A high-speed assisted driving control method and system combined with weather conditions

Abstract

The present invention provides a high-speed assisted driving control method and system combined with weather conditions. The method includes: identifying the visual detection result A by recognizing the vehicle's front wide-angle image information, identifying the visual detection result B by recognizing the vehicle's front narrow-angle image information, and identifying the millimeter-wave radar information to obtain the radar detection result C; obtaining the current weather type and the severity of each type of weather; combining the confidence levels, target categories, and distances of the visual detection results A and B for information fusion to obtain the visual target fusion result D; adjusting the target fusion confidence level according to the visual target fusion result D, the target detection result C, and the weather conditions to obtain the fused target E; and outputting vehicle lateral and longitudinal control commands in combination with the fused target E and the vehicle's driving state. The present invention satisfies high-quality target screening in different weather conditions, adaptively adjusts the vehicle lateral and longitudinal control of the NOA driving system in bad weather in combination with the vehicle's driving state and road environment, and has better control performance.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving, and more specifically, to a high-speed assisted driving control method, system, electronic device and storage medium combined with weather conditions. Background Art

[0002] With the rapid popularization of intelligent driving functions and the continuous growth of user needs, more and more intelligent vehicles are gradually liberating the driver's feet and hands to complete the lateral and longitudinal assisted driving operations of the vehicle. However, most autonomous driving vehicles have poor high-speed assisted driving control performance in bad weather, mainly because the target recognition effect of sensors is poor, resulting in poor vehicle control performance. Summary of the Invention

[0003] In view of the technical problems existing in the prior art, the present invention provides a high-speed assisted driving control method, system, electronic device and storage medium combined with weather conditions, which can meet the high-quality target screening under different weather types, and adaptively adjust the lateral and longitudinal control of the vehicle of the NOA (High-Speed Navigation Assistant) driving system in bad weather in combination with the driving state of the vehicle itself and the road environment, and the vehicle control performance is better.

[0004] According to a first aspect of the present invention, there is provided a high-speed assisted driving control method combined with weather conditions, including:

[0005] Identifying the forward wide-angle image information of the vehicle to obtain a visual detection result A, identifying the forward narrow-angle image information of the vehicle to obtain a visual detection result B, and identifying the millimeter-wave radar information to obtain a radar detection result C; obtaining the current weather type and the severity of each type of weather;

[0006] Combining the confidence levels, target categories and distances of the visual detection result A and the visual detection result B for information fusion to obtain a visual target fusion result D; adjusting the target fusion confidence level according to the visual target fusion result D, the target detection result C, the weather type and the weather severity, and performing fusion decision-making to obtain a fusion target E;

[0007] Combining the fusion target E and the driving state of the vehicle itself, and outputting vehicle lateral and longitudinal control instructions.

[0008] On the basis of the above technical solutions, the present invention can also be improved as follows.

[0009] Optionally, the identifying the forward wide-angle image information of the vehicle to obtain a visual detection result A, identifying the forward narrow-angle image information of the vehicle to obtain a visual detection result B, and identifying the millimeter-wave radar information to obtain a radar detection result C includes:

[0010] Obtain the front view wide-angle image information of the vehicle, extract and identify the features of the wide-angle image information, and calculate to obtain the visual detection result A. The visual detection result A includes at least the type and distance of the long-distance target;

[0011] Obtain the front view narrow-angle image information of the vehicle, extract and identify the features of the narrow-angle image information, and calculate to obtain the visual detection result B. The visual detection result B includes at least the type and distance of the close-range target;

[0012] Obtain the millimeter wave radar information in front of the vehicle, identify the millimeter wave radar information, and obtain the target detection result C. The target detection result C includes at least the distance, speed, and azimuth information of the target.

[0013] Optionally, the obtaining of the current weather type and the severity of each type of weather includes:

[0014] Identify the front view wide-angle image information and / or the front view narrow-angle image information of the vehicle, determine the current weather type as normal, snow, or fog weather according to the image quality diagnosis result, and is also used to judge the level of the severity of the snow and / or fog weather;

[0015] Determine the current weather as normal or rainy weather according to the rain sensor and / or the wiper frequency data of the vehicle, and judge the level of the severity of the rainy weather.

[0016] Optionally, the combining of the confidence levels, target categories, and distances of the visual detection results A and B for information fusion to obtain the visual target fusion result D includes:

[0017] Adaptive adjust the output thresholds of the targets in the visual detection result A and the visual detection result B respectively according to the longitudinal distances of the targets in the visual detection result A and the longitudinal distances of the targets in the visual detection result B, and adjust the targets in the visual detection result A and the visual detection result B to the same distance through the respective output thresholds:

[0018] Compare the confidence levels of the visual detection result A and the visual detection result B, and output the one with the higher confidence level as the visual target fusion result D;

[0019] If only one of the visual detection result A or the visual detection result B has a target, output the visual detection result corresponding to this target as the visual target fusion result D.

[0020] Optionally, the adjusting of the target fusion confidence level according to the visual target fusion result D, the target detection result C, the weather type, and the weather severity, and making a fusion decision to obtain the fusion target E includes:

[0021] Determine whether the current weather type is normal weather or bad weather, where the bad weather includes one or more of rainy days, snowy days, or foggy days;

[0022] If the current weather is normal weather, adaptively increase the confidence level of the visual target fusion result D, decrease the confidence level of the target detection result C, and perform target fusion to obtain the fusion target E corresponding to the current weather;

[0023] If the current weather is bad weather, then determine the severity of the bad weather, and adaptively decrease the confidence level of the visual target fusion result D, increase the confidence level of the target detection result C, and perform target fusion according to the severity level of the bad weather to obtain the fusion target E corresponding to the current weather.

[0024] Optionally, combining the fusion target E and the driving state of the host vehicle to output vehicle longitudinal and lateral control commands, including:

[0025] Judge whether the curvature radius of the front lane is less than the radius threshold according to the fusion target E:

[0026] If the curvature radius of the front lane is less than the radius threshold, adaptively adjust the safe driving speed for the curve according to the curve curvature radius;

[0027] If the curvature radius of the front lane is not less than the radius threshold, then judge whether there is a driving vehicle ahead according to the fusion target E:

[0028] If there is no driving vehicle ahead, adopt the adaptive target fusion method to increase the set safe time interval for vehicle driving;

[0029] If there is a driving vehicle ahead, increase the safe time interval for vehicle driving and preferentially adopt the driving trajectory of the vehicle ahead as the tracking path of the host vehicle.

[0030] Optionally, the wide-angle image information is obtained through the vehicle front-view wide-angle camera, and the narrow-angle image information is obtained through the vehicle front-view narrow-angle camera.

[0031] According to the second aspect of the present invention, there is provided a high-speed assisted driving control system combined with weather conditions, including:

[0032] An information extraction module, which identifies the visual detection result A from the vehicle front-view wide-angle image information, identifies the visual detection result B from the vehicle front-view narrow-angle image information, and identifies the radar detection result C from the millimeter-wave radar information; obtains the current weather type and the severity of each type of weather;

[0033] The target fusion module combines the confidence levels, target categories, and distances of visual detection results A and B for information fusion to obtain the visual target fusion result D; based on the visual target fusion result D, the target detection result C, the weather type, and the weather severity, it adjusts the target fusion confidence level and makes a fusion decision to obtain the fused target E;

[0034] The control decision module combines the fused target E and the self-vehicle driving state to output vehicle lateral and longitudinal control commands.

[0035] According to the third aspect of the present invention, there is provided an electronic device including a memory and a processor, and when the processor executes a computer management program stored in the memory, it implements the steps of the above-mentioned high-speed assisted driving control method combined with weather conditions.

[0036] According to the fourth aspect of the present invention, there is provided a computer-readable storage medium having a computer management program stored thereon, and when the computer management program is executed by a processor, it implements the steps of the above-mentioned high-speed assisted driving control method combined with weather conditions.

[0037] The high-speed assisted driving control method, system, electronic device, and storage medium combined with weather conditions provided by the present invention use a front-view wide-angle camera, a narrow-angle camera, and a forward millimeter-wave radar to respectively output information on road obstacles ahead, and then adaptively adjust the target confidence fusion strategies of multiple sensors in combination with different weather conditions. At the same time, it considers the target output result, weather condition, and self-vehicle driving state to adjust the high-speed assisted driving control logic and parameters. The present invention meets the requirements of high-quality target screening under different weather types, and adaptively adjusts the lateral and longitudinal control of the vehicle in the NOA (high-speed navigation assistance) driving system in bad weather in combination with the self-vehicle driving state and road environment, and the vehicle control performance is better. Description of the Drawings

[0038] Figure 1 It is a flowchart of a high-speed assisted driving control method combined with weather conditions provided by the present invention;

[0039] Figure 2 It is a flowchart of the vehicle control decision-making of the NOA driving system in combination with the target detection result corresponding to the current weather and the self-vehicle driving state;

[0040] Figure 3 It is a structural diagram of a high-speed assisted driving control system combined with weather conditions provided by the present invention;

[0041] Figure 4 It is a schematic hardware structure diagram of a possible electronic device provided by the present invention;

[0042] Figure 5Hardware structure schematic diagram of a possible computer-readable storage medium provided by the present invention. Detailed implementation manners

[0043] The following will further describe in detail the specific implementation manners of the present invention in conjunction with the accompanying drawings and embodiments. The following embodiments are used to illustrate the present invention, but are not used to limit the scope of the present invention.

[0044] Figure 1 Flowchart of a high-speed assisted driving control method combined with weather conditions provided by the present invention. As Figure 1 shown, the method includes:

[0045] Identifying the vehicle's forward wide-angle image information to obtain a visual detection result A, identifying the vehicle's forward narrow-angle image information to obtain a visual detection result B, and identifying the millimeter-wave radar information to obtain a radar detection result C; obtaining the current weather type and the severity of each type of weather;

[0046] Combining the confidence levels, target categories, and distances of the visual detection result A and the visual detection result B for information fusion to obtain a visual target fusion result D; adjusting the target fusion confidence level according to the visual target fusion result D, the target detection result C, the weather type, and the weather severity, and performing fusion decision-making to obtain a fused target E;

[0047] Combining the fused target E and the self-vehicle driving state to output vehicle lateral and longitudinal control commands.

[0048] It can be understood that based on the defects in the background technology, the embodiments of the present invention propose a high-speed assisted driving control method combined with weather conditions. This method uses the wide-angle image information collected by the forward wide-angle camera, the narrow-angle image information collected by the narrow-angle camera, and the millimeter-wave radar information collected by the forward millimeter-wave radar to respectively output the information of the road obstacles ahead, and then adaptively adjusts the multi-sensor target confidence fusion strategy according to different weather conditions. At the same time, considering the target output result, the weather condition, and the self-vehicle driving state to adjust the high-speed assisted driving control logic and parameters. The method of this embodiment meets the high-quality target screening under different weather types, and adaptively adjusts the lateral and longitudinal control of the vehicle in the NOA (High-Speed Navigation Assistance) driving system in bad weather in combination with the self-vehicle driving state and the road environment, and the vehicle control performance is better.

[0049] In a possible embodiment, the step of identifying the vehicle's forward wide-angle image information to obtain a visual detection result A, identifying the vehicle's forward narrow-angle image information to obtain a visual detection result B, and identifying the millimeter-wave radar information to obtain a radar detection result C includes:

[0050] Obtain the forward wide-angle image information of the vehicle, extract and identify the features of the wide-angle image information, and calculate to obtain a visual detection result A, where the visual detection result A includes at least the type and distance of a long-distance target;

[0051] Obtain the forward narrow-angle image information of the vehicle, extract and identify the features of the narrow-angle image information, and calculate to obtain a visual detection result B, where the visual detection result B includes at least the type and distance of a short-distance target;

[0052] Obtain the forward millimeter-wave radar information of the vehicle, identify the millimeter-wave radar information, and obtain a target detection result C, where the target detection result C includes at least the distance, speed, and azimuth information of the target.

[0053] It can be understood that in this embodiment, the forward wide-angle image information of the vehicle contains targets in a relatively large range and at a relatively long distance in front of the vehicle. By performing image recognition on it, information about more possible targets in front of the vehicle can be obtained. The forward narrow-angle image information of the vehicle contains targets in a relatively small range and at a relatively short distance in front of the vehicle. By performing image recognition on it, more clear feature information of the targets in front of the vehicle can be obtained. In subsequent steps, by combining the detection results of the wide-angle image information and the narrow-angle image information for visual detection target fusion, the accuracy of the visual detection result can be improved. The millimeter-wave radar mainly performs millimeter-level electromagnetic wave scanning on the forward environment of the vehicle and detects parameters such as the distance, speed, and azimuth information of the detected target. Since the detection penetration of the millimeter-wave radar is relatively strong and it is less affected by weather such as light compared to visual detection, it can form a complement with image visual detection to increase the accuracy of environmental detection during autonomous driving. Data is collected through three sensors, namely a forward wide-angle camera, a forward narrow-angle camera, and a forward millimeter-wave radar. On the one hand, the use cost of a high-performance single sensor can be reduced, and on the other hand, the demand for high-precision detection of all-weather and full-scene targets can be met.

[0054] In a possible embodiment, the obtaining of the current weather type and the severity of each type of weather includes:

[0055] Identify the forward wide-angle image information and / or the forward narrow-angle image information of the vehicle, and determine that the current weather type is normal, snowy, or foggy weather according to the image quality diagnosis result, and it is also used to judge the level of the severity of the snowy and / or foggy weather;

[0056] Determine that the current weather is normal or rainy weather according to the rain sensor and / or the wiper frequency data of the vehicle, and judge the level of the severity of the rainy weather.

[0057] It can be understood that the weather can be roughly divided into normal weather and bad weather. For normal weather such as sunny days and cloudy days, the vehicle can obtain relatively accurate target detection results. For bad weather, such as rain, snow, and fog, it has a greater impact on visibility. Especially for snow and fog weather, it can directly affect the clarity of the images obtained by image recognition. Therefore, by diagnosing the quality of the images obtained through visual detection (such as image clarity, the number of noise points in the image, etc.), it is possible to determine whether the current weather is snow or fog weather; it is also possible to further judge the severity level of the snow or fog weather according to the image quality. Since the impact of rainy days on air visibility is less than that of snow and fog weather, the impact of rainy days on image clarity is not very large. In order to obtain more accurate weather detection results, the judgment of rainy days is carried out through a rain sensor and / or the activity frequency of the windshield wiper, which improves the detection accuracy on the one hand and realizes sensor reuse on the other hand, saving the computing power of the system.

[0058] In a possible embodiment, as shown in the process Figure 1 shown, the confidence levels, target categories, and distances of visual detection result A and visual detection result B are combined for information fusion to obtain visual target fusion result D; it includes:

[0059] The output thresholds of the targets in visual detection result A and visual detection result B are adaptively adjusted respectively according to the longitudinal distances of the targets in visual detection result A and visual detection result B, and the targets in visual detection result A and visual detection result B are adjusted to the same distance through the respective output thresholds:

[0060] Compare the confidence levels of visual detection result A and visual detection result B, and output the one with the higher confidence level as visual target fusion result D;

[0061] If only one of visual detection result A or visual detection result B has a target, output the visual detection result corresponding to this target as visual target fusion result D.

[0062] It can be understood that by adjusting the distances of the detection targets in visual detection result A and visual detection result B, then judging whether the detected targets in the two detection results are the same target, and obtaining visual target fusion result D through the confidence levels of visual detection result A and visual detection result B, the accuracy of visual detection is further improved.

[0063] In a possible embodiment, in step S2, the target fusion confidence level is adjusted according to visual target fusion result D, target detection result C, weather type, and weather severity, and a fusion decision is made to obtain fusion target E; it includes:

[0064] Determine whether the current weather type is normal weather or severe weather, where the severe weather includes one or more of rainy days, snowy days, or foggy days;

[0065] If the current weather is normal weather, adaptively increase the confidence level of the visual target fusion result D, decrease the confidence level of the target detection result C, and perform target fusion to obtain the fusion target E corresponding to the current weather;

[0066] If the current weather is severe weather, then determine the severity of the severe weather, and adaptively decrease the confidence level of the visual target fusion result D, increase the confidence level of the target detection result C, and perform target fusion according to the severity level of the severe weather to obtain the fusion target E corresponding to the current weather.

[0067] It can be understood that in this embodiment, the multi-sensor fusion decision makes a decision based on information such as the confidence levels, target categories, distances, etc. of the visual detection results A, visual detection results B, and target detection results C, and combines the weather conditions to output the visual target fusion result D information. If the high-speed assisted driving function is enabled in normal weather, the target fusion is performed according to the strategy of mainly relying on visual detection (for example, outputting the visual target when the visual detection confidence level > 98%) and supplementing with radar detection (for example, outputting the radar target when the radar detection confidence level > 95%); if it is in a severe weather state, at this time, the visual detection result may be inaccurate, while the radar detection result is less affected by the weather, so the target fusion is performed in the way of taking vision as the supplement and radar as the main.

[0068] More specifically, during the process of performing target fusion in the way of taking vision as the supplement and radar as the main, adaptively adjust the fusion confidence levels of the visual detection results A, visual detection results B, and target detection results C according to information such as the severity of the severe weather and the longitudinal distance of the target. Examples of the longitudinal distance and confidence level are shown in Table 1. As mentioned above, the visual detection results A and visual detection results B both belong to the visual detection targets. Adaptively adjust the output threshold of the target detection result according to the longitudinal distance, and the visual target fusion outputs the visual target fusion result D based on whether the visual detection results A and visual detection results B are in the same position: if the targets in the visual detection results A and visual detection results B are in the same position, then select the target with the higher confidence level as the visual detection fusion target D, otherwise directly assign the visual detection result of the single target to the visual detection fusion target D.

[0069] Table 1

[0070] Longitudinal distance 10 30 60 100 140 200 Confidence level 95％ 97％ 99％ 95％ 96％ 90％

[0071] The visual detection fuses target D and the target detection result C, and performs multi-sensor fusion according to the severity of different weather conditions to make a decision and output the fusion target E corresponding to the current weather. For example, in bad weather, the visual detection result highly depends on the light condition. At this time, the confidence level of its fusion target can be appropriately reduced, while the millimeter-wave radar is less affected by the weather environment. At this time, the confidence level of the target C output by the millimeter-wave radar is preferentially increased. The adjustment strategy of the severity of bad weather and the confidence level of the fusion target type can be referred to Table 2.

[0072] Table 2

[0073] Severe weather level / Fusion target type Vision Millimeter wave Level I 95％ 90％ Level II 90％ 93％ Level III 85％ 95％

[0074] In a possible embodiment, as shown in the process Figure 2 shown, the vehicle lateral and longitudinal control commands are output by combining the fusion target E and the driving state of the vehicle itself, including:

[0075] Judge whether the curvature radius of the front lane is less than the radius threshold according to the fusion target E:

[0076] If the curvature radius of the front lane is less than the radius threshold, the safe driving speed of the curve is adaptively adjusted according to the curve curvature radius;

[0077] If the curvature radius of the front lane is not less than the radius threshold, judge whether there is a driving vehicle in front according to the fusion target E:

[0078] If there is no driving vehicle in front, the adaptive target fusion method is used to increase the safe time distance set for vehicle driving;

[0079] If there is a driving vehicle in front, increase the safe time distance of vehicle driving and preferentially use the driving trajectory of the vehicle in front as the following path of the vehicle itself.

[0080] It can be understood that in this embodiment, the NOA assisted driving system can adaptively adjust the lateral and longitudinal control of the vehicle in bad weather according to the fusion target E corresponding to the current weather output by multi-sensor fusion and the driving state of the vehicle itself, so as to improve the accuracy of vehicle control and the safety of autonomous driving.

[0081] Figure 3 For the structural diagram of a high-speed assisted driving control system combining weather conditions provided by the embodiment of the present invention, as Figure 3 shown, a high-speed assisted driving control system combining weather conditions includes an information extraction module 301, a target fusion module 302, and a control decision module 303, where:

[0082] An information extraction module 301 is configured to identify the vehicle front view wide-angle image information to obtain a visual detection result A, identify the vehicle front view narrow-angle image information to obtain a visual detection result B, and identify the millimeter wave radar information to obtain a radar detection result C; obtain the current weather type and the severity of each type of weather;

[0083] A target fusion module 302 is configured to perform information fusion by combining the confidence levels, target categories, and distances of the visual detection result A and the visual detection result B to obtain a visual target fusion result D; adjust the target fusion confidence level according to the visual target fusion result D, the target detection result C, the weather type, and the weather severity, and perform a fusion decision to obtain a fusion target E;

[0084] A control decision module 303 is configured to output vehicle longitudinal and lateral control instructions by combining the fusion target E and the self-vehicle driving state.

[0085] It can be understood that a high-speed assisted driving control system combining weather conditions provided by the present invention corresponds to the high-speed assisted driving control method combining weather conditions provided in the foregoing embodiments. The relevant technical features of the high-speed assisted driving control system combining weather conditions can refer to the relevant technical features of the high-speed assisted driving control method combining weather conditions, and will not be elaborated herein.

[0086] Please refer to Figure 4 , Figure 4 which is a schematic diagram of an embodiment of an electronic device provided by an embodiment of the present invention. As Figure 4 shown, an embodiment of the present invention provides an electronic device 400, including a memory 410, a processor 420, and a computer program 411 stored in the memory 410 and executable on the processor 420. When the processor 420 executes the computer program 411, the following steps are implemented:

[0087] Identify the vehicle front view wide-angle image information to obtain a visual detection result A, identify the vehicle front view narrow-angle image information to obtain a visual detection result B, and identify the millimeter wave radar information to obtain a radar detection result C; obtain the current weather type and the severity of each type of weather;

[0088] Combine the confidence levels, target categories, and distances of the visual detection result A and the visual detection result B to perform information fusion to obtain a visual target fusion result D; adjust the target fusion confidence level according to the visual target fusion result D, the target detection result C, the weather type, and the weather severity, and perform a fusion decision to obtain a fusion target E;

[0089] Combine the fusion target E and the self-vehicle driving state to output vehicle longitudinal and lateral control instructions.

[0090] Please refer to Figure 5 , Figure 5Schematic diagram of an embodiment of a computer-readable storage medium provided by the present invention. As Figure 5 shown, this embodiment provides a computer-readable storage medium 500, on which a computer program 511 is stored. When the computer program 511 is executed by a processor, the following steps are implemented:

[0091] Identify the vehicle front view wide-angle image information to obtain the visual detection result A, identify the vehicle front view narrow-angle image information to obtain the visual detection result B, and identify the millimeter-wave radar information to obtain the radar detection result C; obtain the current weather type and the severity of each type of weather;

[0092] Combine the confidence levels, target categories, and distances of the visual detection result A and the visual detection result B for information fusion to obtain the visual target fusion result D; adjust the target fusion confidence level according to the visual target fusion result D, the target detection result C, the weather type, and the weather severity, and perform fusion decision-making to obtain the fusion target E;

[0093] Combine the fusion target E and the driving state of the vehicle itself to output vehicle lateral and longitudinal control commands.

[0094] A high-speed assisted driving control method, system, and storage medium that combine weather conditions provided by the embodiments of the present invention. This method uses a front view wide-angle camera, a narrow-angle camera, and a forward millimeter-wave radar to respectively output information about road obstacles ahead, and then adaptively adjusts the multi-sensor target confidence fusion strategy according to different weather conditions. At the same time, it considers the target output result, weather conditions, and the driving state of the vehicle itself to adjust the high-speed assisted driving control logic and parameters. The present invention meets the requirements of high-quality target screening under different weather types, combines the driving state of the vehicle itself and the road environment to adaptively adjust the lateral and longitudinal control of the vehicle by the NOA (High-Speed Navigation Assistant) driving system in bad weather, and the vehicle control performance is better.

[0095] It should be noted that in the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0096] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0097] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices produce a means for implementing the functions specified in one or more flows and / or one or more blocks in the flow Figure 1 one or more flows and / or blocks Figure 1 or a means for implementing the functions specified in one or more blocks.

[0098] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction means that implements the functions specified in one or more flows and / or one or more blocks in the flow Figure 1 one or more flows and / or blocks Figure 1 or a means for implementing the functions specified in one or more blocks.

[0099] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more flows and / or one or more blocks in the flow Figure 1 one or more flows and / or blocks Figure 1 or a means for implementing the functions specified in one or more blocks.

[0100] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present invention.

[0101] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A high-speed assisted driving control method combined with weather conditions, characterized in that, Including: Identifying the visual detection result A from the vehicle's forward wide-angle image information, identifying the visual detection result B from the vehicle's forward narrow-angle image information, and identifying the millimeter-wave radar information to obtain the radar detection result C; Obtaining the current weather type and the severity of each type of weather; Combining the confidence levels, target categories, and distances of the visual detection result A and the visual detection result B for information fusion to obtain the visual target fusion result D; Adjusting the target fusion confidence level based on the visual target fusion result D, the target detection result C, the weather type, and the weather severity, and making a fusion decision to obtain the fusion target E; Combining the fusion target E and the driving state of the host vehicle to output the vehicle's longitudinal and lateral control commands; The combining the confidence levels, target categories, and distances of the visual detection result A and the visual detection result B for information fusion to obtain the visual target fusion result D includes: Adapting and adjusting the output thresholds of the targets in the visual detection result A and the visual detection result B respectively according to the longitudinal distances of the targets in the visual detection result A and the longitudinal distances of the targets in the visual detection result B, and adjusting the targets in the visual detection result A and the visual detection result B to the same distance through the respective output thresholds: Comparing the confidence levels of the visual detection result A and the visual detection result B, and outputting the one with the higher confidence level as the visual target fusion result D; If only one of the visual detection result A or the visual detection result B has a target, then output the visual detection result corresponding to this target as the visual target fusion result D.

2. The high-speed assisted driving control method combined with weather conditions according to claim 1, wherein The identifying the visual detection result A from the vehicle's forward wide-angle image information, identifying the visual detection result B from the vehicle's forward narrow-angle image information, and identifying the millimeter-wave radar information to obtain the radar detection result C includes: Obtaining the vehicle's forward wide-angle image information, performing feature extraction and recognition on the wide-angle image information, and calculating to obtain the visual detection result A, where the visual detection result A includes at least the type and distance of a long-distance target; Obtaining the vehicle's forward narrow-angle image information, performing feature extraction and recognition on the narrow-angle image information, and calculating to obtain the visual detection result B, where the visual detection result B includes at least the type and distance of a short-distance target; Obtaining the millimeter-wave radar information in front of the vehicle, performing recognition on the millimeter-wave radar information to obtain the target detection result C, where the target detection result C includes at least the distance, speed, and azimuth information of the target.

3. The high-speed assisted driving control method combined with weather conditions according to claim 1, characterized in that, The obtaining the current weather type and the severity of each type of weather includes: Identifying the vehicle's forward wide-angle image information and / or forward narrow-angle image information, determining the current weather type as normal, snow, or fog weather according to the image quality diagnosis result, and also used to judge the severity level of the snow and / or fog weather; Determining the current weather as normal or rainy weather according to the vehicle's rain sensor and / or wiper frequency data, and judging the severity level of the rainy weather.

4. The high-speed assisted driving control method combined with weather conditions according to claim 1, wherein The adjusting the target fusion confidence level based on the visual target fusion result D, the target detection result C, the weather type, and the weather severity, and making a fusion decision to obtain the fusion target E includes: Determine whether the current weather type is normal weather or bad weather, where the bad weather includes one or more of rainy days, snowy days, or foggy days; If the current weather is normal weather, adaptively increase the confidence level of the visual target fusion result D, decrease the confidence level of the target detection result C, and perform target fusion to obtain the fusion target E corresponding to the current weather; If the current weather is bad weather, then determine the severity of the bad weather, and adaptively decrease the confidence level of the visual target fusion result D, increase the confidence level of the target detection result C, and perform target fusion according to the severity level of the bad weather to obtain the fusion target E corresponding to the current weather.

5. The high-speed assisted driving control method combined with weather conditions according to claim 1, wherein, The wide-angle image information is obtained through the vehicle's front-view wide-angle camera, and the narrow-angle image information is obtained through the vehicle's front-view narrow-angle camera.

6. A high-speed assisted driving control system combined with weather conditions, characterized in that, It includes: An information extraction module that identifies the visual detection result A from the vehicle's front-view wide-angle image information, identifies the visual detection result B from the vehicle's front-view narrow-angle image information, and identifies the radar detection result C from the millimeter-wave radar information; Obtain the current weather type and the severity of each type of weather; A target fusion module that combines the confidence levels, target categories, and distances of the visual detection result A and the visual detection result B to perform information fusion and obtain the visual target fusion result D; Adjust the target fusion confidence level according to the visual target fusion result D, the target detection result C, the weather type, and the weather severity, and make a fusion decision to obtain the fusion target E; A control decision module that combines the fusion target E and the driving state of the vehicle itself and outputs vehicle longitudinal and lateral control commands; The combining of the confidence levels, target categories, and distances of the visual detection result A and the visual detection result B to perform information fusion and obtain the visual target fusion result D includes: Adapting and adjusting the output thresholds of the targets in the visual detection result A and the visual detection result B respectively according to the longitudinal distances of the targets in the visual detection result A and the longitudinal distances of the targets in the visual detection result B, and adjusting the targets in the visual detection result A and the visual detection result B to the same distance through the respective output thresholds: Compare the confidence levels of the visual detection result A and the visual detection result B, and output the one with the higher confidence level as the visual target fusion result D; If only one of the visual detection result A or the visual detection result B has a target, then output the visual detection result corresponding to this target as the visual target fusion result D.

7. An electronic device, characterized in that, It includes a memory and a processor, and when the processor executes the computer management program stored in the memory, it implements the steps of a high-speed assisted driving control method combining weather conditions as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, It stores a computer management program, and when the computer management program is executed by the processor, it implements the steps of a high-speed assisted driving control method combining weather conditions as described in any one of claims 1-5.

Images