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

1 . An anti-lost method, comprising:

acquiring a reference face image of a person under guardianship and a reference face image of at least one guardian associated with the person under guardianship;

acquiring an image of a monitored area;

determining, based on the image of the monitored area, the reference face image of the person under guardianship, and the reference face image of the at least one guardian, physical locations of the person under guardianship and the at least one guardian in the monitored area;

determining, according to the physical locations of the person under guardianship and the at least one guardian in the monitored area, a physical distance between the person under guardianship and each of the at least one guardian, and determining whether a minimum physical distance is greater than a preset threshold; and

emitting a warning signal in a case where the minimum physical distance is larger than the preset threshold,

wherein the acquiring the reference face image of the person under guardianship and the reference face image of the at least one guardian associated with the person under guardianship comprises:

acquiring body images of a plurality of persons at an entrance of the monitored area; and

acquiring the reference face image of the person under guardianship and the reference face image of the at least one guardian associated with the person under guardianship from the body images of the plurality of persons.

2 . The anti-lost method according to claim 1 , wherein the determining, based on the image of the monitored area, the reference face image of the person under guardianship, and the reference face image of the at least one guardian, physical locations of the person under guardianship and the at least one guardian in the monitored area comprises:

performing face detection on the image of the monitored area to obtain face image of each person in the monitored area;

determining, according to the face image of each person in the monitored area, the reference face image of the person under guardianship and the reference face image of the at least one guardian, whether the person under guardianship and the guardian are present in the monitored area;

acquiring, in a case where the person under guardianship and the guardian are present in the monitored area, body external frames of the person under guardianship and the guardian; and

determining, according to image positions of the body external frames of the person under guardianship and the guardian in the image of the monitored area, physical locations of the guardian and the person under guardianship in the monitored area.

3 . The anti-lost method according to claim 2 , wherein the acquiring the body external frames of the person under guardianship and the at least one guardian comprises:

performing body detection on the image of the monitored area to obtain a body external frame of each person in the monitored area;

taking a body external frame having a largest overlapping area with a face frame of the person under guardianship as the body external frame of the person under guardianship; and for the at least one guardian, taking a body external frame having a largest overlapping area with a face frame of the guardian as the body external frame of the guardian.

4 . The anti-lost method according to claim 1 , wherein the acquiring the reference face image of the person under guardianship and the reference face image of the at least one guardian associated with the person under guardianship from the body images of the plurality of persons comprises:

determining, according to the body images of the plurality of persons, feature information of each of the plurality of persons, wherein the feature information comprises posture information and/or clothing information;

determining, according to the feature information of each of the plurality of persons, whether a group of associated persons are present in the plurality of persons;

determining, in a case where the group of associated persons are present in the plurality of persons, whether the person under guardianship and the at least one guardian are present in the group of associated persons; and

performing, in a case where the person under guardianship and the at least one guardian are present in the group of associated persons, face detection on the person under guardianship and the at least one guardian to obtain the reference face image of the person under guardianship and the reference face image of the at least one guardian.

5 . The anti-lost method according to claim 1 , wherein before acquiring the reference face image of the person under guardianship and the reference face image of the at least one guardian associated with the person under guardianship, the method further comprises: receiving and storing registration information uploaded by a mobile terminal, wherein the registration information comprises: reference face images of a plurality of persons; and

the acquiring the reference face image of the person under guardianship and the reference face image of at least one guardian associated with the person under guardianship comprises: selecting, in response to a first selection instruction, reference face images of a corresponding person under guardianship and at least one guardian associated with the person under guardianship from the prestored registration information.

6 . The anti-lost method according to claim 5 , wherein the warning signal is sent to the mobile terminal.

7 . The anti-lost method according to claim 5 , wherein after emitting the warning signal, the anti-lost method further comprises:

sending an instruction input request to the mobile terminal to cause the mobile terminal to output instruction request information, wherein the instruction request information is configured to request a user to input a navigation instruction or an abandon instruction;

sending, in a case where the navigation instruction is received, navigation information to the mobile terminal; wherein the navigation information comprises route information between the person under guardianship and the guardian.

8 . The anti-lost method according to claim 1 , wherein before acquiring the reference face image of the person under guardianship and the reference face image of the at least one guardian associated with the person under guardianship, the method further comprises: receiving and storing registration information uploaded by a mobile terminal, wherein the registration information comprises: reference face images of a plurality of persons;

the acquiring the reference face image of the person under guardianship and the reference face image of the at least one guardian associated with the person under guardianship comprises:

selecting, in response to a second selection instruction, at least reference face image of a corresponding person under guardianship from the prestored registration information;

acquiring body images of a plurality of persons at an entrance of the monitored area; and

acquiring, according to the reference face image of the person under guardianship, the reference face image of the at least one guardian associated with the person under guardianship from the body images of the plurality of persons acquired at the entrance of the monitored area.

9 . The anti-lost method according to claim 8 , wherein the acquiring, according to the reference face image of the person under guardianship, the reference face image of the at least one guardian associated with the person under guardianship from the body images of the plurality of persons acquired at the entrance of the monitored area comprises:

determining, according to the reference face image of the person under guardianship and the body images of the plurality of persons, feature information of the person under guardianship and feature information of each of the plurality of persons, wherein the feature information comprises posture information and/or clothing information;

acquiring, according to the feature information of the person under guardianship and the feature information of each of the plurality of persons, a group of associated persons at the entrance of the monitored area, wherein the group of associated persons comprises the person under guardianship and the at least one guardian; and

acquiring a face image of the at least one guardian in the group of associated persons as the reference face image of the at least one guardian.

10 . The anti-lost method according to claim 1 , wherein the preset threshold is related to a crowd density in the monitored area.

11 . A non-transitory computer-readable storage medium having a computer program stored thereon which, when executed by a processor, causes the anti-lost method according to claim 1 to be implemented.

12 . A cloud server, comprising a memory and a processor, wherein the memory has a computer program stored thereon which, when executed by the processor, causes the anti-lost method according to claim 1 to be implemented.

13 . A mobile terminal, comprising a memory and a processor, wherein the memory has a computer program stored thereon which, when executed by the processor, causes the following steps to be implemented:

sending, in response to a warning initiation instruction, a starting signal to a cloud server so that the cloud server, in response to the starting signal, implements the anti-lost method according to claim 1 ; and

outputting corresponding warning information in response to the warning signal.

14 . The mobile terminal according to claim 13 , wherein when executed by the processor, the computer program further causes the following step to be implemented:

acquiring registration information and uploading the registration information to the cloud server; wherein the registration information comprises: reference face images of a plurality of persons.

15 . The mobile terminal according to claim 13 , wherein when executed by the processor, the computer program further causes the following steps to be implemented:

outputting, in response to an instruction input request sent from the cloud server, instruction request information to request a user to input a navigation instruction or an abandon instruction;

sending, when the navigation instruction is received, the navigation instruction to the cloud server so that the cloud server generates navigation information in response to the navigation instruction; and

receiving and displaying the navigation information.

16 . An anti-lost system, comprising: a cloud server and a mobile terminal,

wherein the mobile terminal comprises a memory and a processor, wherein the memory has a computer program stored thereon which, when executed by the processor, causes the following steps to be implemented:

sending, in response to a warning initiation instruction, a starting signal to a cloud server so that the cloud server, in response to the starting signal, implements the anti-lost method according to claim 1 ; and

outputting corresponding warning information in response to the warning signal.

17 . An anti-lost method, comprising:

acquiring a reference face image of a person under guardianship and a reference face image of at least one guardian associated with the person under guardianship;

acquiring an image of a monitored area;

determining, based on the image of the monitored area, the reference face image of the person under guardianship, and the reference face image of the at least one guardian, physical locations of the person under guardianship and the at least one guardian in the monitored area;

determining, according to the physical locations of the person under guardianship and the at least one guardian in the monitored area, a physical distance between the person under guardianship and each of the at least one guardian, and determining whether a minimum physical distance is greater than a preset threshold; and

emitting a warning signal in a case where the minimum physical distance is larger than the preset threshold,

wherein the determining, based on the image of the monitored area, the reference face image of the person under guardianship, and the reference face image of the at least one guardian, physical locations of the person under guardianship and the at least one guardian in the monitored area comprises:

performing face detection on the image of the monitored area to obtain face image of each person in the monitored area;

determining, according to the face image of each person in the monitored area, the reference face image of the person under guardianship and the reference face image of the at least one guardian, whether the person under guardianship and the guardian are present in the monitored area;

acquiring, in a case where the person under guardianship and the guardian are present in the monitored area, body external frames of the person under guardianship and the guardian; and

determining, according to image positions of the body external frames of the person under guardianship and the guardian in the image of the monitored area, physical locations of the guardian and the person under guardianship in the monitored area.

18 . An anti-lost method, comprising:

acquiring a reference face image of a person under guardianship and a reference face image of at least one guardian associated with the person under guardianship;

acquiring an image of a monitored area;

determining, based on the image of the monitored area, the reference face image of the person under guardianship, and the reference face image of the at least one guardian, physical locations of the person under guardianship and the at least one guardian in the monitored area;

determining, according to the physical locations of the person under guardianship and the at least one guardian in the monitored area, a physical distance between the person under guardianship and each of the at least one guardian, and determining whether a minimum physical distance is greater than a preset threshold; and

emitting a warning signal in a case where the minimum physical distance is larger than the preset threshold,

wherein before acquiring the reference face image of the person under guardianship and the reference face image of the at least one guardian associated with the person under guardianship, the method further comprises: receiving and storing registration information uploaded by a mobile terminal, wherein the registration information comprises: reference face images of a plurality of persons; and

the acquiring the reference face image of the person under guardianship and the reference face image of at least one guardian associated with the person under guardianship comprises: selecting, in response to a first selection instruction, reference face images of a corresponding person under guardianship and at least one guardian associated with the person under guardianship from the prestored registration information.