Data transmission method for preventing physiological signal leakage, video stream decoding method, and device and medium
Patent Information
- Application Number
- CN202611578290.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-10-13
- Publication Date
- 2026-11-10
Smart Images

Figure CN123075153A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of data encryption transmission technology, specifically to data transmission methods, video stream decoding methods, devices, and media for preventing the leakage of physiological signals. Background Technology
[0002] Non-contact physiological signal monitoring technologies, such as remote photoplethysmography (rPPG), have been widely used in telemedicine, cardiovascular health management, and smart wearables. These technologies passively acquire subtle changes in optical brightness on the skin surface caused by physiological signals using ordinary cameras or infrared sensors. These changes are recorded as a video stream, from which physiological signals such as heart rate, respiratory rate, and blood pressure are extracted. The acquisition end directly transmits the acquired video stream to the receiving end for physiological signal analysis. However, the body videos (such as those of the face and chest) involved in this type of non-contact monitoring contain highly sensitive personal identification and health physiological characteristics. Physiological waveforms and signals such as heart rate and respiratory rate can be extracted from these images. If these images are leaked during or at the point of transmission, the subject's physiological signals will be compromised.
[0003] In summary, existing video streaming technologies are prone to leaking the physiological signals of the test subjects.
[0004] Therefore, existing technologies still need to be improved and enhanced. Summary of the Invention
[0005] To address the aforementioned technical problems, this invention provides a data transmission method, a video stream decoding method, as well as equipment and media for preventing the leakage of physiological signals, thus resolving the issue of easy leakage of the subject's physiological signals during video stream transmission in the prior art.
[0006] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a data transmission method for preventing the leakage of physiological signals, comprising: Under the illumination of an encrypted light source, an encrypted video stream of the subject is acquired. The encrypted light source is used to generate random brightness values, which are used to mask the brightness data generated by the skin in the video stream, so as to encrypt the video stream. The skin brightness is related to the physiological signals of the subject. Obtain a random brightness value sequence of the encrypted light source, and synchronize the random brightness value sequence with the frames of the encrypted video stream; The encrypted video stream and the random brightness value sequence are sent to the receiving end, which is used to decode the encrypted video stream based on the random brightness value sequence.
[0007] In one implementation, the method for generating the random brightness value includes: Acquire data on the changes in skin pixel brightness of the subject caused by the physiological signals; The range of changes corresponding to the skin pixel brightness variation data is expanded to obtain the brightness value range; Random brightness values are generated by randomly selecting a brightness value within the range of brightness values.
[0008] In one implementation, the random brightness value is generated by controlling the duty cycle of the encrypted light source. The duty cycle is the ratio of the on / off time of the encrypted light source within one frame of image time, and one frame of image time is the time required to acquire one frame of image in the video stream.
[0009] Secondly, embodiments of the present invention also provide a video stream decoding method, comprising: The device receives an encrypted video stream and a random brightness value sequence sent by the transmitting end. The encrypted video stream is a video stream of the subject collected under the illumination of an encrypted light source. The encrypted light source is used to generate random brightness values, which are used to mask the brightness data generated by the skin in the video stream. The skin brightness is related to the physiological signals of the subject. Based on the random brightness value sequence, the obfuscated brightness values of the frame images in the encrypted video stream are decoded to obtain a decoded video stream, which is used to analyze the physiological signals of the subject.
[0010] In one implementation, based on the random luminance value sequence, the obfuscated luminance values of frame images within the encrypted video stream are decoded to obtain a decoded video stream, including: The random brightness target value synchronized with the frame image is extracted from the random brightness value sequence, and the random brightness value adjacent to the random brightness target value is extracted from the random brightness value sequence. The time when the encrypted light source outputs the adjacent random brightness value is earlier than the time when it outputs the random brightness target value. Based on the random brightness target value and the adjacent random brightness values, the confused brightness value of the frame image is decoded to obtain the decoded brightness value of the frame image caused by the physiological signal of the subject. The frame images with the decoded brightness values are assembled into a video stream according to the acquisition time to obtain a decoded video stream.
[0011] In one implementation, based on the random brightness target value and the adjacent random brightness values, the confused brightness value of the frame image is decoded to obtain the decoded brightness value of the frame image, including: The equivalent random brightness value is obtained by weighting the random brightness target value and the adjacent random brightness values. Obtain the brightness gain value of the video stream brightness caused by the ambient light intensity of the subject. The equivalent random brightness value and the brightness gain value are removed from the obfuscated brightness value of the frame image to restore the decoded brightness value of the frame image.
[0012] In one implementation, the fitting method for the brightness gain value includes: Under the illumination of the encrypted light source, sample video streams of the same subject in the same environment were collected; Extract the obfuscated brightness sample values of the frame images in the sample video stream, and collect the random brightness value sample sequence output by the encrypted light source that is synchronized with each of the frame images; Based on the confused brightness sample values and the random brightness sample sequence, a linear model of confused brightness and random brightness is fitted. The brightness gain value is obtained based on the fitted linear model.
[0013] In one implementation, the encrypted video stream is an unobstructed facial video stream or a chest video stream of the test subject.
[0014] Thirdly, embodiments of the present invention also provide a terminal device, wherein the terminal device includes a memory, a processor, and a data transmission method program for preventing leakage of physiological signals stored in the memory and executable on the processor. When the processor executes the data transmission method program for preventing leakage of physiological signals, it implements the steps of the data transmission method for preventing leakage of physiological signals described above. Alternatively, the terminal device includes a memory, a processor, and a video stream decoding program stored in the memory and executable on the processor. When the processor executes the video stream decoding program, it implements the steps of the video stream decoding method described above.
[0015] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing a data transmission method program for preventing leakage of physiological signals. When the data transmission method program for preventing leakage of physiological signals is executed by a processor, it implements the steps of the data transmission method for preventing leakage of physiological signals described above. Alternatively, the computer-readable storage medium stores a video stream decoding program, which, when executed by a processor, implements the steps of the video stream decoding method described above.
[0016] Beneficial effects: The brightness of the encrypted light source of the present invention is random. Under the interference of random brightness, the video stream of the subject is collected to hide and cover up the data of changes in skin brightness caused by physiological signals. Thus, even if the video stream is leaked during transmission, as long as the random brightness value sequence of the encrypted light source is not leaked, the physiological signals of the subject cannot be extracted from the video stream, thereby achieving the purpose of preventing the leakage of physiological signals. Attached Figure Description
[0017] Figure 1 This is an overall flowchart of the present invention; Figure 2 This is a pulse diagram of camera exposure and LED power in an embodiment of the present invention; Figure 3 This is a schematic diagram of the obfuscated signal in an embodiment of the present invention; Figure 4 This is a brightness map of each frame of the image after decoding and restoration in an embodiment of the present invention; Figure 5 This is a block diagram illustrating the internal structure of a terminal device provided in an embodiment of the present invention. Detailed Implementation
[0018] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments and accompanying drawings. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.
[0019] Research has found that non-contact physiological signal monitoring technologies, such as remote photoplethysmography (rPPG), have been widely used in telemedicine, cardiovascular health management, and smart wearables. These technologies passively collect subtle changes in optical brightness on the skin surface caused by physiological signals using ordinary cameras or infrared sensors. This data is recorded as a video stream, from which physiological signals such as heart rate, respiratory rate, and blood pressure are extracted. The acquiring end directly transmits the video stream to the receiving end for physiological signal analysis. However, the body videos (such as those of the face and chest) involved in this type of non-contact monitoring contain highly sensitive personal identification and health physiological characteristics. Physiological waveforms and signals such as heart rate and respiratory rate can be extracted from these images. If these images are leaked during or after video transmission, the subject's physiological signals will be compromised.
[0020] To address the aforementioned technical problems, this invention provides a data transmission method, a video stream decoding method, as well as equipment and media for preventing the leakage of physiological signals, thus resolving the issue of easy leakage of the subject's physiological signals during video stream transmission in the prior art.
[0021] Example 1: This example provides a data transmission method to prevent the leakage of physiological signals. In this example, as... Figure 1 As shown, the data transmission method for preventing the leakage of physiological signals specifically includes the following steps: S110, Under the illumination of an encrypted light source, an encrypted video stream of the subject is acquired. The encrypted light source is used to generate random brightness values, which are used to mask the brightness data generated by the skin in the video stream, so as to encrypt the video stream. The skin brightness is related to the physiological signals of the subject. S120, Obtain a random brightness value sequence of the encrypted light source, and synchronize the random brightness value sequence with the frames of the encrypted video stream; S130, the encrypted video stream and the random brightness value sequence are sent to the receiving end, and the receiving end is used to decode the encrypted video stream based on the random brightness value sequence.
[0022] This embodiment uses a non-contact method to collect encrypted video streams from the test subject, decodes the encrypted video stream, and extracts physiological signals from the decoded video stream. These extracted physiological signals are not used for disease diagnosis and treatment, but rather for human-computer interaction. For example, in human-computer interaction scenarios, streaming media platforms can determine a user's preferences for different types of content based on physiological feedback during viewing, thereby making more accurate recommendations.
[0023] The extracted physiological signals can also be applied to intelligent assisted driving. By collecting video streams of drivers, physiological signals such as heart rate and respiration can be extracted from the video streams. Based on heart rate and respiration, it can be determined whether the driver is fatigued or distracted, so as to issue timely warnings and improve driving safety.
[0024] The encrypted light source in step S110 is a light source whose brightness value can be randomly controlled. This light source can be an LED light, where LED stands for Light Emitting Diode.
[0025] Since the brightness of an LED is positively correlated with its power, the brightness of an LED can be randomly controlled by randomly setting its equivalent power.
[0026] like Figure 2 As shown, camera exposure represents the frame image captured by the camera of the subject, which is the camera exposure (corresponding to...). Figure 2The high-pulse camera captures one frame of image at a time. During camera exposure, the equivalent power of the LED light source is randomly set to randomly set the brightness value of the LED light within the camera exposure time. This makes the brightness value of the frame image captured by the camera random. The random brightness value masks the image brightness change data caused by the subject's physiological signals. In other words, the image brightness value related to physiological signals cannot be directly extracted from the image. Therefore, it is not possible to deduce the physiological signals from the brightness value changes of each frame image in the video stream, thus preventing the leakage of physiological signals.
[0027] Under the influence of random brightness values output by the encrypted light source, the brightness values of each frame of the subject's image captured by the camera are as follows: Figure 3 As shown, from Figure 3 As can be seen, the brightness values of each frame are chaotic, so physiological signals cannot be deduced from the brightness values of each frame, thus preventing the privacy of the subject's physiological signals from being leaked.
[0028] The generation of random brightness values in step S110 includes: acquiring skin pixel brightness change data of the subject caused by the physiological signal; expanding the range of changes corresponding to the skin pixel brightness change data to obtain a brightness value range; and randomly selecting a brightness value within the brightness value range to generate a random brightness value.
[0029] Skin pixel brightness variation data refers to the range of skin brightness values caused by physiological signals. The random brightness output of the encrypted light source must be controlled within a safe range. Within a safe range, random brightness will not cause the skin brightness value to be too low or too high. Too low or too high will affect the video quality. Once the video quality is affected, even if the video brightness is restored, the physiological signal cannot be extracted from the restored video. Therefore, controlling the random brightness within a safe range can ensure video quality.
[0030] For example, when there is no random brightness supplementary light source, the brightness of the matched pixel of the test subject caused by changes in physiological signals varies within the range of [150, 151]. If [150, 151] is extended, for example to [150, 155], then [150, 155] is the brightness value range of the above-mentioned random brightness. Random sampling is performed within this range of [150, 155] to obtain the random brightness value.
[0031] The aforementioned random brightness values are converted into the duty cycle of the encrypted light source. By controlling the encrypted light source to illuminate at this duty cycle, the aforementioned random brightness values can be generated. The duty cycle is the ratio of the on / off time of the encrypted light source within one image frame. A high duty cycle means the light source is on for a longer period than off within one image frame, while a low duty cycle means the light source is on for a shorter period than off within one image frame. The on / off switching speed is very fast, exceeding the resolution capabilities of the human eye and a camera.
[0032] Before the camera begins acquiring each frame of image, the microcontroller of the light source extracts a duty cycle from a set containing multiple duty cycles that matches the aforementioned random brightness value, and uses this duty cycle to adjust the brightness of the light source at the camera exposure boundary of the next frame, so that the light source's luminous brightness presents the aforementioned random brightness value during the camera exposure time of the next frame.
[0033] In step S120, each random brightness value in the random brightness value sequence is synchronized with its corresponding frame image. That is, the camera captures a frame image of the subject and records the acquisition time of the frame image, and obtains the random brightness value output by the light source at the acquisition time. The random brightness value of the light source is synchronized with the frame image, which makes it easy for the receiving end to decode based on the random brightness value corresponding to the frame image and the brightness value of the frame image.
[0034] S130 transmits the encrypted video stream and the random brightness value sequence to the receiving end via the transmitting end. The transmitting end can be a computer connected to a camera to read the encrypted video stream captured by the camera. The computer is also connected to a microcontroller of the encrypted light source, and the computer reads the random brightness value sequence output by the microcontroller.
[0035] Example 2: This example provides a video stream decoding method, including the following steps: S210, receiving the encrypted video stream and random brightness value sequence sent by the transmitting end.
[0036] In other words, the receiver receives the encrypted video stream and random brightness value sequence sent by the transmitter. The receiver can also be a computer.
[0037] The encrypted video stream is a video stream of the subject collected under the illumination of an encrypted light source. The encrypted light source is used to generate random brightness values, which are used to mask the brightness data generated by the skin in the video stream. The skin brightness is related to the physiological signals of the subject.
[0038] S220, based on the random brightness value sequence, the obfuscated brightness values of the frame images in the encrypted video stream are decoded to obtain a decoded video stream, which is used to analyze the physiological signals of the subject.
[0039] Step S220 includes the following specific steps S221, S222, S223, S224, and S225: S221, extract a random brightness target value synchronized with the frame image from the random brightness value sequence, and extract a random brightness value adjacent to the random brightness target value from the random brightness value sequence, wherein the time when the encrypted light source outputs the adjacent random brightness value is earlier than the time when it outputs the random brightness target value.
[0040] use Represents a random brightness value sequence. ,in This represents a random brightness value synchronized with the first frame image. This represents a random brightness value synchronized with the second frame image. Representative and the Random brightness target values for each frame of image synchronization.
[0041] use This represents a brightness sequence composed of adjacent random brightness values. , Represents encrypted light source in the camera acquisition of the first... Random brightness values output for each frame of an image. Represents encrypted light source in the camera acquisition of the first... Random brightness values output for each frame of an image. and Representative and random brightness target value Two adjacent random brightness values. In this embodiment... The value is 6.
[0042] S222, perform a weighted calculation on the random brightness target value and the adjacent random brightness values to obtain an equivalent random brightness value. : ; Represents the weight vector. , represent The weight, represent The weight, represent The weight, , ... Increasing sequentially, and , This represents the transpose of a matrix.
[0043] Because light-emitting devices (i.e., encrypted light sources) have electrical and thermal response delays, and camera sensors have an integral exposure effect, the actual light intensity received by a frame image depends not only on the driving brightness value of that frame image, but also on the residual influence of the historical brightness values generated by the light source in the previous few frames (i.e., lamp flicker delay effect). Therefore, when restoring the brightness value caused by physiological signal fluctuations in a video stream frame image, it is necessary to consider removing the historical brightness values generated by the light source in the previous frame image in order to obtain a more realistic and accurate brightness value caused by physiological signal fluctuations.
[0044] S223, Obtain the brightness gain value of the video stream brightness caused by the ambient light intensity of the subject. .
[0045] S224, Remove the influence factors of the equivalent random brightness value and the brightness gain value on the brightness from the confused brightness value of the frame image to restore the decoded brightness value of the frame image.
[0046] In this embodiment, when restoring the brightness value of the frame image, the restored brightness value is also normalized to a preset constant brightness value. , The brightness level is on the same order of magnitude as the frame image captured by the camera. Used to limit the decoded brightness values of each frame image to the same range.
[0047] use Representing the Decoded luminance values reconstructed from each frame image: ; In the formula, Represents the first data captured directly from the camera. The obfuscated brightness values are extracted from each frame of the image. These obfuscated brightness values cover ambient light brightness, random brightness from encrypted light source output, and skin brightness of the subject induced by physiological signals.
[0048] S225, the frame images having the decoded brightness value are combined into a video stream according to the acquisition time to obtain a decoded video stream.
[0049] The same steps S221, S222, S223, and S224 are applied to other frames to obtain the decoded brightness value of each frame. The decoded frames are then sorted according to the acquisition order to form the decoded video stream.
[0050] This embodiment also calculates the decoding brightness value. First-order difference standard deviation as evaluation index : ; In the formula, Represents the first-order difference. Represents standard deviation.
[0051] The encrypted light source flickers randomly to output random brightness. If the random flickering noise is not effectively suppressed, it will lead to... A drastic change occurred, affecting the evaluation indicators. Significantly increased, while when the weight vector When precisely matched with hardware latency characteristics, flicker noise will be significantly canceled out (theoretically, completely eliminated). The restored luminance value then retains only the luminance value induced by physiological signals. The luminance value differences between adjacent frames induced by physiological signals are extremely small and uniform, thus making the first-order difference standard deviation reach a global minimum. Therefore, the evaluation metrics... The corresponding minimum value The value is the restored brightness value entirely caused by physiological signals, using... Represents the restored brightness value entirely induced by physiological signals, for each frame of the image. like Figure 4 As shown, Figure 4 The vertical axis represents .
[0052] This embodiment also includes extracting the subject's physiological signals from the decoded video stream, that is, obtaining the subject's physiological signals based on the brightness changes of the same pixel point between frames within the decoded video stream. Specifically, it includes the following steps: Step 1, Step 2, Step 3, and Step 4: Step one: In each frame of the decoded video stream, identify and track the target body part of the subject, and delineate at least one region of interest. This region of interest consists of multiple pixels, and maintains a spatial correspondence between different frames.
[0053] Step 2: Extract the brightness information of the region of interest frame by frame to obtain the pixel brightness time-series signal that changes over time.
[0054] That is, calculate the average brightness (or average green channel value) of all pixels in the region of interest in each frame image to obtain a one-dimensional brightness array that varies with the frame number; or, extract the brightness value of a fixed pixel in the region of interest in each frame image to form a brightness time sequence.
[0055] Step 3: The pixel brightness timing signal is preprocessed to filter out non-physiological noise.
[0056] Step four: Perform time-domain or frequency-domain analysis on the filtered luminance timing signal to calculate the subject's physiological signals.
[0057] A Fast Fourier Transform (FFT) is performed on the filtered luminance time-series signal to extract the peak frequency of the spectrum, and the heart rate is calculated based on the peak frequency; alternatively, the waveform period is extracted from the luminance time-series signal to calculate the respiratory rate. Both the heart rate and respiratory rate are physiological signals.
[0058] Example 3, based on Example 2, this example provides a method for fitting brightness gain values, including: S310, Under the illumination of the encrypted light source, a sample video stream of the same subject in the same environment is acquired.
[0059] This embodiment not only requires fitting the brightness gain value under the same ambient light, but also requires fitting the brightness gain value under the same clothing color of the subject. This is because clothing color also affects the brightness of the image.
[0060] S320, extract the obfuscated brightness sample values of the frame images in the sample video stream, and collect the random brightness value sample sequence output by the encrypted light source that is synchronized with each of the frame images.
[0061] Steps S320 and S221 are the same and will not be described again here.
[0062] S330, Based on the confused brightness sample values and the random brightness sample sequence, fit a linear model of confused brightness and random brightness; S340, based on a fitted linear model, yields the brightness gain value.
[0063] In other words, the constant term coefficients of the fitted linear model are the brightness gain values.
[0064] S330 includes the following steps one and two: Step 1: Construct a physical response mapping model between confused luminance and equivalent random luminance: ; Among them, model parameters Corresponding to the obfuscated brightness, another model parameter Corresponding equivalent random brightness, The coefficient representing the influence of the subject's clothing color on image brightness. The above physical response mapping model is a linear mapping model.
[0065] Step two: Solve the problem using parameter estimation methods, optimization algorithms, regression analysis algorithms, or algorithms based on error minimization criteria. and .
[0066] Among them, algorithms based on the error minimization criterion include least squares method, gradient descent method, partial least squares regression, and principal component regression.
[0067] This embodiment uses the least squares method to solve the problem. and : ; ; In the formula, This represents the total number of frames contained in the sample video stream. Representing the The equivalent random brightness sample value of each frame image is calculated based on the weighted random brightness value sample sequence. The method for calculating the equivalent random brightness sample value is the same as that for calculating the equivalent random brightness value in Example 2, and will not be described again here. This represents the confused brightness sample value.
[0068] The solution and Substitute into This yields a physical response mapping model between confused brightness and equivalent random brightness.
[0069] Example 4: Based on Examples 1 and 2, this example provides a non-contact physiological signal privacy protection method based on light source encryption.
[0070] S410, Under the illumination of an encrypted light source, the camera at the transmitting end acquires an encrypted video stream of the subject. The encrypted light source is used to generate random brightness values, which are used to mask the brightness data generated by the skin in the video stream, so as to encrypt the video stream. The skin brightness is related to the physiological signals of the subject.
[0071] Steps S410 and S110 are the same, and will not be described again here.
[0072] S420, the transmitter obtains a random brightness value sequence of the encrypted light source by reading the microcontroller of the encrypted light source, and the random brightness value sequence is synchronized with the frames of the encrypted video stream.
[0073] Steps S420 and S120 are the same, and will not be described in detail here.
[0074] S430, the transmitting segment sends the encrypted video stream and the random luminance value sequence to the receiving end, and the receiving end is used to decode the encrypted video stream based on the random luminance value sequence.
[0075] Steps S430 and S130 are the same, and will not be described again here.
[0076] S440, the receiving end receives the encrypted video stream and random brightness value sequence sent by the transmitting end.
[0077] The encrypted video stream is a video stream of the subject collected under the illumination of an encrypted light source. The encrypted light source is used to generate random brightness values, which are used to mask the brightness data generated by the skin in the video stream. The skin brightness is related to the physiological signals of the subject.
[0078] Steps S440 and S210 are the same, and will not be described in detail here.
[0079] S450, the receiving end decodes the obfuscated brightness values of the frame images in the encrypted video stream based on the random brightness value sequence to obtain a decoded video stream, which is used to analyze the physiological signals of the subject.
[0080] Steps S450 and S220 are the same, and will not be described again here.
[0081] In summary, this invention physically encrypts physiological signals into random and meaningless waveforms at the optical acquisition source to prevent the risk of the original video stream being eavesdropped on, intercepted, and used to reverse-engineer physiological characteristics using algorithms. This achieves privacy protection for the test subject from the physical source of acquisition.
[0082] This invention is based on reversible optical-physical modulation, which can restore the real pulse waveform without loss after decoding, ensuring high accuracy in the measurement of physiological parameters such as heart rate and blood pressure, thereby achieving high accuracy in the restoration of physiological signals.
[0083] This invention avoids the high computational cost and high latency of homomorphic encryption and heavy deep learning encryption algorithms. The decoding process has a small computational load and can be easily implemented in real time on resource-constrained edge devices (such as smartphones and embedded cameras). In other words, this invention balances computational overhead and real-time performance.
[0084] Example 5: Based on Examples 1 and 2, the methods of Examples 1 and 2 are applied to a non-contact physiological signal privacy protection system based on light source encryption provided in this example. The system includes the following components: The video acquisition module is used to acquire an encrypted video stream of the subject under the illumination of an encrypted light source. The encrypted light source is used to generate random brightness values, which are used to mask the brightness data generated by the skin in the video stream, so as to achieve encryption of the video stream. The skin brightness is related to the physiological signals of the subject. A random brightness reading module is used to obtain a random brightness value sequence of the encrypted light source, and the random brightness value sequence is synchronized with the frames of the encrypted video stream; A sending module is used to send the encrypted video stream and the random brightness value sequence to a receiving end, wherein the receiving end is used to decode the encrypted video stream based on the random brightness value sequence; The receiving module is used to receive the encrypted video stream and random brightness value sequence sent by the transmitting end. The encrypted video stream is a video stream of the test subject collected under the illumination of an encrypted light source. The encrypted light source is used to generate random brightness values. The random brightness values are used to mask the brightness data generated by the skin in the video stream. The skin brightness is related to the physiological signals of the test subject. The decoding module is used to decode the obfuscated brightness values of the frame images in the encrypted video stream based on the random brightness value sequence to obtain a decoded video stream, which is used to analyze the physiological signals of the subject.
[0085] The decoding module includes: A random brightness value extraction unit is used to extract a random brightness target value synchronized with the frame image from the random brightness value sequence, and to extract a random brightness value adjacent to the random brightness target value from the random brightness value sequence, wherein the encrypted light source outputs the adjacent random brightness value earlier than the random brightness target value. A weighted calculation unit is used to perform weighted calculations on the random brightness target value and the adjacent random brightness values to obtain an equivalent random brightness value; A brightness gain reading unit is used to obtain the brightness gain value of the video stream brightness caused by the ambient light intensity of the subject. A brightness decoding module is used to remove the influence factors of the equivalent random brightness value and the brightness gain value on brightness from the confused brightness value of the frame image, so as to restore the decoded brightness value of the frame image; A video stream construction unit is used to assemble the frame images with the decoded brightness values into a video stream according to the acquisition time, so as to obtain a decoded video stream.
[0086] Based on the above embodiments, the present invention also provides a terminal device, the principle block diagram of which can be as follows: Figure 5 As shown, the terminal device includes a processor, memory, network interface, and display screen connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a data transmission method to prevent the leakage of physiological signals or a video stream decoding method. The display screen can be a liquid crystal display (LCD) or an e-ink display.
[0087] Those skilled in the art will understand that Figure 5The schematic diagram shown is only a partial structural diagram related to the present invention and does not constitute a limitation on the terminal device to which the present invention is applied. The specific terminal device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.
[0088] In one embodiment, a terminal device is provided, comprising a memory, a processor, and a data transmission program for preventing the leakage of physiological signals stored in the memory and executable on the processor. When the processor executes the data transmission program for preventing the leakage of physiological signals, it implements the following operation instructions: Under the illumination of an encrypted light source, an encrypted video stream of the subject is acquired. The encrypted light source is used to generate random brightness values, which are used to mask the brightness data generated by the skin in the video stream, so as to encrypt the video stream. The skin brightness is related to the physiological signals of the subject. Obtain a random brightness value sequence of the encrypted light source, and synchronize the random brightness value sequence with the frames of the encrypted video stream; The encrypted video stream and the random brightness value sequence are sent to the receiving end, which is used to decode the encrypted video stream based on the random brightness value sequence.
[0089] In one embodiment, a terminal device is provided, comprising a memory, a processor, and a video stream decoding program stored in the memory and executable on the processor. When the processor executes the video stream decoding program, it implements the following operation instructions: The device receives an encrypted video stream and a random brightness value sequence sent by the transmitting end. The encrypted video stream is a video stream of the subject collected under the illumination of an encrypted light source. The encrypted light source is used to generate random brightness values, which are used to mask the brightness data generated by the skin in the video stream. The skin brightness is related to the physiological signals of the subject. Based on the random brightness value sequence, the obfuscated brightness values of the frame images in the encrypted video stream are decoded to obtain a decoded video stream, which is used to analyze the physiological signals of the subject.
[0090] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
[0091] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A data transmission method for preventing the leakage of physiological signals, characterized in that, include: Under the illumination of an encrypted light source, an encrypted video stream of the subject is acquired. The encrypted light source is used to generate random brightness values, which are used to mask the brightness data generated by the skin in the video stream, thereby encrypting the video stream. The skin brightness is related to the physiological signals of the subject. The random brightness values are generated by the encrypted light source by controlling the duty cycle of the encrypted light source. The duty cycle is the ratio of the on-off time of the encrypted light source within one frame of image time, and one frame of image time is the time required to acquire one frame of image in the video stream. Obtain a random brightness value sequence of the encrypted light source, and synchronize the random brightness value sequence with the frames of the encrypted video stream; The encrypted video stream and the random brightness value sequence are sent to the receiving end, which is used to decode the encrypted video stream based on the random brightness value sequence.
2. The data transmission method for preventing leakage of physiological signals as described in claim 1, characterized in that, The method for generating the random brightness value includes: Acquire data on the changes in skin pixel brightness of the subject caused by the physiological signals; The range of changes corresponding to the skin pixel brightness variation data is expanded to obtain the brightness value range; Random brightness values are generated by randomly selecting a brightness value within the range of brightness values.
3. A video stream decoding method, characterized in that, include: The receiver receives an encrypted video stream and a random brightness value sequence sent by the transmitter. The encrypted video stream is a video stream of the subject collected under the illumination of an encrypted light source. The encrypted light source is used to generate random brightness values, which are used to mask the brightness data generated by the skin in the video stream. The skin brightness is related to the physiological signals of the subject. Based on the random brightness value sequence, the obfuscated brightness values of the frame images in the encrypted video stream are decoded to obtain a decoded video stream. The decoded video stream is used to analyze the physiological signals of the subject, and the obfuscated brightness values are the brightness values of the frame images in the encrypted video stream.
4. The video stream decoding method as described in claim 3, characterized in that, Based on the random luminance value sequence, the obfuscated luminance values of the frame images within the encrypted video stream are decoded to obtain a decoded video stream, including: The random brightness target value synchronized with the frame image is extracted from the random brightness value sequence, and the random brightness value adjacent to the random brightness target value is extracted from the random brightness value sequence. The time when the encrypted light source outputs the adjacent random brightness value is earlier than the time when it outputs the random brightness target value. Based on the random brightness target value and the adjacent random brightness values, the confused brightness value of the frame image is decoded to obtain the decoded brightness value of the frame image caused by the physiological signal of the subject. The frame images with the decoded brightness values are assembled into a video stream according to the acquisition time to obtain a decoded video stream.
5. The video stream decoding method as described in claim 4, characterized in that, Based on the random brightness target value and the adjacent random brightness values, the confused brightness value of the frame image is decoded to obtain the decoded brightness value of the frame image triggered by the physiological signals of the subject, including: The equivalent random brightness value is obtained by weighting the random brightness target value and the adjacent random brightness values. Obtain the brightness gain value of the video stream brightness caused by the ambient light intensity of the subject. The equivalent random brightness value and the brightness gain value are removed from the obfuscated brightness value of the frame image to restore the decoded brightness value of the frame image.
6. The video stream decoding method as described in claim 5, characterized in that, The fitting method for the brightness gain value includes: Under the illumination of the encrypted light source, sample video streams of the same subject in the same environment were collected; Extract the obfuscated brightness sample values of the frame images in the sample video stream, and collect the random brightness value sample sequence output by the encrypted light source that is synchronized with each frame image. The obfuscated brightness sample values are the brightness values of the frame images in the sample video stream. Based on the confused brightness sample values and the random brightness sample sequence, a linear model of confused brightness and random brightness is fitted. The brightness gain value is obtained based on the fitted linear model.
7. The video stream decoding method according to any one of claims 3-6, characterized in that, The encrypted video stream is an unobstructed facial or chest video stream of the test subject.
8. A terminal device, characterized in that, The terminal device includes a memory, a processor, and a data transmission method program for preventing the leakage of physiological signals stored in the memory and executable on the processor. When the processor executes the data transmission method program for preventing the leakage of physiological signals, it implements the steps of the data transmission method for preventing the leakage of physiological signals as described in any one of claims 1-2. Alternatively, the terminal device includes a memory, a processor, and a video stream decoding program stored in the memory and executable on the processor. When the processor executes the video stream decoding program, it implements the steps of the video stream decoding method as described in any one of claims 3-7.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a data transmission method program for preventing the leakage of physiological signals. When the data transmission method program for preventing the leakage of physiological signals is executed by a processor, it implements the steps of the data transmission method for preventing the leakage of physiological signals as described in any one of claims 1-2. Alternatively, the computer-readable storage medium stores a video stream decoding program, which, when executed by a processor, implements the steps of the video stream decoding method as described in any one of claims 3-7.
