Driving style switching method based on facial recognition and apparatus

Abstract

The present application discloses a driving style switching method based on facial recognition and an apparatus. The method comprises: recognizing facial expressions of a passenger in a vehicle (S101); according to preset requirements, performing slicing on the basis of the recognized facial expressions, and taking, within each clip, the facial expression lasting for the longest time as a processing result (S102); constructing a facial expression scoring mechanism, and calculating a score value of the processing result (S103); and presetting a driving style switching value, comparing the score value with the switching value, and using the comparison result to determine whether to switch the current driving style (S104).

Description

A method and device for switching driving styles based on facial recognition

[0001] This application claims priority to Chinese Patent Application No. 202510111217.8, filed on January 23, 2025, entitled “Driving Style Switching Method, Vehicle and Related Device Based on Facial Recognition”, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application belongs to the field of vehicle driving technology, specifically relating to a driving style switching method and device based on facial recognition. Background Technology

[0003] With the continuous development of technology, vehicle control and passenger experience have become key technological focuses for automakers to enhance their brand competitiveness. In the classification of vehicles, based on the current pace of technological development, vehicles can be divided into two main categories: autonomous vehicles and non-autonomous vehicles. Summary of the Invention

[0004] This application provides a method and apparatus for switching driving styles based on facial recognition. The technical solution adopted in this application is as follows:

[0005] In a first aspect, embodiments of this application provide a driving style switching method based on facial recognition, the method comprising:

[0006] The identified facial expression data is sliced, and the facial expression with the longest time percentage in each slice is taken as the processing result.

[0007] The score value of the processing result is calculated based on the facial expression scoring mechanism;

[0008] The score value is compared with the preset driving style switching value to determine whether to switch the current driving style.

[0009] In some embodiments, multiple facial expression recognition devices are installed inside the vehicle. These devices are connected to the vehicle's infotainment system. When passengers are in the vehicle, the devices acquire data on the number of passengers and their facial expressions. The process of recognizing the facial expressions of the passengers to obtain the recognized facial expression data includes:

[0010] Acquire facial expression data of all passengers inside the vehicle from the multiple facial expression recognition devices within a preset time period of vehicle operation;

[0011] A facial expression recognition algorithm is used to identify the facial expression data of all passengers in the vehicle, thereby obtaining the identified facial expression data.

[0012] In some embodiments, slicing the identified facial expression data includes:

[0013] The identified facial expression data is processed to remove valid facial expression data. The removal process refers to removing the facial expression data of passengers when they are not observing the vehicle's driving behavior. The facial expressions when they are not observing the vehicle's driving behavior include looking down, talking, and looking at electronic devices.

[0014] The valid facial expression data is sliced ​​according to a preset time interval to obtain multiple slice segments, wherein each slice segment includes facial expression data of at least one passenger, and each passenger corresponds to multiple slice segments.

[0015] In some embodiments, the facial expression scoring mechanism includes a correspondence between facial expressions and score values, and calculating the score value of the processing result based on the facial expression scoring mechanism includes:

[0016] The facial expression scoring mechanism and the number of passengers in the vehicle from the multiple facial expression recognition devices are obtained to determine the processing results of multiple slice segments corresponding to each passenger.

[0017] For each passenger, the processing results of multiple slices corresponding to the passenger are summed and then divided by the number of slices to obtain the average score of the passenger's expression;

[0018] The total score is obtained by summing the average scores of all passengers' facial expressions and then dividing by the number of passengers in the vehicle.

[0019] The total score is used as the score value of the processing result.

[0020] In some embodiments, comparing the score value with a preset driving style switching value to determine whether to switch the current driving style includes:

[0021] If the score value is less than the preset driving style switching value, the current driving style will be switched.

[0022] If the score value is greater than or equal to the preset driving style switching value, the current driving style is maintained.

[0023] In some embodiments, the method further includes:

[0024] When the vehicle is turned off, obtain passenger ratings for the vehicle's driving style;

[0025] Based on the score, update the preset driving style switching value.

[0026] Secondly, embodiments of this application provide a driving style switching device based on facial recognition, the device comprising:

[0027] The recognition module is used to recognize the facial expressions of passengers inside the vehicle and obtain the recognized facial expression data.

[0028] The slicing module is used to slice the identified facial expression data and take the facial expression with the longest time percentage in each slice as the processing result.

[0029] The calculation module is used to calculate the score value of the processing result based on the facial expression scoring mechanism;

[0030] The comparison module is used to compare the score value with the preset driving style switching value to determine whether to switch the current driving style.

[0031] Thirdly, embodiments of this application provide a vehicle infotainment system, which includes a memory and a processor. The memory stores a computer program that can run on the processor. The computer program is loaded and run by the processor to implement the driving style switching method based on facial recognition as described in the first aspect above.

[0032] Fourthly, embodiments of this application provide a non-transitory computer-readable storage medium storing a computer program that, when executed by a processor, implements the facial recognition-based driving style switching method described in the first aspect above.

[0033] Fifthly, embodiments of this application provide a computer program product, including computer instructions that instruct a processor to execute the facial recognition-based driving style switching method as described in the first aspect above.

[0034] Compared with the prior art, this application has at least the following beneficial effects:

[0035] By recognizing passengers' facial expressions in real time, the system can capture changes in passengers' emotions, thereby automatically switching the vehicle's driving style in a timely manner to improve the passenger experience and increase passenger satisfaction. At the same time, this method combines facial recognition technology with driving style switching to achieve intelligent driving assistance functions, which not only improves the degree of automation of driving but also enhances the intelligence level of the driving system. Attached Figure Description

[0036] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 is a schematic diagram of an implementation scenario of a driving style switching method based on facial recognition provided in this application;

[0038] Figure 2 is a schematic diagram of an implementation scenario for another driving style switching method based on facial recognition provided in this application;

[0039] Figure 3 is a flowchart of a driving style switching method based on facial recognition provided in this application;

[0040] Figure 4 is a structural block diagram of a driving style switching device based on facial recognition provided in this application.

[0041] The reference numerals in the attached diagrams are: 1. Vehicle interior; 2. Facial expression recognition device; 3. Passenger. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0043] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0044] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0045] In the description of the embodiments of this application, it should be noted that if terms such as "upper," "lower," "horizontal," or "inner" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of the invention is in use, they are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on this application. In addition, terms such as "first" and "second" are only used to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0046] Furthermore, the use of the term "horizontal" does not imply that the component must be absolutely horizontal, but rather that it can be slightly tilted. For example, "horizontal" simply means that its direction is more horizontal than "vertical," and does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0047] In the description of the embodiments of this application, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0048] Currently, the passenger experience in both autonomous and non-autonomous vehicles depends on vehicle control. In autonomous vehicles, driving style is primarily controlled through the in-vehicle infotainment system. However, current systems mainly focus on navigation and entertainment features, lacking the technology to adjust driving styles based on passenger facial expressions, thus failing to meet passenger expectations. Similarly, in non-autonomous vehicles, passenger experience depends more on the driver's mood than the passenger's needs. Consequently, neither autonomous nor non-autonomous vehicles adequately meet passenger needs and driving experience requirements.

[0049] To address the aforementioned technical issues, this application provides a driving style switching method based on facial recognition, which can automatically switch driving styles based on passengers' facial expressions, thereby improving the passenger's driving experience.

[0050] Before describing the driving style switching method based on facial recognition provided in the embodiments of this application, the implementation environment of the method will be described first:

[0051] Referring to Figures 1 and 2, this method is applied to the vehicle's infotainment system (not shown) or onboard controller. It is understood that, similar to the onboard controller, the infotainment system has a controller that can receive, process, and output data. Simultaneously, multiple facial expression recognition devices 2 are installed inside the vehicle 1, and these devices are connected to the infotainment system. These facial expression recognition devices are used to acquire data on the number of passengers 3 in the vehicle and the facial expression data of all passengers 3 when passengers 3 are in the vehicle. Using the facial expression recognition devices 3, the facial expressions of the passengers 3 in the vehicle can be accurately identified, thereby determining their emotional state and adjusting the driving style accordingly to improve the passenger experience.

[0052] In some embodiments, the facial expression recognition device 2 is positioned inside the vehicle 1 opposite to the seats. When passengers 3 board the vehicle, the facial expression recognition device 2 can identify the number of passengers 3 inside the vehicle 1 and the facial expressions of all passengers 3. The identified facial expressions include neutral, happy, sad, surprised, afraid, disgusted, angry, and contemptuous.

[0053] In one possible implementation, referring to Figures 1 and 2, there are three facial expression recognition devices 2. One facial expression recognition device 2 is located on the center console inside the vehicle 1, and the other two facial expression recognition devices 2 are installed on the back of the front seats and perpendicular to the seat axis. The recognition ends of the three facial expression recognition devices 2 face the seats and are able to recognize the facial expressions of the passengers 3 in the seats.

[0054] In another possible implementation, the number of facial recognition devices 2 is three or more (not shown in the figure). Since the seating posture of passenger 3 is variable, passenger 3's face cannot always be facing the recognition end of facial expression recognition device 2, thus the number of facial recognition devices 2 can be increased. For example, one seat is matched with three facial expression recognition devices 2. Specifically, one facial expression recognition device 2 is installed on the center console directly opposite the front passenger seat, thus capturing the passenger's facial features from the optimal angle and improving the accuracy of facial expression recognition; one facial expression recognition device 2 is installed on each side opposite the front passenger seat, at height to the sides of passenger 3's head. In this way, regardless of whether passenger 3's face is directly facing the facial expression recognition device 2 on the center console, or turned left or right, the facial expression recognition device 2 facing one side of the seat can collect and recognize passenger 3's facial expressions. Similarly, for the two rear seats in vehicle 1, each seat is equipped with three facial expression recognition devices. Two facial expression recognition devices 2 are installed on the back of the two front seats, two more are installed along the edges of the left and right window frames of the rear seats in vehicle 1, and the last two are installed between the two rear seats, with one recognition end facing left and the other facing right. In this way, facial expression information can be collected and recognized regardless of whether the head of the passenger 3 in the two rear seats is facing the front seats or turned to the left or right. It is worth noting that the facial expression recognition devices 2 installed along the edges of the left and right window frames are located inside vehicle 1, not on the windows, and are not affected by the raising or lowering of the windows.

[0055] In practical applications, the facial expression recognition device 2 can be one or more of a camera, a visual sensor, an infrared sensor, or a biosensor. When the facial expression recognition device 2 is a camera, head tracking timing can be used to collect and recognize the facial expression information of the passenger 3 in real time. When the facial expression recognition device 2 is a visual sensor, it can capture and analyze subtle changes in facial expressions, thereby more accurately identifying a person's emotional state. When the facial expression recognition device 2 is an infrared sensor, it can monitor unique human characteristics by emitting and receiving infrared light in low light conditions or at night. When the facial expression recognition device 2 is a biosensor, it can detect user expressions through subtle facial and eye movements, capturing facial dynamics in real time without a camera, and can even recognize individuals wearing masks. When multiple different types of facial expression recognition devices are used in combination, they work together to accurately identify passengers' facial expressions in specific recognition environments, improving the precision and accuracy of facial expression recognition.

[0056] In some embodiments, the vehicle infotainment system stores a facial expression recognition algorithm, which can recognize the facial expressions of passengers in the vehicle after acquiring data from the facial expression recognition device 2, thereby obtaining recognized facial expression data. This facial expression recognition algorithm is trained on an existing dataset and can be used for facial expression recognition. The existing dataset is an open-source dataset, such as the AffectNet dataset; the facial expression recognition algorithm can be an SVM-based algorithm.

[0057] Based on the above implementation environment, the driving style switching method based on facial recognition provided in this application embodiment will be described below. This method is applied to a vehicle infotainment system or vehicle controller, as shown in Figure 3, and includes:

[0058] S101. Recognize the facial expressions of passengers inside the vehicle to obtain the recognized facial expression data.

[0059] By acquiring data from a facial expression recognition device and using a facial expression recognition algorithm, the facial expressions of passengers inside the vehicle are identified, and the identified facial expression data is obtained, which facilitates the data preparation for subsequent determination of whether to switch the current driving style.

[0060] For example, when the facial expression recognition device is a camera, the data from the facial expression recognition device can be video data, and correspondingly, the recognized facial expression data is also video data.

[0061] In some embodiments, this step specifically includes: acquiring facial expression data of all passengers in the vehicle from multiple facial expression recognition devices within a preset time period of vehicle driving; and using a facial expression recognition algorithm to identify the facial expression data of all passengers in the vehicle to obtain the identified facial expression data.

[0062] For example, the preset driving time for a vehicle can be five minutes.

[0063] The system can recognize the facial expressions of all passengers within five minutes of the vehicle's journey, ensuring that a large amount of effective facial expression data can be obtained in a short time, providing a solid foundation for subsequent analysis and processing.

[0064] S102. The identified facial expression data is sliced, and the facial expression with the longest time percentage in each slice is taken as the processing result.

[0065] By slicing the identified facial expression data, further comparison can be made based on the slice fragments to determine whether to switch the current driving style.

[0066] It is understandable that human facial expressions are dynamic and change. By slicing the data, we can capture the changing characteristics of facial expressions in a short period of time. Using the facial expression with the longest duration as the processing result helps to reduce misjudgments caused by short-term changes in facial expressions and improves the accuracy of data processing.

[0067] In some embodiments, this step specifically includes: removing the identified facial expression data to obtain valid facial expression data. The removal process refers to removing the facial expression data of passengers when they are not observing the vehicle's driving behavior. Facial expressions when not observing the vehicle's driving behavior include looking down, talking, and looking at electronic devices. The valid facial expression data is sliced ​​at preset time intervals to obtain multiple slice segments, wherein each slice segment includes facial expression data of at least one passenger, and each passenger corresponds to multiple slice segments.

[0068] By eliminating facial expressions that are not related to observing vehicle performance, such as passengers looking down, talking, or looking at electronic devices, we can focus on facial expressions that are directly related to driving safety and passenger emotions, thereby improving the accuracy and relevance of the data.

[0069] For example, the preset time interval can be five seconds.

[0070] For example, for the identified facial expression data, expressions such as passengers looking down, talking, and looking at electronic devices, which are not related to observing the vehicle's movement, are removed from the data. The removed facial expression data is then considered valid facial expression data. When someone boards the vehicle, the facial expression recognition device can identify the number of passengers within a required time and record the expressions of all passengers over a period of time. In this embodiment, the valid facial expression data with durations of 210s and 180s can be sliced. With a preset time interval of five seconds, the valid facial expression data is sliced ​​to obtain multiple slice segments.

[0071] After obtaining multiple video segments, the facial expression with the longest duration within each segment is taken as the processing result. It can be understood that the processing result corresponds to the facial expression recognition results of passengers inside the vehicle; that is, the processing result belongs to one of the recognized facial expressions, specifically a neutral, happy, sad, surprised, fearful, disgusted, angry, or contemptuous expression.

[0072] S103. Calculate the score value of the processing result based on the facial expression scoring mechanism.

[0073] In this embodiment, a facial expression scoring mechanism is used as input, which includes the correspondence between facial expressions and score values. Based on this input, the facial expression scoring mechanism calculates the processing result to obtain a score value, which prepares data for subsequent determination of whether to switch the current driving style.

[0074] In some embodiments, this step specifically includes: acquiring facial expression scoring mechanism and passenger number data from multiple facial expression recognition devices, determining the processing results of multiple slice segments corresponding to each passenger; for each passenger, summing the processing results of the multiple slice segments corresponding to the passenger and dividing by the number of slices to obtain the passenger's average expression score; summing the average expression scores of all passengers in the vehicle and dividing by the number of passengers in the vehicle to obtain the total score; and using the total score as the score value of the processing result.

[0075] Based on a facial expression scoring mechanism, a quantitative assessment of facial expressions is achieved, making the assessment results more objective and accurate, and reducing errors caused by subjective judgment. The average facial expression score of each passenger, as well as the total score of all passengers in the vehicle, are calculated, taking into account time factors and individual passenger differences, making the assessment results more comprehensive and reliable.

[0076] For example, the correspondence between facial expressions and scores can be as follows: For neutral, happy, sad, surprised, afraid, disgusted, angry, and contemptuous facial expressions, the corresponding scores are 10, 8, 7, 5, 4, 3, 2, and 1 points respectively. For each passenger in the vehicle, the average score is obtained by summing the values ​​of the corresponding expressions from the processing results of multiple video clips and dividing by the number of clips. For example, passenger A's total score from the processing results of multiple video clips is 189 points, which, divided by the total number of clips (42), gives passenger A's average score of 4.5 points. The average scores of all passengers in the vehicle are summed and divided by the number of passengers to obtain the total score. This total score is used as the score value of the processing result. For example, if there are two passengers in the vehicle with average scores of 4.5 and 5.8 points respectively, their scores are summed and then divided by the number of passengers (i.e., divided by 2) to obtain the final score of 5.15 for all passengers in the vehicle.

[0077] S104. Compare the score value with the preset driving style switching value to determine whether to switch the current driving style.

[0078] In this embodiment of the application, the preset driving style switching value can be a value preset by the user in the vehicle system. For example, the preset driving style switching value can be 6.

[0079] In some embodiments, this step specifically includes: switching the current driving style when the score value is less than the preset driving style switching value; and maintaining the current driving style when the score value is greater than or equal to the preset driving style switching value.

[0080] For example, the final score of 5.15 in step S103 is used for judgment. Since 5.15 is less than 6, it means that all passengers in the car are not satisfied with the current driving style of the vehicle, and the vehicle needs to switch the current driving style.

[0081] In some embodiments, the vehicle's driving style includes three modes: conservative, normal, and aggressive. When all passengers in the vehicle are dissatisfied with the current driving style and the vehicle needs to switch driving styles, the driving style can be switched from one mode to another, for example, from conservative to normal.

[0082] In some embodiments, after switching the vehicle's driving style, the facial expressions of all passengers in the vehicle can be recognized, and steps S101 to S104 can be repeated. This allows for rapid capture of passengers' immediate reactions to the new driving style, and such immediate feedback helps in timely adjustments to better meet passengers' needs and expectations. If it is determined that the current vehicle driving style should be maintained, steps S101 to S104 are repeated every fifteen minutes.

[0083] In some embodiments, the facial recognition-based driving style switching method provided in this application can obtain a passenger's rating of the vehicle's driving style when the vehicle is turned off, and update the preset driving style switching value based on the rating, thereby achieving self-optimization of the switching method, making it more accurate in recognizing the passenger's emotional state, and thus more precisely adjusting the driving style.

[0084] In summary, by recognizing passengers' facial expressions in real time, it is possible to capture changes in their emotions, thereby automatically switching the vehicle's driving style to improve passenger experience and satisfaction. Furthermore, this method combines facial recognition technology with driving style switching to achieve intelligent driving assistance functions, not only increasing the level of automation in driving but also enhancing the overall intelligence of the driving system.

[0085] Secondly, this application also provides a vehicle, including an in-vehicle infotainment system, which uses the facial recognition-based driving style switching method described in the above embodiments to switch the vehicle's driving style.

[0086] In some embodiments, the vehicle may be an autonomous vehicle or a non-autonomous vehicle. An autonomous vehicle may be a driverless taxi or driverless bus in commercial operation mode, or a private car in non-commercial operation mode.

[0087] Because the driving style switching method based on facial recognition, as described in the above embodiments, is adopted, the driving style of the vehicle can be switched automatically and in a timely manner, thereby improving the passenger riding experience and enhancing passenger satisfaction.

[0088] Thirdly, this application embodiment also provides a driving style switching device based on facial recognition, as shown in FIG4. The driving style switching device 400 based on facial recognition includes: a recognition module 401, a slicing module 402, a calculation module 403, and a comparison module 404.

[0089] The recognition module 401 is used to recognize the facial expressions of passengers in the vehicle and obtain the recognized facial expression data.

[0090] The slicing module 402 is used to slice the identified facial expression data and take the facial expression with the longest time proportion in each slice as the processing result.

[0091] The calculation module 403 is used to calculate the score value of the processing result based on the facial expression scoring mechanism.

[0092] The comparison module 404 is used to compare the score value with the preset driving style switching value to determine whether to switch the current driving style.

[0093] In some embodiments, the identification module 401 includes:

[0094] The acquisition unit is used to acquire facial expression data of all passengers in the vehicle from multiple facial expression recognition devices within a preset time period of vehicle operation.

[0095] The recognition unit is used to identify the facial expression data of all passengers in the vehicle using a facial expression recognition algorithm, and obtain the identified facial expression data.

[0096] In some embodiments, the slicing module 402 includes:

[0097] The processing unit is used to remove the identified facial expression data to obtain valid facial expression data. The removal process refers to removing the facial expression data of passengers when they are not observing the vehicle's driving behavior. Facial expressions when not observing the vehicle's driving behavior include looking down, talking, and looking at electronic devices.

[0098] The slicing unit is used to slice the valid facial expression data according to a preset time interval to obtain multiple slice segments, wherein each slice segment includes facial expression data of at least one passenger, and each passenger has multiple slice segments.

[0099] In some embodiments, the facial expression scoring mechanism includes a correspondence between facial expressions and score values, and the calculation module 403 includes:

[0100] The acquisition unit is used to acquire data on the number of passengers in the vehicle from the facial expression scoring mechanism and multiple facial expression recognition devices, and to determine the processing results of multiple slice segments corresponding to each passenger.

[0101] The first calculation unit is used to sum the processing results of multiple slices corresponding to each passenger and divide them by the number of slices to obtain the average score of the passenger's expression.

[0102] The second calculation unit is used to sum the average scores of all passengers' facial expressions and then divide the sum by the number of passengers in the vehicle to obtain the total score.

[0103] The numerical value is used to obtain the score value as the processing result of the total score.

[0104] In some embodiments, the comparison module 404 includes:

[0105] The switching unit is used to switch the current driving style when the score value is less than the preset driving style switching value;

[0106] The hold unit is used to maintain the current driving style when the score value is greater than or equal to the preset driving style switching value.

[0107] In some embodiments, the facial recognition-based driving style switching device 400 further includes:

[0108] The acquisition unit is used to acquire passenger ratings of the vehicle's driving style when the vehicle is turned off.

[0109] An update unit is used to update the preset driving style switching value based on the score.

[0110] Therefore, the driving style switching device 400, which is based on facial recognition, can capture changes in passengers' emotions by recognizing their facial expressions in real time. This allows it to automatically switch the vehicle's driving style in a timely manner, thereby improving the passenger experience and increasing passenger satisfaction. Simultaneously, this method combines facial recognition technology with driving style switching to achieve intelligent driving assistance functions, not only improving the automation level of driving but also enhancing the intelligence level of the driving system.

[0111] Fourthly, embodiments of this application also provide an in-vehicle controller. The in-vehicle controller includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the facial recognition-based driving style switching method described above.

[0112] Fifthly, embodiments of this application also provide a non-transitory computer-readable storage medium. This non-transitory computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the facial recognition-based driving style switching method described above.

[0113] Sixthly, embodiments of this application also provide a computer program product. This computer program product includes computer instructions that instruct a computing device to perform operations corresponding to the facial recognition-based driving style switching method described above.

[0114] This application provides a method for switching driving styles based on facial recognition, the method including:

[0115] Recognize the facial expressions of passengers inside the vehicle;

[0116] According to preset requirements, the identified facial expressions are sliced, and the facial expression with the longest time percentage in the slice is taken as the processing result.

[0117] A facial expression scoring mechanism is constructed to calculate the score value of the processing result;

[0118] A preset driving style switching value is set, the score value is compared with the switching value, and the comparison result is used to determine whether to switch the current driving style.

[0119] In some embodiments, recognizing the facial expressions of passengers inside the vehicle specifically includes:

[0120] A facial expression recognition algorithm is trained based on the dataset.

[0121] Inside the vehicle, a certain number of facial expression recognition devices are installed, and the facial expression recognition algorithm is built into the facial expression recognition devices;

[0122] When passengers board the vehicle, the facial expression recognition device identifies the number of passengers in the vehicle and the facial expressions of all passengers.

[0123] In some embodiments, the facial expression recognition device is one of a camera, a visual sensor, an infrared sensor, or a biosensor.

[0124] In some embodiments, the facial expression recognition device is positioned inside the vehicle opposite the seats before facial expression recognition is performed on all passengers.

[0125] In some embodiments, the preset requirements specifically include:

[0126] Within five minutes of the vehicle's operation, the facial expressions of all passengers inside the vehicle can be identified.

[0127] The facial expressions of passengers that are not related to observing the vehicle's driving performance, such as looking down, talking, or looking at electronic devices, are removed from the facial expressions. The facial expressions after removal are used as the benchmark for constructing the facial expression scoring mechanism.

[0128] In some embodiments, the identified facial expressions are sliced, and the facial expression with the longest time percentage within the slice is taken as the processing result, specifically including:

[0129] The recognized facial expressions are sliced ​​in five-second increments, and the facial expression with the longest time percentage in the segment is used as the processing result.

[0130] The processing results are then compared with the facial expression recognition results of the passengers inside the vehicle.

[0131] In some embodiments, the construction of the facial expression scoring mechanism to calculate the score value of the processing result specifically includes:

[0132] The facial expressions of passengers inside the vehicle are assigned different scores based on different recognition results;

[0133] Calculate the total score of all valid segments for a passenger in the car, and divide it by the total number of segments to get the average score of the passenger's facial expressions over five minutes;

[0134] Calculate the average score of all passengers in the vehicle, sum the average scores and divide by the number of passengers in the vehicle to obtain the total score, and use the total score as the score value of the processing result.

[0135] In some embodiments, the facial recognition-based driving style switching method further includes:

[0136] If it is determined that the current driving style is to be switched, the facial expressions of the passengers in the vehicle are identified again after the current driving style is switched, and the score value is compared with the switching value through the constructed facial expression scoring mechanism.

[0137] In some embodiments, the facial recognition-based driving style switching method further includes:

[0138] At the end of the passenger's trip, the passenger is asked to rate the vehicle's driving style. Based on the rating, the facial expression recognition algorithm and the vehicle driving style switching method are iterated.

[0139] This application also provides a vehicle, including a vehicle body, wherein the vehicle body uses the facial recognition-based driving style switching method as described in the above embodiments to switch the vehicle driving style.

[0140] This application also provides a facial recognition-based driving style switching system, which includes:

[0141] A recognition module is used to recognize the facial expressions of passengers inside the vehicle;

[0142] The processing model is used to slice the recognized facial expressions;

[0143] Build modules for constructing facial expression scoring mechanisms;

[0144] The calculation module is used to score the results of technical processing.

[0145] The preset module is used to preset driving style switching values;

[0146] The comparison module is used to compare the score value with the switching value;

[0147] The judgment module is used to determine whether to switch the current driving style.

[0148] This application also provides a mobile terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the facial recognition-based driving style switching method described in the above embodiments.

[0149] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the facial recognition-based driving style switching method described in the above embodiments.

[0150] This application also provides a computer program product, including computer instructions that instruct a computing device to perform operations corresponding to the facial recognition-based driving style switching method described in the above embodiments.

[0151] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and not to limit its protection scope. Although this application has been described in detail with reference to the above embodiments, those skilled in the art should understand that after reading this application, they can still make various changes, modifications or equivalent substitutions to the specific implementation of the invention, but these changes, modifications or equivalent substitutions are all within the protection scope of the appended claims.

Claims

1. A method for switching driving styles based on facial recognition, the method comprising: The facial expressions of passengers inside the vehicle are recognized to obtain the recognized facial expression data; The identified facial expression data is sliced, and the facial expression with the longest time percentage in each slice is taken as the processing result. The score value of the processing result is calculated based on the facial expression scoring mechanism; The score value is compared with the preset driving style switching value to determine whether to switch the current driving style.

2. The driving style switching method based on facial recognition according to claim 1, wherein, Multiple facial expression recognition devices are installed inside the vehicle and connected to the vehicle's infotainment system. These devices are used to acquire data on the number of passengers in the vehicle and the facial expression data of all passengers when passengers are in the vehicle. The process of recognizing the facial expressions of the passengers to obtain the recognized facial expression data includes: Acquire facial expression data of all passengers inside the vehicle from the multiple facial expression recognition devices within a preset time period of vehicle operation; A facial expression recognition algorithm is used to identify the facial expression data of all passengers in the vehicle, thereby obtaining the identified facial expression data.

3. The driving style switching method based on facial recognition according to claim 2, wherein, The process of slicing the identified facial expression data includes: The identified facial expression data is processed to remove valid facial expression data. The removal process refers to removing the facial expression data of passengers when they are not observing the vehicle's driving behavior. The facial expressions when they are not observing the vehicle's driving behavior include looking down, talking, and looking at electronic devices. The valid facial expression data is sliced ​​according to a preset time interval to obtain multiple slice segments, wherein each slice segment includes facial expression data of at least one passenger, and each passenger corresponds to multiple slice segments.

4. The driving style switching method based on facial recognition according to claim 2, wherein, The facial expression scoring mechanism includes the correspondence between facial expressions and score values. The calculation of the score value of the processing result based on the facial expression scoring mechanism includes: The facial expression scoring mechanism and the number of passengers in the vehicle from the multiple facial expression recognition devices are obtained to determine the processing results of multiple slice segments corresponding to each passenger. For each passenger, the processing results of multiple slices corresponding to the passenger are summed and then divided by the number of slices to obtain the average score of the passenger's expression; The total score is obtained by summing the average scores of all passengers' facial expressions and then dividing by the number of passengers in the vehicle. The total score is used as the score value of the processing result.

5. The driving style switching method based on facial recognition according to claim 2, wherein, The step of comparing the score value with the preset driving style switching value to determine whether to switch the current driving style includes: If the score value is less than the preset driving style switching value, the current driving style will be switched. If the score value is greater than or equal to the preset driving style switching value, the current driving style is maintained.

6. The driving style switching method based on facial recognition according to claim 1, wherein, The method further includes: When the vehicle is turned off, obtain passenger ratings for the vehicle's driving style; Based on the score, update the preset driving style switching value.

7. A facial recognition-based driving style switching device, the device comprising: The recognition module is used to recognize the facial expressions of passengers inside the vehicle and obtain the recognized facial expression data. The slicing module is used to slice the identified facial expression data and take the facial expression with the longest time percentage in each slice as the processing result. The calculation module is used to calculate the score value of the processing result based on the facial expression scoring mechanism; The comparison module is used to compare the score value with the preset driving style switching value to determine whether to switch the current driving style.

8. An in-vehicle controller, the in-vehicle controller comprising a memory and a processor, the memory storing a computer program executable on the processor, the computer program being loaded and executed by the processor to implement the facial recognition-based driving style switching method as described in any one of claims 1-6.

9. A non-transitory computer-readable storage medium storing a computer program that, when executed by a processor, implements the facial recognition-based driving style switching method as described in any one of claims 1-6.

10. A computer program product comprising computer instructions, characterized in that, The computer instructions instruct the processor to execute the facial recognition-based driving style switching method as described in any one of claims 1-6.

Images