CN111292504A - Method and system for carrying out safety alarm through image identification - Google Patents

Method and system for carrying out safety alarm through image identification Download PDF

Info

Publication number
CN111292504A
CN111292504A CN202010076813.4A CN202010076813A CN111292504A CN 111292504 A CN111292504 A CN 111292504A CN 202010076813 A CN202010076813 A CN 202010076813A CN 111292504 A CN111292504 A CN 111292504A
Authority
CN
China
Prior art keywords
target
image
camera
cloud
call request
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202010076813.4A
Other languages
Chinese (zh)
Inventor
余承富
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Danale Technology Co ltd
Original Assignee
Shenzhen Danale Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Danale Technology Co ltd filed Critical Shenzhen Danale Technology Co ltd
Priority to CN202010076813.4A priority Critical patent/CN111292504A/en
Publication of CN111292504A publication Critical patent/CN111292504A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/02—Alarms for ensuring the safety of persons
    • G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
    • G08B21/0438—Sensor means for detecting
    • G08B21/0476—Cameras to detect unsafe condition, e.g. video cameras
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
    • G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
    • G08B25/016—Personal emergency signalling and security systems
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
    • G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
    • G08B25/08—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using communication transmission lines

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Emergency Management (AREA)
  • Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computer Security & Cryptography (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Human Computer Interaction (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Computer Graphics (AREA)
  • Geometry (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Gerontology & Geriatric Medicine (AREA)
  • Alarm Systems (AREA)

Abstract

The application discloses a method for carrying out safety alarm through image identification, which comprises the following steps: an image pickup apparatus acquiring target images of contour information of a plurality of target subjects including only target persons; the camera equipment identifies the target image and determines the posture of the target person; the camera equipment generates a warning call request and sends the warning call request to the cloud under the condition that the posture of the target person is a preset key posture; the cloud end receives the alarm call request sent by the camera equipment and sends the alarm call request to terminal equipment; and the terminal equipment receives the alarm call request sent by the cloud. By the scheme, the efficiency of the user for knowing the occurrence of the alarm event through monitoring can be improved, and the privacy safety of people in the monitored area can be protected.

Description

Method and system for carrying out safety alarm through image identification
Technical Field
The application relates to the technical field of monitoring management, in particular to a method and a system for carrying out safety warning through image identification.
Background
Remote camera devices play a very important role in security monitoring. At present, the existing remote camera equipment uploads the shot image information to the cloud, and the cloud transmits the image information to the terminal equipment, so that the purpose of remote monitoring is achieved.
At present, a monitoring camera is visible everywhere, but in some occasions, the installation of the monitoring camera is still forbidden or inconvenient, so that people cannot deal with some emergencies in time. For example, in a hospital ward, it is inconvenient to install the monitor because the patient does not want his or her privacy to be revealed, but when the patient falls down or cannot act by his or her own strength, the worker cannot know the condition of the patient in time through remote monitoring and cannot take measures to help the patient in time. Therefore, how to monitor the monitored area and protect the privacy of people in the monitored area are considered.
Disclosure of Invention
The embodiment of the application provides a method and a system for carrying out safety alarm through image identification, which not only can improve the efficiency of a user for acquiring alarm events through monitoring, but also can protect the privacy and safety of people in a monitoring area.
In a first aspect, an embodiment of the present application provides a method for performing a security alarm through image recognition, including:
an image pickup apparatus acquiring target images of contour information of a plurality of target subjects including only target persons;
the camera equipment identifies the target image and determines the posture of the target person;
the camera equipment generates a warning call request and sends the warning call request to the cloud under the condition that the posture of the target person is a preset key posture;
the cloud end receives the alarm call request sent by the camera equipment and sends the alarm call request to terminal equipment;
and the terminal equipment receives the alarm call request sent by the cloud.
The method and the device for processing the warning event comprise the steps that the image pickup device obtains target images of contour information of a plurality of target bodies only including target characters and performs image recognition on the target images, so that whether the postures of the target characters are preset key postures is determined, and under the condition that the postures of the target characters are the preset key postures, warning conversation requests are generated to timely inform users of the occurrence of the warning events, and the efficiency of the users for knowing the occurrence of the warning events is improved. Meanwhile, as the image pickup device acquires and identifies the target images of the contour information of the target bodies only including the target person, the user can only view the images of the contour information of the target bodies only including the target person by viewing the monitoring video, and the privacy of the user can be well protected from being leaked.
In some possible embodiments, the image capturing apparatus inputs the target image into a character pose recognition model for recognition, and determines the pose of the target character, where the character pose recognition model is trained by a known image training sample, and the known image training sample includes known image sample features and character pose labels corresponding to the known image sample features.
The image pickup device can obtain the figure posture recognition model through training of the known image training sample, then the figure posture recognition model is used for determining the posture of the target figure in the target image, the situation that the target figure in the target image is checked and monitored by a person is not needed to be analyzed and judged, manpower and time are saved, and the efficiency of determining the posture of the target figure in the target image is effectively improved.
In some possible embodiments, in a case where the terminal device receives the alert call request sent by the cloud, the method further includes:
under the condition that the terminal equipment is accessed to a network through a Wireless Local Area Network (WLAN), the terminal equipment displays the target image;
and under the condition that the terminal equipment is not accessed into the network through a Wireless Local Area Network (WLAN), the terminal equipment establishes a voice call with the camera equipment.
In some possible embodiments, in a case where the terminal device establishes a voice call with the image pickup device, the method further includes:
displaying a video call shortcut key on a voice call interface of the terminal equipment;
and under the condition that the video call shortcut key is triggered, the terminal equipment stops the voice call with the camera equipment and displays the target image.
It can be seen that, in the application, a user can establish communication connection with the camera device through the terminal device, and perform video call with the camera device to view the target image or perform voice call with the camera device, and in the process of voice call, the user can switch to the video call to view the target image, so that the user can know the occurrence of an alarm event in time, and the interactive experience between the user and the camera device is also favorably improved.
In some possible embodiments, the imaging device acquires the target image by a three-dimensional reconstruction technique.
In a second aspect, an embodiment of the present application further provides a system for performing a security alarm through image recognition, including: the system comprises a camera device, a cloud terminal and a terminal device;
the image pickup apparatus is configured to acquire target images of contour information of a plurality of target subjects including only a target person;
the camera device is further used for recognizing the target image and determining the posture of the target person;
the camera device is further used for generating an alarm call request and sending the alarm call request to the cloud under the condition that the posture of the target person is a preset key posture;
the cloud end is used for receiving the alarm call request sent by the camera equipment and sending the alarm call request to the terminal equipment;
and the terminal equipment is used for receiving the alarm call request sent by the cloud.
In some possible embodiments, the image capturing apparatus is specifically configured to input the target image into a character pose recognition model for recognition, and determine the pose of the target character, where the character pose recognition model is trained by a known image training sample, and the known image training sample includes known image sample features and their corresponding character pose labels.
In some possible embodiments, the terminal device is further configured to:
under the condition that the terminal equipment is accessed to a network through a Wireless Local Area Network (WLAN), the terminal equipment displays the target image;
and under the condition that the terminal equipment is not accessed into the network through a Wireless Local Area Network (WLAN), the terminal equipment establishes a voice call with the camera equipment.
In some possible embodiments, the terminal device is further configured to:
displaying a video call shortcut key on a voice call interface of the terminal equipment;
and under the condition that the video call shortcut key is triggered, the terminal equipment stops the voice call with the camera equipment and displays the target image.
In some possible embodiments, the imaging device is specifically configured to acquire the target image by a three-dimensional reconstruction technique.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic structural diagram of a security alarm system by image recognition according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a target image provided by an embodiment of the present application;
FIG. 3 is a flowchart illustrating a method for performing a security alarm through image recognition according to an embodiment of the present application;
fig. 4 is an interface schematic diagram of a video call between a terminal device and a camera device according to an embodiment of the present application;
fig. 5 is an interface schematic diagram of a terminal device and an image pickup device performing a voice call according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a cloud according to an embodiment of the present disclosure;
fig. 7 is a schematic structural diagram of a terminal device according to an embodiment of the present application;
fig. 8 is a schematic structural diagram of an image capturing apparatus according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the present application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification of the present application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
According to the method and the system for performing the safety warning through the image recognition, after the target image of the contour information of the target main bodies only including the target person is obtained through the camera device, the target image is recognized, the posture of the target person in the target image is further determined, under the condition that the posture of the target person is determined to be the preset key posture, the warning call request is sent to the cloud end, and then the cloud end forwards the warning call request to the terminal device. The method and the system can not only protect the privacy and the safety of people in the monitoring area, but also can efficiently inform the user of the occurrence of the alarm event, and are convenient for the user to take rescue measures as soon as possible. The method and the system for carrying out safety alarm through image identification can be applied to places such as remote nursing of children and old people, nursing of patients in hospitals and the like which need to be monitored but also need to protect privacy of people in a monitored area.
First, referring to fig. 1, fig. 1 is a schematic structural diagram of a system for performing a security alarm through image recognition according to an embodiment of the present disclosure.
As shown in fig. 1, a system for performing security alarm through image recognition according to an embodiment of the present application includes: cloud 110, terminal device 120, and camera device 130. The cloud 110 may establish a communication connection between the camera device 130 and the terminal device 120.
In a specific embodiment of the present application, an image capturing apparatus related to the present application is different from a conventional image capturing apparatus, most of the conventional image capturing apparatuses only have a function of acquiring image information and do not have a function of image processing or image recognition, and the conventional image capturing apparatus needs to send the acquired image information to a backend server for image processing or image recognition. The camera equipment has the image acquisition function, the image processing function and the image recognition function, can acquire image information, then performs image processing and image recognition on the acquired image information by the camera equipment, and does not need to send the acquired image information to a background server for image processing and image recognition.
In the present application, in a case where the image pickup apparatus detects that a person enters the monitored area, the image pickup apparatus starts to capture image information of a plurality of target subjects including a target person within the monitored area, and then, the image pickup apparatus may directly process the captured image information of the plurality of target subjects including the target person into a target image including only contour information of the plurality of target subjects including the target person. The target image may be picture information (e.g., a plurality of frames of pictures continuously captured at a time), or video information (e.g., a video with a certain duration, such as a video with a length of 10 s), so as to achieve the purpose of monitoring a certain area. It is understood that the target image includes only contour information of a plurality of target subjects including a target person, and specific detail information of the plurality of target subjects, such as contour information of the head, neck, shoulder, elbow, wrist, hip, knee, ankle, etc. of the person, color of eyes of the person, hair on arms, etc., contour information of corners of a table, legs, etc. of the table, and pattern, color, etc. of the surface of the table, is not displayed. The user can only see the main body such as a person and a table in the image by looking up the monitoring video, and cannot distinguish who the person in the image is and what pattern the table is.
As shown in fig. 2, fig. 2 is a schematic diagram of a target image according to an embodiment of the present application, in fig. 2, the target image only displays contour information of a person or an object, and therefore, a user can only see the contour information of the person or the object in a monitored area through the image capturing device 130, and cannot see specific detailed information.
In a specific embodiment of the present application, the image capturing apparatus 130 may acquire target images of contour information of a plurality of target subjects including only a target person by using a three-dimensional reconstruction technique, which may be a Texture From Texture (SFT), a Stereo vision (MVS), a Time of Flight (Tof), a Structured Light (Structured Light), or the like, and is not limited in particular. The camera device 130 may further perform laser scanning on the monitored area to obtain at least one point cloud image of the monitored area, and then register and splice all the point cloud images into a target image that only includes contour information of a plurality of target subjects including the target person, which is not limited herein.
It can be understood that the user can check the target image acquired by the camera device 130 to determine the situation in the monitored area, but because the target image only includes the contour information of a plurality of target subjects including the target person, the user can only see the persons, tables and other subjects existing in the image by checking the monitoring video, and cannot distinguish who the persons are in the image and what patterns the tables are, so that the accuracy of the user in determining the situation of the target person in the target image through eyes is low, and if the user is required to determine the situation in the target image through eyes, the user is required to check and monitor in real time, which consumes much labor and time.
Therefore, in the present application, after the camera device 130 acquires the target image, the camera device 130 may further identify the target image, so as to determine the posture of the person in the target image, and if the posture of the person is the preset key posture, the camera device 130 may generate an alarm call request to be sent to the cloud terminal 110, and establish a video call or a voice call with the terminal device 120 through the cloud terminal 110. When a video call is made with a terminal device, a user can only view contour information of a plurality of target subjects including only a target person through the terminal device. Optionally, the camera device 130 may further generate an alarm prompt message to be sent to the terminal device 120, so that the user can know the type of the alarm event in time without viewing the monitoring video.
In practical application, the camera device 130 may also upload the acquired target image to the cloud terminal 110 for storage at preset intervals, so as to reduce occupation of the memory of the camera device 130. The camera device 130 may be a video camera or a camera, such as an infrared camera, and can normally collect image information of a monitored area both in the day and at night. The image pickup apparatus 130 may be provided in a hospital ward, a washroom in a user's home, or the like, and is not particularly limited herein.
In a specific embodiment of the present application, the cloud terminal 110 may establish a communication connection between the camera device 130 and the terminal device 120, generate an alarm call request to the cloud terminal 110 when the camera device 130 recognizes that the gesture of the person in the target image is a preset key gesture, and then the cloud terminal 110 may forward the alarm call request to the terminal device 120, and if the user selects to receive the alarm call request, a call is established between the camera device 130 and the terminal device 120. Optionally, the warning prompt message generated by the camera device 130 may also be forwarded to the terminal device 120 through the cloud 110, and it can be understood that the camera device 130 may also directly send the warning prompt message to the terminal device 120 through a network, which is not specifically limited herein. In practical applications, the cloud 110 may further store a target image uploaded by the camera 130, and a user may request the cloud 110 to view the target image stored in the cloud 110 through the terminal device 120, so that the camera 130 and the terminal device 120 are not required to store the target image, and the memory occupation of the camera 130 and the terminal device 120 is reduced.
Before the cloud 110 stores the target image uploaded by the camera 130 and establishes a communication connection between the camera 130 and the terminal device 120, the cloud 110 may store identification information of the camera 130 in advance, and then store the target image uploaded by the camera 130 to a suitable position according to the identification information of the camera 130. The cloud 110 may also store the identification information of the terminal device 120 and the binding relationship between the camera device 130 and the identification information of the terminal device 120 in advance, and then establish a communication connection between the camera device 130 and the terminal device 120 according to the identification information of the camera device 130 and the identification information of the terminal device 120 and the binding relationship therebetween.
In a specific embodiment of the present application, the terminal device 120 may receive an alarm call request and an alarm prompt message, establish a call with the camera device 130 when the alarm call request is received, and if the established call is a video call, the user may view a target image acquired by the camera device 130 on the terminal device 120; if the voice call is established, the user can send a voice to the image pickup apparatus 130 through the terminal apparatus 120, so that people in the monitoring area of the image pickup apparatus 130 hear the voice sent by the user. In case of receiving the alarm prompting message, the terminal device 120 displays the alarm prompting message so that the user can know the alarm event type in time. In practical applications, the camera device 130 may send the alarm call request and the alarm prompt message at the same time, and the terminal device 120 may receive and display the alarm call request and the alarm prompt message at the same time, which is not limited herein.
More specifically, the terminal device 120 may further send a request to the cloud terminal 110 to check the historical target image and the real-time target image uploaded by the camera device 130 and stored in the cloud terminal 110, and the user may further download the target image stored in the cloud terminal 110 as needed, and may perform operations such as deleting or renaming on the terminal device 120 side after downloading, which is not limited specifically herein.
It is understood that the system for security alarm through image recognition described in fig. 1 may further include an audio playing device, and the audio playing device is connected to the camera device 130. The audio playing device may be, for example, a smart speaker, a bluetooth speaker, or other devices capable of playing audio files.
In addition, the system for performing security alarm through image recognition as shown in fig. 1 may further include a video playing device, and the video playing device is connected to the terminal device 120. The video playing device may be, for example, a smart tv or other device capable of playing video files.
In addition, it should be noted that the numbers of the cloud 110, the terminal device 120, and the camera device 130 in fig. 1 are merely illustrative. There may be any number of the cloud 110, the terminal device 120, and the camera device 130, as desired for implementation.
As can be seen from the foregoing embodiments, the camera device 130 may acquire a target image of contour information of a plurality of target subjects including only a target person, may further perform image recognition on the target image, and send an alarm call request to the cloud end 110 when it is determined that the posture of the target person is a preset key posture, and then the cloud end 110 forwards the alarm call request to the terminal device 120, so as to notify a user of an occurrence of an alarm event in time, so that the user may take measures in time. By the aid of the scheme, the user can timely know the occurrence of the alarm event, so that the user can conveniently take corresponding measures as soon as possible, and the efficiency of knowing the alarm event in the monitoring area is improved. In the application, the user can also perform a video call or a voice call with the image pickup device 130 as required, and when performing the video call, the user views the target images of the contour information of a plurality of target subjects including only the target person, and cannot view the specific detail information of the target subjects such as the target person, so that the requirement of the user on protecting the privacy and the safety of the persons in the monitored area is met.
The technical solution provided in the embodiment of the present application may be implemented based on the framework shown in fig. 1, which is a system for performing security alarm through image recognition or a deformation framework thereof, and is not limited in detail here.
Next, referring to fig. 2, fig. 2 is a schematic flowchart of a method for performing a security alarm through image recognition according to an embodiment of the present application. The method for performing safety warning through image identification provided by the embodiment of the application can comprise the following steps:
s101: the image pickup apparatus acquires target images of contour information of a plurality of target subjects including only a target person.
In a specific embodiment of the present application, an image capturing apparatus related to the present application is different from a conventional image capturing apparatus, most of the conventional image capturing apparatuses only have a function of acquiring image information and do not have a function of image processing or image recognition, and the conventional image capturing apparatus needs to send the acquired image information to a backend server for image processing or image recognition. The camera equipment has the image acquisition function, the image processing function and the image recognition function, can acquire image information, then performs image processing and image recognition on the acquired image information by the camera equipment, and does not need to send the acquired image information to a background server for image processing and image recognition.
In the present application, in a case where the image pickup apparatus detects that a person enters the monitored area, the image pickup apparatus starts to capture image information of a plurality of target subjects including a target person within the monitored area, and then, the image pickup apparatus may directly process the captured image information of the plurality of target subjects including the target person into a target image including only contour information of the plurality of target subjects including the target person. The target image may be picture information (e.g., a plurality of frames of pictures continuously captured at a time), or video information (e.g., a video with a certain duration, such as a video with a length of 10 s), so as to achieve the purpose of monitoring a certain area. It is understood that the target image includes only contour information of a plurality of target subjects including a target person, and specific detail information of the plurality of target subjects, such as contour information of the head, neck, shoulder, elbow, wrist, hip, knee, ankle, etc. of the person, color of eyes of the person, hair on arms, etc., contour information of corners of a table, legs, etc. of the table, and pattern, color, etc. of the surface of the table, is not displayed. The user can only see the main body such as a person and a table in the image by looking up the monitoring video, and cannot distinguish who the person in the image is and what pattern the table is.
It should be noted that the image capturing device may be one or more cameras or one or more cameras, and the image capturing device may rotate to acquire information in the monitored area from different angles to obtain the target image.
In a specific embodiment of the present application, the image capturing apparatus may acquire target images of contour information of a plurality of target subjects including only a target person by a three-dimensional reconstruction technique, which may be a Texture From Texture (SFT), a stereoscopic vision (MVS), a time of Flight (TOF), a Structured Light (Structured Light), or the like, and is not particularly limited herein. The image capturing device may further perform laser scanning on the monitored area to obtain at least one point cloud image of the monitored area, and then perform registration and stitching on all the point cloud images to form a target image that only includes contour information of a plurality of target subjects including the target person, which is not limited herein. It can be understood that a user can only see the outline information of a person or an object in the monitoring area and cannot see specific detailed information by looking up the monitoring area through the camera device, so that the purpose of protecting the privacy of the person in the monitoring area is achieved.
Taking the example that the camera device includes two cameras with the same model and the method for performing three-dimensional reconstruction on the target image is a stereoscopic vision MVS method, the process of obtaining the target image by the camera device will be described in detail below.
The first step is as follows: and adjusting the positions and shooting angles of the two cameras, and shooting to obtain two-dimensional images at different angles.
The second step is that: and preprocessing two-dimensional images at different angles.
Specifically, the preprocessing may be distortion correction, gaussian filtering, contrast enhancement, and grayscale normalization, where the distortion correction may include: the method comprises the steps of obtaining calibration parameters such as internal parameters and external parameters of two cameras by adopting a Zhang friend calibration method or a chessboard method, obtaining a distortion correction projection matrix based on the calibration parameters, applying the distortion correction projection matrix to each frame of image input into a correction module to perform distortion correction and the like, wherein the distortion correction projection matrix is not specifically limited, denoising two-dimensional images by adopting Gaussian filtering, and enhancing the contrast and the gray level normalization of the two-dimensional images so as to enhance the contour edge of a target main body in the two-dimensional images.
The third step: and performing feature extraction on the two preprocessed two-dimensional images to obtain feature points of a plurality of target main bodies in the two-dimensional images, and then performing feature point matching and limit constraint detection.
Specifically, an image interest point can be detected by adopting an autocorrelation matrix of a luminance function as a feature point, a nearest neighbor matching method is adopted to perform feature point matching to obtain a feature point pair, then epipolar geometric constraint detection is performed on the feature point pair, and the feature point pair which does not meet constraint and is caused by noise or distortion is removed, so that the accuracy of subsequent three-dimensional reconstruction is improved. The method of extracting the feature points may be a nonlinear filtering method, and the method is not limited to the autocorrelation matrix detection method of the luminance function, and is not particularly limited herein.
The fourth step: and further, the three-dimensional structure of the two-dimensional image can be gridded according to the three-dimensional coordinates, so that the contour information of a plurality of target bodies including the target person in the target area can be well represented, and the target image of the contour information of the plurality of target bodies only including the target person can be obtained.
In the specific embodiment of the application, after the camera device obtains the target image, the target image can be uploaded to the cloud at preset intervals, and the cloud can store or forward the target image. The sending of the target image to the cloud by the camera device can be realized in a wireless mode, such as 3G, 4G, WLAN or the like.
Therefore, the camera device can monitor the monitored area in real time, acquire information of the monitored area to obtain a target image, and the obtained target image only displays the contour information of a plurality of target bodies including the target person, does not display the specific appearance characteristics, the body characteristics and the like of the target person, does not display the specific detail characteristics of an object, and can protect the privacy and the safety of the person in the monitored area. Meanwhile, the camera device can send the target image to the cloud for storage, the camera device is not required to store the target image, and the occupation of the memory of the camera device is reduced.
S102: the camera device identifies the target image and determines the posture of the target person.
In a specific embodiment of the present application, the image capturing apparatus recognizes the target image and determines the pose of the target person, and specifically, the image capturing apparatus inputs the target image into a person pose recognition model for recognition, thereby determining the pose of the target person. The character posture recognition model is obtained by training a model by using a known image training sample. The process of training the character gesture recognition model may include:
a1: and acquiring a known image training sample, wherein the known image training sample comprises known image sample characteristics and a character posture label corresponding to the known image sample characteristics.
In the specific embodiment of the present application, the known images in the known image training samples acquired by the image capturing apparatus also include only contour information of a person or an object, and do not include specific detail information of the person or the object. The known image in the known image training sample may be an image acquired by an image capturing device and including only contour information of a person, an object, or the like, or may also be an image acquired from a network resource and including only contour information of a person, an object, or the like, and is not limited specifically here. Each frame of known image in the known image training sample has the characteristic of known image sample characteristic, and the person posture label corresponding to the known image sample characteristic is a classification value determined according to the classification to which the known image sample characteristic belongs.
A2: and training according to the known image training sample to obtain a character posture recognition model.
After the known image training samples are acquired, the image capturing apparatus may train the known image training samples based on the model, and obtain a trained character posture recognition model. The model in the embodiment of the present application may be a supervised learning model or a semi-supervised learning model, and is not specifically limited herein. In supervised and semi-supervised learning models, character pose labels are the desired output.
When the model is trained, the known image sample characteristics are input into the training model, and the relevant parameters of the model are adjusted to make the output of the model approach or reach the expected output as much as possible. To illustrate graphically in a simple example, a model corresponds to a function, the known image sample features correspond to the independent variable X in the function, the desired output (the pose tag of the person) corresponds to the dependent variable Y in the function, and the constants in the function correspond to the relevant parameters of the model that need to be adjusted. When the optimal constant is obtained, a function is obtained, that is, a character posture recognition model is obtained. When using the model, a target image is input, and the character pose recognition model gives an output (character pose tag) which is simply judged to achieve the purpose of determining the pose of the character in the target image. For example, when the classification is performed by using a binary method (e.g., 0 and 1), when the output is 0.8 and the 0.8 is greater than a preset threshold 0.6, the classification of the target image is determined as the classification corresponding to 1, and when the output is 0.3 and less than the preset threshold 0.6, the classification of the target image is determined as the classification corresponding to 0. Those skilled in the art can understand that the model in this embodiment can also achieve the purpose of regression, where the output corresponding to regression is not discrete data but continuous data, and the implementation manner is similar to classification, and this embodiment is not described herein again.
The figure gestures which can be identified and determined in the embodiment of the application include getting up, running, walking, reading, sleeping, falling, lying down, bending and the like, and are not particularly limited herein.
In the specific embodiment of the present application, after the image capturing apparatus acquires the target image including only the contour information of the target subjects including the target person, since the target image may be a single-frame or multi-frame image and may also be video information, the image capturing apparatus may intercept the single-frame or multi-frame image in the target image for image recognition, since the target image includes only the contour information of the target subjects including the target person and does not include specific detail feature information, and therefore, at the time of recognition, it is also only necessary to recognize contour key points of the target subjects including the target person, such as only the position information and the posture information of the head, the neck, the shoulder, the elbow, the wrist, the hip, the knee, the ankle, and the like of the target person, and without recognizing the color of the eyes, the fingerprint of the finger, and the like of the target person, by recognizing the position information and the posture information of the contour key points of the target subjects including the target person, the posture of the target person can be determined, for example, in the target image, there is a person, there is a bed, there is a floor, and the person is in the bed, and if only the position information and posture information of the person are recognized, it is determined that the posture of the person is lying, but it cannot be further determined whether the person is lying in the bed or on the ground. Therefore, by recognizing the position information and posture information of the target person and the other target subjects than the target person in the target image, it can be determined more accurately that the posture of the target person is lying in bed.
S103: and generating an alarm call request and sending the alarm call request to the cloud under the condition that the posture of the target person is the preset key posture.
In a specific embodiment of the application, the camera device identifies the target image, and if the camera device determines that the posture of the target person is a falling posture, a struggling posture, a twitching posture and the like, the camera device determines that the posture of the target person is a preset key posture, generates an alarm call request, and sends the alarm call request to the cloud; and if the camera equipment determines that the posture of the target person is sleeping, reading, walking and the like, the camera equipment determines that the posture of the target person is a normal posture, and does not generate an alarm call request.
In the specific embodiment of the application, under the condition that the camera device determines that the posture of the target person is the preset key posture, the camera device can also generate an alarm prompt message, and if the camera device determines that the posture of the target person is the preset key posture of falling, the alarm prompt message of falling of people is generated, and then the alarm prompt message is sent to the cloud.
S104: and the cloud end receives the alarm call request sent by the camera equipment and sends the alarm call request to the terminal equipment.
In a specific embodiment of the application, the cloud end stores the identification information of the camera device, the identification information of the terminal device, and the binding relationship between the camera device and the terminal device, which is established according to the identification information. The cloud end can also receive an alarm prompt message sent by the camera equipment and send the alarm prompt message to the terminal equipment.
S105: and the terminal equipment receives an alarm call request sent by the cloud.
In the specific embodiment of the application, under the condition that the terminal device is connected to the network through the wireless local area network WLAN, the terminal device receives the alarm call request sent by the cloud, establishes a video call with the camera device, and can be understood that a display interface of the terminal device displays a target image, which is obtained by the camera device and only contains contour information of a plurality of target bodies including target persons, in real time. As shown in fig. 3, fig. 3 is a schematic view of a terminal device and an image capturing device performing a video call according to an embodiment of the present application, in fig. 3, when the terminal device and the image capturing device perform a video call, a user may only view contour information of a person or an object, but may not see specific detail information, so that privacy of the person in a monitored area may be protected.
Under the condition that the terminal device is not accessed to the network through the wireless local area network WLAN, for example, the terminal device receives the alarm call request sent by the cloud and establishes a voice call with the camera device through the 3G, 4G and the like, it can be understood that the terminal device receives the voice input by the user and sends the voice to the camera device through the cloud. Here, when the call established between the image pickup apparatus and the terminal apparatus is a voice call, a video call shortcut key is displayed on a voice call interface of the terminal apparatus, and if the user triggers the video call shortcut key, the image pickup apparatus stops the voice call with the terminal apparatus and switches to the video call with the terminal apparatus, that is, the terminal apparatus displays, in real time, a target image of contour information of a plurality of target subjects including only a target person, which is acquired by the image pickup apparatus.
Here, the terminal device can also receive and display the alarm prompt message sent by the cloud, and the type of the alarm event can be known without establishing a video call or a voice call between the user and the camera device. In practical applications, the camera device may send the alarm call request and the alarm prompt message at the same time, and the terminal device may receive the alarm call request and the alarm prompt message at the same time, which is not limited herein. As shown in fig. 4, fig. 4 is an interface schematic diagram of a terminal device and a camera device performing a voice call according to an embodiment of the present application, where in fig. 4, a warning prompt message "someone falls down" is displayed, and a video call shortcut key, a recording shortcut key, and the like are also included.
It is understood that fig. 3 and fig. 4 are only used as an example, in practical applications, the target image displayed in fig. 3 may be other, the warning prompt message displayed in fig. 4 may be other, fig. 3 and fig. 4 may also display more contents such as identification information of the image capturing apparatus or a location of the image capturing apparatus, and the displayed shortcut key may also be other or more, which is not limited specifically herein.
In a more specific embodiment, the number of image pickup apparatuses may be one or more, and in the case where the number of image pickup apparatuses is one, one image pickup apparatus may have a binding relationship with one or more terminal apparatuses. In the case that the number of the image capturing apparatuses is multiple, the multiple image capturing apparatuses may have a binding relationship with the same terminal apparatus, or may be bound with different terminal apparatuses, which is not specifically limited herein. Specifically, under the condition that the number of the camera devices is one and the camera devices are in a binding relationship with the terminal devices, permission levels of the terminal devices can be set in the camera devices, then, under the condition that the posture of a target person is determined to be a preset key posture by the camera devices, the camera devices firstly generate alarm call requests carrying identification information of the terminal device with the highest permission level and send the alarm call requests to a cloud, the cloud is requested to forward the alarm call requests to the terminal device with the highest permission level, and under the condition that the terminal device with the highest permission level receives the alarm call requests, the camera devices do not generate alarm call requests carrying identification information of other terminal devices and send the alarm call requests to the cloud; and under the condition that the terminal equipment with the highest authority level does not receive the alarm call request, the camera equipment generates an alarm call request carrying identification information of terminal equipment with a lower authority level and sends the alarm call request to the cloud end, and the cloud end is requested to forward the alarm call request to the terminal equipment with the lower authority level.
For example, assume that the terminal device bound by the camera in the user's home includes a terminal device a, a terminal device B, and a terminal device C, the permission level of the terminal device a is set as level a in the camera, the permission level of the terminal device B is set as level B, the permission level of the terminal device C is set as level C, and when the camera determines that the posture of the person in the monitoring area is a preset key posture such as a fall, the camera may first generate an alarm call request a carrying identification information of the terminal device a, and request the cloud to forward the alarm call request a to the terminal device a. Under the condition that the terminal equipment A receives the alarm call request A, the camera can not generate the alarm call request B carrying the identification information of the terminal equipment B any more; under the condition that the terminal device A does not receive the alarm call request A, the camera can generate an alarm call request B carrying identification information of the terminal device B, and the request cloud forwards the alarm call request B to the terminal device B. Similarly, under the condition that the terminal device B does not receive the alarm call request B, the camera may generate an alarm call request C carrying identification information of the terminal device C, and the request cloud forwards the alarm call request C to the terminal device C.
In addition, under the condition that the number of the camera devices is one and the camera devices are in a binding relationship with the terminal devices, the permission levels of the terminal devices can be set in the cloud, then, under the condition that the camera devices determine that the posture of the target person is a preset key posture such as falling, the alarm call request is generated, the cloud is requested to forward the alarm call request to the corresponding terminal device, the cloud firstly forwards the alarm call request to the terminal device with the highest permission level, and under the condition that the terminal device with the highest permission level receives the alarm call request, the cloud does not forward the alarm call request to other terminal devices with lower permission levels; and under the condition that the terminal equipment with the highest authority level does not receive the alarm call request, the cloud end forwards the alarm call request to other terminal equipment with lower authority levels.
In another more specific embodiment, when the number of the camera devices is one, and the camera devices and the terminal devices have a binding relationship, the camera devices may obtain distances from the terminal devices to the camera devices, and when the camera devices determine that the posture of the target person is the preset key posture, the camera devices first generate an alarm call request carrying identification information of the terminal device with the shortest distance, request the cloud terminal to forward the call request to the corresponding terminal device, and when the corresponding terminal device receives the alarm call request, the camera devices do not generate an alarm call request carrying identification information of other terminal devices and send the alarm call request to the cloud terminal; and under the condition that the corresponding terminal equipment does not receive the alarm call request, the camera equipment generates the alarm call request carrying identification information of the terminal equipment with a longer distance, and the request cloud end forwards the call request to the corresponding terminal equipment.
In practical application, in the process of video call or voice call between the camera device and the terminal device, more or other shortcut keys can be set on the call interface of the terminal device, for example, a video recording shortcut key is displayed on the video call interface, a target image displayed by the terminal device can be recorded, and a storage shortcut key on the video call interface is clicked, so that the target image can be stored. For example, when the recording shortcut key is clicked on the voice call interface, the voice message input by the user can be recorded, and when the call ending shortcut key on the video call interface is clicked, the voice call can be ended.
Therefore, the terminal equipment receives the alarm call request sent by the cloud end and establishes a video call or a voice call with the camera equipment, so that a user can know the occurrence of an alarm event in time, and the interactive experience of the user through the terminal equipment and the camera equipment is promoted.
In a specific embodiment of the application, the terminal device may further send a request to the cloud, check a historical target image and a real-time target image uploaded by the camera device and stored on the cloud, and download, update or delete the historical target image and the real-time target image as required.
In the scheme, the camera device can determine the posture of the target character in the target image through the character posture recognition model, the alarm call request is generated to the cloud under the condition that the posture of the target character is the preset key posture, and then the alarm call request is forwarded to the terminal device through the cloud, so that the privacy of the target character in a monitoring area can be protected, a user can timely know the occurrence of an alarm event, the monitoring safety and the efficiency of judging the alarm event are effectively improved, the user can carry out video call or voice call with the camera device as required, and the interaction experience of the user and the camera device is improved.
The embodiment of the present application relates to a cloud, and as shown in fig. 6, fig. 6 is a schematic diagram illustrating a possible cloud 100 related to the present application. The cloud owner deploys the cloud computing infrastructure of the cloud 100 itself, i.e., deploys computing resources 111 (e.g., servers), deploys storage resources 112 (e.g., memory), and deploys network resources 113 (e.g., network cards), among others. The public cloud owner (e.g., operator) then virtualizes the computing resources 111, storage resources 112, and network resources 113 of the cloud computing infrastructure and provides the corresponding services to users (e.g., subscribers) of the cloud for use. The operator can provide the following three services for the user to use: cloud computing infrastructure as a service (IaaS), platform as a service (PaaS), and software as a service (SaaS).
The services provided by IaaS to the user are the utilization of the cloud computing infrastructure, including processing, storage, networking, and other basic computing resources 111, and the user can deploy and run any software, including operating systems and applications, in the cloud 100. Users do not manage or control any cloud computing infrastructure, but can control operating system selection, storage space, deployment applications, and possibly limited network component (e.g., firewall, load balancer, etc.) control.
The services provided by PaaS to users are applications developed or purchased by users using development languages and tools (e.g., Java, python, Net, etc.) provided by vendors, deployed to the cloud computing infrastructure. The user does not need to manage or control the underlying cloud computing infrastructure, including networks, servers, operating systems, storage, etc., but the user can control the deployed applications and possibly also the hosting environment configuration in which the applications are run.
The services provided by SaaS to the user are application programs that the operator runs on the cloud computing infrastructure, and the user can access the application programs on the cloud computing infrastructure through a client interface, such as a browser, on various terminal devices. The user does not need to manage or control any cloud computing infrastructure, including networks, servers, operating systems, storage, and the like.
It can be understood that an operator leases different tenants through any one of IaaS, PaaS, and SaaS, and data and configuration between different tenants are isolated from each other, thereby ensuring security and privacy of data of each tenant.
Those skilled in the art will appreciate that the cloud 100 shown in fig. 6 does not constitute a limitation of the cloud, and may include more or fewer services or facilities than those shown, or some services or facilities may be combined, or some services or facilities may be split, or different service allocations or facility arrangements.
The embodiment of the present application relates to a terminal device, which may be a mobile phone, a tablet computer, a Personal Digital Assistant (PDA), a Mobile Internet Device (MID), a notebook computer, an intelligent wearable device (such as an intelligent watch and an intelligent bracelet), and the like, and the embodiment of the present application is not limited.
Taking a terminal device as an example of a mobile phone, fig. 7 is a block diagram illustrating a partial structure of a mobile phone 200 according to an embodiment of the present application. Referring to fig. 7, the handset 200 includes components such as a memory 211, a processor 212, an input/output (I/O) subsystem 213, other input device controllers 214, other input devices 215, a display controller 216, a display screen 217, and a sensor controller 218.
Those skilled in the art will appreciate that the handset configuration shown in fig. 7 is not intended to be limiting and may include more or fewer components than those shown, or may combine certain components, or split certain components, or arranged in different components.
The following describes the components of the mobile phone 200 in detail with reference to fig. 7:
the memory 211 may be used to store software programs and modules, and the processor 212 executes various functional applications and data processing of the mobile phone 200 by operating the software programs and modules stored in the memory 211. The memory 211 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone 200, and the like. Further, the memory 211 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
Display 217 may be used to display information entered by or provided to the user as well as various menus for handset 200, and may also accept user input. Alternatively, the display screen 217 may include a display panel as well as a touch panel. The display panel may be configured in the form of a Liquid Crystal Display (LCD), an organic light-emitting diode (OLED), or the like. The touch panel, also called a touch screen, a touch sensitive screen, etc., may collect contact or non-contact operations (such as operations performed by a user on or near the touch panel using any suitable object or accessory, such as a finger, a stylus, etc., and may also include somatosensory operations, including operation types such as single-point control operations, multi-point control operations, etc.) on or near the touch panel, and drive the corresponding connection device according to a preset program.
The I/O subsystem 213 controls input and output of peripheral devices, and may include other input device controllers 214, a sensor controller 218, and a display controller 216. Optionally, one or more other input device controllers 214 receive signals from and/or transmit signals to other input devices 215, and other input devices 215 may include physical buttons (push buttons, rocker buttons, etc.), dials, slide switches, joysticks, click wheels, a light mouse (a light mouse is a touch-sensitive surface that does not display visual output, or is an extension of a touch-sensitive surface formed by a touch screen). It is noted that other input device controllers 214 may be connected to any one or more of the above-described devices. The display controller 216 in the I/O subsystem 213 receives signals from the display screen 217 and/or sends signals to the display screen 217. After the display screen 217 detects the user input, the display controller 216 converts the detected user input into interaction with the user interface object displayed on the display screen 217, that is, human-computer interaction is realized. The sensor controller 218 may receive signals from and/or transmit signals to one or more sensors.
The processor 212 is a control center of the mobile phone 200, connects various parts of the entire mobile phone by using various interfaces and lines, and performs various functions of the mobile phone 200 and processes data by operating or executing software programs and/or modules stored in the memory 211 and calling data stored in the memory 211, thereby performing overall monitoring of the mobile phone. Alternatively, processor 212 may include one or more processing units; preferably, the processor 212 may integrate an application processor, which primarily handles operating systems, user interfaces, applications, etc., and a modem processor, which primarily handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 212.
Although not shown, the mobile phone 200 may further include a power supply (such as a battery), an RF (radio frequency) circuit, an audio circuit, a sensor, a camera, a bluetooth module, and the like for supplying power to each component, which is not described herein again.
The embodiment of the present application relates to an image pickup apparatus, which may be various image pickup apparatuses such as a video camera or a smart camera, and the present application takes a video camera as an example, as shown in fig. 8, and fig. 8 is a block diagram illustrating a partial structure of a possible video camera 300 related to the present application. The camera 300 adopts an embedded architecture, integrates various functions of video and audio acquisition, signal processing, coding compression, front-end storage, network transmission and the like, and can form a large-scale distributed network video monitoring system by combining a network video storage and recording system and management platform software. Referring to fig. 8, the camera 300 includes a lens and sensor 310, an encoding processor 320, and a camera main control board 330. Those skilled in the art will appreciate that the camera configuration shown in fig. 8 does not constitute a limitation of the imaging apparatus and may include more or fewer components than those shown, or some components may be combined, or some components may be split, or a different arrangement of components.
The following specifically describes the respective constituent components of the camera 300 with reference to fig. 8:
the lens in the lens and sensor 310 is a key device of the video monitoring system, and the quality of the lens directly affect the quality of the whole camera 300. The lens can be used for imaging an external scene on a sensor, at present, the lenses of the camera 300 are all threaded, and generally comprise a group of lenses and diaphragms, the lenses are divided into Manual Iris (MI) and Auto Iris (AI), the manual iris is suitable for occasions with unchanged brightness, and the iris of the automatic iris can be automatically adjusted when the brightness of the automatic iris is changed, so that the camera is suitable for occasions with changed brightness. Alternatively, the lens may be a standard lens, a telephoto lens, a zoom lens, a variable focus lens, or the like, and the material of the lens may be glass or plastic.
The sensor in the lens and sensor 310 may be an image sensor, such as a Charge Coupled Device (CCD) sensor or a Complementary Metal Oxide Semiconductor (CMOS) sensor, for converting an optical signal (an image of an object) received by the sensor into an electrical signal, outputting the electrical signal to the encoding processor 320 through a driving circuit, performing optimization processing, such as color, sharpness, white balance, etc., on the digital image signal collected by the lens and sensor 310 by the encoding processor 320, and inputting the digital image signal into the camera main control board 330 in the form of a network video signal, where the camera main control board 330 has functions of a Bayonet Nut Connector (BNC) video output, a network communication interface, an audio input, an audio output, an alarm call request output, an alarm prompt message output, a serial communication interface, etc. The encoding processor 320 is configured to perform an optimization process on the digital image signal transmitted from the lens and sensor 310, and the encoding processor 320 may include an Image Signal Processor (ISP) or an image decoder, which is not limited in this respect.
The encoding processor 320 of the camera 300 in the present application further includes an image obtaining module 321 and an image recognizing module 322, wherein the image obtaining module 321 is configured to process the digital image signals collected by the lens and the sensor into a target image including only contour information of a person or an object. The method adopted by the image obtaining module 321 may be a texture restoration shape method, a stereo vision method, a time-of-flight method, a structured light method, and the like, and is not limited in particular here. The image recognition module 322 includes a character pose recognition model for recognizing the target image and determining the pose of the character in the target image. In the event that the character pose is determined to be a preset key pose, encoding processor 320 generates an alert call request and an alert prompt message.
Although not shown, the camera 300 may further include a power source (such as a battery) for supplying power to the respective components, or a bluetooth module, etc., which will not be described herein.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the cloud, the terminal device, the camera device and the unit described above may refer to corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electric, mechanical or other form of connection.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present application.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially or partially contributed by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
While the invention has been described with reference to specific embodiments, the scope of the invention is not limited thereto, and those skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (10)

1. A method for security alarm through image recognition is characterized by comprising the following steps:
an image pickup apparatus acquiring target images of contour information of a plurality of target subjects including only target persons;
the camera equipment identifies the target image and determines the posture of the target person;
the camera equipment generates a warning call request and sends the warning call request to the cloud under the condition that the posture of the target person is a preset key posture;
the cloud end receives the alarm call request sent by the camera equipment and sends the alarm call request to terminal equipment;
and the terminal equipment receives the alarm call request sent by the cloud.
2. The method of claim 1, wherein the image capturing device inputs the target image into a character pose recognition model for recognition, and determines the pose of the target character, wherein the character pose recognition model is trained using known image training samples, and wherein the known image training samples comprise known image sample features and their corresponding character pose labels.
3. The method according to claim 1, wherein in a case where the terminal device receives the alert call request sent by the cloud, the method further comprises:
under the condition that the terminal equipment is accessed to a network through a Wireless Local Area Network (WLAN), the terminal equipment displays the target image;
and under the condition that the terminal equipment is not accessed into the network through a Wireless Local Area Network (WLAN), the terminal equipment establishes a voice call with the camera equipment.
4. The method according to claim 3, wherein in a case where the terminal apparatus establishes a voice call with the image pickup apparatus, the method further comprises:
displaying a video call shortcut key on a voice call interface of the terminal equipment;
and under the condition that the video call shortcut key is triggered, the terminal equipment stops the voice call with the camera equipment and displays the target image.
5. The method according to any one of claims 1 to 4, wherein the imaging apparatus acquires the target image by a three-dimensional reconstruction technique.
6. A security alarm system by image recognition, comprising: the system comprises a camera device, a cloud terminal and a terminal device;
the image pickup apparatus is configured to acquire target images of contour information of a plurality of target subjects including only a target person;
the camera device is further used for recognizing the target image and determining the posture of the target person;
the camera device is further used for generating an alarm call request and sending the alarm call request to the cloud under the condition that the posture of the target person is a preset key posture;
the cloud end is used for receiving the alarm call request sent by the camera equipment and sending the alarm call request to the terminal equipment;
and the terminal equipment is used for receiving the alarm call request sent by the cloud.
7. The system of claim 6, wherein the imaging device is specifically configured to input the target image into a human pose recognition model for recognition to determine the pose of the target human, wherein the human pose recognition model is trained using known image training samples, and wherein the known image training samples comprise known image sample features and their corresponding human pose tags.
8. The system of claim 5, wherein the terminal device is further configured to:
under the condition that the terminal equipment is accessed to a network through a Wireless Local Area Network (WLAN), the terminal equipment displays the target image;
and under the condition that the terminal equipment is not accessed into the network through a Wireless Local Area Network (WLAN), the terminal equipment establishes a voice call with the camera equipment.
9. The system of claim 8, wherein the terminal device is further configured to:
displaying a video call shortcut key on a voice call interface of the terminal equipment;
and under the condition that the video call shortcut key is triggered, the terminal equipment stops the voice call with the camera equipment and displays the target image.
10. The system according to any of claims 5 to 9, characterized in that the camera device is in particular adapted to acquire the target image by means of a three-dimensional reconstruction technique.
CN202010076813.4A 2020-01-23 2020-01-23 Method and system for carrying out safety alarm through image identification Pending CN111292504A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010076813.4A CN111292504A (en) 2020-01-23 2020-01-23 Method and system for carrying out safety alarm through image identification

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010076813.4A CN111292504A (en) 2020-01-23 2020-01-23 Method and system for carrying out safety alarm through image identification

Publications (1)

Publication Number Publication Date
CN111292504A true CN111292504A (en) 2020-06-16

Family

ID=71023560

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010076813.4A Pending CN111292504A (en) 2020-01-23 2020-01-23 Method and system for carrying out safety alarm through image identification

Country Status (1)

Country Link
CN (1) CN111292504A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112167074A (en) * 2020-10-14 2021-01-05 北京科技大学 Automatic feeding device based on pet face recognition
CN112601054A (en) * 2020-12-14 2021-04-02 珠海格力电器股份有限公司 Pickup picture acquisition method and device, storage medium and electronic equipment
CN112686199A (en) * 2021-01-07 2021-04-20 深圳市海雀科技有限公司 Method and system for carrying out safety alarm through encrypted image
CN113114548A (en) * 2020-07-07 2021-07-13 德能森智能科技（成都）有限公司 Terminal management method and system based on privacy management
CN113393652A (en) * 2021-06-18 2021-09-14 国能神东煤炭集团有限责任公司 Alarm method, system, device and storage medium
CN114035603A (en) * 2021-08-08 2022-02-11 中国航空工业集团公司沈阳飞机设计研究所 Dynamic detection and alarm method for threat area of unmanned aerial vehicle

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103517042A (en) * 2013-10-17 2014-01-15 吉林大学 Nursing home old man dangerous act monitoring method
CN104320618A (en) * 2014-10-23 2015-01-28 西北农林科技大学 Calf state monitoring device and method based on behavior characteristics spectrum linkage
CN105448041A (en) * 2016-01-22 2016-03-30 苏州望湖房地产开发有限公司 A human body falling intelligent control system and method
CN205582161U (en) * 2016-04-18 2016-09-14 讯之美物联网服务有限公司 System of internet of things
CN106991787A (en) * 2017-06-07 2017-07-28 京东方科技集团股份有限公司 Intelligent closestool and the safety monitoring system based on intelligent closestool
US20170358195A1 (en) * 2016-06-14 2017-12-14 Board Of Trustees Of The University Of Arkansas Real-Time Awareness of Environmental Hazards for Fall Prevention
CN108197589A (en) * 2018-01-19 2018-06-22 北京智能管家科技有限公司 Semantic understanding method, apparatus, equipment and the storage medium of dynamic human body posture
CN108363966A (en) * 2018-01-30 2018-08-03 广东工业大学 A kind of interior fall detection method and system
CN109008166A (en) * 2018-08-23 2018-12-18 蔡岳林 A kind of intelligence school bag system and management method
CN109446895A (en) * 2018-09-18 2019-03-08 中国汽车技术研究中心有限公司 A kind of pedestrian recognition method based on human body head feature
CN109961038A (en) * 2019-03-20 2019-07-02 苏州浪潮智能科技有限公司 A kind of children's safety monitoring method and system based on computerized algorithm
CN110477925A (en) * 2019-08-23 2019-11-22 广东省智能制造研究所 A kind of fall detection for home for the aged old man and method for early warning and system

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103517042A (en) * 2013-10-17 2014-01-15 吉林大学 Nursing home old man dangerous act monitoring method
CN104320618A (en) * 2014-10-23 2015-01-28 西北农林科技大学 Calf state monitoring device and method based on behavior characteristics spectrum linkage
CN105448041A (en) * 2016-01-22 2016-03-30 苏州望湖房地产开发有限公司 A human body falling intelligent control system and method
CN205582161U (en) * 2016-04-18 2016-09-14 讯之美物联网服务有限公司 System of internet of things
US20170358195A1 (en) * 2016-06-14 2017-12-14 Board Of Trustees Of The University Of Arkansas Real-Time Awareness of Environmental Hazards for Fall Prevention
CN106991787A (en) * 2017-06-07 2017-07-28 京东方科技集团股份有限公司 Intelligent closestool and the safety monitoring system based on intelligent closestool
CN108197589A (en) * 2018-01-19 2018-06-22 北京智能管家科技有限公司 Semantic understanding method, apparatus, equipment and the storage medium of dynamic human body posture
CN108363966A (en) * 2018-01-30 2018-08-03 广东工业大学 A kind of interior fall detection method and system
CN109008166A (en) * 2018-08-23 2018-12-18 蔡岳林 A kind of intelligence school bag system and management method
CN109446895A (en) * 2018-09-18 2019-03-08 中国汽车技术研究中心有限公司 A kind of pedestrian recognition method based on human body head feature
CN109961038A (en) * 2019-03-20 2019-07-02 苏州浪潮智能科技有限公司 A kind of children's safety monitoring method and system based on computerized algorithm
CN110477925A (en) * 2019-08-23 2019-11-22 广东省智能制造研究所 A kind of fall detection for home for the aged old man and method for early warning and system

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113114548A (en) * 2020-07-07 2021-07-13 德能森智能科技（成都）有限公司 Terminal management method and system based on privacy management
CN112167074A (en) * 2020-10-14 2021-01-05 北京科技大学 Automatic feeding device based on pet face recognition
CN112601054A (en) * 2020-12-14 2021-04-02 珠海格力电器股份有限公司 Pickup picture acquisition method and device, storage medium and electronic equipment
CN112686199A (en) * 2021-01-07 2021-04-20 深圳市海雀科技有限公司 Method and system for carrying out safety alarm through encrypted image
CN113393652A (en) * 2021-06-18 2021-09-14 国能神东煤炭集团有限责任公司 Alarm method, system, device and storage medium
CN114035603A (en) * 2021-08-08 2022-02-11 中国航空工业集团公司沈阳飞机设计研究所 Dynamic detection and alarm method for threat area of unmanned aerial vehicle
CN114035603B (en) * 2021-08-08 2023-11-28 中国航空工业集团公司沈阳飞机设计研究所 Unmanned aerial vehicle threat zone dynamic detection and alarm method

Similar Documents

Publication Publication Date Title
CN111292504A (en) Method and system for carrying out safety alarm through image identification
WO2019120029A1 (en) Intelligent screen brightness adjustment method and apparatus, and storage medium and mobile terminal
CN108399349B (en) Image recognition method and device
US9779527B2 (en) Method, terminal device and storage medium for processing image
WO2017054605A1 (en) Picture processing method and device
WO2019080797A1 (en) Living body detection method, terminal, and storage medium
WO2019033386A1 (en) Fingerprint image acquisition method and device, and terminal device
CN109190509B (en) Identity recognition method, device and computer readable storage medium
CN110705365A (en) Human body key point detection method and device, electronic equipment and storage medium
CN107566749B (en) Shooting method and mobile terminal
CN108345845B (en) Image sensor, lens module, mobile terminal, face recognition method and device
CN112446255A (en) Video image processing method and device
CN107749046B (en) Image processing method and mobile terminal
CN108989678A (en) A kind of image processing method, mobile terminal
CN111243105B (en) Augmented reality processing method and device, storage medium and electronic equipment
WO2020088092A1 (en) Key point position determining method and apparatus, and electronic device
CN112257552B (en) Image processing method, device, equipment and storage medium
CN110245607B (en) Eyeball tracking method and related product
CN111339831A (en) Lighting lamp control method and system
CN109688325A (en) A kind of image display method and terminal device
CN109033913A (en) A kind of recognition methods of identification code and mobile terminal
CN110807769A (en) Image display control method and device
CN109639981B (en) Image shooting method and mobile terminal
CN110365906A (en) Image pickup method and mobile terminal
CN112511743B (en) Video shooting method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20200616