Methods of indicating driving intentions and helmets

Abstract

This application discloses a method and helmet for indicating driving intentions, belonging to the field of traffic technology. The method includes collecting the driver's electroencephalogram (EEG) signals using EEG electrodes and sending the EEG signals to a signal processing module. The signal processing module obtains the driver's driving intention indication information based on the EEG signals and a driving intention classification model. The driving intention indication information is used to indicate at least one driving intention: left turn, right turn, or braking. Based on the driving intention indication information, the signal processing module controls at least one indicator light to indicate the driving intention. Using this application can reduce road safety hazards caused by drivers forgetting to use their turn signals when turning.

Description

Technical Field

[0001] This application relates to the field of traffic technology, and in particular to a method for indicating driving intention and a helmet. Background Technology

[0002] Motorcycles, electric bicycles, and other portable modes of transportation are chosen by a large number of users because of their ease of riding and minimal impact from road congestion.

[0003] Currently, drivers often forget to use their turn signals when riding motorcycles, electric bicycles, and other vehicles on the road. As a result, following vehicles cannot promptly receive their driving intentions, such as turning or braking, which may lead to rear-end collisions and other safety accidents, posing a significant road safety hazard. Summary of the Invention

[0004] This application provides a method and helmet for indicating driving intention, which can reduce road safety hazards caused by drivers forgetting to use turn signals when turning. The technical solution is as follows:

[0005] In a first aspect, a method for indicating driving intention is provided, the method being applied to a helmet, the helmet including a helmet shell, electroencephalogram (EEG) electrodes, a power supply module, a signal processing module, and at least one indicator light, the EEG electrodes being disposed on the inner side of the helmet shell, the at least one indicator light being disposed on the rear outer surface of the helmet shell, the power supply module being used to supply power to the EEG electrodes, the signal processing module, and the at least one indicator light, the method comprising:

[0006] The EEG electrodes collect the driver's EEG signals and send the EEG signals to the signal processing module;

[0007] The signal processing module obtains the driver's driving intention indication information based on the EEG signal and the driving intention classification model, wherein the driving intention indication information is used to indicate at least one driving intention among left turn, right turn, and braking;

[0008] The signal processing module controls at least one indicator light to indicate driving intention based on the driving intention indication information.

[0009] In one possible implementation, the signal processing module obtains the driver's driving intention indication information based on the EEG signal and the driving intention classification model, including:

[0010] The signal processing module extracts the feature data of the EEG signal, inputs the feature data into the driving intention classification model, and obtains the driver's driving intention indication information.

[0011] In one possible implementation, the signal processing module extracts feature data from the electroencephalogram (EEG) signal, including:

[0012] The signal processing module filters the EEG signal to obtain a signal in the target frequency band;

[0013] The signal processing module performs principal component analysis on the signal in the target frequency band to obtain the signal amplitude as the proportion of the variance target as feature data.

[0014] In one possible implementation, the helmet further includes an accelerometer, and the signal processing module obtains the driver's driving intention indication information based on the EEG signals and the driving intention classification model, including:

[0015] The accelerometer collects acceleration data and sends the acceleration data to the signal processing module.

[0016] The signal processing module obtains the driver's driving intention indication information based on the electroencephalogram (EEG) signal, the acceleration data, and the driving intention classification model.

[0017] In one possible implementation, the helmet includes a left-turn indicator, a right-turn indicator, and a brake indicator. The signal processing module, based on the driving intention indication information, controls at least one indicator to indicate the driving intention, including:

[0018] If the driving intention indicated by the driving intention information is to turn left, the signal processing module controls the left turn indicator light to illuminate;

[0019] If the driving intention indicated by the driving intention information is to turn right, the signal processing module controls the right turn indicator light to illuminate.

[0020] If the driving intention indicated by the driving intention information is to brake, the signal processing module controls the brake indicator light to illuminate.

[0021] In a second aspect, a helmet is provided, which includes a helmet shell, EEG electrodes, a power supply module, a signal processing module, and at least one indicator light;

[0022] The EEG electrodes are disposed on the inner side of the helmet shell, and the at least one indicator light is disposed on the rear outer surface of the helmet shell. The power supply module is used to supply power to the EEG electrodes, the signal processing module, and the at least one indicator light. The method includes:

[0023] The EEG electrodes are used to collect the driver's EEG signals and send the EEG signals to the signal processing module.

[0024] The signal processing module is used to obtain the driver's driving intention indication information based on the electroencephalogram signal and the driving intention classification model, wherein the driving intention indication information is used to indicate at least one driving intention among left turn, right turn, and braking;

[0025] The signal processing module is used to control the at least one indicator light to indicate driving intention based on the driving intention indication information.

[0026] In one possible implementation, the signal processing module is used to extract feature data from the electroencephalogram (EEG) signal, input the feature data into a driving intention classification model, and obtain the driver's driving intention indication information.

[0027] In one possible implementation, the signal processing module is used to filter the EEG signal to obtain a signal in the target frequency band, and to perform principal component analysis on the signal in the target frequency band to obtain the amplitude of the signal that accounts for the target variance as feature data.

[0028] In one possible implementation, the helmet further includes an accelerometer, and the signal processing module obtains the driver's driving intention indication information based on the EEG signals and the driving intention classification model, including:

[0029] The accelerometer collects acceleration data and sends the acceleration data to the signal processing module.

[0030] The signal processing module obtains the driver's driving intention indication information based on the electroencephalogram (EEG) signal, the acceleration data, and the driving intention classification model.

[0031] In one possible implementation, the helmet further includes a left-turn indicator light, a right-turn indicator light, and a brake indicator light. The signal processing module is configured to control the left-turn indicator light to illuminate if the driving intention indicated by the driving intention information is to turn left; control the right-turn indicator light to illuminate if the driving intention indicated by the driving intention information is to turn right; and control the brake indicator light to illuminate if the driving intention indicated by the driving intention information is to brake.

[0032] The beneficial effects of the technical solutions provided in this application are:

[0033] In the technical solution provided in this application embodiment, an EEG electrode is installed inside the helmet, and a turn signal is installed at the back of the helmet. While the driver is riding with the helmet on, the EEG electrode collects the driver's brain signals. The signal processing module uses the brain signals and a driving intention classification model to determine the driver's current driving intention as a left turn, right turn, or brake. Then, it controls the turn signal to indicate the driver's driving intention. In this way, even if the driver forgets to use the vehicle's turn signal when turning, the helmet can still indicate the predicted driving intention through its own turn signal, thus reminding following vehicles and effectively reducing road safety hazards caused by drivers forgetting to use their turn signals. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 This is a schematic diagram of the structure of a helmet provided in an embodiment of this application;

[0036] Figure 2 This is a flowchart of a method for indicating driving intent provided in an embodiment of this application;

[0037] Figure 3 This is a schematic diagram of a method for determining driving intention indication information provided in an embodiment of this application;

[0038] Figure 4 This is a schematic diagram of a method for determining driving intention indication information provided in an embodiment of this application;

[0039] Figure 5 This is a schematic diagram of a method for determining driving intention indication information provided in an embodiment of this application;

[0040] Figure 6 This is a schematic diagram of a method for determining driving intention indication information provided in an embodiment of this application;

[0041] Figure 7 This is a schematic diagram of a method for determining driving intention indication information provided in an embodiment of this application. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0043] This application provides a method for indicating driving intention, which can be applied in scenarios where riding motorcycles, electric vehicles, bicycles, etc., requires wearing a helmet. The method is implemented by the helmet worn by the driver while riding.

[0044] See Figure 1 The diagram illustrates a structural schematic of a helmet for displaying driving intentions, as provided in an embodiment of this application. Figure 1 As shown, the helmet 100 includes a helmet shell 101 (not shown in the figure), EEG electrodes 102, a power supply module 103, a signal processing module 104, a left turn indicator light 105, a right turn indicator light 106, and a brake indicator light 107.

[0045] The helmet shell 101 can be made of ABS (Acrylonitrile Butadiene Styrene) material. In addition, a cushioning layer can be provided inside the helmet shell for shock absorption and cushioning. The cushioning layer can be sponge, elastic band, etc.

[0046] The EEG electrodes 102 can be installed on the inside of the helmet shell 101 according to relevant standards, so as to collect the driver's EEG signals when the driver wears the helmet 100. Relevant standards may include international standards 10-20, etc. These standards may require 19, 21, or more, or fewer EEG electrodes 102. In this embodiment, the number of EEG electrodes 102 is not limited, as long as it can accurately collect the driver's EEG signals.

[0047] The power supply module 103 can be a lithium battery, a solar cell, or the like. If the power supply module 103 is a solar cell, it can be located on the outside of the helmet shell 101 to absorb solar energy for charging. The power supply module 103 is connected to the EEG electrodes 102, the power supply module 103, the signal processing module 104, the left turn indicator 105, the right turn indicator 106, and the brake indicator 107 to provide power to these components.

[0048] The signal processing module 104 is connected to the EEG electrodes 102 to receive EEG signals transmitted by the EEG electrodes 102. The signal processing module 104 may include a processor, which may be implemented in at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). In some embodiments, the processor may also include an AI (Artificial Intelligence) processor for handling computational operations related to machine learning. Furthermore, the signal processing module 104 may also include a computer-readable storage medium, which may be non-transitory, such as ROM (Read-Only Memory), RAM (Random Access Memory), CD-ROM (Compact Disc Read-Only Memory), magnetic tape, floppy disk, and optical data storage devices.

[0049] In one possible implementation, the signal processing module 104, due to its need to perform neural network model calculations, may be relatively large. Therefore, it can be used as an external device of the helmet 100, housed in a backpack carried by the driver while riding. Alternatively, the signal processing module 104 can be mounted on the vehicle the driver is riding, eliminating the need for the driver to carry it and reducing their burden. In this implementation, two power supply modules 103 can be used. One power supply module 103 is located on the side of the helmet 100 and connected to the EEG electrodes 102, left turn indicator 105, right turn indicator 106, and brake indicator 107, providing power to these components. The other power supply module 103 is located on the side of the signal processing module 104 (e.g., in a backpack or mounted on the vehicle the driver is riding), connected to the signal processing module 104, and providing power to it. In this case, wired or wireless data transmission can occur between the signal processing module 104 and the EEG electrodes.

[0050] The left turn indicator 105, right turn indicator 106, and brake indicator 107 can all be LEDs (light-emitting diodes). These indicators can be positioned on the rear outer surface of the helmet shell 101, ideally with the illumination of the indicators clearly visible to drivers of vehicles behind. In one configuration, from the perspective of a driver in a rear vehicle, the three indicators can be positioned as follows: left turn indicator 105 on the far left, brake indicator 107 in the middle, and right turn indicator 106 on the far right.

[0051] In one possible implementation, the left turn indicator 105, right turn indicator 106, and brake indicator 107 can be replaced by a single indicator light. This indicator light can display different patterns depending on the driver's driving intention. For example, when the driving intention is to turn left, the indicator light can display an arrow pointing to the left; when the driving intention is to turn right, the indicator light can display an arrow pointing to the right; and when the driving intention is to brake, the indicator light can display a red circle, a red "×", or simultaneously display a flashing arrow pointing to the left and a flashing arrow pointing to the right. The specific display effect is not limited in this application embodiment, as long as it can inform the driver of the vehicle's current driving intention to the drivers of vehicles behind.

[0052] The method for indicating driving intent provided in the embodiments of this application will now be described with reference to the accompanying drawings. This method can be performed by... Figure 1 The helmet shown is implemented. See also Figure 2 The method may include the following processing steps:

[0053] Step 201: The EEG electrodes collect the driver's EEG signals and send the EEG signals to the signal processing module.

[0054] In practice, drivers must wear the aforementioned protective gear when riding motorcycles, electric bikes, bicycles, and other portable vehicles. Figure 1 The helmet shown has EEG electrodes installed inside to collect the driver's EEG signals in real time and send the collected EEG signals to the signal processing module.

[0055] Since the brain signals of a driver are different in different states such as normal straight driving, preparing to turn, and preparing to brake, the technical solution provided in this application can collect the driver's brain signals through brain electrodes set in the helmet, so as to analyze the driver's current driving intention through subsequent processing, thereby providing timely driving intention prompts to vehicles behind.

[0056] Step 202: The signal processing module obtains the driver's driving intention indication information based on the EEG signal and driving intention classification model.

[0057] The driving intention indication information is used to indicate at least one driving intention, such as turning left, turning right, or braking. The driving intention classification model can be an AI model such as a neural network model or a deep learning model.

[0058] In implementation, after receiving the EEG signals transmitted by the EEG electrodes, the signal processing module first extracts the feature data of the EEG signals. Then, based on the feature data and the driving intention classification model, it obtains the driver's driving intention instruction information. The following explains how the signal processing module extracts the feature data of the EEG signals:

[0059] The signal processing module amplifies, bandpass-filters, and denoises the EEG signal to obtain the signal in the target frequency band. This target frequency band can be the alpha and beta waves in the EEG signal, with alpha waves ranging from 8 Hz to 13 Hz and beta waves from 13 Hz to 30 Hz. Then, principal component analysis (PCA) is performed on the target frequency band signal to extract the signal representing a target proportion of the variance. The amplitude of this proportion is used as the feature data of the EEG signal. The target proportion can be configured by relevant personnel according to actual needs; for example, a target proportion of 95%.

[0060] This application provides several methods for obtaining driver intention indication information based on feature data and a driving intention classification model, which are described below:

[0061] Method 1:

[0062] The driving intention classification model is an AI model.

[0063] See Figure 3 In this first method, the signal processing module inputs the feature data of the EEG signal into the driving intention classification model, and the driving intention classification model outputs the driver's current driving intention indication information. For example, the driving intention indication information corresponding to a left turn is 00, the driving intention indication information corresponding to a right turn is 01, the driving intention corresponding to braking is 10, and normal driving is 11.

[0064] Alternatively, the signal processing module inputs the feature data of the EEG signal into the driving intention classification model. The driving intention classification model outputs the confidence level corresponding to each driving intention indication. Then, the driving intention indication with the highest confidence level is selected as the driver's current driving intention indication. Alternatively, driving intention indications with a confidence level higher than a threshold are selected as the driver's current driving intention indication.

[0065] For the driving intent classification model used in Method 1, it can be pre-trained using a sample set before use. The sample set includes input samples and output samples. The input samples can be feature data of EEG signals when a person is turning left, turning right, braking, or driving normally. The output samples are the ground truth values ​​of the corresponding driving intent indication information. For sample set collection, relevant personnel wearing the aforementioned helmet or electrode cap can perform left turns, right turns, braking, and normal driving in simulated driving environments or real driving environments using portable vehicles such as motorcycles, electric bicycles, and bicycles. The EEG signals of the relevant personnel are collected by the EEG electrodes and transmitted to a computing device. The computing device performs feature extraction, obtaining the feature data of the EEG signals as input samples, and the corresponding ground truth values ​​of the driving intent indication information as output samples.

[0066] Method 2:

[0067] The driving intention classification model consists of three AI models, which serve as left-turn classifier, right-turn classifier, and braking classifier, respectively.

[0068] See Figure 4 In this second method, the signal processing module inputs the feature data of the EEG signal into a left-turn classifier, a right-turn classifier, and a braking classifier, respectively. The left-turn classifier outputs a first driving intention indication, the right-turn classifier outputs a second driving intention indication, and the braking classifier outputs a third driving intention indication. The first driving intention indication indicates whether the driving intention is a left turn. For example, if the first driving intention indication is 1, it indicates a left turn; if it is 0, it indicates a non-left turn. The second driving intention indication indicates whether the driving intention is a right turn. For example, if the second driving intention indication is 1, it indicates a right turn; if it is 0, it indicates a non-right turn. The third driving intention indication information is used to indicate whether the driving intention is to brake. For example, if the third driving intention indication information is 1, then the third driving intention indication information indicates that the driving intention is to brake; if the third driving intention indication information is 0, then the third driving intention indication information indicates that the driving intention is not to brake.

[0069] After receiving the first driving intention indication information, the second driving intention indication information, and the third driving intention indication information, the signal processing module generates the driver's current driving intention indication information based on the first driving intention indication information, the second driving intention indication information, and the third driving intention indication information.

[0070] For example, if the first driving intention indication is 1, the second driving intention indication is 0, and the third driving intention indication is 0, then the three driving intention indications are combined in the order of the first, second, and third driving intentions to obtain the driver's current driving intention indication as 100. 100 indicates a left turn. The correspondence between the driver's current driving intention indication and the driving intention can be shown in Table 1 below:

[0071] Table 1

[0072]

[0073]

[0074] It is worth noting that in situations where there are multiple driving intentions, the driver may not be clear on how to steer or brake. In such cases, even if the following vehicle cannot accurately understand the driver's intentions, it can still serve as a reminder to the following vehicle, allowing it to reduce its speed and drive cautiously.

[0075] For the left-turn, right-turn, and braking classifiers used in Method 2, they can be pre-trained using sample sets before use. The sample set includes input and output samples. Taking the training of the left-turn classifier as an example, the input samples can be the feature data of a person's EEG signals when turning left, right, or braking. The output sample corresponding to the feature data when turning left is 1, and the output sample corresponding to the feature data when turning right, braking, or driving normally is 0. For the collection of the sample set, relevant personnel wearing the aforementioned helmet or electrode cap can perform left turns, right turns, braking, and normal driving in a simulated driving environment of portable vehicles such as motorcycles, electric bicycles, or bicycles, or in a real driving environment. The EEG electrodes collect the personnel's EEG signals and transmit them to a computing device. The computing device performs feature extraction, obtaining the feature data of the EEG signals as the input samples, and the corresponding driving intention indication information as the output samples.

[0076] In this second method, the left-turn classifier only needs to learn the characteristics of the driver's EEG signal when turning left, the right-turn classifier only needs to learn the characteristics of the driver's EEG signal when turning right, and the braking classifier only needs to learn the characteristics of the driver's EEG signal when braking. In this way, each classifier can more accurately identify the driver's current driving intention.

[0077] Method 3:

[0078] The driving intention classification model is an AI model. In addition, the helmet can be equipped with an accelerometer, which can be placed on the inside or outside of the helmet; it simply needs to be fixed to the helmet to accurately collect acceleration data. The accelerometer collects acceleration data in real time and sends the data to the information processing module.

[0079] See Figure 5 In this third method, the signal processing module inputs the feature data and acceleration data of the simultaneously received EEG signals into the driving intention classification model, and the driving intention classification model outputs the driver's current driving intention indication information.

[0080] Alternatively, the signal processing module inputs the feature data and acceleration data of the simultaneously received EEG signals into the driving intention classification model. The driving intention classification model outputs the confidence level corresponding to each driving intention indication. Then, driving intention indications with confidence levels higher than a threshold are selected as the driver's current driving intention indications. If all confidence levels are lower than the threshold, the driver's current driving intention is considered normal driving.

[0081] Method 4:

[0082] The driving intention classification model consists of three AI models, serving as a left-turn classifier, a right-turn classifier, and a braking classifier, respectively. Additionally, the helmet can be equipped with an acceleration sensor, which can be located either inside or outside the helmet; it simply needs to be fixed to the helmet to accurately collect acceleration data. The acceleration sensor collects acceleration data in real time and sends it to the information processing module.

[0083] See Figure 6 In method four, the signal processing module inputs the feature data and acceleration data of the simultaneously received EEG signals into a left-turn classifier, a right-turn classifier, and a braking classifier, respectively. The left-turn classifier outputs a first driving intention indication, the right-turn classifier outputs a second driving intention indication, and the braking classifier outputs a third driving intention indication. Specifically, the first driving intention indication indicates whether the driving intention is a left turn, the second driving intention indication indicates whether the driving intention is a right turn, and the third driving intention indication indicates whether the driving intention is braking.

[0084] After receiving the first driving intention indication information, the second driving intention indication information, and the third driving intention indication information, the signal processing module generates the driver's current driving intention indication information based on the first driving intention indication information, the second driving intention indication information, and the third driving intention indication information.

[0085] Method 5:

[0086] The driving intention classification model consists of six AI models, which serve as the first left-turn classifier, second left-turn classifier, first right-turn classifier, second right-turn classifier, first braking classifier, and second braking classifier, respectively. Additionally, the helmet can be equipped with an acceleration sensor, which can be located either inside or outside the helmet. Simply fix it to the helmet to accurately collect acceleration data. The acceleration sensor collects acceleration data in real time and sends it to the information processing module.

[0087] See Figure 7 In method five, the signal processing module inputs the feature data of the EEG signal into a first left-turn classifier, a first right-turn classifier, and a first braking classifier, respectively. The first left-turn classifier outputs a first left-turn confidence score, the first right-turn classifier outputs a first right-turn confidence score, and the first braking classifier outputs a first braking confidence score. Specifically, the first left-turn confidence score indicates the probability of a left turn, the first right-turn confidence score indicates the probability of a right turn, and the first braking confidence score indicates the probability of a braking intention.

[0088] The signal processing module also inputs the acceleration data into the second left-turn classifier, the second right-turn classifier, and the second braking classifier. The second left-turn classifier outputs a second left-turn confidence score, the second right-turn classifier outputs a second right-turn confidence score, and the second braking classifier outputs a second braking confidence score. The second left-turn confidence score indicates the probability of a left turn, the second right-turn confidence score indicates the probability of a right turn, and the second braking confidence score indicates the probability of braking.

[0089] Then, the signal processing module adds the product of the first left-turn confidence score and the first weight to the product of the second left-turn confidence score and the second weight to obtain the third left-turn confidence score. Similarly, it adds the product of the first right-turn confidence score and the third weight to the product of the second right-turn confidence score and the fourth weight to obtain the third right-turn confidence score. Finally, it adds the product of the first braking confidence score and the fifth weight to the product of the second braking confidence score and the sixth weight to obtain the third braking confidence score. Here, the first and second weights are both numbers greater than 0 and less than 1, and their sum is 1; the third and fourth weights are both numbers greater than 0 and less than 1, and their sum is 1; and the fifth and sixth weights are both numbers greater than 0 and less than 1, and their sum is 1.

[0090] The values ​​of the first, second, third, fourth, fifth, and sixth weights can be configured by relevant technical personnel. For example, the first, third, and fifth weights can all be the same, 0.6, and the second, fourth, and sixth weights can all be the same, 0.4. Of course, depending on the actual situation, the first, third, and fifth weights can also be different, and correspondingly, the second, fourth, and sixth weights can also be different. This application embodiment does not limit this.

[0091] After obtaining the third left-turn confidence level, the third right-turn confidence level, and the third braking confidence level, the driving intention indication information corresponding to the confidence level greater than the threshold is taken as the driver's current driving intention indication information. The threshold can be configured by relevant personnel according to actual needs; for example, it can be configured to 0.95.

[0092] For the first left-turn classifier, second left-turn classifier, first right-turn classifier, second right-turn classifier, first braking classifier, and second braking classifier used in Method 5, they can be pre-trained using sample sets before use. The sample set includes input samples and output samples. Taking the training of the second left-turn classifier as an example, the input samples can be the acceleration data from the accelerometer when a person is turning left, turning right, or braking. The output sample corresponding to the acceleration data during a left turn is 1, and the output sample corresponding to the feature data during a right turn, braking, or normal driving is 0. For the collection of the sample set, relevant personnel wearing the aforementioned helmet can perform left turns, right turns, braking, and normal driving in a simulated driving environment using portable vehicles such as motorcycles, electric bicycles, or bicycles, or in a real driving environment. EEG electrodes collect the personnel's electroencephalogram (EEG) signals, and accelerometers collect acceleration data, which is then transmitted to a computing device. The computing device performs feature extraction, obtaining the EEG signal feature data and acceleration data as input samples, and the confidence level of the corresponding driving intention indication information as the output sample.

[0093] In this fifth method, the first left-turn classifier only needs to learn the features of the driver's EEG signal when turning left, the second left-turn classifier only needs to learn the features of the driver's acceleration data when turning left, the first right-turn classifier only needs to learn the features of the driver's EEG signal when turning right, the second right-turn classifier only needs to learn the features of the driver's acceleration data when turning right, the first braking classifier only needs to learn the features of the driver's EEG signal when braking, and the second braking classifier only needs to learn the features of the driver's acceleration data when braking. Finally, the driving intention obtained from the acceleration data and EEG signal is combined to comprehensively determine the driver's driving intention. This method is more accurate than single-feature determination. Furthermore, using different classifiers to determine different driving intentions and inputting data from different sources into different classifiers reduces the complexity of individual classifiers and improves computational efficiency.

[0094] Step 203: The signal processing module controls at least one indicator light to indicate the driving intention based on the driving intention indication information.

[0095] In implementation, the signal processing module can control the left turn indicator, right turn indicator, and brake indicator to illuminate or dim based on the driver's intention, thereby indicating the driver's intention. The left turn indicator, right turn indicator, and brake indicator can have the following modes:

[0096] Mode 1: The left turn indicator light is on, while the right turn indicator light and brake indicator light are off.

[0097] Mode 2: The right turn indicator light is on, while the left turn indicator light and brake indicator light are off.

[0098] Mode 3: The brake indicator light is on, while the left turn indicator light and the right turn indicator light are off.

[0099] Mode 4: The left turn indicator, right turn indicator, and brake indicator are all off.

[0100] Mode 5: The left turn indicator and brake indicator are on, while the right turn indicator is off.

[0101] Mode 6: The right turn indicator and brake indicator are on, while the left turn indicator is off.

[0102] Mode 7: Left turn indicator and right turn indicator are on, brake indicator is off.

[0103] Mode 1 indicates the vehicle is turning left, reminding following vehicles to give way. Mode 2 indicates the vehicle is turning right, reminding following vehicles to give way. Mode 3 indicates the vehicle is braking, reminding following vehicles to slow down and give way. Mode 4 indicates the vehicle is driving normally. Mode 5 indicates the vehicle may turn left or brake, reminding following vehicles to slow down and give way. Mode 6 indicates the vehicle may turn right or brake, reminding following vehicles to slow down and give way. Mode 7 indicates the driver's intention is unclear, reminding following vehicles to observe carefully and drive cautiously.

[0104] In the technical solution provided in this application embodiment, an EEG electrode is installed inside the helmet, and a turn signal is installed at the back of the helmet. While the driver is riding with the helmet on, the EEG electrode collects the driver's brain signals. The signal processing module uses the brain signals and a driving intention classification model to determine the driver's current driving intention as a left turn, right turn, or brake. Then, it controls the turn signal to indicate the driver's driving intention. In this way, even if the driver forgets to use the vehicle's turn signal when turning, the helmet can still indicate the predicted driving intention through its own turn signal, thus reminding following vehicles and effectively reducing road safety hazards caused by drivers forgetting to use their turn signals.

[0105] All of the above-mentioned optional technical solutions can be combined in any way to form the optional embodiments of this application, and will not be described in detail here.

[0106] In an exemplary embodiment, a computer-readable storage medium is also provided, such as a memory including instructions that can be executed by a signal processing module in the helmet to complete the driving intention indication method in the above embodiments. The computer-readable storage medium may be non-transitory. For example, the computer-readable storage medium may be ROM (Read-Only Memory), RAM (Random Access Memory), CD-ROM (Compact Disc Read-Only Memory), magnetic tape, floppy disk, and optical data storage devices, etc.

[0107] It should be noted that all information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.), and signals (including but not limited to signals transmitted between the user terminal and other devices) involved in this application have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. For example, the EEG signals and acceleration data involved in this application were obtained with full authorization.

[0108] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0109] The above description is merely an optional embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for indicating driving intention, characterized in that, The method is applied to a helmet, which includes a helmet shell, EEG electrodes, a power supply module, a signal processing module, an accelerometer, and at least one indicator light. The EEG electrodes are disposed on the inner side of the helmet shell, and the at least one indicator light is disposed on the rear outer surface of the helmet shell. The power supply module is used to supply power to the EEG electrodes, the signal processing module, and the at least one indicator light. The method includes: The EEG electrodes collect the driver's EEG signals and send the EEG signals to the signal processing module; The accelerometer collects acceleration data and sends the acceleration data to the signal processing module. The signal processing module filters the EEG signal to obtain a signal in the target frequency band; The signal processing module performs principal component analysis on the signal in the target frequency band to obtain the amplitude of the signal that accounts for the proportion of the variance target as feature data. The signal processing module inputs the feature data and the acceleration data into the driving intention classification model to obtain the driver's driving intention indication information, wherein the driving intention indication information is used to indicate at least one driving intention among left turn, right turn, and braking; The signal processing module controls at least one indicator light to indicate driving intention based on the driving intention indication information.

2. The method according to claim 1, characterized in that, The helmet includes a left-turn indicator light, a right-turn indicator light, and a brake indicator light. The signal processing module, based on the driving intention indication information, controls at least one indicator light to indicate the driving intention, including: If the driving intention indicated by the driving intention information is to turn left, the signal processing module controls the left turn indicator light to illuminate; If the driving intention indicated by the driving intention information is to turn right, the signal processing module controls the right turn indicator light to illuminate; If the driving intention indicated by the driving intention information is to brake, the signal processing module controls the brake indicator light to illuminate.

3. A helmet, characterized in that, The helmet includes a helmet shell, EEG electrodes, a power supply module, a signal processing module, an accelerometer, and at least one indicator light; The EEG electrodes are disposed on the inner side of the helmet shell, and the at least one indicator light is disposed on the rear outer surface of the helmet shell. The power supply module is used to supply power to the EEG electrodes, the signal processing module, and the at least one indicator light. The EEG electrodes are used to collect the driver's EEG signals and send the EEG signals to the signal processing module. The accelerometer collects acceleration data and sends the acceleration data to the signal processing module. The signal processing module is used to filter the EEG signal to obtain a signal in the target frequency band, perform principal component analysis on the signal in the target frequency band to obtain the amplitude of the signal accounting for the target variance as feature data, and input the feature data and the acceleration data into the driving intention classification model to obtain the driver's driving intention indication information, wherein the driving intention indication information is used to indicate at least one driving intention among left turn, right turn, and braking. The signal processing module is used to control the at least one indicator light to indicate driving intention based on the driving intention indication information.

4. The helmet according to claim 3, characterized in that, The helmet includes a left turn indicator, a right turn indicator, and a brake indicator; The signal processing module is configured to control the left turn indicator light to illuminate if the driving intention indicated by the driving intention information is to turn left; control the right turn indicator light to illuminate if the driving intention indicated by the driving intention information is to turn right; and control the brake indicator light to illuminate if the driving intention indicated by the driving intention information is to brake.

Images