Passenger sudden cardiac arrest recognition system based on infrared thermal imaging

Abstract

The present application relates to a passenger sudden heart disease recognition system based on infrared thermal imaging, comprising: a central processing unit for providing computing transmission capability; a video acquisition module for acquiring behavior video information and infrared thermal imaging information; a video analysis module for analyzing abnormal behavior actions; a sudden heart disease recognition module for recognizing passengers with sudden heart disease and generating heart disease recognition information; an emergency warning module for real-time warning according to the heart disease recognition information. The present application greatly improves the timeliness and accuracy of the emergency department in public transportation places in identifying the sudden diseases of passengers in public transportation waiting areas; fundamentally solves the emergency management problems of passenger sudden heart disease recognition difficulty and notification not in time which cannot be solved by relying on artificial traditional inspection mode.

Description

Technical Field

[0001] This invention relates to the field of medical electronic instruments, and more specifically to a passenger sudden heart attack identification system based on infrared thermal imaging. Background Technology

[0002] If a passenger suffers a sudden heart attack while waiting for public transportation and cannot be detected and treated in time, it will not only delay the passenger's best treatment time, but may also cause chaos in the public transportation waiting area.

[0003] The current mainstream approach to emergency treatment of passengers suffering sudden heart attacks in public transportation waiting areas relies on visual observation by on-duty personnel, followed by notification of medical staff in the waiting area for emergency treatment; that is, the manual observation method.

[0004] The shortcomings of existing technology are:

[0005] 1. Due to the large number of people in public transportation waiting areas, it is difficult to detect abnormal behaviors caused by a sudden heart attack in passengers in a timely manner by manual observation, such as clutching the left chest or breathing rapidly, which can easily delay the best rescue window.

[0006] 2. Because the response speed of airport staff to emergency incidents varies depending on individual competence, there may be instances where emergency medical assistance requested from public transportation waiting areas is not timely. Summary of the Invention

[0007] To address the aforementioned problems, this invention provides a passenger sudden heart attack identification system based on infrared thermal imaging. Its purpose is to greatly improve the timeliness and accuracy of identifying sudden illnesses in passengers in public transportation waiting areas; and to fundamentally solve the emergency management problems of difficulty in identifying sudden heart attacks in passengers and untimely notification during traditional patrols of public transportation waiting areas, which cannot be solved manually.

[0008] To solve the above problems, the technical solution provided by the present invention is as follows:

[0009] A passenger sudden cardiac arrest identification system based on infrared thermal imaging includes the following components:

[0010] The central processing unit is used to provide computational processing and transmission capabilities for the data in this cardiac recognition system;

[0011] The video acquisition module is used to collect real-time video information and infrared thermal imaging information of passengers' behavior at a manually preset acquisition frequency.

[0012] The video analysis module is used to identify abnormal behaviors of passengers based on the behavioral video information collected by the video acquisition module. Then, the abnormal behavior identification result of the passenger with the abnormal behavior, the behavioral video information, and the infrared thermal imaging video information are transmitted to the sudden heart attack identification module through the central processing unit. The abnormal behavior identification result includes the abnormal behavior.

[0013] The sudden heart attack detection module analyzes the behavioral video information and infrared thermal imaging video information of passengers exhibiting abnormal behavior from the video analysis module to identify passengers with sudden heart attacks, generates heart attack detection information, and then transmits the heart attack detection information to the emergency warning module through the central processing unit. The heart attack detection information includes heart attack markers, high-density lipoprotein (HDL) levels, total cholesterol levels, surface temperature of the left hand, right temporal region, left neck, and right forefoot. The heart attack markers include the characters "0" and "1". When the heart attack marker is "0", it indicates that the passenger does not have a heart attack; when the heart attack marker is "1", it indicates that the passenger has a heart attack.

[0014] The emergency warning module is used to provide real-time warnings based on the heart disease identification information transmitted by the sudden heart disease identification module.

[0015] Preferably, the video acquisition module includes a high-definition camera for acquiring the behavioral video information and an infrared thermal imager for acquiring the infrared thermal imaging information; wherein:

[0016] The behavioral video information includes behavioral video frames, each of which contains a view of the passenger's behavior at the time of capture and a timestamp; all the behavioral video frames are arranged in ascending order according to the timestamps to form the behavioral video information.

[0017] The infrared thermal imaging information includes infrared thermal imaging frames, each of which contains an infrared thermal image of the passenger at the time of acquisition and the timestamp; all the infrared thermal imaging frames are arranged in ascending order according to the timestamps to form the infrared thermal imaging video information.

[0018] The sequence of timestamps in the behavioral video information is exactly the same as the sequence of timestamps in the infrared thermal imaging information; each behavioral video frame in the behavioral video information has a one-to-one correspondence with the infrared thermal imaging frame in the infrared thermal imaging information according to the timestamp it is stamped.

[0019] Preferably, the video analysis module includes a human target recognition unit for implementing human target detection, tracking, and action recognition functions, and an abnormal behavior recognition unit for detecting and identifying abnormal behavior in the behavioral video information based on a keypoint detection method; wherein:

[0020] The abnormal behavior identification and detection is performed by the AI ​​model in the abnormal behavior identification unit, and the output result is the abnormal behavior identification result.

[0021] The abnormal behaviors include covering one's chest with one's hands and slumping down.

[0022] Preferably, the sudden heart attack recognition module includes an image preprocessing unit, a thermal imaging image acquisition unit, and a sudden heart attack recognition unit; wherein:

[0023] The image preprocessing unit is used to preprocess the infrared thermal imaging frame to obtain a thermal imaging image;

[0024] The thermal imaging image acquisition unit acquires the surface temperature of the left hand, the surface temperature of the right temporal region, the surface temperature of the left neck, and the surface temperature of the right forefoot from the thermal imaging image;

[0025] The sudden heart attack identification unit is used to calculate and determine whether a passenger has a heart attack through a heart attack identification model.

[0026] Preferably, the sudden heart attack identification module analyzes the behavioral video information and infrared thermal imaging video information of passengers exhibiting abnormal behavior from the video analysis module to identify passengers with sudden heart attacks and generate the heart attack identification information, specifically including the following steps:

[0027] S100. The sudden heart attack identification module receives the abnormal behavior identification result, the behavior video information, and the infrared thermal imaging video information forwarded by the video analysis module from the central processing unit;

[0028] S200. The sudden heart attack recognition module extracts frames from the behavioral video information that record the abnormal behavioral action;

[0029] S300. The sudden heart attack identification module locates each infrared thermal imaging frame in the infrared thermal imaging video information according to the timestamp on each of the behavioral video frames; then the sudden heart attack identification module extracts frames from all the corresponding infrared thermal imaging frames.

[0030] S400. The image preprocessing unit preprocesses all the extracted infrared thermal imaging frames to obtain the thermal imaging image; then, it performs a gain operation on the thermal imaging image to make it clearer, resulting in a gained thermal imaging image.

[0031] S500. The thermal imaging image acquisition unit acquires the surface temperature of the left hand, the surface temperature of the right temporal region, the surface temperature of the left neck, and the surface temperature of the right forefoot from each thermal imaging image;

[0032] S600. The sudden heart attack identification unit calculates the high-density lipoprotein content and the total cholesterol content based on the heart attack identification model, the surface temperature of the left hand, the surface temperature of the right temporal region, the surface temperature of the left neck, and the surface temperature of the right forefoot.

[0033] S700. Compare the high-density lipoprotein (HDL) content with a pre-set HDL content threshold, and simultaneously compare the total cholesterol content with a pre-set total cholesterol threshold; then, based on the comparison results, perform the following operations:

[0034] If the high-density lipoprotein (HDL) level is less than the HDL level threshold and the total cholesterol level is higher than the total cholesterol level threshold, the passenger is determined to have heart disease; then S800 is executed.

[0035] If the high-density lipoprotein (HDL) level is not less than the HDL level threshold, or the total cholesterol level is not higher than the total cholesterol level threshold, then the passenger is determined not to have heart disease; then S900 is executed.

[0036] S800. Set the heart disease marker position to the character "1"; then package the heart disease marker position, the high-density lipoprotein content, the total cholesterol content, the surface temperature of the left hand, the surface temperature of the right temporal region, the surface temperature of the left neck, and the surface temperature of the right forefoot into the heart disease identification information; then execute S1000;

[0037] S900. Set the heart disease flag to the character "0"; then package the heart disease flag into the heart disease identification information; then execute S1000;

[0038] S1000. Output the heart disease identification information to the central processing unit; then the central processing unit forwards the heart disease identification information to the emergency warning module.

[0039] Preferably, the heart disease recognition model is expressed by the following formula:

[0040]

[0041] Wherein: HDL is the high-density lipoprotein content, in mg / dl; TC is the total cholesterol content, in mg / dl; X1 is the surface temperature of the left hand, in °C; X2 is the surface temperature of the right temporal region, in °C; X3 is the surface temperature of the left neck, in °C; X4 is the surface temperature of the right forefoot, in °C.

[0042] Preferably, step S400 involves performing a gain operation on the thermal imaging image to make it clearer, resulting in a gained thermal imaging image. This specifically includes the following steps:

[0043] S410. Calculate the grayscale values ​​of all pixels in the thermal image without gain operation;

[0044] S420. Draw a histogram corresponding to the gray level of a pixel and the number of pixels;

[0045] S430. The new gray level of each pixel is calculated using the histogram equalization algorithm;

[0046] S440. Obtain the enhanced thermal imaging image based on the new grayscale level of each pixel;

[0047] Preferably, the histogram equalization algorithm is expressed by the following formula:

[0048]

[0049] Wherein: S k Li is the new grayscale value of the pixel obtained after histogram equalization; L-1 is the maximum grayscale value of the thermal image; i0 is the minimum grayscale value in the thermal image without gain operation; i1 is the second smallest grayscale value in the thermal image without gain operation; i2 is the third smallest grayscale value in the thermal image without gain operation; M is the number of pixels on the wide side of the thermal image without gain operation; N is the number of pixels on the long side of the thermal image without gain operation; MN is the total number of pixels in the thermal image without gain operation; n i is the number of pixels with grayscale value i; k is the number of grayscale values ​​of the pixels in the thermal image without gain operation.

[0050] Preferably, the high-density lipoprotein content threshold is 400 mg / dl; and the total cholesterol content threshold is 200 mg / dl.

[0051] Preferably, the emergency warning module transmits the heart disease identification information via telephone, SMS, platform alarm, and broadcast to achieve real-time warning.

[0052] Compared with the prior art, the present invention has the following advantages:

[0053] 1. Since this invention does not rely on human discovery at all, but instead relies on AI models to identify the actions of passengers, and then calculates the possibility of a heart attack by linking temperature with objective values ​​of heart disease, it greatly improves the timeliness and accuracy of identifying sudden illnesses of passengers in public transportation waiting areas.

[0054] 2. Since the inspection and alarm functions of this invention are performed by a computer system, it fundamentally solves the emergency management problems of difficulty in identifying passengers suffering sudden heart attacks and untimely notification during traditional inspections of public transportation waiting areas, which cannot be solved manually. Attached Figure Description

[0055] Figure 1 This is a schematic diagram of the logical framework of a sudden heart attack recognition system according to a specific embodiment of the present invention;

[0056] Figure 2 This is a schematic diagram illustrating the process of identifying a passenger with a sudden heart attack and generating the heart attack identification information, as shown in a specific embodiment of the present invention. Detailed Implementation

[0057] The present invention will be further illustrated below with reference to specific embodiments. It should be understood that these embodiments are for illustrative purposes only and are not intended to limit the scope of the invention. After reading the present invention, any modifications of the present invention in various equivalent forms by those skilled in the art will fall within the scope defined by the appended claims.

[0058] like Figure 1 As shown, a passenger sudden cardiac arrest identification system based on infrared thermal imaging includes the following components:

[0059] The central processing unit (CPU) provides computational processing and transmission capabilities for the data in this cardiac recognition system.

[0060] The video acquisition module is used to collect real-time video information and infrared thermal imaging information of passengers' behavior at a manually preset acquisition frequency.

[0061] In this specific embodiment, the video acquisition module includes a high-definition camera for acquiring behavioral video information and an infrared thermal imager for acquiring infrared thermal imaging information; wherein:

[0062] Behavioral video information consists of behavioral video frames. Each behavioral video frame contains the passenger's behavior at the time of capture and a timestamp. All behavioral video frames are arranged in ascending order according to the timestamps to form behavioral video information.

[0063] Infrared thermal imaging information includes infrared thermal imaging frames. Each infrared thermal imaging frame contains an infrared thermal image of the passenger at the time of acquisition and a timestamp. All infrared thermal imaging frames are arranged in ascending order according to the timestamps to form infrared thermal imaging video information.

[0064] The sequence of timestamps in the behavioral video information is exactly the same as the sequence of timestamps in the infrared thermal imaging information; each behavioral video frame in the behavioral video information has a one-to-one correspondence with the infrared thermal imaging frame in the infrared thermal imaging information according to the timestamp it is stamped.

[0065] It should be noted that the high-definition camera in the video capture module acquires real-time surveillance video information of passengers in the public transportation waiting area; while the infrared thermal imager in the same module simultaneously tracks passengers, collects thermal image information, and sends it to the central processor. Since the thermal image only shows the outline of the temperature distribution, the privacy of the subjects can be protected.

[0066] It should be further explained that, in order to achieve a high degree of overlap between the objects captured by the high-definition camera and the infrared thermal imager, the high-definition camera and the infrared thermal imager need to be placed side by side, with the distance controlled at 10 centimeters.

[0067] It should be further explained that the genlock (synchronization phase-locked loop) system is used to enable the high-definition camera and the infrared thermal imager to work synchronously.

[0068] It should be further explained that the behavioral video information and infrared thermal imaging video information collected by the video acquisition module will be temporarily stored in the system. After being analyzed and identified by the video analysis module and the sudden heart attack recognition module, they will be saved as historical records and automatically deleted periodically by the administrator or the system.

[0069] The video analysis module is used to identify abnormal behaviors and actions of passengers from the behavioral video information collected by the video acquisition module. Then, the abnormal behavior identification results, behavioral video information, and infrared thermal imaging video information of passengers with abnormal behaviors and actions are transmitted to the sudden heart attack identification module through the central processor. The abnormal behavior identification results include abnormal behaviors and actions.

[0070] In this specific embodiment, the video analysis module includes a human target recognition unit for implementing human target detection, tracking, and action recognition functions, and an abnormal behavior recognition unit for detecting and identifying abnormal behavior in behavioral video information based on a keypoint detection method; wherein:

[0071] The abnormal behavior detection is performed by the AI ​​model in the abnormal behavior detection unit, and the output is the abnormal behavior detection result.

[0072] Abnormal behaviors include covering one's chest with one's hands and slumping down.

[0073] The sudden heart attack detection module analyzes behavioral video information and infrared thermal imaging video information of passengers exhibiting abnormal behavior from the video analysis module to identify passengers with sudden heart attacks, generating heart attack detection information. This information is then transmitted to the emergency warning module via the central processor. The heart attack detection information includes heart attack markers, high-density lipoprotein (HDL) levels, total cholesterol levels, surface temperature of the left hand, right temporal region, left neck, and right forefoot. The heart attack markers consist of the characters "0" and "1". When the heart attack marker is "0", it indicates that the passenger does not have a heart attack; when the heart attack marker is "1", it indicates that the passenger has a heart attack.

[0074] In this specific embodiment, the sudden heart attack recognition module includes an image preprocessing unit, a thermal imaging image acquisition unit, and a sudden heart attack recognition unit; wherein:

[0075] The image preprocessing unit is used to preprocess the infrared thermal imaging frames to obtain thermal imaging images.

[0076] The thermal imaging image acquisition unit acquires the surface temperatures of the left hand, right temporal region, left neck, and right forefoot from the thermal imaging images.

[0077] The sudden heart attack identification unit is used to calculate and determine whether a passenger is suffering from a heart attack using a heart attack identification model.

[0078] like Figure 2 As shown in this specific embodiment, the sudden heart attack recognition module analyzes the behavioral video information and infrared thermal imaging video information of passengers with abnormal behavior from the video analysis module, identifies passengers with sudden heart attacks, and generates heart attack recognition information. Specifically, this includes the following steps:

[0079] S100. The sudden heart attack recognition module receives abnormal behavior recognition results, behavioral video information, and infrared thermal imaging video information forwarded by the video analysis module from the central processing unit.

[0080] S200. The sudden heart attack recognition module extracts frames from behavioral video information that record abnormal behavioral actions.

[0081] The S300 sudden heart attack identification module locates each corresponding infrared thermal imaging frame in the infrared thermal imaging video information based on the timestamp on each behavioral video frame; then the sudden heart attack identification module extracts frames from all corresponding infrared thermal imaging frames.

[0082] S400. The image preprocessing unit preprocesses all the extracted infrared thermal imaging frames to obtain thermal imaging images; then, it performs a gain operation on the thermal imaging images to make them clearer, resulting in a gained thermal imaging image.

[0083] In this specific embodiment, step S400 involves performing a gain operation on the thermal imaging image to make it clearer, resulting in a gained thermal imaging image. This specifically includes the following steps:

[0084] S410. Calculate the grayscale values ​​of all pixels in the thermal image without gain operation.

[0085] S420. Draw a histogram corresponding to the gray levels of pixels and the number of pixels.

[0086] S430. The new gray level of each pixel is calculated using a histogram equalization algorithm.

[0087] In this specific embodiment, the histogram equalization algorithm is expressed according to equation (1):

[0088]

[0089] Wherein: S k Li represents the new grayscale value of the pixel after histogram equalization; L-1 represents the maximum grayscale value of the thermal image; i0 represents the minimum grayscale value of the thermal image without gain operation; i1 represents the second smallest grayscale value of the thermal image without gain operation; i2 represents the third smallest grayscale value of the thermal image without gain operation; M represents the number of pixels on the wide side of the thermal image without gain operation; N represents the number of pixels on the long side of the thermal image without gain operation; MN represents the total number of pixels in the thermal image without gain operation; n i is the number of pixels with grayscale value i; k is the number of grayscale values ​​of pixels in the thermal image without gain operation.

[0090] S440. Obtain the enhanced thermal image based on the new grayscale level of each pixel.

[0091] S500. The thermal imaging image acquisition unit acquires the surface temperatures of the left hand, right temporal region, left neck, and right forefoot from each thermal imaging image.

[0092] S600. The sudden heart attack identification unit calculates the high-density lipoprotein content and total cholesterol content based on the heart attack identification model and the surface temperatures of the left hand, right temporal region, left neck, and right forefoot.

[0093] S700. Compare the high-density lipoprotein (HDL) level with a pre-set HDL threshold, and simultaneously compare the total cholesterol level with a pre-set total cholesterol threshold; then, based on the comparison results, perform the following operations:

[0094] If the high-density lipoprotein (HDL) level is below the HDL threshold and the total cholesterol level is above the total cholesterol threshold, the passenger is diagnosed with heart disease; then S800 is executed.

[0095] If the high-density lipoprotein (HDL) level is not less than the HDL threshold, or the total cholesterol level is not higher than the total cholesterol threshold, the passenger is determined not to have heart disease; then S900 is executed.

[0096] In this specific embodiment, the threshold for high-density lipoprotein content is 400 mg / dl; the threshold for total cholesterol content is 200 mg / dl.

[0097] S800. Set the heart disease marker position to the character "1"; then package the heart disease marker position, high-density lipoprotein content, total cholesterol content, left hand surface temperature, right temporal surface temperature, left neck surface temperature, and right forefoot surface temperature into heart disease identification information; then execute S1000.

[0098] S900. Set the heart disease flag to the character "0"; then package the heart disease flag into heart disease identification information; then execute S1000.

[0099] S1000 outputs heart disease identification information to the central processing unit; then the central processing unit forwards the heart disease identification information to the emergency warning module.

[0100] In this specific embodiment, the heart disease identification model is expressed according to equations (2) and (3):

[0101]

[0102] Where: HDL is high-density lipoprotein content, in mg / dl; TC is total cholesterol content, in mg / dl; X1 is the surface temperature of the left hand, in °C; X2 is the surface temperature of the right temporal region, in °C; X3 is the surface temperature of the left neck, in °C; X4 is the surface temperature of the right forefoot, in °C.

[0103] The emergency warning module is used to provide real-time warnings based on the heart attack identification information transmitted by the sudden heart attack identification module.

[0104] In this specific embodiment, the emergency warning module transmits heart disease identification information via telephone, SMS, platform alarm, and broadcast to achieve real-time warning and provide rescue for passengers.

[0105] In the above detailed description, various features are combined together in a single embodiment to simplify this disclosure. This approach to disclosure should not be construed as reflecting an intention that embodiments of the claimed subject matter require more features than are explicitly stated in each claim. Rather, as reflected in the appended claims, the invention is presented with fewer features than all of the features of the single disclosed embodiment. Therefore, the appended claims are hereby explicitly incorporated into the detailed description, wherein each claim stands alone as a preferred embodiment of the invention.

[0106] The disclosed embodiments have been described above to enable any person skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be applied to other embodiments without departing from the spirit and scope of this disclosure. Therefore, this disclosure is not limited to the embodiments given herein, but is consistent with the broadest scope of the principles and novel features disclosed in this application.

[0107] The foregoing description includes examples of one or more embodiments. It is certainly impossible to describe all possible combinations of components or methods in order to describe the above embodiments, but those skilled in the art will recognize that further combinations and arrangements of the various embodiments are possible. Therefore, the embodiments described herein are intended to cover all such changes, modifications, and variations that fall within the scope of the appended claims. Furthermore, the term "comprising" as used in the specification or claims is interpreted in a manner similar to the term "including," as interpreted when used as a conjunction in the claims. Additionally, the use of any term "or" in the specification of the claims is intended to mean "non-exclusive or."

[0108] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A passenger sudden cardiac arrest identification system based on infrared thermal imaging, characterized in that: Includes the following parts: The central processing unit is used to provide computational processing and transmission capabilities for the data in this cardiac recognition system; The video acquisition module is used to collect real-time video information and infrared thermal imaging information of passengers' behavior at a manually preset acquisition frequency. The video analysis module is used to identify abnormal behaviors of passengers based on the behavioral video information collected by the video acquisition module. Then, the abnormal behavior identification result of the passenger with the abnormal behavior, the behavioral video information, and the infrared thermal imaging video information are transmitted to the sudden heart attack identification module through the central processing unit. The abnormal behavior identification result includes the abnormal behavior. The sudden heart attack detection module analyzes the behavioral video information and infrared thermal imaging video information of passengers exhibiting abnormal behavior from the video analysis module to identify passengers with sudden heart attacks, generates heart attack detection information, and then transmits the heart attack detection information to the emergency warning module through the central processing unit. The heart attack detection information includes heart attack markers, high-density lipoprotein (HDL) levels, total cholesterol levels, left hand surface temperature, right temporal region surface temperature, left neck surface temperature, and right forefoot surface temperature. The heart attack markers include the characters "0" and "1". When the heart attack marker is "0", it indicates that the passenger does not have a heart attack; when the heart attack marker is "1", it indicates that the passenger has a heart attack. The sudden heart attack identification module analyzes the behavioral video information and infrared thermal imaging video information of passengers exhibiting abnormal behavior from the video analysis module, identifies passengers with sudden heart attacks, and generates heart attack identification information. Specifically, this includes the following steps: S100. The sudden heart attack identification module receives the abnormal behavior identification result, the behavior video information, and the infrared thermal imaging video information forwarded by the video analysis module from the central processing unit; S200. The sudden heart attack recognition module extracts frames from the behavioral video information that record the abnormal behavioral action; S300. The sudden heart attack identification module locates each infrared thermal imaging frame in the infrared thermal imaging video information according to the timestamp on each of the behavioral video frames; then the sudden heart attack identification module extracts frames from all the corresponding infrared thermal imaging frames. S400. The image preprocessing unit preprocesses all the extracted infrared thermal imaging frames to obtain the thermal imaging image; then, it performs a gain operation on the thermal imaging image to make it clearer, resulting in a gained thermal imaging image. S500. The thermal imaging image acquisition unit acquires the surface temperature of the left hand, the surface temperature of the right temporal region, the surface temperature of the left neck, and the surface temperature of the right forefoot from each thermal imaging image; S600. The sudden heart attack identification unit calculates the high-density lipoprotein content and the total cholesterol content based on the heart attack identification model, the surface temperature of the left hand, the surface temperature of the right temporal region, the surface temperature of the left neck, and the surface temperature of the right forefoot. S700. Compare the high-density lipoprotein (HDL) content with a pre-set HDL content threshold, and simultaneously compare the total cholesterol content with a pre-set total cholesterol threshold; then, based on the comparison results, perform the following operations: If the high-density lipoprotein (HDL) level is less than the HDL level threshold and the total cholesterol level is higher than the total cholesterol level threshold, the passenger is determined to have heart disease; then S800 is executed. If the high-density lipoprotein (HDL) level is not less than the HDL level threshold, or the total cholesterol level is not higher than the total cholesterol level threshold, then the passenger is determined not to have heart disease; then S900 is executed. S800. Set the heart disease marker position to the character "1"; then package the heart disease marker position, the high-density lipoprotein content, the total cholesterol content, the surface temperature of the left hand, the surface temperature of the right temporal region, the surface temperature of the left neck, and the surface temperature of the right forefoot into the heart disease identification information; then execute S1000; S900. Set the heart disease flag to the character "0"; then package the heart disease flag into the heart disease identification information; then execute S1000; S1000. Output the heart disease identification information to the central processing unit; then the central processing unit forwards the heart disease identification information to the emergency warning module; The emergency warning module is used to provide real-time warnings based on the heart disease identification information transmitted by the sudden heart disease identification module.

2. The passenger sudden cardiac arrest identification system based on infrared thermal imaging according to claim 1, characterized in that: The video acquisition module includes a high-definition camera for acquiring the behavioral video information and an infrared thermal imager for acquiring the infrared thermal imaging information; wherein: The behavioral video information includes behavioral video frames, each of which contains a view of the passenger's behavior at the time of capture and a timestamp; all the behavioral video frames are arranged in ascending order according to the timestamps to form the behavioral video information. The infrared thermal imaging information includes infrared thermal imaging frames, each of which contains an infrared thermal image of the passenger at the time of acquisition and the timestamp; all the infrared thermal imaging frames are arranged in ascending order according to the timestamps to form the infrared thermal imaging video information. The sequence of timestamps in the behavioral video information is exactly the same as the sequence of timestamps in the infrared thermal imaging information; each behavioral video frame in the behavioral video information has a one-to-one correspondence with the infrared thermal imaging frame in the infrared thermal imaging information according to the timestamp it is stamped.

3. The passenger sudden cardiac arrest identification system based on infrared thermal imaging according to claim 2, characterized in that: The video analysis module includes a human target recognition unit for implementing human target detection, tracking, and motion recognition functions, and an abnormal behavior recognition unit for detecting abnormal behavior in the behavioral video information based on a keypoint detection method; wherein: The abnormal behavior identification and detection is performed by the AI ​​model in the abnormal behavior identification unit, and the output result is the abnormal behavior identification result. The abnormal behaviors include covering one's chest with one's hands and slumping down.

4. The passenger sudden cardiac arrest identification system based on infrared thermal imaging according to claim 3, characterized in that: The sudden heart attack recognition module includes an image preprocessing unit, a thermal imaging image acquisition unit, and a sudden heart attack recognition unit; wherein: The image preprocessing unit is used to preprocess the infrared thermal imaging frame to obtain a thermal imaging image; The thermal imaging image acquisition unit acquires the surface temperature of the left hand, the surface temperature of the right temporal region, the surface temperature of the left neck, and the surface temperature of the right forefoot from the thermal imaging image; The sudden heart attack identification unit is used to calculate and determine whether a passenger has a heart attack through a heart attack identification model.

5. The passenger sudden cardiac arrest identification system based on infrared thermal imaging according to claim 4, characterized in that: The heart disease identification model is expressed as follows: Wherein: HDL is the high-density lipoprotein content, in mg / dl; TC is the total cholesterol content, in mg / dl; X1 is the surface temperature of the left hand, in °C; X2 is the surface temperature of the right temporal region, in °C; X3 is the surface temperature of the left neck, in °C; X4 is the surface temperature of the right forefoot, in °C.

6. The passenger sudden cardiac arrest identification system based on infrared thermal imaging according to claim 5, characterized in that: In step S400, a gain operation is performed on the thermal imaging image to make it clearer, resulting in a gained thermal imaging image. This specifically includes the following steps: S410. Calculate the grayscale values ​​of all pixels in the thermal image without gain operation; S420. Draw a histogram corresponding to the gray level of a pixel and the number of pixels; S430. The new gray level of each pixel is calculated using the histogram equalization algorithm; S440. Obtain the enhanced thermal image based on the new grayscale level of each pixel.

7. The passenger sudden cardiac arrest identification system based on infrared thermal imaging according to claim 6, characterized in that: The histogram equalization algorithm is expressed as follows: Wherein: S k Li is the new grayscale value of the pixel obtained after histogram equalization; L-1 is the maximum grayscale value of the thermal image; i0 is the minimum grayscale value in the thermal image without gain operation; i1 is the second smallest grayscale value in the thermal image without gain operation; i2 is the third smallest grayscale value in the thermal image without gain operation; M is the number of pixels on the wide side of the thermal image without gain operation; N is the number of pixels on the long side of the thermal image without gain operation; MN is the total number of pixels in the thermal image without gain operation; n i is the number of pixels with grayscale value i; k is the number of grayscale values ​​of the pixels in the thermal image without gain operation.

8. The passenger sudden cardiac arrest identification system based on infrared thermal imaging according to claim 7, characterized in that: The threshold for high-density lipoprotein content is 400 mg / dl; the threshold for total cholesterol content is 200 mg / dl.

9. The passenger sudden heart attack identification system based on infrared thermal imaging according to claim 8, characterized in that: The emergency warning module transmits the heart disease identification information via telephone, SMS, platform alarm, and broadcast to achieve real-time warning.

Images