Scene information determination method and apparatus, and electronic device
By acquiring the feature information of target trajectory points in high-precision maps and determining their corresponding collection scene information, the problem of low accuracy caused by the lack of differentiation of trajectory point information is solved, thereby improving the recognition and production efficiency of high-precision maps.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING BAIDU NETCOM SCI & TECH CO LTD
- Filing Date
- 2022-11-25
- Publication Date
- 2026-07-21
AI Technical Summary
Existing technologies fail to effectively distinguish the information collected from the scene corresponding to the trajectory points, resulting in low accuracy in the recognition and production of high-precision maps.
The target trajectory points are obtained by sampling on the target lane, and the pre-bound element information of these trajectory points, such as lane line features, hard isolation features and reverse trajectory points, is obtained. This information is then used to determine the collection scene information corresponding to the trajectory points.
This improves the accuracy of the scene information collected corresponding to the trajectory points, thereby increasing the recognition and production efficiency of high-precision maps.
Smart Images
Figure CN115718789B_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of artificial intelligence technology, particularly to cloud computing and intelligent transportation, and specifically to a method, apparatus, and electronic device for determining scene information. Background Technology
[0002] With the development of mapping technology, the application of high-definition maps is becoming increasingly widespread. Currently, high-definition maps are being used more and more in autonomous vehicles, and the accuracy of high-definition map data is receiving increasing attention. The creation or recognition of high-definition maps typically relies on trajectory point information. Currently, there is no distinction between the data collection scene information corresponding to the trajectory point information. Summary of the Invention
[0003] This disclosure provides a method, apparatus, and electronic device for determining scene information.
[0004] According to a first aspect of this disclosure, a method for determining scene information is provided, comprising:
[0005] Determine the target trajectory point, which is a trajectory point sampled on the target lane;
[0006] Obtain the element information pre-bound to the target trajectory point;
[0007] The collection scene information corresponding to the target trajectory point is determined based on the element information.
[0008] According to a second aspect of this disclosure, a scene information determining apparatus is provided, comprising:
[0009] The first determining module is used to determine the target trajectory point, which is a trajectory point sampled on the target lane;
[0010] The acquisition module is used to acquire the element information pre-bound to the target trajectory point;
[0011] The second determining module is used to determine the collection scene information corresponding to the target trajectory point based on the element information.
[0012] According to a third aspect of this disclosure, an electronic device is provided, comprising:
[0013] At least one processor; and
[0014] A memory that is communicatively connected to at least one processor; wherein,
[0015] The memory stores instructions that can be executed by at least one processor to enable the at least one processor to perform any of the methods in the first aspect.
[0016] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions for causing a computer to perform any of the methods in the first aspect.
[0017] According to a fifth aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements any of the methods in the first aspect.
[0018] In this embodiment of the disclosure, the element information pre-bound to the target trajectory point can be obtained first, and the collection scene information corresponding to the target trajectory point can be determined according to the element information. In this way, the accuracy of the collection scene information corresponding to the target trajectory point can be improved, and the recognition efficiency or production efficiency of the high-precision map can be improved when identifying or creating a high-precision map based on the collection scene information.
[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description
[0020] Figure 1 This is a flowchart of a method for determining scene information provided in an embodiment of this disclosure;
[0021] Figure 2 This is a flowchart of a target trajectory point filtering method provided in an embodiment of this disclosure;
[0022] Figure 3 This is a schematic diagram of the structure of a scene information determination device provided in an embodiment of this disclosure;
[0023] Figure 4 This is one of the structural schematic diagrams of the second determining module included in the scene information determining device provided in this embodiment of the present disclosure;
[0024] Figure 5 This is a second schematic diagram of the structure of the second determining module included in the scene information determining device provided in this embodiment of the present disclosure;
[0025] Figure 6 This is the third schematic diagram of the structure of the second determining module included in the scene information determining device provided in this embodiment of the present disclosure;
[0026] Figure 7 This is the fourth structural schematic diagram of the second determining module included in the scene information determining device provided in this embodiment of the present disclosure;
[0027] Figure 8 This is the fifth schematic diagram of the structure of the second determining module included in the scene information determining device provided in this embodiment of the present disclosure;
[0028] Figure 9 This is a schematic block diagram of an example electronic device used to implement embodiments of the present disclosure. Detailed Implementation
[0029] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.
[0030] Currently, there is no distinction between the data collection scene information corresponding to trajectory points. Often, the same scene information is used as the data collection scene information for multiple trajectory points, resulting in low accuracy in the identification of trajectory point data collection scene information. This also leads to low accuracy in the identification and production of high-precision maps. To address these issues, the following implementation method is proposed:
[0031] See Figure 1 , Figure 1 A flowchart of a scene information determination method provided in this disclosure embodiment is shown below. Figure 1 As shown, the method for determining scene information includes the following steps:
[0032] Step S101: Determine the target trajectory point, which is the trajectory point sampled on the target lane.
[0033] The target trajectory point can be the trajectory point obtained by the sampling device on the target lane, and the sampling device is not limited here. For example, the sampling device can be a sampling vehicle.
[0034] The number of lanes included in the target lane is not limited here. The target lane can include single lane, two lane and multi lane. When the target lane includes two lane and multi lane, the lanes included in the two lane and multi lane can be lanes in the same direction or lanes in opposite directions, and there is no specific limitation.
[0035] Step S102: Obtain the element information pre-bound to the target trajectory point.
[0036] It should be noted that the specific content of the element information is not limited here.
[0037] As an optional implementation, the element information includes at least one of the following: lane line features, hard isolation features, and reverse trajectory points.
[0038] Among them, lane line features can refer to the boundary line features of the lane, hard isolation features can refer to features located at the edge of the road, such as fences or street lights, and reverse trajectory points can refer to trajectory points that travel in the opposite direction to the target trajectory point.
[0039] The more content included in the feature information, the higher the accuracy of the scene information determined based on the feature information. For example, when the feature information includes lane line features, hard barrier features, and reverse trajectory points, the accuracy of the scene information determined based on the above feature information is greater than the accuracy of the scene information determined when the feature information includes only lane line features and hard barrier features.
[0040] In this embodiment of the disclosure, since the element information includes lane line features, hard isolation features and reverse trajectory points, and the above element information is highly correlated with the collection scene information corresponding to the collection target trajectory point, determining the collection scene information based on the above element information can improve the accuracy of the determination result of the collection scene information.
[0041] As an optional implementation, the number of target trajectory points can be at least two, and each target trajectory point can perform the steps included in the embodiments of this disclosure.
[0042] It should be noted that the aforementioned at least two target trajectory points can be obtained by filtering from multiple trajectory points. Optionally, the multiple trajectory points can be sorted according to their timestamps, and at least two target trajectory points can be obtained from the sorted trajectory points based on the distance between them. For example, the distance between any two adjacent target trajectory points can be greater than a preset distance threshold.
[0043] The method for selecting at least two target trajectory points from multiple trajectory points can be found in [reference needed]. Figure 2 As shown. Figure 2 As shown, the method for filtering target trajectory points may include the following steps:
[0044] Step S201: Sort the trajectory points according to time;
[0045] Sorting the trajectory points by time can be understood as sorting the above multiple trajectory points by time, where the above time can be the timestamp information corresponding to each trajectory point.
[0046] Step S202: Select the first target trajectory point;
[0047] The method of selecting the first target trajectory point is not limited here. For example, the first target trajectory point can be selected randomly, or the first target trajectory point can be selected according to preset conditions, which can be selected based on user input.
[0048] Step S203: Does the next target trajectory point exist? Or, does the distance between the next target trajectory point and the first target trajectory point exceed the threshold S? If it exceeds the threshold S, proceed to step S204; if it does not exceed the threshold S, end the process.
[0049] Step S203 can be used to determine whether there are at least two target trajectory points on the same path. When the distance between the next target trajectory point and the first target trajectory point does not exceed the threshold S, it is determined that the first target trajectory point and the next target trajectory point are on the same path. When the distance between the next target trajectory point and the first target trajectory point exceeds the threshold S, it is determined that the first target trajectory point and the next target trajectory point are on different paths.
[0050] Step S204: Does the distance between the next target trajectory point and the first target trajectory point exceed the threshold D? If it does, proceed to step S206; if it does not exceed the threshold D, proceed to step S205.
[0051] Wherein, if the distance between the next target trajectory point and the first target trajectory point exceeds the threshold D, it can be considered that the distance between the next target trajectory point and the first target trajectory point is greater than the preset threshold, and it can be determined that both the next target trajectory point and the first target trajectory point are valid trajectory points; if the distance between the next target trajectory point and the first target trajectory point does not exceed the threshold D, it can be considered that the distance between the next target trajectory point and the first target trajectory point is too small, and it can be determined that the next target trajectory point is invalid, and it is necessary to reselect a target trajectory point after the next target trajectory point. In step S205, the distances corresponding to all trajectory points between the first target trajectory point and the target trajectory point after the next target trajectory point can be superimposed.
[0052] Step S205: Overlay the current point spacing;
[0053] Step S206: Find the difference point at the threshold D position;
[0054] Among them, the difference point at the threshold D position can be considered as: the trajectory point on the path corresponding to the first target trajectory point whose distance from the first target trajectory point is greater than the threshold D position is determined as the valid target trajectory point;
[0055] Step S207: Calculate whether the remaining distance from the difference point exceeds the threshold D. If it exceeds the threshold D, return to step S206. If it does not exceed the threshold D, return to step S203.
[0056] The aforementioned remaining spacing refers to the distance between the position of a certain trajectory point and the end position of the path. In other words, the remaining spacing can be the remaining spacing of the path, that is, the remaining spacing on the path corresponding to the first target trajectory point. When the remaining spacing exceeds the threshold D, it indicates that the target trajectory points on the path corresponding to the first target trajectory point have not been completely filtered, and the filtering of target trajectory points can continue. When the remaining spacing does not exceed the threshold D, it indicates that the filtering of target trajectory points on the path corresponding to the first target trajectory point has been completed.
[0057] Once at least two target trajectory points are obtained through filtering, a spatial search can be performed on each target trajectory point to obtain the information of the feature closest to that target trajectory point, and then the target trajectory point can be bound to the information of the feature closest to that target trajectory point.
[0058] It should be noted that the number of target trajectory points bound to a feature can vary depending on the type of feature information. For example, lane line features can be bound to multiple target trajectory points, hard isolation features can also be bound to multiple target trajectory points, and reverse trajectory points can be bound to target trajectory points one by one.
[0059] In addition, it can also calculate the distance between lane line features and the bound target trajectory points (also known as the perpendicular distance), the distance between hard isolation features and the bound target trajectory points, and the distance between reverse trajectory points and the bound target trajectory points.
[0060] Step S103: Determine the acquisition scene information corresponding to the target trajectory point based on the element information.
[0061] In this embodiment of the disclosure, the element information pre-bound to the target trajectory point can be obtained first, and the collection scene information corresponding to the target trajectory point can be determined according to the element information. That is, the collection scene information corresponding to the target trajectory point is determined by the element information corresponding to each target trajectory point. In this way, the accuracy of the collection scene information corresponding to the target trajectory point can be improved, and the recognition efficiency or production efficiency of high-precision map can be improved when identifying or creating high-precision map based on the collection scene information.
[0062] As an optional implementation, the element information includes: the reverse trajectory point; and determining the acquisition scene information corresponding to the target trajectory point based on the element information includes:
[0063] If a corresponding reverse trajectory point exists for the target trajectory point, and the distance between the reverse trajectory point and the target trajectory point is less than or equal to a first threshold, the acquisition scene information corresponding to the target trajectory point is determined to be dual acquisition scene information. The dual acquisition scene information indicates that the target trajectory point is acquired bidirectionally on the target lane; or...
[0064] If a corresponding reverse trajectory point exists for the target trajectory point, and the distance between the reverse trajectory point and the target trajectory point is greater than the first threshold, then the acquisition scene information corresponding to the target trajectory point is determined to be single acquisition scene information; or,
[0065] If there is no corresponding reverse trajectory point for the target trajectory point, the acquisition scene information corresponding to the target trajectory point is determined to be single acquisition scene information;
[0066] The single-collection scene information is used to indicate that the target trajectory point is collected unidirectionally on the target lane.
[0067] In this case, the direction of the lane where the reverse trajectory point is located is opposite to the direction of the lane where the target trajectory point is located. For example, the direction of the lane where the target trajectory point is located is from point A to point B, while the direction of the lane where the reverse trajectory point corresponding to the target trajectory point is located is from point B to point A.
[0068] In this context, single-collection scenario information can be understood as trajectory points being collected only in the lane where the target trajectory point is located, and not in the lane where the reverse trajectory point corresponding to the target trajectory point is located; dual-collection scenario information can be understood as trajectory points being collected in both the lane where the target trajectory point is located and the lane where the reverse trajectory point corresponding to the target trajectory point is located.
[0069] It should be noted that when a target trajectory point has a corresponding reverse trajectory point, and the distance between the reverse trajectory point and the target trajectory point is greater than the first threshold, it can be determined that the target trajectory point and the corresponding reverse trajectory point are mismatched. Therefore, it can also be determined that the collection scene information corresponding to the target trajectory point is single collection scene information.
[0070] In this embodiment of the disclosure, the collection scene information corresponding to the target trajectory point can be determined by whether there is a corresponding reverse trajectory point, and when there is a corresponding reverse trajectory point, the collection scene information corresponding to the target trajectory point can be determined by the distance between the target trajectory point and the corresponding reverse trajectory point, thereby enhancing the diversity and flexibility of the collection scene information determination method.
[0071] As an optional implementation, the element information further includes: hard isolation features, wherein the target trajectory point has corresponding first hard isolation features and second hard isolation features, and the first hard isolation features and the second hard isolation features are respectively located on opposite sides of the target trajectory point;
[0072] When a corresponding reverse trajectory point exists at the target trajectory point, and the distance between the reverse trajectory point and the target trajectory point is less than or equal to a first threshold, determining the acquisition scene information corresponding to the target trajectory point as dual acquisition scene information includes:
[0073] If a corresponding reverse trajectory point exists for the target trajectory point, and the distance between the reverse trajectory point and the target trajectory point is less than or equal to a first threshold, the first distance between the first hard isolation feature and the second hard isolation feature is identified. If the first distance is greater than a second threshold, the acquisition scene information corresponding to the target trajectory point is determined to be the dual acquisition scene information; or...
[0074] When a corresponding reverse trajectory point exists at the target trajectory point, and the distance between the reverse trajectory point and the target trajectory point is greater than the first threshold, determining that the acquisition scene information corresponding to the target trajectory point is single acquisition scene information includes:
[0075] If a corresponding reverse trajectory point exists for the target trajectory point, and the distance between the reverse trajectory point and the target trajectory point is greater than the first threshold, identify the first distance between the first hard isolation feature and the second hard isolation feature. If the first distance is greater than a third threshold, determine the acquisition scene information corresponding to the target trajectory point as the single acquisition scene information; or,
[0076] When there is no corresponding reverse trajectory point for the target trajectory point, determining that the acquisition scene information corresponding to the target trajectory point is single acquisition scene information includes:
[0077] If there is no corresponding reverse trajectory point for the target trajectory point, identify the first distance between the first hard isolation feature and the second hard isolation feature. If the first distance is greater than a fourth threshold, determine the acquisition scene information corresponding to the target trajectory point as the single acquisition scene information.
[0078] Specifically, when the target lane is a one-way lane, the first hard isolation feature and the second hard isolation feature can be understood as hard isolation features located on the road edges on both sides of the target lane, respectively; when the target lane is a two-way lane, one of the first hard isolation feature and the second hard isolation feature can be understood as the intermediate hard isolation feature in the middle of the two-way lane used to separate the two-way lane, and the other of the first hard isolation feature and the second hard isolation feature can be understood as the hard isolation feature at the road edge of the two-way lane.
[0079] The second, third, and fourth thresholds can be the same value or different values.
[0080] In this embodiment of the disclosure, since it is necessary to determine the acquisition scene information of the target trajectory point by simultaneously using the reverse trajectory point and the first distance between the first hard isolation feature and the second hard isolation feature, the accuracy of the determination result of the acquisition scene information of the target trajectory point is further enhanced.
[0081] As an optional implementation, determining the acquisition scene information corresponding to the target trajectory point as the dual acquisition scene information when the first distance is greater than the second threshold includes:
[0082] If the first distance is greater than the second threshold, the width of the target lane is identified;
[0083] When the width is greater than the second distance, the scene information corresponding to the target trajectory point is determined to be bidirectional multi-lane dual-collection scene information;
[0084] Wherein, the second distance is the distance between the target trajectory point and the first hard isolation feature or the second hard isolation feature.
[0085] In this embodiment, since the second distance is the distance between the target trajectory point and the first hard isolation feature or the second hard isolation feature, the second distance can be understood as the width of a one-way lane. When the width of the target lane is greater than the second distance, combined with the content of the above embodiment, it can be said that the target lane is a two-way lane. Therefore, it can be determined that the collection scene information corresponding to the target trajectory point is dual collection scene information, thereby further reducing the possibility of misjudgment of dual collection scene information, that is, further enhancing the accuracy of the determination result of dual collection scene information.
[0086] As an optional implementation, the element information further includes: lane line features, wherein determining the acquisition scene information corresponding to the target trajectory point as the single acquisition scene information when the first distance is greater than a third threshold includes:
[0087] If the first distance is greater than the third threshold, the distance between the target trajectory point and the lane line feature corresponding to the target trajectory point is identified;
[0088] If the distance between the target trajectory point and the lane line feature corresponding to the target trajectory point is greater than the third distance, the collection scene information corresponding to the target trajectory point is determined to be bidirectional multi-lane single collection scene information;
[0089] The third distance is the distance between the target trajectory point and either the first hard isolation feature or the second hard isolation feature.
[0090] In this embodiment, the third distance can also be understood as the width of a one-way lane, and the lane line feature corresponding to the target trajectory point can be the lane line feature closest to the target trajectory point. When the distance between the target trajectory point and the lane line feature corresponding to the target trajectory point is greater than the third distance, combined with the content of the above embodiment, it can be concluded that the target lane is a two-way multi-lane lane, and the collection scene information corresponding to the target trajectory point can be determined as two-way multi-lane single collection scene information, thereby further refining the range of collection scene information corresponding to the target trajectory point, that is, further enhancing the accuracy of the determination result of single collection scene information, and also increasing the diversity and flexibility of the collection scene information determination method.
[0091] As an optional implementation, the first hard isolation feature includes a first sub-feature and a second sub-feature with intervals; determining the acquisition scene information corresponding to the target trajectory point as the single acquisition scene information when the first distance is greater than a third threshold includes:
[0092] If the first distance is greater than the third threshold, the distance between the first sub-feature and the second sub-feature is identified;
[0093] If the distance between the first sub-feature and the second sub-feature is greater than the fourth distance, the acquisition scene information corresponding to the target trajectory point is determined to be bidirectional multi-lane single acquisition scene information; or...
[0094] If the first distance is greater than the third threshold, the distance between the third sub-feature and the fourth sub-feature is identified, and the second hard isolation feature includes the third sub-feature and the fourth sub-feature that are spaced apart;
[0095] If the distance between the third sub-feature and the fourth sub-feature is greater than the fourth threshold, the acquisition scene information corresponding to the target trajectory point is determined to be the bidirectional multi-lane single acquisition scene information.
[0096] Among them, one of the first sub-feature and the second sub-feature can be the feature closest to the target trajectory point, and the other of the first sub-feature and the second sub-feature can be the feature second closest to the target trajectory point. The second closest feature can also be called the feature second closest to the target trajectory point. Similarly, one of the third sub-feature and the fourth sub-feature can be the feature closest to the target trajectory point, and the other of the third sub-feature and the fourth sub-feature can be the feature second closest to the target trajectory point. The second closest feature can also be called the feature second closest to the target trajectory point.
[0097] Specifically, if the distance between the first sub-feature and the second sub-feature is greater than the fourth distance, or the distance between the third sub-feature and the fourth sub-feature is greater than the fourth threshold, it indicates that the first sub-feature, the second sub-feature, the third sub-feature, and the fourth sub-feature are located in the middle hard isolation feature of the target lane, which means that the target lane is a two-way multi-lane lane.
[0098] In this embodiment of the disclosure, the range of the collection scene information corresponding to the target trajectory point is further refined based on the distance between the first sub-feature and the second sub-feature, or the distance between the third sub-feature and the fourth sub-feature. This further enhances the accuracy of the determination result of single collection scene information and increases the diversity and flexibility of the collection scene information determination method.
[0099] As an optional implementation, determining the acquisition scene information corresponding to the target trajectory point as the single acquisition scene information when the first distance is greater than the fourth threshold includes:
[0100] If the first distance is greater than the fourth threshold, determine the number of the first hard isolation feature and the second hard isolation feature;
[0101] When the number of the first hard isolation feature and the second hard isolation feature is both 1, determine whether the first hard isolation feature and the second hard isolation feature have corresponding lane line features;
[0102] If neither the first hard isolation feature nor the second hard isolation feature has a corresponding lane line feature, the acquisition scene information corresponding to the target trajectory point is determined to be bidirectional single-lane single acquisition scene information.
[0103] Where neither the first hard isolation feature nor the second hard isolation feature has a corresponding lane line feature, it means that there is no lane line feature on the side of the first hard isolation feature and the second hard isolation feature that is far from the target trajectory point. In other words, when the first hard isolation feature and the second hard isolation feature have corresponding lane line features, the first hard isolation feature is located between the target trajectory point and the lane line feature, and the second hard isolation feature is located between the target trajectory point and the lane line feature.
[0104] In this embodiment, the scope of the scene information corresponding to the target trajectory point can be further refined, which further enhances the accuracy of the determination result of single scene information and increases the diversity and flexibility of the determination method of scene information.
[0105] It should be noted that once the collection scene information corresponding to the target trajectory point is determined, a high-precision map can be generated based on the collection scene information. That is, high-precision maps for different scenes can be generated based on the trajectory points corresponding to different collection scene information, thereby improving the accuracy and production efficiency of the high-precision map. Alternatively, the high-precision map can also be identified based on the collection scene information, thereby improving the recall and accuracy of the high-precision map.
[0106] See Figure 3 , Figure 3 This is a schematic diagram of the structure of a scene information determination device provided in an embodiment of the present disclosure, as shown below. Figure 3 As shown, the scene information determining device 300 includes:
[0107] The first determining module 301 is used to determine the target trajectory point, wherein the target trajectory point is a trajectory point sampled on the target lane;
[0108] The acquisition module 302 is used to acquire the element information pre-bound to the target trajectory point;
[0109] The second determining module 303 is used to determine the collection scene information corresponding to the target trajectory point based on the element information.
[0110] As an optional implementation, the element information includes at least one of the following: lane line features, hard isolation features, and reverse trajectory points.
[0111] As an optional implementation, the element information includes: the reverse trajectory point; the second determining module 303 is further used for:
[0112] If a corresponding reverse trajectory point exists for the target trajectory point, and the distance between the reverse trajectory point and the target trajectory point is less than or equal to a first threshold, the acquisition scene information corresponding to the target trajectory point is determined to be dual acquisition scene information. The dual acquisition scene information indicates that the target trajectory point is acquired bidirectionally on the target lane; or...
[0113] If a corresponding reverse trajectory point exists for the target trajectory point, and the distance between the reverse trajectory point and the target trajectory point is greater than the first threshold, then the acquisition scene information corresponding to the target trajectory point is determined to be single acquisition scene information; or,
[0114] If there is no corresponding reverse trajectory point for the target trajectory point, the acquisition scene information corresponding to the target trajectory point is determined to be single acquisition scene information;
[0115] The single-collection scene information is used to indicate that the target trajectory point is collected unidirectionally on the target lane.
[0116] As an optional implementation, the element information further includes: hard isolation features, wherein the target trajectory point has corresponding first hard isolation features and second hard isolation features, and the first hard isolation features and the second hard isolation features are respectively located on opposite sides of the target trajectory point; the second determining module 303 is further configured to:
[0117] If a corresponding reverse trajectory point exists for the target trajectory point, and the distance between the reverse trajectory point and the target trajectory point is less than or equal to a first threshold, the first distance between the first hard isolation feature and the second hard isolation feature is identified. If the first distance is greater than a second threshold, the acquisition scene information corresponding to the target trajectory point is determined to be the dual acquisition scene information; or...
[0118] If a corresponding reverse trajectory point exists for the target trajectory point, and the distance between the reverse trajectory point and the target trajectory point is greater than the first threshold, identify the first distance between the first hard isolation feature and the second hard isolation feature. If the first distance is greater than a third threshold, determine the acquisition scene information corresponding to the target trajectory point as the single acquisition scene information; or,
[0119] If there is no corresponding reverse trajectory point for the target trajectory point, identify the first distance between the first hard isolation feature and the second hard isolation feature. If the first distance is greater than a fourth threshold, determine the acquisition scene information corresponding to the target trajectory point as the single acquisition scene information.
[0120] As an optional implementation, see [link to implementation details]. Figure 4 The second determining module 303 includes:
[0121] The first identification submodule 3031 is used to identify the width of the target lane when the first distance is greater than the second threshold.
[0122] The first determining submodule 3032 is used to determine that the acquisition scene information corresponding to the target trajectory point is bidirectional multi-lane dual acquisition scene information when the width is greater than the second distance;
[0123] Wherein, the second distance is the distance between the target trajectory point and the first hard isolation feature or the second hard isolation feature.
[0124] As an optional implementation, see [link to implementation details]. Figure 5 The element information further includes: lane line features; the second determining module 303 includes:
[0125] The second recognition submodule 3033 is used to recognize the distance between the target trajectory point and the lane line feature corresponding to the target trajectory point when the first distance is greater than the third threshold.
[0126] The second determining submodule 3034 is used to determine that the collection scene information corresponding to the target trajectory point is bidirectional multi-lane single collection scene information when the distance between the target trajectory point and the lane line feature corresponding to the target trajectory point is greater than the third distance.
[0127] The third distance is the distance between the target trajectory point and either the first hard isolation feature or the second hard isolation feature.
[0128] As an optional implementation, see [link to implementation details]. Figure 6 The first hard isolation feature includes a first sub-feature and a second sub-feature with an interval setting; the second determining module 303 includes:
[0129] The third identification submodule 3035 is used to identify the distance between the first sub-feature and the second sub-feature when the first distance is greater than the third threshold.
[0130] The third determining submodule 3036 is used to determine that the acquisition scene information corresponding to the target trajectory point is bidirectional multi-lane single acquisition scene information when the distance between the first sub-feature and the second sub-feature is greater than the fourth distance.
[0131] As an optional implementation, see [link to implementation details]. Figure 7 The second determining module 303 includes:
[0132] The fourth identification submodule 3037 is used to identify the distance between the third sub-feature and the fourth sub-feature when the first distance is greater than the third threshold, wherein the second hard isolation feature includes the third sub-feature and the fourth sub-feature that are spaced apart;
[0133] The fourth determining submodule 3038 is used to determine the acquisition scene information corresponding to the target trajectory point as the bidirectional multi-lane single acquisition scene information when the distance between the third sub-feature and the fourth sub-feature is greater than the fourth threshold.
[0134] As an optional implementation, see [link to implementation details]. Figure 8 The second determining module 303 includes:
[0135] The fifth determining submodule 3039 is used to determine the number of the first hard isolation feature and the second hard isolation feature when the first distance is greater than the fourth threshold.
[0136] The sixth determining submodule 30310 is used to determine whether there is a corresponding lane line feature for the first hard isolation feature and the second hard isolation feature when the number of the first hard isolation feature and the second hard isolation feature is both 1.
[0137] The seventh determination submodule 30311 is used to determine that the acquisition scene information corresponding to the target trajectory point is bidirectional single-lane single acquisition scene information when neither the first hard isolation feature nor the second hard isolation feature has a corresponding lane line feature.
[0138] The scene information determination device 300 provided in this disclosure can implement all the processes implemented in the scene information determination method embodiments and can achieve the same beneficial effects. To avoid repetition, it will not be described again here.
[0139] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.
[0140] Figure 9 A schematic block diagram of an example electronic device 900 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.
[0141] like Figure 9 As shown, device 900 includes a computing unit 901, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 902 or a computer program loaded from storage unit 908 into random access memory (RAM) 903. RAM 903 may also store various programs and data required for the operation of device 900. The computing unit 901, ROM 902, and RAM 903 are interconnected via bus 904. Input / output (I / O) interface 905 is also connected to bus 904.
[0142] Multiple components in device 900 are connected to I / O interface 905, including: input unit 906, such as keyboard, mouse, etc.; output unit 907, such as various types of monitors, speakers, etc.; storage unit 908, such as disk, optical disk, etc.; and communication unit 909, such as network card, modem, wireless transceiver, etc. Communication unit 909 allows device 900 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0143] The computing unit 901 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 901 performs the various methods and processes described above, such as the scene information determination method. For example, in some embodiments, the scene information determination method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 908. In some embodiments, part or all of the computer program may be loaded and / or installed on device 900 via ROM 902 and / or communication unit 909. When the computer program is loaded into RAM 903 and executed by the computing unit 901, one or more steps of the scene information determination method described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to perform the scene information determination method by any other suitable means (e.g., by means of firmware).
[0144] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.
[0145] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0146] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
[0147] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).
[0148] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.
[0149] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.
[0150] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.
[0151] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.
Claims
1. A method for determining scene information, comprising: Determine the target trajectory point, which is the trajectory point obtained by the sampling device on the target lane; the sampling device is the sampling vehicle. Obtain the element information pre-bound to the target trajectory point; The collection scene information corresponding to the target trajectory point is determined based on the element information. The collection scene information is either a single collection scene or a dual collection scene. The collection scene information is used for the recognition or production of high-precision maps. The element information includes: lane line features, hard isolation features, and reverse trajectory points. The hard isolation features are features located at the edge of the road, and the reverse trajectory points are trajectory points that travel in the opposite direction to the target trajectory point. The step of determining the acquisition scene information corresponding to the target trajectory point based on the element information includes: If a corresponding reverse trajectory point exists for the target trajectory point, and the distance between the reverse trajectory point and the target trajectory point is less than or equal to a first threshold, the acquisition scene information corresponding to the target trajectory point is determined to be dual acquisition scene information. The dual acquisition scene information indicates that the target trajectory point is acquired bidirectionally on the target lane; or... If a corresponding reverse trajectory point exists for the target trajectory point, and the distance between the reverse trajectory point and the target trajectory point is greater than the first threshold, then the acquisition scene information corresponding to the target trajectory point is determined to be single acquisition scene information; or, If there is no corresponding reverse trajectory point for the target trajectory point, the acquisition scene information corresponding to the target trajectory point is determined to be single acquisition scene information; The single-collection scene information is used to indicate that the target trajectory point is collected unidirectionally on the target lane.
2. The method according to claim 1, wherein, The element information also includes: hard isolation features, wherein the target trajectory point has corresponding first hard isolation features and second hard isolation features, and the first hard isolation features and the second hard isolation features are located on opposite sides of the target trajectory point; When a corresponding reverse trajectory point exists at the target trajectory point, and the distance between the reverse trajectory point and the target trajectory point is less than or equal to a first threshold, determining the acquisition scene information corresponding to the target trajectory point as dual acquisition scene information includes: If a corresponding reverse trajectory point exists for the target trajectory point, and the distance between the reverse trajectory point and the target trajectory point is less than or equal to a first threshold, the first distance between the first hard isolation feature and the second hard isolation feature is identified. If the first distance is greater than a second threshold, the acquisition scene information corresponding to the target trajectory point is determined to be the dual acquisition scene information; or... When a corresponding reverse trajectory point exists at the target trajectory point, and the distance between the reverse trajectory point and the target trajectory point is greater than the first threshold, determining that the acquisition scene information corresponding to the target trajectory point is single acquisition scene information includes: If a corresponding reverse trajectory point exists for the target trajectory point, and the distance between the reverse trajectory point and the target trajectory point is greater than the first threshold, identify the first distance between the first hard isolation feature and the second hard isolation feature. If the first distance is greater than a third threshold, determine the acquisition scene information corresponding to the target trajectory point as the single acquisition scene information; or, When there is no corresponding reverse trajectory point for the target trajectory point, determining that the acquisition scene information corresponding to the target trajectory point is single acquisition scene information includes: If there is no corresponding reverse trajectory point for the target trajectory point, identify the first distance between the first hard isolation feature and the second hard isolation feature. If the first distance is greater than a fourth threshold, determine the acquisition scene information corresponding to the target trajectory point as the single acquisition scene information.
3. The method according to claim 2, wherein, When the first distance is greater than the second threshold, determining the acquisition scene information corresponding to the target trajectory point as the dual acquisition scene information includes: If the first distance is greater than the second threshold, the width of the target lane is identified; When the width is greater than the second distance, the scene information corresponding to the target trajectory point is determined to be bidirectional multi-lane dual-collection scene information; Wherein, the second distance is the distance between the target trajectory point and the first hard isolation feature or the second hard isolation feature.
4. The method according to claim 2, wherein, The element information further includes: lane line features. The step of determining the acquisition scene information corresponding to the target trajectory point as the single acquisition scene information when the first distance is greater than the third threshold includes: If the first distance is greater than the third threshold, the distance between the target trajectory point and the lane line feature corresponding to the target trajectory point is identified; If the distance between the target trajectory point and the lane line feature corresponding to the target trajectory point is greater than the third distance, the scene information collected corresponding to the target trajectory point is determined to be bidirectional multi-lane single-collection scene information. The third distance is the distance between the target trajectory point and either the first hard isolation feature or the second hard isolation feature.
5. The method according to claim 2, wherein, The first hard isolation feature includes a first sub-feature and a second sub-feature with interval settings. The step of determining the acquisition scene information corresponding to the target trajectory point as the single acquisition scene information when the first distance is greater than a third threshold includes: If the first distance is greater than the third threshold, the distance between the first sub-feature and the second sub-feature is identified; If the distance between the first sub-feature and the second sub-feature is greater than the fourth distance, the acquisition scene information corresponding to the target trajectory point is determined to be bidirectional multi-lane single acquisition scene information; or... If the first distance is greater than the third threshold, the distance between the third sub-feature and the fourth sub-feature is identified, and the second hard isolation feature includes the third sub-feature and the fourth sub-feature that are spaced apart; If the distance between the third sub-feature and the fourth sub-feature is greater than the fourth threshold, the acquisition scene information corresponding to the target trajectory point is determined to be the bidirectional multi-lane single acquisition scene information.
6. The method according to claim 2, wherein, The step of determining the acquisition scene information corresponding to the target trajectory point as the single acquisition scene information when the first distance is greater than the fourth threshold includes: If the first distance is greater than the fourth threshold, determine the number of the first hard isolation feature and the second hard isolation feature; When the number of the first hard isolation feature and the second hard isolation feature is both 1, determine whether the first hard isolation feature and the second hard isolation feature have corresponding lane line features; If neither the first hard isolation feature nor the second hard isolation feature has a corresponding lane line feature, the acquisition scene information corresponding to the target trajectory point is determined to be bidirectional single-lane single acquisition scene information.
7. A scene information determining device, comprising: The first determining module is used to determine the target trajectory point, wherein the target trajectory point is the trajectory point obtained by the sampling device on the target lane, and the sampling device is the sampling vehicle; The acquisition module is used to acquire the element information pre-bound to the target trajectory point; The second determining module is used to determine the collection scene information corresponding to the target trajectory point based on the element information. The collection scene information is one of a single collection scene and a dual collection scene. The collection scene information is used for the recognition or production of high-precision maps. The element information includes: lane line features, hard isolation features, and reverse trajectory points. The hard isolation features are features located at the edge of the road, and the reverse trajectory points are trajectory points that travel in the opposite direction to the target trajectory point. The second determining module is further configured to: If a corresponding reverse trajectory point exists for the target trajectory point, and the distance between the reverse trajectory point and the target trajectory point is less than or equal to a first threshold, the acquisition scene information corresponding to the target trajectory point is determined to be dual acquisition scene information. The dual acquisition scene information indicates that the target trajectory point is acquired bidirectionally on the target lane; or... If a corresponding reverse trajectory point exists for the target trajectory point, and the distance between the reverse trajectory point and the target trajectory point is greater than the first threshold, the collection scene information corresponding to the target trajectory point is determined to be single collection scene information. or, If there is no corresponding reverse trajectory point for the target trajectory point, the acquisition scene information corresponding to the target trajectory point is determined to be single acquisition scene information; The single-collection scene information is used to indicate that the target trajectory point is collected unidirectionally on the target lane.
8. The apparatus according to claim 7, wherein, The element information further includes: hard isolation features, wherein the target trajectory point has corresponding first hard isolation features and second hard isolation features, and the first hard isolation features and the second hard isolation features are respectively located on opposite sides of the target trajectory point; the second determining module is further configured to: If a corresponding reverse trajectory point exists for the target trajectory point, and the distance between the reverse trajectory point and the target trajectory point is less than or equal to a first threshold, the first distance between the first hard isolation feature and the second hard isolation feature is identified. If the first distance is greater than a second threshold, the acquisition scene information corresponding to the target trajectory point is determined to be the dual acquisition scene information; or... If a corresponding reverse trajectory point exists for the target trajectory point, and the distance between the reverse trajectory point and the target trajectory point is greater than the first threshold, identify the first distance between the first hard isolation feature and the second hard isolation feature. If the first distance is greater than a third threshold, determine the acquisition scene information corresponding to the target trajectory point as the single acquisition scene information; or, If there is no corresponding reverse trajectory point for the target trajectory point, identify the first distance between the first hard isolation feature and the second hard isolation feature. If the first distance is greater than a fourth threshold, determine the acquisition scene information corresponding to the target trajectory point as the single acquisition scene information.
9. The apparatus according to claim 8, wherein, The second determining module includes: The first identification submodule is used to identify the width of the target lane when the first distance is greater than the second threshold. The first determining submodule is used to determine that the acquisition scene information corresponding to the target trajectory point is bidirectional multi-lane dual acquisition scene information when the width is greater than the second distance; Wherein, the second distance is the distance between the target trajectory point and the first hard isolation feature or the second hard isolation feature.
10. The apparatus according to claim 8, wherein, The element information further includes: lane line features; the second determining module includes: The second identification submodule is used to identify the distance between the target trajectory point and the lane line feature corresponding to the target trajectory point when the first distance is greater than the third threshold. The second determining submodule is used to determine that the collection scene information corresponding to the target trajectory point is bidirectional multi-lane single collection scene information when the distance between the target trajectory point and the lane line feature corresponding to the target trajectory point is greater than the third distance. The third distance is the distance between the target trajectory point and either the first hard isolation feature or the second hard isolation feature.
11. The apparatus according to claim 8, wherein, The first hard isolation feature includes a first sub-feature and a second sub-feature with an interval setting; The second determining module includes: The third identification submodule is used to identify the distance between the first sub-feature and the second sub-feature when the first distance is greater than the third threshold. The third determining submodule is used to determine, when the distance between the first sub-feature and the second sub-feature is greater than the fourth distance, that the acquisition scene information corresponding to the target trajectory point is bidirectional multi-lane single acquisition scene information; or... The fourth identification submodule is used to identify the distance between the third sub-feature and the fourth sub-feature when the first distance is greater than the third threshold, wherein the second hard isolation feature includes the third sub-feature and the fourth sub-feature that are spaced apart; The fourth determination submodule is used to determine the acquisition scene information corresponding to the target trajectory point as the bidirectional multi-lane single acquisition scene information when the distance between the third sub-feature and the fourth sub-feature is greater than the fourth threshold.
12. The apparatus according to claim 8, wherein, The second determining module includes: The fifth determining submodule is used to determine the number of the first hard isolation feature and the second hard isolation feature when the first distance is greater than the fourth threshold. The sixth determining submodule is used to determine whether there is a corresponding lane line feature for the first hard isolation feature and the second hard isolation feature when the number of the first hard isolation feature and the second hard isolation feature is both 1. The seventh determination submodule is used to determine that the acquisition scene information corresponding to the target trajectory point is bidirectional single-lane single acquisition scene information when neither the first hard isolation feature nor the second hard isolation feature has a corresponding lane line feature.
13. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.
14. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.
15. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.