Pet escape detection method and system, storage medium and intelligent lock

Abstract

The embodiment of the invention discloses a pet escape detection method and system, a storage medium and an intelligent lock. The method comprises the steps that when it is detected that the intelligent lock is awakened, a first camera is started to shoot in the indoor downward direction, and a second camera is started to shoot in the outdoor downward direction; if it is detected that a living body exists on the indoor side corresponding to the intelligent lock before the intelligent lock is locked, a first video shot by the first camera is obtained after the intelligent lock is locked; if it is detected that a living body exists on the outdoor side corresponding to the intelligent lock after the intelligent lock is unlocked, a second video shot by a second camera is obtained when the preset delay duration is reached after the intelligent lock is locked; uploading the first video and the second video to a cloud platform, and obtaining a cloud platform identification result issued by the cloud platform after video image identification; and determining whether the pet escapes or not according to the identification result of the cloud platform. Whether the pet escapes from the doorway or not can be accurately detected, and the supervision strength of the door lock on the pet is improved.

Description

Technical Field

[0001] The present application relates to the field of pet monitoring technology, and in particular to a pet escape detection method, system, storage medium and smart lock. Background Art

[0002] As people pursue a better quality of life, more and more families keep pets. However, due to the high flexibility of pets, especially cats, when users open the door of their residence, it is easy for pets to quickly run out of the door and escape from the residence. Especially when the light is insufficient or the user is not paying attention to his feet, the pet may escape from the residence without the user noticing. However, existing door locks can only be used for unlocking verification, but cannot detect whether the pet has escaped, that is, the existing door locks have very low supervision over pets. Summary of the invention

[0003] The embodiments of the present application provide a pet escape detection method, system, storage medium and smart lock, which can accurately detect whether a pet escapes from a door, thereby improving the supervision of the door lock on the pet. The technical solution is as follows:

[0004] The first embodiment of the present application provides a pet escape detection method, which is applied to a smart lock, wherein the smart lock includes a first camera corresponding to an indoor side and a second camera corresponding to an outdoor side;

[0005] The method includes:

[0006] When it is detected that the smart lock is awakened, the first camera is started to shoot in a downward direction indoors, and the second camera is started to shoot in a downward direction outdoors;

[0007] If a living body is detected on the indoor side corresponding to the smart lock before the smart lock is locked, a first video recorded by the first camera is obtained after the smart lock is locked; if a living body is detected on the outdoor side corresponding to the smart lock after the smart lock is unlocked, a second video recorded by the second camera is obtained when a preset delay time is reached after the smart lock is locked;

[0008] Uploading the first recorded video and the second recorded video to the cloud platform, and obtaining a cloud platform recognition result issued by the cloud platform after performing video image recognition;

[0009] According to the recognition result of the cloud platform, it is determined whether the pet escapes.

[0010] The second embodiment of the present application provides a pet escape detection system, including: a smart lock and a cloud platform; the smart lock includes a first camera corresponding to an indoor side and a second camera corresponding to an outdoor side;

[0011] When detecting that the smart lock is awakened, the smart lock starts the first camera to shoot in a downward direction indoors, and starts the second camera to shoot in a downward direction outdoors;

[0012] If a living body is detected on the indoor side corresponding to the smart lock before the smart lock is locked, the first video recorded by the first camera is obtained after the smart lock is locked; if a living body is detected on the outdoor side corresponding to the smart lock after the smart lock is unlocked, the smart lock obtains a second video recorded by the second camera when a preset delay time is reached after locking;

[0013] The smart lock uploads the first recorded video and the second recorded video to the cloud platform;

[0014] The cloud platform performs video image recognition on the first recorded video and the second recorded video, obtains a recognition result, and sends it to the smart lock;

[0015] The smart lock determines whether the pet has escaped based on the recognition result of the cloud platform.

[0016] A third embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the pet escape detection method described above are implemented.

[0017] The fourth embodiment of the present application provides a smart lock, which is used to execute the steps of the pet escape detection method as described above.

[0018] Compared with the related art, when the present application detects that the smart lock is awakened, the first camera is started to shoot in the downward direction of the indoor, and the second camera is started to shoot in the downward direction of the outdoor. If a living body is detected on the indoor side corresponding to the smart lock before the smart lock is locked, the first video recorded by the first camera is obtained after the smart lock is locked; if a living body is detected on the outdoor side corresponding to the smart lock after the smart lock is unlocked, the second video recorded by the second camera is obtained when the preset delay time is reached after the lock is locked, and then the first video recorded and the second video recorded are uploaded to the cloud platform, and the cloud platform recognition result issued by the cloud platform after the video image recognition is obtained, and then the cloud platform recognition result is determined to determine whether the pet escapes. Since the first video recorded and the second video recorded are the videos shot indoors and outdoors respectively corresponding to the process of the user unlocking and opening the door and closing and locking the door, that is, when the pet escapes, the first video recorded and the second video recorded will record the image of the pet escaping. Therefore, the cloud platform recognition result obtained by the cloud platform through the video image recognition of the first video recorded and the second video recorded can accurately indicate whether the pet escapes from the door, which is conducive to detecting the situation that the pet escapes from the door without the user's attention, and improves the supervision of the door lock on the pet.

[0019] In order to provide a clearer understanding of the present application, the specific implementation of the present application will be described below in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 This is a flow chart of a pet escape detection method according to an embodiment of the present application.

[0022] Figure 2 This is a flow chart of steps S5-S7 of a pet escape detection method according to an embodiment of the present application.

[0023] Figure 3 A schematic diagram of a pet escape detection system according to an embodiment of the present application.

[0024] 100. Pet escape detection system; 101. Smart lock; 102. Cloud platform. DETAILED DESCRIPTION

[0025] In order to make the objectives, technical solutions and advantages of the present application more clear, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

[0026] It should be clear that the described embodiments are only 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 the embodiments of the present application.

[0027] When the following description relates to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. In the description of the present application, it should be understood that the terms "first", "second", "third", etc. are only used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence, nor can they be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to the specific circumstances. The singular forms of "a", "said" and "the" used in the present application and the appended claims are also intended to include the majority form, unless the context clearly indicates other meanings. The words "if" / "if" used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0028] In addition, in the description of this application, unless otherwise specified, "plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0029] The technical solution of the present application relates to a smart lock on a door body, wherein a first camera is provided on the side of the smart lock corresponding to the indoors, and a second camera is provided on the side of the smart lock corresponding to the outdoor. It should be noted that the first camera and the second camera of the present application are high-frame-rate motion HD cameras, such as megapixel lenses, that is, the videos captured by the first camera and the second camera can clearly display multiple frames of images of a pet in motion. Specifically, the motion HD camera has at least the following differences from an ordinary camera:

[0030] The difference in clarity: The lens of the sports HD camera has fewer impurities and produces less interfering light, which is beneficial to improving the clarity of the captured video images. In addition, the lens of the sports HD camera uses aspherical lenses to reduce aberrations. The image quality from the center to the peripheral part of the sports HD camera image will present a high-resolution, high-contrast picture due to the optical design, which is about 2.5 times higher than that of ordinary lenses. Even when the image is cut or enlarged, high image quality can still be guaranteed.

[0031] The difference in spectral transmission capability: The sports HD camera supports the transmission of wide-frequency light, which will greatly increase the amount of light received by the camera target surface, enhance the contrast and brightness of the picture, and show richer details of the picture.

[0032] Difference in spectral correction capability: Only wide spectrum transmission capability is far from enough for high-definition imaging. Therefore, the sports HD camera also has powerful spectral correction capability, which can accurately image various wavelengths of light on the camera target surface.

[0033] Difference in frame rate: The shooting frame rate of a sports HD camera is greater than that of an ordinary camera. Specifically, the shooting frame rate of a sports HD camera can be 2-3 times that of an ordinary camera.

[0034] The smart lock includes an indoor liveness detection sensor facing the indoor side and an outdoor liveness detection sensor facing the outdoor side; the indoor liveness detection sensor detects whether there is a liveness on the indoor side corresponding to the smart lock; the outdoor liveness detection sensor detects whether there is a liveness on the outdoor side corresponding to the smart lock. Optionally, the first camera and the second camera can be controlled to start shooting according to the result of whether the first sensor detects a liveness, and the first camera and the second camera can be controlled to end shooting according to the result of whether the second sensor detects a liveness.

[0035] The technical solution of the present application also involves image recognition processing of a first video recorded by a first camera and a second video recorded by a second camera. When the smart lock is limited by the size of the data processing module, the technical solution of the present application can also obtain the first video recorded and the second video recorded uploaded by the smart lock through a cloud platform or a cloud server, and then the cloud platform or the cloud server performs image recognition on the first video recorded and the second video recorded to obtain a detection result, and then the cloud platform or the cloud server sends the detection result to the smart lock and / or a preset electronic device. The preset electronic device can be a computer, a smart phone, a tablet computer, or other communication device with network communication and image display functions.

[0036] See also Figure 1 , which is a flow chart of a pet escape detection method according to the first embodiment of the present application, comprising:

[0037] S1: When it is detected that the smart lock is awakened, the first camera is started to shoot in a downward direction indoors, and the second camera is started to shoot in a downward direction outdoors.

[0038] Among them, the smart lock is awakened when the user operates the smart lock to switch from a sleep or dormant state to a working state. For example, the user sends a command to the smart lock to wake up the smart lock, or the user directly operates the smart lock to wake up the smart lock.

[0039] In a feasible embodiment, the first camera and the second camera both have a tilted downward shooting angle, which means that the shooting area of ​​the first camera of the present application covers the door body below the first camera and the ground within a first distance range from the door body; the shooting area of ​​the second camera covers the door body below the second camera and the ground within a second distance range from the door body. When the user opens and closes the door body, since the first camera and the second camera shoot downward from two different directions, the user's visual blind spot can be captured without lowering his head. This visual blind spot is also the area where pets such as cats and dogs that can walk on the ground often move.

[0040] S2: If a living body is detected on the indoor side corresponding to the smart lock before the smart lock is locked, a first video recorded by the first camera is obtained after locking; if a living body is detected on the outdoor side corresponding to the smart lock after the smart lock is unlocked, a second video recorded by the second camera is obtained when a preset delay time is reached after locking.

[0041] Herein, living things refer to living animals, including humans and pets, which are not limited to cats, dogs, etc.

[0042] Since the first camera and the second camera are started for shooting only when the smart lock is unlocked and a living body is detected on the indoor side corresponding to the smart lock, if the smart lock is not unlocked, the first camera and the second camera will not be started for shooting even if a living body is detected on the indoor side corresponding to the smart lock; when the smart lock is unlocked, the first camera and the second camera will not be started for shooting even if no living body is detected on the indoor side corresponding to the smart lock. Therefore, the start-up time of the first camera and the second camera can be effectively controlled, the power consumption of the first camera and the second camera due to shooting can be reduced, and the shooting of too many videos that are not related to the pet's escape can be avoided, thereby reducing the storage space occupied by videos that are not related to the pet's escape.

[0043] If a pet escapes, the pet should escape from the door before the door is closed. Since the smart lock needs to be locked after the door is closed, that is, the first camera is facing indoors at this time, the picture taken by the first camera will no longer show the escaped pet, so the shooting of the first camera can be ended at this time to obtain the first video; and since the second camera is facing outdoors after the door is closed, the second camera may still capture the escaped pet, and even the direction of the pet's escape, so it is necessary to end the shooting of the second camera according to the preset delay time to obtain a second video that is helpful for judging whether the pet has escaped and the direction of the animal's escape. Among them, the preset delay time can be the time set by the manufacturer or the user, and the unit can be minutes, such as 3 minutes, 5 minutes, 8 minutes, 10 minutes, etc.

[0044] S3: Upload the first recorded video and the second recorded video to the cloud platform, and obtain the cloud platform recognition result sent by the cloud platform after performing video image recognition.

[0045] The first recorded video and the second recorded video are both recorded videos, but are respectively recorded by different shooting subjects, that is, they are respectively recorded by a first camera and a second camera.

[0046] Video image recognition refers to the process of performing image recognition on each video frame of a recorded video to identify the pets appearing in the recorded video. Video image recognition can be implemented in combination with a trained pet recognition network. For example, multiple pictures marked with pets can be used as training samples to train the neural network to obtain a pet recognition network. Then, when an animal is recognized in the video image, the corresponding video frame is input into the pet recognition network to determine whether the animal is a pet through the pet recognition network, thereby obtaining a first recognition result and a second recognition result, and then obtaining a cloud platform recognition result based on the first recognition result and the second recognition result.

[0047] The cloud platform can perform video image recognition by including the following steps:

[0048] S31: The cloud platform obtains a first video recognition segment and a first video candidate segment from the first recorded video.

[0049] Among them, the first video recognition segment and the first video candidate segment are video segments with different priorities. Specifically, the priority of the first video recognition segment is higher than that of the first video candidate segment, that is, video image recognition can be performed on the first video recognition segment first, and then on the first video candidate segment.

[0050] Specifically, step S31 may include:

[0051] S311: Divide the first recorded video according to the video start time of the first recorded video and the preset segment duration to obtain a first video identification segment including the video start time; and / or divide the first recorded video according to the video end time of the first recorded video and the segment duration to obtain a first video identification segment including the video end time.

[0052] After unlocking the smart lock and opening the door, and before closing the door and locking the smart lock, are time periods when users are prone to negligence and not knowing that their pets have escaped. Since the first recorded video is shot when the smart lock is unlocked and a living body is detected on the indoor side corresponding to the smart lock, that is, the video start time of the first recorded video is the time when the smart lock is locked and the door is opened. Therefore, the first recorded video is divided according to the video start time and the preset segment duration of the first recorded video, and a first video recognition segment with a higher image recognition priority including the video start time can be obtained; since the first recorded video is shot after the smart lock is locked and a living body is detected on the outdoor side corresponding to the smart lock, that is, the video end time of the first recorded video is the time when the smart lock is locked. Therefore, the first recorded video is divided according to the video end time and the segment duration of the first recorded video, and a first video recognition segment with a higher image recognition priority including the video end time can be obtained.

[0053] S312: Determine video segments in the first recorded video other than the first video identification segment as first video candidate segments.

[0054] In the first recorded video, video segments other than the first video recognition segment are first video candidate segments with lower image recognition priorities.

[0055] The first video candidate segment with a higher image recognition priority and the first video candidate segment with a lower image recognition priority can be accurately identified based on the video start time and the preset segment duration of the first recorded video, and / or based on the video end time and the segment duration of the first recorded video.

[0056] S32: The cloud platform performs video image recognition on the first video recognition segment. If it is recognized that the first video recognition segment includes a pet, the first recognition result is generated according to the recognized pet.

[0057] Among them, if the user has only one pet, the first recognition result can be obtained when it is recognized that the first video recognition segment includes the pet, because the recognition that the first video recognition segment includes the pet indicates that the first recognition result of the first recorded video includes the pet. Therefore, there is no need to perform video image recognition on the first video candidate segment, which can save data processing resources; if the user has at least two pets, the first recognition result can be obtained when it is recognized that the first video recognition segment includes all pets, because the recognition that the first video recognition segment includes all pets indicates that the first recognition result of the first recorded video includes all pets. Therefore, there is no need to perform video image recognition on the first video candidate segment, which can save data processing resources; and if it is recognized that the first video recognition segment does not include all pets, video image recognition can be performed on the first video candidate segment to prevent other pets from escaping during the shooting time corresponding to the first video candidate segment.

[0058] S33: If the cloud platform recognizes that the first video recognition segment does not include a pet, the cloud platform performs video image recognition on the first video candidate segment, and generates the first recognition result based on the recognized pet.

[0059] Among them, if it is identified that the first video recognition segment does not include the pet, it means that the pet may still escape during the shooting time of the first video candidate segment. Therefore, it is necessary to perform image recognition on the first video candidate segment to generate a first recognition result based on the identified pet.

[0060] S34: The cloud platform obtains a second video recognition segment and a second video candidate segment from the second recorded video.

[0061] Among them, the second video identification segment and the second video candidate segment are video segments with different priorities. Specifically, the priority of the second video identification segment is higher than that of the second video candidate segment, that is, video image recognition can be performed on the second video identification segment first, and then on the second video candidate segment.

[0062] Specifically, step S34 may include:

[0063] S341: The cloud platform divides the second recorded video according to the video start time and the preset segment duration of the second recorded video to obtain a second video identification segment including the video start time; and / or, divides the second recorded video according to the locking time of the smart lock and the segment duration to obtain a second video identification segment including the locking time.

[0064] After unlocking the smart lock and opening the door, and before closing the door and locking the smart lock, are time periods when users may be careless and fail to notice that their pets have escaped. Since the second recorded video is shot when the smart lock is unlocked and a living body is detected on the indoor side corresponding to the smart lock, that is, the video start time of the second recorded video is the time when the smart lock is locked and the door is opened, the second recorded video is divided according to the video start time of the second recorded video and the preset segment length, and a second video recognition segment with a higher image recognition priority including the video start time can be obtained; since the second recorded video continues to be shot for an end time after the smart lock is locked and a living body is detected on the outdoor side corresponding to the smart lock, that is, the video end time of the second recorded video is later than the time when the smart lock is locked, the second recorded video is divided according to the video end time of the second recorded video and the segment length, and the obtained second video recognition segment with a higher image recognition priority including the video end time can be a video segment with the time of locking the smart lock as the time starting point, the time of locking the smart lock as the time midpoint, or the time of locking the smart lock as the time end.

[0065] S342: The cloud platform determines the video segments in the second recorded video, except for the second video identification segment, as second video candidate segments.

[0066] In the second recorded video, the video segments other than the second video recognition segment are the second video candidate segments with lower image recognition priority. Therefore, according to the preset segment duration, the first video candidate segments with higher image recognition priority and the first video candidate segments with lower image recognition priority can be accurately obtained from the second recorded video.

[0067] S35: The cloud platform performs video image recognition on the second video recognition segment. If it is recognized that the second video recognition segment includes a pet, the second recognition result is generated according to the recognized pet.

[0068] Among them, if the user has only one pet, the second recognition result can be obtained when it is recognized that the second video recognition segment includes the pet, because the recognition that the second video recognition segment includes the pet indicates that the second recognition result of the second recorded video includes the pet. Therefore, there is no need to perform video image recognition on the second video candidate segment, which can save data processing resources; if the user has at least two pets, the second recognition result can be obtained when it is recognized that the second video recognition segment includes all pets, because the recognition that the second video recognition segment includes all pets indicates that the second recognition result of the second recorded video includes all pets. Therefore, there is no need to perform video image recognition on the second video candidate segment, which can save data processing resources; and if it is recognized that the second video recognition segment does not include all pets, video image recognition can be performed on the second video candidate segment to prevent other pets from escaping during the shooting time corresponding to the second video candidate segment.

[0069] S36: If the cloud platform recognizes that the second video recognition segment does not include a pet, the cloud platform performs video image recognition on the second video candidate segment, and generates the second recognition result based on the recognized pet.

[0070] Among them, if it is identified that the second video recognition segment does not include the pet, it means that the pet may still escape during the shooting time of the second video candidate segment. Therefore, it is necessary to perform image recognition on the second video candidate segment to generate a second recognition result based on the identified pet.

[0071] Specifically, if the first recognition result and the second recognition result include the same pet, it is determined that the cloud platform recognition result is that the pet has escaped.

[0072] Among them, both the first identification result and the second identification result include the pet name or pet characteristics of the identified pet. By comparing the pet name or pet characteristics of the first identification result and the second identification result, it can be determined whether the first identification result and the second identification result include the same pet, thereby obtaining the cloud platform identification result of whether the pet has escaped.

[0073] S4: Determine whether a pet escapes based on the recognition result of the cloud platform.

[0074] Among them, the smart lock can directly determine whether a pet has escaped based on the recognition results of the cloud platform.

[0075] Compared with the related art, when the present application detects that the smart lock is awakened, the first camera is started to shoot in the downward direction of the indoor, and the second camera is started to shoot in the downward direction of the outdoor. If a living body is detected on the indoor side corresponding to the smart lock before the smart lock is locked, the first video recorded by the first camera is obtained after the smart lock is locked; if a living body is detected on the outdoor side corresponding to the smart lock after the smart lock is unlocked, the second video recorded by the second camera is obtained when the preset delay time is reached after the lock is locked, and then the first video recorded and the second video recorded are uploaded to the cloud platform, and the cloud platform recognition result issued by the cloud platform after the video image recognition is obtained, and then the cloud platform recognition result is determined to determine whether the pet escapes. Since the first video recorded and the second video recorded are the videos shot indoors and outdoors respectively corresponding to the process of the user unlocking and opening the door and closing and locking the door, that is, when the pet escapes, the first video recorded and the second video recorded will record the image of the pet escaping. Therefore, the cloud platform recognition result obtained by the cloud platform through the video image recognition of the first video recorded and the second video recorded can accurately indicate whether the pet escapes from the door, which is conducive to detecting the situation that the pet escapes from the door without the user's attention, and improves the supervision of the door lock on the pet.

[0076] See also Figure 2 In a feasible embodiment, the smart lock further includes a third camera corresponding to the outdoor side, and the shooting wide angle of the third camera is greater than that of the second camera; the method further includes:

[0077] S5: When it is detected that the smart lock is awakened, the third camera is started to shoot in the outdoor direction.

[0078] Among them, the third camera is a wide-angle camera, and its shooting angle is 140°~160°; while the shooting angles of the first camera and the second camera are only 100°~120°, so the third camera has a wider shooting range. Moreover, since the third camera is a wide-angle camera, the central shooting angle of the third camera is higher than the central shooting angle of the second camera, which is conducive to shooting more outdoor direction video images through the third camera, so that users can check the activity direction of the pet after escaping through the third video.

[0079] S6: If a living body is detected on the outdoor side corresponding to the smart lock before the smart lock is locked, a third video shot by the third camera is obtained when a preset delay time is reached after the smart lock is locked.

[0080] Among them, the third camera is suitable for capturing the direction of the pet's activities after it escapes. Therefore, the preset delay time for the third camera to end shooting can be the same as the preset delay time for the second camera to end shooting, or it can be greater than the preset delay time for the second camera to end shooting, so that after the second camera ends shooting, the third camera can continue shooting to capture the direction of the pet's activities after it escapes.

[0081] S7: If it is determined according to the recognition result of the cloud platform that the pet has escaped, the third video recording is uploaded to the cloud platform.

[0082] Among them, after the third video recorded by the third camera is uploaded to the cloud platform, the user can view the third video from the cloud platform through a display device, which can be a smart phone, computer or other electronic device with network communication function and video playback and display function.

[0083] In this embodiment, the third video recorded by the third camera can record the direction of the pet's activities after escaping, so that the user can determine the escape direction of the escaped pet based on the third video.

[0084] In a feasible embodiment, the shooting frame rates of the first camera and the second camera are greater than the shooting frame rate of the third camera. For example, the shooting frame rates of the first camera and the second camera are 40-60, and the shooting frame rate of the third camera is 15-20.

[0085] Specifically, since the cloud platform needs to perform video image recognition on the first and second recorded videos, and the higher the shooting frame rates of the first and second cameras, the greater the chance of capturing video images that reflect the pet characteristics of the escaped pet; therefore, the higher the shooting frame rates of the first and second cameras, the more accurate the cloud platform recognition results obtained by the cloud platform. Since the video shot by the third camera is used to indicate the escape direction of the escaped pet, the user mainly views it in the form of video playback, so the shooting frame rate of the third camera is relatively low, and the effect on the video shot by the third camera is also relatively small.

[0086] In this embodiment, by limiting the relationship between the shooting frame rates of the first camera, the second camera and the third camera, it is beneficial to improve the accuracy of the cloud platform recognition results.

[0087] In a feasible embodiment, after the step of determining whether the pet escapes, S4 includes:

[0088] S41: If it is determined that the pet has escaped, the smart lock is driven to broadcast an alarm, and / or a pet escape warning is sent to a preset terminal device through the cloud platform.

[0089] The preset terminal device can be an electronic device with communication function pre-set by the user, including a smart lock, a smart phone, etc. For example, a pet escape warning can be sent to a smart phone through a text message or a program message, so that the user can view the pet escape warning through a text message or a program message. Among them, when the terminal device includes a smart lock, in order to remind the user when the smart lock receives the pet escape warning, the smart lock can be driven to start the playback module through sound to broadcast the alarm, wherein the broadcast alarm can be to play a preset music ringtone or to play a pre-recorded call of a pet that has escaped.

[0090] In this embodiment, a pet escape warning may be sent to notify the user of the alarm information through a preset terminal device.

[0091] In a feasible embodiment, the S41: step of driving the smart lock to broadcast an alarm includes: if the cloud platform recognition result includes a target alarm audio corresponding to the escaped pet individual; driving the smart lock to broadcast the target alarm audio; wherein the target alarm audio is obtained according to the correspondence between the escaped pet individual and the preset pet individual and the alarm audio.

[0092] Specifically, this can be achieved through the following steps:

[0093] S411: According to the preset correspondence between the pet individual and the alarm audio, the target alarm audio corresponding to the escaped pet individual is obtained.

[0094] Among them, the preset correspondence between pet individuals and alarm audio can be a mapping relationship between pet individuals and alarm audio, that is, one pet individual corresponds to one alarm audio, and each alarm audio can be a preset different music ringtone, or a pre-recorded call of the corresponding pet individual.

[0095] S412: Drive the smart lock to broadcast the target alarm audio.

[0096] In this embodiment, by driving the smart lock to broadcast the target alarm audio, the user can identify the escaped pet individual through the broadcast audio.

[0097] See also Figure 3 The second embodiment of the present application provides a pet escape detection system 100, including: a smart lock 101 and a cloud platform 102; the smart lock 101 includes a first camera corresponding to an indoor side and a second camera corresponding to an outdoor side;

[0098] When the smart lock is detected to be awakened, the smart lock 101 starts the first camera to shoot in a downward direction indoors, and starts the second camera to shoot in a downward direction outdoors;

[0099] If a living body is detected on the indoor side corresponding to the smart lock before the smart lock 101 is locked, the first video recorded by the first camera is obtained after the smart lock 101 is locked; if a living body is detected on the outdoor side corresponding to the smart lock after the smart lock 101 is unlocked, the smart lock 101 obtains the second video recorded by the second camera when a preset delay time is reached after locking;

[0100] The smart lock 101 uploads the first recorded video and the second recorded video to the cloud platform 102;

[0101] The cloud platform 102 performs video image recognition on the first recorded video and the second recorded video, obtains a recognition result, and sends it to the smart lock 101;

[0102] The smart lock 101 determines whether a pet has escaped based on the identification result of the cloud platform.

[0103] It should be noted that the pet escape detection system 100 provided in the second embodiment of the present application only uses the division of the above-mentioned functional bodies as an example when executing the pet escape detection method. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the pet escape detection system 100 provided in the second embodiment of the present application and the pet escape detection method of the first embodiment of the present application are of the same concept. The implementation process thereof is detailed in the method embodiment and will not be repeated here.

[0104] A third aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the pet escape detection method described above are implemented.

[0105] The device embodiments described above are merely illustrative, wherein the components described as separate parts may or may not be physically separated, and the parts displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application. Ordinary technicians in this field can understand and implement it without creative work.

[0106] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0107] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0108] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0109] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0110] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0111] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0112] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0113] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0114] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A pet escape detection method, characterized in that: Applied to a smart lock, the smart lock includes a first camera corresponding to an indoor side and a second camera corresponding to an outdoor side; The method includes: When it is detected that the smart lock is awakened, the first camera is started to shoot in a downward direction indoors, and the second camera is started to shoot in a downward direction outdoors; If a living body is detected on the indoor side corresponding to the smart lock before the smart lock is locked, a first video recorded by the first camera is obtained after the smart lock is locked; if a living body is detected on the outdoor side corresponding to the smart lock after the smart lock is unlocked, a second video recorded by the second camera is obtained when a preset delay time is reached after the smart lock is locked; Uploading the first recorded video and the second recorded video to the cloud platform, and obtaining a cloud platform recognition result issued by the cloud platform after performing video image recognition; According to the recognition result of the cloud platform, it is determined whether the pet escapes.

2. The pet escape detection method according to claim 1, characterized in that: The shooting area of ​​the first camera covers the door body below the first camera and the ground within a first distance range from the door body; the shooting area of ​​the second camera covers the door body below the second camera and the ground within a second distance range from the door body.

3. The pet escape detection method according to claim 1, characterized in that: The smart lock further includes a third camera corresponding to the outdoor side, and the shooting wide angle of the third camera is greater than that of the second camera; The method also includes: When the smart lock is detected to be awakened, the third camera is started to shoot in the outdoor direction; If a living body is detected on the outdoor side corresponding to the smart lock before the smart lock is locked, a third video shot by the third camera is obtained when a preset delay time is reached after the smart lock is locked; If it is determined according to the recognition result of the cloud platform that the pet has escaped, the third video recording is uploaded to the cloud platform.

4. The pet escape detection method according to claim 3, characterized in that: The shooting frame rates of the first camera and the second camera are greater than the shooting frame rate of the third camera.

5. The pet escape detection method according to claim 1, characterized in that: The smart lock also includes an indoor liveness detection sensor facing the indoor side and an outdoor liveness detection sensor facing the outdoor side; the indoor liveness detection sensor is used to detect whether there is a living body on the indoor side corresponding to the smart lock; the outdoor liveness detection sensor is used to detect whether there is a living body on the outdoor side corresponding to the smart lock.

6. The pet escape detection method according to claim 1, characterized in that: After the step of determining whether the pet has escaped, the method includes: If it is determined that a pet has escaped, the smart lock is driven to broadcast an alarm, and / or a pet escape warning is sent to a preset terminal device through the cloud platform.

7. The pet escape detection method according to claim 6, characterized in that: The step of driving the smart lock to broadcast an alarm includes: If the cloud platform recognition result includes the target alarm audio corresponding to the escaped pet individual; drive the smart lock to broadcast the target alarm audio; wherein the target alarm audio is obtained according to the correspondence between the escaped pet individual and the preset pet individual and the alarm audio.

8. A pet escape detection system, characterized in that: include: Smart locks and cloud platforms; The smart lock includes a first camera corresponding to an indoor side and a second camera corresponding to an outdoor side; When detecting that the smart lock is awakened, the smart lock starts the first camera to shoot in a downward direction indoors, and starts the second camera to shoot in a downward direction outdoors; If a living body is detected on one side of the room corresponding to the smart lock before the smart lock is locked, a first video shot by the first camera is obtained after the smart lock is locked; If the smart lock detects a living body on the outdoor side corresponding to the smart lock after being unlocked, the smart lock obtains the second video captured by the second camera when a preset delay time is reached after being locked; The smart lock uploads the first recorded video and the second recorded video to the cloud platform; The cloud platform performs video image recognition on the first recorded video and the second recorded video, obtains a recognition result, and sends it to the smart lock; The smart lock determines whether the pet has escaped based on the recognition result of the cloud platform.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the pet escape detection method according to any one of claims 1 to 7 are implemented.

10. A smart lock, characterized in that: The smart lock is used to execute the steps of the pet escape detection method as described in any one of claims 1 to 7.

Images