Remote monitoring method for intelligent obstetric ward

Abstract

The invention relates to the technical field of video encryption, and particularly discloses a remote monitoring method for a smart obstetric ward, comprising the following steps: S1, acquiring a monitoring video frame sequence, grouping monitoring video frames, and determining the serial number of the monitoring video frames in the group; s2, establishing a coordinate system, and determining initial coordinates of pixels; grouping the monojective functions, determining serial numbers of the monojective functions in groups, and determining a target x function and a target y function corresponding to the monitoring video frame according to the serial numbers; s3, converting the initial coordinates according to the target x function and the target y function to obtain standard coordinates; and adjusting the position of the pixel according to the standard coordinate to obtain a target video frame, obtaining a target video and sending the target video to a receiving end. According to the method, the video is encrypted by adjusting the pixel position, so that the security of the monitoring video in the transmission process is effectively protected.

Description

Technical Field

[0001] The present invention relates to the technical field of video encryption, and in particular to a remote monitoring method for a smart obstetric ward. Background Art

[0002] Smart obstetric ward refers to a ward environment that uses modern information technology (such as the Internet of Things, big data, artificial intelligence, etc.) to improve the quality and efficiency of obstetric medical services. The monitoring video system is an important part of the smart obstetric ward. Through monitoring video, the hospital can observe the condition of the mothers in the obstetric ward in real time, so as to timely discover potential risks and abnormal changes, and ensure the safety of the mothers during the period of waiting for labor and delivery.

[0003] Since surveillance videos involve a lot of sensitive information, unprotected video data may be stolen or tampered by unauthorized personnel during transmission. Therefore, it is particularly necessary to take effective security measures. By encrypting the video, even if the data is intercepted during transmission, it cannot be interpreted or tampered by a third party, thereby improving the overall security of the surveillance system. Therefore, how to encrypt the video to improve the security of the surveillance system has become an urgent problem to be solved. Summary of the invention

[0004] The purpose of the present invention is to provide a remote monitoring method for a smart obstetric ward to solve the above technical problems.

[0005] The purpose of the present invention can be achieved through the following technical solutions: A remote monitoring method for a smart obstetric ward comprises the following steps: S1: Obtain a surveillance video in the obstetric ward, perform frame processing on the surveillance video to obtain a surveillance video frame sequence, and starting from the first surveillance video frame in the surveillance video frame sequence, group m / 2 consecutive surveillance video frames as the same group, where m is a preset number, and the sequence number of the ath surveillance video frame in the same group is a; S2: Establish a coordinate system with the preset pixel in the monitoring video frame as the origin, determine the coordinates of the pixel in the monitoring video frame, and use it as the initial coordinates, (x i ,y i ) represents the initial coordinates of the i-th pixel; Determine m injective functions, randomly divide the m injective functions into two groups, and name them as x group and y group respectively, record the injective functions in the x group and the y group as x function and y function respectively, one x function corresponds to a sequence number and one y function corresponds to a sequence number, and mark the x function and y function with the same sequence number as the monitoring video frame as the target x function and the target y function respectively; S3: Set the horizontal coordinate x of the initial coordinate of the i-th pixeli Substitute the corresponding target x function to obtain the standard horizontal coordinate X i , the ordinate y of the initial coordinate of the i-th pixel i Substitute the corresponding target y function to obtain the standard ordinate Y i , determine the standard coordinates of the i-th pixel (X i , Y i ); The position of the pixel in the monitoring video frame is adjusted according to the standard coordinates, the adjusted monitoring video frame is used as the target video frame, all the target video frames are synthesized into a target video, and the target video is sent to the receiving end.

[0006] As a further solution of the present invention: the step S3 further includes the following steps: After receiving the target video, the receiving end divides the target video into frames to obtain target video frames, determines the target x function DYX and the target y function DYY corresponding to the target video frames, and determines the inverse function DYX' of the target x function DYX and the inverse function DYY' of the target y function DYY; The standard coordinates are restored to initial coordinates according to the inverse functions DYX' and DYY', and the positions of pixels are adjusted according to the initial coordinates to obtain monitoring video frames, which are synthesized into monitoring videos for playback and / or storage.

[0007] As a further solution of the present invention: in the step S3, when the difference between the standard abscissa and / or standard ordinate of any two standard coordinates is less than the pixel width C, the following steps are performed: The standard coordinate whose standard abscissa and / or standard ordinate difference is less than the pixel width C is used as the undetermined coordinate, and the undetermined coordinate whose distance from the origin is larger is used as the first coordinate, and the first coordinate is adjusted so that the standard abscissa difference between the first coordinate and the second coordinate is equal to the pixel width C and the standard ordinate difference is equal to the pixel width C, and the second coordinate represents the undetermined coordinate whose distance from the origin is closest; Repeat the above steps until the standard abscissa difference between any two standard coordinates is greater than or equal to the pixel width C and the standard ordinate difference is greater than or equal to the pixel width C.

[0008] As a further solution of the present invention: recording the adjustment amount of the first coordinate, the adjustment amount includes a standard horizontal coordinate adjustment amount and a standard vertical coordinate adjustment amount, the horizontal coordinate adjustment amount represents the distance between the standard horizontal coordinate of the first coordinate and the standard vertical coordinate of the first coordinate before adjustment when the standard horizontal coordinate difference between the first coordinate and the second coordinate is equal to the pixel width C, and the vertical coordinate adjustment amount represents the distance between the standard vertical coordinate of the first coordinate and the standard vertical coordinate of the first coordinate before adjustment when the standard vertical coordinate difference between the first coordinate and the second coordinate is equal to the pixel width C, and before restoring the standard coordinate to the initial coordinate according to the inverse functions DYX' and DYY', restoring the first coordinate according to the adjustment amount of the first coordinate; The adjustment amount of the first coordinate and the target video are sent to the receiving end through different transmission paths.

[0009] As a further solution of the present invention: in step S2, the domain of the target x function includes the interval [0, ZB x ] and the independent variable of the target x function belongs to the interval [0, ZB x ], the corresponding function value belongs to the interval [0, ZB x ], ZB x Represents the total pixel width on the x-axis of the coordinate system; The domain of the target y function includes the interval [0, ZB y ] and the independent variable of the target y function belongs to the interval [0, ZB y ], the corresponding function value belongs to the interval [0, ZB y ], ZB y Represents the total pixel width on the y-axis of the coordinate system.

[0010] As a further solution of the present invention: when the first judgment value PD fir =B+C / 2>ZB x *C and / or the second judgment value PD sce =E+C / 2>ZB y *C, send warning information for reporting, B and E represent the standard horizontal coordinate and standard vertical coordinate respectively.

[0011] As a further solution of the present invention: in the step S2, the m injective functions are regrouped after every preset time period.

[0012] As a further solution of the present invention: in the step S1, the resolution of the monitoring video remains unchanged.

[0013] Beneficial effects of the present invention: In this solution, by decomposing the surveillance video by frames and performing group processing, the encryption operation can be performed in frames, which enhances the flexibility and pertinence of the processing; dividing according to the fixed number of frames in each group helps to control the size of the data block, facilitates the subsequent batch encryption and transmission, and reduces the system processing load. By subsequent frame-by-frame processing, even if part of the frame data is intercepted or lost, it is difficult to restore the complete video content, which further enhances the security of the video data during the transmission process; thereafter, a pixel coordinate system is established to assign a specific position to each pixel, so that the encryption operation can act on the smallest unit of the video, achieve precise adjustment, introduce a single-shot function and use mathematical mapping to convert pixels The position adjustment is bound to the frame number, which greatly increases the complexity of encryption. At the same time, the design of random grouping of injective functions divides the encryption strategy into two dimensions, horizontal and vertical, so that cracking the encryption requires solving mapping problems in two different directions at the same time, which significantly increases the difficulty of decryption. When obtaining the standard coordinates, the value of the initial coordinates can be substituted; the combination of pixel coordinates and injective functions makes each frame have a unique encryption method. The superposition of randomness and complexity makes it impossible for an attacker to infer the pixel position distribution of other frames even if he obtains the original data or a single function mapping of a certain frame, thereby greatly improving the overall security of video encryption; then, the pixel coordinates are substituted into the target function and generated. Standard coordinates (substitute the values ​​of the horizontal and vertical coordinates of the initial coordinates into the target x function and the target y function) completely disrupt the pixel arrangement of the original video through mathematical mapping, so that the encrypted frame cannot directly identify the original content. The adjustment of each pixel is completed according to the target function related to the frame number to ensure that the encryption result of each frame is unique, which increases the difficulty and workload of cracking. Moreover, the pixel adjustment process maintains the integrity of the original data and only changes its position in the picture, so that there is no need to reconstruct the data during the decryption process, which helps to maintain the video quality. The horizontal and vertical coordinates are adjusted separately to ensure that the chaos of the pixels reaches full two-dimensional coverage, leaving no trace of the regularity of the original arrangement, providing stronger reliability for data protection. , pixel position adjustment is the core step of encryption. By thoroughly disrupting the content of the picture, it is ensured that even if unauthorized personnel intercept the data frame, it is difficult to restore the original picture visually or technically, directly realizing strong encryption protection of the video and preventing sensitive information leakage; finally, the adjusted video frame is resynthesized into a complete video to ensure that the video maintains continuity and operability during transmission. The encrypted video frame combination will not affect the decryption process. The original picture can be easily restored through the restoration function (the inverse function of the target x function and the target y function), which reduces the technical requirements for the decryption end. Even if it is stolen or tampered with, the original information cannot be cracked or forged, providing comprehensive security for the monitoring system. The present invention encrypts the video by adjusting the pixel position, effectively protecting the security of the monitoring video during transmission. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The present invention will be further described below in conjunction with the accompanying drawings.

[0015] Figure 1 It is a flow chart of a remote monitoring method for a smart obstetric ward according to the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] See also Figure 1 As shown, the present invention is a remote monitoring method for a smart obstetric ward, comprising the following steps: S1: Obtain a surveillance video in the obstetric ward, perform frame processing on the surveillance video to obtain a surveillance video frame sequence, and starting from the first surveillance video frame in the surveillance video frame sequence, group m / 2 consecutive surveillance video frames as the same group, where m is a preset number, and the sequence number of the ath surveillance video frame in the same group is a; S2: Establish a coordinate system with the preset pixel in the monitoring video frame as the origin, determine the coordinates of the pixel in the monitoring video frame, and use it as the initial coordinates, (x i ,y i ) represents the initial coordinates of the i-th pixel; Determine m injective functions, randomly divide the m injective functions into two groups, and name them as x group and y group respectively, record the injective functions in the x group and the y group as x function and y function respectively, one x function corresponds to a sequence number and one y function corresponds to a sequence number, and mark the x function and y function with the same sequence number as the monitoring video frame as the target x function and the target y function respectively; S3: Set the horizontal coordinate x of the initial coordinate of the i-th pixel i Substitute the corresponding target x function to obtain the standard horizontal coordinate X i , the ordinate y of the initial coordinate of the i-th pixel i Substitute the corresponding target y function to obtain the standard ordinate Y i , determine the standard coordinates of the i-th pixel (X i , Y i ); The position of the pixel in the monitoring video frame is adjusted according to the standard coordinates, the adjusted monitoring video frame is used as the target video frame, all the target video frames are synthesized into a target video, and the target video is sent to the receiving end.

[0018] It should be noted that by decomposing the surveillance video by frames and processing them in groups, the encryption operation can be performed in frames, which enhances the flexibility and pertinence of the processing; dividing according to a fixed number of frames in each group helps to control the size of the data block, facilitates subsequent batch encryption and transmission, and reduces the system processing load. Through subsequent frame-by-frame processing, even if part of the frame data is intercepted or lost, it is difficult to restore the complete video content, which further improves the security of the video data during transmission; then, a pixel coordinate system is established to assign a specific position to each pixel, so that the encryption operation can act on the smallest unit of the video to achieve precise adjustment, introduce the single-shot function and use mathematical mapping to convert pixels The position adjustment is bound to the frame number, which greatly increases the complexity of encryption. At the same time, the design of random grouping of injective functions divides the encryption strategy into two dimensions, horizontal and vertical, so that cracking the encryption requires solving mapping problems in two different directions at the same time, which significantly increases the difficulty of decryption. The combination of pixel coordinates and injective functions makes each frame have a unique encryption method. The superposition of randomness and complexity means that even if an attacker obtains the original data or a single function mapping of a certain frame, it is impossible to infer the pixel position distribution of other frames, thereby greatly improving the overall security of video encryption. Then, the pixel coordinates are substituted into the target function and the standard coordinates are generated (the horizontal and vertical coordinates of the initial coordinates are replaced by the horizontal and vertical coordinates of the initial coordinates). Substitute the value of into the target x function and the target y function), completely disrupt the pixel arrangement of the original video through mathematical mapping, so that the encrypted frame cannot directly identify the original content. The adjustment of each pixel is completed according to the target function related to the frame number to ensure that the encryption result of each frame is unique, which increases the difficulty and workload of cracking. Moreover, the pixel adjustment process maintains the integrity of the original data and only changes its position in the picture, so that there is no need to reconstruct the data during the decryption process, which helps to maintain the video quality. The horizontal and vertical coordinates are adjusted separately to ensure that the chaos of the pixels reaches full two-dimensional coverage, leaving no trace of the regularity of the original arrangement, providing stronger reliability for data protection. Pixel position adjustment is The core step of encryption is to completely disrupt the content of the picture to ensure that even if unauthorized personnel intercept the data frame, it is difficult to restore the original picture visually or technically, thereby directly realizing strong encryption protection for the video and preventing the leakage of sensitive information; finally, the adjusted video frames are resynthesized into a complete video to ensure that the video maintains continuity and operability during transmission. The encrypted video frame combination will not affect the decryption process. The original picture can be easily restored through the restoration function (the inverse function of the target x function and the target y function), which reduces the technical requirements for the decryption end. Even if it is stolen or tampered with, the original information cannot be cracked or forged, providing comprehensive security protection for the monitoring system.

[0019] In another preferred embodiment of the present invention, the step S3 further includes the following steps: After receiving the target video, the receiving end divides the target video into frames to obtain target video frames, determines the target x function DYX and the target y function DYY corresponding to the target video frames, and determines the inverse function DYX' of the target x function DYX and the inverse function DYY' of the target y function DYY; The standard coordinates are restored to initial coordinates according to the inverse functions DYX' and DYY', and the positions of pixels are adjusted according to the initial coordinates to obtain monitoring video frames, which are synthesized into monitoring videos for playback and / or storage.

[0020] It is worth noting that the receiving end receives the encrypted target video and processes it frame by frame, decomposing the target video into independent target video frames again to facilitate frame-by-frame decryption; the receiving end locates the corresponding target x function (DYX) and target y function (DYY) through the serial number of the target video frame, and further calculates or retrieves their inverse functions DYX' and DYY'. Since the function corresponding to each frame is unique, this mechanism ensures that the decryption process is completely symmetrical with the encryption process, preventing erroneous restoration or information loss; the application of inverse functions is highly efficient, and does not require the storage of redundant coordinate data. The pixel position can be restored only through mathematical calculations, which optimizes the decryption storage requirements and performance.

[0021] In another preferred embodiment of the present invention, in step S3, when the difference between the standard abscissa and / or standard ordinate of any two standard coordinates is less than the pixel width C, the following steps are performed: The standard coordinate whose standard abscissa and / or standard ordinate difference is less than the pixel width C is used as the undetermined coordinate, and the undetermined coordinate whose distance from the origin is larger is used as the first coordinate, and the first coordinate is adjusted so that the standard abscissa difference between the first coordinate and the second coordinate is equal to the pixel width C and the standard ordinate difference is equal to the pixel width C, and the second coordinate represents the undetermined coordinate whose distance from the origin is closest; Repeat the above steps until the standard abscissa difference between any two standard coordinates is greater than or equal to the pixel width C and the standard ordinate difference is greater than or equal to the pixel width C.

[0022] It can be understood that by difference judgment, potential coordinate overlap or too close problems can be identified to prevent confusion between pixels. By controlling the minimum pixel spacing, blurry or incomplete images caused by pixels being too close after decryption can be prevented, thereby ensuring the clarity and accuracy of the decrypted image.

[0023] In another preferred embodiment of the present invention, the adjustment amount of the first coordinate is recorded, the adjustment amount includes a standard horizontal coordinate adjustment amount and a standard vertical coordinate adjustment amount, the horizontal coordinate adjustment amount represents when the standard horizontal coordinate difference between the first coordinate and the second coordinate is equal to the pixel width C, the vertical coordinate adjustment amount represents when the standard vertical coordinate difference between the first coordinate and the second coordinate is equal to the pixel width C, the distance between the standard vertical coordinate of the first coordinate and the standard vertical coordinate of the first coordinate before adjustment, before restoring the standard coordinate to the initial coordinate according to the inverse functions DYX' and DYY', the first coordinate is restored according to the adjustment amount of the first coordinate; The adjustment amount of the first coordinate and the target video are sent to the receiving end through different transmission paths.

[0024] It should be noted that by recording the adjustment amount of the first coordinate, giving priority to using the adjustment amount when restoring the coordinates, and then restoring according to the inverse function, and using multi-path transmission of the adjustment amount and the target video, the security and anti-attack ability of the encrypted video are further enhanced.

[0025] In another preferred embodiment of the present invention, in step S2, the domain of the target x function includes the interval [0, ZB x ] and the independent variable of the target x function belongs to the interval [0, ZB x ], the corresponding function value belongs to the interval [0, ZB x ], ZB x Represents the total pixel width on the x-axis of the coordinate system; The domain of the target y function includes the interval [0, ZB y ] and the independent variable of the target y function belongs to the interval [0, ZB y ], the corresponding function value belongs to the interval [0, ZB y ], ZB y Represents the total pixel width on the y-axis of the coordinate system.

[0026] It should be noted that the domain and range of the target x function and the target y function are clearly restricted to ensure that the mapping of pixel coordinates by the target function during the encryption process is strictly constrained within the range of the picture, thereby avoiding pixel coordinate out-of-bounds or mapping errors; ensuring that the encrypted video picture is complete and has no "pixel loss" or "boundary fault" problems, providing guarantee for the quality of the decrypted picture.

[0027] In another preferred embodiment of the present invention, when the first judgment value PD fir =B+C / 2>ZB x *C and / or the second judgment value PD sce =E+C / 2>ZB y*C, send warning information for reporting, B and E represent the standard horizontal coordinate and standard vertical coordinate respectively.

[0028] It can be understood that by calculating the judgment value and comparing it with the boundary conditions of the picture range, it is possible to monitor in real time whether there are abnormal pixel coordinates in the encryption process, give early warning of possible operational errors, ensure that all coordinate adjustments are made within the preset range, and avoid abnormal adjustments that cause picture encryption distortion or decryption failure.

[0029] In another preferred embodiment of the present invention, in the step S2, the m injective functions are regrouped after every preset time period.

[0030] It is worth noting that dynamic grouping makes the combination of encryption functions different in each period of time, which increases the randomness and unpredictability of the encrypted data, thereby effectively resisting attacks against fixed encryption strategies; and in this process, the receiving end and the sending end share a time synchronization mechanism, and dynamic grouping does not increase the complexity of the decryption end. It only needs to call the corresponding grouping scheme according to the timestamp to accurately restore the data.

[0031] In another preferred embodiment of the present invention, in the step S1, the resolution of the monitoring video remains unchanged.

[0032] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A remote monitoring method for a smart obstetric ward, characterized in that: The following steps are involved: S1: Obtain a surveillance video in the obstetric ward, perform frame processing on the surveillance video to obtain a surveillance video frame sequence, and starting from the first surveillance video frame in the surveillance video frame sequence, group m / 2 consecutive surveillance video frames as the same group, where m is a preset number, and the sequence number of the ath surveillance video frame in the same group is a; S2: Establish a coordinate system with the preset pixel in the monitoring video frame as the origin, determine the coordinates of the pixel in the monitoring video frame, and use it as the initial coordinates, (x i ,y i ) represents the initial coordinates of the i-th pixel; Determine m injective functions, randomly divide the m injective functions into two groups, and name them as x group and y group respectively, record the injective functions in the x group and the y group as x function and y function respectively, one x function corresponds to a sequence number and one y function corresponds to a sequence number, and mark the x function and y function with the same sequence number as the monitoring video frame as the target x function and the target y function respectively; S3: Set the horizontal coordinate x of the initial coordinate of the i-th pixel i Substitute the corresponding target x function to obtain the standard horizontal coordinate X i , the ordinate y of the initial coordinate of the i-th pixel i Substitute the corresponding target y function to obtain the standard ordinate Y i , determine the standard coordinates of the i-th pixel (X i , Y i ); The position of the pixel in the monitoring video frame is adjusted according to the standard coordinates, the adjusted monitoring video frame is used as the target video frame, all the target video frames are synthesized into a target video, and the target video is sent to the receiving end.

2. A remote monitoring method for a smart obstetric ward according to claim 1, characterized in that: The step S3 further includes the following steps: After receiving the target video, the receiving end divides the target video into frames to obtain target video frames, determines the target x function DYX and the target y function DYY corresponding to the target video frames, and determines the inverse function DYX' of the target x function DYX and the inverse function DYY' of the target y function DYY; The standard coordinates are restored to initial coordinates according to the inverse functions DYX' and DYY', and the positions of pixels are adjusted according to the initial coordinates to obtain monitoring video frames, which are synthesized into monitoring videos for playback and / or storage.

3. A remote monitoring method for a smart obstetric ward according to claim 2, characterized in that: In step S3, when the difference between the standard abscissa and / or standard ordinate of any two standard coordinates is less than the pixel width C, the following steps are performed: The standard coordinate whose standard abscissa and / or standard ordinate difference is less than the pixel width C is used as the undetermined coordinate, and the undetermined coordinate whose distance from the origin is larger is used as the first coordinate, and the first coordinate is adjusted so that the standard abscissa difference between the first coordinate and the second coordinate is equal to the pixel width C and the standard ordinate difference is equal to the pixel width C, and the second coordinate represents the undetermined coordinate whose distance from the origin is closest; Repeat the above steps until the standard abscissa difference between any two standard coordinates is greater than or equal to the pixel width C and the standard ordinate difference is greater than or equal to the pixel width C.

4. A remote monitoring method for a smart obstetric ward according to claim 3, characterized in that: Recording the adjustment amount of the first coordinate, the adjustment amount includes a standard horizontal coordinate adjustment amount and a standard vertical coordinate adjustment amount, the horizontal coordinate adjustment amount represents the distance between the standard vertical coordinate of the first coordinate and the standard vertical coordinate of the first coordinate before adjustment when the standard horizontal coordinate difference between the first coordinate and the second coordinate is equal to the pixel width C, and the vertical coordinate adjustment amount represents the distance between the standard vertical coordinate of the first coordinate and the standard vertical coordinate of the first coordinate before adjustment when the standard vertical coordinate difference between the first coordinate and the second coordinate is equal to the pixel width C, and before restoring the standard coordinate to the initial coordinate according to the inverse functions DYX' and DYY', restoring the first coordinate according to the adjustment amount of the first coordinate; The adjustment amount of the first coordinate and the target video are sent to the receiving end through different transmission paths.

5. A remote monitoring method for a smart obstetric ward according to claim 4, characterized in that: In step S2, the domain of the target x function includes the interval [0, ZB x ] and the independent variable of the target x function belongs to the interval [0, ZB x ], the corresponding function value belongs to the interval [0, ZB x ], ZB x Represents the total pixel width on the x-axis of the coordinate system; The domain of the target y function includes the interval [0, ZB y ] and the independent variable of the target y function belongs to the interval [0, ZB y ], the corresponding function value belongs to the interval [0, ZB y ], ZB y Represents the total pixel width on the y-axis of the coordinate system.

6. A remote monitoring method for a smart obstetric ward according to claim 5, characterized in that: When the first judgment value PD fir =B+C / 2>ZB x *C and / or the second judgment value PD sce =E+C / 2>ZB y *C, send warning information for reporting, B and E represent the standard horizontal coordinate and standard vertical coordinate respectively.

7. A remote monitoring method for a smart obstetric ward according to claim 1, characterized in that: In the step S2, the m injective functions are grouped again after every preset time period.

8. A remote monitoring method for a smart obstetric ward according to claim 1, characterized in that: In the step S1, the resolution of the surveillance video remains unchanged.

Images