Method, device and equipment for privacy shielding by data encryption and optical shielding
Through data encryption and optical occlusion technology, the location of private information in infant videos collected by AI care equipment is detected and encoded, which solves the problem of private information leakage in the existing technology, and achieves the dual goals of privacy shielding and video image integrity.
Patent Information
- Application Number
- CN202210912152.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-07-29
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2042-07-29
AI Technical Summary
When collecting video images of infants and young children, existing AI care equipment often contains privacy information from other people, resulting in privacy leakage and affecting user experience.
Using data encryption and optical occlusion methods, by obtaining video images collected by the camera and thermal imaging images collected by infrared sensors, detecting and encoding the location of privacy information, generating encrypted frame header information, replacing the original frame header, and realizing the shielding of privacy information.
It effectively blocks private information in video images, avoids information leakage, improves user experience, and does not destroy the integrity of video images.
Smart Images

Figure CN115426498B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of video data processing, and in particular to a method, a device and an apparatus for performing privacy shielding by using data encryption and optical shielding. Background Art
[0002] As the urbanization process continues to deepen, young parents are unable to take care of their infants and young children themselves, so they have to ask the elderly to take care of them instead. This results in young parents being unable to pay better attention to the growth of their infants and young children. To solve this problem, young parents choose to use AI care equipment to assist in the care of their infants and young children.
[0003] However, in the prior art, AI care equipment mainly determines the status of infants and young children by performing target analysis based on real-time video images of infant scenes collected by cameras; however, the care of infants and young children cannot be separated from the care of guardians. At the same time, other people often appear in the infant environment, which leads to the video images of infant scenes collected by AI care equipment often containing the privacy information of other people. Whether the video images are transmitted back to the server for technical analysis or disseminated on other platforms, privacy leakage will occur, which not only causes visual discomfort to viewers, but also brings a bad experience to people involved in privacy. Summary of the invention
[0004] In view of this, an embodiment of the present invention provides a method, device and equipment for privacy shielding using data encryption and optical occlusion, so as to solve the technical problem that the video images of infant products collected by existing AI care devices involve the privacy information of other people, resulting in a poor user experience.
[0005] The technical solution adopted by the present invention is:
[0006] The present invention provides a method for privacy shielding by using data encryption and optical shielding, the method comprising:
[0007] S1: Obtain a first basic video corresponding to the privacy information to be shielded in a first type of image source, and a first image set consisting of frame images corresponding to the acquisition time sequence of each frame image of the first basic video in a second type of image source;
[0008] S2: according to the position information corresponding to the privacy information in each frame image of the first image set, encode and encrypt the privacy information corresponding to each position information in each frame image of the first basic video and the original frame header information to obtain each target frame header information of each frame image of the first basic video;
[0009] S3: replacing original frame header information of each frame image in the first basic video with each target frame header information, to obtain a target video in which the privacy information is shielded in an encrypted manner;
[0010] Among them, the first type of image source is the video image of the infant care scene collected in real time by the camera under the first lens, and the second type of image source is the thermal imaging image collected by the infrared sensor.
[0011] Preferably, the S1 includes:
[0012] S101: Acquire a basic video of an infant sleeping and an image set of the second type of image source corresponding to the acquisition timing of each frame image of the basic video;
[0013] S102: performing target detection on each frame image of the basic video to obtain the first basic video composed of each target frame image containing privacy information;
[0014] S103: Marking each detection target corresponding to the privacy information in each frame image corresponding to the image set according to the position information corresponding to the privacy information in each target frame image, to obtain the first image set.
[0015] Preferably, the S102 includes:
[0016] S1021: Acquire the basic video for real-time care of infants and young children using the first type of image source;
[0017] S1022: performing privacy information detection on each frame image of the basic video, and generating a shielding signal according to the privacy information;
[0018] S1023: Optically shielding a first lens for collecting the first type of image source according to the shielding signal to obtain the first basic video corresponding to each target frame image of the first type of image source containing privacy information.
[0019] Preferably, the S1 includes:
[0020] S111: Acquire a first interval time and a second interval time for performing target detection on the basic video for real-time infant care using a first type of image source, wherein the first interval time is smaller than the second interval time;
[0021] S122: performing other living target detection of non-target infants and young children on the basic video according to the first interval time to obtain a first frame target image;
[0022] S123: After obtaining the first frame target image, continue to detect other living objects other than the target infants and young children on the basic video at the second interval time to obtain the last frame target image;
[0023] S124: Obtain the first basic video according to the first frame target image and the last frame target image.
[0024] Preferably, the S2 includes:
[0025] S21: Acquire the basic video of real-time care of infants and young children using the first type of image source;
[0026] S22: Detecting other living objects other than the target infants and young children on each frame image of the basic video to obtain a first frame target image containing private information of other living objects;
[0027] S23: obtaining first position information corresponding to the privacy information in the first target image according to the initial position information of the privacy information in the first target image, wherein the first target image is an image in the first image set that is acquired at the same time as the first target image;
[0028] S24: Obtaining, according to the first position information, position information corresponding to the private information in each frame image of the first image set.
[0029] Preferably, after S3, the step further includes:
[0030] S4: Obtaining frame header information of each frame of the first basic video;
[0031] S5: determining each target frame image containing privacy information according to each frame header information;
[0032] S6: According to the privacy information in each frame header information, shield and play the image corresponding to the privacy information in each target frame image.
[0033] Preferably, the S6 includes:
[0034] S61: Obtaining category information and location information of each of the private information;
[0035] S62: screening each of the target frame images according to each of the category information to obtain each frame image to be shielded;
[0036] S63: performing masking processing on each of the frame images to be masked and the image of the corresponding position information, obtaining each local masking image corresponding to each of the frame images to be masked, and decoding and playing them.
[0037] The present invention further provides a device for performing privacy shielding by using data encryption and optical shielding based on any one of the above items, comprising:
[0038] Data acquisition module: used to acquire a first basic video corresponding to the privacy information to be shielded in the first type of image source, and a first image set consisting of each frame image in the second type of image source corresponding to the acquisition time sequence of each frame image of the first basic video;
[0039] A data processing module: used for encoding and encrypting the privacy information corresponding to each position information in each frame image of the first basic video and the original frame header information according to the position information corresponding to the privacy information in each frame image of the first image set, so as to obtain each target frame header information of each frame image of the first basic video;
[0040] A privacy shielding module: used to replace the original frame header information of each frame image in the first basic video with each target frame header information, so as to obtain a target video shielding the privacy information in an encrypted manner;
[0041] Among them, the first type of image source is the video image of the infant care scene collected in real time by the camera under the first lens, and the second type of image source is the thermal imaging image collected by the infrared sensor.
[0042] The present invention also provides an electronic device, comprising: at least one processor, at least one memory, and computer program instructions stored in the memory, and when the computer program instructions are executed by the processor, any of the above-mentioned methods is implemented.
[0043] The present invention also provides a medium on which computer program instructions are stored, and when the computer program instructions are executed by a processor, any of the above-mentioned methods is implemented.
[0044] In summary, the beneficial effects of the present invention are as follows:
[0045] The present invention provides a method, device and equipment for privacy shielding by data encryption and optical occlusion, which obtain a first basic video corresponding to a first type of image source containing privacy information and a first image set corresponding to a second type of image source, wherein the acquisition timing of each frame image of the first type of image source and the second type of image source corresponds to each other, the first type of image source is a video image, and the second type of image source is a thermal imaging image; when privacy information is detected in an infant care scene, the location of the privacy information is determined in the second type of image source, and then the image data corresponding to the location of the privacy information in the first type of image source and the original frame header information are encoded and encrypted by using the feature that the detection target has the same position in the first type of image source and the second type of image source, so as to generate new target frame header information for each frame image in the first basic image, thereby converting the first basic video into a new image. The privacy information is encrypted and shielded by encoding it together with the frame header information. When the first basic video is played, each time the frame header information is decrypted, the image data of the frame image containing the privacy information, specifically the privacy information category and position of the frame image, can be obtained, so that the image area corresponding to the position can be selected not to be decoded or mosaics can be added to complete the privacy information shielding. The present invention determines the location of the privacy information of the first category image source based on the second category image source, thereby shielding the privacy information of each frame image in the first basic video of the first category image source, without the need to detect and analyze each frame of the video image, which can not only preserve the video image of the first category image source, but also achieve the shielding of privacy information, and there is no need to worry about information leakage caused by the privacy information detection link of the first basic video. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the drawings required for use in the embodiment of the present invention will be briefly introduced below. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work, and these are all within the protection scope of the present invention.
[0047] Figure 1 This is a flow chart of a method for performing privacy shielding by using data encryption and optical shielding in Embodiment 1 of the present invention;
[0048] Figure 2 This is a schematic diagram of a process for obtaining a first image set in Embodiment 1 of the present invention;
[0049] Figure 3 This is a schematic diagram of a process for obtaining a first basic video in Embodiment 1 of the present invention;
[0050] Figure 4 This is a schematic diagram of a process for obtaining the location of private information in Embodiment 1 of the present invention;
[0051] Figure 5It is a schematic diagram of the structure of a device for performing privacy shielding by using data encryption and optical shielding in Embodiment 2 of the present invention;
[0052] Figure 6 Schematic diagram of the structure of an electronic device in Embodiment 3 of the present invention. DETAILED DESCRIPTION
[0053] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution in the embodiment of the present invention will be clearly and completely described in conjunction with the drawings in the embodiment of the present invention. It should be noted that, in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. In the description of the present invention, it should be understood that the orientation or position relationship indicated by the terms "center", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc. is based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. Moreover, the term "include", "comprise" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such a process, method, article or device. In the absence of further restrictions, the elements defined by the phrase "comprising..." do not exclude the existence of other identical elements in the process, method, article or device comprising the elements. If there is no conflict, the various features of the present invention and the embodiments can be combined with each other, all within the protection scope of the present invention.
[0054] Example 1
[0055] See also Figure 1 , Figure 1 A method for privacy shielding by using data encryption and optical shielding in Embodiment 1 of the present invention comprises:
[0056] S1: Obtain a first basic video corresponding to the privacy information to be shielded in a first type of image source, and a first image set consisting of frame images corresponding to the acquisition time sequence of each frame image of the first basic video in a second type of image source;
[0057] S2: according to the position information corresponding to the privacy information in each frame image of the first image set, encode and encrypt the privacy information corresponding to each position information in each frame image of the first basic video and the original frame header information to obtain each target frame header information of each frame image of the first basic video;
[0058] S3: replacing original frame header information of each frame image in the first basic video with each target frame header information, to obtain a target video in which the privacy information is shielded in an encrypted manner;
[0059] Among them, the first type of image source is the video image of the infant care scene collected in real time by the camera under the first lens, and the second type of image source is the thermal imaging image collected by the infrared sensor.
[0060] Specifically, the first type of image source and the second type of image source are used to provide real-time care for infants and young children. The first type of image source is a video image, and the second type of image source is a thermal imaging image. The acquisition timing of each frame of the first type of image source and the second type of image source is one-to-one corresponding. It can be understood that when the A-th frame image in the first image set is acquired at the same time as the A-th frame image in the first basic video, and the screen area is the same; when there is privacy information at position B of the A-th frame image in the first image set, the same privacy information also exists at position B of the A-th frame image in the first basic video; the privacy information of each frame image of the first basic video is determined by using the location of the privacy information in the first image set; thereby the privacy information and the frame header information are jointly encoded and encrypted , obtain new target frame header information containing privacy information, thereby obtaining a target video in which the privacy information is recorded in the frame header of each frame image, preferably recording the category information and location information of the privacy information in the frame header, rather than directly recording all information of the privacy information including image data in the frame header, to avoid causing the frame header data to be too large; by using the location information of the privacy information in the second image set to replace the privacy information detection of each frame image of the first basic video, and then encoding and encrypting the privacy information and the frame header to complete the privacy information shielding of the first basic video, it can not only ensure the integrity of the collected first basic video, but also avoid the leakage of privacy information, and at the same time, there is no need to worry about the information leakage caused by the privacy information detection link of the first basic video. Among them, after determining the first image set containing privacy information, the other image frames of the second image source can be deleted to release storage space; it is beneficial to reduce the frequency of data erasure in the storage area during cyclic storage and increase the service life of the storage medium.
[0061] In one embodiment, see Figure 2 , the S1 comprises:
[0062] S101: Acquire a basic video of an infant sleeping and an image set of the second type of image source corresponding to the acquisition timing of each frame image of the basic video;
[0063] S102: performing target detection on each frame image of the basic video to obtain the first basic video composed of each target frame image containing privacy information;
[0064] S103: Marking each detection target corresponding to the privacy information in each frame image corresponding to the image set according to the position information corresponding to the privacy information in each target frame image, to obtain the first image set.
[0065] Specifically, at the camera end, the video image of the camera and the thermal imaging image of the thermal imaging sensor are used to perform real-time monitoring of the area where the target infant is located, and target detection is performed on the basic video corresponding to the first type of image source collected by the camera. When privacy information is detected in the image, the first frame target image with the privacy information in the basic video is obtained, and the first frame target image is recorded as the first frame image of the first basic video, and the image frames with privacy information corresponding to the first image source collected subsequently are used as other frame images of the first basic video; the position information of the privacy information in each frame image of the first basic video is used to mark the detected targets in each frame image corresponding to the image set, that is, the heat source targets corresponding to the privacy information are marked in each frame image corresponding to the image set, so as to obtain a first image set consisting of each frame image of the second type of image source marked with privacy information.
[0066] In one embodiment, the S102 includes:
[0067] S1021: Acquire the basic video for real-time care of infants and young children using the first type of image source;
[0068] S1022: performing privacy information detection on each frame image of the basic video, and generating a shielding signal according to the privacy information;
[0069] S1023: Optically shielding a first lens for collecting the first type of image source according to the shielding signal to obtain the first basic video corresponding to each target frame image of the first type of image source containing privacy information.
[0070] Specifically, the privacy information is other target persons other than non-target infants and young children, including at least one of the following: other infants and young children, caregivers of target infants, etc. The AI care device uses the first category of image sources and the second category of image sources to care for infants and young children at the same time. When there is no privacy information, the first category of image sources are used as the main source and the second category of image sources are used as the auxiliary source to care for infants and young children. When privacy information is present, the second category of image sources are used as the main source and the first category of image sources are used as the auxiliary source to care for infants and young children. When the basic video is analyzed for privacy information, a shielding signal for shielding the privacy information is generated. The signal optically shields the first lens of the camera used to collect the first type of image source. The optical shielding method is to switch the lens of the camera of the AI care device from the first lens to the second lens. The first lens is a lens with normal focal length, and the second lens is a near-focus lens. The first lens collects a clear image of the area where the infant is located, and the second lens collects a blurred image of the area where the infant is located. However, a cleaned image will be collected at a close distance of the second lens, that is, all frame images after the privacy information is detected for the first time in the first basic video are blurred images collected under the second lens, thereby protecting privacy from the video screen.
[0071] In one embodiment, see Figure 3 , the S1 comprises:
[0072] S111: Acquire a first interval time and a second interval time for performing target detection on the basic video for real-time infant care using a first type of image source, wherein the first interval time is smaller than the second interval time;
[0073] S122: performing other living target detection of non-target infants and young children on the basic video according to the first interval time to obtain a first frame target image;
[0074] S123: After obtaining the first frame target image, continue to detect other living objects other than the target infants and young children on the basic video at the second interval time to obtain the last frame target image;
[0075] S124: Obtain the first basic video according to the first frame target image and the last frame target image.
[0076] Specifically, target detection is performed on each frame image of the basic video, and a frame sampling detection method is adopted, so as to reduce the computer computing power required for privacy information screening. Specifically, a first interval time and a second interval time are set to perform frame sampling detection on the basic video. Before the privacy information is detected, the first interval time is used to detect each frame image of the basic video until the image corresponding to the privacy information is detected for the first time, which is recorded as the first frame target image. Then, frame sampling detection is continued for each frame image of the first type of image source collected subsequently according to the second interval time, until the last frame target image corresponding to the privacy information is detected for the last time, all images between the first frame target image and the last frame target image are recorded as each target frame image, and all target frame images except the first frame target image are recorded as other frame target images. The frame sampling detection method can reduce the computing power consumption of the computer. The first interval time is less than the second interval time, which can further speed up the screening of each target frame image.
[0077] In one embodiment, the first interval time and the second interval time are integer multiples of a unit time, and the unit time is the interval time between two adjacent frames of images.
[0078] In one embodiment, if the first interval time is n times the unit time, and n is a positive integer greater than or equal to 1, the S122 includes:
[0079] Performing other living object detection of non-target infants and young children on the basic video according to the first time interval to obtain a first target frame image;
[0080] If n is equal to 1, the first target frame image is the first frame target image;
[0081] If n is equal to 2, the previous frame image of the first target frame image is used as the first frame target image;
[0082] If n is greater than 2, target detection is performed on the first target frame image and other frame images between the detection frame image selected in the previous frame at a third interval time to obtain the first frame target image, wherein the third interval time is less than or equal to 2 unit times.
[0083] Specifically, when the first interval time is a unit time, that is, each frame image of the basic video is checked to obtain the first target frame image, which is also the first frame target image. When the first interval time is 2 unit times, that is, the basic video is detected once every frame image interval, which can reduce the amount of data processing and improve detection efficiency; using the previous frame of the first detected target frame image as the first frame target image can avoid incomplete privacy information, and no secondary detection is required, saving computer resources; when the first interval time is greater than 2 unit times, the other frame images between the last two frame images detected by the first interval time are subjected to frame sampling detection at a third interval time, and the third interval time is preferably 1 unit time or 2 unit times, so as to determine the first frame target image; by setting the third interval time, after quickly completing the detection of each frame image without privacy information, the last frame target image of a small range of multiple frames can be located, further saving computer resources and improving detection efficiency.
[0084] In one embodiment, if the first interval time is n times the unit time, and n is a positive integer greater than or equal to 1, the S123 includes:
[0085] Performing other living object detection of non-target infants and young children on the basic video according to the second interval time to obtain a last target frame image;
[0086] If n is equal to 1, the last target frame image is the last target frame image;
[0087] If n is equal to 2, the next frame image of the last target frame image is used as the last frame target image;
[0088] If n is greater than 2, target detection is performed on the last target frame image and the other image frames between the next detection frame image selected at the second interval time at a third interval time to obtain the last frame target image, wherein the third interval time is less than or equal to 2 unit times.
[0089] Specifically, when the second interval time is a unit time, that is, each frame image of the basic video is checked to obtain the last target frame image, and the last target frame image is also the last frame target image. When the second interval time is 2 unit time, that is, the basic video is detected once every frame image interval, which can reduce the amount of data processing and improve detection efficiency; the next frame after the last target frame image detected is used as the last frame target image, which can avoid incomplete privacy information, and does not require secondary detection, saving computer resources; when the second interval time is greater than 2 unit time, the last target frame image in which the privacy information is detected in the second interval time and the interval between the last target frame image and the last target frame image are obtained. The next detection frame image corresponding to the second interval time is recorded as the reference frame image. For example, if the last detected privacy information is the 180th frame image and the second interval time is 10 unit times, then the reference frame image is the 190th frame image. The other frame images between the last target frame image and the reference frame image are subjected to frame sampling detection at the third interval time. The third interval time is preferably 1 unit time or 2 unit times, so as to determine the last frame target image. By setting the third interval time, after quickly completing the detection of each frame image without privacy information, the last frame target image can be located for multiple frame images in a small range, thereby further saving computer resources and improving detection efficiency.
[0090] In one embodiment, see Figure 4 , said S2 comprises:
[0091] S21: Acquire the basic video of real-time care of infants and young children using the first type of image source;
[0092] S22: Detecting other living objects other than the target infants and young children on each frame image of the basic video to obtain a first frame target image containing private information of other living objects;
[0093] S23: obtaining first position information corresponding to the privacy information in the first target image according to the initial position information of the privacy information in the first target image, wherein the first target image is an image in the first image set that is acquired at the same time as the first target image;
[0094] S24: Obtaining, according to the first position information, position information corresponding to the private information in each frame image of the first image set.
[0095] Specifically, at the camera end, target detection is performed on each frame of the basic video captured by the camera, and the first frame of the target image that includes other living things in addition to the target infant in each frame is screened out. The other living things include: other infants, other family members, etc., and the first position information corresponding to the privacy information in the first target image is obtained according to the initial position information corresponding to the privacy information in the first target image. The first target image is a thermal imaging image in the first image set with the same acquisition time as the first target image. Therefore, the imaging position of the person corresponding to the privacy information is determined in the first image set, and the position of the privacy information in each frame of the first image set is obtained through the imaging position of the person with the privacy information in each frame. The position of the privacy information in each frame of the first image set corresponds to the position of the privacy information in each frame of the first basic video. Therefore, after knowing the position of the privacy information in the first image set, there is no need to perform privacy information detection on each frame of the first basic video, and the position of the privacy information in each frame of the first basic video can still be determined, thereby shielding.
[0096] In one embodiment, after S3, the method further includes:
[0097] S4: Obtaining frame header information of each frame of the first basic video;
[0098] S5: determining each target frame image containing privacy information according to each frame header information;
[0099] S6: According to the privacy information in each frame header information, shield and play the image corresponding to the privacy information in each target frame image.
[0100] Specifically, the App receives a first basic video of infant care transmitted from the camera. When playing the first basic video, when decoding and decrypting the frame header file, the image corresponding to the privacy information in the header file is shielded and then played; the shielding method includes one of the following: mosaic, blur processing, etc.
[0101] In one embodiment, the S6 includes:
[0102] S61: Obtaining category information and location information of each of the private information;
[0103] S62: screening each of the target frame images according to each of the category information to obtain each frame image to be shielded;
[0104] S63: performing masking processing on each of the frame images to be masked and the image of the corresponding position information, obtaining each local masking image corresponding to each of the frame images to be masked, and decoding and playing them.
[0105] Specifically, when playing a video, privacy information can be selectively blocked according to category information. For example, if the privacy information is the presence of other infants and young children in the monitoring area, you can choose not to block it, or you can choose to block part of it. For example, when playing on the App side (that is, the caregiver plays directly), you can choose not to block it and play it with the full picture. When playing at other locations (server side, other platforms), you can choose to block the privacy information. This allows differentiated playback of videos with different functional requirements and improves playback flexibility.
[0106] The present invention provides a method for privacy shielding by data encryption and optical occlusion, wherein a first basic video corresponding to a first type of image source containing privacy information and a first image set corresponding to a second type of image source are obtained, wherein the acquisition timing of each frame image of the first type of image source and the second type of image source corresponds to each other, the first type of image source is a video image, and the second type of image source is a thermal imaging image; when privacy information is detected in an infant care scene, the location of the privacy information is determined in the second type of image source, and then, by using the feature that the detection target has the same position in the first type of image source and the second type of image source, the image data corresponding to the location of the privacy information in the first type of image source and the original frame header information are encoded and encrypted, and new target frame header information of each frame image in the first basic image is generated, thereby the privacy of the first basic video is shielded. The information is encrypted and shielded by encoding it together with the frame header information. When the first basic video is played, each time the frame header information is decrypted, image data containing privacy information in the frame image will be obtained, specifically, the privacy information category and position of the frame image, so that the image area corresponding to the position can be selected not to be decoded or mosaics can be added to complete the privacy information shielding. The present invention determines the location of the privacy information of the first category of image sources based on the second category of image sources, thereby shielding the privacy information of each frame image in the first basic video of the first category of image sources, without the need to detect and analyze each frame of the video image, which can not only preserve the video image of the first category of image sources, but also achieve the shielding of privacy information, and there is no need to worry about information leakage caused by the privacy information detection link of the first basic video.
[0107] Example 2
[0108] The present invention also provides an infant care device based on optical shielding of privacy information, see Figure 5 ,include:
[0109] Data acquisition module: used to acquire a first basic video corresponding to the privacy information to be shielded in the first type of image source, and a first image set consisting of each frame image in the second type of image source corresponding to the acquisition time sequence of each frame image of the first basic video;
[0110] A data processing module: used for encoding and encrypting the privacy information corresponding to each position information in each frame image of the first basic video and the original frame header information according to the position information corresponding to the privacy information in each frame image of the first image set, so as to obtain each target frame header information of each frame image of the first basic video;
[0111] A privacy shielding module: used to replace the original frame header information of each frame image in the first basic video with each target frame header information, so as to obtain a target video shielding the privacy information in an encrypted manner;
[0112] Among them, the first type of image source is the video image of the infant care scene collected in real time by the camera under the first lens, and the second type of image source is the thermal imaging image collected by the infrared sensor.
[0113] In one embodiment, the data acquisition module S1 includes:
[0114] Image acquisition unit S101: acquiring a basic video of an infant sleeping and an image set of the second type of image source corresponding to the acquisition timing of each frame image of the basic video;
[0115] Image detection unit S102: performing target detection on each frame image of the basic video to obtain the first basic video composed of each target frame image containing privacy information;
[0116] Image processing unit S103: Marking each detection target corresponding to the privacy information in each frame image corresponding to the image set according to the position information corresponding to the privacy information in each target frame image, to obtain the first image set.
[0117] In one embodiment, the image detection unit S102 includes:
[0118] The original image acquisition unit S1021: acquires the basic video of real-time infant care using the first type of image source;
[0119] The shielding signal unit S1022 performs privacy information detection on each frame image of the basic video, and generates a shielding signal according to the privacy information;
[0120] Shielding unit S1023: optically shielding the first lens used for collecting the first type of image source according to the shielding signal, to obtain the first basic video corresponding to each target frame image of the first type of image source containing privacy information.
[0121] In one embodiment, the data acquisition module S1 includes:
[0122] Sampling parameter acquisition unit S111: acquiring a first interval time and a second interval time for performing target detection on the basic video of real-time infant care using a first type of image source, wherein the first interval time is smaller than the second interval time;
[0123] First frame image unit S122: performing other living object detection of non-target infants and young children on the basic video according to the first interval time to obtain a first frame target image;
[0124] Last frame image unit S123: after obtaining the first frame target image, continue to detect other living objects other than the target infants and young children on the basic video at the second interval time to obtain a last frame target image;
[0125] First basic video unit S124: obtain the first basic video according to the first frame target image and the last frame target image.
[0126] In one embodiment, the data processing module S2 includes:
[0127] The first image acquisition unit S21 is used to acquire the basic video of real-time infant care using the first type of image source;
[0128] Target detection unit S22: Detecting other living targets other than the target infant on each frame image of the basic video, and obtaining a first frame target image containing privacy information of other living targets;
[0129] Position mapping unit S23: obtaining first position information corresponding to the privacy information in the first target image according to the initial position information of the privacy information in the first target image, wherein the first target image is an image in the first image set that is acquired at the same time as the first target image;
[0130] The privacy information transfer unit S24 obtains the position information corresponding to the privacy information in each frame image of the first image set according to the first position information.
[0131] In one embodiment, it further includes:
[0132] A frame header information acquisition module: acquires frame header information of each frame image of the first basic video;
[0133] A privacy information confirmation module: determining each target frame image containing privacy information according to each frame header information;
[0134] The shielded playback module is configured to shield and play the image corresponding to the privacy information in each target frame image according to the privacy information in each frame header information.
[0135] In one embodiment, the frame header information acquisition module includes:
[0136] Privacy information unit: obtains category information and location information of each privacy information;
[0137] An information shielding and screening unit is configured to screen each of the target frame images according to each of the category information to obtain each frame image to be shielded;
[0138] The shielding processing unit performs shielding processing on each of the frame images to be shielded and the image of the corresponding position information, and obtains each local shielding image corresponding to each of the frame images to be shielded for decoding and playback.
[0139] The present invention provides an infant care device based on optically shielding privacy information, which obtains a first basic video corresponding to a first type of image source containing privacy information and a first image set corresponding to a second type of image source, wherein the acquisition timing of each frame image of the first type of image source and the second type of image source corresponds to each other one by one, the first type of image source is a video image, and the second type of image source is a thermal imaging image; when privacy information is detected in an infant care scene, the position of the privacy information is determined in the second type of image source, and then, by using the feature that the position of the detection target in the first type of image source and the second type of image source is consistent, the image data corresponding to the position of the privacy information in the first type of image source and the original frame header information are encoded and encrypted, and new target frame header information of each frame image in the first basic image is generated, thereby the privacy of the first basic video is shielded. The information is encrypted and shielded by encoding it together with the frame header information. When the first basic video is played, each time the frame header information is decrypted, image data containing privacy information in the frame image will be obtained, specifically, the privacy information category and position of the frame image, so that the image area corresponding to the position can be selected not to be decoded or mosaics can be added to complete the privacy information shielding. The present invention determines the location of the privacy information of the first category of image sources based on the second category of image sources, thereby shielding the privacy information of each frame image in the first basic video of the first category of image sources, without the need to detect and analyze each frame of the video image, which can not only preserve the video image of the first category of image sources, but also achieve the shielding of privacy information, and there is no need to worry about information leakage caused by the privacy information detection link of the first basic video.
[0140] Example 3
[0141] The present invention provides an electronic device and a medium, such as Figure 6 As shown, the system comprises at least one processor, at least one memory and computer program instructions stored in the memory.
[0142] Specifically, the above-mentioned processor may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of an embodiment of the present invention, and the electronic device includes at least one of the following: a camera, a mobile device with a camera, and a wearable device with a camera.
[0143] The memory may include a large capacity memory for data or instructions. By way of example and not limitation, the memory may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. Where appropriate, the memory may include a removable or non-removable (or fixed) medium. Where appropriate, the memory may be inside or outside a data processing device. In a particular embodiment, the memory is a non-volatile solid-state memory. In a particular embodiment, the memory includes a read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM) or a flash memory or a combination of two or more of these.
[0144] The processor reads and executes computer program instructions stored in the memory to implement any one of the target detection privacy video transmission and playback methods in the first embodiment described above.
[0145] In one example, the electronic device may further include a communication interface and a bus, wherein the processor, the memory, and the communication interface are connected via the bus and communicate with each other.
[0146] The communication interface is mainly used to implement communication between the modules, devices, units and / or equipment in the embodiments of the present invention.
[0147] Bus includes hardware, software or both, and the parts of electronic equipment are coupled to each other.For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In suitable cases, bus may include one or more buses. Although the embodiment of the present invention describes and shows a specific bus, the present invention considers any suitable bus or interconnection.
[0148] In summary, the embodiments of the present invention provide a method, apparatus and device for privacy shielding by data encryption and optical occlusion, wherein a first basic video corresponding to a first type of image source containing privacy information and a first image set corresponding to a second type of image source are obtained, and the acquisition timing of each frame image of the first type of image source and the second type of image source correspond one to one, the first type of image source is a video image, and the second type of image source is a thermal imaging image; when privacy information is detected in an infant care scene, the location of the privacy information is determined in the second type of image source, and then the image data corresponding to the location of the privacy information in the first type of image source and the original frame header information are encoded and encrypted by using the feature that the detection target has the same position in the first type of image source and the second type of image source, so as to generate new target frame header information for each frame image in the first basic image, thereby converting the first The privacy information of the basic video is encrypted and shielded by encoding it together with the frame header information. When the first basic video is played, each time the frame header information is decrypted, the image data of the frame image containing the privacy information, specifically the privacy information category and position of the frame image, can be obtained, so that the image area corresponding to the position can be selected not to be decoded or mosaics can be added to complete the privacy information shielding. The present invention determines the location of the privacy information of the first category of image sources based on the second category of image sources, thereby shielding the privacy information of each frame image in the first basic video of the first category of image sources, without the need to detect and analyze each frame of the video image, which can not only preserve the video image of the first category of image sources, but also achieve the shielding of privacy information, and there is no need to worry about information leakage caused by the privacy information detection link of the first basic video.
[0149] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.
[0150] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present invention are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.
[0151] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for privacy shielding by data encryption and optical shielding, characterized in that: The method comprises: S1: Obtain a first basic video corresponding to the privacy information to be shielded in a first type of image source, and a first image set consisting of frame images corresponding to the acquisition time sequence of each frame image of the first basic video in a second type of image source; S2: according to the position information corresponding to the privacy information in each frame image of the first image set, encode and encrypt the privacy information corresponding to each position information in each frame image of the first basic video and the original frame header information to obtain each target frame header information of each frame image of the first basic video; S3: replacing original frame header information of each frame image in the first basic video with each target frame header information, to obtain a target video in which the privacy information is shielded in an encrypted manner; The first type of image source is a video image of an infant care scene captured in real time by a camera under a first lens, and the second type of image source is a thermal imaging image captured by an infrared sensor; The S2 includes: S21: Acquire the basic video of real-time care of infants and young children using the first type of image source; S22: Detecting other living objects other than the target infants and young children on each frame image of the basic video to obtain a first frame target image containing private information of other living objects; S23: obtaining first position information corresponding to the privacy information in the first target image according to the initial position information of the privacy information in the first target image, wherein the first target image is an image in the first image set that is acquired at the same time as the first target image; S24: Obtaining, according to the first position information, position information corresponding to the private information in each frame image of the first image set.
2. The method for privacy shielding by data encryption and optical shielding according to claim 1, characterized in that: The S1 includes: S101: Acquire a basic video of an infant sleeping and an image set of the second type of image source corresponding to the acquisition timing of each frame image of the basic video; S102: performing target detection on each frame image of the basic video to obtain the first basic video composed of each target frame image containing privacy information; S103: Marking each detection target corresponding to the privacy information in each frame image corresponding to the image set according to the position information corresponding to the privacy information in each target frame image, to obtain the first image set.
3. The method for privacy shielding by data encryption and optical shielding according to claim 2, characterized in that: The S102 includes: S1021: Acquire the basic video for real-time care of infants and young children using the first type of image source; S1022: performing privacy information detection on each frame image of the basic video, and generating a shielding signal according to the privacy information; S1023: Optically shielding a first lens for collecting the first type of image source according to the shielding signal to obtain the first basic video corresponding to each target frame image of the first type of image source containing privacy information.
4. The method for privacy shielding by data encryption and optical shielding according to claim 1, characterized in that: The S1 includes: S111: Acquire a first interval time and a second interval time for performing target detection on the basic video for real-time infant care using a first type of image source, wherein the first interval time is smaller than the second interval time; S122: performing other living target detection of non-target infants and young children on the basic video according to the first interval time to obtain a first frame target image; S123: After obtaining the first frame target image, continue to detect other living objects other than the target infants and young children on the basic video at the second interval time to obtain the last frame target image; S124: Obtain the first basic video according to the first frame target image and the last frame target image.
5. The method for privacy shielding by data encryption and optical shielding according to any one of claims 1 to 4, characterized in that: The S3 also includes: S4: Obtaining frame header information of each frame of the first basic video; S5: determining each target frame image containing privacy information according to each frame header information; S6: According to the privacy information in each frame header information, shield and play the image corresponding to the privacy information in each target frame image.
6. The method for privacy shielding by data encryption and optical shielding according to claim 5, characterized in that: The S6 includes: S61: Obtaining category information and location information of each of the private information; S62: screening the target frame images according to the category information to obtain the frame images to be shielded; S63: performing masking processing on each of the frame images to be masked and the image of the corresponding position information, obtaining each local masking image corresponding to each of the frame images to be masked, and decoding and playing them.
7. A device for privacy shielding by data encryption and optical shielding, characterized in that: include: Data acquisition module: used to acquire a first basic video corresponding to the privacy information to be shielded in the first type of image source, and a first image set consisting of each frame image in the second type of image source corresponding to the acquisition time sequence of each frame image of the first basic video; A data processing module: used for encoding and encrypting the privacy information corresponding to each position information in each frame image of the first basic video and the original frame header information according to the position information corresponding to the privacy information in each frame image of the first image set, so as to obtain each target frame header information of each frame image of the first basic video; A privacy shielding module: used to replace the original frame header information of each frame image in the first basic video with each target frame header information, so as to obtain a target video with the privacy information shielded in an encrypted manner; The first type of image source is a video image of an infant care scene captured in real time by a camera under a first lens, and the second type of image source is a thermal imaging image captured by an infrared sensor; According to the position information corresponding to the privacy information in each frame image of the first image set, the privacy information corresponding to each position information in each frame image of the first basic video and the original frame header information are encoded and encrypted to obtain each target frame header information of each frame image of the first basic video, including: Acquire the basic video of real-time infant care using the first type of image source; Performing other living target detection of non-target infants on each frame image of the basic video to obtain a first frame target image containing privacy information of other living targets; According to the initial position information of the privacy information in the first frame target image, first position information corresponding to the privacy information in the first target image is obtained, wherein the first target image is an image in the first image set that is acquired at the same time as the first frame target image; The position information corresponding to the private information in each frame image of the first image set is obtained according to the first position information.
8. An electronic device, characterized in that: include: At least one processor, at least one memory and computer program instructions stored in the memory, when the computer program instructions are executed by the processor, implement the method according to any one of claims 1 to 6.
9. A medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 6 is implemented.
