Boltzmann entropy-based head-up display method and system

Abstract

This invention provides a method and system for in-vehicle head-up display based on Boltzmann entropy. The method includes: mapping a driving scene into several microstates and defining quantifiable data indicators for each microstate as micro-features; acquiring micro-feature data for each microstate of the current driving scene and calculating the Boltzmann entropy of the current driving scene; and determining the in-vehicle head-up display level based on the Boltzmann entropy of the current driving scene, wherein different in-vehicle head-up display levels contain different numbers of display elements. This invention introduces Boltzmann entropy to quantify the absolute complexity of the current driving scene, constructing a complete microstate mapping system to extract the number of microstates in the driving scene, thereby accurately calculating the Boltzmann entropy of the current driving scene.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle-mounted human-computer interaction systems, and in particular to a vehicle-mounted head-up display method and system based on Boltzmann entropy. BACKGROUND

[0002] With the development of intelligent driving technology, head-up vehicle navigation electronic maps are increasingly used. Although these maps provide convenience for drivers, too many visual symbol guide contents can also interfere with the attention of the driver. Therefore, it is particularly important to reasonably configure guide information, and the configuration of this information needs to be determined based on the information entropy of the head-up vehicle navigation real scene map.

[0003] In the traditional method, the information uncertainty is calculated based on the distribution using the Shannon entropy method, so as to quantify the complexity of the current driving scene, and the guide information of the vehicle-mounted head-up display system is configured based on the complexity of the driving scene.

[0004] However, the calculation method based on the Shannon entropy is difficult to quantify the absolute complexity of the driving scene, so that the accuracy of the judgment of the complexity of the actual driving scene is lacking, and it is difficult to accurately adjust the guide information of the vehicle-mounted head-up display system. SUMMARY

[0005] The present application provides a vehicle-mounted head-up display method and system based on Boltzmann entropy, to solve the defect of poor accuracy of the vehicle-mounted head-up display system based on the Shannon entropy in the prior art, and to realize a vehicle-mounted head-up display method with higher accuracy, so as to quantify the absolute complexity of the driving scene.

[0006] The present application provides a vehicle-mounted head-up display method based on Boltzmann entropy, comprising:

[0007] mapping the driving scene into a plurality of microstates, and defining quantifiable data indicators of each microstate as micro features of each microstate;

[0008] obtaining each micro feature data of each microstate of the current driving scene, and calculating the Boltzmann entropy of the current driving scene;

[0009] determining the vehicle-mounted head-up display level according to the Boltzmann entropy of the current driving scene, wherein different vehicle-mounted head-up display levels contain different numbers of display elements.

[0010] According to the vehicle-mounted head-up display method based on Boltzmann entropy provided by the present application, the step of calculating the Boltzmann entropy of the current driving scene specifically comprises:

[0011] According to the road type to which the current driving scene belongs, the weight of each microstate is selected, wherein a mapping relationship between the road type and the weight of each microstate is predefined;

[0012] According to each micro feature data of each microstate, the Boltzmann entropy state number of each micro feature data is determined, wherein a mapping relationship between each micro feature data and the Boltzmann entropy state number is predefined;

[0013] The first product of all the Boltzmann entropy state numbers corresponding to each microstate is calculated.

[0014] The first product of each microstate is weighted using the weight of each microstate, and the weighted product of all microstates is calculated to obtain the Boltzmann entropy of the current driving scene.

[0015] According to the vehicle head-up display method based on the Boltzmann entropy provided by the application, before the step of selecting the weight of each micro feature according to the road type to which the current driving scene belongs, the method further comprises:

[0016] According to the results of the driving cognition experiment, the weight of each micro feature under each road type is defined, wherein the road types include expressway, urban main road, urban secondary road, rural road and tunnel.

[0017] According to the vehicle head-up display method based on the Boltzmann entropy provided by the application, the vehicle head-up display level includes the first level representing the low complexity scene, the second level representing the medium complexity scene and the third level representing the high complexity scene, and the number of display elements contained in the vehicle head-up display level decreases step by step from the first level to the third level.

[0018] According to the vehicle head-up display method based on the Boltzmann entropy provided by the application, the microstate is defined as four categories, namely people, vehicles, roads and environment.

[0019] According to the vehicle head-up display method based on the Boltzmann entropy provided by the application, the step of obtaining each micro feature data of each microstate of the current driving scene specifically comprises:

[0020] Extracting the vehicle video of the current driving process, wherein the vehicle video represents the visual field environment of the driver;

[0021] Extracting the image frame of the vehicle video, and using a target detection model to detect the target bounding box corresponding to the people, vehicles and road signs in each image frame;

[0022] Based on the detection result of the target detection model, the micro feature data of each microstate of the current driving scene is determined.

[0023] The application also provides a head-up display system based on Boltzmann entropy, comprising:

[0024] An acquisition module is configured to acquire each item of microscopic feature data of each type of microscopic state of a current driving scene and calculate Boltzmann entropy of the current driving scene;

[0025] A determination module is configured to determine a head-up display level according to the Boltzmann entropy of the current driving scene;

[0026] A display module is configured to adjust and display display elements according to the determined head-up display level.

[0027] The application also provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the head-up display method based on Boltzmann entropy according to any one of the above.

[0028] The application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program is executable on a processor to implement the head-up display method based on Boltzmann entropy according to any one of the above.

[0029] The application also provides a computer program product comprising a computer program, wherein the computer program is executable on a processor to implement the head-up display method based on Boltzmann entropy according to any one of the above.

[0030] The head-up display method and system based on Boltzmann entropy provided by the application quantifies the absolute complexity of a current driving scene by introducing Boltzmann entropy, constructs a complete microscopic state mapping system to extract the number of microscopic states in a driving scene, accurately calculates the Boltzmann entropy of the current driving scene, determines the corresponding head-up display level according to the Boltzmann entropy of the driving scene, and displays the level to control the number of display elements and reduce the driving load of a driver in a complex scene. BRIEF DESCRIPTION OF DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the application or prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0032] Figure 1 is a flowchart of the head-up display method based on Boltzmann entropy provided by the application;

[0033] Figure 2This is a schematic diagram of the structure of the vehicle head-up display system based on Boltzmann entropy provided by the present invention;

[0034] Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0035] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0036] The following is combined with Figure 1 This invention introduces a vehicle head-up display method based on Boltzmann entropy, such as... Figure 1 As shown, it includes:

[0037] Step 101: Map the driving scenario into several types of micro-states, and define quantifiable data indicators for each type of micro-state as micro-features of each type of micro-state.

[0038] A head-up display (HUD) system projects driver assistance information onto the windshield in front of the driver, allowing the driver to access relevant driving information without looking down, thus assisting the driver in driving.

[0039] However, the information projected by the HUD also increases the content in the driver's field of vision. In complex driving scenarios, too much information displayed by the HUD can affect the driver's judgment of the current driving environment. Therefore, it is necessary to adjust the number of display elements of the HUD projection according to the actual driving environment of the driver.

[0040] Traditional quantification methods based on Shannon entropy typically rely on probability distributions to determine the uncertainty of driving scenarios. This means that driving scenarios with higher uncertainty require fewer display elements. However, probability distributions are difficult to accurately quantify the absolute complexity of a scenario, which can lead to errors in the assessment of scenario complexity.

[0041] Therefore, this invention introduces Boltzmann entropy to map driving scenarios into a number of microstates and quantifies absolute complexity through statistical mechanics principles.

[0042] To achieve driving scenario quantization based on Boltzmann entropy, the driving scenario needs to be pre-mapped into a number of microstates.

[0043] Optionally, factors that have a significant impact on drivers can be selected as micro-states, and quantifiable data indicators for each type of factor can be determined as micro-features, and a quantification method for each micro-feature can be defined.

[0044] As a preferred implementation, the microstate is defined as four categories: people, vehicles, roads, and environment. Then, the micro characteristics and quantification methods corresponding to each category of microstate are defined respectively.

[0045] Optionally, when the micro-state is a person, the micro-features may include pedestrian density, pedestrian movement direction, pedestrian movement speed, etc.; when the micro-state is a vehicle, the micro-features may include the vehicle's own speed, road vehicle density, road vehicle type, road vehicle taillight status, road vehicle speed, distance, etc.; when the micro-state is a road, the micro-features may include road type, number of lanes, traffic sign density, road curvature radius, road slope, road material, etc.; when the micro-state is an environment, the micro-features may include weather, lighting conditions, tunnels, overpasses, backlighting, etc.

[0046] However, considering the need to reduce the amount of parallel computation on the micro-state of the onboard host and enhance real-time performance, the following preferred scheme is implemented among the many optional micro-features mentioned above, based on the results of a driver questionnaire survey:

[0047] For the microscopic state of humans, pedestrian density is defined as its microscopic feature. Optionally, the number of pedestrians in a frame of an image can be further defined as the method for calculating pedestrian density.

[0048] For the micro-state of a vehicle, its own speed, road vehicle density, and road vehicle type are defined as its micro-features. Optionally, the vehicle speed is further defined as calculated in kilometers per hour, the number of vehicles in a frame of an image is defined as the road vehicle density, and the composition of large vehicles, small vehicles, and non-motorized vehicles in a frame of an image is defined as the road vehicle type.

[0049] For the micro-state of a road, road type, number of lanes, and traffic sign density are defined as its micro-features. Optionally, road type refers to the type of road, such as highway, urban arterial road, and urban secondary arterial road; number of lanes refers to the number of drivable lanes; and traffic sign density refers to the number of traffic signs contained in a frame of an image.

[0050] For the micro-state of environment, weather and light conditions are defined as its micro-characteristics. Optionally, weather includes sunny, cloudy, overcast, rainy, foggy, and snowy days, and light conditions refer to the brightness of light.

[0051] The questionnaire for drivers included basic driver information, micro-state, micro-characteristics, and their weights (1-10 points). 56 valid questionnaires were collected offline. Analysis showed that: when the micro-state was human, the factors were pedestrian density (9.8), pedestrian movement direction (8.2), and pedestrian movement speed (8.5); when the micro-state was vehicle, the factors were vehicle speed (9.6), road vehicle density (9.2), road vehicle type (9.3), road vehicle taillight status (8.6), road vehicle speed (8.8), and distance (8.2); when the micro-state was road, the factors were road type (9.2), number of lanes (9.6), traffic sign density (9.3), road curvature radius (8.7), road slope (7.8), and road material (6.5); when the micro-state was environment, the factors were weather (9.8), lighting conditions (9.6), tunnels (9.1), elevated roads (8.3), and backlighting (8.6). Based on the above results, micro-features with a weight of 9 or higher are selected.

[0052] Based on this, micro-feature data of actual driving scenarios are obtained to characterize the micro-states of the corresponding categories, so as to calculate the Boltzmann entropy of the current driving scenario based on the number of micro-states, and realize the quantification of scenario complexity based on Boltzmann entropy.

[0053] Step 102: Obtain each micro-feature data of each type of micro-state in the current driving scenario, and calculate the Boltzmann entropy of the current driving scenario;

[0054] Acquire real-time in-vehicle video, and determine each micro-feature data of each micro-state of the current driving scenario based on each frame of the in-vehicle video.

[0055] Among them, the vehicle-mounted video is the video acquired by an image acquisition device installed in front of the vehicle, so that the video content simulates the driver's field of vision.

[0056] In one feasible implementation, the image acquisition device can be a camera shared with the intelligent driving / assisted driving system, typically mounted at the center of the outer side of the vehicle's windshield.

[0057] In other feasible implementations, the image acquisition device can also be set up independently, for example, installed inside the vehicle and located in front of the driver's seat, so that the shooting range of the image acquisition device can be closer to the driver's field of vision, so as to better quantify the current driving scene based on the driver's driving posture rather than the machine's field of vision.

[0058] Based on the definition of each micro-feature data, each micro-feature data of each micro-state in the current driving scenario is extracted and calculated from each frame of the in-vehicle video. On this basis, the micro-feature data is further discretized into state levels to obtain the Boltzmann state number corresponding to each micro-feature data. Then, the Boltzmann entropy of the current driving scenario is calculated using the Boltzmann entropy calculation formula.

[0059] Step 103: Determine the vehicle head-up display level based on the Boltzmann entropy of the current driving scenario, wherein different vehicle head-up display levels contain different numbers of display elements.

[0060] The calculated Boltzmann entropy of the current driving scenario characterizes the absolute complexity of the current driving scenario. Specifically, when the number of microstates in the current driving scenario is fixed, the Boltzmann entropy value remains unchanged even if the internal state distribution of the system changes. As the number of microstates in the current driving scenario increases, the larger the Boltzmann entropy value, the more complex the current driving environment.

[0061] Based on this, the vehicle head-up display levels are pre-defined, and the number and content of display elements corresponding to each vehicle head-up display level, as well as the Boltzmann entropy range corresponding to each vehicle head-up display level, are determined.

[0062] It is understandable that the larger the starting value of the Boltzmann entropy range corresponding to the normal display level of the vehicle, the more complex the current driving environment of the driver, the fewer the number of display elements, and the more concise the content.

[0063] This invention introduces Boltzmann entropy to quantify the absolute complexity of the current driving scenario, constructs a complete microstate mapping system to extract the number of microstates in the driving scenario, accurately calculates the Boltzmann entropy of the current driving scenario, and determines the corresponding in-vehicle head-up display level based on the Boltzmann entropy of the driving scenario to control the number of display elements and reduce the driving load of the driver in complex scenarios.

[0064] In the in-vehicle head-up display method based on Boltzmann entropy of the present invention, the step of calculating the Boltzmann entropy of the current driving scene specifically includes:

[0065] Based on the road type of the current driving scenario, the weight of each microstate is selected, wherein the mapping relationship between road type and the weight of each microstate is predefined;

[0066] It is understandable that different types of microstates have different impacts on the complexity of driving scenarios in different driving scenarios.

[0067] For example, in the micro-state including people and vehicles, if the current driving scenario is an urban road, the presence of pedestrians on the road has a significant impact on the complexity of the driving scenario and the driver's workload. However, if the current driving scenario is a highway, the probability of pedestrians appearing is greatly reduced, and the impact of vehicles on the complexity of the driving scenario and the driver's workload increases.

[0068] Therefore, the weights of each microstate need to be dynamically adjusted to better suit the current driving scenario. However, it should be noted that if the weights are entirely based on the real-time driving scenario, such as the acquisition and adjustment of real-time in-vehicle video content, the computational requirements will be high, making it difficult to apply to the in-vehicle environment. At the same time, the large amount of computation will also affect the real-time performance of Boltzmann entropy calculation.

[0069] Therefore, in this embodiment, the current driving scenario is characterized by the road type to which the current driving scenario belongs. The weight of each micro-state under each road type is determined in advance, thereby obtaining a mapping relationship table between road type and the weight of each micro-state.

[0070] Based on this, the road type is determined according to the current driving scenario. Then, the weight of each microstate can be queried and selected according to the mapping relationship table to realize the calculation of the weighted microstate number.

[0071] Optionally, the weight of each microstate under each road type can be an empirical value or determined by a machine learning model.

[0072] As a preferred approach, based on the results of driver cognitive experiments, the weight of each micro-feature under each road type is defined, wherein the road types include highways, urban arterial roads, urban secondary arterial roads, rural roads, and tunnels.

[0073] Specifically, this implementation aims to obtain real behavioral and physiological data of drivers by conducting cognitive experiments on them, in order to obtain accurate microstate weights with interpretability.

[0074] In one specific implementation, an eye-tracking experiment is conducted on the driver to perform a cognitive experiment, thereby obtaining the weight of each type of microstate.

[0075] The eye-tracking experiment included scenarios such as highways, urban main roads, urban secondary roads, rural roads, and tunnels, with elements of people, vehicles, roads, and the environment included. By recording and analyzing the eye-tracking data of 31 participants under these conditions, the attention allocation of drivers under different micro-states was obtained, and the following weight matrix was derived:

[0076] .

[0077] Therefore, the mapping relationship constructed from the results of the driver cognitive test is shown in Table 1 below:

[0078] Table 1

[0079]

[0080] Specifically, when the road type is a highway, the weight of people is considered low because highways mainly serve vehicle traffic and there are fewer pedestrians; the weight of vehicles is considered high because the main purpose of highways is efficient vehicle transportation; the weight of roads is considered high because road conditions have a significant impact on the safety and efficiency of vehicle driving; and the weight of the environment is considered moderate because environmental factors such as weather and visibility have an impact on highway traffic, but are not the main factors.

[0081] When the road type is an urban arterial road, the weight of people is considered moderate because there is a large flow of pedestrians and non-motorized vehicles on urban arterial roads; the weight of vehicles is considered high because urban arterial roads are the main channels of urban traffic; the weight of roads is considered moderate because road conditions affect traffic flow; and the weight of the environment is considered low because environmental factors have a relatively small impact on urban arterial roads.

[0082] When the road type is a secondary arterial road in the city, the weight of people is considered to be relatively high because there is a large flow of pedestrians and non-motorized vehicles on secondary arterial roads; the weight of vehicles is considered to be moderate because secondary arterial roads mainly serve the traffic within the region; the weight of roads is considered to be moderate because road conditions affect traffic flow; and the weight of the environment is considered to be moderate because environmental factors have a certain impact on traffic on secondary arterial roads.

[0083] When the road type is rural road, people are considered to have a higher weight because there is a large flow of pedestrians and non-motorized vehicles on rural roads; vehicles are considered to have a moderate weight because rural roads mainly serve the traffic within the region; roads are considered to have a moderate weight because road conditions affect traffic flow; and the environment is considered to have a lower weight because environmental factors have a relatively small impact on rural roads.

[0084] When the road type is a tunnel, the weight of people is considered low because tunnels mainly serve vehicle traffic and there are few pedestrians; the weight of vehicles is considered the highest because the smoothness and safety of tunnel traffic mainly depend on the driving conditions of vehicles; the weight of roads is considered moderate because road conditions have an important impact on the safety and efficiency of vehicle driving; the weight of the environment is considered moderate because environmental factors such as ventilation and lighting have an impact on tunnel traffic.

[0085] By using the above method, a mapping table between road types and weights can be pre-built. Based on real-time in-vehicle video, the current road type can be determined, and the corresponding micro-state weight can be directly selected by looking up the mapping table.

[0086] Based on each micro-feature data of each type of micro-state, determine the Boltzmann entropy state number of each micro-feature data, wherein the mapping relationship between each micro-feature data and the Boltzmann entropy state number is predefined.

[0087] To normalize microscopic feature data at different scales to the same range for Boltzmann entropy calculation, this embodiment predefines a mapping table between each microscopic feature data item and the Boltzmann entropy state number, as shown in Table 2 below:

[0088] Table 2

[0089]

[0090] Specifically, the Boltzmann entropy state number is predefined into levels, and then a mapping relationship is constructed between each micro-feature data and its level. For example, when the pedestrian density is 0, the Boltzmann entropy state number corresponding to the pedestrian density is 1; when the pedestrian density is 1, the Boltzmann entropy state number corresponding to the pedestrian density is 2, and so on. When the pedestrian density is 7, the Boltzmann entropy state number corresponding to the pedestrian density is 6. As another example, when the lighting conditions are good, the corresponding Boltzmann entropy state number is 1. That is, in the third column of Table 2, the Boltzmann entropy state number increases sequentially from 1, from left to right.

[0091] Based on this, after determining the various micro-feature data of the current driving scenario, the Boltzmann entropy state number corresponding to each micro-feature data can be determined.

[0092] In one specific implementation, the road type in Scenario 1 is a highway, and the remaining micro-feature data and their corresponding Boltzmann entropy state numbers are shown in Table 3 below:

[0093] Table 3

[0094]

[0095] Scenario 1 describes a driving scenario where a vehicle is traveling on a highway on a sunny day. There are no pedestrians on the road, the vehicle's speed is between 106 km / h, the road vehicle density is 4 vehicles, the road vehicle types are a mix of small and large vehicles (as shown in Table 2), there are 3 lanes, and the lighting conditions are good.

[0096] The road type in Scenario 2 is a secondary arterial road in the city. The remaining micro-feature data and their corresponding Boltzmann entropy state numbers are shown in Table 4 below:

[0097] Table 4

[0098]

[0099] Scenario 2 describes a driving scenario where a vehicle is traveling on a secondary urban road on a sunny day. There are 3 pedestrians on the road, the vehicle's speed is 45 km / h, the road vehicle density is 7 vehicles, the road vehicle type is small cars, there are 2 lanes, and the lighting conditions are good.

[0100] Calculate the first product of the number of Boltzmann entropy states corresponding to each type of microstate;

[0101] The Boltzmann entropy of the current driving scenario is obtained by weighting the first product of each microstate with the weight of each microstate and calculating the weighted product of all microstates.

[0102] Based on this, the Boltzmann entropy of the current driving scenario can be calculated based on the Boltzmann entropy state number corresponding to the micro-state of the current driving scenario.

[0103] Specifically, the formula for calculating Boltzmann entropy is:

[0104] ;

[0105] In the formula, It is a constant. Let be the number of possible microstates of the system. Therefore, the entropy increases monotonically with the number of states. The larger, S The higher the number of states, the more entropy remains constant. However, when the number of states is fixed, the entropy value remains unchanged. The entropy remains constant, even if the internal state distribution of the system changes.

[0106] because Since it is a constant, to simplify the calculation, the simplified formula for calculating Boltzmann entropy is:

[0107] ;

[0108] Furthermore, to highlight the impact of different categories of microstates on driver load under different driving scenarios, each category of microstates is weighted according to its weight, resulting in the weighted Boltzmann entropy calculation formula:

[0109] ;

[0110] In the formula, Represents the weighted number of microstates. Indicates the product symbol. Indicates the first i Individual microstate data, Indicates the first i The weights corresponding to each micro-feature data point n This represents the total number of micro-feature data.

[0111] Among them, the i-th microstate data It is the first product of the number of Boltzmann entropy states corresponding to each type of microstate.

[0112] Taking scenario one above as an example, the calculated Boltzmann entropy for scenario one is:

[0113] ;

[0114] ;

[0115] That is, the first product of the microstate categories of people, vehicles, roads and environment is 1, 24, 9 and 1 respectively. After weighting each type of microstate as an index, the product of the weighted microstate numbers of all categories is calculated to obtain the final weighted microstate number.

[0116] Taking scenario two above as an example, the Boltzmann entropy of scenario two is calculated as follows:

[0117] ;

[0118] ;

[0119] That is, the first products for the microstate categories of people, vehicles, roads, and environment are 4, 9, 18, and 1, respectively.

[0120] The above method enables the calculation of the Boltzmann entropy of the current driving scenario, so as to determine the HUD display level based on the Boltzmann entropy of the current driving scenario.

[0121] It is important to emphasize that, based on Boltzmann entropy quantization, the absolute complexity of a driving scenario remains unchanged as long as the number of microstates in the scenario remains constant, regardless of how these microstates change. In simpler terms, if the driver's speed remains constant, and the number of vehicles, pedestrians, and / or available lanes in front of the driver remains constant, the entropy value will not change.

[0122] This is because cognitive experiments on drivers show that if the number of vehicles, pedestrians and / or lanes ahead remains constant, even if the state of the vehicles ahead changes, such as deceleration or lane change, the driver's workload remains unchanged. This is because during normal driving, drivers naturally maintain attention to the state of vehicles and pedestrians ahead. When the number of vehicles and pedestrians that need to be monitored remains constant, the driver's workload does not change.

[0123] Based on this, this embodiment selects to introduce Boltzmann entropy into the calculation of driving scenario complexity to characterize the absolute complexity of the driving scenario. By measuring the absolute complexity of the driving scenario, the driver's driving burden in the current scenario is characterized, thereby configuring an appropriate number of HUD display elements for the driver.

[0124] Furthermore, compared to using a neural network model to determine dynamic weights, this implementation selects weights based on road type and calculates entropy values ​​using a lookup table method, reducing reliance on chip computing power and meeting the real-time requirements of the vehicle system.

[0125] In the vehicle head-up display method based on Boltzmann entropy of the present invention, the vehicle head-up display level includes a first level representing low-complexity scenarios, a second level representing medium-complexity scenarios, and a third level representing high-complexity scenarios, and the number of display elements included in the vehicle head-up display level decreases progressively from the first level to the third level.

[0126] In this embodiment, the vehicle's normal display level, i.e., the HUD display level, is divided into three levels, which are the first level, the second level, and the third level, in order of increasing scene complexity. Therefore, from the first level to the third level, the number of display elements contained in each level decreases progressively.

[0127] Specifically, in the first level of display, the display elements contain complete navigation information; in the second level of display, the display elements include simplified secondary information; and in the third level of display, the display elements only include key instructions.

[0128] Specifically, if the calculated Boltzmann entropy is less than or equal to 1.0, the current driving scenario is considered to be at Level 1; if the calculated Boltzmann entropy is greater than 1.0 and less than 1.5, the current driving scenario is considered to be at Level 2; and if the calculated Boltzmann entropy is greater than or equal to 1.5, the current driving scenario is considered to be at Level 3.

[0129] In the vehicle head-up display method based on Boltzmann entropy of this invention, the step of acquiring each micro-feature data of each type of micro-state in the current driving scenario specifically includes:

[0130] Extract the in-vehicle video of the current driving process, wherein the in-vehicle video represents the driver's visual field environment;

[0131] Extract image frames from the vehicle video and use an object detection model to detect the target bounding boxes corresponding to people, vehicles and road signs in each image frame;

[0132] Based on the detection results of the target detection model, each micro-feature data of each micro-state in the current driving scenario is determined.

[0133] Extract the in-vehicle video stream of the current driving process. In this embodiment, the video stream resolution is 1280×70 and the frame rate is 30fps. Extract continuous frame images and in-vehicle sensor data, including vehicle speed and GPS location.

[0134] It is understandable that the content of in-vehicle video is considered to represent the driver's visual field environment, that is, the absolute complexity in the image frames of in-vehicle video reflects the driver's driving burden.

[0135] A lightweight object detection model (such as YOLOv8-tiny) is used to detect vehicles, pedestrians, and traffic signs in real-time extracted image frames. The model outputs information such as the bounding box coordinates, category, and confidence level of the identified targets, and retains the bounding boxes of targets with a confidence level ≥ 0.5. Data such as vehicle, pedestrian, and traffic sign data are calculated for each frame, and based on this, pedestrian density Pt, pedestrian distance Dt, road vehicle density Nt, type composition Tt, number of lanes Lt, and traffic sign density Mt are calculated. Road type Rt and vehicle speed St are obtained from Beidou positioning information, and weather information Et is obtained from location information network queries. Light conditions Bt are obtained from light sensors.

[0136] Understandably, when the defined microscopic feature data are different, different sensing devices or detection models can be selected, and the corresponding settings and calculations can be performed.

[0137] The following describes the vehicle head-up display system based on Boltzmann entropy provided by the present invention. The vehicle head-up display system based on Boltzmann entropy described below can be referred to in correspondence with the vehicle head-up display method based on Boltzmann entropy described above.

[0138] like Figure 2 As shown, the vehicle head-up display system based on Boltzmann entropy of the present invention includes an acquisition module 201, a determination module 202 and a display module 203;

[0139] The acquisition module 201 is used to acquire each micro-feature data of each type of micro-state in the current driving scenario, and calculate the Boltzmann entropy of the current driving scenario.

[0140] Acquire real-time in-vehicle video, and determine each micro-feature data of each micro-state of the current driving scenario based on each frame of the in-vehicle video.

[0141] Among them, the vehicle-mounted video is the video acquired by an image acquisition device installed in front of the vehicle, so that the video content simulates the driver's field of vision.

[0142] In one feasible implementation, the image acquisition device can be a camera shared with the intelligent driving / assisted driving system, typically mounted at the center of the outer side of the vehicle's windshield.

[0143] In other feasible implementations, the image acquisition device can also be set up independently, for example, installed inside the vehicle and located in front of the driver's seat, so that the shooting range of the image acquisition device can be closer to the driver's field of vision, so as to better quantify the current driving scene based on the driver's driving posture rather than the machine's field of vision.

[0144] Based on the definition of each micro-feature data, each micro-feature data of each micro-state in the current driving scenario is extracted and calculated from each frame of the in-vehicle video. On this basis, the micro-feature data is further discretized into state levels to obtain the Boltzmann state number corresponding to each micro-feature data. Then, the Boltzmann entropy of the current driving scenario is calculated using the Boltzmann entropy calculation formula.

[0145] The determining module 202 is used to determine the vehicle head-up display level based on the Boltzmann entropy of the current driving scenario;

[0146] The calculated Boltzmann entropy of the current driving scenario characterizes the absolute complexity of the current driving scenario. Specifically, when the number of microstates in the current driving scenario is fixed, the Boltzmann entropy value remains unchanged even if the internal state distribution of the system changes. As the number of microstates in the current driving scenario increases, the larger the Boltzmann entropy value, the more complex the current driving environment.

[0147] Based on this, the vehicle head-up display levels are pre-defined, and the number and content of display elements corresponding to each vehicle head-up display level, as well as the Boltzmann entropy range corresponding to each vehicle head-up display level, are determined.

[0148] It is understandable that the larger the starting value of the Boltzmann entropy range corresponding to the normal display level of the vehicle, the more complex the current driving environment of the driver, the fewer the number of display elements, and the more concise the content.

[0149] This invention introduces Boltzmann entropy to quantify the absolute complexity of the current driving scenario, constructs a complete microstate mapping system to extract the number of microstates in the driving scenario, accurately calculates the Boltzmann entropy of the current driving scenario, and determines the corresponding in-vehicle head-up display level based on the Boltzmann entropy of the driving scenario to control the number of display elements and reduce the driving load of the driver in complex scenarios.

[0150] Display module 203 is used to adjust and display display elements according to the determined vehicle head-up display level.

[0151] Optionally, the display module includes a HUD display, which projects and displays the number of display elements according to a determined vehicle normal display level.

[0152] The vehicle's normal display level, i.e., the HUD display level, is divided into three levels, in order of increasing scene complexity: Level 1, Level 2, and Level 3. Therefore, from Level 1 to Level 3, the number of display elements contained in each level decreases progressively.

[0153] Specifically, in the first level of display, the display elements contain complete navigation information; in the second level of display, the display elements include simplified secondary information; and in the third level of display, the display elements only include key instructions.

[0154] Specifically, if the calculated Boltzmann entropy is less than or equal to 1.0, the current driving scenario is considered to be at Level 1; if the calculated Boltzmann entropy is greater than 1.0 and less than 1.5, the current driving scenario is considered to be at Level 2; and if the calculated Boltzmann entropy is greater than or equal to 1.5, the current driving scenario is considered to be at Level 3.

[0155] Figure 3 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3 As shown, the electronic device may include a processor 310, a communication interface 320, a memory 330, and a communication bus 340. The processor 310, communication interface 320, and memory 330 communicate with each other via the communication bus 340. The processor 310 can call logical instructions in the memory 330 to execute a Boltzmann entropy-based in-vehicle head-up display method. This method includes: mapping a driving scene into several micro-states and defining quantifiable data indicators for each micro-state as micro-features; acquiring micro-feature data for each micro-state of the current driving scene and calculating the Boltzmann entropy of the current driving scene; and determining the in-vehicle head-up display level based on the Boltzmann entropy of the current driving scene, wherein different in-vehicle head-up display levels contain different numbers of display elements.

[0156] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0157] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the in-vehicle head-up display method based on Boltzmann entropy provided by the above methods. The method includes: mapping a driving scene into several types of microstates and defining quantifiable data indicators for each type of microstate as micro-features of each type of microstate; acquiring micro-feature data for each type of microstate in the current driving scene and calculating the Boltzmann entropy of the current driving scene; and determining the in-vehicle head-up display level based on the Boltzmann entropy of the current driving scene, wherein different in-vehicle head-up display levels contain different numbers of display elements.

[0158] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the in-vehicle head-up display method based on Boltzmann entropy provided by the above methods. This method includes: mapping a driving scene into several classes of microstates, and defining quantifiable data indicators for each class of microstates as micro-features of each class of microstates; acquiring micro-feature data for each class of microstates in the current driving scene, and calculating the Boltzmann entropy of the current driving scene; determining the in-vehicle head-up display level based on the Boltzmann entropy of the current driving scene, wherein different in-vehicle head-up display levels contain different numbers of display elements.

[0159] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0160] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0161] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention 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; and these 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 the present invention.

Claims

1. A vehicle-mounted head-up display method based on Boltzmann entropy, characterized in that, include: The driving scenario is mapped into several micro-states, and quantifiable data indicators for each micro-state are defined as micro-features of each micro-state. The micro-states are defined as four categories: people, vehicles, roads, and environment. Then, the micro-features corresponding to each micro-state and their quantification methods are defined respectively. Obtain the micro-feature data of each micro-state in the current driving scenario, and calculate the Boltzmann entropy of the current driving scenario; The vehicle head-up display level is determined based on the Boltzmann entropy of the current driving scenario, wherein different vehicle head-up display levels contain different numbers of display elements; The step of calculating the Boltzmann entropy of the current driving scenario specifically includes: Based on the road type of the current driving scenario, the weight of each microstate is selected, wherein the mapping relationship between road type and the weight of each microstate is predefined; Based on each micro-feature data of each type of micro-state, determine the Boltzmann entropy state number of each micro-feature data, wherein the mapping relationship between each micro-feature data and the Boltzmann entropy state number is predefined. Calculate the first product of the number of Boltzmann entropy states corresponding to each type of microstate; The Boltzmann entropy of the current driving scenario is obtained by weighting the first product of each microstate with the weight of each microstate and calculating the weighted product of all microstates.

2. The vehicle head-up display method based on Boltzmann entropy according to claim 1, characterized in that, Before the step of selecting the weight of each micro-feature based on the road type of the current driving scenario, the method further includes: Based on the results of a cognitive experiment on drivers, the weight of each micro-feature under each road type is defined, wherein the road types include highways, urban arterial roads, urban secondary arterial roads, rural roads and tunnels.

3. The in-vehicle head-up display method based on Boltzmann entropy according to claim 1, characterized in that, The vehicle head-up display levels include a first level representing low-complexity scenarios, a second level representing medium-complexity scenarios, and a third level representing high-complexity scenarios. From the first level to the third level, the number of display elements included in the vehicle head-up display level decreases progressively.

4. The vehicle head-up display method based on Boltzmann entropy according to claim 1, characterized in that, The step of obtaining each micro-feature data of each type of micro-state in the current driving scenario specifically includes: Extract the in-vehicle video of the current driving process, wherein the in-vehicle video represents the driver's visual field environment; Extract image frames from the vehicle video and use an object detection model to detect the target bounding boxes corresponding to people, vehicles and road signs in each image frame; Based on the detection results of the target detection model, each micro-feature data of each micro-state in the current driving scenario is determined.

5. A vehicle-mounted head-up display system based on Boltzmann entropy, characterized in that, The method for implementing the vehicle head-up display based on Boltzmann entropy as described in any one of claims 1-4 includes: The acquisition module is used to acquire each micro-feature data of each type of micro-state in the current driving scenario and calculate the Boltzmann entropy of the current driving scenario. The determination module is used to determine the vehicle head-up display level based on the Boltzmann entropy of the current driving scenario; The display module is used to adjust and display display elements according to the determined vehicle head-up display level.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the in-vehicle head-up display method based on Boltzmann entropy as described in any one of claims 1 to 4.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the vehicle head-up display method based on Boltzmann entropy as described in any one of claims 1 to 4.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the vehicle head-up display method based on Boltzmann entropy as described in any one of claims 1 to 4.

Images