Vehicle driving scene area determination method and device and vehicle

Abstract

The invention provides a vehicle driving scene area determination method and device and a vehicle. The method comprises the steps that altitude change data of the vehicle in a current time window period, a first accumulative variable quantity of all course angle variable quantities and a second accumulative variable quantity of a dominant direction course angle are acquired; determining vertical motion characteristic data of the vehicle in the current time window period based on the altitude change data; on the basis of the first accumulative variable quantity and the second accumulative variable quantity, course angle change characteristic data of the vehicle in the current time window period are determined; and inputting the vertical motion feature data and the course angle change feature data into a classification model to obtain a driving scene area of the vehicle. According to the method, the vertical motion features are considered, the accuracy of the determined driving scene area where the vehicle is located is improved, the vehicle driving scene area can be accurately recognized through the vertical motion feature data and the course angle change feature data of the vehicle, and accurate recognition of the vehicle driving scene area is achieved.

Description

Technical Field

[0001] This application belongs to the field of vehicle driving navigation technology, and in particular relates to a method, device, vehicle and computer storage medium for determining a vehicle driving scene area. Background Technology

[0002] Current methods for analyzing the driving scene of a vehicle mostly rely on GPS and visual SLAM technology. However, when the GPS signal is weak or even malfunctions, and the scene structure is repetitive, causing visual SLAM technology to also fail, it is impossible to determine the current driving scene of the vehicle. This leads to the failure of the vehicle's navigation system and related functions.

[0003] This section uses a parking lot with a spiral ramp as an example. Existing parking lots with spiral ramps allow vehicles to ascend to each parking level, effectively improving land utilization. The smooth driving experience and strong adaptability of these ramps make them a suitable solution for large-scale urban parking hubs. However, the internal road environment of parking lots with spiral ramps is complex. Specifically, GPS signals in indoor and underground parking lots with spiral ramps attenuate sharply to the point of complete disappearance; the similar internal structure of spiral ramps makes visual SLAM technology prone to cumulative errors.

[0004] Therefore, in parking lots with spiral ramps, inaccurate GPS signals cannot accurately locate vehicles, and the application of visual SLAM technology suffers from the problem of cumulative errors. Summary of the Invention

[0005] This application provides a method, apparatus, and vehicle for determining a vehicle driving scene area, which can accurately locate the vehicle driving scene area when GPS signals cannot accurately locate the vehicle and visual SLAM technology has accumulated errors.

[0006] In a first aspect, embodiments of this application provide a method for determining a vehicle driving scene area, the method comprising: Acquire the vehicle's altitude change data, the first cumulative change of all heading angle changes, and the second cumulative change of the heading angle in the dominant direction within the current time window period; Based on altitude change data, the vertical motion characteristics of the vehicle within the current time window are determined; the vertical motion characteristics are used to characterize the vehicle's vertical motion pattern. Based on the first and second cumulative changes, the heading angle change characteristic data of the vehicle within the current time window period is determined; the heading angle change characteristic data is used to characterize the vehicle's steering motion pattern. Vertical motion feature data and heading angle change feature data are input into the classification model to obtain the vehicle's driving scene area.

[0007] In one feasible implementation, the above-mentioned determination of the vehicle's vertical motion characteristics within the current time window period based on altitude change data includes: Constructing vertical motion feature vectors based on altitude change data; The aforementioned data, based on the first and second cumulative changes, determines the vehicle's heading angle variation characteristics within the current time window period, including: Construct a heading angle change feature vector based on the first and second cumulative changes; Vertical motion feature data and heading angle change feature data are input into the classification model to obtain the vehicle's driving scene region, including: The vertical motion feature vector and the heading angle change feature vector are input into the classification model to obtain the vehicle's driving scene area.

[0008] In one feasible implementation, the vertical motion feature vector and heading angle change feature vector are input into the classification model to obtain the vehicle's driving scene region, including: The vertical motion feature vector and the heading angle change feature vector are input into the classification model to obtain the set of probability values ​​of the vehicle in each driving scenario area; each driving scenario area includes the ordinary road driving scenario area, the entrance road driving scenario area, the spiral ramp driving scenario area, and the parking lot level road driving scenario area. The driving scenario area where the vehicle is located is determined based on the probability value set and time series feature data. The time series feature data includes the driving scenario area where the vehicle is located within each historical time window period, the preset sequence of each driving scenario area, and the preset state transition conditions between driving scenario areas.

[0009] In one feasible implementation, the vertical motion feature vector and heading angle change feature vector are input into the classification model to obtain the vehicle's driving scene region, including: The vertical motion feature vector and the heading angle change feature vector are input into the classification model; When the vertical motion mode is determined to be either continuous ascent or continuous descent based on the vertical motion feature vector, and the steering motion mode is determined to be unidirectional continuous steering based on the heading angle change feature vector, the output vehicle is in the spiral ramp driving scenario area.

[0010] In one feasible implementation, the spiral ramp driving scenario area is the spiral ramp driving scenario area within a multi-story parking garage. The above-mentioned method for determining the vehicle driving scene area also includes: The driving scenario area where the vehicle is located within each historical time window period is determined based on vertical motion feature data and heading angle change feature data. The driving scenario area within each historical time window period is one of the following: ordinary road driving scenario area, entrance road driving scenario area, spiral ramp driving scenario area, and parking lot level road driving scenario area. The above-mentioned scenario, where the vertical motion mode is determined to be either continuous ascent or continuous descent based on the vertical motion feature vector, and the steering motion mode is determined to be unidirectional continuous steering based on the heading angle change feature vector, outputs that the vehicle is in a spiral ramp driving scenario area, including: Based on the driving scenario area where the vehicle is located within each historical time window period, the preset sequence of each driving scenario area, and the preset state transition conditions between driving scenario areas, it is verified whether the vehicle is in the spiral ramp driving scenario area within the current time window period. If the current driving scenario area of ​​the vehicle is verified and the set sequence and corresponding state transition conditions are met, it is determined that the vehicle is in the spiral ramp driving scenario area.

[0011] In one feasible implementation, the aforementioned preset sequence includes various driving scenario areas where the vehicle is located within multiple time window periods, arranged sequentially as follows: ordinary road driving scenario area, entrance road driving scenario area, spiral ramp driving scenario area, and parking lot level road driving scenario area.

[0012] In one feasible implementation, the determination of the vehicle's heading angle change characteristic data within the current time window period based on the first cumulative change and the second cumulative change includes: Calculate the ratio of the first cumulative change to the current time window period, and use it as the spiral motion index; The ratio of the second cumulative change to the first cumulative change is calculated and used as the orientation consistency index. The helical motion index and steering consistency index are used as characteristic data of the vehicle's heading angle change within the current time window period.

[0013] In one feasible implementation, the above method further includes: Obtain the variance of the rate of change of the vehicle's heading angle within the current time window period, and use it as the steering stability index; The above-mentioned spiral motion index and steering consistency index are used as characteristic data of the vehicle's heading angle change within the current time window period, including: The spiral motion index, steering consistency index, and steering stability index are used as characteristic data for heading angle variation.

[0014] In one feasible implementation, the above method further includes: Obtain vehicle air pressure change data within the current time window period; The aforementioned acquisition of vehicle altitude change data within the current time window includes: Acquire triaxial accelerometer data for the vehicle; Extract the vertical component of the vehicle within the current time window period from the triaxial accelerometer data; The vertical component is integrated twice to obtain the original elevation change data; Altitude change data is determined based on raw altitude change data and air pressure change data.

[0015] In one feasible implementation, the above method further includes: Obtain vehicle speed characteristic data within the current time window period; the vehicle speed characteristic data includes the vehicle's average speed data, speed standard deviation data, and stopping time percentage data within the current time window period; The above-mentioned vertical motion feature data and heading angle change feature data are input into the classification model to obtain the vehicle's driving scene region, including: Vertical motion feature data, heading angle change feature data, and vehicle speed feature data are input into the classification model to obtain the vehicle's driving scene area.

[0016] Secondly, embodiments of this application provide a vehicle driving scene area determination device, the device comprising: The acquisition module is used to acquire the vehicle's altitude change data, the first cumulative change of all heading angle changes, and the second cumulative change of the heading angle in the dominant direction within the current time window period; The vertical motion feature data determination module is used to determine the vertical motion feature data of the vehicle within the current time window period based on altitude change data; the vertical motion feature data is used to characterize the vertical motion pattern of the vehicle. The heading angle change characteristic data determination module is used to determine the heading angle change characteristic data of the vehicle within the current time window period based on the first cumulative change and the second cumulative change; the heading angle change characteristic data is used to characterize the vehicle's steering motion pattern. The driving scene area determination module is used to input vertical motion feature data and heading angle change feature data into the classification model to obtain the driving scene area of ​​the vehicle.

[0017] Thirdly, embodiments of this application provide a vehicle, which includes: a processor and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the vehicle driving scene area determination method as described above.

[0018] Fourthly, embodiments of this application provide a computer storage medium storing computer program instructions, which, when executed by a processor, implement the vehicle driving scene area determination method described above.

[0019] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements any of the methods for determining a vehicle driving scene area in the above embodiments.

[0020] The vehicle driving scene area determination method, device, and vehicle of this application embodiment obtain the vehicle's altitude change data, the first cumulative change of all heading angle changes, and the second cumulative change of the heading angle in the dominant direction within the current time window period. The altitude change data is used to determine the vehicle's vertical motion characteristics, taking into account the vehicle's vertical motion characteristics, which improves the accuracy of determining the driving scene area where the vehicle is located. In addition, the first and second cumulative changes are used to determine the vehicle's heading angle change characteristic data. Then, based on the vehicle's vertical motion characteristics and heading angle change characteristic data, the driving scene area where the vehicle is located can be accurately identified, achieving accurate identification of the vehicle driving scene area. Attached Figure Description

[0021] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart illustrating a method for determining a vehicle driving scene area according to an embodiment of this application; Figure 2 This is a flowchart illustrating a method for acquiring altitude change data provided in an embodiment of this application; Figure 3 This is a flowchart illustrating a method for determining a vehicle driving scene area based on a set of probability values ​​and time-series feature data, provided in an embodiment of this application. Figure 4 This is a flowchart illustrating a method for determining a driving area on a spiral ramp, as provided in an embodiment of this application. Figure 5 This is a flowchart illustrating a vehicle driving scenario area verification method provided in an embodiment of this application; Figure 6 This is a flowchart illustrating a method for acquiring heading angle variation feature data provided in an embodiment of this application; Figure 7This is an example diagram illustrating an application scenario of a method for determining a vehicle driving scene area provided in an embodiment of this application; Figure 8 This is a schematic diagram of the structure of a vehicle driving scene area determination device provided in an embodiment of this application; Figure 9 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application. Detailed Implementation

[0023] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0024] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0025] This section focuses on parking lots with spiral ramps as an example. In existing parking lots with spiral ramps, vehicles can ascend the ramps to reach each parking level. However, the internal road environment of parking lots with spiral ramps is complex. Especially in indoor and underground parking lots with spiral ramps, GPS signals can attenuate rapidly or even disappear completely. This leads to significant errors in locating vehicles using GPS signals in indoor and underground parking lots with spiral ramps. In severe cases, the complete loss of GPS signals makes it impossible to locate the vehicle. Furthermore, the internal structure of spiral ramps in parking lots is similar, making it easy for visual SLAM technology to accumulate errors when identifying the vehicle's location, thus failing to guarantee accurate identification of the vehicle's position.

[0026] Therefore, in order to ensure that the vehicle can determine the driving scene area in any scenario, it is necessary to analyze and identify the driving scene area based on the data collected by the vehicle itself. Although the vehicle's speed and direction of travel can be used to determine the vehicle's planar position in a specific area, it is not possible to accurately analyze the vehicle's position in areas with roads such as spiral ramps. This results in the inability to provide map navigation for the vehicle's current driving status, as well as other functions related to the vehicle's driving scene area.

[0027] To address the problems in the prior art, this application provides a method, apparatus, and vehicle for determining a vehicle driving scene area.

[0028] This application embodiment obtains the vehicle's altitude change data, the first cumulative change of all heading angle changes, and the second cumulative change of the heading angle in the dominant direction within the current time window period. It uses the altitude change data to determine the vehicle's vertical motion characteristics, taking into account the vehicle's vertical motion characteristics, thus improving the accuracy of determining the driving scene area where the vehicle is located. In addition, it uses the first and second cumulative changes to determine the vehicle's heading angle change characteristic data. Then, based on the vehicle's vertical motion characteristics and heading angle change characteristic data, it can accurately identify the driving scene area where the vehicle is located, achieving accurate identification of the vehicle's driving scene area.

[0029] The method for determining the vehicle driving scene area provided in the embodiments of this application will be introduced first.

[0030] Figure 1 A flowchart illustrating a method for determining a vehicle driving scene area according to an embodiment of this application is shown. Figure 1 As shown, the method may include the following steps: S101: Obtain the vehicle's altitude change data, the first cumulative change of all heading angle changes, and the second cumulative change of the heading angle in the dominant direction within the current time window period; S102: Determine the vertical motion characteristic data of the vehicle within the current time window period based on altitude change data; the vertical motion characteristic data is used to characterize the vertical motion pattern of the vehicle; S103: Based on the first cumulative change and the second cumulative change, determine the heading angle change characteristic data of the vehicle within the current time window period; the heading angle change characteristic data is used to characterize the vehicle's steering motion mode; S104: Input the vertical motion feature data and heading angle change feature data into the classification model to obtain the vehicle's driving scene area.

[0031] This application embodiment obtains the vehicle's altitude change data, the first cumulative change of all heading angle changes, and the second cumulative change of the heading angle in the dominant direction within the current time window period. It uses the altitude change data to determine the vehicle's vertical motion characteristics, taking into account the vehicle's vertical motion characteristics, thus improving the accuracy of determining the driving scene area where the vehicle is located. In addition, it uses the first and second cumulative changes to determine the vehicle's heading angle change characteristic data. Then, based on the vehicle's vertical motion characteristics and heading angle change characteristic data, it can accurately identify the driving scene area where the vehicle is located, achieving accurate identification of the vehicle's driving scene area.

[0032] The following provides a detailed explanation of each of the above steps.

[0033] In S101, firstly, the altitude change data of the vehicle within the current time window period obtained in this embodiment is calculated by subtracting the altitude of the vehicle at the initial moment of the current time window period from the altitude of the vehicle at the moment of acquisition. To ensure that the calculated altitude change data is meaningful, it is necessary to ensure that the altitude of the vehicle at the moment of acquisition and the altitude of the vehicle at the initial moment of the current time window period are values ​​in the same coordinate system. Therefore, this embodiment can set up a coordinate system to determine the altitude of the vehicle at each moment, or it can set up a coordinate system for each time window period. To avoid the complexity of altitude change data acquisition, a coordinate system can be constructed for all moments. In addition, the altitude change data obtained in this embodiment contains positive and negative numbers. Positive altitude change data can be set to indicate that the vehicle's altitude is increasing, and negative altitude change data can indicate that the vehicle's altitude is decreasing.

[0034] This application does not limit the frequency of acquiring vehicle altitude change data within the current time window period. For example, the altitude change data can be acquired in real time, that is, the next acquisition operation is performed immediately after the first acquisition operation is completed, or the altitude change data acquisition operation can be performed at preset intervals. This application does not limit the setting value of the preset interval time, for example, it can be set to 5 seconds, 7 seconds, or 10 seconds. This application does not limit the basis for setting the preset interval time, it can be set in response to the operator's instructions, or it can be set according to the current vehicle speed. It can be set that the faster the current vehicle speed, the smaller the preset interval time setting value. To avoid failure to determine in time when switching driving scene areas, the altitude change data can be acquired in real time. In this application embodiment, the heading angle can be determined by the vehicle yaw rate output by the IMU (Inertial Measurement Unit).

[0035] Secondly, the first cumulative change in all heading angle changes obtained in this embodiment requires dividing the current time window period into multiple time intervals. For each time interval, the difference between the initial heading angle and the ending heading angle of that time interval can be obtained, and the absolute value of this difference can be recorded as the absolute value of the heading angle change within that time interval. The absolute values ​​of the changes in each interval within all time intervals of the current time window period are added together to obtain the first cumulative change in all heading angle changes within the current time window period. This avoids the problem that when directly using the initial and ending heading angles within the current time window period to calculate the first cumulative change, the heading angle change may exceed 360 degrees and be considered an acute angle. This ensures that the calculated first cumulative change accurately represents the change in heading angle within the current time window period, guaranteeing the accuracy of the vehicle driving scenario area determination. Regarding the description of the frequency of obtaining the first cumulative change, please refer to the description of the frequency of obtaining altitude change data above; it will not be repeated here. To ensure timely response, the first cumulative change can be obtained in real-time.

[0036] Finally, in this embodiment, the heading angle is divided into clockwise and counterclockwise turns. Therefore, when determining the dominant direction heading angle, it is necessary to distinguish between positive and negative clockwise and counterclockwise turns. Specifically, the heading angle change can be set to positive when the heading angle turns clockwise and negative when the heading angle turns counterclockwise. To determine the dominant direction heading angle, it is only necessary to determine the relationship between the absolute values ​​of the cumulative heading angle changes in clockwise and counterclockwise directions within the current time window period. The direction with the larger absolute value is selected as the dominant direction, and the cumulative heading angle change in the dominant direction is the aforementioned second cumulative change. Similarly, the description of the frequency of obtaining the second cumulative change can be found in the description of the frequency of obtaining altitude change data above, and will not be repeated here. To ensure timely response to requests for determining the vehicle driving scenario area, the second cumulative change can be obtained in real time.

[0037] In one feasible embodiment, to ensure successful acquisition of altitude change data and improve the accuracy of the acquired altitude change data, the above method may further include: Obtain vehicle air pressure change data within the current time window period; The above-mentioned acquisition of vehicle altitude change data within the current time window period may include the following steps, which can be referred to for details. Figure 2 , Figure 2 This is a flowchart illustrating a method for acquiring altitude change data provided in an embodiment of this application.

[0038] S201: Acquire triaxial accelerometer data of the vehicle; S202: Extract the vertical component of the vehicle within the current time window period from the triaxial accelerometer data; S203: Perform a second integration on the vertical component to obtain the original elevation change data; S204: Determine altitude change data based on raw altitude change data and air pressure change data.

[0039] In this embodiment, the triaxial accelerometer data can also be determined by the vehicle's IMU unit. For the calculated triaxial accelerometer data, the vertical component of the data within the current time window needs to be extracted; that is, only the accelerometer data along the vertical axis is extracted. Then, this vertical component is integrated twice to obtain the vehicle's raw altitude change data. This raw altitude change data is then combined with air pressure change data to determine the final altitude change data, thereby improving the accuracy of the acquired altitude change data. In this embodiment, air pressure change data can characterize the vehicle's altitude change. Therefore, this embodiment can specifically take the average of the altitude change data represented by the air pressure change data and the raw altitude change data as the final altitude change data. Alternatively, other more complex methods can be used to process the raw altitude change data and air pressure change data to determine the final altitude change data.

[0040] S102: Determine the vertical motion characteristic data of the vehicle within the current time window period based on altitude change data; the vertical motion characteristic data is used to characterize the vertical motion pattern of the vehicle; In this embodiment, data representing vertical motion features that can be received and processed by the classification model can be set accordingly. This data can be vectors generated based on altitude change data, characterizing the vehicle's vertical motion pattern; the specific vectors can be determined based on the classification model.

[0041] S103: Based on the first cumulative change and the second cumulative change, determine the heading angle change characteristic data of the vehicle within the current time window period; the heading angle change characteristic data is used to characterize the vehicle's steering motion mode; In this embodiment, heading angle change feature data that can be received and processed by the classification model can be set accordingly. This data can be a vector generated based on a first cumulative change and a second cumulative change, capable of representing the vehicle's steering motion pattern.

[0042] S104: Input the vertical motion feature data and heading angle change feature data into the classification model to obtain the vehicle's driving scene area.

[0043] In this embodiment, the classification model is trained using training samples composed of vertical motion feature data, heading angle change feature data, and corresponding driving scene areas. After training, the classification model can output the driving scene area of ​​the vehicle by simply inputting the vertical motion feature data and heading angle change feature data into it.

[0044] In one feasible embodiment, to facilitate the classification model in receiving data outputting the vehicle's driving scene area, the aforementioned vertical motion characteristic data of the vehicle within the current time window period based on altitude change data may include: Constructing vertical motion feature vectors based on altitude change data; The aforementioned determination of the vehicle's heading angle change characteristics within the current time window period based on the first and second cumulative changes may include: Construct a heading angle change feature vector based on the first and second cumulative changes; The above-mentioned input of vertical motion feature data and heading angle change feature data into the classification model to obtain the vehicle's driving scene area can include: The vertical motion feature vector and the heading angle change feature vector are input into the classification model to obtain the vehicle's driving scene area.

[0045] In this embodiment, a vertical motion feature vector is constructed based on altitude change data, and a heading angle change feature vector is constructed based on the first cumulative change and the second cumulative change. The constructed feature vector is then input into the classification model, which can ensure that the classification model can efficiently determine the driving scene area of ​​the vehicle and ensure the efficient operation of the classification model.

[0046] In one feasible embodiment, to improve the accuracy of the vehicle driving scene area determined based on the classification model, the above-mentioned input of the vertical motion feature vector and heading angle change feature vector into the classification model to obtain the vehicle driving scene area may include the following steps, which can be referred to in detail. Figure 3 , Figure 3 This is a flowchart illustrating a method for determining a vehicle driving scene area based on a set of probability values ​​and time-series feature data, as provided in an embodiment of this application.

[0047] S301: Input the vertical motion feature vector and the heading angle change feature vector into the classification model to obtain the set of probability values ​​of the vehicle in each driving scenario area; each driving scenario area includes the ordinary road driving scenario area, the entrance road driving scenario area, the spiral ramp driving scenario area, and the parking lot level road driving scenario area. S302: Determine the driving scenario area where the vehicle is located based on the probability value set and time series feature data; the time series feature data includes the driving scenario area where the vehicle is located within each historical time window period, the preset sequence of each driving scenario area, and the preset state transition conditions between driving scenario areas.

[0048] In this embodiment, after obtaining the probability value set for each driving scenario region, the driving scenario region corresponding to the highest probability value is not selected as the determined vehicle driving scenario region. Instead, the probability value set is combined with temporal feature data for analysis. By introducing temporal feature data, the accuracy of the determined vehicle driving scenario region is improved. Specifically, this embodiment can perform weighted fusion processing on the probability value set and temporal feature data, and select the driving scenario region corresponding to the highest value after weighted fusion processing as the determined vehicle driving scenario region. Alternatively, the probability value set and temporal feature data can be combined in other ways, as long as it can comprehensively analyze the probability value set and temporal feature data to determine the vehicle driving scenario region.

[0049] In one feasible embodiment, to improve the ease of determining the vehicle driving scene area and enhance the model's analysis and processing efficiency, the above-mentioned input of the vertical motion feature vector and heading angle change feature vector into the classification model to obtain the vehicle driving scene area may include the following steps, which can be referred to in detail. Figure 4 , Figure 4 This is a flowchart illustrating a method for determining a driving area on a spiral ramp, as provided in an embodiment of this application.

[0050] S401: Input the vertical motion feature vector and the heading angle change feature vector into the classification model; S402: When the vertical motion mode is determined to be either continuous ascent or continuous descent based on the vertical motion feature vector, and the steering motion mode is determined to be unidirectional continuous steering based on the heading angle change feature vector, the output vehicle is in the spiral ramp driving scenario area.

[0051] In this embodiment, the classification model directly determines the vehicle's vertical motion mode based on the input vertical motion feature vector, and determines the vehicle's steering motion mode based on the input heading angle change feature vector. When it is determined that the vehicle's vertical motion mode is continuously rising or falling, and the steering motion mode is unidirectional continuous steering, it directly determines and outputs that the vehicle is in the spiral ramp driving scene area. This not only realizes the determination of the vehicle in the spiral ramp driving scene area, but also improves the efficiency of determining the vehicle in the spiral ramp driving scene area.

[0052] In one feasible embodiment, in order to improve the accuracy of determining the vehicle driving scene area while ensuring the efficiency of model analysis and processing, the above-mentioned spiral ramp driving scene area can be set as the spiral ramp driving scene area in a multi-story parking lot. The above-mentioned method for determining the vehicle driving scenario area may also include: The driving scenario area where the vehicle is located within each historical time window period is determined based on vertical motion feature data and heading angle change feature data. The driving scenario area within each historical time window period is one of the following: ordinary road driving scenario area, entrance road driving scenario area, spiral ramp driving scenario area, and parking lot level road driving scenario area. When the vertical motion mode is determined to be either continuous ascent or continuous descent based on the vertical motion feature vector, and the steering motion mode is determined to be unidirectional continuous steering based on the heading angle change feature vector, the output vehicle is in a spiral ramp driving scenario area. This can include the following steps, which can be found in the following reference: Figure 5 , Figure 5 This is a flowchart illustrating a vehicle driving scenario area verification method provided in an embodiment of this application.

[0053] S501: Based on the driving scenario area where the vehicle is located within each historical time window period, the preset sequence of each driving scenario area, and the preset state transition conditions between driving scenario areas, verify whether the vehicle is in the spiral ramp driving scenario area within the current time window period. S502: After verifying that the current driving scenario area of ​​the vehicle meets the set sequence and corresponding state transition conditions, determine that the vehicle is in the spiral ramp driving scenario area.

[0054] For multi-level parking lots with spiral ramps, this embodiment can also obtain the driving scene area where the vehicle is located within each historical time window period. This historical time window period is the time window period before the current time window period. Based on a set sequence and corresponding state transition conditions, this embodiment determines whether the driving scene area where the vehicle is currently located satisfies the temporal relationship with the driving scene areas where the vehicle was located in the historical time window period. This temporal relationship is determined by a preset set sequence of each driving scene area. This set sequence determines the order in which the vehicle appears in each driving scene area, and the state transition conditions are the conditions that the corresponding data of the vehicle's driving process must satisfy when the driving scene area where the vehicle is located changes. For example, the sequence can be set as: ordinary road driving scenario area, entrance road driving scenario area, spiral ramp driving scenario area, and parking lot level road driving scenario area; the state transition condition for the vehicle changing from the ordinary road driving scenario area to the entrance road driving scenario area is condition A, the state transition condition for the vehicle changing from the entrance road driving scenario area to the spiral ramp driving scenario area is condition B, and the state transition condition for the vehicle changing from the spiral ramp driving scenario area to the parking lot level road driving scenario area is condition C. At this time, it is necessary to obtain the driving scenario area where the vehicle was located in the previous time window period. For example, if the vertical motion feature vector determines the vertical motion mode to be continuously ascending or descending, and the steering motion mode is determined to be unidirectional continuous steering based on the heading angle change feature vector, the output shows that the vehicle is in the spiral ramp driving scenario area. At this time, the driving scenario area where the vehicle was located in the previous time window period is the entrance road driving scenario area, and the vehicle state satisfies condition B during the time period from the previous time window period to the current time window period. If the verification passes, it can be determined that the vehicle is in the spiral ramp driving scenario area. The verification process in this embodiment can be specifically completed using finite state machine reasoning.

[0055] In one feasible embodiment, in order to improve the adaptability of the vehicle driving scene area determination method to multi-story parking lots with spiral ramps, the above-mentioned preset setting sequence may include various driving scene areas where the vehicle is located in multiple time window periods, arranged in chronological order as: ordinary road driving scene area, entrance road driving scene area, spiral ramp driving scene area, and parking lot level road driving scene area.

[0056] In this embodiment, the set sequence is set as a normal road driving scenario area, an entrance road driving scenario area, a spiral ramp driving scenario area, and a parking lot level road driving scenario area. Specifically, when a vehicle changes from a normal road driving scenario area to an entrance road driving scenario area, the state transition condition can be set as follows: the probability of the vehicle being in the entrance road driving scenario area suddenly increases beyond a probability surge threshold, and the vehicle's driving speed decreases. Specifically, the vehicle's driving speed decreases beyond a speed decrease threshold. When a vehicle changes from an entrance road driving scenario area to a spiral ramp driving scenario area, the state transition condition can be set as follows: the probability of the vehicle being in the spiral ramp driving scenario area exceeds a probability threshold, and the vehicle continuously rises or falls vertically. Specifically, the vehicle's altitude rise or fall exceeds an altitude change threshold. When a vehicle changes from a spiral ramp driving scenario area to a parking lot level road driving scenario area, the state transition condition can be set as follows: the vehicle's altitude stops changing vertically, and the vehicle's driving pattern is irregular.

[0057] Furthermore, embodiments of this application can also be added to allow the vehicle to change from a level driving area in a parking lot to a spiral ramp driving area. In this case, the state transition condition is that the vehicle continues to rise or fall vertically again, and the probability of being in the spiral ramp driving area exceeds a probability threshold. Additionally, the vehicle can also be added to allow the vehicle to change from a level driving area in a parking lot to a normal road driving area. In this case, the state transition condition is that the speed is continuously higher than a speed threshold for a specified time period. The specified time period is not limited; for example, it can be set to 3 seconds or 5 seconds. For safety, it can also be set to a longer time.

[0058] In one feasible embodiment, to improve the accuracy of determining the vehicle driving scene area and ensure that the collected data during vehicle driving can effectively characterize the vehicle driving scene area, the above-mentioned determination of the vehicle's heading angle change characteristic data within the current time window period based on the first and second cumulative change amounts may include the following steps, which can be referred to in detail. Figure 6 , Figure 6 This is a flowchart illustrating a method for acquiring heading angle change feature data provided in an embodiment of this application.

[0059] S601: Calculate the ratio of the first cumulative change to the current time window period, as the spiral motion index; S602: Calculate the ratio of the second cumulative change to the first cumulative change, and use it as the orientation consistency index; S603: Use the helical motion index and steering consistency index as characteristic data of the vehicle's heading angle change within the current time window period.

[0060] Within the current time window period, when the vehicle is in a spiral ramp driving scenario area, the first cumulative change will continuously increase over time. This embodiment uses the ratio of the first cumulative change to the current time window period as the spiral motion index. This spiral motion index effectively characterizes whether the vehicle is in a spiral ramp driving scenario area. Furthermore, the ratio of the second cumulative change to the first cumulative change determines the proportion of the change in the dominant directional heading angle among all heading angle changes. The larger the spiral motion index and steering consistency index, the greater the probability that the vehicle is in a spiral ramp driving scenario area. Especially when the vehicle is in a spiral ramp driving scenario area, the steering consistency index approaches 1. Specifically, this embodiment can determine that the vehicle is in a spiral ramp driving scenario area when the spiral motion index is greater than the first index threshold and the steering consistency index is greater than the second index threshold. This embodiment does not limit the setting values ​​of the first and second index thresholds; for example, they can be set based on the operator's experience, or they can be determined by training samples during the classification model training process.

[0061] In one feasible embodiment, in order to improve the accuracy of determining the vehicle driving scene area and reduce the risk of misjudgment, the above method may further include: Obtain the variance of the rate of change of the vehicle's heading angle within the current time window period, and use it as the steering stability index; Using the helical motion index and steering consistency index as characteristic data of the vehicle's heading angle change within the current time window period, it can include: The spiral motion index, steering consistency index, and steering stability index are used as characteristic data for heading angle variation.

[0062] When the vehicle is in a spiral ramp driving scenario, the vehicle's steering is smooth and continuous, resulting in a low variance in the heading angle change rate. Specifically, this application embodiment can set a variance threshold corresponding to the variance of the heading angle change rate. When the variance of the heading angle change rate is less than this threshold, it can be preliminarily confirmed that the vehicle is in a spiral ramp driving scenario based on the heading angle change rate.

[0063] In one feasible embodiment, to expand the dimensions of the data used to determine the vehicle driving scene region and improve the accuracy of vehicle driving scene region determination, the above method may further include: Obtain vehicle speed characteristic data within the current time window period; the vehicle speed characteristic data includes the vehicle's average speed data, speed standard deviation data, and stopping time percentage data within the current time window period; The above-mentioned input of vertical motion feature data and heading angle change feature data into the classification model to obtain the vehicle's driving scene area can include: Vertical motion feature data, heading angle change feature data, and vehicle speed feature data are input into the classification model to obtain the vehicle's driving scene area.

[0064] In this embodiment, vehicle speed characteristic data is used to determine the driving scenario area where the vehicle is located within the current time window period. Specifically, when the vehicle is in a spiral ramp driving scenario area, the vehicle's average speed is lower than when it is in a normal road driving scenario area, the speed standard deviation is relatively lower, the stopping time percentage is relatively lower, corresponding to a lower vehicle speed, a lower speed change rate, and a lower ratio of stopping time to driving time. In this embodiment, three thresholds can be set for the aforementioned average speed data, speed standard deviation data, and stopping time percentage data. When the vehicle's average speed data, speed standard deviation data, and stopping time percentage data are all lower than the corresponding thresholds, it is preliminarily considered that the vehicle is in a spiral ramp driving scenario area. In this embodiment, the vehicle speed characteristic data can be obtained based on the vehicle's CAN bus.

[0065] The vehicle driving scene area determination method provided in this application obtains the vehicle's altitude change data, the first cumulative change of all heading angle changes, and the second cumulative change of the heading angle in the dominant direction within the current time window period. The vertical motion characteristics of the vehicle are determined using the altitude change data, which takes the vehicle's vertical motion characteristics into consideration, thus improving the accuracy of the determined driving scene area. In addition, the heading angle change characteristic data of the vehicle are determined using the first and second cumulative changes. Based on the vehicle's vertical motion characteristics and heading angle change characteristic data, the driving scene area where the vehicle is located can be accurately identified, thus achieving accurate identification of the vehicle driving scene area.

[0066] Furthermore, this embodiment extracts the vertical component of the triaxial accelerometer data within the current time window period, then performs a second integration on this vertical component to obtain the vehicle's original altitude change data. This original altitude change data, combined with air pressure change data, is then used to determine the final altitude change data, improving the accuracy of the acquired altitude change data. A vertical motion feature vector is constructed based on the altitude change data, and a heading angle change feature vector is constructed based on the first and second cumulative changes. The constructed feature vectors are then input into the classification model, ensuring that the classification model efficiently determines the vehicle's driving scenario area and guarantees efficient operation. Introducing temporal feature data improves the accuracy of the determined vehicle driving scenario area. When the vertical motion mode is determined to be continuously ascending or descending based on the vertical motion feature vector, and the steering motion mode is determined to be unidirectional continuous steering based on the heading angle change feature vector, the vehicle is determined to be in a spiral ramp driving scenario area, improving the convenience of determining the vehicle's driving scenario area and increasing the model's analysis and processing efficiency. The temporal feature data was used to validate the determination results, improving the accuracy of determining the vehicle driving scene area while ensuring the model's analytical processing efficiency. Setting the sequence as ordinary road driving scene area, entrance road driving scene area, spiral ramp driving scene area, and parking lot level road driving scene area improved the adaptability of the vehicle driving scene area determination method to multi-story parking lots with spiral ramps. Using the spiral motion index and steering consistency index as characteristic data of the vehicle's heading angle change within the current time window period improved the accuracy of determining the vehicle driving scene area, ensuring that the collected data during vehicle movement effectively characterizes the vehicle's driving scene area. Using the spiral motion index, steering consistency index, and steering stability index as characteristic data of heading angle change further improved the accuracy of determining the vehicle driving scene area and reduced the risk of misjudgment. Using vehicle speed feature data to determine the vehicle's driving scene area within the current time window period expanded the dimensions of the data used to determine the vehicle driving scene area, further improving the accuracy of vehicle driving scene area determination.

[0067] To make the embodiments of this application easier to understand, this application also provides a specific application scenario embodiment, which specifically includes the following steps. (See below for details.) Figure 7 , Figure 7 This is an example diagram illustrating an application scenario of a method for determining a vehicle driving scene area provided in an embodiment of this application.

[0068] S701: Acquire the vehicle's three-axis accelerometer data, air pressure change data, the first cumulative change of all heading angle changes, the second cumulative change of the heading angle in the dominant direction, and vehicle speed characteristic data within the current time window period; the vehicle speed characteristic data includes the vehicle's average speed data, vehicle speed standard deviation data, and stopping time percentage data within the current time window period. S702: Constructing vehicle speed feature vectors based on vehicle speed feature data; S703: Extract the vertical component of the vehicle within the current time window from the triaxial accelerometer data, perform a second integration on the vertical component to obtain the original altitude change data, determine the altitude change data based on the original altitude change data and air pressure change data, and construct a vertical motion feature vector based on the altitude change data. In the embodiments of this application, the vertical motion feature vector is used to characterize the vertical motion pattern of the vehicle.

[0069] S704: Calculate the ratio of the first cumulative change to the current time window period as the helical motion index; calculate the ratio of the second cumulative change to the first cumulative change as the steering consistency index; calculate the variance of the rate of change of the vehicle's heading angle within the current time window period as the steering stability index; construct a heading angle change feature vector based on the helical motion index, steering consistency index, and steering stability index. In the embodiments of this application, the heading angle variation feature vector is used to characterize the vehicle's steering motion pattern.

[0070] S705: Input the vehicle speed feature vector, vertical motion feature vector, and heading angle change feature vector into the classification model to obtain the set of probability values ​​of the vehicle in each driving scenario area; each driving scenario area includes the ordinary road driving scenario area, the entrance road driving scenario area, the spiral ramp driving scenario area, and the parking lot level road driving scenario area. S706: Determine the driving scenario area where the vehicle is located based on the probability value set and time series feature data; the time series feature data includes the driving scenario area where the vehicle is located within each historical time window period, the preset sequence of each driving scenario area, and the preset state transition conditions between driving scenario areas.

[0071] The preset sequence in this embodiment includes various driving scenario areas where the vehicle is located within multiple time window periods, arranged sequentially as follows: ordinary road driving scenario area, entrance road driving scenario area, spiral ramp driving scenario area, and parking lot level road driving scenario area. The vehicle driving scenario area determination function in this embodiment can be set to automatic triggering and can provide a pre-trigger signal to the automatic parking system, allowing it to perform sensor preheating and environmental scanning in advance. Furthermore, when the vehicle's driving scenario area is determined, the driver can be shown the confirmed information. For example, when the vehicle is determined to be in the spiral ramp driving scenario area, the driver can be visually displayed on the vehicle's dashboard or head-up display as "driving on a spiral ramp." Data from each time window period can also be stored for later analysis and retrieval.

[0072] Figure 8 This is a schematic diagram of the structure of a vehicle driving scene area determination device provided in an embodiment of this application. Figure 8 As shown, the device may include an acquisition module 801, a vertical motion feature data determination module 802, a heading angle change feature data determination module 803, and a driving scene area determination module 804.

[0073] The acquisition module 801 is used to acquire the vehicle's altitude change data, the first cumulative change of all heading angle changes, and the second cumulative change of the heading angle in the dominant direction within the current time window period; The vertical motion feature data determination module 802 is used to determine the vertical motion feature data of the vehicle within the current time window period based on the altitude change data; the vertical motion feature data is used to characterize the vertical motion pattern of the vehicle. The heading angle change characteristic data determination module 803 is used to determine the heading angle change characteristic data of the vehicle within the current time window period based on the first cumulative change amount and the second cumulative change amount; the heading angle change characteristic data is used to characterize the vehicle's steering motion mode; The driving scene area determination module 804 is used to input vertical motion feature data and heading angle change feature data into the classification model to obtain the driving scene area of ​​the vehicle.

[0074] In one embodiment, the vertical motion feature data determination module 802 described above may include: Vertical motion feature vector construction unit, used to construct vertical motion feature vectors based on altitude change data; The aforementioned heading angle change characteristic data determination module 803 may include: The heading angle change feature vector construction unit is used to construct a heading angle change feature vector based on the first cumulative change and the second cumulative change. The aforementioned driving scenario area determination module 804 may include: The driving scene region determination unit is used to input the vertical motion feature vector and the heading angle change feature vector into the classification model to obtain the driving scene region of the vehicle.

[0075] In one embodiment, the driving scene area determination unit may include: The probability determination subunit is used to input the vertical motion feature vector and the heading angle change feature vector into the classification model to obtain the set of probability values ​​of the vehicle in each driving scenario area; each driving scenario area includes the ordinary road driving scenario area, the entrance road driving scenario area, the spiral ramp driving scenario area, and the parking lot level road driving scenario area. The driving scenario area determination subunit is used to determine the driving scenario area where the vehicle is located based on the probability value set and time series feature data. The time series feature data includes the driving scenario area where the vehicle is located within each historical time window period, the preset sequence of each driving scenario area, and the preset state transition conditions between driving scenario areas.

[0076] In one embodiment, the driving scene area determination unit may include: The classification model input sub-unit is used to input the vertical motion feature vector and the heading angle change feature vector into the classification model; The spiral ramp output subunit is used to output the vehicle's position in the spiral ramp driving scenario area when the vertical motion mode is determined to be either continuous ascent or continuous descent based on the vertical motion feature vector, and the steering motion mode is determined to be unidirectional continuous steering based on the heading angle change feature vector.

[0077] In one embodiment, the spiral ramp driving scene area in the above-mentioned vehicle driving scene area determination device can be configured as a spiral ramp driving scene area in a multi-story parking lot. The aforementioned vehicle driving scene area determination device may further include: The historical data acquisition module is used to acquire the driving scene area where the vehicle is located within each historical time window period, which is determined based on vertical motion feature data and heading angle change feature data. The driving scene area within each historical time window period is one of the following: ordinary road driving scene area, entrance road driving scene area, spiral ramp driving scene area, and parking lot level road driving scene area. The aforementioned spiral ramp output subunit may include: The verification subunit is used to verify whether the vehicle is in the spiral ramp driving scenario area in the current time window period based on the driving scenario area where the vehicle is located in each historical time window period, the preset sequence of each driving scenario area, and the preset state transition conditions between driving scenario areas. The verification spiral ramp sub-unit is used to determine that the vehicle is in the spiral ramp driving scenario area when the set sequence and corresponding state transition conditions are met in the current driving scenario area of ​​the verification vehicle.

[0078] In one embodiment, the preset sequence in the above verification subunit can be configured to include various driving scenario areas where the vehicle is located in multiple time window periods, arranged in chronological order as: ordinary road driving scenario area, entrance road driving scenario area, spiral ramp driving scenario area, and parking lot level road driving scenario area.

[0079] In one embodiment, the heading angle change feature data determination module 803 described above may include: The spiral motion index calculation unit is used to calculate the ratio of the first cumulative change to the current time window period, which is used as the spiral motion index. The steering consistency index calculation unit is used to calculate the ratio of the second cumulative change to the first cumulative change, which is used as the steering consistency index. The heading angle change characteristic data determination unit is used to take the spiral motion index and steering consistency index as the heading angle change characteristic data of the vehicle within the current time window period.

[0080] In one embodiment, the vehicle driving scene area determination device may further include: The steering stability index acquisition module is used to obtain the variance of the rate of change of the heading angle of the vehicle within the current time window period, which is used as the steering stability index. The aforementioned heading angle change characteristic data determination unit may include: The heading angle variation characteristic data determination sub-unit is used to take the spiral motion index, steering consistency index, and steering stability index as heading angle variation characteristic data.

[0081] In one embodiment, the vehicle driving scene area determination device may further include: The air pressure change data acquisition module is used to acquire air pressure change data of the vehicle within the current time window period; The aforementioned acquisition module 801 may include: The triaxial accelerometer data acquisition unit is used to acquire triaxial accelerometer data of the vehicle. The vertical component extraction unit is used to extract the vertical component of the vehicle within the current time window period from the triaxial accelerometer data. The raw elevation change data calculation unit is used to perform a second integration on the vertical component to obtain the raw elevation change data. The altitude change data determination unit is used to determine altitude change data based on the original altitude change data and air pressure change data.

[0082] In one embodiment, the vehicle driving scene area determination device may further include: The vehicle speed feature data acquisition module is used to acquire vehicle speed feature data within the current time window period; the vehicle speed feature data includes the vehicle's average speed data, vehicle speed standard deviation data, and stopping time percentage data within the current time window period; The aforementioned driving scenario area determination module 804 may include: The classification model output unit is used to input vertical motion feature data, heading angle change feature data, and vehicle speed feature data into the classification model to obtain the vehicle's driving scene area.

[0083] This application embodiment obtains the vehicle's altitude change data, the first cumulative change of all heading angle changes, and the second cumulative change of the heading angle in the dominant direction within the current time window period. It uses the altitude change data to determine the vehicle's vertical motion characteristics, taking into account the vehicle's vertical motion characteristics, thus improving the accuracy of determining the driving scene area where the vehicle is located. In addition, it uses the first and second cumulative changes to determine the vehicle's heading angle change characteristic data. Then, based on the vehicle's vertical motion characteristics and heading angle change characteristic data, it can accurately identify the driving scene area where the vehicle is located, achieving accurate identification of the vehicle's driving scene area.

[0084] Figure 9 A schematic diagram of the structure of a vehicle provided in an embodiment of this application is shown.

[0085] The vehicle may include a processor 901 and a memory 902 storing computer program instructions.

[0086] Specifically, the processor 901 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0087] Memory 902 may include mass storage for data or instructions. For example, and not limitingly, memory 902 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. In one instance, memory 902 may include removable or non-removable (or fixed) media, or memory 902 may be non-volatile solid-state memory. Memory 902 may be internal or external to the integrated gateway disaster recovery device.

[0088] Memory 902 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Therefore, generally, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of this disclosure.

[0089] The processor 901 reads and executes computer program instructions stored in the memory 902 to achieve... Figure 1 The method for determining the vehicle driving scene area in the illustrated embodiment.

[0090] In one example, the vehicle may also include a communication interface 903 and a bus 904. Wherein, as... Figure 9 As shown, the processor 901, memory 902, and communication interface 903 are connected through bus 904 and complete communication with each other.

[0091] The communication interface 903 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0092] Bus 904 includes hardware, software, or both, that couples components of an online data traffic metering device together. For example, and not as a limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 904 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, this application contemplates any suitable bus or interconnect.

[0093] Furthermore, in conjunction with the vehicle driving scene area determination method in the above embodiments, this application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the vehicle driving scene area determination methods in the above embodiments.

[0094] This application also provides a computer program product, including a computer program that, when executed by a processor, implements any of the methods for determining the vehicle driving scene area in the above embodiments.

[0095] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0096] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, read-only memory (ROM), flash memory, erasable read-only memory (EROM), floppy disks, compact disc read-only memory (CD-ROM), optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0097] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0098] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0099] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A method for determining a vehicle driving scene area, characterized in that, include: Acquire the vehicle's altitude change data, the first cumulative change of all heading angle changes, and the second cumulative change of the heading angle in the dominant direction within the current time window period; Based on the altitude change data, determine the vertical motion characteristic data of the vehicle within the current time window period; The vertical motion feature data is used to characterize the vertical motion pattern of the vehicle. Based on the first cumulative change and the second cumulative change, the heading angle change characteristic data of the vehicle within the current time window period is determined; the heading angle change characteristic data is used to characterize the steering motion mode of the vehicle. The vertical motion feature data and the heading angle change feature data are input into the classification model to obtain the driving scene area of ​​the vehicle.

2. The method for determining the vehicle driving scene area according to claim 1, characterized in that, The process of determining the vertical motion characteristic data of the vehicle within the current time window period based on the altitude change data includes: A vertical motion feature vector is constructed based on the altitude change data; The step of determining the heading angle change characteristic data of the vehicle within the current time window period based on the first cumulative change and the second cumulative change includes: Construct a heading angle change feature vector based on the first cumulative change and the second cumulative change; The step of inputting the vertical motion feature data and the heading angle change feature data into the classification model to obtain the driving scene area of ​​the vehicle includes: The vertical motion feature vector and the heading angle change feature vector are input into the classification model to obtain the driving scene area of ​​the vehicle.

3. The method for determining the vehicle driving scene area according to claim 2, characterized in that, The step of inputting the vertical motion feature vector and the heading angle change feature vector into the classification model to obtain the driving scene region of the vehicle includes: The vertical motion feature vector and the heading angle change feature vector are input into the classification model to obtain a set of probability values ​​for the vehicle in each driving scenario area; the various driving scenario areas include ordinary road driving scenario area, entrance road driving scenario area, spiral ramp driving scenario area, and parking lot level road driving scenario area. The driving scenario region where the vehicle is located is determined based on the set of probability values ​​and the time-series feature data; the time-series feature data includes the driving scenario region where the vehicle is located within each historical time window period, a preset sequence of driving scenario regions, and preset state transition conditions between driving scenario regions.

4. The method for determining the vehicle driving scene area according to claim 2, characterized in that, The step of inputting the vertical motion feature vector and the heading angle change feature vector into the classification model to obtain the driving scene region of the vehicle includes: The vertical motion feature vector and the heading angle change feature vector are input into the classification model; If the vertical motion mode is determined to be either continuous ascent or continuous descent based on the vertical motion feature vector, and the steering motion mode is determined to be unidirectional continuous steering based on the heading angle change feature vector, the output shows that the vehicle is in the spiral ramp driving scenario area.

5. The method for determining the vehicle driving scene area according to claim 4, characterized in that, The spiral ramp driving scenario area is the spiral ramp driving scenario area in a multi-story parking lot. The method for determining the vehicle driving scene area also includes: The driving scenario area where the vehicle is located within each historical time window period is obtained based on the vertical motion feature data and the heading angle change feature data. The driving scenario area within each historical time window period is one of the following: ordinary road driving scenario area, entrance road driving scenario area, spiral ramp driving scenario area, and parking lot level road driving scenario area. When the vertical motion mode is determined to be either continuous ascent or continuous descent based on the vertical motion feature vector, and the steering motion mode is determined to be unidirectional continuous steering based on the heading angle change feature vector, the output that the vehicle is in a spiral ramp driving scenario area includes: Based on the driving scenario area where the vehicle is located within each historical time window period, the preset sequence of each driving scenario area, and the preset state transition conditions between driving scenario areas, it is verified whether the vehicle is in the spiral ramp driving scenario area within the current time window period. If the current driving scenario area of ​​the vehicle is verified to meet the set sequence and the corresponding state transition conditions, it is determined that the vehicle is in the spiral ramp driving scenario area.

6. The method for determining the vehicle driving scene area according to claim 5, characterized in that, The preset sequence includes the various driving scenario areas where the vehicle is located within multiple time window periods, arranged sequentially as follows: the ordinary road driving scenario area, the entrance road driving scenario area, the spiral ramp driving scenario area, and the parking lot level road driving scenario area.

7. The method for determining the vehicle driving scene area according to any one of claims 1-6, characterized in that, The step of determining the heading angle change characteristic data of the vehicle within the current time window period based on the first cumulative change and the second cumulative change includes: Calculate the ratio of the first cumulative change to the current time window period, and use it as the spiral motion index; Calculate the ratio of the second cumulative change to the first cumulative change, and use it as the steering consistency index; The helical motion index and the steering consistency index are used as the characteristic data of the heading angle change of the vehicle within the current time window period.

8. The method for determining the vehicle driving scene area according to claim 7, characterized in that, The method further includes: The variance of the rate of change of the heading angle of the vehicle within the current time window period is obtained as the steering stability index; The step of using the helical motion index and the steering consistency index as the characteristic data of the vehicle's heading angle change within the current time window period includes: The helical motion index, the steering consistency index, and the steering stability index are used as the characteristic data of the heading angle change.

9. The method for determining the vehicle driving scene area according to claim 1, characterized in that, The method further includes: Obtain vehicle air pressure change data within the current time window period; The acquisition of vehicle altitude change data within the current time window period includes: Acquire triaxial accelerometer data for the vehicle; Extract the vertical component of the vehicle within the current time window period from the triaxial accelerometer data; The vertical component is integrated twice to obtain the original elevation change data. The altitude change data is determined based on the original altitude change data and the air pressure change data.

10. The method for determining the vehicle driving scene area according to claim 1, characterized in that, The method further includes: Obtain the vehicle speed characteristic data within the current time window period; the vehicle speed characteristic data includes the vehicle's average speed data, speed standard deviation data, and stopping time percentage data within the current time window period; The step of inputting the vertical motion feature data and the heading angle change feature data into the classification model to obtain the driving scene area of ​​the vehicle includes: The vertical motion feature data, the heading angle change feature data, and the vehicle speed feature data are input into the classification model to obtain the driving scene area of ​​the vehicle.

11. A device for determining a vehicle driving scene area, characterized in that, The device includes: The acquisition module is used to acquire the vehicle's altitude change data, the first cumulative change of all heading angle changes, and the second cumulative change of the heading angle in the dominant direction within the current time window period; A vertical motion feature data determination module is used to determine the vertical motion feature data of the vehicle within the current time window period based on the altitude change data; the vertical motion feature data is used to characterize the vertical motion pattern of the vehicle. The heading angle change feature data determination module is used to determine the heading angle change feature data of the vehicle within the current time window period based on the first cumulative change amount and the second cumulative change amount; the heading angle change feature data is used to characterize the steering motion mode of the vehicle. The driving scene area determination module is used to input the vertical motion feature data and the heading angle change feature data into the classification model to obtain the driving scene area of ​​the vehicle.

12. A vehicle, characterized in that, The vehicle includes: a processor and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the vehicle driving scene area determination method as described in any one of claims 1-10.

13. A computer storage medium, characterized in that, The computer storage medium stores computer program instructions, which, when executed by a processor, implement the vehicle driving scene area determination method as described in any one of claims 1-10.

14. A computer program product, characterized in that, Includes a computer program, which, when executed, implements the vehicle driving scene area determination method as described in any one of claims 1-10.

Images