Signal processing method for non-contact physiological sign parameter monitoring

Abstract

The invention discloses a signal processing method for non-contact physiological sign parameter monitoring. The method comprises the following steps: acquiring multi-modal sign signal information; the multi-modal sign signal information comprises first modal sign signal information and second modal sign signal information; the second modal sign signal information comprises a plurality of pieces of sign image information distributed according to a time sequence; performing feature analysis processing on the multi-modal sign signal information to obtain target signal analysis result information; the target signal analysis result information comprises first target analysis result information and second target analysis result information; and judging, analyzing and processing the target signal analysis result information to obtain target sign parameter monitoring result information.

Description

Technical Field

[0001] The present invention relates to the technical field of signal processing, and in particular, to a signal processing method for non-contact physiological sign parameter monitoring. Background Art

[0002] Physiological sign parameters are objective measurable indicators characterizing the signs of human life activities, and they are widely used in health tests, sports evaluations, psychological assessments, etc. The basic physiological sign parameters mainly include indicators such as heart rate, respiratory rate, blood oxygen saturation, and body temperature. Currently, the traditional detection methods mainly rely on contact means. For example, electrocardiogram signals are obtained by pasting electrode patches on the patient's chest, body temperature values are obtained by the change of mercury columns, and the change of blood oxygen saturation is measured by optical sensors. Contact physiological parameter detection methods are still the gold standard methods for clinical detection due to their good accuracy and stability. However, these contact methods need to contact the human body, which may cause skin irritation or discomfort to some patients who need long-term monitoring. Therefore, developing a non-contact physiological sign parameter monitoring and warning algorithm is an urgent problem to be solved. Therefore, a signal processing method for non-contact physiological sign parameter monitoring is provided to achieve real-time non-contact remote multi-modal physiological sign parameter measurement and improve the monitoring efficiency and accuracy of physiological sign parameters. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a signal processing method for non-contact physiological sign parameter monitoring, which is beneficial to realizing real-time non-contact remote multi-modal physiological sign parameter measurement and improving the monitoring efficiency and accuracy of physiological sign parameters.

[0004] To solve the above technical problem, in the first aspect of the embodiments of the present invention, a signal processing method for non-contact physiological sign parameter monitoring is disclosed, and the method includes:

[0005] Obtain multi-modal sign signal information; the multi-modal sign signal information includes first-modal sign signal information and second-modal sign signal information; the second-modal sign signal information includes several sign image information distributed in chronological order;

[0006] Perform feature analysis processing on the multi-modal sign signal information to obtain target signal analysis result information; the target signal analysis result information includes first target analysis result information and second target analysis result information;

[0007] Perform judgment analysis processing on the target signal analysis result information to obtain target sign parameter monitoring result information.

[0008] In a second aspect of the embodiments of the present invention, a signal processing device for non-contact physiological sign parameter monitoring is disclosed. The device includes:

[0009] An acquisition module, configured to acquire multi-modal sign signal information; the multi-modal sign signal information includes first-modal sign signal information and second-modal sign signal information; the second-modal sign signal information includes several sign image information distributed in chronological order;

[0010] A first processing module, configured to perform feature analysis processing on the multi-modal sign signal information to obtain target signal analysis result information; the target signal analysis result information includes first target analysis result information and second target analysis result information;

[0011] A second processing module, configured to perform judgment and analysis processing on the target signal analysis result information to obtain target sign parameter monitoring result information.

[0012] In a third aspect of the present invention, another signal processing device for non-contact physiological sign parameter monitoring is disclosed. The device includes:

[0013] A memory storing executable program code;

[0014] A processor coupled to the memory;

[0015] The processor calls the executable program code stored in the memory and executes some or all of the steps in the signal processing method for non-contact physiological sign parameter monitoring disclosed in the first aspect of the embodiments of the present invention.

[0016] In a fourth aspect of the present invention, a computer-readable storage medium is disclosed. The computer-readable storage medium stores computer instructions, which are used to execute some or all of the steps in the signal processing method for non-contact physiological sign parameter monitoring disclosed in the first aspect of the embodiments of the present invention when the computer instructions are called. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0018] Figure 1 is a schematic diagram of the scenario of the signal processing system for non-contact physiological sign parameter monitoring provided by the embodiments of the present invention;

[0019] Figure 2It is a schematic flowchart of a signal processing method for non-contact physiological sign parameter monitoring disclosed in an embodiment of the present invention;

[0020] Figure 3 It is a schematic structural diagram of a signal processing device for non-contact physiological sign parameter monitoring disclosed in an embodiment of the present invention;

[0021] Figure 4 It is a schematic structural diagram of another signal processing device for non-contact physiological sign parameter monitoring disclosed in an embodiment of the present invention. Detailed implementation manners

[0022] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts belong to the scope of protection of the present invention.

[0023] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or equipment.

[0024] Referring to "embodiment" herein means that a specific feature, structure or characteristic described in connection with the embodiment can be included in at least one embodiment of the present invention. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0025] In this application, the term "exemplary" is used to mean "serving as an example, illustration, or instance". Any embodiment described as "exemplary" in this application is not necessarily to be construed as more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. In the following description, details are set forth for purposes of explanation. It should be understood that those of ordinary skill in the art can recognize that this application can be implemented without these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid obscuring the description of this application with unnecessary details. Therefore, this application is not intended to be limited to the embodiments shown, but rather to be in line with the broadest scope consistent with the principles and features disclosed in this application.

[0026] It should be noted that since the method of the embodiments of this application is executed in a computer device, the processing objects of each computer device exist in the form of data or information. For example, time, which is actually time information. It can be understood that in subsequent embodiments, if dimensions, quantities, positions, etc. are mentioned, they are all corresponding data existences for the computer device to process, and specific details are not elaborated here.

[0027] It should be noted that a brief description of the artificial intelligence-related technologies that may be involved in this application is provided. Artificial Intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a way similar to human intelligence. Artificial intelligence also studies the design principles and implementation methods of various intelligent machines to enable the machines to have the functions of perception, reasoning, and decision-making.

[0028] Artificial intelligence technology is an interdisciplinary subject with a wide range of fields involved, including both hardware-level technologies and software-level technologies. The basic technologies of artificial intelligence generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, and mechatronics. The software technologies of artificial intelligence mainly include several major directions such as computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0029] Computer Vision Technology (CV) Computer vision is a science that studies how to enable machines to "see". More specifically, it refers to using cameras and computers to replace human eyes for tasks such as object recognition and measurement in machine vision, and further performing graphics processing to make the images processed by the computer more suitable for human eyes to observe or be transmitted to instruments for detection. As a scientific discipline, computer vision researches related theories and technologies, and attempts to establish artificial intelligence systems that can obtain information from images or multi-dimensional data. Computer vision technology usually includes image processing, image recognition, image semantic understanding, image retrieval, OCR, video processing, video semantic understanding, video content / behavior recognition, three-dimensional object reconstruction, 3D technology, virtual reality, augmented reality, simultaneous localization and mapping, etc. technologies, and also includes common biometric recognition technologies such as face recognition and fingerprint recognition.

[0030] Single-modal information is data of only one type, such as one of the data information of text, image, audio, video, electromagnetic signal, etc. Multi-modal information is data information that includes at least 2 types of single-modal information. Further, multi-modal information is applicable to complex tasks that require integrating multiple information sources, such as sentiment analysis, robot interaction, autonomous driving, etc. By integrating information of multiple modalities, higher performance and accuracy can usually be achieved in tasks.

[0031] A large model refers to an artificial neural network model with a very large number of parameters. In the field of artificial intelligence, a large model usually refers to a model with hundreds of millions to trillions of parameters. The model usually needs to be trained on a large-scale dataset and requires a large amount of computing resources for optimization and adjustment. Large models are usually used to solve complex natural language processing, computer vision, and speech recognition tasks. Generative AI is a type of AI that can create new content and ideas, including conversations, stories, images, videos, and music. In the embodiments of this application, the large model can be large language models such as ChatGPT, BERT, XLNet, Zhipu Model, Claude, Moonshot AI Model, ChatGLM Model, Tongwen Qianyi Model, MiniMax Model, Spark Model, Llama Model, 360GPT Model, Qwen Model, Baichuan Model, Lark Model, vivoLM Model, and Wenxin Yiyan, and the embodiments of this application do not make any limitations.

[0032] The embodiments of this application provide a signal processing method, device, computer device, and computer-readable storage medium for non-contact physiological sign parameter monitoring, which will be described in detail below.

[0033] Please refer to Figure 1 , Figure 1This is a scenario schematic diagram of the signal processing system for non-contact physiological sign parameter monitoring provided by the embodiments of the present application. The signal processing system for non-contact physiological sign parameter monitoring may include a computer device 100, and a signal processing device for non-contact physiological sign parameter monitoring is integrated in the computer device 100, such as Figure 1 the computer device in

[0034] In the embodiments of the present application, the computer device 100 is mainly used to obtain multi-modal sign signal information; the multi-modal sign signal information includes first-modal sign signal information and second-modal sign signal information; the second-modal sign signal information includes several sign image information distributed in chronological order.

[0035] Perform feature analysis processing on the multi-modal sign signal information to obtain target signal analysis result information; the target signal analysis result information includes first-target analysis result information and second-target analysis result information;

[0036] Perform judgment analysis processing on the target signal analysis result information to obtain target sign parameter monitoring result information.

[0037] It can realize real-time non-contact remote multi-modal physiological sign parameter measurement, and improve the efficiency and accuracy of physiological sign parameter monitoring.

[0038] In the embodiments of the present application, the computer device 100 may be an independent server, or a server network or server cluster composed of servers. For example, the computer device 100 described in the embodiments of the present application includes, but is not limited to, a computer, a network host, a single network server, a set of multiple network servers, or a cloud server composed of multiple servers. Among them, the cloud server is composed of a large number of computers or network servers based on cloud computing.

[0039] It can be understood that the computer device 100 used in the embodiments of the present application may be a device that includes both receiving and transmitting hardware, that is, a device having receiving and transmitting hardware capable of performing two-way communication on a two-way communication link. Such devices may include: cellular or other communication devices, which have a single-line display or a multi-line display or a cellular or other communication device without a multi-line display. Specifically, the computer device 100 may specifically be a desktop terminal or a mobile terminal, and the computer device 100 may specifically also be one of a mobile phone, a tablet computer, a laptop computer, etc.

[0040] Those skilled in the art can understand that Figure 1 the application environment shown inFigure 1 more or fewer computer devices as shown, such as Figure 1 only 1 computer device is shown in Figure 1 . It can be understood that the signal processing system for non-contact physiological sign parameter monitoring may further include one or more other services, which are not specifically limited herein.

[0041] In addition, as Figure 1 shown, the signal processing system for non-contact physiological sign parameter monitoring may further include a memory 200 for storing data such as image data, location information, etc.

[0042] It should be noted that Figure 1 the scenario schematic diagram of the signal processing system for non-contact physiological sign parameter monitoring shown in Figure 1 is only an example. The signal processing system and scenario for non-contact physiological sign parameter monitoring described in the embodiments of the present application are for more clearly illustrating the technical solutions of the embodiments of the present application, and do not constitute a limitation to the technical solutions provided by the embodiments of the present application. Those of ordinary skill in the art can know that with the evolution of the signal processing system for non-contact physiological sign parameter monitoring and the emergence of new service scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

[0043] The present invention discloses a signal processing method for non-contact physiological sign parameter monitoring, which is conducive to realizing real-time non-contact remote multi-modal physiological sign parameter measurement and improving the efficiency and accuracy of physiological sign parameter monitoring. The following will be described in detail respectively.

[0044] Embodiment 1

[0045] Please refer to Figure 2 , Figure 2 which is a flowchart of a signal processing method for non-contact physiological sign parameter monitoring disclosed in an embodiment of the present invention. Among them, Figure 2 the signal processing method for non-contact physiological sign parameter monitoring described is applied to a management system, such as a local server or a cloud server for management, etc., which is not limited in the embodiments of the present invention. As Figure 2 shown, the signal processing method for non-contact physiological sign parameter monitoring may include the following operations:

[0046] 101. Obtain multi-modal sign signal information.

[0047] In the embodiments of the present invention, the multi-modal sign signal information includes first-modal sign signal information and second-modal sign signal information; the second-modal sign signal information includes several sign image information distributed in chronological order.

[0048] 102. Perform feature analysis and processing on the multi-modal physiological sign signal information to obtain the target signal analysis result information.

[0049] In the embodiment of the present invention, the target signal analysis result information includes the first target analysis result information and the second target analysis result information.

[0050] 103. Perform judgment and analysis processing on the target signal analysis result information to obtain the target physiological sign parameter monitoring result information.

[0051] It should be noted that the above multi-modal physiological sign signal information represents at least two single-modal physiological sign parameters collected in chronological order, and the embodiment of the present invention does not make any limitations. Further, the above first-modal physiological sign signal information represents microwave data, and the second-modal physiological sign signal information represents image information. Further, the above first-modal physiological sign signal information can be the echo data collected by using a microwave module (such as a smart bracelet, a millimeter-wave radar, etc.), and the second-modal physiological sign signal information can be the visible light image collected by using a visible light module (such as a camera, etc.), and the embodiment of the present invention does not make any limitations.

[0052] It should be noted that the above non-contact multi-modal physiological sign signal information collected is obtained without contacting the human body when using a microwave module and an optical module for data collection, and the embodiment of the present invention does not make any limitations.

[0053] It should be noted that the above first target analysis result information includes the first analysis result value information (such as representing heart rate parameter information) and the second analysis result value information (such as representing respiratory rate parameter information), and the embodiment of the present invention does not make any limitations.

[0054] In this optional embodiment, as an optional implementation manner, the above performing judgment and analysis processing on the target signal analysis result information to obtain the target physiological sign parameter monitoring result information includes:

[0055] Count the number of all first analysis result values in the first target analysis result information that are outside the first parameter interval to obtain the first abnormal number;

[0056] Judge whether the first abnormal number is greater than or equal to the first quantity threshold to obtain the first quantity judgment result;

[0057] When the first quantity judgment result is yes, take the physiological sign parameter abnormality as the target physiological sign parameter monitoring result information;

[0058] When the first quantity judgment result is no, count the number of all second analysis result values in the second target analysis result information that are outside the second parameter interval to obtain the second abnormal number;

[0059] Determine whether the second abnormal quantity is greater than or equal to the second quantity threshold to obtain a second quantity judgment result;

[0060] When the second quantity judgment result is yes, take the abnormal physical sign parameter as the target physical sign parameter monitoring result information;

[0061] When the second quantity judgment result is no, count the quantity of the third analysis result value outside the third parameter interval in the second target analysis result information to obtain a third abnormal quantity;

[0062] Determine whether the third abnormal quantity is greater than or equal to the third quantity threshold to obtain a third quantity judgment result;

[0063] When the third quantity judgment result is yes, take the abnormal physical sign parameter as the target physical sign parameter monitoring result information;

[0064] When the third quantity judgment result is no, take the normal physical sign parameter as the target physical sign parameter monitoring result information.

[0065] It should be noted that the above first parameter interval can be [50, 120], and the embodiments of the present invention do not make limitations.

[0066] It should be noted that the above second parameter interval can be [8, 30], and the embodiments of the present invention do not make limitations.

[0067] It should be noted that the above third parameter interval can be [94, 100], and the embodiments of the present invention do not make limitations.

[0068] It should be noted that the above first quantity threshold, second quantity threshold, and third quantity threshold can be positive integers between [5, 50], and the embodiments of the present invention do not make limitations.

[0069] It should be noted that through the multi-dimensional statistics and judgment analysis of the multi-modal physical sign parameters, it is possible to accurately determine whether the parameters are abnormal, so as to achieve accurate remote non-contact accurate physical sign parameter monitoring. The embodiments of the present invention do not make limitations.

[0070] It should be noted that the above multi-modal physical sign signal information may also include temperature information. The infrared module measures temperature by detecting the infrared energy emitted by all materials above absolute zero. The infrared module performs imaging and detection on electromagnetic waves in the 9-14μm band. According to the principle of blackbody radiation, any object emits electromagnetic waves outward. The higher the temperature, the shorter the wavelength of the emitted electromagnetic waves. For an object at normal temperature (27°C), its radiation peak is about 10μm, and the radiation power is positively correlated with the temperature. It can use the radiation of the object itself for imaging without the need for an external illumination source, so it can also image in environments such as at night, achieving an effect similar to that of a night vision device. Since the intensity of the radiation is positively correlated with the temperature, the brightness of the imaging is also positively correlated with the human body temperature: the higher the temperature, the higher the radiation power, the stronger the detected signal, and the brighter the corresponding imaging. This imaging device can be used to measure the human body temperature, obtain the body temperature, and distinguish the normal body temperature range of 34°C to 38°C.

[0071] It can be seen that implementing the signal processing method for non-contact physiological sign parameter monitoring described in the embodiments of the present invention is beneficial to realizing real-time non-contact remote multi-modal physiological sign parameter measurement, and improving the efficiency and accuracy of physiological sign parameter monitoring.

[0072] In an optional embodiment, the above-mentioned feature analysis and processing of the multi-modal physical sign signal information to obtain the target signal analysis result information includes:

[0073] Performing feature analysis on the first-modal physical sign signal information to obtain the first signal feature information;

[0074] Performing feature analysis on the second-modal physical sign signal information to obtain the second signal feature information; the second signal feature information includes the first signal component feature information, the second signal component feature information, and the third signal component feature information;

[0075] Based on the first signal feature information and the second signal feature information, determining the first target analysis result information;

[0076] Based on the second signal feature information, determining the second target analysis result information.

[0077] It should be noted that the above-mentioned second target analysis result information includes several third analysis result values, which are not limited in the embodiments of the present invention.

[0078] It should be noted that the above-mentioned second signal component feature information and third signal component feature information respectively include a number of second sub-signal component feature information and third sub-signal component feature information corresponding to the number of second sub-signal component feature information, which are not limited in the embodiments of the present invention. Further, the above-mentioned second sub-signal component feature information and the third sub-signal component feature information corresponding to the second sub-signal component feature information correspond to a physical sign image information, which is not limited in the embodiments of the present invention.

[0079] In this optional embodiment, as an optional implementation manner, determining the second target analysis result information based on the second signal feature information includes:

[0080] For any second sub-signal component feature information in the second signal component feature information, perform mean square error calculation processing on the second sub-signal component feature information and the third signal component feature information corresponding to the second sub-signal component feature information, to obtain the first signal mean square error value information and the second mean square error value information corresponding to the second sub-signal component feature information;

[0081] Use the second signal calculation model to perform calculation processing on the first signal mean square error value information and the second mean square error value information, to obtain the third analysis result value corresponding to the second sub-signal component feature information;

[0082] Wherein, the second signal calculation model is:

[0083]

[0084] In the formula, XY represents the third analysis result value; K1 and K3 respectively represent the standard variance and mean value in the first signal mean square error value information; K2 and K4 respectively represent the standard variance and mean value in the second signal mean square error value information; c1 and c2 respectively represent the first calculation coefficient and the second calculation coefficient.

[0085] It should be noted that the above-mentioned first calculation coefficient and second calculation coefficient can be set by the user or can be default values given by the system, which are not limited in the embodiments of the present invention. Further, the above-mentioned first calculation coefficient is a negative number not greater than -20, and the second calculation coefficient is a positive number not less than 100, which are not limited in the embodiments of the present invention.

[0086] It should be noted that determining the second target analysis result information based on the second signal feature information is to first analyze the laws of the signals themselves in a single dimension for the two monochromatic image signal information respectively, and then perform coupled calculation and linear fitting on the laws of the two unit signals, so as to realize the in-depth and accurate feature representation of the image signal, improve the accuracy and reliability of the signal representation, which is not limited in the embodiments of the present invention.

[0087] In this optional embodiment, as an optional implementation manner, the above-mentioned feature analysis of the first modal physical sign signal information to obtain the first signal feature information includes:

[0088] Performing spectrum analysis on the first modal physical sign signal information to obtain target distance information;

[0089] Performing signal parameter estimation processing on the first modal physical sign signal information to obtain target angle information;

[0090] Performing signal phase difference processing on the target distance information, target angle information, and the first modal physical sign signal information to obtain first processing feature information;

[0091] Performing filtering processing on the first processing feature information to obtain second processing feature information;

[0092] Performing time-frequency transformation processing on the second processing feature information to obtain the first signal feature information.

[0093] It should be noted that the above-mentioned time-frequency transformation processing of the second processing feature information is to perform a fast Fourier transform on the signal to transform the signal from the time domain to the frequency domain to extract the cardiac physiological signal in the signal, and the embodiments of the present invention are not limited thereto.

[0094] It should be noted that the above-mentioned signal phase difference processing of the target distance information, target angle information, and the first modal physical sign signal information is to decompose the phase signal by using the complete adaptive noise ensemble empirical mode decomposition algorithm, that is, to enhance the heartbeat signal by using the phase difference, apply the complete adaptive noise ensemble empirical mode decomposition algorithm to decompose the phase signal, and extract the heartbeat and respiration signals of the microwave module to achieve efficient and accurate signal extraction, and the embodiments of the present invention are not limited thereto. Further, the phase difference is achieved by subtracting consecutive phase values, which can eliminate the drift of the phase baseline, enhance the high-frequency component, that is, the heartbeat signal, and suppress the respiration harmonic, and the embodiments of the present invention are not limited thereto.

[0095] It should be noted that the above-mentioned filtering processing of the first processing feature information is to perform smoothing processing by using wavelet filtering, and the embodiments of the present invention are not limited thereto.

[0096] It should be noted that the above spectral analysis of the first-modal physical sign signal information uses Fourier transform to extract the signal at the maximum amplitude to determine the target signal, and the phase signal is restored through phase unwrapping to determine the target distance of the signal. The embodiments of the present invention are not limited thereto. It should be noted that since the frequency-modulated continuous-wave radar periodically emits a frequency signal that linearly increases with time, and the range resolution is not sufficient to resolve the fluctuations of the chest cavity and the heart, the acquisition pair can be regarded as a stationary target. The distance from the acquisition pair to the radar board is proportional to the frequency of the intermediate-frequency signal. Therefore, the distance detection from the acquisition object to the microwave module can be achieved by finding the spectral peak through FFT. The embodiments of the present invention are not limited thereto.

[0097] It should be noted that the above signal parameter estimation processing of the first-modal physical sign signal information uses the Music algorithm to analyze the angle of the physiological sign parameters collected by the device, that is, the target angle is obtained. The embodiments of the present invention are not limited thereto. Further, the above signal parameter estimation processing of the first-modal physical sign signal information performs eigenvalue decomposition on the received data of the array antenna to obtain mutually orthogonal signal subspaces and noise subspaces, constructs a spatial scan spectrum, and determines the target direction (acquisition object) through spectral peak search, so as to obtain the angle of the acquisition object relative to the microwave module. The embodiments of the present invention are not limited thereto.

[0098] It can be seen that implementing the signal processing method for non-contact physiological sign parameter monitoring described in the embodiments of the present invention is beneficial to realizing real-time non-contact remote multi-modal physiological sign parameter measurement and improving the efficiency and accuracy of physiological sign parameter monitoring.

[0099] In another optional embodiment, feature analysis is performed on the second-modal physical sign signal information to obtain second signal feature information, including:

[0100] Performing image optimization processing on the second-modal physical sign signal information to obtain optimized modal physical sign signal information;

[0101] Performing feature extraction processing on the optimized modal physical sign signal information to obtain second signal feature information.

[0102] It should be noted that the above optimized modal physical sign signal information represents physiological sign parameters after filtering and signal amplification, such as cardiac physiological signals (heart rate physiological parameters, respiratory rate physiological parameters), blood oxygen saturation signals, etc. The embodiments of the present invention are not limited thereto.

[0103] It should be noted that the above second signal feature information is a signal obtained by separating the RGB three color channels, extracting the monochromatic signals, and then filtering and synthesizing them, so as to analyze the single physiological sign feature information specifically. The embodiments of the present invention are not limited thereto.

[0104] It can be seen that implementing the signal processing method for non-contact physiological sign parameter monitoring described in the embodiments of the present invention is conducive to realizing real-time non-contact remote multi-modal physiological sign parameter measurement, and improving the efficiency and accuracy of physiological sign parameter monitoring.

[0105] In yet another alternative embodiment, image optimization processing is performed on the second-modal sign signal information to obtain optimized-modal sign signal information, including:

[0106] Performing first-dimension filtering processing on the second-modal sign signal information to obtain first-optimized sign signal information;

[0107] Performing second-dimension filtering processing on the first-optimized sign signal information to obtain second-optimized sign signal information;

[0108] Performing signal amplification processing on the second-optimized sign signal information to obtain third-optimized sign signal information;

[0109] Performing image synthesis processing on the third-optimized sign signal information to obtain synthesized-modal sign signal information;

[0110] Performing superposition and fusion processing on the synthesized-modal sign signal information and the second-modal sign signal information to obtain optimized-modal sign signal information.

[0111] It should be noted that the above first-dimension filtering and second-dimension filtering respectively represent spatial filtering and time-domain filtering, and the embodiments of the present invention do not make limitations. Further, the above first-dimension filtering may be to perform pyramid multi-resolution decomposition on a plurality of sign image information distributed in chronological order to obtain a plurality of basebands with different spatial frequencies, and the embodiments of the present invention do not make limitations. Further, the above second-dimension filtering may be to perform band-pass filtering on images of different scales to retain low frequencies (such as effective frequencies of 0.2 - 5 Hz) to avoid amplifying other noise frequencies during subsequent signal amplification, which is conducive to improving the accuracy of signal analysis, and the embodiments of the present invention do not make limitations.

[0112] It should be noted that the above signal amplification processing on the second-optimized sign signal information is to reasonably amplify the signal to facilitate amplifying the signal difference and improving the accuracy of signal analysis, and the embodiments of the present invention do not make limitations.

[0113] It should be noted that the above image synthesis processing on the third-optimized sign signal information is to reconstruct the extracted multi-scale image signals to reconstruct the image details of the multi-scale decomposition, obtain a more excellent representation of image edges and textures, and improve the accuracy of image signal analysis. It may be implemented based on a deep learning algorithm, and the embodiments of the present invention do not make limitations.

[0114] It should be noted that the above-mentioned superposition and fusion processing of the synthetic modal sign signal information and the second modal sign signal information is to sum and average the pixel points at the same positions in the two images, so as to achieve image fusion that both deeply extracts and optimizes the detailed features of the image and retains the detailed feature information of the original image, improving the richness of image information representation. The embodiments of the present invention are not limited thereto.

[0115] It can be seen that implementing the signal processing method for non-contact physiological sign parameter monitoring described in the embodiments of the present invention is beneficial to realizing real-time non-contact remote multi-modal physiological sign parameter measurement, and improving the efficiency and accuracy of physiological sign parameter monitoring.

[0116] In another optional embodiment, feature extraction processing is performed on the optimized modal sign signal information to obtain second signal feature information, including:

[0117] Separate the color channels of the optimized modal sign signal information to obtain first color image information, second color image information, and third color image information; the first color image information includes a plurality of first sub-color image information; the second color image information includes a plurality of second sub-color image information; the third color image information includes a plurality of third sub-color image information;

[0118] Perform signal optimization processing on the first color image information to obtain first signal component feature information;

[0119] Perform signal optimization processing on the second color image information to obtain second signal component feature information;

[0120] Perform signal optimization processing on the third color image information to obtain third signal component feature information.

[0121] It should be noted that the above-mentioned separation of the color channels of the optimized modal sign signal information is to extract the image signal information according to the RGB three-color channels, so as to obtain the image signal information of each single color. The embodiments of the present invention are not limited thereto. Further, the above-mentioned color channel separation is mainly considered that the signal representations of different physiological sign parameters under different colors are significantly different. For example, the cardiac physiological signal is more obvious in the G channel, while the blood oxygen saturation is more obvious in the R channel and the B channel. Therefore, separating the single-color channel signals is more conducive to the precise analysis of a specific physiological feature. The embodiments of the present invention are not limited thereto.

[0122] It should be noted that the above-mentioned signal optimization processing methods for the second color image information and the third color image information are the same as those for the first color image information. The embodiments of the present invention are not limited thereto.

[0123] It can be seen that implementing the signal processing method for non-contact physiological sign parameter monitoring described in the embodiments of the present invention is conducive to realizing real-time non-contact remote multi-modal physiological sign parameter measurement, and improving the efficiency and accuracy of physiological sign parameter monitoring.

[0124] In an alternative embodiment, the above-mentioned signal optimization processing of the first color image information to obtain the first signal component feature information includes:

[0125] For any first sub-color image information in the first color image information, use the first signal calculation model to perform calculation processing on the first sub-color image information to obtain the color signal value corresponding to the first sub-color image information;

[0126] Among them, the first signal calculation model is:

[0127]

[0128] In the formula, y represents the color signal value; xsz(a, b) represents the gray value of the pixel at the coordinate (a, b) in the image corresponding to the first sub-color image information; X and Y respectively represent the number of rows and columns of the pixel points of the image corresponding to the first sub-color image information;

[0129] Arrange all the color signal values in the order from front to back according to the time sequence corresponding to the first sub-color image information to obtain the first color signal value information;

[0130] Perform smoothing processing on the first color signal value information to obtain the first signal component feature information.

[0131] It should be noted that in this application, the coordinate system established is a two-dimensional rectangular coordinate system, the origin of the coordinate is the position of the pixel at the lower left corner of the image, the positive direction of the X-axis is from left to right, and the positive direction of the Y-axis is from bottom to top. The embodiments of the present invention do not make any limitations.

[0132] It should be noted that the above-mentioned calculation processing of the first sub-color image information using the first signal calculation model is to convert the image information into a numerical signal that is easier to analyze, and based on a single image, perform a normalization process of converting the image information into a single numerical signal, reducing the data processing dimension and improving the efficiency and accuracy of data analysis. The embodiments of the present invention do not make any limitations.

[0133] It should be noted that arranging all the color signal values in the order from front to back according to the time sequence corresponding to the first sub-color image information is to convert the calculated numerical signal into a vector in the time dimension according to the time sequence, so as to facilitate data analysis. The embodiments of the present invention do not make any limitations.

[0134] It should be noted that the above-mentioned smoothing process can be implemented based on wavelet filtering, which is mainly used to remove noise signals such as environmental noise and image artifacts caused by abnormal shaking, and the embodiment of the present invention is not limited thereto.

[0135] It can be seen that the signal processing method for non-contact physiological sign parameter monitoring described in the embodiment of the present invention is conducive to realizing real-time non-contact remote multimodal physiological sign parameter measurement and improving the efficiency and accuracy of physiological sign parameter monitoring.

[0136] In another optional embodiment, determining first target analysis result information based on the first signal feature information and the second signal feature information includes:

[0137] Performing fusion processing on the first signal characteristic information and the second signal characteristic information to obtain third signal characteristic information;

[0138] Performing outlier removal processing on the third signal characteristic information to obtain fourth signal characteristic information;

[0139] Perform spectrum analysis on the fourth signal characteristic information to obtain first target analysis result information.

[0140] It should be noted that the above-mentioned fusion processing of the first signal characteristic information and the second signal characteristic information is to perform a joint mean filtering on the signals obtained in two ways (the first signal component characteristic information and the second signal characteristic information) to obtain a fused signal, thereby realizing the effective fusion of signals of different dimensions and depths, improving the richness of the signal representation characterizing the cardiac physiological signals, and being more conducive to the accurate extraction and analysis of the signals, which is not limited in the embodiments of the present invention.

[0141] It should be noted that the above-mentioned outlier removal processing of the third signal characteristic information is to remove significant outliers of the signal, thereby reducing the interference of abnormal values ​​on signal analysis and improving the accuracy of signal analysis, which is not limited in the embodiment of the present invention.

[0142] It should be noted that the above-mentioned spectral analysis of the fourth signal characteristic information can be performed by fast Fourier transform calculation to obtain the two physiological characteristic parameters of heart rate and respiratory rate in the first target analysis result information, so as to achieve accurate extraction of specific physiological characteristic parameters, which is not limited in the embodiment of the present invention.

[0143] It can be seen that the signal processing method for non-contact physiological sign parameter monitoring described in the embodiment of the present invention is conducive to realizing real-time non-contact remote multimodal physiological sign parameter measurement and improving the efficiency and accuracy of physiological sign parameter monitoring.

[0144] Embodiment 2

[0145] See also Figure 3 ,Figure 3 This is a schematic structural diagram of a signal processing device for non-contact physiological sign parameter monitoring disclosed in an embodiment of the present invention. Among them, Figure 3 The described device can be applied to a management system, such as a local server or a cloud server for management, etc., which is not limited in the embodiments of the present invention. For example, Figure 3 As shown, the device may include:

[0146] An acquisition module 201, configured to acquire multi-modal sign signal information; the multi-modal sign signal information includes first-modal sign signal information and second-modal sign signal information; the second-modal sign signal information includes several sign image information distributed in chronological order;

[0147] A first processing module 202, configured to perform feature analysis processing on the multi-modal sign signal information to obtain target signal analysis result information; the target signal analysis result information includes first target analysis result information and second target analysis result information;

[0148] A second processing module 203, configured to perform judgment analysis processing on the target signal analysis result information to obtain target sign parameter monitoring result information.

[0149] It can be seen that implementing Figure 3 The described signal processing device for non-contact physiological sign parameter monitoring is beneficial to realizing real-time non-contact remote multi-modal physiological sign parameter measurement, and improving the efficiency and accuracy of physiological sign parameter monitoring.

[0150] In another optional embodiment, as Figure 3 shown, performing feature analysis processing on the multi-modal sign signal information to obtain target signal analysis result information includes:

[0151] Performing feature analysis on the first-modal sign signal information to obtain first signal feature information;

[0152] Performing feature analysis on the second-modal sign signal information to obtain second signal feature information; the second signal feature information includes first signal component feature information, second signal component feature information, and third signal component feature information;

[0153] Determining first target analysis result information based on the first signal feature information and the second signal feature information;

[0154] Determining second target analysis result information based on the second signal feature information.

[0155] It can be seen that implementing Figure 3The described signal processing device for non-contact physiological sign parameter monitoring facilitates the realization of real-time non-contact remote multi-modal physiological sign parameter measurement, improving the efficiency and accuracy of physiological sign parameter monitoring.

[0156] In yet another alternative embodiment, as Figure 3 shown, perform feature analysis on the second-modal sign signal information to obtain second signal feature information, including:

[0157] Perform image optimization processing on the second-modal sign signal information to obtain optimized-modal sign signal information;

[0158] Perform feature extraction processing on the optimized-modal sign signal information to obtain second signal feature information.

[0159] It can be seen that implementing Figure 3 the described signal processing device for non-contact physiological sign parameter monitoring facilitates the realization of real-time non-contact remote multi-modal physiological sign parameter measurement, improving the efficiency and accuracy of physiological sign parameter monitoring.

[0160] In yet another alternative embodiment, as Figure 3 shown, perform image optimization processing on the second-modal sign signal information to obtain optimized-modal sign signal information, including:

[0161] Perform first-dimension filtering processing on the second-modal sign signal information to obtain first optimized sign signal information;

[0162] Perform second-dimension filtering processing on the first optimized sign signal information to obtain second optimized sign signal information;

[0163] Perform signal amplification processing on the second optimized sign signal information to obtain third optimized sign signal information;

[0164] Perform image synthesis processing on the third optimized sign signal information to obtain synthesized-modal sign signal information;

[0165] Perform superposition and fusion processing on the synthesized-modal sign signal information and the second-modal sign signal information to obtain optimized-modal sign signal information.

[0166] It can be seen that implementing Figure 3 the described signal processing device for non-contact physiological sign parameter monitoring facilitates the realization of real-time non-contact remote multi-modal physiological sign parameter measurement, improving the efficiency and accuracy of physiological sign parameter monitoring.

[0167] In yet another alternative embodiment, as Figure 3 shown, perform feature extraction processing on the optimized-modal sign signal information to obtain second signal feature information, including:

[0168] Perform color channel separation on the optimized modal sign signal information to obtain first color image information, second color image information, and third color image information; the first color image information includes a number of first sub-color image information; the second color image information includes a number of second sub-color image information; the third color image information includes a number of third sub-color image information;

[0169] Perform signal optimization processing on the first color image information to obtain first signal component feature information;

[0170] Perform signal optimization processing on the second color image information to obtain second signal component feature information;

[0171] Perform signal optimization processing on the third color image information to obtain third signal component feature information.

[0172] It can be seen that implementing Figure 3 the described signal processing device for non-contact physiological sign parameter monitoring is conducive to realizing real-time non-contact remote multi-modal physiological sign parameter measurement, and improving the monitoring efficiency and accuracy of physiological sign parameters.

[0173] In another optional embodiment, as Figure 3 shown, performing signal optimization processing on the first color image information to obtain first signal component feature information includes:

[0174] For any first sub-color image information in the first color image information, use the first signal calculation model to perform calculation processing on the first sub-color image information to obtain the color signal value corresponding to the first sub-color image information;

[0175] Among them, the first signal calculation model is:

[0176]

[0177] In the formula, y represents the color signal value; xsz(a, b) represents the gray value at the coordinate (a, b) in the image corresponding to the first sub-color image information; X and Y respectively represent the number of rows and columns of the pixel points in the image corresponding to the first sub-color image information;

[0178] Arrange all the color signal values in the order from front to back according to the time sequence corresponding to the first sub-color image information to obtain first color signal value information;

[0179] Perform smoothing processing on the first color signal value information to obtain the first signal component feature information.

[0180] It can be seen that implementing Figure 3The described signal processing device for non-contact physiological sign parameter monitoring is conducive to realizing real-time non-contact remote multi-modal physiological sign parameter measurement, and improving the efficiency and accuracy of physiological sign parameter monitoring.

[0181] In yet another alternative embodiment, as Figure 3 shown, based on the first signal feature information and the second signal feature information, a first target analysis result information is determined, including:

[0182] Performing fusion processing on the first signal feature information and the second signal feature information to obtain third signal feature information;

[0183] Performing outlier removal processing on the third signal feature information to obtain fourth signal feature information;

[0184] Performing spectrum analysis on the fourth signal feature information to obtain the first target analysis result information.

[0185] It can be seen that implementing Figure 3 the described signal processing device for non-contact physiological sign parameter monitoring is conducive to realizing real-time non-contact remote multi-modal physiological sign parameter measurement, and improving the efficiency and accuracy of physiological sign parameter monitoring.

[0186] Embodiment III

[0187] Please refer to Figure 4 , Figure 4 which is a schematic structural diagram of another signal processing device for non-contact physiological sign parameter monitoring disclosed in the embodiments of the present invention. Among them, Figure 4 the described device can be applied to a management system, such as a local server or a cloud server for management, etc., which is not limited in the embodiments of the present invention. As Figure 4 shown, the device may include:

[0188] A memory 301 storing executable program code;

[0189] A processor 302 coupled to the memory 301;

[0190] The processor 302 calls the executable program code stored in the memory 301 to execute the steps in the signal processing method for non-contact physiological sign parameter monitoring described in Embodiment I.

[0191] Embodiment IV

[0192] The embodiments of the present invention disclose a computer-readable storage medium, which stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps in the signal processing method for non-contact physiological sign parameter monitoring described in Embodiment I.

[0193] Example 5

[0194] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the steps in the signal processing method for non-contact physiological sign parameter monitoring described in Example 1.

[0195] The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without creative labor.

[0196] Through the above specific descriptions of the embodiments, those skilled in the art can clearly understand that each implementation mode can be realized by means of software plus a necessary general hardware platform, and of course, it can also be realized by hardware. Based on such an understanding, the above technical solution, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, and the storage medium includes read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc memories, magnetic disk memories, tape memories, or any other computer-readable medium capable of carrying or storing data.

[0197] Finally, it should be noted that what is disclosed in a signal processing method for non-contact physiological sign parameter monitoring disclosed by the embodiments of the present invention is only the preferred embodiments of the present invention, which is only used to illustrate the technical solutions of the present invention, rather than limiting it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A signal processing method, characterized in that: The method comprises: Acquire multimodal vital sign signal information; the multimodal vital sign signal information includes first modal vital sign signal information and second modal vital sign signal information; the second modal vital sign signal information includes a plurality of vital sign image information distributed in time sequence; Performing feature analysis processing on the multimodal vital sign signal information to obtain target signal analysis result information; the target signal analysis result information includes first target analysis result information and second target analysis result information; The target signal analysis result information is judged, analyzed and processed to obtain the target vital sign parameter monitoring result information.

2. The signal processing method according to claim 1, characterized in that: The performing feature analysis processing on the multimodal vital sign signal information to obtain target signal analysis result information includes: Performing feature analysis on the first modal vital sign signal information to obtain first signal feature information; Performing feature analysis on the second modal vital sign signal information to obtain second signal feature information; the second signal feature information includes first signal component feature information, second signal component feature information and third signal component feature information; Determining the first target analysis result information based on the first signal feature information and the second signal feature information; Based on the second signal characteristic information, second target analysis result information is determined.

3. The signal processing method according to claim 2, characterized in that: The performing feature analysis on the second modal vital sign signal information to obtain second signal feature information includes: performing image optimization processing on the second modality vital sign signal information to obtain optimized modality vital sign signal information; The optimized modal vital sign signal information is subjected to feature extraction processing to obtain second signal feature information.

4. The signal processing method according to claim 3, characterized in that: The performing image optimization processing on the second modality vital sign signal information to obtain optimized modality vital sign signal information includes: Performing first-dimensional filtering processing on the second modal vital sign signal information to obtain first optimized vital sign signal information; Performing second-dimensional filtering processing on the first optimized vital sign signal information to obtain second optimized vital sign signal information; performing signal amplification processing on the second optimized vital sign signal information to obtain third optimized vital sign signal information; Performing image synthesis processing on the third optimized vital sign signal information to obtain synthetic modality vital sign signal information; The synthetic modality vital sign signal information and the second modality vital sign signal information are superimposed and fused to obtain optimized modality vital sign signal information.

5. The signal processing method according to claim 3, characterized in that: The step of performing feature extraction processing on the optimized modal vital sign signal information to obtain second signal feature information includes: Performing color channel separation on the optimized modality vital sign signal information to obtain first color image information, second color image information and third color image information; the first color image information includes a plurality of the first sub-color image information; the second color image information includes a plurality of the second sub-color image information; the third color image information includes a plurality of the third sub-color image information; Performing signal optimization processing on the first color image information to obtain the first signal component characteristic information; performing signal optimization processing on the second color image information to obtain characteristic information of the second signal component; Signal optimization processing is performed on the third color image information to obtain the third signal component characteristic information.

6. The signal processing method according to claim 5, characterized in that: The performing signal optimization processing on the first color image information to obtain the first signal component characteristic information includes: For any of the first sub-color image information in the first color image information, use a first signal calculation model to calculate and process the first sub-color image information to obtain a color signal value corresponding to the first sub-color image information; Wherein, the first signal calculation model is: Wherein, y represents the color signal value; xsz(a, b) represents the gray value of the coordinates (a, b) in the image corresponding to the first sub-color image information; X and Y represent the number of rows and columns of pixels in the image corresponding to the first sub-color image information, respectively; Arrange all the color signal values ​​from front to back according to the time sequence corresponding to the first sub-color image information to obtain first color signal value information; The first color signal value information is smoothed to obtain the first signal component feature information.

7. The signal processing method according to claim 2, characterized in that: The determining the first target analysis result information based on the first signal feature information and the second signal feature information includes: fusing the first signal characteristic information and the second signal characteristic information to obtain third signal characteristic information; Performing outlier removal processing on the third signal characteristic information to obtain fourth signal characteristic information; Perform spectrum analysis on the fourth signal characteristic information to obtain first target analysis result information.

8. A signal processing device, characterized in that: The device comprises: An acquisition module, used for acquiring multi-modal vital sign signal information; the multi-modal vital sign signal information includes first-modal vital sign signal information and second-modal vital sign signal information; the second-modal vital sign signal information includes a plurality of vital sign image information distributed in time sequence; A first processing module is used to perform feature analysis processing on the multimodal vital sign signal information to obtain target signal analysis result information; the target signal analysis result information includes first target analysis result information and second target analysis result information; The second processing module is used to judge, analyze and process the target signal analysis result information to obtain target vital sign parameter monitoring result information.

9. A signal processing device, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the signal processing method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the signal processing method according to any one of claims 1 to 7.

Images