Millimeter wave and thermal imaging fusion face detection method and system for lying person

Abstract

The application provides a lying person face covering detection method and system based on millimeter wave and thermal imaging fusion, which comprises the following steps: detecting a target based on ADC original data to detect the position of the target and extract vital signs of the target; extracting the face region temperature of the target based on temperature matrix data, and performing temperature distribution entropy value calculation on the face region temperature to obtain a distribution entropy value calculation result; judging the vital sign abnormality of the target based on the vital signs to obtain a judgment result, and judging the human distribution abnormality based on the distribution entropy value calculation result to obtain a judgment result; performing weighted probability fusion on the judgment result and the judgment result to obtain a shielding probability of the target, and judging whether the shielding probability exceeds a preset value, if yes, triggering an alarm. The application can effectively monitor whether the vital signs and the face of the target are shielded under different conditions, and can also monitor without infringing on the privacy of the target.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of nursing monitoring, in particular to a millimeter wave and thermal imaging fusion bedridden person face covering detection method and system. BACKGROUND

[0002] In the home / institutional elderly care scene, bedridden old people may cause suffocation or even death due to body movement or neglect of care. Therefore, it is necessary to monitor bedridden old people, and visible light cameras, thermal imaging or pure millimeter wave radars are usually used for observation.

[0003] In the prior art, visible light cameras will infringe privacy, be invalid at night and have high computing power requirements; pure infrared thermal imaging has high false alarm rate and cannot distinguish between face covering and environmental temperature difference; pure millimeter wave radar can monitor vital signs, but cannot directly sense whether the face is covered. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a millimeter wave and thermal imaging fusion bedridden person face covering detection method and system to solve the above problems in the prior art.

[0005] In a first aspect, the present application provides a millimeter wave and thermal imaging fusion bedridden person face covering detection method, which comprises:

[0006] Collecting ADC raw data of millimeter radar waves and temperature matrix data of thermal imaging sensors;

[0007] Detecting a target based on the ADC raw data to detect the position of the target and extract the vital signs of the target;

[0008] Extracting the face region temperature of the target based on the temperature matrix data, and performing temperature distribution entropy value calculation on the face region temperature to obtain a distribution entropy value calculation result;

[0009] Performing vital sign abnormality judgment on the target based on the vital signs to obtain a judgment result, and performing human distribution abnormality judgment through the distribution entropy value calculation result to obtain a judgment result;

[0010] Weighted probability fusion is performed on the judgment result and the judgment result to obtain a covering probability of the target, and it is judged whether the covering probability exceeds a preset value, if yes, an alarm is triggered.

[0011] Compared with the prior art, the present application has the beneficial effects that: by means of vital sign abnormality judgment on the target, distribution entropy calculation result calculated by temperature distribution entropy of the face area temperature, and the weighted probability fusion of the judgment result and the determination result, the shielding probability of the target can be obtained, and then whether the target is shielded or not can be judged according to whether the shielding probability exceeds the threshold value, and the judgment is made by the weighted fusion of the two, which can not only effectively monitor whether the target sign and the face are shielded under different conditions, but also monitor under the premise of not infringing the privacy of the target.

[0012] Further, the ADC raw data includes target distance, target speed and target angle information.

[0013] Further, the step of extracting the vital signs of the target comprises:

[0014] extracting the respiratory rate and heart rate from the chest micro-movement of the target by a phase demodulation algorithm;

[0015] calculating the body movement intensity of the target based on Doppler energy integration.

[0016] Further, before the step of extracting the face area temperature of the target based on the temperature matrix data, the method further comprises:

[0017] locating the face area based on the temperature matrix data and by temperature gradient, and evaluating the temperature distribution uniformity of the face area by an information entropy formula.

[0018] Further, after the step of judging whether the shielding probability exceeds the preset value, the method further comprises:

[0019] If the shielding probability does not exceed the preset value, the steps of collecting the ADC raw data of the millimeter radar wave and the temperature matrix data of the thermal imaging sensor, detecting the target based on the ADC raw data to detect the target position and extract the vital signs of the target, extracting the face area temperature of the target based on the temperature matrix data and performing temperature distribution entropy calculation on the face area temperature to obtain the distribution entropy calculation result, performing vital sign abnormality judgment on the target based on the vital signs to obtain the judgment result and performing face distribution abnormality determination based on the distribution entropy calculation result to obtain the determination result, and performing weighted probability fusion on the judgment result and the determination result to obtain the shielding probability of the target and judging whether the shielding probability exceeds the preset value are repeated.

[0020] In a second aspect, the present application also provides a millimeter wave and thermal imaging fusion face shielding detection system for bedridden personnel, which comprises:

[0021] The collection module is configured to collect ADC raw data of millimeter radar waves and temperature matrix data of a thermal imaging sensor;

[0022] The detection module is configured to detect a target based on the ADC raw data to detect a position of the target and extract vital signs of the target.

[0023] The extraction module is configured to extract a facial region temperature of the target based on the temperature matrix data and perform temperature distribution entropy value calculation on the facial region temperature to obtain a distribution entropy value calculation result.

[0024] The judgment module is configured to perform vital sign abnormality judgment on the target based on the vital signs to obtain a judgment result and perform human distribution abnormality judgment based on the distribution entropy value calculation result to obtain a judgment result.

[0025] The fusion module is configured to perform weighted probability fusion on the judgment result and the judgment result to obtain an occlusion probability of the target, and judge whether the occlusion probability exceeds a preset value, and if so, trigger an alarm.

[0026] Further, the detection module comprises:

[0027] The extraction unit is configured to extract a respiratory rate and a heart rate from chest cavity micro-movement of the target through a phase demodulation algorithm.

[0028] The calculation unit is configured to calculate a body movement intensity of the target based on Doppler energy integration.

[0029] Further, the extraction module comprises:

[0030] The positioning unit is configured to position a facial region based on the temperature matrix data and through temperature gradient positioning, and evaluate temperature distribution uniformity of the facial region through an information entropy formula.

[0031] In a third aspect, the present application further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the millimeter wave and thermal imaging fusion bed occupant face covering detection method described above when executing the computer program.

[0032] In a fourth aspect, the present application further provides a storage medium having a computer program stored thereon, wherein the program is executed by a processor to implement the millimeter wave and thermal imaging fusion bed occupant face covering detection method described above. BRIEF DESCRIPTION OF DRAWINGS

[0033] Figure 1 Flowchart of the millimeter wave and thermal imaging fusion bed occupant face covering detection method in the first embodiment of the present application;

[0034] Figure 2 This is a structural block diagram of the bedridden person face occlusion detection system that fuses millimeter wave and thermal imaging according to the second embodiment of the present invention.

[0035] Figure 3 This is a structural block diagram of the electronic device in the third embodiment of the present invention.

[0036] Explanation of key component symbols:

[0037] 10. Acquisition Module; 20. Detection Module; 30. Extraction Module; 40. Judgment Module; 50. Fusion Module;

[0038] 60. Bus; 61. Processor; 62. Memory; 63. Communication interface.

[0039] The following detailed description, in conjunction with the accompanying drawings, will further illustrate the present invention. Detailed Implementation

[0040] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. Several embodiments of the invention are illustrated in the drawings. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

[0041] It should be noted that when a component is said to be "fixed to" another component, it can be directly on the other component or there may be an intervening component. When a component is said to be "connected to" another component, it can be directly connected to the other component or there may be an intervening component. The terms "vertical," "horizontal," "left," "right," and similar expressions used in this document are for illustrative purposes only.

[0042] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0043] Example 1

[0044] Please see Figure 1 The image shows a method for detecting face occlusion in bedridden individuals by fusing millimeter-wave and thermal imaging in the first embodiment of the present invention. The method includes steps S1 to S5:

[0045] S1, acquires raw ADC data of millimeter radar waves and temperature matrix data of thermal imaging sensors;

[0046] It should be noted that the millimeter-wave radar uses 60GHz MIMO FMCW modulation and outputs an ADC data stream. In this embodiment, the raw ADC data includes target distance, target velocity, and target angle information. The thermal imaging sensor uses a 32×24 resolution low-cost infrared array (such as MLX90640) and outputs a temperature distribution matrix (accuracy ±0.5℃).

[0047] S2, Detect the target based on the raw data of the ADC to detect the target's location and extract the target's vital signs;

[0048] Specifically, step S2 includes steps S21 to S22:

[0049] S21, the respiratory rate and heart rate are extracted from the chest cavity micro-movements of the target using a phase demodulation algorithm;

[0050] S22, calculate the body dynamics of the target based on the Doppler energy integral;

[0051] Understandably, the CFAR algorithm is used to detect human targets within the bed area (distance ≤ 1.5m), and the phase demodulation algorithm is used to extract respiratory rate (accuracy ± 0.2 Hz) and heart rate (accuracy ± 3 bpm) from chest micro-movements; the body motion intensity (0-100 scale) is calculated by Doppler energy integration.

[0052] S3, extract the facial region temperature of the target based on the temperature matrix data, and calculate the temperature distribution entropy value of the facial region temperature to obtain the distribution entropy value calculation result;

[0053] Specifically, step S3 includes step S31:

[0054] S31, based on the temperature matrix data and by locating the facial region through the temperature gradient, and by evaluating the temperature distribution uniformity of the facial region through the information entropy formula;

[0055] It is understandable that the typical temperature of the facial area is 34-37℃ when the ROI is used to locate the facial region; the entropy value of a normal face is >2.5, and the entropy value is <1.0 when covered (the cotton quilt causes temperature uniformity).

[0056] It should be noted that the expression for assessing the uniformity of temperature distribution in the facial area is:

[0057] ;

[0058] In the formula, H represents the facial temperature distribution entropy, and p(i) represents the probability of temperature i.

[0059] S4, based on the vital signs, the target is judged to be abnormal to obtain the judgment result, and the human distribution is judged to be abnormal through the distribution entropy value calculation result to obtain the judgment result;

[0060] It should be explained that, in this embodiment, thermal imaging abnormalities include: entropy value < threshold T1 (e.g., 1.2) and lasting > 10s; and radar vital signs abnormalities include: respiratory rate < 0.1Hz or > 0.6Hz, or heart rate < 40bpm or > 120bpm, or kinetic energy > 80 (struggle characteristics).

[0061] S5, perform weighted probability fusion on the judgment result and the determination result to obtain the occlusion probability of the target, and determine whether the occlusion probability exceeds a preset value. If so, trigger an alarm.

[0062] Understandably, the overall probability is: Where I is the normalized anomaly index, I_thermal represents the normalized value of the thermal imaging facial temperature distribution entropy, and I_radar represents the normalized value of radar vital signs anomalies; when P>0.8, an alarm is triggered, and the alarm can be pushed through audible and visual warnings and cloud platform.

[0063] It is worth noting that if the occlusion probability does not exceed the preset value, the process of collecting raw ADC data of millimeter radar waves and temperature matrix data of thermal imaging sensors is repeated; the target is detected based on the raw ADC data to detect the target position and extract the target's vital signs; the facial region temperature of the target is extracted based on the temperature matrix data, and the temperature distribution entropy value of the facial region temperature is calculated to obtain the distribution entropy value calculation result; the target is judged for abnormal vital signs based on the vital signs to obtain the judgment result, and the human distribution abnormality is judged based on the distribution entropy value calculation result to obtain the judgment result; the judgment result and the judgment result are weighted probability fused to obtain the occlusion probability of the target, and it is determined whether the occlusion probability exceeds the preset value.

[0064] This can be specifically applied in nursing home bedrooms during winter, where elderly residents sleep under thick quilts (3cm thick), and their faces are sometimes covered by the quilts due to turning over. The ambient temperature is 22℃, and the human body temperature is 36.5℃. In practical implementation:

[0065] Initial state:

[0066] The radar detected a target in the bed area (distance 0.8m). Vital signs: respiratory rate 0.25Hz, heart rate 68bpm, energy level 5.

[0067] Thermal imaging facial ROI entropy value = 2.8 (normal distribution);

[0068] The incident occurred:

[0069] t=0s: The elderly person turns over, and the quilt covers the area around the mouth and nose;

[0070] t+5s: Thermal imaging detected that the facial entropy value dropped to 0.9 (temperature homogenization), and marked it as "suspected occlusion";

[0071] t+8s: The radar detected a sudden drop in respiratory rate to 0.08Hz (decreased blood oxygen), heart rate rising to 112bpm (panic), and energy level rising to 75 (struggling).

[0072] Decision-making and alarms:

[0073] Fusion algorithm calculation: ;

[0074] Alarm triggered: The bedside lamp flashes red light (2Hz), the buzzer sounds at 85dB, and an alarm message is pushed to the nursing station PDA;

[0075] The nurse confirms and removes the bedding on-site; the process takes less than 2 minutes.

[0076] Reset: Thermal imaging entropy value recovers to >2.5, radar vital signs are normal (respiratory rate 0.28Hz, heart rate 72bpm); system returns to low power standby state (power consumption ≤1.5W).

[0077] In summary, the millimeter-wave and thermal imaging fusion method for detecting face occlusion in bedridden individuals in the above embodiments of the present invention judges abnormalities in the target's vital signs through vital signs, calculates the distribution entropy value based on the temperature distribution entropy value of the facial area, and obtains the target's occlusion probability through weighted probability fusion judgment result. Then, based on whether the occlusion probability exceeds a threshold, it is determined whether the target is occluded. This weighted fusion judgment not only effectively monitors the target's vital signs and whether the face is occluded under different conditions, but also allows monitoring without infringing on the target's privacy. Furthermore, pure thermal imaging may produce false alarms when the environment warms up (e.g., a hot water bottle near the face), but the absence of abnormal radar vital signs suppresses false alarms. Low-resolution thermal imaging cannot reconstruct facial features (approximately 2 cm² per pixel), complying with GDPR / CCPA specifications. Through dual-modal cross-validation, the false alarm rate of occlusion detection is reduced from 15% to <2% (laboratory simulation data); it can work reliably in an ambient temperature range of 15-38℃ (traditional thermal imaging solutions fail at >35℃); it does not collect visible light images, and the thermal imaging resolution is only 32×24 (unable to identify individuals); raw data is processed locally without uploading to the cloud to improve privacy and security; it provides early warning of suffocation risk (average delay from occlusion occurrence to alarm <10s), avoiding brain damage.

[0078] Example 2

[0079] The second embodiment of the present invention also provides a face-covering detection system for bedridden persons that integrates millimeter-wave and thermal imaging. Please refer to [link to relevant documentation]. Figure 2 The image shows a millimeter-wave and thermal imaging fusion system for detecting face occlusion in bedridden individuals according to a second embodiment of the present invention. The system includes:

[0080] The acquisition module 10 is used to acquire the raw ADC data of the millimeter radar wave and the temperature matrix data of the thermal imaging sensor.

[0081] The detection module 20 is used to detect the target based on the raw data of the ADC, so as to detect the target position and extract the target's vital signs;

[0082] The extraction module 30 is used to extract the facial region temperature of the target based on the temperature matrix data, and to calculate the temperature distribution entropy value of the facial region temperature to obtain the distribution entropy value calculation result.

[0083] The judgment module 40 is used to judge the target based on the vital signs to obtain a judgment result, and to judge the human distribution abnormality through the distribution entropy value calculation result to obtain a judgment result.

[0084] The fusion module 50 is used to perform weighted probability fusion on the judgment result and the determination result to obtain the occlusion probability of the target, and to determine whether the occlusion probability exceeds a preset value. If so, an alarm is triggered.

[0085] In some alternative embodiments, the detection module 20 includes:

[0086] The extraction unit is used to extract respiratory rate and heart rate from the chest cavity micro-movements of the target using a phase demodulation algorithm;

[0087] The calculation unit is used to calculate the body dynamics of the target based on the Doppler energy integral.

[0088] In some alternative embodiments, the extraction module 30 includes:

[0089] The positioning unit is used to locate the facial region based on the temperature matrix data and the temperature gradient, and to evaluate the temperature distribution uniformity of the facial region using the information entropy formula.

[0090] In some alternative embodiments, the fusion module 50 includes:

[0091] The judgment unit is configured to: determine if the occlusion probability does not exceed the preset value, then repeatedly execute the acquisition of raw ADC data of millimeter radar waves and temperature matrix data of thermal imaging sensors; detect the target based on the raw ADC data to detect the target position and extract the target's vital signs; extract the facial region temperature of the target based on the temperature matrix data, and calculate the temperature distribution entropy value of the facial region temperature to obtain the distribution entropy value calculation result; perform a vital sign anomaly judgment on the target based on the vital signs to obtain a judgment result, and perform a human distribution anomaly judgment based on the distribution entropy value calculation result to obtain a judgment result; perform weighted probability fusion on the judgment result and the judgment result to obtain the occlusion probability of the target, and determine whether the occlusion probability exceeds the preset value.

[0092] The functions or operation steps implemented by the above modules and units are largely the same as those in the above method embodiments, and will not be repeated here.

[0093] The millimeter-wave and thermal imaging fusion face-covering detection system for bedridden individuals provided in this embodiment of the invention has the same implementation principle and technical effects as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the system embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0094] Example 3

[0095] The third embodiment of the present invention also proposes an electronic device, please refer to [link / reference]. Figure 3 The image shows an electronic device according to a third embodiment of the present invention.

[0096] The electronic device may include a processor 61 and a memory 62 storing computer program instructions.

[0097] Specifically, the processor 61 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the present application.

[0098] The memory 62 may include a large-capacity storage device for data or instructions. For example, and not limitingly, the memory 62 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), flash memory, an optical disk drive, a magneto-optical disk drive, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 62 may include removable or non-removable (or fixed) media. Where appropriate, the memory 62 may be internal or external to a data processing device. In a particular embodiment, the memory 62 is non-volatile memory. In a particular embodiment, the memory 62 includes read-only memory (ROM) and random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), an electrically alterable read-only memory (EAROM), or flash memory, or a combination of two or more of these. Where appropriate, the RAM can be Static Random-Access Memory (SRAM) or Dynamic Random-Access Memory (DRAM). DRAM can be Fast Page Mode Dynamic Random-Access Memory (FPMDRAM), Extended Data Out Dynamic Random-Access Memory (EDODRAM), Synchronous Dynamic Random-Access Memory (SDRAM), etc.

[0099] The memory 62 can be used to store or cache various data files that need to be processed and / or communicated, as well as possible computer program instructions executed by the processor 61.

[0100] The processor 61 reads and executes the computer program instructions stored in the memory 62 to implement the millimeter wave and thermal imaging fusion method for detecting face occlusion of bedridden persons as described in Embodiment 1 above.

[0101] In some embodiments, the electronic device may further include a communication interface 63 and a bus 60. For example, Figure 3 As shown, the processor 61, memory 62, and communication interface 63 are connected through bus 60 and complete communication with each other.

[0102] The communication interface 63 is used to enable communication between the various modules, devices, units, and / or equipment in this application. The communication interface 63 can also enable data communication with other components such as external devices, image / data acquisition devices, databases, external storage, and image / data processing workstations.

[0103] Bus 60 includes hardware, software, or both, that couples components of a device together. Bus 60 includes, but is not limited to, at least one of the following: data bus, address bus, control bus, expansion bus, and local bus. For example, and not as a limitation, bus 60 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 60 may include one or more buses. Although this application describes and illustrates a specific bus, this application considers any suitable bus or interconnection.

[0104] The electronic device can acquire a bedridden person face occlusion detection system that integrates millimeter wave and thermal imaging, and execute the bedridden person face occlusion detection method that integrates millimeter wave and thermal imaging in this embodiment.

[0105] Furthermore, in conjunction with the millimeter-wave and thermal imaging fusion method for detecting face occlusion in bedridden individuals described in Embodiment 1 above, this application can provide a storage medium for implementation. This storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement the millimeter-wave and thermal imaging fusion method for detecting face occlusion in bedridden individuals described in Embodiment 1 above.

[0106] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0107] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

Claims

1. A method for detecting face occlusion in bedridden individuals using millimeter-wave and thermal imaging fusion, characterized in that, The method includes: Acquire raw ADC data from millimeter-wave radar and temperature matrix data from thermal imaging sensors; The target is detected based on the raw data from the ADC to detect the target's location and extract the target's vital signs. Based on the temperature matrix data, the facial region temperature of the target is extracted, and the temperature distribution entropy value of the facial region temperature is calculated to obtain the distribution entropy value calculation result. Based on the vital signs, the target is assessed for abnormalities to obtain a judgment result, and the distribution entropy value is used to calculate the human distribution abnormality to obtain a judgment result. The judgment result and the determination result are weighted and probabilistically fused to obtain the occlusion probability of the target, and it is determined whether the occlusion probability exceeds a preset value. If so, an alarm is triggered.

2. The method for detecting face occlusion in bedridden individuals by fusing millimeter-wave and thermal imaging according to claim 1, characterized in that, The raw data from the ADC includes target distance, target velocity, and target angle information.

3. The method for detecting face occlusion in bedridden individuals by fusing millimeter-wave and thermal imaging according to claim 1, characterized in that, The step of extracting the vital signs of the target includes: The respiratory rate and heart rate are extracted from the chest cavity micro-movements of the target using a phase demodulation algorithm; The body dynamics of the target are calculated based on the Doppler energy integral.

4. The method for detecting face occlusion in bedridden individuals by fusing millimeter-wave and thermal imaging according to claim 1, characterized in that, Before extracting the facial region temperature of the target based on the temperature matrix data, the method further includes the following steps: Based on the temperature matrix data, the facial region is located using the temperature gradient, and the uniformity of temperature distribution in the facial region is evaluated using the information entropy formula.

5. The method for detecting face occlusion in bedridden individuals by fusing millimeter-wave and thermal imaging according to claim 1, characterized in that, After the step of determining whether the occlusion probability exceeds a preset value, the method further includes: If the occlusion probability does not exceed the preset value, the process of collecting raw ADC data of millimeter radar waves and temperature matrix data of thermal imaging sensors is repeated; the target is detected based on the raw ADC data to detect the target position and extract the target's vital signs; the facial region temperature of the target is extracted based on the temperature matrix data, and the temperature distribution entropy value of the facial region temperature is calculated to obtain the distribution entropy value calculation result; the target is judged for abnormal vital signs based on the vital signs to obtain the judgment result, and the human distribution abnormality is judged based on the distribution entropy value calculation result to obtain the judgment result; the judgment result and the judgment result are weighted probability fused to obtain the occlusion probability of the target, and it is determined whether the occlusion probability exceeds the preset value.

6. A face-covering detection system for bedridden individuals using millimeter-wave and thermal imaging fusion, characterized in that, The system includes: The acquisition module is used to acquire raw ADC data of millimeter radar waves and temperature matrix data of thermal imaging sensors; The detection module is used to detect the target based on the raw data of the ADC, so as to detect the target location and extract the target's vital signs; The extraction module is used to extract the facial region temperature of the target based on the temperature matrix data, and to calculate the temperature distribution entropy value of the facial region temperature to obtain the distribution entropy value calculation result. The judgment module is used to judge the target based on the vital signs to obtain the judgment result, and to judge the human distribution abnormality through the distribution entropy value calculation result to obtain the judgment result. The fusion module is used to perform weighted probability fusion on the judgment result and the determination result to obtain the occlusion probability of the target, and to determine whether the occlusion probability exceeds a preset value. If so, an alarm is triggered.

7. The millimeter-wave and thermal imaging fusion system for detecting face occlusion in bedridden individuals according to claim 6, characterized in that, The detection module includes: The extraction unit is used to extract respiratory rate and heart rate from the chest cavity micro-movements of the target using a phase demodulation algorithm; The calculation unit is used to calculate the body dynamics of the target based on the Doppler energy integral.

8. The millimeter-wave and thermal imaging fusion system for detecting face occlusion in bedridden individuals according to claim 6, characterized in that, The extraction module includes: The positioning unit is used to locate the facial region based on the temperature matrix data and the temperature gradient, and to evaluate the temperature distribution uniformity of the facial region using the information entropy formula.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method for detecting face occlusion of bedridden persons by fusion of millimeter wave and thermal imaging as described in any one of claims 1 to 5.

10. A storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method for detecting face occlusion of bedridden persons by fusion of millimeter wave and thermal imaging as described in any one of claims 1 to 5.

Images