Following distance adjustment method and apparatus, in-vehicle computing device, and vehicle

Abstract

The present application relates to the technical field of intelligent driving, and provides a method and apparatus for adjusting a following distance of a vehicle, an in-vehicle computing device, and a vehicle, used for adaptively adjusting a following distance on the basis of the specific conditions of a driving environment. The method in the present application comprises: obtaining contour completeness and contour clarity of a target in front of an ego vehicle on the basis of a forward-facing image of the ego vehicle; obtaining a target visual distance level of the ego vehicle on the basis of the contour completeness and contour clarity of said target; determining a target following gear to which the target visual distance level belongs; and on the basis of the target following gear and the current following gear of the ego vehicle, adjusting the current following distance of the ego vehicle.

Description

Following distance adjustment methods, devices, on-board computing equipment, and vehicles Cross-references to related applications This application claims priority to Chinese Patent Application No. 2024118214634, filed on December 11, 2024, entitled “Method, Apparatus, On-board Computing Device and Vehicle for Adjusting Following Distance”, the entire contents of which are incorporated herein by reference. Technical Field

[0001] This application relates to, but is not limited to, the field of intelligent driving technology, and in particular to a method, apparatus, on-board computing device, vehicle, storage medium, and computer program product for adjusting following distance. Background Technology

[0002] When the vehicle is in intelligent driving mode, it can automatically determine the following distance relative to the vehicle in front using the onboard vision system, and follow the vehicle in front accordingly. Summary of the Invention

[0003] The following is an overview of the subject matter described in detail herein. This overview is not intended to limit the scope of the claims.

[0004] This application provides a method for adjusting the following distance of a vehicle, the method comprising: obtaining the completeness and clarity of the outline of a forward target based on a forward-facing image of the vehicle; obtaining the target visibility distance level of the vehicle based on the completeness and clarity of the forward target outline; determining the target following gear to which the target visibility distance level belongs; and adjusting the current following distance of the vehicle based on the target following gear and the current following gear of the vehicle.

[0005] In one embodiment, adjusting the current following distance of the vehicle based on the target following gear and the current following gear of the vehicle includes: if the target following gear is higher than the current following gear of the vehicle, then increasing the current following distance of the vehicle; the increased current following distance is within the following distance range corresponding to the target following gear.

[0006] In one embodiment, adjusting the current following distance of the vehicle based on the target following gear and the current following gear of the vehicle includes: if the target following gear is equal to the current following gear, obtaining a set of visibility distance levels corresponding to the target following gear; determining the gear-level within the target visibility distance level based on the set of visibility distance levels and the target visibility distance level; if the gear-level within the gear is not the lowest level within the gear, increasing the current following distance of the vehicle; the increased current following distance is within the following distance range corresponding to the current following gear.

[0007] In one embodiment, if the gear level is not the lowest gear level, increasing the current following distance of the vehicle includes: if the gear level is not the lowest gear level, determining a first increase ratio based on the gear level; the higher the gear level, the larger the first increase ratio; and increasing the current following distance of the vehicle based on the first increase ratio.

[0008] In one embodiment, increasing the current following distance of the vehicle includes: determining a second increase ratio based on the vehicle's current environmental data; wherein the current environmental data indicates that the more the current environment interferes with the vehicle's onboard vision, the greater the second increase ratio; and increasing the vehicle's current following distance based on the second increase ratio.

[0009] In one embodiment, obtaining the target visibility distance level of the vehicle based on the completeness of the target outline and the clarity of the target outline includes: obtaining a first visibility distance level based on the completeness of the target outline; obtaining a second visibility distance level based on the clarity of the target outline; and obtaining the target visibility distance level of the vehicle based on the first visibility distance level and the second visibility distance level.

[0010] In one embodiment, obtaining the target visibility level of the vehicle based on the first visibility level and the second visibility level includes: obtaining a first confidence level based on the completeness of the target outline in front; obtaining a second confidence level based on the clarity of the target outline in front; determining a first weight and a second weight based on the relative magnitude between the first confidence level and the second confidence level; and performing a weighted summation of the first visibility level and the second visibility level according to the first weight and the second weight to obtain the target visibility level of the vehicle.

[0011] In one embodiment, obtaining the target visibility distance level of the vehicle based on the completeness and sharpness of the target outline in front includes: performing a weighted summation of the completeness and sharpness of the target outline in front to obtain a target outline evaluation value for the vehicle in front; determining the target outline evaluation value interval to which the target outline evaluation value of the vehicle in front belongs; and determining the visibility distance level associated with the target outline evaluation value interval as the target visibility distance level of the vehicle in front, based on the correlation between the target outline evaluation value interval and the visibility distance level.

[0012] In one embodiment, obtaining the completeness of the front target contour based on the forward-facing image of the vehicle includes: locating the target in the forward-facing image to determine the front target in the forward-facing image; converting the forward-facing image from a color image to a black-and-white binary image; determining the minimum envelope of the front target in the binary image; determining the number of pixels in the minimum envelope as a first number of pixels; filling the minimum envelope to obtain a minimum envelope without missing pixels; determining the number of pixels in the minimum envelope without missing pixels as a second number of pixels; determining the ratio of the first number of pixels to the second number of pixels as the ratio of the number of pixels in the envelope of the forward-facing image; and obtaining the completeness of the front target contour based on the ratio of the number of pixels in the envelope.

[0013] In one embodiment, obtaining the sharpness of the forward target outline based on the forward image of the vehicle includes: performing target localization on the forward image to determine the forward target in the forward image; converting the forward image from a color image to a black-and-white binary image; determining the outline of the forward target in the binary image and using the outline as the forward target outline; obtaining the grayscale gradient values ​​of each point on the forward target outline; and averaging the grayscale gradient values ​​of each point to obtain the sharpness of the forward target outline.

[0014] This application provides a vehicle following distance adjustment device, the device comprising: a contour processing module, a visibility distance level determination module, a target following gear determination module, and a following distance adjustment module.

[0015] The contour processing module is used to obtain the completeness and clarity of the front target contour based on the forward image of the vehicle.

[0016] The visibility distance level determination module is used to determine the target visibility distance level of the vehicle based on the completeness and clarity of the target outline in front.

[0017] The target following gear determination module is used to determine the target following gear to which the target visibility distance level belongs.

[0018] The following distance adjustment module is used to adjust the current following distance of the vehicle based on the target following gear and the current following gear of the vehicle.

[0019] This application provides an in-vehicle computing device, including a memory and a processor, wherein the memory stores a computer program and the processor executes the above-described method.

[0020] This application provides a vehicle that includes an on-board computing device as described in the above embodiments.

[0021] This application provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor using the methods described above.

[0022] This application provides a computer program product having a computer program stored thereon, the computer program being executed by a processor using the above-described method. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. The drawings are used to provide a further understanding of the technical solutions of this application and constitute a part of the specification. They are used together with the embodiments of this application to explain the technical solutions of this application and do not constitute a limitation on the technical solutions of this application.

[0024] Figure 1 is a flowchart illustrating a method for adjusting following distance in one embodiment.

[0025] Figure 2 is a flowchart illustrating the process of determining the integrity of the outline of a target in front in one embodiment.

[0026] Figure 3 is a flowchart illustrating the process of determining the sharpness of the outline of a target in front in one embodiment.

[0027] Figure 4 is a structural block diagram of a following distance adjustment device in one embodiment.

[0028] Figure 5 is an internal structure diagram of an in-vehicle computing device in one embodiment. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0030] In driving environments with poor visibility, such as nighttime, heavy rain, dense fog, or severe sandstorms, it is difficult to adaptively adjust the following distance according to the specific driving conditions, which poses certain safety risks.

[0031] The following distance adjustment method provided in this application can be executed by an onboard computing device. The onboard computing device is a device with computing capabilities installed in the vehicle. While driving, the user can activate the intelligent driving mode, in which the following distance can be adaptively adjusted using the method provided in this application.

[0032] The method may include steps S101-S104 as shown in Figure 1.

[0033] Step S101: Based on the forward image of the vehicle, obtain the completeness of the forward target outline and the clarity of the forward target outline.

[0034] During vehicle operation, the vehicle's onboard vision system, including the image acquisition device, can acquire images of the forward field of view, which can be referred to as forward-facing images. After acquiring at least one frame of the forward-facing image, contour analysis can be performed on the forward-facing image to obtain the completeness and sharpness of the forward-facing target contour. The forward-facing targets include, but are not limited to, vehicles ahead of the vehicle (which can be simply referred to as the "front vehicle") and road signs.

[0035] The specific processing steps for contour analysis of the forward image to obtain the completeness of the foreground target contour can include steps S201-S208 as shown in Figure 2. Step S201: Target localization is performed on the forward image to determine the foreground target. Step S202: The forward image is converted from a color image to a black-and-white binary image. Step S203: The minimum envelope of the foreground target in the binary image is determined. This minimum envelope may be discontinuous or missing due to visual blur. Step S204: The number of pixels in this minimum envelope is determined as the first number of pixels. Step S205: The minimum envelope is filled to obtain a minimum envelope without missing pixels. Step S206: The number of pixels in the minimum envelope without missing pixels is determined as the second number of pixels. Step S207: The ratio of the first number of pixels to the second number of pixels is determined as the ratio of the number of pixels in the envelope of the forward image. Step S208: The completeness of the foreground target contour is obtained based on the ratio of the number of pixels in the envelope.

[0036] In some scenarios, to ensure the accuracy of the assessment of the completeness of the foreground target contour, the above processing method can be used to process multiple frames of forward images, obtain the ratio of the number of pixels in the envelope of each frame, and then statistically analyze the ratio of the number of pixels in the envelope of the multiple frames to obtain the completeness of the foreground target contour. The statistical method can include, but is not limited to, averaging.

[0037] The specific processing steps for contour analysis of the forward image to obtain the sharpness of the foreground target contour can include steps S301-S305 shown in Figure 3. Step S301: Target localization is performed on the forward image to determine the foreground target. Step S302: The forward image is converted from a color image to a black-and-white binary image. Step S303: The contour of the foreground target in the binary image is determined, and this contour is taken as the foreground target contour. Step S304: The grayscale gradient values ​​of each point on the foreground target contour are obtained. Step S305: The grayscale gradient values ​​of each point are averaged to obtain the sharpness of the foreground target contour.

[0038] When obtaining the grayscale gradient values ​​of each point on the target contour, grayscale gradient operators can be used for processing. Grayscale gradient operators include, but are not limited to: Roberts gradient operator, Sobel gradient operator, Prewitt gradient operator, and Laplacian gradient operator.

[0039] Step S102: Based on the completeness and clarity of the target outline in front, the target visibility distance level of this vehicle is obtained.

[0040] Multiple visibility levels can be pre-defined, and the number of visibility levels can be an integer multiple of the number of following gears; for example, if there are 5 following gears, then 5 visibility levels, or 10 visibility levels, or 15 visibility levels can be defined.

[0041] The lower the following gear, the shorter the following distance. For example, with five following gears, the first gear has the shortest following distance, and the fifth gear has the longest. Correspondingly, the lower the visibility level, the longer the visibility distance can be set; for example, with 15 visibility levels, the first visibility level has the longest visibility distance, and the fifteenth visibility level has the shortest.

[0042] For example, with 5 following gears, after 15 visibility distance levels are calibrated, the following gears and visibility distance levels can be associated sequentially in ascending order of gear, thereby obtaining the association relationship between the following gears and visibility distance levels.

[0043] For example, the visibility levels associated with the first following gear include: the first visibility level, the second visibility level, and the third visibility level; the visibility levels associated with the second following gear include: the fourth visibility level, the fifth visibility level, and the sixth visibility level; the visibility levels associated with the third following gear include: the seventh visibility level, the eighth visibility level, and the ninth visibility level; the visibility levels associated with the fourth following gear include: the tenth visibility level, the eleventh visibility level, and the twelfth visibility level; and the visibility levels associated with the fifth following gear include: the thirteenth visibility level, the fourteenth visibility level, and the fifteenth visibility level.

[0044] After obtaining the completeness and clarity of the target outline in front, a weighted sum can be made between the completeness and clarity of the target outline in front to obtain the target outline evaluation value of the vehicle (which can also be simply referred to as the target outline evaluation value). Based on the target outline evaluation value of the vehicle, the target visibility distance level of the vehicle is determined.

[0045] When determining the target visibility level of the vehicle using this method, the pre-preparation phase may include the following steps: obtaining several forward contour evaluation value intervals; ensuring the number of forward contour evaluation value intervals matches the number of visibility levels; and associating the forward contour evaluation value intervals with the visibility levels. For example, with 15 visibility levels, the contour evaluation value scores can be divided from 0 to 100, resulting in 15 forward contour evaluation value intervals; in descending order, the largest forward contour evaluation value interval is designated as the first forward contour evaluation value interval, and the smallest forward contour evaluation value interval is designated as the fifteenth forward contour evaluation value interval; the first forward contour evaluation interval is associated with the first visibility level, the second forward contour evaluation interval is associated with the second visibility level, and so on, until the fifteenth forward contour evaluation interval is associated with the fifteenth visibility level. After association, the relationship between the forward contour evaluation value intervals and the visibility levels can be obtained.

[0046] When determining the target visibility distance level of a vehicle based on its front profile assessment value, the specific steps may include: determining the front profile assessment value range to which the vehicle's front profile assessment value belongs; determining the visibility distance level associated with the front profile assessment value range based on the correlation between the front profile assessment value range and the visibility distance level; and determining the visibility distance level as the target visibility distance level of the vehicle.

[0047] Step S103: Determine the target following gear to which the target visibility distance level belongs.

[0048] After determining the target visibility level, the following gear associated with the target visibility level can be determined based on the relationship between the following gear and the visibility level, and this following gear can be used as the target following gear.

[0049] Taking 5 following gears and 15 visibility levels as an example: If the target visibility level is the eighth visibility level, based on the relationship between the following gear and the visibility level, the following gear associated with the target visibility level can be determined as the third following gear, and the third following gear can be used as the target following gear.

[0050] Step S104: Adjust the current following distance of the vehicle according to the target following gear and the current following gear of the vehicle.

[0051] After obtaining the target following gear and the current following gear of the vehicle, the relative height between the target following gear and the current following gear can be used to determine whether to adjust the current following distance of the vehicle.

[0052] Specifically, when the target following gear is lower than the current following gear, it means the following distance corresponding to the target gear is shorter, while the following distance corresponding to the current gear is longer. In this case, without shortening the following distance, the current following gear does not need to be adjusted to the target gear, and the current following distance remains unchanged. When the target following gear is higher than the current following gear, it means the following distance corresponding to the target gear is longer, while the current following distance is shorter. In this case, the current following gear can be adjusted to the target gear, increasing the current following distance. When the target following gear is equal to the current following gear, it means the following distance corresponding to the target gear is consistent with the following distance corresponding to the current gear. In this case, the current following distance does not need to be adjusted, or it can be slightly adjusted, ensuring the adjusted current following distance remains within the range corresponding to the current following gear.

[0053] In the above-mentioned method for adjusting the following distance of a vehicle, after obtaining the forward image of the vehicle, the completeness and clarity of the forward target outline can be obtained based on the forward image. The completeness and clarity of the forward target outline in the forward image can reflect the visibility distance of the vehicle in the current driving environment. Therefore, this application uses the completeness and clarity of the forward target outline in the forward image to obtain the target visibility distance level of the vehicle. Based on the current following gear of the vehicle and the target following gear to which the target visibility distance level belongs, the current following distance of the vehicle is adjusted to achieve adaptive adjustment of the current following distance according to the specific driving environment, thereby reducing safety risks.

[0054] In one embodiment, adjusting the current following distance of the vehicle based on the target following gear and the current following gear of the vehicle includes: if the target following gear is higher than the current following gear of the vehicle, then increasing the current following distance of the vehicle; the increased current following distance is within the following distance range corresponding to the target following gear.

[0055] When the target following gear is higher than the current following gear, it means that the following distance corresponding to the target following gear is longer, while the following distance corresponding to the current following gear is shorter. If you continue driving in the current following gear, there is a risk of collision. Therefore, you can adjust the current following gear to the target following gear to increase the current following distance. The increased current following distance will be within the following distance range corresponding to the target following gear.

[0056] For example, if the current following gear of this vehicle is the third following gear and the target following gear is the fifth following gear, the current following gear can be adjusted to the fifth following gear, and the current following distance of this vehicle can be increased. The increased current following distance is within the following distance range corresponding to the fifth following gear.

[0057] In this embodiment, when the target following gear is higher than the current following gear of the vehicle, the following distance corresponding to the target following gear is longer, while the following distance corresponding to the current following gear is shorter. Adjusting the current following gear to the target following gear increases the current following distance of the vehicle, which can reduce the risk of collision and further improve driving safety.

[0058] In one embodiment, adjusting the current following distance of the vehicle based on the target following gear and the current following gear of the vehicle includes: if the target following gear is equal to the current following gear, obtaining a set of visibility distance levels corresponding to the target following gear; determining the gear-level within the target visibility distance level based on the set of visibility distance levels and the target visibility distance level; if the gear-level within the gear is not the lowest level within the gear, increasing the current following distance of the vehicle; the increased current following distance is within the following distance range corresponding to the current following gear.

[0059] When the target following gear is equal to the current following gear of the vehicle, it means that the following distance corresponding to the target following gear is consistent with the following distance corresponding to the current following gear. At this time, the current following distance of the vehicle can be finely adjusted.

[0060] The following description uses the example of 5 following gears, 15 visibility distance levels, and the current following gear of this vehicle as the third following gear.

[0061] If the target visibility level is the eighth visibility level, then based on the correlation between the following gear and the visibility level, the target following gear can be determined to be the third following gear. The target following gear is equal to the current following gear of the vehicle. In this case, the visibility level set corresponding to the target following gear is obtained, that is, the visibility level set corresponding to the third following gear is obtained. The visibility level set includes: the seventh visibility level, the eighth visibility level, and the ninth visibility level. The seventh visibility level is the lowest level in this visibility level set and is the lowest level within the gear. The eighth visibility level is the middle level in this visibility level set and is the middle level within the gear. The ninth visibility level is the highest level in this visibility level set and is the highest level within the gear. The non-lowest levels within the gear include the middle levels and the highest levels within the gear.

[0062] The target visibility level is the eighth visibility level, which is the middle level within the gear, meaning it is not the lowest level within the gear.

[0063] When the current following gear of this vehicle is the third following gear, the default visibility level is the lowest visibility level in the gear, that is, the default visibility level is the seventh visibility level.

[0064] Since the target visibility level is the eighth visibility level, which is higher than the default visibility level, the current following distance of this vehicle can be slightly increased. The increased current following distance is within the following distance range corresponding to the third following gear.

[0065] In this embodiment, when the target following gear is equal to the current following gear of the vehicle, if the target visibility level is not the lowest level within the gear, it means that the current visibility of the vehicle has not reached the optimal visibility of the current following gear. The current following distance of the vehicle can be slightly increased. The increased current following distance is within the following distance range corresponding to the third following gear, further reducing the risk of collision and further improving driving safety.

[0066] In one embodiment, if the gear level is not the lowest level within the gear, increasing the current following distance of the vehicle includes: if the gear level is not the lowest level within the gear, determining a first increase ratio based on the gear level; the higher the gear level, the larger the first increase ratio; and increasing the current following distance of the vehicle based on the first increase ratio.

[0067] Using the example above as an example, in the example above, the target following gear and the current following gear of the vehicle are both the third following gear, and the target visibility level is the eighth visibility level.

[0068] If each following gear corresponds to a set of visibility distance levels including three visibility distance levels, then the middle level within the gear can be associated with a first proportional value, and the highest level within the gear can be associated with a second proportional value, thus obtaining the relationship between the levels and proportional values ​​within the gear. The first proportional value is less than the second proportional value; for example, the first proportional value can be set to 110%, and the second proportional value to 120%. In the visibility distance level set corresponding to the third following gear, the eighth visibility distance level is the middle level within the gear. Based on the relationship between the levels and proportional values ​​within the gear, the proportional value associated with the eighth visibility distance level can be determined as the first proportional value, which can then be used as the first increase proportional value. For example, if the first proportional value is 110%, then the first increase proportional value is 110%, at which point the following distance can be increased to 110% of the current following distance of the vehicle.

[0069] Different first and second ratio values ​​can be set for different vehicle models. At this time, different vehicle models have their own correlation between the gear level and the ratio value. Based on the vehicle model, the correlation relationship matching the vehicle model can be determined from the pre-built correlation relationships between the gear level and the ratio value of multiple vehicle models. Based on the correlation relationship, the first ratio value associated with the eighth visibility distance level can be determined. Then, the first ratio value can be used as the first increase ratio, and the current following distance of the vehicle can be increased by the first increase ratio.

[0070] In this embodiment, if the target visibility distance level is not the lowest level within the gear, the lower the target visibility distance level is within the gear, the closer the current visibility of the vehicle is to the optimal visibility of the current following gear. The smaller the first increase ratio, the smaller the increase in the current following distance of the vehicle. This reduces the risk of collision while allowing for more precise adjustment of the following distance.

[0071] In one embodiment, increasing the current following distance of the vehicle includes: determining a second increase ratio based on the current environmental data of the vehicle; the current environmental data indicates that the more the current environment interferes with the vehicle's onboard vision, the larger the second increase ratio; and increasing the current following distance of the vehicle based on the second increase ratio.

[0072] The current environmental data of this vehicle may include, but is not limited to: the current weather data of the area where this vehicle is driving and the current environmental data of the area surrounding this vehicle.

[0073] The methods for obtaining current weather data for the area where this vehicle is traveling may include: obtaining current weather data for the area where this vehicle is traveling via this vehicle, the Internet, and the vehicle's location signal.

[0074] There are three ways to obtain current data about the environment around the vehicle.

[0075] 1. Based on the vehicle's sunlight and rain sensor, the current brightness and rainfall of the surrounding environment can be obtained.

[0076] 2. Based on the vehicle's temperature and humidity sensors, the current temperature and humidity of the surrounding environment can be obtained.

[0077] 3. Based on the vehicle's PM2.5 environmental sensor, the current particulate matter content in the surrounding environment can be obtained.

[0078] By using the current brightness and rainfall of the surrounding environment, it can be determined whether the vehicle is driving at night or in heavy rain.

[0079] By using the clarity of the outline of the target ahead, the current rainfall, temperature, and humidity of the surrounding environment, it can be determined whether the vehicle is driving in dense fog. Specifically, if the clarity of the target ahead is below a threshold, the current rainfall is below a threshold, the current humidity is above a threshold, and the current temperature is within a certain range, then it can be determined that the vehicle is driving in dense fog.

[0080] By using the current particulate matter concentration and humidity levels in the vehicle's surroundings, it can be determined whether the vehicle is operating in a sandstorm environment. Specifically, if the current particulate matter concentration is above a threshold and the current humidity is below a threshold, it can be determined that the vehicle is operating in a sandstorm environment.

[0081] After obtaining the vehicle's current environmental data, if the current environmental data indicates that the environment interferes more with the vehicle's onboard vision, such as heavy rain, darkness, dense fog, or sandstorms, the value of the second increment ratio will be larger accordingly. After obtaining the second increment ratio, the vehicle's current following distance can be increased by the second increment ratio.

[0082] The following distance is increased by the second increase ratio, and the specific handling process can be described in several cases.

[0083] Scenario 1: When the target following gear is higher than the current following gear, the current following gear can be adjusted to the target following gear. First, increase the current following distance to the minimum following distance corresponding to the target following gear, and then increase the minimum following distance corresponding to the target following gear by the second increase ratio. The increased minimum following distance corresponding to the target following gear is within the range of the target following gear. The increased minimum following distance corresponding to the target following gear can be set as the target following distance. Control the vehicle to travel at the target following distance.

[0084] Scenario 2: When the target following gear is equal to the current following gear of the vehicle, the current following distance of the vehicle can be increased directly according to the second increase ratio. The increased current following distance is within the following distance range corresponding to the current following gear. The increased current following distance can be set as the target following distance. The vehicle can then be controlled to travel at the target following distance.

[0085] Scenario 3: When the target following gear is equal to the current following gear of the vehicle and the first increase ratio is determined, the current following distance of the vehicle can be increased by the first increase ratio to obtain the intermediate following distance; the intermediate following distance can be increased by the second increase ratio to obtain the target following distance, which is within the following distance range corresponding to the current following gear; the vehicle can be controlled to travel at the target following distance.

[0086] In this embodiment, the current environmental data of the vehicle indicates that the more the current environment interferes with the vehicle's onboard vision, the larger the second increase ratio becomes. Increasing the current following distance of the vehicle according to the second increase ratio can further reduce the risk of collision and improve driving safety in special weather conditions such as heavy rain and fog.

[0087] In one embodiment, obtaining the target visibility distance level of the vehicle based on the completeness and clarity of the target outline in front includes: obtaining a first visibility distance level based on the completeness of the target outline in front; obtaining a second visibility distance level based on the clarity of the target outline in front; and obtaining the target visibility distance level of the vehicle based on the first visibility distance level and the second visibility distance level.

[0088] After obtaining the completeness and sharpness of the target outline in front, a first visibility level can be determined based on the completeness of the target outline; a second visibility level can be determined based on the sharpness of the target outline. Based on the first and second visibility levels, the target visibility level of this vehicle is obtained.

[0089] When using this method to determine the target visibility level of the vehicle, the pre-preparation phase may include the following steps:

[0090] Obtain several foreground target outline integrity intervals; the number of foreground target outline integrity intervals should be consistent with the number of viewing distance levels; associate the foreground target outline integrity intervals with the viewing distance levels. For example, with 15 viewing distance levels, the integrity can be divided from 0 to 100%, resulting in 15 foreground target outline integrity intervals; in descending order, the 15 foreground target outline integrity intervals are designated as follows: the largest foreground target outline integrity interval is designated as the first foreground target outline integrity interval, and the smallest foreground target outline integrity interval is designated as the fifteenth foreground target outline integrity interval; the first foreground target outline integrity interval is associated with the first viewing distance level, the second foreground target outline integrity interval is associated with the second viewing distance level, and so on, until the fifteenth foreground target outline integrity interval is associated with the fifteenth viewing distance level. After association, the relationship between the foreground target outline integrity intervals and the viewing distance levels can be obtained.

[0091] Obtain several target outline sharpness intervals; the number of target outline sharpness intervals should match the number of viewing distance levels; associate the target outline sharpness intervals with the viewing distance levels. For example, with 15 viewing distance levels, the sharpness can be divided from 0 to 100%, resulting in 15 target outline sharpness intervals; in descending order, the 15 target outline sharpness intervals are designated as follows: the largest interval is designated as the first, and the smallest interval as the fifteenth; the first interval is associated with the first viewing distance level, the second with the second, and so on, until the fifteenth interval is associated with the fifteenth viewing distance level. After association, the relationship between the target outline sharpness intervals and the viewing distance levels can be obtained.

[0092] When determining the first visibility distance level based on the completeness of the target outline in front, the specific steps may include: determining the completeness range of the target outline in front of the vehicle; determining the visibility distance level associated with the target outline completeness range in front based on the correlation between the target outline completeness range and the visibility distance level; and determining the visibility distance level as the first visibility distance level.

[0093] When determining the second visibility distance level based on the sharpness of the target outline in front, the specific steps may include: determining the target outline sharpness interval to which the vehicle's target outline sharpness belongs; determining the visibility distance level associated with the target outline sharpness interval based on the correlation between the target outline sharpness interval and the visibility distance level; and determining the visibility distance level as the second visibility distance level.

[0094] After obtaining the first and second visibility levels, two pre-configured weights can be obtained. The first and second visibility levels are then weighted and summed according to these two weights to obtain the target visibility level of the vehicle.

[0095] In this embodiment, two visibility distance levels are obtained based on the completeness of the target outline and the clarity of the target outline. Combining these two visibility distance levels can yield a more accurate target visibility distance level, thereby further reducing the risk of collision and improving driving safety.

[0096] In one embodiment, obtaining the target visibility level of the vehicle based on a first visibility level and a second visibility level includes: obtaining a first confidence level based on the completeness of the target outline in front; obtaining a second confidence level based on the clarity of the target outline in front; determining a first weight and a second weight based on the relative magnitude between the first confidence level and the second confidence level; and performing a weighted summation of the first visibility level and the second visibility level according to the first weight and the second weight to obtain the target visibility level of the vehicle.

[0097] After obtaining the forward image, contour analysis can be performed on it to obtain the completeness of the forward target contour. To determine the confidence level of the completeness of the forward target contour, the following steps can be performed:

[0098] The target pattern is acquired, and its outline is processed to reduce its outline completeness to a set level. The outline-deficient target pattern is then pasted onto the forward image, and the forward image is further processed for outline analysis to obtain the outline completeness of the target pattern and the outline completeness of the target pattern. The confidence level of the outline completeness of the target pattern is obtained based on the difference between the obtained outline completeness of the target pattern and the set outline completeness. The smaller the difference, the higher the confidence level.

[0099] After obtaining the confidence level of the completeness of the target outline, this confidence level can be called the first confidence level.

[0100] After obtaining the forward image, contour analysis can be performed on it to obtain the sharpness of the foreground target contour. To determine the confidence level of the foreground target contour sharpness, the following steps can be performed:

[0101] The target pattern is acquired, and its outline is blurred to reduce its sharpness to a set level. The blurred target pattern is then pasted onto the forward image, and the forward image is subjected to outline analysis to obtain the sharpness of the target outline and the sharpness of the target pattern. The confidence level of the target outline is obtained based on the difference between the obtained sharpness of the target pattern and the set sharpness; the smaller the difference, the higher the confidence level.

[0102] After obtaining the confidence level of the sharpness of the target outline, this confidence level can be called the second confidence level.

[0103] After obtaining the first confidence level and the second confidence level, the first weight and the second weight are determined based on the relative size between the first confidence level and the second confidence level. If the first confidence level is greater than the second confidence level, the maximum value of the two values ​​can be determined as the first weight and the minimum value of the two values ​​as the second weight. If the first confidence level is less than the second confidence level, the minimum value of the two values ​​can be determined as the first weight and the maximum value of the two values ​​as the second weight.

[0104] Multiply the first weight by the first visibility distance level; the resulting product is called the first product. Multiply the second weight by the second visibility distance level; the resulting product is called the second product. The sum of the first and second product results is used to obtain the target visibility distance level for this vehicle.

[0105] In this embodiment, the matching weight is determined based on the confidence level of the completeness of the target outline and the relative magnitude of the sharpness of the target outline. This weight is used to perform a weighted summation of the first visibility distance level and the second visibility distance level, thereby obtaining a more accurate target visibility distance level, further reducing the risk of collision and improving driving safety.

[0106] In the solution provided in this application, when the current following gear or current following distance of the vehicle is adjusted, the user can be notified by voice that the following status of the vehicle has changed. In addition, the user can be informed of the reason for the change based on the current environmental data of the vehicle. For example, because the vehicle is currently driving in a certain special weather, the current following distance is adjusted to ensure driving safety, thereby avoiding user tension caused by the change in the following status of the vehicle.

[0107] In addition, in the solution provided in this application, when adjusting the current following distance, if the user intervenes, the following distance requested by the user can be given the highest priority, and the following distance can be maintained according to the following distance requested by the user.

[0108] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0109] Based on the same inventive concept, this application also provides a vehicle following distance adjustment device. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more vehicle following distance adjustment device embodiments provided below can be found in the limitations of the vehicle following distance adjustment method described above, and will not be repeated here.

[0110] In one embodiment, as shown in FIG4, a vehicle following distance adjustment device is provided, including: a contour processing module 401, a visibility distance level determination module 402, a target following gear determination module 403, and a following distance adjustment module 404.

[0111] The contour processing module 401 is used to obtain the completeness and clarity of the front target contour based on the forward image of the vehicle.

[0112] The visibility distance level determination module 402 is used to obtain the target visibility distance level of the vehicle based on the completeness of the target outline and the clarity of the target outline.

[0113] The target following gear determination module 403 is used to determine the target following gear to which the target visibility distance level belongs.

[0114] The following distance adjustment module 404 is used to adjust the current following distance of the vehicle according to the target following gear and the current following gear of the vehicle.

[0115] In one embodiment, the following distance adjustment module 404 is further configured to: if the target following gear is higher than the current following gear of the vehicle, increase the current following distance of the vehicle; the increased current following distance is within the following distance range corresponding to the target following gear.

[0116] In one embodiment, the following distance adjustment module 404 is further configured to: if the target following gear is equal to the current following gear, obtain a set of visible distance levels corresponding to the target following gear; determine the gear level of the target visible distance level based on the set of visible distance levels and the target visible distance level; if the gear level is not the lowest gear level, increase the current following distance of the vehicle; the increased current following distance is within the following distance range corresponding to the current following gear.

[0117] In one embodiment, the following distance adjustment module 404 is further configured to: if the gear level is not the lowest level within the gear, determine a first increase ratio based on the gear level; the higher the gear level, the greater the first increase ratio; and increase the current following distance of the vehicle based on the first increase ratio.

[0118] In one embodiment, the following distance adjustment module 404 is further configured to: determine a second increase ratio based on the current environmental data of the vehicle; wherein the current environmental data indicates that the more the current environment interferes with the vehicle's onboard vision, the greater the second increase ratio; and increase the current following distance of the vehicle based on the second increase ratio.

[0119] In one embodiment, the visibility distance level determination module 402 is further configured to: obtain a first visibility distance level based on the completeness of the outline of the target in front; obtain a second visibility distance level based on the clarity of the outline of the target in front; and obtain the target visibility distance level of the vehicle based on the first visibility distance level and the second visibility distance level.

[0120] In one embodiment, the visibility distance level determination module 402 is further configured to: obtain a first confidence level based on the confidence level of the completeness of the target outline in front; obtain a second confidence level based on the confidence level of the clarity of the target outline in front; determine a first weight and a second weight based on the relative magnitude between the first confidence level and the second confidence level; and perform a weighted summation of the first visibility distance level and the second visibility distance level according to the first weight and the second weight to obtain the target visibility distance level of the vehicle.

[0121] The various modules in the following distance adjustment device for the aforementioned vehicle can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of the onboard computing device in hardware form or independently of it, or they can be stored in the memory of the onboard computing device in software form, so that the processor can call and execute the corresponding operations of each module.

[0122] In an exemplary embodiment, an in-vehicle computing device is provided, the internal structure of which can be shown in Figure 5. The in-vehicle computing device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is connected to the system bus via the I / O interfaces. The processor of the in-vehicle computing device provides computing and control capabilities. The memory of the in-vehicle computing device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the in-vehicle computing device stores data involved in the above methods. The I / O interfaces of the in-vehicle computing device are used for information exchange between the processor and external devices. The communication interface of the in-vehicle computing device is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements the vehicle following distance adjustment method described in any of the above embodiments.

[0123] Those skilled in the art will understand that the structure shown in Figure 5 is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the in-vehicle computing device to which the present application is applied. A specific in-vehicle computing device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0124] In one embodiment, an in-vehicle computing device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the various method embodiments described above.

[0125] In one embodiment, a vehicle is provided that includes the on-board computing device described in the above embodiments.

[0126] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the various method embodiments described above.

[0127] In one embodiment, a computer program product is provided having a computer program stored thereon, the computer program being executed by a processor of the steps described in the various method embodiments above.

[0128] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0129] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0130] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0131] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for adjusting the following distance of a vehicle, comprising: Based on the forward-facing image of this vehicle, the completeness and clarity of the target outline in front are obtained. The target visibility distance level of this vehicle is obtained based on the completeness and clarity of the target outline in front. Determine the target following gear to which the target's visibility distance level belongs; Adjust the current following distance of this vehicle according to the target following gear and the current following gear of this vehicle.

2. The method according to claim 1, wherein, Based on the target following gear and the current following gear of the vehicle, adjust the current following distance of the vehicle, including: If the target following gear is higher than the current following gear of the vehicle, the current following distance of the vehicle is increased; the increased current following distance is within the following distance range corresponding to the target following gear.

3. The method according to claim 1, wherein, Based on the target following gear and the current following gear of the vehicle, adjust the current following distance of the vehicle, including: If the target following gear is equal to the current following gear, then obtain the set of visible distance levels corresponding to the target following gear; Based on the visible distance level set and the target visible distance level, determine the in-gear level of the target visible distance level; If the gear level is not the lowest level within the gear, increase the current following distance of this vehicle; the increased current following distance is within the following distance range corresponding to the current following gear.

4. The method according to claim 3, wherein, If the gear level is not the lowest level within the gear, increase the current following distance of this vehicle, including: If the gear level is not the lowest level within the gear, then a first increase ratio is determined based on the gear level; the higher the gear level, the larger the first increase ratio. Increase the current following distance of this vehicle according to the first increase ratio.

5. The method according to any one of claims 2 to 4, wherein, Increase the current following distance of this vehicle, including: Based on the current environmental data of the vehicle, a second increase ratio is determined; the current environmental data indicates that the more the current environment interferes with the vehicle's onboard vision, the larger the second increase ratio will be. Increase the current following distance of this vehicle according to the second increase ratio.

6. The method according to claim 1, wherein, Based on the completeness and sharpness of the target outline in front, the target visibility distance level of this vehicle is obtained, including: The first visibility distance level is obtained based on the completeness of the target outline in front; Based on the clarity of the target outline in front, a second visibility distance level is obtained; The target visibility level of this vehicle is obtained based on the first visibility level and the second visibility level.

7. The method according to claim 6, wherein, Based on the first visibility level and the second visibility level, the target visibility level of this vehicle is obtained, including: The first confidence level is obtained based on the completeness of the target outline in front; The second confidence level is obtained based on the clarity of the target outline in front; The first weight and the second weight are determined based on the relative magnitude between the first confidence level and the second confidence level; The first visibility level and the second visibility level are weighted and summed according to the first weight and the second weight to obtain the target visibility level of the vehicle.

8. The method according to claim 1, wherein, Based on the completeness and sharpness of the target outline in front, the target visibility distance level of this vehicle is obtained, including: The completeness of the front target outline and the clarity of the front target outline are weighted and summed to obtain the evaluation value of the front target outline of the vehicle. Determine the range of front profile evaluation values ​​to which the front target profile evaluation value of this vehicle belongs; Based on the correlation between the forward profile assessment value range and the visibility distance level, the visibility distance level associated with the forward profile assessment value range is determined as the target visibility distance level of the vehicle.

9. The method according to claim 1, wherein, The determination of the completeness of the front target outline based on the forward image of the vehicle includes: locating the target in the forward image and determining the front target in the forward image; The forward image is converted from a color image to a black-and-white binary image; Determine the minimum envelope of the target in the binary image; The number of pixels in the minimum envelope is determined as the first number of pixels; The minimum envelope is filled to obtain a minimum envelope without missing parts; The number of pixels in the minimum envelope without missing pixels is determined as the second number of pixels; The ratio of the first number of pixels to the second number of pixels is determined as the envelope pixel ratio of the forward image; and The completeness of the front target contour is obtained based on the ratio of the number of pixels in the envelope.

10. The method according to claim 1, wherein, Based on the forward-facing image of the vehicle, the sharpness of the outline of the forward target is obtained as follows: Target localization is performed on the forward image to determine the target in front of the forward image; The forward image is converted from a color image to a black-and-white binary image; Determine the outline of the target in the binary image, and use the outline as the target outline. Obtain the grayscale gradient values ​​of each point on the front target contour; and The grayscale gradient values ​​of each point are averaged to obtain the clarity of the target outline in front.

11. A vehicle following distance adjustment device, comprising: The contour processing module is set to obtain the completeness and clarity of the front target contour based on the forward image of the vehicle. The visibility distance level determination module is configured to obtain the target visibility distance level of the vehicle based on the completeness and clarity of the target outline in front. The target following gear determination module is configured to determine the target following gear to which the target visibility distance level belongs; The following distance adjustment module is configured to adjust the current following distance of the vehicle based on the target following gear and the current following gear of the vehicle.

12. An in-vehicle computing device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 10.

13. A vehicle, characterized in that, The vehicle includes the on-board computing device as described in claim 12.

Images