A driver state recognition system and method for a hazardous chemical transportation vehicle
By acquiring and analyzing the historical state characteristics of drivers of hazardous chemical transport vehicles, calculating causal indicators and determining weights, the limitations and low accuracy of driver state recognition for hazardous chemical transport vehicles are solved, achieving more efficient driver state recognition.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SPECIAL EQUIP SAFETY SUPERVISION INSPECTION INST OF JIANGSU PROVINCE
- Filing Date
- 2023-09-06
- Publication Date
- 2026-07-28
AI Technical Summary
Existing technologies for identifying the status of drivers of hazardous chemical transport vehicles have limitations and low accuracy, making them unsuitable for complex driving scenarios.
By acquiring the historical hazardous state characteristics of drivers of hazardous chemical transport vehicles, calculating the causal indices of visual features, physiological features, and vehicle driving features, screening feature types that meet the preset requirements, and determining the weights of visual features, physiological features, and vehicle driving features based on the driving scenario fit, the driver's state is finally identified.
It improves the accuracy and adaptability of driver state recognition, enabling it to better adapt to complex driving scenarios and avoid the limitations of recognition.
Smart Images
Figure CN117727013B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of vehicle driver recognition technology, and more specifically, to a driver status recognition system and method for hazardous chemical transport vehicles. Background Technology
[0002] Driver status identification for hazardous materials transport vehicles is a key technology designed to monitor and assess driver condition during driving, ensuring they are in optimal driving condition, thereby improving road safety and reducing potential hazards. This technology relies on a variety of background technologies to achieve comprehensive status monitoring and analysis.
[0003] First, visual monitoring technology is a crucial component of driver condition recognition. Using cameras or infrared sensors, the system can monitor the driver's eyes, facial expressions, and head posture in real time. This monitoring information includes characteristics such as drowsiness, inattention, and frequent blinking, helping to determine whether the driver is fatigued, distracted, or in other unsuitable driving conditions.
[0004] Secondly, physiological parameter monitoring technology plays a crucial role in driver condition identification. Through physiological sensors, such as heart rate monitors and blood pressure monitors, the system can detect the driver's physiological state in real time. Abnormal physiological parameters, such as excessively high heart rate or abnormal blood pressure, may indicate that the driver is in a state of stress, fatigue, or physical discomfort.
[0005] Furthermore, driving behavior monitoring technology is also a key factor in driver condition recognition. Vehicle sensors can monitor driving behaviors such as vehicle speed, steering angle, and braking force. Abnormal driving behaviors may indicate a poor driver condition, requiring attention and warning.
[0006] In existing technologies, these three aspects are often monitored separately and cannot be organically combined, resulting in certain limitations in recognition, poor recognition accuracy, low adaptability, and inability to adapt to complex driving situations.
[0007] Therefore, how to improve the limitations and accuracy of recognition is a technical problem that needs to be solved. Summary of the Invention
[0008] This invention provides a driver status recognition system for hazardous chemical transport vehicles, addressing the technical problems of limitations, low accuracy, and poor adaptability in existing technologies. The system includes:
[0009] The first module is used to obtain the historical hazardous status characteristics of drivers of hazardous chemical transport vehicles and the corresponding driver status degree. The historical hazardous status characteristics of drivers of hazardous chemical transport vehicles include visual characteristics, physiological characteristics and vehicle driving characteristics.
[0010] The second module is used to calculate the causal indicators of visual features, physiological features, vehicle driving features and driver state, and to filter out the types of visual features, physiological features and vehicle driving features that meet the preset requirements.
[0011] The third module is used to determine the corresponding weight ranges based on the selected visual features, physiological features, and vehicle driving features, and to determine the driving scenario fit.
[0012] The fourth module is used to determine the weights of visual features, physiological features, and vehicle driving features within the corresponding weight range based on the driving scenario fit.
[0013] The fifth module is used to acquire visual features, physiological features, and vehicle driving features, and determine the driver's state according to the corresponding weights, and to identify the driver's state.
[0014] In some embodiments of this application, the second module is used for:
[0015] Construct a first state space based on each visual feature, physiological feature, or vehicle driving feature;
[0016] Construct a second state space based on the driver's state level;
[0017] Calculate the causal index between the first state space and the second state space respectively;
[0018] The feature types whose causality index is greater than the first causality index threshold are retained;
[0019] Features whose causal index is greater than the second causal index threshold but not greater than the first causal index threshold are denoted as features to be investigated.
[0020] The difference between the causal index of the feature to be investigated and the threshold of the second causal index is recorded as the first difference, and the difference between the causal index of the feature to be investigated and the threshold of the first causal index is recorded as the second difference. A preset ratio is determined according to the type of feature to be investigated, wherein the preset ratio is the ratio of the first difference to the second difference.
[0021] If the ratio of the first difference to the second difference is greater than the preset ratio, then the feature type of the feature to be investigated is retained.
[0022] In some embodiments of this application, the third module is used for:
[0023] The visual features, physiological features, and vehicle driving features of each type after screening are quantified.
[0024] The total number of visual features, total number of physiological features, and total number of vehicle driving features are determined based on the visual features, physiological features, and vehicle driving features of each type after screening.
[0025] The first weight interval is determined based on the types and total amount of visual features, the second weight interval is determined based on the types and total amount of physiological features, and the third weight interval is determined based on the types and total amount of vehicle driving features.
[0026] The driving scenario fit is determined based on the total amount of physiological characteristics and the total amount of vehicle driving characteristics.
[0027] In some embodiments of this application, the fourth module is used for:
[0028] Based on the driving scenario fit, the corresponding standard weight interval is found in the preset weight table. In the weight table, each driving scenario fit corresponds to a standard weight interval for visual features, physiological features, and vehicle driving features.
[0029] If the standard weight interval of the corresponding feature overlaps with the first weight interval, the second weight interval, or the third weight interval, then the overlapping interval is taken as the weight of the feature.
[0030] Otherwise, the average of the standard weight interval and the first weight interval or the second weight interval or the third weight interval is used as the weight corresponding to the feature.
[0031] In some embodiments of this application, the fifth module is used for:
[0032] The influencing factors corresponding to visual features, physiological features, and vehicle driving features are obtained respectively, and the total influence of visual features, physiological features, and vehicle driving features is calculated respectively.
[0033] The weights of each of the three factors—visual features, physiological features, and vehicle driving features—are adjusted based on their total influence, and the driver's state level is determined based on the total amount of visual features, physiological features, and vehicle driving features.
[0034] Correspondingly, this application also provides a method for driver status recognition of hazardous chemical transport vehicles, the method comprising:
[0035] To obtain the historical hazardous status characteristics and corresponding driver status levels of drivers of hazardous chemical transport vehicles, the historical hazardous status characteristics of drivers of hazardous chemical transport vehicles include visual characteristics, physiological characteristics and vehicle driving characteristics;
[0036] The causal indices of visual features, physiological features, vehicle driving features and driver state level are calculated respectively, and the types of visual features, physiological features and vehicle driving features that meet the preset requirements are selected.
[0037] Based on the selected visual features, physiological features, and vehicle driving features, the corresponding weight intervals are determined, and the driving scenario fit is determined.
[0038] The weights of visual features, physiological features, and vehicle driving features are determined within the corresponding weight range based on the driving scenario fit.
[0039] The system acquires visual features, physiological features, and vehicle driving features, and determines the driver's state based on the corresponding weights, thereby identifying the driver's state.
[0040] In some embodiments of this application, causal indices between visual features, physiological features, vehicle driving features, and driver state levels are calculated respectively, and feature types of visual features, physiological features, and vehicle driving features that meet preset requirements are selected, including:
[0041] Construct a first state space based on each visual feature, physiological feature, or vehicle driving feature;
[0042] Construct a second state space based on the driver's state level;
[0043] Calculate the causal index between the first state space and the second state space respectively;
[0044] The feature types whose causality index is greater than the first causality index threshold are retained;
[0045] Features whose causal index is greater than the second causal index threshold but not greater than the first causal index threshold are denoted as features to be investigated.
[0046] The difference between the causal index of the feature to be investigated and the threshold of the second causal index is recorded as the first difference, and the difference between the causal index of the feature to be investigated and the threshold of the first causal index is recorded as the second difference. A preset ratio is determined according to the type of feature to be investigated, wherein the preset ratio is the ratio of the first difference to the second difference.
[0047] If the ratio of the first difference to the second difference is greater than the preset ratio, then the feature type of the feature to be investigated is retained.
[0048] In some embodiments of this application, corresponding weight intervals are determined based on the selected visual features, physiological features, and vehicle driving features, and the driving scenario fit is determined, including:
[0049] The visual features, physiological features, and vehicle driving features of each type after screening are quantified.
[0050] The total number of visual features, total number of physiological features, and total number of vehicle driving features are determined based on the visual features, physiological features, and vehicle driving features of each type after screening.
[0051] The first weight interval is determined based on the types and total amount of visual features, the second weight interval is determined based on the types and total amount of physiological features, and the third weight interval is determined based on the types and total amount of vehicle driving features.
[0052] The driving scenario fit is determined based on the total amount of physiological characteristics and the total amount of vehicle driving characteristics.
[0053] In some embodiments of this application, the weights of visual features, physiological features, and vehicle driving features are determined within corresponding weight intervals based on the driving scene fit, including:
[0054] Based on the driving scenario fit, the corresponding standard weight interval is found in the preset weight table. In the weight table, each driving scenario fit corresponds to a standard weight interval for visual features, physiological features, and vehicle driving features.
[0055] If the standard weight interval of the corresponding feature overlaps with the first weight interval, the second weight interval, or the third weight interval, then the overlapping interval is taken as the weight of the feature.
[0056] Otherwise, the average of the standard weight interval and the first weight interval or the second weight interval or the third weight interval is used as the weight corresponding to the feature.
[0057] In some embodiments of this application, the driver's state is determined according to corresponding weights, and the driver's state is identified, including:
[0058] The influencing factors corresponding to visual features, physiological features, and vehicle driving features are obtained respectively, and the total influence of visual features, physiological features, and vehicle driving features is calculated respectively.
[0059] The weights of each of the three factors—visual features, physiological features, and vehicle driving features—are adjusted based on their total influence, and the driver's state level is determined based on the total amount of visual features, physiological features, and vehicle driving features.
[0060] By applying the above technical solution, the first module is used to acquire the historical hazardous state characteristics and corresponding driver state levels of drivers of hazardous chemical transport vehicles. These historical hazardous state characteristics include visual features, physiological features, and vehicle driving characteristics. The second module is used to calculate the causal indices between visual features, physiological features, vehicle driving characteristics, and driver state levels, and to filter out feature types that meet preset requirements. The third module is used to determine the corresponding weight intervals for the filtered visual features, physiological features, and vehicle driving characteristics, and to determine the driving scenario fit. The fourth module is used to determine the weights of visual features, physiological features, and vehicle driving characteristics within the corresponding weight intervals based on the driving scenario fit. The fifth module is used to acquire visual features, physiological features, and vehicle driving characteristics, and determine the driver state according to the corresponding weights, thus identifying the driver state. This avoids limitations in recognition, improves recognition accuracy, and ensures that the recognition can adapt to relatively complex driving scenarios, thereby improving adaptability. Attached Figure Description
[0061] 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.
[0062] Figure 1 A flowchart illustrating a method for identifying the driver status of a hazardous chemical transport vehicle according to an embodiment of the present invention is shown.
[0063] Figure 2 A schematic diagram of the structure of a driver status recognition system for hazardous chemical transport vehicles proposed in an embodiment of the present invention is shown. Detailed Implementation
[0064] 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. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0065] This application provides a driver status recognition system for hazardous chemical transport vehicles, such as... Figure 2 As shown, the system includes the following modules:
[0066] The first module is used to obtain the historical hazardous status characteristics of drivers of hazardous chemical transport vehicles and the corresponding driver status degree. The historical hazardous status characteristics of drivers of hazardous chemical transport vehicles include visual characteristics, physiological characteristics and vehicle driving characteristics.
[0067] In this embodiment, visual features, physiological features, and vehicle driving features represent the following: Visual monitoring: using cameras or infrared sensors to monitor the driver's eyes, facial expressions, and head posture. This involves detecting features such as drowsiness, distraction, and blinking frequency. Physiological parameter monitoring: using physiological sensors to detect the driver's physiological state, such as heart rate, blood pressure, and skin conductance. These parameters can help determine whether the driver is under stress, fatigued, or in other abnormal states. Vehicle sensors are used to monitor driving behavior, such as vehicle speed, steering angle, and braking force. Abnormal driving behavior may indicate a poor driver condition.
[0068] It is understandable that the above features can be obtained through neural network models or extraction algorithms, which are conventional techniques in this field and will not be elaborated here.
[0069] The second module is used to calculate the causal indicators of visual features, physiological features, vehicle driving features and driver state, and to filter out the types of visual features, physiological features and vehicle driving features that meet the preset requirements.
[0070] In this embodiment, features that meet the requirements are selected from a large number of feature types.
[0071] In some embodiments of this application, the second module is used for:
[0072] Construct a first state space based on each visual feature, physiological feature, or vehicle driving feature;
[0073] Construct a second state space based on the driver's state level;
[0074] Calculate the causal index between the first state space and the second state space respectively;
[0075] The feature types whose causality index is greater than the first causality index threshold are retained;
[0076] Features whose causal index is greater than the second causal index threshold but not greater than the first causal index threshold are denoted as features to be investigated.
[0077] The difference between the causal index of the feature to be investigated and the threshold of the second causal index is recorded as the first difference, and the difference between the causal index of the feature to be investigated and the threshold of the first causal index is recorded as the second difference. A preset ratio is determined according to the type of feature to be investigated, wherein the preset ratio is the ratio of the first difference to the second difference.
[0078] If the ratio of the first difference to the second difference is greater than the preset ratio, then the feature type of the feature to be investigated is retained.
[0079] In this embodiment, the causal index is a nonlinear interdependence index, which is based on state space reconstruction and nearest neighbor distance methods to determine the direction and magnitude of causal relationships. For two independent systems or factors X and Y, the state spaces of the two systems are established according to state space reconstruction theory.
[0080] For a sample point x in the state space X n x rn，1 , ..., x rn，k 。 represents x n Calculate x from the k nearest neighbors in the state space X. n The average Euclidean distance to the k nearest neighbors;
[0081]
[0082] For a sample point y in the state space Y n y sn，1 , ..., y sn，k Indicates y n Find the k nearest neighbors in state space Y, map them to state space X, and compute x. n with k nearest neighbors x sn，1 , ..., x sn，k The average Euclidean distance;
[0083]
[0084] To simplify the calculation, we can use x n The average distance to all N sample points;
[0085]
[0086] The nonlinear interdependence index, based on the state-space method, determines the causal relationship between systems according to the mapping relationship in the state space. It is defined as follows:
[0087]
[0088] According to the definition, 0 < S X→Y ≤1, when S X→Y As S approaches 0, systems X and Y are independent; when S... X→Y When the value is significantly greater than 0, there is a causal relationship from system X to Y, and the closer it is to 1, the stronger the causal relationship.
[0089] The third module is used to determine the corresponding weight ranges based on the selected visual features, physiological features, and vehicle driving features, and to determine the driving scenario fit.
[0090] In some embodiments of this application, the third module is used for:
[0091] The visual features, physiological features, and vehicle driving features of each type after screening are quantified.
[0092] The total number of visual features, total number of physiological features, and total number of vehicle driving features are determined based on the visual features, physiological features, and vehicle driving features of each type after screening.
[0093] The first weight interval is determined based on the types and total amount of visual features, the second weight interval is determined based on the types and total amount of physiological features, and the third weight interval is determined based on the types and total amount of vehicle driving features.
[0094] The driving scenario fit is determined based on the total amount of physiological characteristics and the total amount of vehicle driving characteristics.
[0095] In this embodiment, the total amount of physiological features and the total amount of vehicle driving features together correspond to a driving scenario fit.
[0096] The fourth module is used to determine the weights of visual features, physiological features, and vehicle driving features within the corresponding weight range based on the driving scenario fit.
[0097] In some embodiments of this application, the fourth module is used for:
[0098] Based on the driving scenario fit, the corresponding standard weight interval is found in the preset weight table. In the weight table, each driving scenario fit corresponds to a standard weight interval for visual features, physiological features, and vehicle driving features.
[0099] If the standard weight interval of the corresponding feature overlaps with the first weight interval, the second weight interval, or the third weight interval, then the overlapping interval is taken as the weight of the feature.
[0100] Otherwise, the average of the standard weight interval and the first weight interval or the second weight interval or the third weight interval is used as the weight corresponding to the feature.
[0101] The fifth module is used to acquire visual features, physiological features, and vehicle driving features, and determine the driver's state according to the corresponding weights, and to identify the driver's state.
[0102] In some embodiments of this application, the fifth module is used for:
[0103] The influencing factors corresponding to visual features, physiological features, and vehicle driving features are obtained respectively, and the total influence of visual features, physiological features, and vehicle driving features is calculated respectively.
[0104] The weights of each of the three factors—visual features, physiological features, and vehicle driving features—are adjusted based on their total influence, and the driver's state level is determined based on the total amount of visual features, physiological features, and vehicle driving features.
[0105] In this embodiment, "correction" refers to the fact that there is a correction coefficient corresponding to the total influence amount, and the product of the correction coefficient and the weight is the correction.
[0106] By applying the above technical solution, the first module is used to acquire the historical hazardous state characteristics and corresponding driver state levels of drivers of hazardous chemical transport vehicles. These historical hazardous state characteristics include visual features, physiological features, and vehicle driving characteristics. The second module is used to calculate the causal indices between visual features, physiological features, vehicle driving characteristics, and driver state levels, and to filter out feature types that meet preset requirements. The third module is used to determine the corresponding weight intervals for the filtered visual features, physiological features, and vehicle driving characteristics, and to determine the driving scenario fit. The fourth module is used to determine the weights of visual features, physiological features, and vehicle driving characteristics within the corresponding weight intervals based on the driving scenario fit. The fifth module is used to acquire visual features, physiological features, and vehicle driving characteristics, and determine the driver state according to the corresponding weights, thus identifying the driver state. This avoids limitations in recognition, improves recognition accuracy, and ensures that the recognition can adapt to relatively complex driving scenarios, thereby improving adaptability.
[0107] Those skilled in the art will understand that the modules in the system of the implementation scenario can be distributed throughout the system of the implementation scenario as described, or they can be modified to reside in one or more systems different from this implementation scenario. The modules of the above-mentioned implementation scenario can be merged into one module, or they can be further divided into multiple sub-modules.
[0108] Correspondingly, this application also provides a method for identifying the driver status of a hazardous chemical transport vehicle, such as... Figure 2 As shown, the method includes:
[0109] Step 1: Obtain the historical hazardous status characteristics and corresponding driver status levels of the drivers of hazardous chemical transport vehicles. The historical hazardous status characteristics of the drivers of hazardous chemical transport vehicles include visual characteristics, physiological characteristics, and vehicle driving characteristics.
[0110] Step 2: Calculate the causal indices between visual features, physiological features, vehicle driving features and driver state level, and select the types of visual features, physiological features and vehicle driving features that meet the preset requirements.
[0111] Step 3: Determine the corresponding weight ranges for the selected visual features, physiological features, and vehicle driving features, and determine the driving scenario fit.
[0112] Step 4: Determine the weights of visual features, physiological features, and vehicle driving features within the corresponding weight range based on the driving scenario fit.
[0113] Step 5: Obtain visual features, physiological features, and vehicle driving features, and determine the driver's status according to the corresponding weights, and identify the driver's status.
[0114] In some embodiments of this application, causal indices between visual features, physiological features, vehicle driving features, and driver state levels are calculated respectively, and feature types of visual features, physiological features, and vehicle driving features that meet preset requirements are selected, including:
[0115] Construct a first state space based on each visual feature, physiological feature, or vehicle driving feature;
[0116] Construct a second state space based on the driver's state level;
[0117] Calculate the causal index between the first state space and the second state space respectively;
[0118] The feature types whose causality index is greater than the first causality index threshold are retained;
[0119] Features whose causal index is greater than the second causal index threshold but not greater than the first causal index threshold are denoted as features to be investigated.
[0120] The difference between the causal index of the feature to be investigated and the threshold of the second causal index is recorded as the first difference, and the difference between the causal index of the feature to be investigated and the threshold of the first causal index is recorded as the second difference. A preset ratio is determined according to the type of feature to be investigated, wherein the preset ratio is the ratio of the first difference to the second difference.
[0121] If the ratio of the first difference to the second difference is greater than the preset ratio, then the feature type of the feature to be investigated is retained.
[0122] In some embodiments of this application, corresponding weight intervals are determined based on the selected visual features, physiological features, and vehicle driving features, and the driving scenario fit is determined, including:
[0123] The visual features, physiological features, and vehicle driving features of each type after screening are quantified.
[0124] The total number of visual features, total number of physiological features, and total number of vehicle driving features are determined based on the visual features, physiological features, and vehicle driving features of each type after screening.
[0125] The first weight interval is determined based on the types and total amount of visual features, the second weight interval is determined based on the types and total amount of physiological features, and the third weight interval is determined based on the types and total amount of vehicle driving features.
[0126] The driving scenario fit is determined based on the total amount of physiological characteristics and the total amount of vehicle driving characteristics.
[0127] In some embodiments of this application, the weights of visual features, physiological features, and vehicle driving features are determined within corresponding weight intervals based on the driving scene fit, including:
[0128] Based on the driving scenario fit, the corresponding standard weight interval is found in the preset weight table. In the weight table, each driving scenario fit corresponds to a standard weight interval for visual features, physiological features, and vehicle driving features.
[0129] If the standard weight interval of the corresponding feature overlaps with the first weight interval, the second weight interval, or the third weight interval, then the overlapping interval is taken as the weight of the feature.
[0130] Otherwise, the average of the standard weight interval and the first weight interval or the second weight interval or the third weight interval is used as the weight corresponding to the feature.
[0131] In some embodiments of this application, the driver's state is determined according to corresponding weights, and the driver's state is identified, including:
[0132] The influencing factors corresponding to visual features, physiological features, and vehicle driving features are obtained respectively, and the total influence of visual features, physiological features, and vehicle driving features is calculated respectively.
[0133] The weights of each of the three factors—visual features, physiological features, and vehicle driving features—are adjusted based on their total influence, and the driver's state level is determined based on the total amount of visual features, physiological features, and vehicle driving features.
[0134] Through the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented in hardware or by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) and includes several instructions to cause a computer device (such as a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.
[0135] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.
Claims
1. A driver status recognition system for hazardous chemical transport vehicles, characterized in that, The system includes: The first module is used to obtain the historical hazardous status characteristics of drivers of hazardous chemical transport vehicles and the corresponding driver status degree. The historical hazardous status characteristics of drivers of hazardous chemical transport vehicles include visual characteristics, physiological characteristics and vehicle driving characteristics. The second module is used to calculate the causal indicators of visual features, physiological features, vehicle driving features and driver state, and to filter out the types of visual features, physiological features and vehicle driving features that meet the preset requirements. The third module is used to determine the corresponding weight ranges based on the selected visual features, physiological features, and vehicle driving features, and to determine the driving scenario fit. The fourth module is used to determine the weights of visual features, physiological features, and vehicle driving features within the corresponding weight range based on the driving scenario fit. The fifth module is used to acquire visual features, physiological features, and vehicle driving features, and determine the driver's state according to the corresponding weights, thereby identifying the driver's state. The third module is used for: The visual features, physiological features, and vehicle driving features of each type after screening are quantified. The total number of visual features, total number of physiological features, and total number of vehicle driving features are determined based on the visual features, physiological features, and vehicle driving features of each type after screening. The first weight interval is determined based on the types and total amount of visual features, the second weight interval is determined based on the types and total amount of physiological features, and the third weight interval is determined based on the types and total amount of vehicle driving features. The driving scenario fit is determined based on the total amount of physiological characteristics and the total amount of vehicle driving characteristics; The fourth module is used for: Based on the driving scenario fit, the corresponding standard weight interval is found in the preset weight table. In the weight table, each driving scenario fit corresponds to a standard weight interval for visual features, physiological features, and vehicle driving features. If the standard weight interval of the corresponding feature overlaps with the first weight interval, the second weight interval, or the third weight interval, then the overlapping interval is taken as the weight of the feature. Otherwise, the average of the standard weight interval and the first weight interval or the second weight interval or the third weight interval is used as the weight corresponding to the feature.
2. The driver status recognition system for hazardous chemical transport vehicles as described in claim 1, characterized in that, The second module is used for: Construct a first state space based on each visual feature, physiological feature, or vehicle driving feature; Construct a second state space based on the driver's state level; Calculate the causal index between the first state space and the second state space respectively; The feature types whose causality index is greater than the first causality index threshold are retained; Features whose causal index is greater than the second causal index threshold but not greater than the first causal index threshold are denoted as features to be investigated. The difference between the causal index of the feature to be investigated and the threshold of the second causal index is recorded as the first difference, and the difference between the causal index of the feature to be investigated and the threshold of the first causal index is recorded as the second difference. A preset ratio is determined according to the type of feature to be investigated, wherein the preset ratio is the ratio of the first difference to the second difference. If the ratio of the first difference to the second difference is greater than the preset ratio, then the feature type of the feature to be investigated is retained.
3. The driver status recognition system for hazardous chemical transport vehicles as described in claim 2, characterized in that, The fifth module is used for: The influencing factors corresponding to visual features, physiological features, and vehicle driving features are obtained respectively, and the total influence of visual features, physiological features, and vehicle driving features is calculated respectively. The weights of each of the three factors—visual features, physiological features, and vehicle driving features—are adjusted based on their total influence, and the driver's state level is determined based on the total amount of visual features, physiological features, and vehicle driving features.
4. A method for identifying the driver status of a hazardous chemical transport vehicle, characterized in that, The method includes: To obtain the historical hazardous status characteristics and corresponding driver status levels of drivers of hazardous chemical transport vehicles, the historical hazardous status characteristics of drivers of hazardous chemical transport vehicles include visual characteristics, physiological characteristics and vehicle driving characteristics. The causal indices of visual features, physiological features, vehicle driving features and driver state level are calculated respectively, and the types of visual features, physiological features and vehicle driving features that meet the preset requirements are selected. Based on the selected visual features, physiological features, and vehicle driving features, the corresponding weight intervals are determined, and the driving scenario fit is determined. The weights of visual features, physiological features, and vehicle driving features are determined within the corresponding weight range based on the driving scenario fit. The system acquires visual features, physiological features, and vehicle driving features, and determines the driver's state based on the corresponding weights, thereby identifying the driver's state. Based on the selected visual features, physiological features, and vehicle driving features, corresponding weight intervals are determined, and the driving scenario fit is determined, including: The visual features, physiological features, and vehicle driving features of each type after screening are quantified. The total number of visual features, total number of physiological features, and total number of vehicle driving features are determined based on the visual features, physiological features, and vehicle driving features of each type after screening. The first weight interval is determined based on the types and total amount of visual features, the second weight interval is determined based on the types and total amount of physiological features, and the third weight interval is determined based on the types and total amount of vehicle driving features. The driving scenario fit is determined based on the total amount of physiological characteristics and the total amount of vehicle driving characteristics; The weights of visual features, physiological features, and vehicle driving features are determined within the corresponding weight range based on the driving scenario fit, including: Based on the driving scenario fit, the corresponding standard weight interval is found in the preset weight table. In the weight table, each driving scenario fit corresponds to a standard weight interval for visual features, physiological features, and vehicle driving features. If the standard weight interval of the corresponding feature overlaps with the first weight interval, the second weight interval, or the third weight interval, then the overlapping interval is taken as the weight of the feature. Otherwise, the average of the standard weight interval and the first weight interval or the second weight interval or the third weight interval is used as the weight corresponding to the feature.
5. The method for driver status identification of hazardous chemical transport vehicles as described in claim 4, characterized in that, The causal indices between visual features, physiological features, vehicle driving features, and driver state levels are calculated separately, and feature types that meet preset requirements are selected, including: Construct a first state space based on each visual feature, physiological feature, or vehicle driving feature; Construct a second state space based on the driver's state level; Calculate the causal index between the first state space and the second state space respectively; The feature types whose causality index is greater than the first causality index threshold are retained; Features whose causal index is greater than the second causal index threshold but not greater than the first causal index threshold are denoted as features to be investigated. The difference between the causal index of the feature to be investigated and the threshold of the second causal index is recorded as the first difference, and the difference between the causal index of the feature to be investigated and the threshold of the first causal index is recorded as the second difference. A preset ratio is determined according to the type of feature to be investigated, wherein the preset ratio is the ratio of the first difference to the second difference. If the ratio of the first difference to the second difference is greater than the preset ratio, then the feature type of the feature to be investigated is retained.
6. The method for driver status identification of hazardous chemical transport vehicles as described in claim 5, characterized in that, The driver's status is determined based on corresponding weights, and the driver's status is identified, including: The influencing factors corresponding to visual features, physiological features, and vehicle driving features are obtained respectively, and the total influence of visual features, physiological features, and vehicle driving features is calculated respectively. The weights of each of the three factors—visual features, physiological features, and vehicle driving features—are adjusted based on their total influence, and the driver's state level is determined based on the total amount of visual features, physiological features, and vehicle driving features.