Cabin crew thermal sensation evaluation method and system based on infrared thermal imaging, and medium

Abstract

The application provides a cabin personnel thermal sensation evaluation method and system based on infrared thermal imaging, comprising the following steps: S1, collecting the temperature of an imaging area, the solar radiation intensity in the vehicle cabin and the air temperature in the breathing area of the vehicle passenger in real time; S2, extracting the cheek area temperature in the thermal image and carrying out denoising processing to obtain a cheek skin temperature signal; S3, transmitting the air temperature, the solar radiation intensity and the cheek skin temperature to a vehicle cabin thermal sensation calculation model to calculate a thermal sensation grade; and S4, generating a corresponding air conditioner temperature adjustment instruction according to the thermal sensation grade of the vehicle passenger and transmitting the instruction to a microcontroller, and the microcontroller sends the instruction to a cabin air conditioner main controller to adjust the set point of the air conditioner. The application evaluates the thermal sensation by using the skin temperature of a single part, is simple and portable, does not need to use the skin temperature of multiple nodes as input, and has high accuracy.

Description

Technical Field

[0001] This invention relates to the field of air conditioning energy-saving technology, specifically to a method and system for evaluating the thermal sensation of cabin occupants based on infrared thermal imaging. Background Technology

[0002] Human temperature perception is achieved through cold-sensitive and heat-sensitive nerve endings beneath the skin, which send signals to the hypothalamus via the sympathetic nervous system. Since the body's perception of hot and cold drives the dilation and constriction of blood vessels flowing through the skin surface, skin temperature changes. This creates a clear correlation between skin temperature and thermal sensation. Furthermore, because metabolic rate and hormone levels participate in the regulation of blood flow to the body surface, skin temperature contains certain population-specific information; that is, under different sensations of hot and cold, specific individuals may exhibit unique differences in skin temperature response. Existing research indicates that skin temperature in specific areas of the body, such as the wrist and arm, is related to thermal sensation. Based on these research theories, many researchers use physiological sensors to collect skin temperature and then establish thermal comfort models. In recent years, with the development of thermal imaging technology, the accuracy of thermal imagers has been significantly improved. Using infrared thermal imaging to collect skin temperature can provide a continuous method to monitor the surface temperature of a person and thus predict their thermal state.

[0003] Currently, regulating the thermal environment inside the vehicle cabin primarily relies on controlling the air conditioning system to achieve the user's customized temperature preferences. While this control mode allows users freedom of choice, it also has certain drawbacks. On one hand, it requires the driver to manually adjust the air conditioning settings while driving, thus affecting the overall driving experience and potentially posing safety hazards. Conversely, prolonged use of a constant air conditioning configuration and improper user adjustments can lead to low energy efficiency.

[0004] The use of thermal imaging sensors to assess human thermal sensation and guide automatic environmental control has garnered increasing attention from professionals in the construction industry. Chinese utility model patent application CN201620177986.4 discloses a "central air conditioning energy-saving control system based on human thermal comfort." This system controls air conditioning settings using an infrared thermometer and environmental parameter monitoring. However, this patent does not specify the sensitive and effective skin temperature for assessing human thermal sensation, nor does it provide a suitable skin temperature acquisition area, nor does it explain the correlation between human thermal sensation and the acquired parameters. Chinese invention patent application CN202211498648.7 discloses a "thermal comfort evaluation method based on infrared thermal imaging technology." This patent uses infrared thermal imaging to automatically adjust the temperature of target equipment by reading the skin temperature data of the target object and combining it with a thermal sensation evaluation model. However, this system is based on building interiors and does not consider the significant difference in thermal characteristics between car cabins (which have heavy building envelopes) and those highly susceptible to solar radiation. Therefore, it does not provide a quantitative relationship between solar radiation and thermal sensation and skin temperature, rendering the system completely unsuitable for cabin space systems. Similar limitations exist in Chinese invention patent application CN202210522388.6 (“Intelligent Indoor Human Thermal Comfort Control Method and System Based on Infrared Thermal Imaging”). Compared to buildings, the cabin environment of automobiles and other similar spaces is significantly affected by dynamic factors such as solar radiation, background radiation, and surrounding airflow. Due to the relatively weak thermal insulation performance of the cabin's outer walls, the thermal environment field inside the cabin fluctuates more significantly than in building environments. Therefore, simply applying existing evaluation models and control strategies to mobile cabins is not suitable. Chinese invention patent application CN202310279496.X discloses “An Intelligent Vehicle Occupant Cabin Thermal Management Method,” which explicitly points out that the assessment of occupant thermal sensation in automobile cabins is affected by fluctuations in the outdoor environment and provides a thermal management method applicable to cabin environments. However, this patent primarily uses environmental parameters as the basis for evaluating occupant thermal sensation. This results in a lack of individual adaptability in the control method, making it difficult to identify occupant comfort and implement personalized adjustments. This limitation also exists in Chinese invention patent application number CN202110911988.7 (“An Intelligent Control System for Automotive Air Conditioning”). Chinese invention patent number 202310657365.0 discloses a “Method for Cooling and Heating the Occupant Cabin Based on Local Thermal Comfort Characteristics of the Human Body and an Automobile.” This patent, from the perspective of ensuring individual comfort, proposes a method to adjust the temperature of the occupant area by real-time monitoring of the occupant's surface temperature and combining it with environmental parameters. However, this method does not consider the influence of solar radiation intensity on the occupant's thermal sensation in terms of environmental parameters, nor does it provide a method for implementing infrared temperature measurement within the cabin; furthermore, the temperature acquisition method and acquisition area are unclear. Summary of the Invention

[0005] In view of the deficiencies in the prior art, the purpose of this invention is to provide a method and system for evaluating the thermal sensation of cabin occupants based on infrared thermal imaging.

[0006] A method for evaluating the thermal sensation of cockpit occupants based on infrared thermal imaging, provided by the present invention, includes:

[0007] Step S1: Real-time acquisition of the temperature of the imaging area, the intensity of solar radiation inside the cabin, and the air temperature in the breathing area of ​​the occupants inside the vehicle;

[0008] Step S2: Extract the temperature of the cheek area from the thermal image and perform noise reduction processing to obtain the cheek skin temperature signal;

[0009] Step S3: By transmitting air temperature, solar radiation intensity, and cheek skin temperature to the vehicle cabin thermal sensation calculation model, the thermal sensation level is calculated.

[0010] Step S4: Based on the thermal perception level of the occupants, generate the corresponding air conditioning temperature adjustment command and transmit it to the microcontroller. The microcontroller then sends the command to the cabin air conditioning main controller to adjust the air conditioning setpoint.

[0011] Preferably, in step S1:

[0012] As passengers enter the vehicle, thermal imaging sensors collect the temperature of the imaging area in real time; solar radiation sensors in front of the control panel inside the vehicle collect the solar radiation intensity inside the cabin in real time; and air temperature sensors at the seats inside the vehicle collect the air temperature in the breathing area of ​​the occupants in real time.

[0013] The face recognition algorithm and cheek region segmentation algorithm were trained using an open-source infrared human image dataset and YOLO V5. The trained infrared imaging face recognition algorithm was used to detect whether there were passengers in the vehicle. When a passenger was detected to have boarded the vehicle, infrared imaging data of the target object's face was collected at detection time intervals using a thermal imaging sensor device mounted under the rearview mirror.

[0014] Preferably, in step S2:

[0015] The vehicle's computer uses a facial recognition algorithm to extract the temperature of the cheek area from the thermal image, performs noise reduction processing, and obtains the skin temperature signal; it then transmits the cheek skin temperature, the intensity of solar radiation inside the vehicle, and the cabin air temperature to the storage medium.

[0016] Using a pre-trained infrared imaging face recognition algorithm, the temperature measurement value of the cheek is extracted, and the skin temperature data within the preset range is removed to correct the cheek imaging temperature of the occupants in the vehicle.

[0017] Preferably, in step S3:

[0018] The USB-Type C microcontroller transmits data on cheek skin temperature, solar radiation intensity, and passenger cabin air temperature to the vehicle terminal via USB. After obtaining the cheek skin temperature, real-time solar radiation intensity, and air temperature near the passenger area, the vehicle terminal inputs the three types of data into the thermal sensation calculation model to calculate the thermal sensation of the occupants inside the vehicle.

[0019] The pre-trained model is represented as follows:

[0020] TSV = A × T air +B×R s +C×T incheek +D

[0021] Among them, T air Indicates cabin air temperature; R s T represents the total solar radiation inside the cockpit; incheek A is the skin temperature of the occupant's cheek on the non-window side; B is the regression coefficient of the cabin air temperature, representing the change in thermal sensation when the air temperature changes by a unit; C is the regression coefficient of the solar radiation intensity inside the cabin, representing the change in thermal sensation when the solar radiation intensity changes by a unit; D is the constant term of the thermal sensation calculation model.

[0022] Preferably, in step S4:

[0023] The vehicle terminal generates a corresponding air conditioning temperature adjustment command based on the calculated thermal sensation values ​​of the occupants inside the vehicle; the vehicle terminal transmits the temperature adjustment command to the microcontroller, and the microcontroller sends a command to the cabin air conditioning main controller to adjust the air conditioning setpoint; the vehicle LCD screen displays the current solar radiation intensity inside the vehicle, the detected cheek skin temperature, the cabin air temperature, and the thermal sensation of the target passenger; when the timer set time is reached, it jumps to step S1;

[0024] If the calculated perceived heat level is greater than the preset value, the passenger's perceived heat level is determined to be hot, and the air outlet temperature is lowered while the air outlet speed is increased; if the calculated perceived heat level is within the preset range, the passenger's perceived heat level is determined to be neutral, and no adjustment is made to the air outlet temperature or air outlet speed; if the calculated perceived heat level is less than the preset value, the passenger's perceived heat level is determined to be cold, and the air outlet temperature is increased while the air outlet speed is decreased.

[0025] A cockpit occupant thermal perception assessment system based on infrared thermal imaging, according to the present invention, includes:

[0026] Module M1: Real-time acquisition of the temperature of the imaging area, the intensity of solar radiation inside the cabin, and the air temperature in the breathing area of ​​the occupants.

[0027] Module M2: Extracts the temperature of the cheek area from the thermal image, performs noise reduction processing, and obtains the cheek skin temperature signal;

[0028] Module M3: The thermal sensation level is calculated by transmitting air temperature, solar radiation intensity, and cheek skin temperature to the cabin thermal sensation calculation model;

[0029] Module M4: Based on the thermal perception level of the occupants, it generates corresponding air conditioning temperature adjustment commands and transmits them to the microcontroller. The microcontroller then sends commands to the cabin air conditioning main controller to adjust the air conditioning setpoint.

[0030] Preferably, in module M1:

[0031] As passengers enter the vehicle, thermal imaging sensors collect the temperature of the imaging area in real time; solar radiation sensors in front of the control panel inside the vehicle collect the solar radiation intensity inside the cabin in real time; and air temperature sensors at the seats inside the vehicle collect the air temperature in the breathing area of ​​the occupants in real time.

[0032] The face recognition algorithm and cheek region segmentation algorithm were trained using an open-source infrared human image dataset and YOLO V5. The trained infrared imaging face recognition algorithm was used to detect whether there were passengers in the vehicle. When a passenger was detected to have boarded the vehicle, infrared imaging data of the target object’s face was collected at detection time intervals using a thermal imaging sensor device mounted under the rearview mirror.

[0033] In module M2:

[0034] The vehicle's computer uses a facial recognition algorithm to extract the temperature of the cheek area from the thermal image, performs noise reduction processing, and obtains the skin temperature signal; it then transmits the cheek skin temperature, the intensity of solar radiation inside the vehicle, and the cabin air temperature to the storage medium.

[0035] Using a pre-trained infrared imaging face recognition algorithm, the temperature measurement value of the cheek is extracted, and the skin temperature data within the preset range is removed to correct the cheek imaging temperature of the occupants in the vehicle.

[0036] Preferably, in module M3:

[0037] The USB-Type C microcontroller transmits data on cheek skin temperature, solar radiation intensity, and passenger cabin air temperature to the vehicle terminal via USB. After obtaining the cheek skin temperature, real-time solar radiation intensity, and air temperature near the passenger area, the vehicle terminal inputs the three types of data into the thermal sensation calculation model to calculate the thermal sensation of the occupants inside the vehicle.

[0038] The pre-trained model is represented as follows:

[0039] TSV = A × T air +B×Rs +C×T incheek +D

[0040] Among them, T air Indicates cabin air temperature; R s T represents the total solar radiation inside the cockpit; incheek A is the skin temperature of the occupant's cheek on the non-window side; B is the regression coefficient of the cabin air temperature, representing the change in thermal sensation when the air temperature changes by a unit; C is the regression coefficient of the solar radiation intensity inside the cabin, representing the change in thermal sensation when the solar radiation intensity changes by a unit; D is the constant term of the thermal sensation calculation model.

[0041] Preferably, in module M4:

[0042] The vehicle terminal generates corresponding air conditioning temperature adjustment commands based on the calculated thermal sensation values ​​of the occupants inside the vehicle; the vehicle terminal transmits the temperature adjustment commands to the microcontroller, and the microcontroller sends commands to the cabin air conditioning main controller to adjust the air conditioning setpoint; the vehicle LCD screen displays the current solar radiation intensity inside the vehicle, the detected cheek skin temperature, the cabin air temperature, and the thermal sensation of the target passenger; when the timer set time is reached, it jumps to module M1;

[0043] If the calculated perceived heat level is greater than the preset value, the passenger's perceived heat level is determined to be hot, and the air outlet temperature is lowered while the air outlet speed is increased; if the calculated perceived heat level is within the preset range, the passenger's perceived heat level is determined to be neutral, and no adjustment is made to the air outlet temperature or air outlet speed; if the calculated perceived heat level is less than the preset value, the passenger's perceived heat level is determined to be cold, and the air outlet temperature is increased while the air outlet speed is decreased.

[0044] According to the present invention, a computer-readable storage medium storing a computer program is provided, wherein when the computer program is executed by a processor, it implements the steps of any of the claims of the infrared thermal imaging-based cockpit occupant thermal sensation evaluation methods.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] 1. This invention evaluates thermal sensation by using skin temperature at a single site, which is simple and portable, does not require skin temperature at multiple points as input, and has high accuracy.

[0047] 2. This invention uses facial skin temperature as one of the inputs to automatically adjust the cabin air conditioning temperature based on the thermal perception of each passenger; the system provides personalized temperature settings for each passenger; this means that without manual operation, the air conditioning system will provide personalized temperature settings for each passenger, ensuring that everyone can travel safely in a comfortable temperature.

[0048] 3. This invention achieves automatic control of cabin air conditioning by adopting a non-contact air conditioning control scheme, ensuring the driving safety of passengers and staff (drivers, tower crane operators, etc.) in the cabin.

[0049] 4. By adopting the method of this invention, the air conditioning air supply parameters can be dynamically optimized in real time based on the user's thermal sensation, avoiding long-term fixed air supply and having energy-saving potential; by adjusting the air conditioning according to the actual needs of passengers, the air conditioning system can utilize energy more effectively; this can reduce fuel or battery consumption, improve cabin energy efficiency, reduce operating costs and reduce environmental impact.

[0050] 5. By employing the method of this invention, driver fatigue can be assessed through thermal imaging; for long-distance travel, the air conditioning system using this method and system can help reduce passenger fatigue and discomfort, improving driving safety. It can also help reduce health problems caused by excessive exposure to extreme temperatures;

[0051] 6. By adopting the method of the present invention, the number and position of passengers in the vehicle can be detected in real time, and the air supply parameters of multiple air outlets can be dynamically adjusted. Attached Figure Description

[0052] Other features, objects, and advantages of the present invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0053] Figure 1 A schematic diagram of a cockpit occupant thermal perception assessment system based on infrared thermal imaging;

[0054] Figure 2 A schematic diagram of the display screen interface of a cockpit occupant thermal perception assessment system based on infrared thermal imaging;

[0055] Figure 3 This is a schematic diagram showing the stability and accuracy test results of the cabin occupant thermal sensation evaluation system based on infrared thermal imaging in the embodiment. Detailed Implementation

[0056] The present invention will now be described in detail with reference to specific embodiments. These embodiments will help those skilled in the art to further understand the present invention, but do not limit the invention in any way. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all fall within the protection scope of the present invention.

[0057] Example 1:

[0058] This invention relates to a method and system for evaluating the thermal sensation of occupants in a vehicle cabin based on infrared thermal imaging. The method uses a thermal imaging sensor to collect the facial temperature of occupants, extracts data from the vehicle's solar radiometer and the cabin air temperature, and calculates the occupants' thermal sensation based on a laboratory-established model. Furthermore, the evaluation system applies this method, using an onboard computer to calculate occupant thermal sensation and transmitting corresponding temperature adjustment commands to the cabin air conditioning main controller via a microcontroller, automatically adjusting the cabin thermal environment and displaying the calculation results on a monitor. This method and system aim to optimize the passenger experience, increase occupant comfort, and reduce driving hazards caused by manual air conditioning adjustments during driving.

[0059] The unique advantage of this patent lies in its integration with the cabin air conditioning system, achieving automatic temperature adjustment through intelligent thermal sensation evaluation, thus providing a more comfortable riding experience for passengers. This invention, taking a forward-looking approach, uses facial skin temperature and readings from common vehicle sensors (solar radiation sensor and cabin temperature sensor) to calculate and evaluate the thermal sensation of cabin occupants, thereby automatically controlling the temperature of the vehicle's air conditioning system.

[0060] According to the present invention, a method for evaluating the thermal sensation of cockpit occupants based on infrared thermal imaging is provided, such as... Figures 1-3 As shown, it includes:

[0061] Step S1: Real-time acquisition of the temperature of the imaging area, the intensity of solar radiation inside the cabin, and the air temperature in the breathing area of ​​the occupants inside the vehicle;

[0062] Specifically, in step S1:

[0063] As passengers enter the vehicle, thermal imaging sensors collect the temperature of the imaging area in real time; solar radiation sensors in front of the control panel inside the vehicle collect the solar radiation intensity inside the cabin in real time; and air temperature sensors at the seats inside the vehicle collect the air temperature in the breathing area of ​​the occupants in real time.

[0064] The face recognition algorithm and cheek region segmentation algorithm were trained using an open-source infrared human image dataset and YOLO V5. The trained infrared imaging face recognition algorithm was used to detect whether there were passengers in the vehicle. When a passenger was detected to have boarded the vehicle, infrared imaging data of the target object's face was collected at detection time intervals using a thermal imaging sensor device mounted under the rearview mirror.

[0065] Step S2: Extract the temperature of the cheek area from the thermal image and perform noise reduction processing to obtain the cheek skin temperature signal;

[0066] Specifically, in step S2:

[0067] The vehicle's computer uses a facial recognition algorithm to extract the temperature of the cheek area from the thermal image, performs noise reduction processing, and obtains the skin temperature signal; it then transmits the cheek skin temperature, the intensity of solar radiation inside the vehicle, and the cabin air temperature to the storage medium.

[0068] Using a pre-trained infrared imaging face recognition algorithm, the temperature measurement value of the cheek is extracted, and the skin temperature data within the preset range is removed to correct the cheek imaging temperature of the occupants in the vehicle.

[0069] Step S3: By transmitting air temperature, solar radiation intensity, and cheek skin temperature to the vehicle cabin thermal sensation calculation model, the thermal sensation level is calculated.

[0070] Specifically, in step S3:

[0071] The USB-Type C microcontroller transmits data on cheek skin temperature, solar radiation intensity, and passenger cabin air temperature to the vehicle terminal via USB. After obtaining the cheek skin temperature, real-time solar radiation intensity, and air temperature near the passenger area, the vehicle terminal inputs the three types of data into the thermal sensation calculation model to calculate the thermal sensation of the occupants inside the vehicle.

[0072] The pre-trained model is represented as follows:

[0073] TSV = A × T air +B×R s +C×T incheek +D

[0074] Among them, T air Indicates cabin air temperature; R s T represents the total solar radiation inside the cockpit; incheekA is the skin temperature of the occupant's cheek on the non-window side; B is the regression coefficient of the cabin air temperature, representing the change in thermal sensation when the air temperature changes by a unit; C is the regression coefficient of the solar radiation intensity inside the cabin, representing the change in thermal sensation when the solar radiation intensity changes by a unit; D is the constant term of the thermal sensation calculation model.

[0075] Step S4: Based on the thermal perception level of the occupants, generate the corresponding air conditioning temperature adjustment command and transmit it to the microcontroller. The microcontroller then sends the command to the cabin air conditioning main controller to adjust the air conditioning setpoint.

[0076] Specifically, in step S4:

[0077] The vehicle terminal generates a corresponding air conditioning temperature adjustment command based on the calculated thermal sensation values ​​of the occupants inside the vehicle; the vehicle terminal transmits the temperature adjustment command to the microcontroller, and the microcontroller sends a command to the cabin air conditioning main controller to adjust the air conditioning setpoint; the vehicle LCD screen displays the current solar radiation intensity inside the vehicle, the detected cheek skin temperature, the cabin air temperature, and the thermal sensation of the target passenger; when the timer set time is reached, it jumps to step S1;

[0078] If the calculated perceived heat level is greater than the preset value, the passenger's perceived heat level is determined to be hot, and the air outlet temperature is lowered while the air outlet speed is increased; if the calculated perceived heat level is within the preset range, the passenger's perceived heat level is determined to be neutral, and no adjustment is made to the air outlet temperature or air outlet speed; if the calculated perceived heat level is less than the preset value, the passenger's perceived heat level is determined to be cold, and the air outlet temperature is increased while the air outlet speed is decreased.

[0079] Example 2:

[0080] Example 2 is a preferred embodiment of Example 1, and is used to illustrate the present invention in more detail.

[0081] The present invention also provides a cockpit occupant thermal perception evaluation system based on infrared thermal imaging. The cockpit occupant thermal perception evaluation system based on infrared thermal imaging can be implemented by executing the process steps of the cockpit occupant thermal perception evaluation method based on infrared thermal imaging. That is, those skilled in the art can understand the cockpit occupant thermal perception evaluation method based on infrared thermal imaging as a preferred embodiment of the cockpit occupant thermal perception evaluation system based on infrared thermal imaging.

[0082] A cockpit occupant thermal perception assessment system based on infrared thermal imaging, according to the present invention, includes:

[0083] Module M1: Real-time acquisition of the temperature of the imaging area, the intensity of solar radiation inside the cabin, and the air temperature in the breathing area of ​​the occupants.

[0084] Specifically, in module M1:

[0085] As passengers enter the vehicle, thermal imaging sensors collect the temperature of the imaging area in real time; solar radiation sensors in front of the control panel inside the vehicle collect the solar radiation intensity inside the cabin in real time; and air temperature sensors at the seats inside the vehicle collect the air temperature in the breathing area of ​​the occupants in real time.

[0086] The face recognition algorithm and cheek region segmentation algorithm were trained using an open-source infrared human image dataset and YOLO V5. The trained infrared imaging face recognition algorithm was used to detect whether there were passengers in the vehicle. When a passenger was detected to have boarded the vehicle, infrared imaging data of the target object’s face was collected at detection time intervals using a thermal imaging sensor device mounted under the rearview mirror.

[0087] Module M2: Extracts the temperature of the cheek area from the thermal image, performs noise reduction processing, and obtains the cheek skin temperature signal;

[0088] In module M2:

[0089] The vehicle's computer uses a facial recognition algorithm to extract the temperature of the cheek area from the thermal image, performs noise reduction processing, and obtains the skin temperature signal; it then transmits the cheek skin temperature, the intensity of solar radiation inside the vehicle, and the cabin air temperature to the storage medium.

[0090] Using a pre-trained infrared imaging face recognition algorithm, the temperature measurement value of the cheek is extracted, and the skin temperature data within the preset range is removed to correct the cheek imaging temperature of the occupants in the vehicle.

[0091] Module M3: The thermal sensation level is calculated by transmitting air temperature, solar radiation intensity, and cheek skin temperature to the cabin thermal sensation calculation model;

[0092] Specifically, in module M3:

[0093] The USB-Type C microcontroller transmits data on cheek skin temperature, solar radiation intensity, and passenger cabin air temperature to the vehicle terminal via USB. After obtaining the cheek skin temperature, real-time solar radiation intensity, and air temperature near the passenger area, the vehicle terminal inputs the three types of data into the thermal sensation calculation model to calculate the thermal sensation of the occupants inside the vehicle.

[0094] The pre-trained model is represented as follows:

[0095] TSV = A × T air +B×R s +C×T incheek +D

[0096] Among them, Tair Indicates cabin air temperature; R s T represents the total solar radiation inside the cockpit; incheek A is the skin temperature of the occupant's cheek on the non-window side; B is the regression coefficient of the cabin air temperature, representing the change in thermal sensation when the air temperature changes by a unit; C is the regression coefficient of the solar radiation intensity inside the cabin, representing the change in thermal sensation when the solar radiation intensity changes by a unit; D is the constant term of the thermal sensation calculation model.

[0097] Module M4: Based on the thermal perception level of the occupants, it generates corresponding air conditioning temperature adjustment commands and transmits them to the microcontroller. The microcontroller then sends commands to the cabin air conditioning main controller to adjust the air conditioning setpoint.

[0098] Specifically, in module M4:

[0099] The vehicle terminal generates corresponding air conditioning temperature adjustment commands based on the calculated thermal sensation values ​​of the occupants inside the vehicle; the vehicle terminal transmits the temperature adjustment commands to the microcontroller, and the microcontroller sends commands to the cabin air conditioning main controller to adjust the air conditioning setpoint; the vehicle LCD screen displays the current solar radiation intensity inside the vehicle, the detected cheek skin temperature, the cabin air temperature, and the thermal sensation of the target passenger; when the timer set time is reached, it jumps to module M1;

[0100] If the calculated perceived heat level is greater than the preset value, the passenger's perceived heat level is determined to be hot, and the air outlet temperature is lowered while the air outlet speed is increased; if the calculated perceived heat level is within the preset range, the passenger's perceived heat level is determined to be neutral, and no adjustment is made to the air outlet temperature or air outlet speed; if the calculated perceived heat level is less than the preset value, the passenger's perceived heat level is determined to be cold, and the air outlet temperature is increased while the air outlet speed is decreased.

[0101] According to the present invention, a computer-readable storage medium storing a computer program is provided, wherein when the computer program is executed by a processor, it implements the steps of any of the claims of the infrared thermal imaging-based cockpit occupant thermal sensation evaluation methods.

[0102] Example 3:

[0103] Example 3 is a preferred example of Example 1, and is used to illustrate the present invention in more detail.

[0104] This invention provides a method and system for evaluating the thermal sensation of cockpit occupants based on infrared thermal imaging (see...). Figure 1 The process includes the following steps:

[0105] Step one: Passengers enter the vehicle, and thermal imaging sensors collect the temperature of the imaging area in real time. A solar radiation sensor in front of the control panel inside the vehicle collects the solar radiation intensity inside the cabin in real time; an air temperature sensor at the seats collects the air temperature in the breathing area of ​​the occupants in real time.

[0106] Step two: Extract the temperature of the cheek area from the thermal image using a pre-trained face recognition algorithm, and perform noise reduction processing to obtain a clean skin temperature signal.

[0107] Step 3: By transmitting air temperature, solar radiation intensity, and cheek skin temperature to a pre-trained cabin thermal sensation calculation model, the thermal sensation level is calculated.

[0108] Based on our existing research results, the pre-trained model can be represented as follows:

[0109] TSV = A × T air +B×R s +C×T incheek +D

[0110] Among them, "T" air "R" indicates the cabin air temperature. s "This represents the total solar radiation inside the cockpit." (T) incheek "This refers to the temperature of the occupant's cheek on the non-window side. A is the regression coefficient of the cabin air temperature, representing the change in thermal sensation when the air temperature changes by a unit. B is the regression coefficient of the cabin solar radiation intensity, representing the change in thermal sensation when the solar radiation intensity changes by a unit. C are the regression coefficients of the occupant's cheek temperature on the non-window side, representing the change in thermal sensation when the cheek temperature changes by a unit. D is the constant term of the thermal sensation calculation model."

[0111] The present invention also provides a cockpit occupant thermal perception assessment system based on infrared thermal imaging.

[0112] The system includes the following devices: an onboard computer (including a processor and chip), a thermal imaging sensor, a USB-Type-C microcontroller, a cockpit solar radiometer, a cockpit air temperature sensor, an automotive LCD screen, and storage media. The specific implementation process of this solution includes the following steps (see...). Figure 2 ):

[0113] Step one: Passengers enter the vehicle, and the thermal imaging sensor collects the temperature of the imaging area in real time.

[0114] Step two: The onboard computer extracts the temperature of the cheek area from the thermal image using a facial recognition algorithm, and performs noise reduction processing to obtain a clean skin temperature signal. The cheek temperature, the intensity of solar radiation inside the vehicle, and the cabin air temperature are then transmitted to the storage medium.

[0115] Step three: The USB-Type-C microcontroller transmits facial temperature, solar radiation intensity, and passenger cabin air temperature data to the in-vehicle terminal via USB. After receiving the facial temperature, real-time solar radiation intensity, and near-occupant air temperature, the in-vehicle terminal inputs these three data points into the thermal perception calculation model to calculate the passenger's thermal sensation inside the vehicle.

[0116] Step four: The vehicle terminal generates corresponding air conditioning temperature adjustment commands based on the calculated thermal sensation values ​​of the occupants inside the vehicle.

[0117] Step 5: The vehicle terminal transmits the temperature adjustment command to the microcontroller, which then sends the command to the cabin air conditioning main controller to adjust the air conditioning setpoint.

[0118] Step six: The in-vehicle LCD screen displays the current solar radiation intensity inside the vehicle, the detected skin temperature on the cheeks, the cabin air temperature, and the target passenger's thermal sensation.

[0119] Step 7: When the timer reaches the set time, proceed to Step 1.

[0120] In step one, an open-source infrared portrait image dataset and YOLO V5 are used to train a face recognition algorithm and a cheek region segmentation algorithm. The trained infrared imaging face recognition algorithm is then used to detect whether there are passengers inside the vehicle. Once a passenger is detected, infrared imaging data of the target's face is collected at detection time intervals (1, 2, 5, and 8 minutes after the passenger boards, and every 10 minutes after 16 minutes). This is done using a thermal imaging sensor mounted below the rearview mirror.

[0121] In step two, a pre-trained infrared imaging face recognition algorithm is used to extract the temperature measurement value of the cheek. Assuming the infrared emissivity of the human body being measured is 0.98 and the imaging distance is set to 0.7m (the thermal imaging sensor is installed near the front reading lights), skin temperature data outside the 30-40℃ range are removed, and the cheek imaging temperature of the occupants in the vehicle is corrected.

[0122] In step three, air temperature, solar radiation intensity, and facial skin temperature are transmitted to a cabin thermal sensation evaluation model established based on laboratory experiments to calculate the thermal sensation level. The following formula is used to calculate the thermal sensation:

[0123] TSV = A × T air +B×R s +C×T incheek +D

[0124] Among them, "T" air "R" indicates the cabin air temperature. s "This represents the total solar radiation inside the cockpit." (T) incheek"This refers to the temperature of the occupant's cheek on the non-window side. A is the regression coefficient of the cabin air temperature, representing the change in thermal sensation when the air temperature changes by a unit. B is the regression coefficient of the cabin solar radiation intensity, representing the change in thermal sensation when the solar radiation intensity changes by a unit. C are the regression coefficients of the occupant's cheek temperature on the non-window side, representing the change in thermal sensation when the cheek temperature changes by a unit. D is the constant term of the thermal sensation calculation model."

[0125] In step four, if the calculated thermal sensation value is greater than 0.5, the passenger's thermal sensation level is determined to be hot, and the air outlet temperature is lowered while the air outlet speed is increased. If the calculated value is -0.5 < thermal sensation value < 0.5, the passenger's thermal sensation level is determined to be neutral, and no adjustment is made to the air outlet temperature or air outlet speed. If the calculated thermal sensation value is less than -0.5, the passenger's thermal sensation level is determined to be cold, and the air outlet temperature is increased while the air outlet speed is decreased.

[0126] In step five, the timer is triggered at the following intervals: 1, 2, 5, and 8 minutes after the passenger boards the vehicle, and every 10 minutes after the 16th minute.

[0127] The present invention also provides a storage component for storing the data calculated and read by any of the methods described above. The method can also be combined with a computer-readable storage medium storing a corresponding computer program for executing a thermal evaluation method based on infrared thermal imaging technology. The computer program is capable of interpreting and executing computer instructions, including computer program code, which can exist in various forms, such as source code, object code, executable files, or other intermediate forms. Computer-readable storage media can include various forms of media and devices, such as physical storage media, recording media, USB drives, portable hard drives, disks, optical discs, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media. It is important to emphasize that the specific scope of computer-readable storage media may vary depending on the laws and patent practices of different jurisdictions. For example, in some jurisdictions, electrical carrier signals and telecommunication signals may not be considered computer-readable storage media.

[0128] Example 4:

[0129] Example 4 is a preferred example of Example 1, which is used to illustrate the present invention in more detail.

[0130] Test objective: To test the effectiveness and accuracy of an infrared thermal imaging-based cockpit occupant thermal perception assessment system.

[0131] Test conditions: Conducted outdoors in Shanghai during the summer. A total of 6 healthy subjects were recruited for the experiment. All participants were undergraduate or graduate students aged 20-30. All subjects were in good health, with no history of cardiovascular or other serious illnesses, and were non-smokers. All subjects had lived in Shanghai for more than three years and were acclimatized to the hot-winter, cold-summer climate. Clothing consisted of underwear, a thin short-sleeved T-shirt, athletic pants, thin socks, and athletic shoes; the estimated thermal resistance of the clothing was approximately 0.5 clo. Throughout the experiment, subjects wore the same clothing under all conditions.

[0132] Test conditions: from 55℃ to 24℃; from 26℃ to 35℃, then to 20℃; from 35℃ to 26℃ (cloudy day, 50W / m2 solar radiation). Two subjects were randomly assigned to participate in two experiments (randomized conditions), and the remaining subjects each participated in one experiment (randomized conditions).

[0133] Implementation process:

[0134] Figure 1 The flowchart of an embodiment entitled "A Cockpit Occupant Thermal Sensation Evaluation System Based on Infrared Thermal Imaging Technology" is shown. The system includes the following devices: an in-vehicle computer (NVIDIA X1 processor, the in-vehicle system is based on Android and equipped with a Qualcomm Snapdragon 8155 chip), a thermal imaging sensor (Iray thermal imaging sensor, resolution 256×192), a USB-Type-C microcontroller, and an in-vehicle LCD display. Its workflow is as follows:

[0135] (1) Each time one or two occupants enter the cabin from the outside, the Iray thermal imaging sensor determines the presence of occupants in the vehicle through a facial recognition algorithm, the calculation process begins, and the timer starts.

[0136] (2) The Iray thermal imaging sensor collects the temperature of the imaging area in real time. The onboard computer extracts the temperature of the cheek area in the thermal image through a facial recognition algorithm, and performs noise reduction processing to obtain a clean skin temperature signal (skin temperature in the range of 30-40℃). The cheek temperature, the intensity of solar radiation inside the vehicle, and the cabin air temperature are transmitted to the storage medium.

[0137] (3) The USB-Type C microcontroller transmits data on cheek temperature, solar radiation intensity, and passenger cabin air temperature to the vehicle terminal via USB. After obtaining the cheek temperature, real-time solar radiation intensity, and air temperature near the passenger area, the vehicle terminal inputs these three types of data into a thermal perception calculation model suitable for the vehicle, which is fitted based on laboratory experimental results. The model calculates the passenger's thermal perception and generates corresponding temperature adjustment commands: if the calculated thermal perception is >0.5, the passenger's thermal perception level is determined to be hot, and commands to lower the air outlet temperature and increase the air outlet speed are generated; if the calculated thermal perception is -0.5 < thermal perception < 0.5, the passenger's thermal perception level is determined to be neutral, and no commands to adjust the air outlet temperature and air outlet speed are generated; if the calculated thermal perception is <-0.5, the passenger's thermal perception level is determined to be cold, and commands to increase the air outlet temperature and decrease the air outlet speed are generated.

[0138] (4) The in-vehicle LCD screen displays the current solar radiation intensity inside the vehicle, the detected facial skin temperature, the cabin air temperature, and the thermal sensation of the target passenger (see Figure 2 ).

[0139] (6) When the timer reaches the set time, proceed to step one.

[0140] (7) Compare the thermal sensation output results in the evaluation system with the actual thermal sensation votes (see...). Figure 3 The system outputs thermal sensations that closely match real-world thermal sensations, demonstrating high accuracy.

[0141] Those skilled in the art will understand that, besides implementing the system and its various devices, modules, and units provided by this invention in the form of purely computer-readable program code, the same functions can be achieved entirely through logical programming of the method steps, making the system and its various devices, modules, and units of this invention function in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, the system and its various devices, modules, and units provided by this invention can be considered as a hardware component, and the devices, modules, and units included therein for implementing various functions can also be considered as structures within the hardware component; alternatively, the devices, modules, and units for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0142] Specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the specific embodiments described above, and those skilled in the art can make various changes or modifications within the scope of the claims, which do not affect the essence of the present invention. Unless otherwise specified, the embodiments and features described in this application can be arbitrarily combined with each other.

Claims

1. A method for evaluating the thermal sensation of cockpit occupants based on infrared thermal imaging, characterized in that, include: Step S1: Real-time acquisition of the temperature of the imaging area, the intensity of solar radiation inside the cabin, and the air temperature in the breathing area of ​​the occupants inside the vehicle; Step S2: Extract the temperature of the cheek area from the thermal image and perform noise reduction processing to obtain the cheek skin temperature signal; Step S3: By transmitting air temperature, solar radiation intensity, and cheek skin temperature to the vehicle cabin thermal sensation calculation model, the thermal sensation level is calculated. Step S4: Based on the thermal perception level of the occupants, generate corresponding air conditioning temperature adjustment commands and transmit them to the microcontroller. The microcontroller then sends commands to the cabin air conditioning main controller to adjust the air conditioning setpoint. In step S3: The USB-Typec microcontroller transmits data on cheek skin temperature, solar radiation intensity, and passenger cabin air temperature to the vehicle terminal via USB. After obtaining the skin temperature of the cheek, the real-time solar radiation intensity, and the air temperature near the occupants, the vehicle terminal inputs the three types of data into the thermal sensation calculation model to calculate the thermal sensation of the occupants inside the vehicle. The pre-trained model is represented as follows: TSV=A×T air +B×R s +C×T incheek +D Among them, T air Indicates cabin air temperature; R s T represents the total solar radiation inside the cockpit; incheek A is the skin temperature of the occupant's cheek on the non-window side; B is the regression coefficient of the cabin air temperature, representing the change in thermal sensation when the air temperature changes by a unit; C is the regression coefficient of the solar radiation intensity inside the cabin, representing the change in thermal sensation when the solar radiation intensity changes by a unit; D is the constant term of the thermal sensation calculation model.

2. The method for evaluating cockpit occupant thermal sensation based on infrared thermal imaging according to claim 1, characterized in that, In step S1: As passengers enter the vehicle, thermal imaging sensors collect the temperature of the imaging area in real time; solar radiation sensors in front of the control panel inside the vehicle collect the solar radiation intensity inside the cabin in real time; and air temperature sensors at the seats inside the vehicle collect the air temperature in the breathing area of ​​the occupants in real time. The face recognition algorithm and cheek region segmentation algorithm were trained using an open-source infrared human image dataset and YOLO V5. The trained infrared imaging face recognition algorithm was used to detect whether there were passengers in the vehicle. When a passenger was detected to have boarded the vehicle, infrared imaging data of the target object's face was collected at detection time intervals using a thermal imaging sensor device mounted under the rearview mirror.

3. The method for evaluating cockpit occupant thermal sensation based on infrared thermal imaging according to claim 1, characterized in that, In step S2: The vehicle's computer uses a facial recognition algorithm to extract the temperature of the cheek area from the thermal image, performs noise reduction processing, and obtains the skin temperature signal; it then transmits the cheek skin temperature, the intensity of solar radiation inside the vehicle, and the cabin air temperature to the storage medium. Using a pre-trained infrared imaging face recognition algorithm, the temperature measurement value of the cheek is extracted, and the skin temperature data within the preset range is removed to correct the cheek imaging temperature of the occupants in the vehicle.

4. The method for evaluating cockpit occupant thermal sensation based on infrared thermal imaging according to claim 1, characterized in that, In step S4: The vehicle terminal generates corresponding air conditioning temperature adjustment commands based on the calculated thermal sensation values ​​of the occupants inside the vehicle; the vehicle terminal transmits the temperature adjustment commands to the microcontroller, and the microcontroller sends commands to the cabin air conditioning main controller to adjust the air conditioning setpoint; the vehicle LCD screen displays the current solar radiation intensity inside the vehicle, the detected cheek skin temperature, the cabin air temperature, and the thermal sensation of the target passenger. When the timer reaches the set time, proceed to step S1; If the calculated thermal sensation is greater than the preset value, the passenger's thermal sensation level is determined to be hot, and the air outlet temperature is lowered and the air outlet speed is increased. If the calculated thermal sensation is within the preset range, the passenger's thermal sensation level is determined to be neutral, and no adjustment is made to the air outlet temperature and air outlet speed; if the calculated thermal sensation is less than the set value, the passenger's thermal sensation level is determined to be cold, and the air outlet temperature is increased and the air outlet speed is decreased.

5. A cockpit occupant thermal perception assessment system based on infrared thermal imaging, characterized in that, include: Module M1: Real-time acquisition of the temperature of the imaging area, the intensity of solar radiation inside the cabin, and the air temperature in the breathing area of ​​the occupants. Module M2: Extracts the temperature of the cheek area from the thermal image, performs noise reduction processing, and obtains the cheek skin temperature signal; Module M3: The thermal sensation level is calculated by transmitting air temperature, solar radiation intensity, and cheek skin temperature to the cabin thermal sensation calculation model; Module M4: Based on the thermal perception level of the occupants, it generates corresponding air conditioning temperature adjustment commands and transmits them to the microcontroller. The microcontroller then sends commands to the cabin air conditioning main controller to adjust the air conditioning setpoint. In module M3: The USB-Typec microcontroller transmits data on cheek skin temperature, solar radiation intensity, and passenger cabin air temperature to the vehicle terminal via USB. After obtaining the skin temperature of the cheek, the real-time solar radiation intensity, and the air temperature near the occupants, the vehicle terminal inputs the three types of data into the thermal sensation calculation model to calculate the thermal sensation of the occupants inside the vehicle. The pre-trained model is represented as follows: TSV=A×T air +B×R s +C×T incheek +D Among them, T air Indicates cabin air temperature; R s T represents the total solar radiation inside the cockpit; incheek A is the skin temperature of the occupant's cheek on the non-window side; B is the regression coefficient of the cabin air temperature, representing the change in thermal sensation when the air temperature changes by a unit; C is the regression coefficient of the solar radiation intensity inside the cabin, representing the change in thermal sensation when the solar radiation intensity changes by a unit; D is the constant term of the thermal sensation calculation model.

6. The cockpit occupant thermal sensation assessment system based on infrared thermal imaging according to claim 5, characterized in that, In module M1: As passengers enter the vehicle, thermal imaging sensors collect the temperature of the imaging area in real time; solar radiation sensors in front of the control panel inside the vehicle collect the solar radiation intensity inside the cabin in real time; and air temperature sensors at the seats inside the vehicle collect the air temperature in the breathing area of ​​the occupants in real time. The face recognition algorithm and cheek region segmentation algorithm were trained using an open-source infrared human image dataset and YOLO V5. The trained infrared imaging face recognition algorithm was used to detect whether there were passengers in the vehicle. When a passenger was detected to have boarded the vehicle, infrared imaging data of the target object’s face was collected at detection time intervals using a thermal imaging sensor device mounted under the rearview mirror. In module M2: The vehicle's computer uses a facial recognition algorithm to extract the temperature of the cheek area from the thermal image, performs noise reduction processing, and obtains the skin temperature signal; it then transmits the cheek skin temperature, the intensity of solar radiation inside the vehicle, and the cabin air temperature to the storage medium. Using a pre-trained infrared imaging face recognition algorithm, the temperature measurement value of the cheek is extracted, and the skin temperature data within the preset range is removed to correct the cheek imaging temperature of the occupants in the vehicle.

7. The cockpit occupant thermal sensation assessment system based on infrared thermal imaging according to claim 5, characterized in that, In module M4: The vehicle terminal generates corresponding air conditioning temperature adjustment commands based on the calculated thermal sensation values ​​of the occupants inside the vehicle; the vehicle terminal transmits the temperature adjustment commands to the microcontroller, and the microcontroller sends commands to the cabin air conditioning main controller to adjust the air conditioning setpoint; the vehicle LCD screen displays the current solar radiation intensity inside the vehicle, the detected cheek skin temperature, the cabin air temperature, and the thermal sensation of the target passenger. When the timer reaches the set time, jump to module M1; If the calculated thermal sensation is greater than the preset value, the passenger's thermal sensation level is determined to be hot, and the air outlet temperature is lowered and the air outlet speed is increased. If the calculated thermal sensation is within the preset range, the passenger's thermal sensation level is determined to be neutral, and no adjustment is made to the air outlet temperature and air outlet speed; if the calculated thermal sensation is less than the set value, the passenger's thermal sensation level is determined to be cold, and the air outlet temperature is increased and the air outlet speed is decreased.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the cockpit occupant thermal sensation evaluation method based on infrared thermal imaging as described in any one of claims 1 to 4.

Images