In-vehicle gas circulation control methods, equipment, storage media and devices

Abstract

This invention discloses a method, device, storage medium, and apparatus for controlling in-vehicle gas circulation. The invention acquires images of passengers' faces inside the vehicle and determines their facial coordinates based on these images. It then determines a target vent based on the facial coordinates and a preset vent location, and obtains the in-vehicle gas concentration through the target vent. Finally, it controls in-vehicle gas circulation based on the in-vehicle gas concentration and a preset gas concentration. Compared to existing technologies where in-vehicle gas detection sensors have a small detection range and cannot accurately determine the gas information around passengers' faces, leading to inaccurate detection results and affecting user experience, this invention solves the problem of limited gas detection locations. By combining facial recognition technology to accurately locate passengers, it can perform real-time gas detection at the passenger's facial position, achieving more accurate concentration detection and improving user experience.

Description

Technical Field

[0001] This invention relates to the field of automotive technology, and in particular to a method, device, storage medium, and apparatus for controlling in-vehicle gas circulation. Background Technology

[0002] With economic development and advancements in automotive technology, there is increasing attention being paid to in-vehicle air pollution. To prevent in-vehicle pollutants from affecting the health of passengers, in-vehicle gases are detected, and corresponding devices are controlled to circulate the gases based on the detection results. However, in existing technologies, in-vehicle gas detection sensors have a small detection range and cannot accurately determine the gas information around the passenger's face, resulting in inaccurate detection results and affecting the user experience.

[0003] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main objective of this invention is to provide a method, device, storage medium, and apparatus for controlling in-vehicle gas circulation, aiming to solve the technical problem that in the prior art, in-vehicle gas detection sensors have a small detection range and cannot accurately determine the gas information around the passenger's face, resulting in inaccurate detection results and affecting user experience.

[0005] To achieve the above objectives, the present invention provides a method for controlling in-vehicle air circulation, the method comprising the following steps:

[0006] Collect facial images of passengers inside the vehicle, and determine facial coordinate information based on the facial images of passengers inside the vehicle;

[0007] The target vent is determined based on the face coordinate information and the preset vent location, and the gas concentration inside the vehicle is obtained through the target vent.

[0008] The vehicle's internal gas circulation is controlled based on the vehicle's internal gas concentration and a preset gas concentration.

[0009] Optionally, the step of acquiring facial images of passengers inside the vehicle and determining facial coordinate information based on the facial images of passengers inside the vehicle includes:

[0010] The system captures facial images of passengers inside the vehicle using a preset dual-camera setup, and then binarizes these images to obtain a processed binarized image.

[0011] Gradient features are extracted from the binarized image, and face coordinate information is determined based on the gradient features of the binarized image.

[0012] Optionally, the step of extracting gradient features from the binarized image and determining face coordinate information based on the gradient features of the binarized image includes:

[0013] Gradient feature extraction is performed on the binarized image to obtain the first gradient feature in the horizontal direction and the second gradient feature in the vertical direction;

[0014] Face coordinate information is determined based on the first gradient feature and the second gradient feature.

[0015] Optionally, the step of determining face coordinate information based on the first gradient feature and the second gradient feature includes:

[0016] The first gradient feature is augmented with data, and a first face image is generated based on the augmented first gradient feature;

[0017] The second gradient feature is augmented with data, and a second face image is generated based on the augmented second gradient feature;

[0018] The facial coordinate information is determined based on the first facial image and the second facial image.

[0019] Optionally, the step of determining face coordinate information based on the first face image information and the second face image information includes:

[0020] The vertical coordinate of the human eye is determined based on the first face image and the second face image;

[0021] The target eye region is determined based on the vertical coordinate of the human eye, and the upper and lower eye socket contours are extracted from the target eye region.

[0022] The intersection of the upper and lower eye sockets is determined based on the upper and lower eye socket contours, and the coordinates of the target eye corner are determined based on the intersection of the upper and lower eye sockets.

[0023] The facial coordinate information is determined based on the target eye corner coordinates.

[0024] Optionally, the step of determining the vertical coordinate of the human eye based on the first face image information and the second face image information includes:

[0025] Binary segmentation of the first and second face images is performed based on the maximum inter-class variance thresholding method to obtain the segmented foreground and background images;

[0026] The eye edge contour region and pupil region are determined based on the white gradient features in the foreground and background images;

[0027] The vertical coordinates of the human eye are determined based on the eye's edge contour region and pupil region.

[0028] Optionally, the step of controlling the in-vehicle gas circulation based on the in-vehicle gas concentration and a preset gas concentration includes:

[0029] When the gas concentration inside the vehicle exceeds the preset gas concentration, an alarm is triggered based on the gas concentration inside the vehicle, and the air conditioning is automatically turned on to circulate the external air.

[0030] If the alarm duration exceeds the preset time and the car window is not open, the car window will automatically lower.

[0031] Furthermore, to achieve the above objectives, the present invention also proposes an in-vehicle gas circulation control device, which includes a memory, a processor, and an in-vehicle gas circulation control program stored in the memory and executable on the processor. The in-vehicle gas circulation control program is configured to implement the steps of in-vehicle gas circulation control as described above.

[0032] Furthermore, to achieve the above objectives, the present invention also proposes a storage medium storing an in-vehicle air circulation control program, wherein when the in-vehicle air circulation control program is executed by a processor, the in-vehicle air circulation control method steps described above are implemented.

[0033] Furthermore, to achieve the above objectives, the present invention also proposes an in-vehicle air circulation control device, the in-vehicle air circulation control device comprising:

[0034] The coordinate detection module is used to collect facial images of passengers inside the vehicle and determine facial coordinate information based on the facial images of passengers inside the vehicle.

[0035] The gas detection module is used to determine the target vent based on the face coordinate information and the preset vent location, and to obtain the gas concentration inside the vehicle through the target vent.

[0036] An air circulation module is used to control the air circulation inside the vehicle based on the in-vehicle gas concentration and a preset gas concentration.

[0037] This invention acquires facial images of passengers inside a vehicle and determines facial coordinates based on these images. It then determines a target vent based on the facial coordinates and a preset vent location, and obtains the in-vehicle gas concentration through the target vent. Finally, it controls in-vehicle gas circulation based on the in-vehicle gas concentration and a preset gas concentration. Compared to existing technologies where in-vehicle gas detection sensors have a small detection range and cannot accurately determine the gas information around a passenger's face, leading to inaccurate detection results and affecting user experience, this invention solves the problem of limited gas detection locations. By combining facial recognition technology to accurately locate passengers, it enables real-time gas detection at the passenger's facial position, achieving more precise concentration detection and improving user experience. Attached Figure Description

[0038] Figure 1 This is a schematic diagram of the in-vehicle gas circulation control device in the hardware operating environment involved in the embodiments of the present invention;

[0039] Figure 2 This is a flowchart illustrating the first embodiment of the in-vehicle gas circulation control method of the present invention;

[0040] Figure 3 This is a schematic diagram of the overall control framework of the first embodiment of the in-vehicle gas circulation control method of the present invention;

[0041] Figure 4 This is a flowchart illustrating the second embodiment of the in-vehicle gas circulation control method of the present invention;

[0042] Figure 5 This is a schematic diagram of the eye corner positioning process in the second embodiment of the in-vehicle gas circulation control method of the present invention;

[0043] Figure 6 This is a structural block diagram of the first embodiment of the in-vehicle gas circulation control device of the present invention.

[0044] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0045] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0046] Reference Figure 1 , Figure 1 This is a schematic diagram of the in-vehicle gas circulation control device structure in the hardware operating environment of the embodiment of the present invention.

[0047] like Figure 1As shown, the in-vehicle air circulation control device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen, and optionally, it may also include a standard wired interface or a wireless interface. In this invention, the wired interface of the user interface 1003 may be a USB interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (RAM) or a non-volatile memory (NVM), such as a disk storage device. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0048] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the in-vehicle air circulation control device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0049] like Figure 1 As shown, the memory 1005, which is identified as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an in-vehicle air circulation control program.

[0050] exist Figure 1 In the in-vehicle air circulation control device shown, the network interface 1004 is mainly used to connect to the backend server and communicate data with the backend server; the user interface 1003 is mainly used to connect to the user equipment; the in-vehicle air circulation control device calls the in-vehicle air circulation control program stored in the memory 1005 through the processor 1001 and executes the in-vehicle air circulation control method provided in this embodiment of the invention.

[0051] Based on the above hardware structure, an embodiment of the in-vehicle gas circulation control method of the present invention is proposed.

[0052] Reference Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the in-vehicle gas circulation control method of the present invention, which presents the first embodiment of the in-vehicle gas circulation control method of the present invention.

[0053] In this embodiment, the in-vehicle air circulation control method includes the following steps:

[0054] Step S10: Collect facial images of passengers inside the vehicle, and determine facial coordinate information based on the facial images of passengers inside the vehicle.

[0055] It should be noted that the executing entity in this embodiment can be a device including an in-vehicle air circulation control system, such as an on-board computer, or other devices that can achieve the same or similar functions. This embodiment does not limit this. The in-vehicle air circulation control system includes an in-vehicle air detection sensor, a venting pipe device with multiple vents, a camera for facial recognition and positioning, a central control system based on a microcontroller, an alarm module, and a window motor. In this embodiment and the following embodiments, the in-vehicle air circulation control system is used as an example to describe the in-vehicle air circulation control method of the present invention.

[0056] It should be understood that the vehicle may be equipped with a camera that can identify the occupants in real time. The camera may be a pre-set dual camera that captures facial images of passengers in the vehicle and determines the facial coordinate information based on the facial images of the passengers in the vehicle.

[0057] Understandably, by using dual cameras to capture facial images of passengers inside the vehicle, and then using a face localization method to synthesize the two-dimensional coordinates from the captured facial images into three-dimensional coordinates, the facial coordinate information is determined based on these three-dimensional coordinates. Using dual cameras for face localization, and synthesizing three-dimensional coordinates from two two-dimensional coordinates, results in more accurate localization. This device has a simple structure, is relatively easy to assemble, occupies little space, does not require excessive computer resources, and all cameras are centrally controlled, resulting in high system stability.

[0058] In practice, a set of dual face positioning cameras can be installed above the rearview mirror. The dual cameras can capture images of passengers inside the vehicle and capture images of their faces. The two two-dimensional coordinates of the face in the images of the two cameras can be combined into a three-dimensional coordinate to obtain the face coordinate information.

[0059] Step S20: Determine the target vent based on the face coordinate information and the preset vent location, and obtain the gas concentration inside the vehicle through the target vent.

[0060] It should be noted that in existing gas detection technologies, fixed detection devices require multiple probes to detect gases in various locations within the vehicle due to the lack of air circulation. While mobile gas detection devices allow for probe repositioning as needed, the limited space inside a vehicle makes probe movement inconvenient. The preset vent location can be a pre-defined gas transmission port for absorbing and detecting gases. This gas transmission port can be a venting pipe device fixed inside the vehicle, whose on / off state can be changed in real time. This venting pipe device can detect air quality at different locations as needed and is easy to operate. The venting pipe device is used to collect gas from inside the vehicle and transport it to the gas detection sensor. The gas detection sensor includes a detection probe, a venting duct installed inside the vehicle, and air inlets near the driver, passenger, and rear seats. A fan is installed at each air inlet to guide air into the venting duct, accelerating airflow and delivering the gas to the gas detection probe within the venting duct. The gas is then discharged outside the vehicle through the outlet. When the camera locates a face, it sends the face information to the central control system. The central control system then triggers the detection device to automatically open the air inlet closest to the face's coordinates. At this time, the fan operates to guide the surrounding gas into the ventilation duct. When the gas reaches the installation position of the monitoring probe, the detection probe is used to detect the gas concentration value.

[0061] Understandably, the target vent can refer to the ventilation device that is closest to the occupant's face in a straight line when performing gas detection. Based on the location of the face, the location of the air inlet closest to the face can be determined. Air can be blown into the ventilation duct by a fan, and the flowing gas can be detected, making the detection value more reliable. At the same time, it solves the problem that fixed gas detection sensors have a small detection range and cannot objectively represent the overall air quality inside the vehicle.

[0062] In practice, the vehicle is equipped with cameras for real-time occupant identification, a ventilation system that adjusts the opening and closing of vents based on the coordinates of captured faces, and gas sensors. An onboard battery powers the system, which uses a dual-camera facial localization method to detect passenger facial positions in real time. The sensors automatically determine the nearest air inlet based on the detected face positions, drawing in gas through the nearest target vent and delivering it to a fixed gas detection sensor for analysis, thus determining the in-vehicle gas concentration. This concentration can refer to VOC (volatile organic compound) concentrations and carbon dioxide concentrations, among others.

[0063] Step S30: Control the gas circulation inside the vehicle according to the gas concentration inside the vehicle and the preset gas concentration.

[0064] It should be noted that the preset gas concentration can be a pre-set concentration threshold for judging whether the actual gas concentration inside the vehicle exceeds the standard conditions. The concentration threshold can be set according to international standards or according to user habits. In this embodiment, no specific restrictions are placed on the concentration threshold.

[0065] It should be understood that by comparing the gas concentration inside the vehicle with the preset gas concentration, the system determines whether the gas concentration inside the vehicle needs to be adjusted based on the comparison results. When the gas concentration inside the vehicle needs to be adjusted, the system controls the gas circulation inside the vehicle.

[0066] Furthermore, step S30 also includes: when the gas concentration inside the vehicle is greater than a preset gas concentration, issuing an alarm based on the gas concentration inside the vehicle and automatically turning on the air conditioning external circulation; and automatically lowering the windows when the alarm duration exceeds a preset duration and the windows are not open.

[0067] For further explanation of this solution, please refer to the following documentation. Figure 3 The overall control framework diagram shown illustrates that if the detected VOC gas concentration exceeds the set value, the sensor module transmits the collected data to the central control system, triggering the alarm and display modules. The system then displays which gas is exceeding the limit on the screen, reminding passengers to open windows for ventilation or automatically activating the air conditioning's external circulation mode. If the concentration does not decrease over a prolonged period, the system automatically detects whether the windows are open; if not, it automatically lowers the windows.

[0068] This embodiment acquires images of passengers' faces inside the vehicle and determines their facial coordinates based on these images. It then determines a target vent based on the facial coordinates and a preset vent location, and obtains the in-vehicle gas concentration through the target vent. Finally, it controls the in-vehicle gas circulation based on the in-vehicle gas concentration and a preset gas concentration. Compared to existing technologies where in-vehicle gas detection sensors have a small detection range and cannot accurately determine the gas information around passengers' faces, leading to inaccurate detection results and affecting user experience, this embodiment solves the problem of limited gas detection locations. By combining facial recognition technology to accurately locate passengers, it can perform real-time gas detection on passengers' faces, achieving more accurate concentration detection and improving user experience.

[0069] Reference Figure 4 , Figure 4 This is a flowchart illustrating the second embodiment of the in-vehicle gas circulation control method of the present invention, based on the above. Figure 2 The first embodiment shown presents a second embodiment of the in-vehicle gas circulation control method of the present invention.

[0070] In this embodiment, step S10 includes:

[0071] Step S101: Acquire passenger facial images inside the vehicle based on preset dual cameras, and perform binarization processing on the passenger facial images inside the vehicle to obtain the processed binarized image.

[0072] It should be noted that, to avoid inaccurate image recognition due to lighting conditions, after acquiring the facial images of passengers inside the vehicle, the images are first binarized to obtain a binarized image. This binarization process can involve first converting the image to grayscale, then selecting appropriate thresholds for the 256 brightness levels to obtain a binarized image that still reflects the overall and local features of the image. The binarization method can be the OTSU method for image binarization segmentation.

[0073] Step S102: Extract gradient features from the binarized image and determine face coordinate information based on the gradient features of the binarized image.

[0074] It should be noted that gradient feature extraction is performed on the binarized image. The gradient features include the gradient features corresponding to the facial features and contour curves of the face. That is, the gradient features corresponding to the facial features and contour curves of the face are extracted from the binarized image, and the face coordinate information is determined based on the extracted gradient features.

[0075] In the specific implementation, gradient features are extracted from the binarized image, and the face position is located based on the extracted features. Then, the three-dimensional coordinate information corresponding to each part of the face is determined based on the location information.

[0076] Furthermore, step S102 further includes: extracting gradient features from the binarized image to obtain a first gradient feature in the horizontal direction and a second gradient feature in the vertical direction; and determining face coordinate information based on the first gradient feature and the second gradient feature.

[0077] It should be noted that, since the interior of the car is relatively dark, after the image is captured by the camera, it is necessary to first binarize the image. By observation, we can see that the facial features and contour curves have gradient features. By enhancing these gradient features in the horizontal and vertical directions, we can achieve facial feature enhancement. Then, through facial feature localization, the position of the corner of the eye is located.

[0078] Understandably, the first gradient feature in the horizontal direction could refer to features found based on the facial structure, such as the contour curves of the upper and lower eye sockets being two features distributed in an approximately horizontal direction, and the partial contour curve of the mouth area also being a feature distributed in an approximately horizontal direction. The second gradient feature in the vertical direction could refer to the boundary line between the pupil and the sclera, the approximately vertical contour curve of the face edge, and the features corresponding to the contour curve of the nose.

[0079] In practice, facial coordinate information is determined based on the features that the contour curves of the upper and lower eye sockets are two features distributed in an approximately horizontal direction, the features that the partial contour curves of the mouth area are distributed in an approximately horizontal direction, the boundary line between the pupil and the white of the eye, the approximately vertical contour curves of the face edge, and the features corresponding to the contour curves of the nose.

[0080] Furthermore, the step of determining face coordinate information based on the first gradient feature and the second gradient feature includes: performing data augmentation on the first gradient feature and generating a first face image based on the augmented first gradient feature; performing data augmentation on the second gradient feature and generating a second face image based on the augmented second gradient feature; and determining face coordinate information based on the first face image and the second face image.

[0081] It should be noted that using algorithms to enhance image features can highlight facial feature regions while minimizing noise, shadows, and other interfering factors, facilitating rapid location of facial features. Enhancing these gradient features horizontally and vertically achieves facial feature enhancement, resulting in an enhanced facial feature image. Based on this image, facial feature localization is performed, facilitating accurate acquisition of facial coordinate information later.

[0082] Understandably, by enhancing the gradient features in the horizontal direction and the gradient features in the vertical direction of the face, a first face image and a second face image with enhanced features are obtained. The first face image is the image obtained after enhancing the gradient in the horizontal direction, and the second face image is the image obtained after enhancing the gradient in the vertical direction.

[0083] In the specific implementation, (1) the gradient features in the horizontal direction of the face are enhanced. Based on the feature structure of the face, the contour curves of the upper and lower eye sockets are determined to be two lines distributed in an approximately horizontal direction. The partial contour curves of the mouth area are also distributed in an approximately horizontal direction. These line features can all be expressed on the horizontal gradient. Therefore, a convolutional template to enhance the horizontal gradient can be constructed to extract the features in the horizontal direction of the face. The convolutional template to enhance the horizontal gradient is shown below:

[0084]

[0085]

[0086] Let E(x,y) be the grayscale image of the face, then F1(x,y) is the image after enhancing the horizontal gradient, which can be calculated by F1(x,y) = E(x,y)*g1 + E(x,y)*g2.

[0087] (2) Enhance the vertical gradient features of the face. Observation reveals that vertical gradient features include: the boundary between the pupil and the sclera, the contour curve of the approximately vertical portion of the face edge, and the contour curve of the nose. The convolutional template for enhancing the vertical gradient is as follows:

[0088]

[0089]

[0090] The image F2(x,y) after enhancing the vertical gradient can be calculated using the formula F2(x,y)=E(x,y)*g3+E(x,y)*g4.

[0091] Further, the step of determining face coordinate information based on the first face image information and the second face image information includes: determining the vertical coordinate of the human eye based on the first face image and the second face image; determining the target human eye region based on the vertical coordinate of the human eye, and extracting the upper and lower eye socket contours from the target human eye region; determining the intersection point of the upper and lower eye sockets based on the upper and lower eye socket contours, and determining the target eye corner coordinates based on the intersection point of the upper and lower eye sockets; and determining face coordinate information based on the target eye corner coordinates.

[0092] It should be noted that, in order to accurately locate the three-dimensional coordinates of a face, the three-dimensional coordinates of a face can be easily determined by locating the coordinates of the corners of the eyes. This solution uses the corners of the eyes to determine the three-dimensional coordinates of a face compared to locating other facial areas because eye features are easy to distinguish during the binarization process and can be better identified than other organs. Therefore, this solution determines the three-dimensional coordinates of a face by locating the corners of the eyes.

[0093] It should be understood that, to further illustrate the main process of eye corner positioning in this solution, you can refer to... Figure 5 The diagram shows the eye corner localization process, in which the first face image and the second face image are obtained by using enhanced gradient template processing to determine the vertical coordinate of the human eye, and the target human eye region is located in the image based on the vertical coordinate of the human eye. The upper and lower eye socket contours are extracted from the target human eye using the maximum inter-class variance (OTSU) thresholding method, and the intersection of the upper and lower eye sockets is determined, thereby determining the target eye corner coordinates, and the face coordinate information is determined based on the target eye corner coordinates.

[0094] Further, the step of determining the vertical coordinate of the human eye based on the first face image information and the second face image information includes: performing binary segmentation on the first face image and the second face image based on the maximum inter-class variance thresholding method to obtain the segmented foreground image and background image; determining the eye edge contour region and pupil region based on the white gradient features in the foreground image and background image; and determining the vertical coordinate of the human eye based on the eye edge contour region and pupil region.

[0095] It should be noted that, from the perspective of horizontal gradient values, the target region to be extracted is the region with a high gradient value. Flat regions similar in color to skin are designated as the background region. The Otsu's maximum inter-class variance (OIS) thresholding method is used to perform binary segmentation on the F1(x,y) image. OIS is a binarization method unaffected by image brightness and contrast. It divides the image into two parts based on the image's grayscale characteristics: the foreground and the background, which have the largest inter-class variance. It has good segmentation results for images like human eye images, where the grayscale difference between the target region and the background region is significant. After binarization, the eye's edge contour and pupil, which have gradient characteristics, become white, while other parts become black. Searching for white pixels from the leftmost and rightmost parts of the binarized human eye region towards the center, the first white pixel encountered is the left and right outer corners of the eye. Searching for white pixels from the center towards both ends, the first white pixel encountered is the left and right inner corners of the eye.

[0096] This embodiment acquires passenger facial images from a preset dual-camera setup, binarizes these images to obtain a processed binarized image, extracts gradient features from the binarized image, and determines facial coordinates based on these features. A target vent is then determined based on the facial coordinates and a preset vent location, and the in-vehicle gas concentration is obtained through this target vent. In-vehicle gas circulation is controlled based on the in-vehicle gas concentration and a preset gas concentration. Compared to existing technologies where in-vehicle gas detection sensors have a small detection range and cannot accurately determine the gas information around the passenger's face, leading to inaccurate detection results and affecting user experience, this embodiment solves the problem of limited gas detection locations. By combining facial recognition technology to accurately locate the passenger's position, it enables real-time gas detection at the passenger's face location, achieving more precise concentration detection and improving user experience.

[0097] Furthermore, to achieve the above objectives, the present invention also proposes a storage medium storing an in-vehicle air circulation control program, wherein when the in-vehicle air circulation control program is executed by a processor, the in-vehicle air circulation control method steps described above are implemented.

[0098] Reference Figure 6 , Figure 6 This is a structural block diagram of the first embodiment of the in-vehicle gas circulation control device of the present invention.

[0099] like Figure 6 As shown, the in-vehicle gas circulation control device proposed in this embodiment of the invention includes:

[0100] The coordinate detection module 10 is used to collect facial images of passengers inside the vehicle and determine facial coordinate information based on the facial images of passengers inside the vehicle.

[0101] Gas detection module 20 is used to determine the target vent based on the face coordinate information and the preset vent location, and to obtain the gas concentration inside the vehicle through the target vent.

[0102] The air circulation module 30 is used to control the air circulation inside the vehicle based on the gas concentration inside the vehicle and the preset gas concentration.

[0103] This embodiment acquires images of passengers' faces inside the vehicle and determines their facial coordinates based on these images. It then determines a target vent based on the facial coordinates and a preset vent location, and obtains the in-vehicle gas concentration through the target vent. Finally, it controls the in-vehicle gas circulation based on the in-vehicle gas concentration and a preset gas concentration. Compared to existing technologies where in-vehicle gas detection sensors have a small detection range and cannot accurately determine the gas information around passengers' faces, leading to inaccurate detection results and affecting user experience, this embodiment solves the problem of limited gas detection locations. By combining facial recognition technology to accurately locate passengers, it can perform real-time gas detection on passengers' faces, achieving more accurate concentration detection and improving user experience.

[0104] Furthermore, the coordinate detection module 10 is also used to acquire passenger face images in the vehicle based on preset dual cameras, and to perform binarization processing on the passenger face images in the vehicle to obtain a processed binarized image; to extract gradient features from the binarized image, and to determine face coordinate information based on the gradient features of the binarized image.

[0105] Furthermore, the coordinate detection module 10 is also used to extract gradient features from the binarized image to obtain a first gradient feature in the horizontal direction and a second gradient feature in the vertical direction; and to determine face coordinate information based on the first gradient feature and the second gradient feature.

[0106] Furthermore, the coordinate detection module 10 is also used to perform data augmentation on the first gradient feature and generate a first face image based on the augmented first gradient feature; perform data augmentation on the second gradient feature and generate a second face image based on the augmented second gradient feature; and determine face coordinate information based on the first face image and the second face image.

[0107] Furthermore, the coordinate detection module 10 is also used to determine the vertical coordinate of the human eye based on the first face image and the second face image; determine the target human eye region based on the vertical coordinate of the human eye, and extract the upper and lower eye socket contours from the target human eye region; determine the intersection of the upper and lower eye sockets based on the upper and lower eye socket contours, and determine the target eye corner coordinates based on the intersection of the upper and lower eye sockets; and determine the face coordinate information based on the target eye corner coordinates.

[0108] Furthermore, the coordinate detection module 10 is also used to perform binary segmentation on the first face image and the second face image based on the maximum inter-class variance thresholding method to obtain the segmented foreground image and background image; determine the eye edge contour region and pupil region based on the white gradient features in the foreground image and background image; and determine the vertical coordinate of the human eye based on the eye edge contour region and pupil region.

[0109] Furthermore, the air circulation module 30 is also used to issue an alarm based on the in-vehicle gas concentration when the in-vehicle gas concentration is greater than a preset gas concentration, and to automatically turn on the air conditioning external circulation; and to automatically lower the windows when the alarm duration exceeds a preset duration and the windows are not open.

[0110] It should be understood that the above are merely illustrative examples and do not constitute any limitation on the technical solutions of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any restrictions on this.

[0111] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this invention. In practical applications, those skilled in the art can select some or all of the workflow to achieve the purpose of this embodiment according to actual needs, and no restrictions are imposed here.

[0112] In addition, for technical details not described in detail in this embodiment, please refer to the in-vehicle gas circulation control method provided in any embodiment of the present invention, which will not be repeated here.

[0113] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0114] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments. In the unit claims listing several devices, several of these devices may be embodied by the same hardware item. The use of the terms first, second, and third, etc., does not indicate any order and can be interpreted as names.

[0115] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as a read-only memory image (ROM) / random access memory (RAM), magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0116] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for controlling in-vehicle air circulation, characterized in that, The in-vehicle air circulation control includes the following steps: Collect facial images of passengers inside the vehicle, and determine facial coordinate information based on the facial images of passengers inside the vehicle; The target vent is determined based on the facial coordinate information and the preset vent location, and the in-vehicle gas concentration is obtained through the target vent. The preset vent is a pre-set gas transmission port for absorbing gas for detection. The gas transmission port is a ventilation pipe device fixed in the vehicle that changes the on / off state of the vent in real time. The ventilation pipe device detects the air quality at different locations as needed and transports the collected in-vehicle gas to the gas detection sensor. The target vent is the ventilation device that is closest to the occupant's face in a straight line when performing gas detection. The vehicle interior gas circulation is controlled based on the in-vehicle gas concentration and the preset gas concentration. The step of acquiring facial images of passengers inside the vehicle and determining facial coordinate information based on the facial images of passengers inside the vehicle includes: The system captures facial images of passengers inside the vehicle using a preset dual-camera setup, and then binarizes these images to obtain a processed binarized image. Gradient feature extraction is performed on the binarized image to obtain the first gradient feature in the horizontal direction and the second gradient feature in the vertical direction; The first gradient feature is augmented with data, and a first face image is generated based on the augmented first gradient feature; The second gradient feature is augmented with data, and a second face image is generated based on the augmented second gradient feature; Binary segmentation of the first and second face images is performed based on the maximum inter-class variance thresholding method to obtain the segmented foreground and background images; The eye edge contour region and pupil region are determined based on the white gradient features in the foreground and background images; The vertical coordinates of the human eye are determined based on the eye edge contour region and the pupil region; The target eye region is determined based on the vertical coordinate of the human eye, and the upper and lower eye socket contours are extracted from the target eye region. The intersection of the upper and lower eye sockets is determined based on the upper and lower eye socket contours, and the coordinates of the target eye corner are determined based on the intersection of the upper and lower eye sockets. The facial coordinate information is determined based on the target eye corner coordinates.

2. The in-vehicle air circulation control method as described in claim 1, characterized in that, The step of controlling the in-vehicle gas circulation based on the in-vehicle gas concentration and the preset gas concentration includes: When the gas concentration inside the vehicle exceeds the preset gas concentration, an alarm is triggered based on the gas concentration inside the vehicle, and the air conditioning is automatically turned on to circulate the external air. If the alarm duration exceeds the preset time and the car window is not open, the car window will automatically lower.

3. A vehicle interior gas circulation control device, characterized in that, The in-vehicle air circulation control device includes: a memory, a processor, and an in-vehicle air circulation control program stored in the memory and executable on the processor. When the in-vehicle air circulation control program is executed by the processor, it implements the in-vehicle air circulation control method as described in any one of claims 1 or 2.

4. A storage medium, characterized in that, The storage medium stores an in-vehicle air circulation control program, which, when executed by a processor, implements the in-vehicle air circulation control method as described in any one of claims 1 or 2.

5. A vehicle interior air circulation control device, characterized in that, The in-vehicle gas circulation control device includes: The coordinate detection module is used to collect facial images of passengers inside the vehicle and determine facial coordinate information based on the facial images of passengers inside the vehicle. The gas detection module is used to determine the target vent based on the face coordinate information and the preset vent location, and to obtain the gas concentration inside the vehicle through the target vent. The preset vent is a pre-set gas transmission port for absorbing gas for detection. The gas transmission port is a ventilation pipe device fixed inside the vehicle that changes the on / off state of the vent in real time. The ventilation pipe device detects the air quality at different locations as needed and transports the collected gas inside the vehicle to the gas detection sensor. The target vent is the ventilation device that is closest to the occupant's face in a straight line when performing gas detection. An air circulation module is used to control the air circulation inside the vehicle based on the in-vehicle gas concentration and a preset gas concentration. The step of acquiring facial images of passengers inside the vehicle and determining facial coordinate information based on the facial images of passengers inside the vehicle includes: The system captures facial images of passengers inside the vehicle using a preset dual-camera setup, and then binarizes these images to obtain a processed binarized image. Gradient feature extraction is performed on the binarized image to obtain the first gradient feature in the horizontal direction and the second gradient feature in the vertical direction; The first gradient feature is augmented with data, and a first face image is generated based on the augmented first gradient feature; The second gradient feature is augmented with data, and a second face image is generated based on the augmented second gradient feature; Binary segmentation of the first and second face images is performed based on the maximum inter-class variance thresholding method to obtain the segmented foreground and background images; The eye edge contour region and pupil region are determined based on the white gradient features in the foreground and background images; The vertical coordinates of the human eye are determined based on the eye edge contour region and the pupil region; The target eye region is determined based on the vertical coordinate of the human eye, and the upper and lower eye socket contours are extracted from the target eye region. The intersection of the upper and lower eye sockets is determined based on the upper and lower eye socket contours, and the coordinates of the target eye corner are determined based on the intersection of the upper and lower eye sockets. The facial coordinate information is determined based on the target eye corner coordinates.

Images