Trajectory detection method, apparatus, device, and medium

Abstract

The present disclosure relates to the technical field of map, in particular to a trajectory detection method and device, equipment and medium, the method comprises: acquiring trajectory point information of each trajectory point in a map data collection trajectory including a plurality of trajectory points; obtaining the heading angle difference sum of the trajectory points corresponding to each of the at least two first time intervals according to the trajectory point information; determining at least two turning time intervals from the at least two first time intervals according to the heading angle difference sum of the trajectory points corresponding to each of the at least two first time intervals; for any two turning time intervals, in response to the time difference of any two turning intervals being less than or equal to a second time length threshold, and the turning directions of any two turning time intervals being different, generating target trajectory indication information. The target trajectory indication information obtained based on the scheme can quickly and accurately determine the part of the map data collection trajectory matching the 8-shaped trajectory, which helps to improve the map data processing efficiency.

Description

Technical Field

[0001] This disclosure relates to the field of map technology, specifically to a trajectory detection method, apparatus, device, and medium. Background Technology

[0002] With technological advancements, electronic maps are evolving from standard-precision maps to high-precision maps. High-precision maps, also known as high-resolution maps (HD maps), primarily serve applications such as intelligent driving and smart city management. Compared to standard-precision maps, high-precision maps provide not only road-level network data but also lane-level road network data.

[0003] In related technologies, high-precision map data is typically collected along a corresponding trajectory using a map data acquisition device. To improve the accuracy of the collected map data, the map data acquisition device can be calibrated using a stereo figure-eight calibration method.

[0004] While the above-mentioned solutions can improve the accuracy of the collected map data, the accuracy of the map data collected by the map data acquisition device is often low when traveling along a figure-eight trajectory, which cannot meet the corresponding requirements. Therefore, it is necessary to determine the portion of the map data acquisition trajectory that matches the figure-eight trajectory in order to remove the data collected by the map data acquisition device while traveling along the figure-eight trajectory. The inventors of this disclosure have discovered that, compared with the prior art that relies on manual determination of the portion of the map data acquisition trajectory that matches the figure-eight trajectory, if the portion of the map data acquisition trajectory that matches the figure-eight trajectory can be determined more quickly and accurately, the efficiency of processing the corresponding map data can be effectively improved. Summary of the Invention

[0005] To address the problems in the related technologies, this disclosure provides a trajectory detection method, apparatus, device, and medium.

[0006] In a first aspect, this disclosure provides a trajectory detection method, including:

[0007] Acquire trajectory point information for each trajectory point in a map data acquisition trajectory that includes multiple trajectory points. The trajectory point information includes the trajectory time and trajectory heading angle.

[0008] Based on the trajectory point information, obtain the sum of the heading angle differences of the trajectory points corresponding to each of the two first time intervals, wherein the duration of the first time interval is less than or equal to the first duration threshold, and the sum of the heading angle differences is the sum of the heading angle differences of any adjacent trajectory points whose trajectory times belong to the same time interval;

[0009] Based on the sum of the heading angle differences of the trajectory points corresponding to at least two first time intervals, at least two turning time intervals are determined from at least two first time intervals, wherein the turning time interval is the first time interval in which the corresponding trajectory is in a turning state;

[0010] For any two turning time intervals, in response to the time difference between any two turning time intervals being less than or equal to the second duration threshold, and the trajectory turning directions corresponding to any two turning time intervals being different, target trajectory indication information is generated.

[0011] In one embodiment of this disclosure, determining a turning time interval from at least two first time intervals based on the sum of the heading angle differences between trajectory points corresponding to at least two first time intervals includes:

[0012] In response to the absolute value of the sum of heading angle differences corresponding to any first time interval being greater than or equal to the heading angle difference threshold, any first time interval is determined as a turning time interval.

[0013] In one embodiment of this disclosure, before determining any first time interval as a turning time interval in response to the absolute value of the sum of heading angle differences corresponding to any first time interval being greater than or equal to a heading angle difference threshold, the method further includes:

[0014] Obtain the average velocity of the trajectory corresponding to at least one second time interval, wherein the second time interval belongs to the first time interval;

[0015] In response to the absolute value of the sum of heading angle differences corresponding to any first time interval being greater than or equal to a heading angle difference threshold, any first time interval is determined as a turning time interval, including:

[0016] In response to the absolute value of the sum of heading angle differences corresponding to any first time interval being greater than or equal to the heading angle difference threshold, and the average velocity of the trajectory corresponding to each second time interval in any first time interval belonging to the first velocity interval, any first time interval is determined as the turning time interval.

[0017] In one embodiment of this disclosure, the trajectory turning directions corresponding to any two turning time intervals are different, including:

[0018] The product of the sum of the heading angle differences between any two turning time intervals is less than 0.

[0019] In one embodiment of this disclosure, before generating target trajectory indication information for any two turning time intervals, in response to the time difference between any two turning time intervals being less than or equal to a second duration threshold, and the trajectory turning directions corresponding to the two turning time intervals being different, the method further includes:

[0020] Obtain the average velocity of the trajectory corresponding to the third time interval, where the third time interval includes any two turning time intervals;

[0021] For any two turning time intervals, in response to the time difference between any two turning intervals being less than or equal to a second duration threshold, and the turning directions corresponding to the two turning time intervals being different, target trajectory indication information is generated, including:

[0022] For any two turning time intervals, in response to the time difference between any two turning intervals being less than or equal to the second duration threshold, the turning directions of the trajectories corresponding to the two turning time intervals being different, and the average speed of the trajectory corresponding to the third time interval belonging to the second speed interval, target trajectory indication information is generated.

[0023] In one embodiment of this disclosure, the map data sampling trajectory is obtained by sampling from the original trajectory according to a target sampling frequency, where the target sampling frequency is less than the original trajectory sampling frequency.

[0024] In one embodiment of this disclosure, the sum of heading angle differences is the sum of heading angle differences among any two adjacent trajectory points whose trajectory times belong to the same time interval and which belong to the target heading angle difference interval.

[0025] In one embodiment of this disclosure, the time difference between any two adjacent first time intervals is greater than or equal to a third duration threshold.

[0026] Secondly, this disclosure provides a trajectory detection device, comprising:

[0027] The trajectory point information acquisition module is configured to acquire trajectory point information for each trajectory point in a map data acquisition trajectory that includes multiple trajectory points. The trajectory point information includes the trajectory time and the trajectory heading angle.

[0028] The heading angle difference acquisition module is configured to acquire the heading angle difference sum of at least two first time intervals based on the trajectory point information, wherein the duration of the first time interval is less than or equal to a first duration threshold, and the heading angle difference sum is the sum of the heading angle differences of any adjacent trajectory points whose trajectory times belong to the same time interval;

[0029] The turning determination module is configured to determine at least two turning time intervals from at least two first time intervals based on the sum of the heading angle differences of the trajectory points corresponding to at least two first time intervals, wherein the turning time interval is the first time interval in which the corresponding trajectory is in a turning state;

[0030] The target trajectory detection module is configured to generate target trajectory indication information for any two turning time intervals, in response to the time difference between any two turning time intervals being less than or equal to a second duration threshold, and the turning directions corresponding to the two turning time intervals being different.

[0031] Thirdly, embodiments of this disclosure provide an electronic device including a memory and a processor, wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method as described in any one of the first aspects and any implementation thereof.

[0032] Fourthly, this disclosure provides a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the method described in the first aspect and any implementation thereof.

[0033] In the technical solution proposed in this disclosure, trajectory point information of each trajectory point in a map data acquisition trajectory including multiple trajectory points is obtained. The map data acquisition trajectory is used to collect map data to be processed, which can be understood as the map data acquisition device acquiring the corresponding map data while moving along the map data acquisition trajectory. Based on the trajectory point information, the sum of the heading angle differences of the trajectory points corresponding to at least two first time intervals is obtained. The duration of each first time interval is less than or equal to a first duration threshold, indicating that the probability of the map data acquisition device moving along an overly complex trajectory (e.g., a serpentine trajectory) within that first time interval is relatively low. Based on the sum of the heading angle differences of the trajectory points corresponding to at least two first time intervals, at least two turning time intervals are determined from the at least two first time intervals. Within one turning time interval, the map data acquisition device may have turned in one direction while moving. For any two turning time intervals, the time difference between any two turning time intervals is less than or equal to a second duration threshold, and the time difference between any two turning time intervals is less than or equal to a second duration threshold. The trajectory turning directions corresponding to each interval are different, generating target trajectory indication information. Since the trajectory turning directions corresponding to any two turning time intervals are different, it can be assumed that the map data acquisition device turned in different directions successively during its movement. If the time difference between any two turning intervals is less than or equal to a second time threshold, it can be assumed that the probability of the map data acquisition device moving along an overly complex trajectory between any two turning intervals is low. Since the probability of a trajectory turning in two different directions successively being a figure-eight trajectory is high, this scheme generates target trajectory indication information to indicate that the trajectory of the map data acquisition device in at least any two turning time intervals is a figure-eight trajectory. Based on this target trajectory indication information, the portion of the map data acquisition trajectory that matches the figure-eight trajectory can be quickly and accurately determined. This allows for the removal of the portion of the map data collected by the map data acquisition device while moving along the figure-eight trajectory to obtain higher-precision map data, which helps improve the efficiency of processing the corresponding map data and enhances the user experience.

[0034] In the technical solution proposed in this disclosure, since the duration of the first time interval is less than or equal to the first duration threshold, it can be considered that the probability of the map data acquisition device moving along an overly complex trajectory (such as a serpentine trajectory) within the first time interval is small. However, when the absolute value of the sum of the heading angle differences corresponding to the first time interval is greater than or equal to the sum of the heading angle differences and the threshold, it can be considered that the probability of the map data acquisition device turning in one direction within the first time interval is high. Therefore, by determining any first time interval as a turning time interval in response to the absolute value of the sum of the heading angle differences corresponding to any first time interval being greater than or equal to the sum of the heading angle differences and the threshold, the accuracy of the determined turning time interval can be improved.

[0035] In the technical solution proposed in this disclosure, by acquiring the average speed of the trajectory corresponding to at least one second time interval, and in response to the absolute value of the sum of the heading angle differences corresponding to any first time interval being greater than or equal to a threshold, and the average speed of the trajectory corresponding to each second time interval in any first time interval belonging to a first speed interval, any first time interval is determined as a turning time interval. Since the map data acquisition device is moving along a figure-eight trajectory, if it turns in one direction, it is usually in a state of continuous movement at a relatively slow speed during this process. Therefore, by limiting the upper limit of the average speed corresponding to the second time interval in the first time interval, it can be ensured that false detections will not occur due to the map data acquisition device moving too fast, thus improving the accuracy of the determined turning time interval.

[0036] In the technical solution proposed in this disclosure, by limiting the difference in trajectory turning direction between any two turning time intervals to include a product of the sum of the heading angle differences between any two turning time intervals being less than 0, the accuracy of determining the difference in trajectory turning direction between any two turning time intervals can be improved.

[0037] In the technical solution proposed in this disclosure, considering that when the map data acquisition device moves along the figure-eight trajectory, it is usually in a state of continuous movement and slow speed not only when turning in one direction, but also when switching from turning in one direction to turning in another direction, the target trajectory indication information is generated for any two turning time intervals. This is done in response to the time difference between any two turning time intervals being less than or equal to a second duration threshold, the trajectory turning directions corresponding to the two turning time intervals being different, and the average speed of the trajectory corresponding to the third time interval including any two turning time intervals belonging to the second speed interval. This can improve the accuracy of determining the part of the map data acquisition trajectory that matches the figure-eight trajectory based on the target trajectory indication information.

[0038] In the technical solution proposed in this disclosure, by limiting the map data sampling trajectory to be sampled from the original trajectory according to the target sampling frequency, and the target sampling frequency being less than the original trajectory sampling frequency, it can be ensured that the map data sampling trajectory can accurately reflect the state of the original trajectory when the map data acquisition device is collecting data, under the premise that the amount of data sampled from the original trajectory is small. This helps to improve the accuracy of determining the part of the map data acquisition trajectory that matches the figure-eight trajectory based on the target trajectory indication signal.

[0039] In the technical solution proposed in this disclosure, by limiting the sum of heading angle differences to the sum of heading angle differences among any two adjacent trajectory points belonging to the target heading angle difference interval within the same time interval, errors in the sum of heading angle differences due to errors in the trajectory point information corresponding to a few trajectory points can be avoided, thereby improving the accuracy of the sum of heading angle differences. This helps to improve the accuracy of determining the part of the map data collection trajectory that matches the figure-eight trajectory based on the target trajectory indication information.

[0040] In the technical solution proposed in this disclosure, by limiting the time difference between any two adjacent first time intervals to be greater than or equal to a third duration threshold, it is possible to avoid two first time intervals that are too close to each other. This improves the accuracy of determining whether the high-precision map data acquisition device moves along the figure-eight trajectory in the corresponding time interval while minimizing the amount of data processing, and also improves the accuracy of determining the part of the map data acquisition trajectory that matches the figure-eight trajectory based on the target trajectory indication signal.

[0041] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0042] Other features, objects, and advantages of this disclosure will become more apparent from the following detailed description of non-limiting embodiments, taken in conjunction with the accompanying drawings. In the drawings:

[0043] Figure 1 A flowchart illustrating a trajectory detection method according to an embodiment of the present disclosure is shown.

[0044] Figure 2 A schematic diagram of a map data acquisition trajectory according to an embodiment of the present disclosure is shown.

[0045] Figure 3 A schematic diagram of a map data acquisition trajectory according to an embodiment of the present disclosure is shown.

[0046] Figure 4 A structural block diagram of a trajectory detection apparatus according to an embodiment of the present disclosure is shown.

[0047] Figure 5 A structural block diagram of an electronic device according to an embodiment of the present disclosure is shown.

[0048] Figure 6 A schematic diagram of the structure of a computer system suitable for implementing the method according to embodiments of the present disclosure is shown. Detailed Implementation

[0049] In the following, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings to enable those skilled in the art to readily implement them. Furthermore, for clarity, portions unrelated to the description of exemplary embodiments have been omitted from the drawings.

[0050] In this disclosure, it should be understood that terms such as “comprising” or “having” are intended to indicate the presence of features, figures, steps, behaviors, components, parts or combinations thereof disclosed in this specification, and are not intended to exclude the possibility of the presence or addition of one or more other features, figures, steps, behaviors, components, parts or combinations thereof.

[0051] It should also be noted that, unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other. This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0052] In this disclosure, any operation involving the acquisition of user information or user data, or the display of user information or user data to others, is an operation authorized or confirmed by the user, or actively selected by the user.

[0053] In related technologies, high-precision map data is collected by a high-precision map data acquisition device along a corresponding trajectory. For example, a high-precision map data acquisition device can be mounted on a vehicle and driven along the corresponding trajectory, during which the high-precision map data is collected by the high-precision map data acquisition device mounted on the vehicle.

[0054] The high-precision map data acquisition device relies on its own electronic compass to collect high-precision map data. However, the electronic compass is affected by the Earth's magnetic field during use. Therefore, to improve the accuracy of the acquired map data, the electronic compass needs to be calibrated. Specifically, the electronic compass can be calibrated using a three-dimensional figure-eight calibration method. This involves the high-precision map data acquisition device with its electronic compass traveling along a figure-eight trajectory, during which the electronic compass can complete the calibration process.

[0055] While this approach improves the calibration accuracy of the electronic compass in the high-precision map data acquisition device, the point cloud data collected by the device while traveling along a figure-eight trajectory is often difficult to distinguish, resulting in lower accuracy and making the high-precision map data unsuitable for the required specifications. Furthermore, the large volume of point cloud data collected during this process significantly increases the difficulty of processing it. Therefore, related technologies require identifying the portion of the map data acquisition trajectory that matches the figure-eight trajectory in order to remove the data collected during this phase.

[0056] In one approach, the portion of the map data collection trajectory that matches the figure-eight trajectory can be determined manually. This involves operators viewing the map data collection trajectory using a display device and inputting figure-eight trajectory identification information via a human-computer interaction device such as a keyboard, mouse, or touchscreen. This allows them to determine the portion of the map data collection trajectory that matches the figure-eight trajectory based on the figure-eight trajectory identification information.

[0057] The inventors of this disclosure have discovered that, since this scheme relies on manual labor, the speed of determining the part of the map data collection trajectory that matches the figure-eight trajectory is slow and the accuracy is low. Therefore, if the part of the map data collection trajectory that matches the figure-eight trajectory can be determined more quickly and accurately, the efficiency of processing the corresponding map data can be effectively improved.

[0058] The inventors of this disclosure propose a new solution: This solution acquires trajectory point information for each trajectory point in a map data acquisition trajectory that includes multiple trajectory points. The map data acquisition trajectory is used to collect map data to be processed; that is, the map data acquisition device collects the corresponding map data while moving along the map data acquisition trajectory. Based on the trajectory point information, the solution obtains the sum of the heading angle differences of the trajectory points corresponding to at least two first time intervals. The duration of each first time interval is less than or equal to a first duration threshold, indicating that the probability of the map data acquisition device moving along an overly complex trajectory (e.g., a serpentine trajectory) within that first time interval is relatively low. Based on the sum of the heading angle differences of the trajectory points corresponding to at least two first time intervals, at least two turning time intervals are determined from the at least two first time intervals. Within one turning time interval, the map data acquisition device may have turned in more than one direction while moving. For any two turning time intervals, the time difference between any two turning intervals is less than or equal to a second duration threshold, and the time difference between any two turning intervals is less than or equal to a second duration threshold. By generating target trajectory indication information based on the different turning directions corresponding to the time intervals, it can be assumed that the map data acquisition device has turned in different directions during its movement if the turning directions of any two turning time intervals are different. If the time difference between any two turning intervals is less than or equal to a second time duration threshold, it can be assumed that the probability of the map data acquisition device moving along an overly complex trajectory between any two turning intervals is small. Since the probability of a trajectory that turns in two different directions is a figure-eight trajectory is relatively high, this scheme generates target trajectory indication information to indicate that the trajectory of the map data acquisition device is a figure-eight trajectory at least in any two turning time intervals. Based on this target trajectory indication information, the portion of the map data acquisition trajectory that matches the figure-eight trajectory can be quickly and accurately determined. This allows for the removal of the portion of the map data collected by the map data acquisition device while moving along the figure-eight trajectory to obtain higher-precision map data, which helps improve the efficiency of processing the corresponding map data and enhances the user experience.

[0059] Figure 1 A flowchart illustrating a trajectory detection method according to an embodiment of the present disclosure is shown. Figure 1 As shown, the trajectory detection method includes the following steps S101-S104:

[0060] In step S101, the trajectory point information of each trajectory point in the map data acquisition trajectory, which includes multiple trajectory points, is obtained;

[0061] The trajectory point information includes the trajectory time and trajectory heading angle;

[0062] In step S102, the heading angle difference values ​​of at least two first time intervals are obtained based on the trajectory point information;

[0063] Wherein, the duration of the first time interval is less than or equal to the first duration threshold, and the sum of heading angle differences is the sum of the heading angle differences of any adjacent trajectory points whose trajectory times belong to the same time interval;

[0064] In step S103, at least two turning time intervals are determined from the at least two first time intervals based on the sum of the heading angle differences of the trajectory points corresponding to the at least two first time intervals.

[0065] Among them, the turning time interval is the first time interval in which the corresponding trajectory is in a turning state;

[0066] In step S104, for any two turning time intervals, in response to the time difference between any two turning time intervals being less than or equal to the second duration threshold, and the trajectory turning directions corresponding to any two turning time intervals being different, target trajectory indication information is generated.

[0067] In one embodiment of this disclosure, the map data acquisition trajectory can be understood as the process by which the map data acquisition device acquires map data while moving along the map data acquisition trajectory to obtain map data to be processed, wherein the map data to be processed may include high-precision map data to be processed. During this process, in order to calibrate the electronic compass in the map data acquisition device, the map data acquisition trajectory may include a figure-eight pattern.

[0068] In one embodiment of this disclosure, the trajectory time can be understood as the time when the map data acquisition device samples map data at the corresponding trajectory point. The trajectory heading angle can be understood as the heading angle of the map data sampling device when it passes the corresponding trajectory point during its movement.

[0069] In one embodiment of this disclosure, obtaining the trajectory point information of each trajectory point in the map data acquisition trajectory can be understood as reading the trajectory point information of each trajectory point in the map data acquisition trajectory that has been stored in advance, or it can be understood as receiving the trajectory point information of each trajectory point in the map data acquisition trajectory sent by a corresponding device or system (such as a map data acquisition device).

[0070] In one embodiment of this disclosure, the first time interval can be understood as any time interval between the earliest trajectory time corresponding to the map data acquisition trajectory and the latest trajectory time corresponding to the map data acquisition trajectory, where the duration is less than or equal to a first duration threshold. It should be noted that different first time intervals have the same duration; for example, the duration of each first time interval can be 25 seconds. The first duration threshold can be preset, obtained from a corresponding device or system, or obtained based on a first duration threshold indication input through a corresponding human-computer interaction device. By limiting the duration of the first time interval to be less than or equal to the first duration threshold, it can be ensured that the probability of the map data acquisition device moving along an overly complex trajectory (e.g., a serpentine trajectory) during its movement within the first time interval is relatively small.

[0071] In one embodiment of this disclosure, the sum of the heading angle differences of trajectory points corresponding to the first time interval can be understood as the sum of the heading angle differences of any two adjacent trajectory points within the first time interval. The heading angle difference between two adjacent trajectory points can be understood as the difference between the heading angle of the trajectory point with the later trajectory time and the heading angle of the trajectory point with the earlier trajectory time. The heading angle corresponding to a trajectory point can be understood as the angle between the direction of movement of the map acquisition device and the horizontal axis of the ground coordinate system at the corresponding trajectory point.

[0072] For example, Figure 2 A schematic diagram illustrating a map data collection trajectory according to an embodiment of the present disclosure is shown, such as... Figure 2 As shown, the map data acquisition trajectory 200 includes trajectory points 201-205, where the acquisition times of trajectory points 202-204 all belong to the first time interval. The difference between the heading angle of trajectory point 203 and the heading angle of trajectory point 202 is the first heading angle difference, and the difference between the heading angle of trajectory point 204 and the heading angle of trajectory point 203 is the second heading angle difference. The sum of the first heading angle difference and the second heading angle difference is the sum of the heading angle differences corresponding to the first time interval.

[0073] In one embodiment of this disclosure, at least two turning time intervals are determined from at least two first time intervals based on the sum of the heading angle differences of the trajectory points corresponding to each of the at least two first time intervals. This can be understood as using a pre-acquired turning time interval determination algorithm, substituting the sum of the heading angle differences of the trajectory points corresponding to each of the at least two first time intervals into the algorithm to obtain the calculation result, and then determining at least two turning time intervals from the at least two first time intervals based on the calculation result. Alternatively, a turning time interval model obtained in advance can be acquired, and the sum of the heading angle differences of the trajectory points corresponding to each of the at least two first time intervals can be used as input to the turning time interval model. The at least two turning time intervals can then be determined from the at least two first time intervals based on the output of the turning time interval model. This disclosure does not limit the specific implementation method of determining at least two turning time intervals from at least two first time intervals based on the sum of the heading angle differences of the trajectory points corresponding to each of the at least two first time intervals.

[0074] In one embodiment of this disclosure, the time difference between two first time intervals can be understood as the time difference between the start time of the earlier first time interval and the start time of the later first time interval; the time difference between two first time intervals can also be understood as the time difference between the end time of the earlier first time interval and the end time of the later first time interval.

[0075] In one embodiment of this disclosure, the trajectory turning directions corresponding to the two turning time intervals are different. This can be understood as the trajectory turning direction corresponding to one turning time interval being clockwise, while the trajectory turning direction corresponding to the other turning time interval being counterclockwise; or, it can be understood as the trajectory turning direction corresponding to one turning time interval being counterclockwise, while the trajectory turning direction corresponding to the other turning time interval being clockwise.

[0076] In one embodiment of this disclosure, determining whether the trajectory turning directions corresponding to the two turning time intervals are the same can be achieved by substituting the difference in heading angles corresponding to the two turning time intervals into a pre-acquired trajectory turning direction algorithm for calculation, and determining whether the trajectory turning directions corresponding to the two turning time intervals are the same based on the calculation results; alternatively, a pre-trained trajectory turning direction judgment model can be obtained, the difference in heading angles corresponding to the two turning time intervals can be used as input to the trajectory turning direction judgment model, and the output of the trajectory turning direction judgment model can be used to determine whether the trajectory turning directions corresponding to the two turning time intervals are the same. This disclosure does not limit the specific implementation method for determining whether the trajectory turning directions corresponding to the two turning time intervals are the same.

[0077] In one embodiment of this disclosure, the target trajectory indication information can be understood as indicating that the trajectory of the map data acquisition device during at least two turning time intervals is a figure-eight trajectory, meaning that the map data acquired by the map data acquisition device during any two turning time intervals matches the figure-eight trajectory. Alternatively, the target trajectory indication information can also be understood as indicating that the trajectories corresponding to both the two turning time intervals and the trajectories between the two turning time intervals are figure-eight trajectories, meaning that the map data acquired by the map data acquisition device during both the two turning time intervals and the trajectories between the two turning time intervals match the figure-eight trajectory.

[0078] In the technical solution proposed in this disclosure, trajectory point information of each trajectory point in a map data acquisition trajectory including multiple trajectory points is obtained. The map data acquisition trajectory is used to collect map data to be processed, which can be understood as the map data acquisition device acquiring the corresponding map data while moving along the map data acquisition trajectory. Based on the trajectory point information, the sum of the heading angle differences of the trajectory points corresponding to at least two first time intervals is obtained. The duration of each first time interval is less than or equal to a first duration threshold, indicating that the probability of the map data acquisition device moving along an overly complex trajectory (e.g., a serpentine trajectory) within that first time interval is relatively low. Based on the sum of the heading angle differences of the trajectory points corresponding to at least two first time intervals, at least two turning time intervals are determined from the at least two first time intervals. Within one turning time interval, the map data acquisition device may have turned in one direction while moving. For any two turning time intervals, the time difference between any two turning time intervals is less than or equal to a second duration threshold, and the time difference between any two turning time intervals is less than or equal to a second duration threshold. The trajectory turning directions corresponding to each interval are different, generating target trajectory indication information. Since the trajectory turning directions corresponding to any two turning time intervals are different, it can be assumed that the map data acquisition device turned in different directions successively during its movement. If the time difference between any two turning intervals is less than or equal to a second time threshold, it can be assumed that the probability of the map data acquisition device moving along an overly complex trajectory between any two turning intervals is low. Since the probability of a trajectory turning in two different directions successively being a figure-eight trajectory is high, this scheme generates target trajectory indication information to indicate that the trajectory of the map data acquisition device in at least any two turning time intervals is a figure-eight trajectory. Based on this target trajectory indication information, the portion of the map data acquisition trajectory that matches the figure-eight trajectory can be quickly and accurately determined. This allows for the removal of the portion of the map data collected by the map data acquisition device while moving along the figure-eight trajectory to obtain higher-precision map data, which helps improve the efficiency of processing the corresponding map data and enhances the user experience.

[0079] In one embodiment of this disclosure, determining a turning time interval from at least two first time intervals based on the sum of the heading angle differences between trajectory points corresponding to at least two first time intervals includes:

[0080] In response to the absolute value of the sum of heading angle differences corresponding to any first time interval being greater than or equal to the heading angle difference threshold, any first time interval is determined as a turning time interval.

[0081] In one embodiment of this disclosure, the heading angle difference and threshold can be understood as being preset, or as being obtained from a corresponding device or system, or as being obtained through heading angle difference and threshold indication information input by a corresponding human-machine interaction device. For example, the heading angle difference and threshold can be 155°.

[0082] For example, Figure 3 A schematic diagram illustrating a map data collection trajectory according to an embodiment of the present disclosure is shown, such as... Figure 3 As shown, the map data acquisition trajectory 200 includes trajectory points 201-209. The acquisition times of trajectory points 202-204 all belong to a first time interval. The difference between the heading angle of trajectory point 202 and the heading angle of trajectory point 203 is the first heading angle difference, and the difference between the heading angle of trajectory point 203 and the heading angle of trajectory point 204 is the second heading angle difference. The sum of the first heading angle difference and the second heading angle difference is the sum of the first heading angle differences corresponding to the first time interval. When the absolute value of the sum of the first heading angle differences is greater than or equal to a heading angle difference threshold, the first time interval corresponding to trajectory points 202-204 can be considered a turning time interval.

[0083] The acquisition times of trajectory points 206-208 all belong to another first time interval. The difference between the heading angle of trajectory point 206 and the heading angle of trajectory point 207 is the third heading angle difference, and the difference between the heading angle of trajectory point 207 and the heading angle of trajectory point 208 is the fourth heading angle difference. The sum of the third and fourth heading angle differences is the sum of the second heading angle differences corresponding to this other first time interval. Wherein, when the absolute value of the sum of the second heading angle differences is greater than or equal to the heading angle difference threshold, the first time interval corresponding to trajectory points 206-208 can be considered the turning time interval.

[0084] In the technical solution proposed in this disclosure, since the duration of the first time interval is less than or equal to the first duration threshold, it can be considered that the probability of the map data acquisition device moving along an overly complex trajectory (such as a serpentine trajectory) within the first time interval is small. However, when the absolute value of the sum of the heading angle differences corresponding to the first time interval is greater than or equal to the sum of the heading angle differences and the threshold, it can be considered that the probability of the map data acquisition device turning in one direction within the first time interval is high. Therefore, by determining any first time interval as a turning time interval in response to the absolute value of the sum of the heading angle differences corresponding to any first time interval being greater than or equal to the sum of the heading angle differences and the threshold, the accuracy of the determined turning time interval can be improved.

[0085] In one embodiment of this disclosure, before determining any first time interval as a turning time interval in response to the absolute value of the sum of heading angle differences corresponding to any first time interval being greater than or equal to a heading angle difference threshold, the method further includes:

[0086] Obtain the average velocity of the trajectory corresponding to at least one second time interval, wherein the second time interval belongs to the first time interval;

[0087] In response to the absolute value of the sum of heading angle differences corresponding to any first time interval being greater than or equal to a heading angle difference threshold, any first time interval is determined as a turning time interval, including:

[0088] In response to the absolute value of the sum of heading angle differences corresponding to any first time interval being greater than or equal to the heading angle difference threshold, and the average velocity of the trajectory corresponding to each second time interval in any first time interval belonging to the first velocity interval, any first time interval is determined as the turning time interval.

[0089] In one embodiment of this disclosure, the second time interval can be understood as a time interval within each first time interval whose duration is shorter than the duration of the first time interval. It should be noted that the duration of different second time intervals is the same. For example, the duration of the second time interval can be 3 seconds.

[0090] In one embodiment of this disclosure, the average speed corresponding to the second time interval can be understood as the average speed of the map data sampling device moving within the second time interval. Obtaining the average speed corresponding to the second time interval can be achieved by: obtaining the trajectory distance between the position of the earliest trajectory point and the position of the latest trajectory point within the second time interval (i.e., the trajectory distance corresponding to the second time interval); obtaining the trajectory time difference between the earliest and latest trajectory points within the second time interval (i.e., the trajectory time difference corresponding to the second time interval) based on the trajectory point information; and calculating the ratio between the trajectory distance and the trajectory time difference to obtain the average speed corresponding to the second time interval. Alternatively, it can be achieved by reading pre-stored average speed data corresponding to the second time interval and obtaining the average speed based on this data. It can also be achieved by receiving average speed data corresponding to the second time interval sent by a corresponding device or system and obtaining the average speed based on this data.

[0091] In one embodiment of this disclosure, the first speed range can be understood as being preset, obtained from a corresponding device or system, or obtained based on first speed range indication information input through a corresponding human-computer interaction device. For example, the first speed range can be understood as greater than or equal to 1 meter per second and less than or equal to 8 meters per second.

[0092] For example, such as Figure 3 As shown, the map data collection trajectory 200 includes trajectory points 201-209, where the collection times of trajectory points 202-204 all belong to a first time interval, and the duration of the first time interval is 25 seconds, which satisfies the condition that the duration of the first time interval is less than or equal to the first duration threshold.

[0093] The difference between the heading angle of trajectory point 202 and the heading angle of trajectory point 203 is the first heading angle difference, and the difference between the heading angle of trajectory point 203 and the heading angle of trajectory point 204 is the second heading angle difference. The sum of the first heading angle difference and the second heading angle difference is the sum of the first heading angle differences corresponding to the first time interval.

[0094] When the absolute value of the sum of the first heading angle differences is greater than or equal to 155° (that is, the absolute value of the sum of the first heading angle differences is greater than or equal to the heading angle difference threshold), and the average speed of the trajectory corresponding to any second time interval with a duration of 3 seconds in the first time interval where trajectory point 202-204 is located belongs to the first speed interval of (1m / s, 8m / s), the first time interval where trajectory point 202-204 is located is determined to be the turning time interval;

[0095] The acquisition times of trajectory points 206-208 all belong to another first time interval, the duration of which is 25 seconds. The time difference between the first time interval containing trajectory points 202-204 and the first time interval containing trajectory points 206-208 is 2 seconds.

[0096] The difference between the heading angle of trajectory point 206 and the heading angle of trajectory point 207 is the third heading angle difference, and the difference between the heading angle of trajectory point 207 and the heading angle of trajectory point 208 is the fourth heading angle difference. The sum of the third heading angle difference and the fourth heading angle difference is the sum of the second heading angle difference corresponding to the other first time interval.

[0097] When the absolute value of the sum of the second heading angle differences is greater than or equal to 155° (i.e., the absolute value of the sum of the second heading angle differences is greater than or equal to the heading angle difference threshold), and the average speed of the trajectory corresponding to any second time interval with a duration of 3 seconds in the first time interval where trajectory point 206-208 is located belongs to the first speed interval of (1m / s, 8m / s), the first time interval where trajectory point 206-208 is located is determined to be the turning time interval.

[0098] In the technical solution proposed in this disclosure, by acquiring the average speed of the trajectory corresponding to at least one second time interval, and in response to the absolute value of the sum of the heading angle differences corresponding to any first time interval being greater than or equal to a threshold, and the average speed of the trajectory corresponding to each second time interval in any first time interval belonging to a first speed interval, any first time interval is determined as a turning time interval. Since the map data acquisition device is moving along a figure-eight trajectory, if it turns in one direction, it is usually in a state of continuous movement at a relatively slow speed during this process. Therefore, by limiting the average speed corresponding to the second time interval in the first time interval, it can be ensured that false detections will not occur due to the map data acquisition device moving too fast, thus improving the accuracy of the determined turning time interval.

[0099] In one embodiment of this disclosure, the trajectory turning directions corresponding to any two turning time intervals are different, including:

[0100] The product of the sum of the heading angle differences between any two turning time intervals is less than 0.

[0101] In one embodiment of this disclosure, the product of the sum of the heading angle differences corresponding to any two turning time intervals is less than 0. This can be understood as the sum of the heading angle differences corresponding to one of the two turning time intervals being greater than 0, while the sum of the heading angle differences corresponding to the other turning time interval is less than 0.

[0102] For example, such as Figure 3As shown, the map data acquisition trajectory 200 includes trajectory points 201-209. The acquisition times of trajectory points 202-204 all belong to one turning time interval, while the acquisition times of trajectory points 206-208 all belong to another turning time interval. The difference between the heading angles of trajectory point 202 and 203 is the first heading angle difference; the difference between the heading angles of trajectory point 203 and 204 is the second heading angle difference; and the sum of the first and second heading angle differences is the sum of the first heading angle differences corresponding to the first time interval. The difference between the heading angles of trajectory point 206 and 207 is the third heading angle difference; and the difference between the heading angles of trajectory point 207 and 208 is the fourth heading angle difference; and the sum of the third and fourth heading angle differences is the sum of the second heading angle differences corresponding to the other turning time interval. If the product of the sum of the first heading angle differences and the sum of the second heading angle differences is less than 0, then the turning direction of the trajectory corresponding to trajectory point 202-204 is different from the turning direction of the trajectory corresponding to trajectory point 206-208. That is, the turning direction of the trajectory corresponding to the above-mentioned one turning time interval is different from that of the above-mentioned other turning time interval.

[0103] In the technical solution proposed in this disclosure, by limiting the difference in trajectory turning direction between any two turning time intervals to include a product of the sum of the heading angle differences between any two turning time intervals being less than 0, the accuracy of determining the difference in trajectory turning direction between any two turning time intervals can be improved.

[0104] In one embodiment of this disclosure, before generating target trajectory indication information for any two turning time intervals, in response to the time difference between any two turning time intervals being less than or equal to a second duration threshold, and the trajectory turning directions corresponding to the two turning time intervals being different, the method further includes:

[0105] Obtain the average velocity of the trajectory corresponding to the third time interval, where the third time interval includes any two turning time intervals;

[0106] For any two turning time intervals, in response to the time difference between any two turning intervals being less than or equal to a second duration threshold, and the turning directions corresponding to the two turning time intervals being different, target trajectory indication information is generated, including:

[0107] For any two turning time intervals, in response to the time difference between any two turning intervals being less than or equal to the second duration threshold, and the turning directions of the trajectories corresponding to any two turning time intervals being different, and the average speed of the trajectory corresponding to the third time interval belonging to the second speed interval, target trajectory indication information is generated.

[0108] For example, such as Figure 3 As shown, the map data collection trajectory 200 includes trajectory points 201-209, where the collection times of trajectory points 202-204 all belong to one turning time interval, and the collection times of trajectory points 206-208 all belong to another turning time interval, and the time difference between the two turning time intervals is less than or equal to 45 seconds (that is, it satisfies the condition that the time difference between the two turning intervals is less than or equal to the second duration threshold).

[0109] The difference between the heading angle of trajectory point 202 and the heading angle of trajectory point 203 is the first heading angle difference, and the difference between the heading angle of trajectory point 203 and the heading angle of trajectory point 204 is the second heading angle difference. The sum of the first heading angle difference and the second heading angle difference is the sum of the first heading angle differences corresponding to the first time interval.

[0110] The difference between the heading angle of trajectory point 206 and the heading angle of trajectory point 207 is the third heading angle difference, and the difference between the heading angle of trajectory point 207 and the heading angle of trajectory point 208 is the fourth heading angle difference. The sum of the third heading angle difference and the fourth heading angle difference is the sum of the second heading angle difference corresponding to the other turning time interval.

[0111] If the product of the sum of the first heading angle differences and the sum of the second heading angle differences is less than 0, then the turning direction of the trajectory corresponding to trajectory point 202-204 is different from the turning direction of the trajectory corresponding to trajectory point 206-208 (that is, the turning directions of the trajectories corresponding to the above two turning time intervals are different).

[0112] Furthermore, if the average speed of the third time interval, which includes the two turning time intervals mentioned above, is within the second speed interval of (1 m / s, 8 m / s), then target trajectory indication information can be generated, indicating that the trajectory of the map data acquisition device is a figure-eight trajectory at least during the two turning time intervals mentioned above.

[0113] In one embodiment of this disclosure, the average speed corresponding to the third time interval can be understood as the average speed at which the map data sampling device moves within the third time interval. Obtaining the average speed corresponding to the third time interval can be achieved by: obtaining the trajectory distance between the earliest trajectory point and the latest trajectory point within the third time interval (i.e., the trajectory distance corresponding to the third time interval) based on trajectory point information; obtaining the trajectory time difference between the earliest and latest trajectory points within the third time interval (i.e., the trajectory time difference corresponding to the third time interval) based on trajectory point information; and calculating the ratio between the trajectory distance and the trajectory time difference to obtain the average speed corresponding to the third time interval. Alternatively, it can be achieved by reading pre-stored average speed data corresponding to the third time interval and obtaining the average speed based on this data. It can also be achieved by receiving average speed data corresponding to the third time interval sent by a corresponding device or system and obtaining the average speed based on this data.

[0114] In one embodiment of this disclosure, the second speed range can be understood as being preset, or as being obtained from a corresponding device or system, or as being obtained based on second speed range indication information input through a corresponding human-computer interaction device. For example, the first speed range can be understood as greater than or equal to 1 meter per second and less than or equal to 8 meters per second.

[0115] In the technical solution proposed in this disclosure, considering that when the map data acquisition device moves along the figure-eight trajectory, it is usually in a state of continuous movement and slow speed not only when turning in one direction, but also when switching from turning in one direction to turning in another direction, the target trajectory indication information is generated for any two turning time intervals. This is done in response to the time difference between any two turning time intervals being less than or equal to a second duration threshold, the trajectory turning directions corresponding to the two turning time intervals being different, and the average speed of the trajectory corresponding to the third time interval including any two turning time intervals belonging to the second speed interval. This can improve the accuracy of determining the part of the map data acquisition trajectory that matches the figure-eight trajectory based on the target trajectory indication information.

[0116] In one embodiment of this disclosure, the map data sampling trajectory is obtained by sampling from the original trajectory according to a target sampling frequency, where the target sampling frequency is less than the original trajectory sampling frequency.

[0117] In one embodiment of this disclosure, the target sampling frequency can be understood as the time difference between the corresponding trajectory times of two adjacent trajectory points in the map data sampling trajectory, that is, how often the trajectory point information corresponding to a trajectory point is collected from the original trajectory. For example, the sampling frequency threshold is 10 Hz, that is, trajectory point information corresponding to a trajectory point is collected every 0.1 seconds.

[0118] In one embodiment of this disclosure, the original trajectory can be understood as the trajectory recorded by the map data acquisition device when it collects data. When the accuracy of the data collected by the map data acquisition device is high, the amount of data in the original trajectory is large.

[0119] In the technical solution proposed in this disclosure, by limiting the map data sampling trajectory to be sampled from the original trajectory according to the target sampling frequency, and the target sampling frequency being less than the original trajectory sampling frequency, it can be ensured that the amount of data sampled from the original trajectory is small, so that the trajectory point information can accurately reflect the state of the original trajectory when the map data acquisition device is collecting data. This helps to improve the accuracy of determining the part of the map data acquisition trajectory that matches the figure-eight trajectory based on the target trajectory indication signal.

[0120] In one embodiment of this disclosure, the sum of heading angle differences is the sum of heading angle differences among any two adjacent trajectory points whose trajectory times belong to the same time interval and which belong to the target heading angle difference interval.

[0121] In one embodiment of this disclosure, the target heading angle difference range can be understood as being preset, or it can be understood as being obtained from a corresponding device or system, or it can be obtained based on the target heading angle difference range indication information input through a corresponding human-machine interaction device. For example, the target heading angle difference range can be understood as being greater than or equal to -18° and less than or equal to 18°.

[0122] In the technical solution proposed in this disclosure, by limiting the sum of heading angle differences to the sum of heading angle differences among any two adjacent trajectory points belonging to the target heading angle difference interval within the same time interval, errors in the sum of heading angle differences due to errors in the trajectory point information corresponding to a few trajectory points can be avoided, thereby improving the accuracy of the sum of heading angle differences. This helps to improve the accuracy of determining the part of the map data collection trajectory that matches the figure-eight trajectory based on the target trajectory indication information.

[0123] In one embodiment of this disclosure, the time difference between any two adjacent first time intervals is greater than or equal to a third duration threshold.

[0124] In one embodiment of this disclosure, the third duration threshold can be understood as being preset, or it can be understood as being obtained from a corresponding device or system, or it can be obtained based on third duration threshold indication information input through a corresponding human-computer interaction device. For example, the third duration threshold can be understood as 2 seconds.

[0125] In the technical solution proposed in this disclosure, by limiting the time difference between any two adjacent first time intervals to be greater than or equal to a third time duration threshold, it is possible to avoid two first time intervals that are too close to each other. This improves the accuracy of determining whether the map data acquisition device moves along the figure-eight trajectory in the corresponding time interval while minimizing the amount of data processing, and also improves the accuracy of determining the part of the map data acquisition trajectory that matches the figure-eight trajectory based on the target trajectory indication signal.

[0126] Figure 4 A structural block diagram of a trajectory detection device according to an embodiment of the present disclosure is shown. This device can be implemented as part or all of an electronic device through software, hardware, or a combination of both.

[0127] like Figure 4 As shown, the trajectory detection device 300 includes:

[0128] The trajectory point information acquisition module 301 is configured to acquire trajectory point information for each trajectory point in a map data acquisition trajectory that includes multiple trajectory points. The trajectory point information includes the trajectory time and the trajectory heading angle.

[0129] The heading angle difference acquisition module 302 is configured to acquire the heading angle difference sum of at least two first time intervals corresponding to the trajectory points based on the trajectory point information, wherein the duration of the first time interval is less than or equal to a first duration threshold, and the heading angle difference sum is the sum of the heading angle differences of any adjacent trajectory points whose trajectory times belong to the same time interval;

[0130] The turning determination module 303 is configured to determine at least two turning time intervals from at least two first time intervals based on the sum of the heading angle differences of the trajectory points corresponding to at least two first time intervals, wherein the turning time interval is the first time interval in which the corresponding trajectory is in a turning state;

[0131] The target trajectory detection module 304 is configured to generate target trajectory indication information for any two turning time intervals, in response to the time difference between any two turning time intervals being less than or equal to a second duration threshold, and the trajectory turning directions corresponding to the two turning time intervals being different.

[0132] In the technical solution proposed in this disclosure, trajectory point information of each trajectory point in a map data acquisition trajectory including multiple trajectory points is obtained. The map data acquisition trajectory is used to collect map data to be processed, which can be understood as the map data acquisition device acquiring the corresponding map data while moving along the map data acquisition trajectory. Based on the trajectory point information, the sum of the heading angle differences of the trajectory points corresponding to at least two first time intervals is obtained. The duration of each first time interval is less than or equal to a first duration threshold, indicating that the probability of the map data acquisition device moving along an overly complex trajectory (e.g., a serpentine trajectory) within that first time interval is relatively low. Based on the sum of the heading angle differences of the trajectory points corresponding to at least two first time intervals, at least two turning time intervals are determined from the at least two first time intervals. Within one turning time interval, the map data acquisition device may have turned in one direction while moving. For any two turning time intervals, the time difference between any two turning time intervals is less than or equal to a second duration threshold, and the time difference between any two turning time intervals is less than or equal to a second duration threshold. The trajectory turning directions corresponding to each interval are different, generating target trajectory indication information. Since the trajectory turning directions corresponding to any two turning time intervals are different, it can be assumed that the map data acquisition device turned in different directions successively during its movement. If the time difference between any two turning intervals is less than or equal to a second time threshold, it can be assumed that the probability of the map data acquisition device moving along an overly complex trajectory between any two turning intervals is low. Since the probability of a trajectory turning in two different directions successively being a figure-eight trajectory is high, this scheme generates target trajectory indication information to indicate that the trajectory of the map data acquisition device in at least any two turning time intervals is a figure-eight trajectory. Based on this target trajectory indication information, the portion of the map data acquisition trajectory that matches the figure-eight trajectory can be quickly and accurately determined. This allows for the removal of the portion of the map data collected by the map data acquisition device while moving along the figure-eight trajectory to obtain higher-precision map data, which helps improve the efficiency of processing the corresponding map data and enhances the user experience.

[0133] This disclosure also discloses an electronic device. Figure 5 A structural block diagram of an electronic device according to an embodiment of the present disclosure is shown.

[0134] like Figure 5 As shown, the electronic device includes a memory and a processor, wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method according to embodiments of the present disclosure.

[0135] Figure 6 A schematic diagram of the structure of a computer system suitable for implementing the method according to embodiments of the present disclosure is shown.

[0136] like Figure 6 As shown, the computer system includes a processing unit that can execute various methods described above based on a program stored in a read-only memory (ROM) or a program loaded from a storage portion into a random access memory (RAM). The RAM also stores various programs and data required for the operation of the computer system. The processing unit, ROM, and RAM are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus.

[0137] The following components are connected to the I / O interface: input sections including keyboards, mice, etc.; output sections including cathode ray tubes (CRTs), liquid crystal displays (LCDs), and speakers; storage sections including hard disks, etc.; and communication sections including network interface cards such as LAN cards and modems. The communication section performs communication processes via a network such as the Internet. Drives are also connected to the I / O interface as needed. Removable media, such as disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on the drive as needed so that computer programs read from them can be installed into the storage section as needed. The processing unit can be implemented as a CPU, GPU, TPU, FPGA, NPU, etc.

[0138] In particular, according to embodiments of this disclosure, the methods described above can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program containing program code for performing the methods described above. In such embodiments, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium.

[0139] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0140] The units or modules described in the embodiments of this disclosure can be implemented in software or programmable hardware. The described units or modules can also be located in a processor, and the names of these units or modules do not necessarily constitute a limitation on the unit or module itself.

[0141] In another aspect, this disclosure also provides a computer-readable storage medium, which may be a computer-readable storage medium included in the electronic device or computer system described above; or it may be a standalone computer-readable storage medium not assembled into a device. The computer-readable storage medium stores one or more programs, which are used by one or more processors to perform the methods described in this disclosure.

[0142] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

Claims

1. A trajectory detection method, wherein, include: Acquire trajectory point information for each trajectory point in a map data acquisition trajectory that includes multiple trajectory points, wherein the trajectory point information includes trajectory time and trajectory heading angle; Based on the trajectory point information, obtain the sum of heading angle differences of at least two first time intervals, wherein the duration of the first time interval is less than or equal to a first duration threshold, and the sum of heading angle differences is the sum of heading angle differences of any adjacent trajectory points whose trajectory times belong to the same time interval; Based on the sum of the heading angle differences of the trajectory points corresponding to the at least two first time intervals, at least two turning time intervals are determined from the at least two first time intervals, wherein the turning time interval is the first time interval in which the trajectory is in a turning state and the absolute value of the sum of the heading angle differences is greater than or equal to the threshold of the sum of the heading angle differences; For any two turning time intervals, in response to the time difference between the two turning time intervals being less than or equal to a second duration threshold, and the trajectory turning directions corresponding to the two turning time intervals being different, target trajectory indication information is generated.

2. The trajectory detection method according to claim 1, wherein, Based on the sum of the heading angle differences between the trajectory points corresponding to the at least two first time intervals, a turning time interval is determined from the at least two first time intervals, including: In response to the absolute value of the sum of heading angle differences corresponding to any first time interval being greater than or equal to the heading angle difference threshold, the any first time interval is determined as a turning time interval.

3. The trajectory detection method according to claim 2, wherein, Before determining any first time interval as a turning time interval when the absolute value of the sum of the heading angle differences corresponding to any first time interval is greater than or equal to a heading angle difference threshold, the method further includes: Obtain the average velocity of the trajectory corresponding to at least one second time interval, wherein the second time interval belongs to the first time interval; The step of determining any first time interval as a turning time interval when the absolute value of the sum of the heading angle differences corresponding to any first time interval is greater than or equal to a heading angle difference threshold includes: In response to the absolute value of the sum of the heading angle differences corresponding to any first time interval being greater than or equal to the heading angle difference threshold, and the average velocity of the trajectory corresponding to each second time interval in any first time interval belonging to the first velocity interval, the any first time interval is determined as the turning time interval.

4. The trajectory detection method according to claim 1, wherein, The trajectory turning directions corresponding to any two turning time intervals are different, including: The product of the sum of the heading angle differences corresponding to any two turning time intervals is less than 0.

5. The trajectory detection method according to claim 1, wherein, Before generating target trajectory indication information for any two turning time intervals, in response to the time difference between the two turning time intervals being less than or equal to a second duration threshold, and the turning directions corresponding to the two turning time intervals being different, the method further includes: Obtain the average velocity of the trajectory corresponding to the third time interval, wherein the third time interval includes any two turning time intervals; For any two turning time intervals, in response to the time difference between the two turning time intervals being less than or equal to a second duration threshold, and the turning directions corresponding to the two turning time intervals being different, target trajectory indication information is generated, including: For any two turning time intervals, in response to the time difference between the two turning time intervals being less than or equal to a second duration threshold, the turning directions of the trajectories corresponding to the two turning time intervals being different, and the average speed of the trajectory corresponding to the third time interval belonging to the second speed interval, the target trajectory indication information is generated.

6. The trajectory detection method according to any one of claims 1-5, wherein, The map data sampling trajectory is obtained by sampling from the original trajectory according to the target sampling frequency, where the target sampling frequency is less than the original trajectory sampling frequency.

7. The trajectory detection method according to any one of claims 1-5, wherein, The sum of the heading angle differences is the sum of the heading angle differences of any two adjacent trajectory points belonging to the target heading angle difference interval, where the trajectory time is within the same time interval.

8. The trajectory detection method according to any one of claims 1-5, wherein, The time difference between any two adjacent first time intervals is greater than or equal to the third duration threshold.

9. A trajectory detection device, wherein, include: The trajectory point information acquisition module is configured to acquire trajectory point information for each trajectory point in a map data acquisition trajectory that includes multiple trajectory points, wherein the trajectory point information includes trajectory time and trajectory heading angle. The heading angle difference acquisition module is configured to acquire the heading angle difference sum of at least two first time intervals corresponding to the trajectory points based on the trajectory point information, wherein the duration of the first time interval is less than or equal to a first duration threshold, and the heading angle difference sum is the sum of the heading angle differences of any adjacent trajectory points whose trajectory times belong to the same time interval; The turning determination module is configured to determine at least two turning time intervals from the at least two first time intervals based on the sum of the heading angle differences of the trajectory points corresponding to the at least two first time intervals, wherein the turning time intervals are the first time intervals in which the corresponding trajectory is in a turning state; The target trajectory detection module is configured to generate target trajectory indication information for any two turning time intervals, in response to the time difference between the two turning time intervals being less than or equal to a second duration threshold, and the turning directions corresponding to the two turning time intervals being different.

10. An electronic device, wherein, It includes a memory and a processor; wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method steps of any one of claims 1-8.

11. A computer-readable storage medium having stored thereon computer instructions, wherein, When executed by a processor, the computer instructions implement the method steps of any one of claims 1-8.

Images