persons.

[0116] Optionally, the individuals in the associated group can be clustered to determine the category to which each individual belongs (e.g., elderly, youth, child), and based on the category to which each individual belongs, it can be determined whether both a ward and a guardian exist in the associated group. For example, if it is determined that there is one child and one youth in the associated group, then the child is identified as the ward and the youth as the guardian; if it is determined that there is one child and two youths in the associated group, then the child is identified as the ward and both youths are identified as guardians.

[0117] S124. When there are both a ward and a guardian in the associated person group, perform face detection on the ward and the guardian to obtain reference face images of the ward and the guardian.

[0118] After step S10, the following is also included:

[0119] S20. Acquire images of the monitored area.

[0120] S30. Based on the images of the monitored area, the reference facial image of the ward, and the associated reference facial image of each guardian, determine the physical location of the ward in the monitored area and the physical location of each guardian in the monitored area.

[0121] Specifically, step S30 may include S31 to S34 mentioned above, which will not be repeated here.

[0122] S40. Determine the physical distance between the ward and each guardian based on the physical location of the ward in the monitoring area and the physical location of each guardian in the monitoring area.

[0123] S41. Determine whether the minimum value among all physical distances is greater than a preset threshold. If so, issue a warning signal.

[0124] The warning signal can be sent from the cloud server to the guardian's mobile terminal, or it can be issued in other forms, such as by broadcasting.

[0125] Figure 5Here is a flowchart of an anti-wandering method provided in some other embodiments of this disclosure, such as... Figure 5 As shown, methods to prevent people from getting lost include:

[0126] S01. Receive and store the registration information uploaded by the mobile terminal, wherein the registration information includes: reference facial images of multiple individuals. These multiple individuals may include guardians and wards. The reference facial image of each individual in the registration information may be a recently taken facial image of that individual.

[0127] S10. Obtain a reference facial image of the ward and a reference facial image of at least one guardian associated with the ward. Optionally, step S10 may specifically include:

[0128] S10b, In response to the second selection instruction, at least the reference face image of the corresponding ward is selected from the pre-stored registration information.

[0129] Users can select at least one person to be monitored on their mobile device. The mobile device then generates a second selection instruction based on the user's selection and uploads it to the cloud server. The cloud server then selects a reference facial image of the corresponding person from its storage module based on the second selection instruction.

[0130] S10c. Obtain human images of multiple individuals at the entrance of the monitored area. These human images can be acquired by the image acquisition device at the entrance and then uploaded to the cloud server.

[0131] S10d: Based on the reference facial image of the ward, obtain the reference facial image of the guardian associated with the ward from the human body images of multiple people at the entrance of the monitored area.

[0132] Optionally, step S10d may include:

[0133] S101d. Based on the reference facial image of the ward and the human body images of multiple individuals, determine the characteristic information of the ward and the characteristic information of each of the multiple individuals, including posture information and / or clothing information.

[0134] For example, after obtaining the reference face image of the ward according to the second selection instruction, each face image at the entrance of the monitoring area is compared with the reference face image of the ward to determine which face image at the entrance of the monitoring area belongs to the ward, and then the human body image of the ward is determined (for example, the human body image with the largest overlap area with the face image of the ward is the human body image of the ward).

[0135] S102d. Based on the characteristic information of the ward and the characteristic information of each of the multiple individuals, obtain the associated group of individuals at the entrance of the monitoring area, wherein the associated group of individuals includes the ward and the guardian.

[0136] For example, when a person is close to the person under their guardianship (e.g., less than 1 meter apart) and wears similar clothing (e.g., matching outfits), that person and the person under their guardianship are identified as a group of related persons. Similarly, when a person is close to the person under their guardianship and is in a specific posture (e.g., holding hands with the person under their guardianship), that person and the person under their guardianship are identified as a group of related persons.

[0137] S103d: Obtain the facial images of all guardians in the associated person group, and use them as reference facial images for each guardian.

[0138] S20. Acquire images of the monitored area.

[0139] S30. Based on the images of the monitored area, the reference facial image of the ward, and the associated reference facial image of the guardian, determine the physical location of the ward in the monitored area and the physical location of the guardian in the monitored area.

[0140] Specifically, step S30 may include S31 to S34 mentioned above, which will not be repeated here.

[0141] S40. Determine the physical distance between the ward and each guardian based on the physical location of the ward in the monitoring area and the physical location of each guardian in the monitoring area.

[0142] S41. Determine whether the minimum value among all physical distances is greater than a preset threshold. If so, issue a warning signal.

[0143] The warning signal can be sent from the cloud server to the guardian's mobile terminal.

[0144] In some embodiments, after step S41, the following steps are further included:

[0145] S50: The cloud server sends a command input request to the mobile terminal, requesting the mobile terminal to send navigation commands or abandon commands. When the mobile terminal receives the command input request from the cloud server, it outputs a command request signal to request the user to input navigation commands or abandon commands.

[0146] S60. When the cloud server receives a navigation instruction from the mobile terminal, it sends navigation information to the mobile terminal. The navigation information includes route information between the ward and the guardian, enabling the user to quickly find the ward based on the navigation information. When the cloud server receives an abandonment instruction from the mobile terminal, it does not need to send navigation information.

[0147] This disclosure also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the anti-wandering method described in the above embodiments.

[0148] This disclosure also provides a cloud server, which includes a memory and a processor. The memory stores a computer program, wherein when the computer program is executed by the processor, it implements the anti-wandering method in the above embodiments.

[0149] The aforementioned memory and computer-readable storage medium include, but are not limited to, the following readable media: such as random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable PROM (EEPROM), flash memory, magnetic or optical data storage, registers, magnetic disks or magnetic tapes, optical storage media such as optical discs (CDs) or DVDs (Digital Universal Discs), and other non-transitory media. Examples of processors include, but are not limited to, general-purpose processors, central processing units (CPUs), microprocessors, digital signal processors (DSPs), controllers, microcontrollers, state machines, etc.

[0150] This disclosure also provides a mobile terminal, which can be a mobile phone, tablet computer, or other mobile terminal. The mobile terminal includes a memory and a processor, and the memory stores a computer program. Figure 6 This diagram illustrates the steps involved when a computer program on a mobile terminal is executed by a processor. Figure 6 As shown, when a computer program is executed by a processor, it performs the following steps:

[0151] S100. In response to the warning activation command, a start signal is sent to the cloud server, so that the cloud server responds to the start signal to implement the anti-wandering method in the above embodiment. The warning activation command is an instruction input by the user (who is the guardian about to enter the monitored area) to the mobile terminal.

[0152] S200 responds to the warning signal and outputs the corresponding warning information.

[0153] When the cloud server issues an early warning signal, the mobile terminal responds to the signal and outputs corresponding warning information to remind the user (i.e., the guardian) that the distance between them and the person being guarded is currently too far.

[0154] In some embodiments, when a computer program stored in a mobile terminal is executed by a processor, the following steps are also performed:

[0155] S300 responds to the instruction input request sent by the cloud server and outputs instruction request information to request the user to input navigation instructions or abandon instructions.

[0156] For example, the instruction request information is output in text and / or voice form, such as "Do you need navigation?".

[0157] S400: When a navigation instruction is received from the user, the navigation instruction is sent to the cloud server so that the cloud server can generate navigation information in response to the navigation instruction.

[0158] The S500 receives and displays navigation information, making it easier for users to quickly locate the person under their care.

[0159] In some embodiments, when a computer program stored in a mobile terminal is executed by a processor, the following steps are also performed:

[0160] S001. Obtain registration information and upload it to the cloud server for storage. The registration information includes: identity information for multiple individuals. Each individual's identity information includes: a reference facial image, and may also include ID number, phone number, name, etc.

[0161] For example, a user (who can be the owner of the mobile device and also a guardian) first registers as an administrator on the mobile device. During registration, the user can add their own identity information, such as name, ID number, phone number, and a reference facial image. The user can also bind the identity information of the person under their guardianship to the mobile device, such as name, ID number, and a reference facial image. The mobile device then uploads this registration information (i.e., the identity information of the guardian and the person under their guardianship) to the storage module of the cloud server for storage.

[0162] It should be noted that the registration information can include reference facial images of multiple guardians. For example, after registering as an administrator on a mobile device, a user can add the identity information of not only the ward but also other guardians. Furthermore, the administrator can manage the added identity information, such as deleting it.

[0163] This disclosure also provides an anti-lost system. Figure 7 This is a schematic diagram of an anti-lost system provided in some embodiments of this disclosure, such as... Figure 7As shown, the anti-lost system includes the aforementioned cloud server 1 and the aforementioned mobile terminal 2. The cloud server 1 communicates with the mobile terminal. Additionally, the cloud server 1 can establish a communication connection with the image acquisition device 3 in the monitoring area, thereby obtaining images of the monitoring area captured by the image acquisition device 3, as well as images of the entrance to the monitoring area.

[0164] Using the anti-lost system in this embodiment, when the physical distance between the ward and the guardian is far, the cloud server can send a warning signal to the mobile terminal to remind the guardian, thereby reducing the possibility of the ward getting lost, and the ward does not need to wear a device.

[0165] It is understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of this disclosure, and this disclosure is not limited thereto. For those skilled in the art, various modifications and improvements can be made without departing from the spirit and substance of this disclosure, and these modifications and improvements are also considered to be within the scope of protection of this disclosure.

Claims

1. A method for preventing people from getting lost, comprising: Obtain a reference facial image of the ward, and a reference facial image of at least one guardian associated with the ward; Acquire images of the monitored area; Based on the images of the monitored area, the reference facial images of the ward, and the associated reference facial images of each of the guardians, the physical locations of the ward and each of the guardians in the monitored area are determined. Based on the physical locations of the ward and each of the guardians in the monitored area, the physical distance between the ward and each of the guardians is determined, and it is determined whether the minimum value among all physical distances is greater than a preset threshold; when the minimum value among all physical distances is greater than the preset threshold, an early warning signal is issued. Specifically, determining the physical location of the ward and each guardian within the monitored area, based on images of the monitored area, a reference facial image of the ward, and a associated reference facial image of each guardian, includes: Face detection is performed on the images of the monitored area to obtain individual face images in the monitored area; Based on the facial images of each person in the monitoring area, the reference facial image of the person under guardianship, and the reference facial image of each guardian, it is determined whether the person under guardianship and the guardian exist in the monitoring area; When the ward and the guardian are present in the monitoring area, obtain the external frame of the ward and each of the guardians; Based on the image position of the external frame of each guardian and the ward in the image of the monitored area, determine the physical position of each guardian and the ward in the monitored area; Specifically, determining the physical location of each guardian and ward in the monitoring area based on the image position of their external frames in the image of the monitoring area includes: determining the physical location of the guardian based on a preset position mapping relationship and the image position of the guardian's external frame; and determining the physical location of the ward based on the position mapping relationship and the image position of the ward's external frame. The preset threshold is determined by the cloud server based on the image of the monitored area to determine the population density, and is set according to the population density. The preset threshold is negatively correlated with the population density in the monitored area.

2. The method for preventing people from getting lost according to claim 1, wherein, Obtaining the external frame of the ward and each of the guardians, including: Human detection is performed on the images of the monitored area to obtain the bounding boxes of each person in the monitored area; The outer frame of the person whose face frame overlaps with the person under guardianship is taken as the outer frame of the person under guardianship; for any guardian, the outer frame of the person whose face frame overlaps with the person under guardianship is taken as the outer frame of the person under guardianship.

3. The method for preventing lost children according to any one of claims 1 to 2, wherein, Obtaining a reference facial image of the ward and a reference facial image of at least one guardian associated with the ward, specifically including: Acquire human images of multiple individuals at the entrance of the monitored area; From the human body images of the multiple individuals, obtain a reference facial image of the ward and a reference facial image of at least one guardian associated with the ward.

4. The method for preventing people from getting lost according to claim 3, wherein, From the human body images of the multiple individuals, a reference facial image of the ward and a reference facial image of at least one guardian associated with the ward are obtained, specifically including: Based on the human images of the plurality of individuals, the feature information of each individual among the plurality of individuals is determined, the feature information including posture information and / or clothing information; Based on the characteristic information of each of the multiple individuals, determine whether there is a group of related individuals among the multiple individuals; When there is a group of related individuals among the multiple individuals, determine whether the ward and the guardian are in the group of related individuals. When the ward and the guardian are present in the associated person group, face detection is performed on the ward and the guardian to obtain reference face images of the ward and the guardian.

5. The method for preventing lost children according to any one of claims 1 to 2, wherein, The process of acquiring a reference facial image of the ward and a reference facial image of at least one guardian associated with the ward also includes: receiving and storing registration information uploaded by a mobile terminal, wherein the registration information includes: reference facial images of multiple individuals; Obtaining a reference facial image of the ward and a reference facial image of at least one guardian associated with the ward specifically includes: in response to a first selection instruction, selecting the corresponding reference facial images of the ward and the guardian from pre-stored registration information.

6. The method for preventing people from getting lost according to claim 5, wherein, The warning signal is sent to the mobile terminal.

7. The method for preventing lost children according to claim 5, wherein, After issuing the warning signal, the method for preventing people from getting lost also includes: Send an instruction input request to the mobile terminal so that the mobile terminal outputs instruction request information, the instruction request information being used to request the user to input navigation instructions or abandon instructions; When the navigation instruction is received, navigation information is sent to the mobile terminal; the navigation information includes route information between the ward and the guardian.

8. The method for preventing lost children according to any one of claims 1 to 2, wherein, Obtaining a reference facial image of the ward and a reference facial image of at least one guardian associated with the ward, specifically including: In response to the second selection instruction, at least the reference face image of the corresponding ward is selected from the pre-stored registration information; Acquire human images of multiple individuals at the entrance of the monitored area; Based on the reference facial image of the ward, the reference facial image of at least one guardian associated with the ward is obtained from the human images of multiple people at the entrance of the monitored area.

9. The method for preventing people from getting lost according to claim 8, wherein, Based on the reference facial image of the ward, obtain the reference facial image of at least one guardian associated with the ward from the human images of multiple individuals at the entrance of the monitored area, specifically including: Based on the reference facial image of the ward and the human body images of the multiple individuals, determine the characteristic information of the ward and the characteristic information of each of the multiple individuals, wherein the characteristic information includes posture information and / or clothing information; Based on the characteristic information of the ward and the characteristic information of each of the multiple individuals, obtain the associated group of individuals at the entrance of the monitoring area, wherein the associated group of individuals includes the ward and the guardian; Obtain the facial images of all guardians in the associated group, and use them as reference facial images for each guardian.

10. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the anti-wandering method according to any one of claims 1 to 9.

11. A cloud server comprising a memory and a processor, wherein the memory stores a computer program, wherein, When the computer program is executed by the processor, it implements the anti-wandering method according to any one of claims 1 to 9.

12. A mobile terminal comprising a memory and a processor, wherein the memory stores a computer program, wherein... When the computer program is executed by the processor, it performs the following steps: In response to the warning activation command, a start signal is sent to the cloud server, so that the cloud server responds to the start signal to implement the anti-wandering method according to any one of claims 1 to 9; In response to the warning signal, corresponding warning information is output.

13. The mobile terminal according to claim 12, wherein, When the computer program is executed by the processor, it also performs the following steps: The registration information is obtained and uploaded to the cloud server; wherein, the registration information includes: reference facial images of multiple individuals.

14. The mobile terminal according to claim 12, wherein, When the computer program is executed by the processor, it also performs the following steps: In response to the instruction input request sent by the cloud server, an instruction request message is output to request the user to input navigation instructions or abandon instructions; When the navigation instruction is received, the navigation instruction is sent to the cloud server so that the cloud server generates navigation information in response to the navigation instruction; Receive and display the navigation information.

15. An anti-wandering system, comprising: The cloud server of claim 11 and the mobile terminal of any one of claims 12 to 14.

Images