Waveform parameter detection method and device of multi-parameter monitor
By using image acquisition and deep learning technology on a multi-parameter monitor, waveform parameters are automatically extracted and analyzed, and the problems of low efficiency and error prone in traditional methods are solved, and efficient and accurate waveform parameter detection is achieved.
Patent Information
- Application Number
- CN202510301270.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-14
- Publication Date
- 2025-06-27
AI Technical Summary
When traditional methods detect waveform parameters such as the ECG voltage, amplitude and frequency characteristics and scanning speed of multi-parameter monitors, there are problems such as strong subjectivity, low efficiency and error-prone, and cannot effectively solve the problems of signal noise, interference, data acquisition quality and complex parameters.
The original monitoring image on the monitor screen is obtained through the image acquisition device, and the waveform image and numerical image are extracted using the YOLOv11 network fused with the BiFPN module, the average amplitude and period width of the waveform signal are identified, the actual values of the waveform amplitude and wavelength are calculated, and the numerical values in the numerical image are identified through the OCR model.
It realizes automatic detection of waveform parameters of multi-parameter monitors, improves detection efficiency and accuracy, reduces the time and cost of manual operation, and is suitable for monitors of different brands and models, with good versatility and applicability.
Smart Images
Figure CN120213102A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of parameter detection of medical monitoring devices, and particularly relates to a method and device for detecting waveform parameters of a multi-parameter monitor. Background Art
[0002] A multi-parameter monitor is a typical vital sign monitoring device that can real-time monitor important parameters of the human body such as electrocardiogram, non-invasive blood pressure, pulse oximetry, and end-tidal carbon dioxide through various functional modules. It is widely used in the emergency rooms, operating rooms, and intensive care units of hospitals and is an important device for clinical diagnosis and monitoring, directly related to the life and health of patients.
[0003] Currently, for the detection of multi-parameter monitors, in the JJG 1163-2019 Verification Regulation for Multi-parameter Monitors, it is clearly stipulated that the verification items of monitors cover four categories of electrocardiogram, non-invasive blood pressure, pulse oxygen saturation, and end-tidal carbon dioxide, a total of 12 vital sign parameters. Among them, the electrocardiogram waveform parameters mainly include waveform parameters such as electrocardiogram voltage, amplitude-frequency characteristics, and sweep speed. Since traditional methods rely on manual operations such as waveform observation and data recording when detecting waveform parameters such as electrocardiogram voltage, amplitude-frequency characteristics, and sweep speed of multi-parameter monitors, and obtain detection results by means of human eye observation and steel ruler measurement, there are problems such as strong subjectivity, low efficiency, and easy error. In addition, there are problems such as signal noise, interference, data acquisition quality, and complex parameters in waveform parameters, and traditional detection methods often cannot solve them.
[0004] Therefore, it is necessary to develop a method for detecting waveform parameters in the automated detection process of multi-parameter monitors, which can efficiently and accurately extract and analyze the waveform parameters of monitors. Summary of the Invention
[0005] In view of the above-mentioned defects or deficiencies in the prior art, the present invention provides a method and device for detecting waveform parameters of a multi-parameter monitor, which can realize the automated detection of waveform parameters of a multi-parameter monitor to improve the efficiency and accuracy of detection.
[0006] In one aspect of the present invention, a method for detecting waveform parameters of a multi-parameter monitor is provided, including: obtaining an original monitor image on the monitor screen through an image acquisition device; extracting a waveform image and a numerical image in the original monitor image through a YOLOv11 network integrated with a BiFPN module, wherein the BiFPN module is arranged before each C3k2 module in the neck network of YOLOv11; identifying the pixel difference of the average amplitude of the waveform signal and the pixel difference of the average period width of the waveform signal in the waveform image, and calculating the actual values of the waveform amplitude and the waveform wavelength according to the unit pixel size, the pixel difference of the average amplitude of the waveform signal, and the pixel difference of the average amplitude of the waveform signal; and identifying the numerical value in the numerical image through an OCR model.
[0007] On the other hand, the present invention also provides a waveform parameter detection device for a multi-parameter monitor, including: an image acquisition module for acquiring an original monitor image on the monitor screen through an image acquisition device; an image extraction module for extracting a waveform image and a numerical image in the original monitor image through a YOLOv11 network integrated with a BiFPN module, wherein the BiFPN module is arranged before each C3k2 module in the neck network of YOLOv11; a waveform recognition module for recognizing the pixel difference of the average amplitude of the waveform signal and the pixel difference of the average period width of the waveform signal in the waveform image, and calculating the actual values of the waveform amplitude and the waveform wavelength according to the unit pixel size, the pixel difference of the average amplitude of the waveform signal, and the pixel difference of the average amplitude of the waveform signal; a numerical value recognition module for recognizing the numerical value in the numerical image through an OCR model.
[0008] The waveform parameter detection method and device for a multi-parameter monitor provided by the present invention improve the efficiency and accuracy of waveform parameter detection, reduce the time and cost of manual operation, have strong scalability, are applicable to multi-parameter monitors of different brands and models, and have good versatility and applicability. BRIEF DESCRIPTION OF THE DRAWINGS
[0009] Other features, objects, and advantages of the present application will become more apparent by reading the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 is a flowchart of a waveform parameter detection method for a multi-parameter monitor provided by an embodiment of the present application Figure 1 ; Figure 2 is a flowchart of a waveform parameter detection method for a multi-parameter monitor provided by an embodiment of the present application Figure 2 ; Figure 3 is a schematic diagram of an original monitor image provided by an embodiment of the present application; Figure 4 is a schematic diagram of the structure of a target detection network provided by an embodiment of the present application; Figure 5 is a schematic diagram of the detection result of a square wave signal provided by an embodiment of the present application; Figure 6 is a schematic diagram of the detection result of a sine wave signal provided by an embodiment of the present application; Figure 7 is a schematic diagram of the structure of a waveform parameter detection device for a multi-parameter monitor provided by an embodiment of the present application; Figure 8 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0010] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, 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. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.
[0011] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.
[0012] It should be understood that although the terms first, second, third, etc. may be used in the embodiments of the present invention to describe the acquisition modules, these acquisition modules should not be limited to these terms. These terms are only used to distinguish the acquisition modules from each other.
[0013] Depending on the context, the word "if" as used herein can be interpreted as "when" or "while" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if determined" or "if detecting (stated condition or event)" can be interpreted as "when determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)".
[0014] It should be noted that the orientation terms such as "upper", "lower", "left", "right", etc. described in the embodiments of the present invention are described from the angles shown in the accompanying drawings, and should not be construed as limiting the embodiments of the present invention. In addition, in the context, it should also be understood that when it is mentioned that one element is formed "on" or "under" another element, it can not only be directly formed "on" or "under" another element, but also be indirectly formed "on" or "under" another element through an intermediate element.
[0015] In the prior art, metrology personnel often obtain the detection parameters of a multi-parameter monitor manually. For example: relying on the human eye and experience to select measurement points, using a magnifying glass and a steel ruler to measure the distance difference of the vertical coordinates between two measurement points as the actual amplitude, and calculating the electrocardiogram waveform parameters according to the recorded data. The traditional detection method has low efficiency, and the detection result highly depends on the experience and operation specifications of the operator, resulting in problems of unstable measurement data and low accuracy.
[0016] To solve the above technical problems, an embodiment of the present application provides a method for detecting waveform parameters of a multi-parameter monitor. See Figure 1 , 2 , the method includes the following steps: Step S101, obtaining an original monitor image on the monitor screen through an image acquisition device; Specifically, first, use a camera or other image acquisition device to obtain the original monitor image on the monitor screen. See Figure 3 , the original monitor image includes parameters such as electrocardiogram waveform signals, heart rate values, blood oxygen saturation values, pulse rate values, dynamic blood pressure values, static blood pressure values, and respiratory rate values.
[0017] Step S102, extracting waveform images and numerical images from the original monitor image through the YOLOv11 network integrated with the BiFPN module; wherein, the BiFPN module is arranged before each C3k2 module in the neck network of YOLOv11; See Figure 4 , in this embodiment, the network architecture of YOLOv11+BiFPN is selected as the improved object detection network. The improved object detection network includes a backbone network, a neck network, and a detection head.
[0018] Among them, the main task of the backbone network is to extract multi-dimensional features from the input original monitor image and generate a high-dimensional feature map.
[0019] Among them, the neck network is located between the backbone network and the detection head. Its main function is to further enhance the features extracted by the backbone network and provide richer and more suitable features for the detection head for the object detection task. In this embodiment, the BiFPN module is introduced before each C3k2 module in the YOLOv11 neck network. On the one hand, the multi-scale feature fusion of the BiFPN module can more effectively improve the global nature of feature expression, making the subsequent C3K2 module more efficient in extracting features; on the other hand, by optimizing the feature map in advance through the BiFPN module, the processing burden of the C3K2 module can be reduced, thereby improving the overall robustness of the network; on the other hand, the BiFPN module set before the C3K2 module can also better fuse the detailed features of small targets and improve the detection performance of small targets; finally, the BiFPN module fuses multi-dimensional features, uses its efficient weighted feature convergence, inputs the enhanced feature map into the subsequent detection head for accurate object localization and classification, can achieve enhanced box selection for each type in the classification label parameters, extract and return colors and position coordinates, and at the same time divide the trend parameters into waveform parameters and numerical parameters for further processing.
[0020] Among them, the detection head is the last part of the object detection network, directly responsible for generating the final detection results, including the category and location of the object, enabling the features targeted at image classification extracted from the backbone network to be effectively transformed into features suitable for object detection, further enhancing the network's performance in processing complex scenes and diverse objects.
[0021] Finally, the waveform image and the numerical image in the original monitoring image are extracted through the improved object detection network.
[0022] Step S103: Identify the pixel difference of the average amplitude of the waveform signal and the pixel difference of the average period width of the waveform signal in the waveform image, and calculate the actual values of the waveform amplitude and the waveform wavelength according to the unit pixel size, the pixel difference of the average amplitude of the waveform signal, and the pixel difference of the average amplitude of the waveform signal. Specifically, this step identifies the waveform amplitude and the waveform wavelength of the square wave signal and the sine wave signal in the obtained waveform image. The following details the extraction steps of the amplitude and wavelength of various waveform signals in this embodiment.
[0023] (1) Inflection point detection Refer to Figure 5 , use the Harris corner detection algorithm to detect all the feature points of the rising edge and the falling edge of the square wave signal in the waveform image, obtain the ordinate values of all the feature points, sort them according to the ordinate size, and screen out the upper inflection points of the rising edge (type A), the lower inflection points of the rising edge (type B), the upper inflection points of the falling edge (type C), and the lower inflection points of the falling edge (type D) and other four types of inflection points from the ordinate values of the feature points. Among them, the preset screening threshold can filter out the points with lower response values and only retain the feature points that may be real inflection points.
[0024] Refer to Figure 6 , adopt a method similar to that for detecting the square wave signal, use the Harris corner detection algorithm to detect all the feature points of the rising edge and the falling edge of the sine wave signal in the waveform image (the inflection points of the rising edge of the sine wave signal are also the inflection points of the falling edge), obtain the ordinate values of all the feature points, sort them according to the ordinate size, and screen out the peak points and the valley points from the ordinate values of the feature points.
[0025] (2) Pixel difference of the average amplitude of the waveform Calculate the pixel difference of the average amplitude of the square wave signal according to the following formula : Among them, p represents the number of upper inflection points of the rising edge, q represents the number of lower inflection points of the rising edge, represents the ordinate value of the i-th upper inflection point of the rising edge, represents the ordinate value of the lower inflection point of the i-th rising edge; alternatively, p represents the number of upper inflection points of the falling edge, q represents the number of lower inflection points of the falling edge, represents the ordinate value of the upper inflection point of the i-th falling edge, represents the ordinate value of the lower inflection point of the i-th falling edge. That is to say, the effect of calculating with the two inflection points of the rising edge of the square wave and calculating with the two inflection points of the falling edge of the square wave is the same.
[0026] Calculate the pixel difference of the average amplitude of the sine wave signal according to the following formula : where p represents the number of peak points, q represents the number of valley points, represents the ordinate value of the i-th peak point, represents the ordinate value of the i-th valley point.
[0027] Pixel difference of the average period width of the waveform The waveform on the monitor has a certain scanning speed, and the scanning speed represents the moving speed of the waveform on the screen. For example: 25 mm / s, 50 mm / s, etc. For a scanning speed of 25 mm / s, the horizontal compression of the waveform signal is less, and a longer period distance (such as four periods from A0 to A4) can be selected to calculate the period width; for a scanning speed of 50 mm / s, the horizontal compression of the waveform signal is more, and a long period distance will increase the error. Therefore, a shorter period distance (such as two periods from A0 to A2) is selected to calculate the period width, which is more suitable for the current scanning speed. In summary, the technical solution can also be summarized as: when the scanning speed is greater than the preset threshold, select a shorter period distance to calculate the period width; when the scanning speed is less than the preset threshold, select a longer period distance to calculate the period width. Among them, the preset threshold and the period distance can be determined according to experience and the actual scanning speed.
[0028] Specifically: When the scanning speed of the square wave signal is lower than the preset threshold, calculate the pixel difference of the average period width of the waveform signal according to the following formula : where represents the total number of upper inflection points of the rising edge in the square wave signal, represents the abscissa value of the (i + 4)-th upper inflection point of the rising edge, represents the abscissa value of the i-th upper inflection point of the rising edge; or, represents the total number of upper inflection points of the falling edge in the square wave signal, represents the abscissa value of the (i + 4)-th upper inflection point of the falling edge, represents the abscissa value of the upper inflection point of the i-th falling edge. That is to say, the calculation effect using the inflection point of the rising edge of the square wave is the same as that using the inflection point of the falling edge of the square wave.
[0029] When the scanning speed of the square wave signal is higher than the preset threshold, calculate the pixel difference of the average period width of the square wave signal according to the following formula : where, represents the total number of upper inflection points of the rising edge in the square wave signal, represents the abscissa value of the (i + 2)-th upper inflection point of the rising edge, represents the abscissa value of the i-th upper inflection point of the rising edge; or, represents the total number of upper inflection points of the falling edge in the square wave signal, represents the abscissa value of the (i + 2)-th upper inflection point of the falling edge, represents the abscissa value of the i-th upper inflection point of the falling edge; that is to say, the calculation effect using the inflection point of the rising edge of the square wave is the same as that using the inflection point of the falling edge of the square wave.
[0030] When the scanning speed of the sine wave signal is lower than the preset threshold, calculate the pixel difference of the average period width of the sine wave signal according to the following formula : where, represents the total number of peak points of the sine wave signal, represents the abscissa value of the (i + 4)-th peak point, represents the abscissa value of the i-th peak point; or, represents the total number of valley points of the sine wave signal, represents the abscissa value of the (i + 4)-th valley point, represents the abscissa value of the i-th valley point; that is to say, the calculation effect using the peak point of the sine wave is the same as that using the valley point of the sine wave.
[0031] When the scanning speed of the sine wave signal is higher than the preset threshold, calculate the pixel difference of the average period width of the sine wave signal according to the following formula : where, represents the total number of peak points of the sine wave signal, represents the abscissa value of the (i + 2)-th peak point, represents the abscissa value of the i-th peak point; or, represents the total number of valley points in the sine wave signal, represents the abscissa value of the (i + 2)-th valley point, represents the abscissa value of the i-th valley point; that is to say, the effect of calculating using the peak points of the sine wave and calculating using the valley points of the sine wave is the same.
[0032] Actual value calculation According to the unit pixel size, the pixel difference of the average amplitude of the waveform signal, and the pixel difference of the average amplitude of the waveform signal, the actual values of the waveform amplitude and the waveform wavelength are calculated.
[0033] Step S104, recognize the numerical values in the numerical image through the OCR model.
[0034] Specifically, the OCR text detection and recognition model is a technology based on image processing and machine learning for extracting text information from images. In this embodiment, the OCR system is divided into three parts: text detection, text recognition, and direction classifier. First, use the text detection algorithm to obtain the polygon information of the text area; then, crop, perform perspective transformation, and perspective correction on the text area, convert the perspective-corrected text area into a rectangular box, and use the direction classifier to correct the text direction within the rectangular box; finally, recognize the text within the rectangular box to obtain the recognition result of the numerical image. Preferably, use the text detection algorithm based on segmentation and the CRNN text recognition algorithm.
[0035] The waveform parameter detection method of the multi-parameter monitor provided by this embodiment improves the efficiency and accuracy of waveform parameter detection, reduces the time and cost of manual operation, has strong scalability, is applicable to multi-parameter monitors of different brands and models, and has good versatility and applicability.
[0036] See Figure 7 , another embodiment of the present invention also provides a waveform parameter detection device 200 for a multi-parameter monitor, including an image acquisition module 201, an image extraction module 202, a waveform recognition module 203, and a numerical value recognition module 204. The waveform parameter detection device 200 for a multi-parameter monitor can execute the waveform parameter detection method for a multi-parameter monitor in the method embodiment.
[0037] Specifically, the waveform parameter detection device 200 for a multi-parameter monitor includes: The image acquisition module 201 is used to obtain the original monitor image on the monitor screen through an image acquisition device; The image extraction module 202 is used to extract the waveform image and the numerical image from the original monitoring image through the YOLOv11 network integrated with the BiFPN module. Among them, the BiFPN module is arranged before each C3k2 module in the neck network of YOLOv11. The waveform recognition module 203 is used to recognize the pixel difference of the average amplitude of the waveform signal and the pixel difference of the average period width of the waveform signal in the waveform image, and calculate the actual values of the waveform amplitude and the waveform wavelength according to the unit pixel size, the pixel difference of the average amplitude of the waveform signal, and the pixel difference of the average amplitude of the waveform signal. The numerical value recognition module 204 is used to recognize the numerical value in the numerical image through the OCR model.
[0038] It should be noted that the waveform parameter detection device 200 of the multi-parameter monitor provided in this embodiment can be used to execute the technical solutions of the method embodiments. Its implementation principle and technical effects are similar to those of the method, and will not be elaborated here.
[0039] See Figure 8 , another embodiment of the present invention provides a schematic structural diagram of an electronic device 300, which is used to implement the waveform parameter detection method of the multi-parameter monitor in the method embodiment. The electronic device 300 in the embodiment of the present invention may include, but is not limited to, computer devices such as smart phones, PDAs, tablet computers, PCs, or notebook computers. Figure 8 The illustrated electronic device 300 is only an example and should not impose any limitations on the functions and usage scope of the embodiments of the present invention.
[0040] As Figure 8 shown, the electronic device 300 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 301, which can execute various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage device 308 into the random access memory (RAM) 303 to implement the method of the embodiments as described in the present invention. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other through a bus 304. The input / output (I / O) interface 305 is also connected to the bus 304.
[0041] Typically, the following devices can be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 can allow the electronic device 300 to communicate with other devices wirelessly or wiredly to exchange data. Although Figure 8 the electronic device 300 with various devices is shown, it should be understood that it is not required to implement or have all the shown devices. More or fewer devices can be alternatively implemented or had.
[0042] The above description is only a preferred embodiment of the present invention. Those skilled in the art should understand that the disclosed scope in the present invention is not limited to the technical solution formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the technical solution formed by mutually replacing the above features with the technical features (but not limited to) having similar functions disclosed in the present invention.
Claims
1. A waveform parameter detection method for a multi-parameter monitor, characterized in that include: Acquire the original monitoring image on the monitor screen through the image acquisition device; The waveform image and the numerical image in the original monitoring image are extracted by a YOLOv11 network integrated with a BiFPN module; wherein the BiFPN module is arranged before each C3k2 module of the neck network of YOLOv11; Identify the pixel difference of the average amplitude of the waveform signal and the pixel difference of the average cycle width of the waveform signal in the waveform image, and calculate the actual values of the waveform amplitude and the waveform wavelength according to the unit pixel size, the pixel difference of the average amplitude of the waveform signal and the pixel difference of the average amplitude of the waveform signal; Recognize the numerical value in the numerical image through the OCR model.
2. The waveform parameter detection method of a multi-parameter monitor according to claim 1, characterized in that: The step of identifying the pixel difference of the average amplitude of the waveform signal and the pixel difference of the average cycle width of the waveform signal in the waveform image comprises: Detect all feature points of the rising and falling edges of the square wave signal, obtain the ordinate values of all feature points, and sort them by the size of the ordinates, and filter out the upper inflection point of the rising edge, the lower inflection point of the rising edge, the upper inflection point of the falling edge, and the lower inflection point of the falling edge from the ordinate values of the feature points according to a preset threshold; and detect all feature points of the rising and falling edges of the sinusoidal wave signal, obtain the ordinate values of all feature points, and sort them by the size of the ordinates, and filter out the peak points and valley points from the ordinate values of the feature points.
3. The waveform parameter detection method of a multi-parameter monitor according to claim 2, characterized in that: The step of identifying the pixel difference of the average amplitude of the waveform signal in the waveform image comprises: The pixel difference of the average amplitude of the square wave signal is calculated according to the following formula : Among them, p represents the number of inflection points on the upper part of the rising edge, and q represents the number of inflection points on the lower part of the rising edge. Indicates the ordinate value of the upper inflection point of the i-th rising edge, represents the ordinate value of the lower inflection point of the i-th rising edge; or, p represents the number of upper inflection points of the falling edge, and q represents the number of lower inflection points of the falling edge. Indicates the ordinate value of the upper inflection point of the i-th falling edge, Indicates the ordinate value of the lower inflection point of the i-th falling edge.
4. The waveform parameter detection method of a multi-parameter monitor according to claim 2, characterized in that: The step of identifying the pixel difference of the average amplitude of the waveform signal in the waveform image comprises: The pixel difference of the average amplitude of the sine wave signal is calculated according to the following formula : Among them, p represents the number of peak points, q represents the number of valley points, Represents the ordinate value of the i-th peak point, Represents the ordinate value of the i-th valley point.
5. The waveform parameter detection method of a multi-parameter monitor according to claim 2, characterized in that: The step of identifying the pixel difference of the average cycle width of the waveform signal comprises: When the square wave signal scanning speed is lower than the preset threshold, the pixel difference of the average cycle width of the waveform signal is calculated according to the following formula: : in, Indicates the total number of inflection points on the rising edge of the square wave signal. Indicates the horizontal coordinate value of the upper inflection point of the i+4th rising edge, Represents the horizontal coordinate value of the upper inflection point of the i-th rising edge; or, Indicates the total number of inflection points on the falling edge of the square wave signal. Indicates the horizontal coordinate value of the upper inflection point of the i+4th falling edge, Indicates the horizontal coordinate value of the upper inflection point of the i-th falling edge; When the square wave signal scanning speed is higher than the preset threshold, the pixel difference of the average period width of the square wave signal is calculated according to the following formula: : in, Indicates the total number of inflection points on the rising edge of the square wave signal. Indicates the horizontal coordinate value of the upper inflection point of the i+2th rising edge, Represents the horizontal coordinate value of the upper inflection point of the i-th rising edge; or, Indicates the total number of inflection points on the falling edge of the square wave signal. Indicates the horizontal coordinate value of the upper inflection point of the i+2th falling edge, Indicates the horizontal coordinate value of the upper inflection point of the i-th falling edge.
6. The waveform parameter detection method of a multi-parameter monitor according to claim 2, characterized in that: The step of identifying the pixel difference of the average cycle width of the waveform signal comprises: When the scanning speed of the sine wave signal is lower than the preset threshold, the pixel difference of the average period width of the sine wave signal is calculated according to the following formula: : in, Represents the total number of peak points of the sine wave signal. Indicates the horizontal coordinate value of the i+4th peak point, represents the horizontal coordinate value of the i-th peak point; or, Represents the total number of valley points of the sine wave signal. Represents the horizontal coordinate value of the i+4th valley point, Represents the horizontal coordinate value of the i-th valley point; When the scanning speed of the sine wave signal is higher than the preset threshold, the pixel difference of the average period width of the sine wave signal is calculated according to the following formula: : in, Represents the total number of peak points of the sine wave signal. Indicates the horizontal coordinate value of the i+2th peak point, represents the horizontal coordinate value of the i-th peak point; or, Represents the total number of valley points in the sine wave signal. Represents the horizontal coordinate value of the i+2th valley point, Represents the horizontal coordinate value of the i-th valley point.
7. The waveform parameter detection method of a multi-parameter monitor according to claim 2, characterized in that: The step of identifying the numerical value in the numerical image by using the OCR model comprises: Use text detection algorithm to obtain polygon information of text area; The text area is cropped, perspective transformed and perspective corrected, the perspective-corrected text area is converted into a rectangular frame, and a direction classifier is used to correct the direction of the text in the rectangular frame; Recognize the text in the rectangular frame and obtain the recognition result of the numerical image.
8. A waveform parameter detection device for a multi-parameter monitor, characterized in that include: An image acquisition module is used to acquire the original monitoring image on the monitor screen through an image acquisition device; An image extraction module, used to extract a waveform image and a numerical image from an original monitoring image through a YOLOv11 network integrated with a BiFPN module; wherein the BiFPN module is arranged before each C3k2 module of the neck network of YOLOv11; A waveform recognition module is used to recognize the pixel difference of the average amplitude of the waveform signal and the pixel difference of the average cycle width of the waveform signal in the waveform image, and calculate the actual value of the waveform amplitude and the waveform wavelength according to the unit pixel size, the pixel difference of the average amplitude of the waveform signal and the pixel difference of the average amplitude of the waveform signal; The numerical recognition module is used to recognize numerical values in numerical images through the OCR model.
9. The waveform parameter detection device of a multi-parameter monitor according to claim 8, characterized in that: The waveform recognition module is also used for: Detect all feature points of the rising and falling edges of the square wave signal, obtain the ordinate values of all feature points, and sort them by the size of the ordinates, and filter out the upper inflection point of the rising edge, the lower inflection point of the rising edge, the upper inflection point of the falling edge, and the lower inflection point of the falling edge from the ordinate values of the feature points according to a preset threshold; and detect all feature points of the rising and falling edges of the sinusoidal wave signal, obtain the ordinate values of all feature points, and sort them by the size of the ordinates, and filter out the peak points and valley points from the ordinate values of the feature points.
10. The waveform parameter detection device of a multi-parameter monitor according to claim 9, characterized in that: The waveform recognition module is also used for: The pixel difference of the average amplitude of the square wave signal is calculated according to the following formula : Among them, p represents the number of inflection points on the upper part of the rising edge, and q represents the number of inflection points on the lower part of the rising edge. Indicates the ordinate value of the upper inflection point of the i-th rising edge, represents the ordinate value of the lower inflection point of the i-th rising edge; or, p represents the number of upper inflection points of the falling edge, and q represents the number of lower inflection points of the falling edge. Indicates the ordinate value of the upper inflection point of the i-th falling edge, Indicates the ordinate value of the lower inflection point of the i-th falling edge; The pixel difference of the average amplitude of the sine wave signal is calculated according to the following formula : Among them, p represents the number of peak points, q represents the number of valley points, Represents the ordinate value of the i-th peak point, Represents the ordinate value of the i-th valley point; When the square wave signal scanning speed is lower than the preset threshold, the pixel difference of the average cycle width of the waveform signal is calculated according to the following formula: : in, Indicates the total number of inflection points on the rising edge of the square wave signal. Indicates the horizontal coordinate value of the upper inflection point of the i+4th rising edge, Represents the horizontal coordinate value of the upper inflection point of the i-th rising edge; or, Indicates the total number of inflection points on the falling edge of the square wave signal. Indicates the horizontal coordinate value of the upper inflection point of the i+4th falling edge, Indicates the horizontal coordinate value of the upper inflection point of the i-th falling edge; When the square wave signal scanning speed is higher than the preset threshold, the pixel difference of the average period width of the square wave signal is calculated according to the following formula: : in, Indicates the total number of inflection points on the rising edge of the square wave signal. Indicates the horizontal coordinate value of the upper inflection point of the i+2th rising edge, Represents the horizontal coordinate value of the upper inflection point of the i-th rising edge; or, Indicates the total number of inflection points on the falling edge of the square wave signal. Indicates the horizontal coordinate value of the upper inflection point of the i+2th falling edge, Indicates the horizontal coordinate value of the upper inflection point of the i-th falling edge; When the scanning speed of the sine wave signal is lower than the preset threshold, the pixel difference of the average period width of the sine wave signal is calculated according to the following formula: : in, Represents the total number of peak points of the sine wave signal. Indicates the horizontal coordinate value of the i+4th peak point, represents the horizontal coordinate value of the i-th peak point; or, Represents the total number of valley points of the sine wave signal. Represents the horizontal coordinate value of the i+4th valley point, Represents the horizontal coordinate value of the i-th valley point; When the scanning speed of the sine wave signal is higher than the preset threshold, the pixel difference of the average period width of the sine wave signal is calculated according to the following formula: : in, Represents the total number of peak points of the sine wave signal. Indicates the horizontal coordinate value of the i+2th peak point, represents the horizontal coordinate value of the i-th peak point; or, Represents the total number of valley points in the sine wave signal. Represents the horizontal coordinate value of the i+2th valley point, Represents the horizontal coordinate value of the i-th valley point.