Method and device for generating evaluation data, electronic equipment and storage medium

Abstract

The present disclosure provides a kind of generation method, device, electronic equipment and storage medium of evaluation data, it is related to intelligent transportation, automatic driving and other technical fields.The specific implementation scheme is: based on the first high-precision map and the second high-precision map, the change information of specified traffic environment element is obtained;The version update time of the second high-precision map is closer to the current time than the version update time of the first high-precision map;Based on the change information of the specified traffic environment element, the sensor data collected by the collection vehicle based on the environment of the second high-precision map is obtained;Based on the sensor data, the identification information of the first high-precision map and the change information of the specified traffic environment element, evaluation data is generated.The present disclosure can effectively improve the accuracy of the generated evaluation data and the generation efficiency of the evaluation data.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, specifically to the fields of intelligent transportation and autonomous driving, and in particular to a method, apparatus, electronic device and storage medium for generating evaluation data. Background Technology

[0002] Autonomous driving systems rely on lane line information and prior information such as traffic lights recorded in high-precision maps for high-precision positioning, motion planning, and rapid detection and recognition of traffic light colors. However, problems such as road repairs, lane line repainting, and traffic light equipment replacement often occur at the roadside, resulting in insufficient map freshness, which in turn affects the motion control of autonomous vehicles and may lead to unexpected situations such as running red lights, driving over solid lane lines, not driving in designated lanes, and insufficient positioning accuracy.

[0003] The lane change detection and traffic light change detection functions are mainly designed to solve the above problems, detect and discover lane change or traffic light change information at the road end as early as possible, and update the high-precision map in a timely manner. Summary of the Invention

[0004] This disclosure provides a method, apparatus, electronic device, and storage medium for generating evaluation data.

[0005] According to one aspect of this disclosure, a method for generating evaluation data is provided, comprising:

[0006] Based on the first and second high-precision maps, change information of specified traffic environment elements is obtained; the version update time of the second high-precision map is more recent than the version update time of the first high-precision map.

[0007] Based on the change information of the specified traffic environment elements, obtain the sensor data collected by the data collection vehicle based on the environment of the second high-precision map;

[0008] Evaluation data is generated based on the sensor data, the identification information of the first high-precision map, and the change information of the specified traffic environment elements.

[0009] According to another aspect of this disclosure, an apparatus for generating evaluation data is provided, comprising:

[0010] The change information acquisition module is used to acquire change information of specified traffic environment elements based on the first high-precision map and the second high-precision map; the version update time of the second high-precision map is closer to the current time than the version update time of the first high-precision map.

[0011] The sensor data acquisition module is used to acquire sensor data collected by the vehicle based on the environment of the second high-precision map, based on the change information of the specified traffic environment elements.

[0012] The generation module is used to generate evaluation data based on the sensor data, the identification information of the first high-precision map, and the change information of the specified traffic environment elements.

[0013] According to another aspect of this disclosure, an electronic device is provided, comprising:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the methods described above and any possible implementations.

[0017] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions for causing the computer to perform the methods described above and any possible implementation thereof.

[0018] According to another aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the aspects and any possible implementations described above.

[0019] According to the technology disclosed herein, the accuracy and efficiency of the generated evaluation data can be effectively improved.

[0020] 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

[0021] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0022] Figure 1 This is a schematic diagram based on the first embodiment of the present disclosure;

[0023] Figure 2 This is a schematic diagram according to the second embodiment of the present disclosure;

[0024] Figure 3 This is a schematic diagram according to the third embodiment of the present disclosure;

[0025] Figure 4 This is a schematic diagram according to the fourth embodiment of the present disclosure;

[0026] Figure 5 This is a block diagram of an electronic device used to implement the methods of the embodiments of this disclosure. Detailed Implementation

[0027] 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.

[0028] Obviously, the described embodiments are only some, not all, of the embodiments disclosed herein. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without inventive effort are within the scope of protection of this disclosure.

[0029] It should be noted that the terminal devices involved in the embodiments of this disclosure may include, but are not limited to, smart devices such as mobile phones, personal digital assistants (PDAs), wireless handheld devices, and tablet computers; the display devices may include, but are not limited to, personal computers, televisions, and other devices with display functions.

[0030] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0031] To improve the efficiency of detecting changes in lane markings or traffic lights on vehicles, the efficient and accurate evaluation of lane marking or traffic light change detection algorithms is crucial. In existing technologies, safety operators can manually take over and visually replay the data collected from vehicles. They can manually mark the time, location, and type of changes to lane markings or traffic lights on the real road to create evaluation data. This marked evaluation data is then used to detect and evaluate the vehicle-side detection algorithms.

[0032] However, in the existing technology, the evaluation data constructed by manual labeling is not only inefficient in generating evaluation data, but also has poor accuracy due to the manual nature of the process.

[0033] Figure 1 This is a schematic diagram based on the first embodiment of the present disclosure; as shown Figure 1As shown, this embodiment provides a method for generating evaluation data, which can be used to automatically generate evaluation data for detection algorithms of autonomous vehicles. Specifically, it may include the following steps:

[0034] S101. Based on the first high-precision map and the second high-precision map, obtain the change information of the specified traffic environment elements; the version update time of the second high-precision map is closer to the current time than the version update time of the first high-precision map;

[0035] S102. Based on the change information of specified traffic environment elements, obtain the sensor data collected by the vehicle based on the environment of the second high-precision map;

[0036] S103. Based on sensor data, the identification information of the first high-precision map, and the change information of specified traffic environment elements, generate evaluation data.

[0037] The subject executing the evaluation data generation method in this embodiment can be an evaluation data generation device. This device can be an electronic entity or a software-integrated application. When in use, it can run on a computer or other device to realize the automatic generation of evaluation data.

[0038] In this embodiment, the first and second high-precision maps are two different versions of high-precision maps. Specifically, in this embodiment, the version update time of the second high-precision map is more recent than that of the first high-precision map, meaning the second high-precision map is a newer version than the first high-precision map. Specifically, the first and second high-precision maps in this embodiment can be two consecutive versions or non-consecutive versions, meaning there can be multiple versions between the second and first high-precision maps. In this case, the second high-precision map shows more changes in traffic environment elements compared to the first high-precision map, resulting in richer evaluation data.

[0039] The traffic environment elements in this embodiment are traffic elements used to indicate the movement of vehicles on the road. For example, traffic environment elements may include lane lines or traffic lights. The traffic lights in this embodiment can also be called red and green lights. The specified traffic environment elements in this embodiment can be any traffic environment element in a first high-definition map or a second high-definition map. Using this embodiment, corresponding evaluation data can be generated based on any traffic environment element that has changed relative to the first high-definition map but in the second high-definition map.

[0040] In this embodiment, change information of specified traffic environment elements is first obtained based on a first high-precision map and a second high-precision map. If the type of the specified traffic environment element is a lane line, the changes to the specified traffic environment element can include changes in the position of the lane line and / or changes in other parameter attributes besides the position of the lane line, such as changes in the lane type. Changes in the position of the lane line can include adding a lane line at a specified location, deleting a lane line at a specified location, shifting the lane line position left or right, moving the lane line position forward or backward, or moving the lane line from a first position to a second position, etc. Changes in the lane type can include changing from none to one, from one to none, or changing from one type of lane type to another, such as changing a solid line to a dashed line, a straight line to a left-turn line, and a left-turn line to a straight line, etc. In the cases of changing from none to one and from one to none, the specific position and type of the lane line also need to be clearly defined.

[0041] When the specified traffic environment element is a traffic light, changes to this element can include changes to the location of the traffic light and / or changes to other parameter attributes besides its location, such as changes to the light type. Changes to the location of a traffic light can include adding or deleting it at a specified location, shifting it horizontally or vertically, or moving it from one location to another. Changes to the light type can include adding or removing the light, changing it from one type to another (e.g., from square to round, round to square, arrow lights to traffic lights, traffic lights to arrow lights), and changes in the number of traffic lights.

[0042] Additionally, it should be noted that in this embodiment, the change of a traffic environment element from one location to another must be within a preset area; otherwise, it is considered an addition or deletion of the traffic environment element. The preset area can be set according to the actual scenario or needs. For example, the preset area can be set to a region where the distance does not exceed a preset distance threshold. This preset distance threshold can be set to a distance value such as 10m or 9m, and is not limited here. For example, regarding the change of traffic light location, if the distance difference before and after the change is within 10m, it can be considered that the traffic light has changed from its original location to the new location. However, if the distance before and after the change exceeds 10m, it is considered that the traffic light was deleted from the original location and added to the new location.

[0043] To generate high-quality evaluation data, this embodiment also requires acquiring sensor data collected by the data collection vehicle based on the environment of the second high-precision map, based on the change information of specified traffic environmental elements. In this embodiment, the data collection vehicle is a road test or operational vehicle, capable of collecting sensor data in the environment corresponding to the second high-precision map, thus providing effective data support for the evaluation data. Finally, based on the sensor data, the identification information of the first high-precision map, and the change information of the specified traffic environmental elements, the evaluation data can be automatically generated.

[0044] The evaluation data generation method of this embodiment can automatically generate evaluation data by adopting the above-described approach. Compared with the prior art, it does not rely on manual generation and can effectively improve the accuracy and efficiency of the generated evaluation data.

[0045] In one embodiment of this disclosure, step S101 may include the following steps:

[0046] (1) Load the attribute information of traffic environment elements in the first and second high-precision maps;

[0047] In this embodiment, the attribute information of traffic environment elements may include location and other parameter attribute information.

[0048] For example, when the type of traffic environment element is lane markings, the attribute information of the traffic environment element can include the position and type of the lane markings. For example, the lane marking type can include solid straight lines, dashed straight lines, left-turn lines, etc. Other parameter attribute information can also include descriptive information about the lane markings. This descriptive information can include location descriptions such as the first lane marking from the left, the second lane marking from the left, and a description of the vehicle travel direction on the road where the lane markings are located. It can also include descriptions of the lane markings' color, line width, etc. For example, at non-intersection locations, some lane markings are only marked with solid lines and no arrow markings. In this case, the corresponding vehicle travel direction can be described in the descriptive information. The position of the lane markings can be identified using the coordinates of key points on the lane markings. That is, the position of the lane markings can be identified using a coordinate sequence including multiple sets of coordinates.

[0049] If the type of traffic environment element is traffic light, the attribute information of the traffic environment element includes the location of the traffic light, as well as other parameter attribute information such as the light type and other descriptive information.

[0050] Based on the above, it can be understood that the attribute information of traffic environment elements can include all the basic information of the traffic environment element, such as location, line type or light type, as well as all the descriptive information of the traffic environment element in the high-precision map.

[0051] (2) Compare the attribute information of traffic environment elements in the same location area in the first high-precision map and the second high-precision map to obtain the change information of the specified traffic environment elements.

[0052] Specifically, the attribute information of traffic environment elements within the same location area in the first and second high-precision maps can be traversed and compared. A correspondence relationship is established between traffic environment elements in the same location area in the first and second high-precision maps, and then, based on this correspondence, change information of a specified traffic environment element can be obtained. Specifically, this change information of the specified traffic environment element can be used to identify changes in the specified traffic environment element relative to the first high-precision map and described in the second high-precision map. In this embodiment, the maximum distance between the position coordinates of all points within the same location area is not greater than a preset distance threshold, such as 10m, 9m, etc., depending on actual needs. For example, if the distance between the positions of a first traffic environment element in the first high-precision map and a second traffic environment element in the second high-precision map is less than or equal to the preset distance threshold, they are considered to belong to the same location area; otherwise, if it is greater than the preset distance threshold, they are considered not to belong to the same location area.

[0053] For example, in a certain location area, both the first and second high-definition maps include a traffic light. The traffic light in the first high-definition map and the traffic light in the second high-definition map can be considered to correspond. Then, the positions and other parameter attributes of the two traffic lights are compared. If the positions and other parameter attributes are exactly the same, the traffic light is considered unchanged. If the positions and / or other parameter attributes have changed, the traffic light is considered changed. In this case, the change information of the traffic light can be obtained by comparing the attribute information of the corresponding two traffic lights in the two high-definition maps. Specifically, the description of the traffic light change information can be a description of the change in the traffic light relative to the first high-definition map and in the second high-definition map. The principle is the same when the type of traffic environment element is a lane line, and will not be elaborated further here.

[0054] In this embodiment, the changes to the specified traffic environment elements may include the following:

[0055] The first scenario involves specified traffic environment elements existing in both the first and second high-precision maps, but with changes in location and / or other attributes.

[0056] The second type, compared to the first high-precision map, adds specified traffic environment elements to the second high-precision map.

[0057] The third type involves deleting specific traffic environment elements in a second high-definition map relative to the first high-definition map. For example, the change information for the specified traffic environment element obtained in this case could be the deletion of the specified traffic environment element at a certain location in the second high-definition map relative to the first high-definition map.

[0058] Based on the above, it can be seen that regardless of whether the specified traffic environment element is a lane line or a traffic light, the location and other parameter attribute information such as the line type or light type of the specified traffic environment element can be obtained, thereby determining the attribute information of the change of the specified traffic environment element; and the change information of the specified traffic environment element can be determined based on the location and the changed attribute information of the specified traffic environment element.

[0059] For example, in this embodiment, the change information of the specified traffic environment element may include the changed location and changed content of the specified traffic environment element.

[0060] The "Change Location of Designated Traffic Environment Elements" is used to identify the location information of designated traffic environment elements that have changed. The "Change Location of Designated Traffic Environment Elements" includes the location of the designated traffic environment element before and / or after the change, or it includes the location of the designated traffic environment element where parameter attribute information other than location has changed. In other words, the "Change Location of Designated Traffic Environment Elements" does not necessarily mean that the location of the designated traffic environment element has changed; it can also refer to the location of the designated traffic environment element where other attribute information, such as lane alignment or traffic light pattern, has changed.

[0061] In this embodiment, the change location of a specified traffic environment element can include a specified location. For example, this specified location can indicate that a change of the specified traffic environment element has occurred at that location, meaning that there are two corresponding traffic environment elements in the two versions of the high-definition map, but the positions of the two traffic environment elements have not changed, while other parameter attribute information besides the position has changed. Alternatively, the specified location can also include only the changed location, in which case the specified traffic environment element has been added at the specified location in the second high-definition map relative to the first high-definition map. Alternatively, the specified location can also include only the location before the change, in which case the specified traffic environment element has been deleted at the specified location in the second high-definition map relative to the first high-definition map.

[0062] Alternatively, the specified change location of traffic environment elements may include two locations: the location before the change and the location after the change. In this embodiment, a specified location is not a single coordinate information, but rather the location of a set of coordinate markers. For example, if a lane line changes from a solid line to a dashed line, the corresponding change location is the position of the lane line as indicated by the coordinates of multiple key points of the lane line.

[0063] Correspondingly, changes to specified traffic environment elements can include several scenarios: adding specified traffic environment elements at specified locations, deleting specified traffic environment elements at specified locations, and modifying specified traffic environment elements; among which, modifying specified traffic environment elements can include changing the location and / or other parameter attribute information of specified traffic environment elements.

[0064] By using the above method, the change information of each specified traffic environment element can be determined by traversing each location area in the first high-precision map and the second high-precision map and comparing the traffic environment elements in each location area in the first high-precision map and the second high-precision map, thus providing rich data support for the generation of subsequent evaluation data.

[0065] Figure 2 This is a schematic diagram based on the second embodiment of the present disclosure; as shown Figure 2 As shown, the evaluation data generation method of this embodiment, in the above... Figure 1 Based on the technical solutions of the embodiments shown, the technical solutions of this disclosure will be described in further detail.

[0066] S201. Load the attribute information of traffic environment elements from the first and second high-precision maps;

[0067] S202. Obtain the attribute information of the first traffic environment element in the second high-precision map;

[0068] The attribute information of the first traffic environment element may include the location and other parameter attribute information of the first traffic environment element, such as the line type or light type, and other descriptive information.

[0069] S203. Based on the attribute information of the first traffic environment element, detect whether the same location area in the first high-precision map includes a second traffic environment element corresponding to the first traffic environment element; if it includes, proceed to step S204; if it does not include, proceed to step S206.

[0070] In this embodiment, the method of traversing and comparing the attribute information of traffic environment elements in each location area of ​​the first high-precision map and the second high-precision map can be used to detect whether the same location area in the first high-precision map includes a second traffic environment element corresponding to the first traffic environment element.

[0071] For example, following step S202, the location and attribute information of a first traffic environment element in the second high-precision map can be obtained first. Then, a preset area with a diameter equal to a preset distance threshold is drawn, centered on the location of the first traffic environment element, as the same location area. Then, based on this same location area, it is detected whether the first high-precision map includes the corresponding traffic environment element. In this embodiment, the corresponding traffic environment element can refer to traffic environment elements of the same type, such as lane lines or traffic lights.

[0072] Furthermore, if there are two or more traffic environment elements of the same type in the first high-precision map within the same location area, the description information of the traffic environment elements can be referenced to select one of the corresponding traffic environment elements as the second traffic environment element corresponding to the first traffic environment element; the others can be added as new traffic environment elements.

[0073] In one application scenario of this disclosure, since lane lines are typically close in lateral distance but long in longitudinal distance, if we follow the single lane line comparison method described above, first obtaining a lane line from the second high-precision map, and then, within the same location area, the first high-precision map may include two or three lane lines, it is necessary to further check whether the second high-precision map includes other lane lines within the same location area to accurately determine the correspondence between the lane lines in the first and second high-precision maps. This operation is rather cumbersome. To improve efficiency, when obtaining lane lines from the second high-precision map, all lane lines within the same location area can be directly selected, such as lane lines whose lateral vertical distance is no greater than a preset distance threshold. Then, the correspondence between the lane lines in the first and second high-precision maps can be determined by referring to the description information of each lane line, such as the lane line sequence identifier and the corresponding vehicle driving direction. Specifically, a correspondence can be established between lane lines in the two high-precision maps that have the same vehicle driving direction and the same lane line sequence identifier. Lane lines for which no correspondence cannot be found are considered newly added or deleted lane lines. Of course, other methods can also be used to determine the correspondence between the same type of traffic environment elements in the two versions of high-precision maps, which is not limited here.

[0074] S204. Based on the attribute information of the first traffic environment element, obtain the attribute information of the second traffic environment element corresponding to the first traffic environment element from the same location area in the first high-precision map; execute step S205.

[0075] S205. Based on the attribute information of the first traffic environment element and the attribute information of the second traffic environment element, determine the first traffic environment element as the change information of the designated traffic environment element; execute step S207.

[0076] The change information for the specified traffic environment element is used to identify changes that occur relative to the first high-precision map and in the second high-precision map. This change information includes the changed location and the changed content. As described in the above embodiments, the changed location of the specified traffic environment element is used to identify the location information of the changed specified traffic environment element; the changed location includes the location of the specified traffic environment element before and / or after the change, or includes the location of the specified traffic environment element where other parameter attribute information besides location has changed.

[0077] Steps S202-S205 in this embodiment are a specific implementation of step (2) in the above embodiment.

[0078] In this implementation method, taking the acquisition of any first traffic environment element in the second high-precision map as an example, the method then compares whether the same location area in the first high-precision map includes the corresponding traffic environment element, thereby efficiently and accurately determining the change information of the specified traffic environment element.

[0079] The above steps S204-205 correspond to the following situation: in the same location area in the first high-precision map and the second high-precision map, there are two corresponding traffic environment elements, but the location of the two corresponding traffic environment elements has changed or other parameter attribute information such as line type or light type has changed.

[0080] S206. Based on the attribute information of the first traffic environment element in the second high-precision map, determine the first traffic environment element as the change information of the designated traffic environment element; execute step S207.

[0081] The scenario corresponding to step S206 is that, in the second high-definition map, traffic environment elements have been added compared to the first high-definition map. The change information of the specified traffic environment elements obtained in step S206 is also change information describing the changes of the specified traffic environment elements in the second high-definition map compared to the first high-definition map.

[0082] It should be noted that, following steps S202-S206 above, taking the acquisition of the first traffic environment element from any location in the second high-precision map as an example, traffic environment elements present in the first high-precision map but deleted from the second high-precision map cannot be detected. To solve this problem, in one embodiment of this disclosure, the following steps can also be performed:

[0083] (a) Obtain the attribute information of the third traffic environment element from the first high-precision map; wherein there is no traffic environment element corresponding to the third traffic environment element in the same location area as the third traffic environment element in the second high-precision map;

[0084] (b) Based on the attribute information of the third traffic environment element, determine the change information of the third traffic environment element as the specified traffic environment element;

[0085] The change information for the specified traffic environment element is also the change information describing the changes that have occurred in the specified traffic environment element in the second high-precision map, relative to the first high-precision map.

[0086] Based on the above, change information of specified traffic environment elements under various circumstances can be obtained, which can effectively ensure the comprehensiveness and richness of the change information of specified traffic environment elements, and thus effectively enrich the content of the generated evaluation data.

[0087] Next, taking the change information of any specified traffic environment element obtained above as an example, the process of generating the evaluation data of this disclosure will be described in more detail. As described in the above embodiments, the change information of the specified traffic environment element includes the change location and the change content.

[0088] S207. Based on the changed location of the specified traffic environment elements, the driving trajectory of the vehicle based on the second high-precision map, and the video data collected by the vehicle, obtain the first time point before the vehicle travels to the changed location of the specified traffic environment elements and the first time the camera captures the changed location of the specified traffic environment elements; execute step S208.

[0089] In this embodiment, the vehicle's driving trajectory within the environment of the second high-precision map includes the trajectory points reached by the vehicle at each time point. The video data collected by the vehicle may include video frames captured by the vehicle at each time point.

[0090] This step involves analyzing each video frame in the video data before the vehicle travels to the changed location of the specified traffic environment element, to obtain the first time point before the camera first captures the changed location of the specified traffic environment element.

[0091] For example, if the change location of a specified traffic environment element includes only one location, the following situations apply: the specified traffic environment element is added at the change location, the specified traffic environment element is deleted at the change location, or other attribute information of the specified traffic environment element is changed at the change location.

[0092] When a specified traffic environment element is added or its attributes are changed at a particular location, the camera can still capture that element. Therefore, by analyzing each video frame in the video data, the first time point at which the camera initially captured the specified traffic environment element can be determined, serving as the first time point at which the camera initially captured the changed location of the specified traffic environment element. Conversely, when a specified traffic environment element is deleted at a particular location, meaning it cannot be captured in the video data collected by the sensor in the environment of the second high-precision map, the real-world location of each point in the camera's captured image in each video frame can be deduced by analyzing each video frame. This allows us to deduce the first time point at which the camera initially captured the changed location of the specified traffic environment element.

[0093] If the change location of a specified traffic environment element includes two locations—one before the change and one after the change—the location closest to the vehicle along its direction of travel can be used as a reference location. The time point at which the camera first captures this reference location is then taken as the first time point.

[0094] S208. Based on the changed location of the specified traffic environment element and the driving trajectory of the collected vehicle, obtain the second time point corresponding to when the collected vehicle travels to the changed location of the specified traffic environment element or the stop line before the changed location; execute step S209.

[0095] For example, if the type of the specified traffic environment element is lane line, then the second time point corresponding to when the vehicle travels to the changed position of the specified traffic environment element can be obtained based on the changed position of the specified traffic environment element and the driving trajectory of the collected vehicle.

[0096] Correspondingly, if the change location of the specified traffic environment element includes only one location, the second time point corresponding to when the vehicle travels to the changed location can be obtained by analyzing the driving trajectory of the collected vehicle.

[0097] Correspondingly, if the change location of a specified traffic environment element includes two locations—a location before the change and a location after the change—the location closest to the vehicle in the direction of travel can be taken as a reference location. The time point corresponding to when the vehicle reaches this reference location can then be obtained as the second time point.

[0098] If the type of the specified traffic environment element is traffic light, then, based on the change location of the specified traffic environment element and the driving trajectory of the collected vehicle, the corresponding second time point can be obtained when the collected vehicle travels to the stop line before the change location of the specified traffic environment element.

[0099] For traffic lights, the second time point is the time when the vehicle stops before it reaches the stop line of the designated traffic environment element, and not the time when the vehicle is at the traffic light. If the vehicle is at the traffic light and fails to recognize the change in the traffic light in time, there is a risk of traffic violation.

[0100] Correspondingly, if the change location of the specified traffic environment element includes only one location, the location of the stop line can be obtained based on the attribute information of the stop line, and then the second time point corresponding to when the collected vehicle travels to the stop line can be obtained by analyzing the driving trajectory of the collected vehicle.

[0101] Similarly, if the specified changes in traffic environment elements include two locations, we can detect whether the corresponding stop line changes after the traffic light position changes. If it doesn't change, meaning it corresponds to one stop line, the above method can be used. If the two positions before and after the change correspond to two stop lines, we can obtain the stop line closer to the vehicle in the direction of travel as a reference stop line. We can then obtain the time point corresponding to when the vehicle reaches the reference stop line as the second time point.

[0102] S209. Based on the first time point and the second time point, determine the target time period; execute step S210;

[0103] For example, in order to obtain a more accurate and effective target time period, the starting time point of the target time period can be obtained by subtracting a first preset duration threshold from the first time point.

[0104] The second time point plus a second preset duration threshold is used as the end time point of the target time period. Then, the target time period is determined based on the start time point and the end time point of the target time period.

[0105] The first and second preset duration thresholds in this embodiment can be set according to actual needs or experience. For example, the first preset duration threshold can be 10 seconds, or it can be a duration value around 10 seconds, such as 9 seconds or 11 seconds. The second preset duration threshold can also be a duration value around 10 seconds, such as 10 seconds, 9 seconds, or 11 seconds, or it can be a duration value around 20 seconds, such as 20 seconds, 21 seconds, or 19 seconds.

[0106] The target time period determined by the above method is very reasonable and accurate. The video data of this target time period can identify the process of the collecting vehicle from the change position of the specified traffic environment element to the stop line before the change position of the specified traffic environment element. The content is very complete and can provide effective data support for the generation of evaluation data.

[0107] S210. Based on the changed location of the specified traffic environment elements, obtain the intrinsic and extrinsic parameters of the camera of the data collection vehicle, the video data collected by the camera during the target time period when the data collection vehicle is collecting data based on the environment of the second high-precision map, and the pose information of the positioning system of the data collection vehicle during the target time period; execute step S211.

[0108] As mentioned above, the target time period can identify the process from when the data collection vehicle collects data at the changed location of the specified traffic environment element to when it reaches the changed location of the specified traffic environment element or the stop line before the changed location.

[0109] In this embodiment, the collected sensor data includes the intrinsic and extrinsic parameters of the vehicle's camera, video data collected by the camera during the target time period when the vehicle is collecting data based on the environment of the second high-precision map, and the pose information of the vehicle's positioning system during the target time period. This method yields very comprehensive and rich sensor data.

[0110] S211. Based on the target time period, collect sensor data from vehicles and verify the change information of specified traffic environment elements; execute step S212.

[0111] S212. Check if the verification is successful; if successful, proceed to step S213; otherwise, proceed to step S215.

[0112] For example, the verification in this embodiment may include verification in at least one of the following ways:

[0113] The first method involves collecting the intrinsic and extrinsic parameters of the vehicle's camera and the pose information of the vehicle's positioning system at various time points within the target time period. At each time point, the changed position of the specified traffic environment element is projected onto the camera coordinate system of the vehicle. If the proportion of successful projection within the target time period reaches a preset threshold, the verification is considered successful. Otherwise, the verification is considered unsuccessful, indicating that the vehicle could not collect the changed position of the specified traffic environment element within the target time period exceeding the preset threshold. In this case, the vehicle cannot identify the change of the specified traffic environment element, and cannot generate effective evaluation data based on the change of the specified traffic environment element.

[0114] In this embodiment, the camera used to collect vehicle data faces forward and detects information ahead. However, this camera also has blind spots, resulting in some areas of information not being visible. Therefore, in this method, for each time point within the target time period for vehicle data collection, based on the camera's intrinsic and extrinsic parameters and the pose information of the vehicle's positioning system corresponding to that time point, and referring to the changing position of a specified traffic environmental element in space, the changing position of the specified traffic environmental element is projected onto the camera coordinate system. If the projection is successful, it can be considered that the camera has collected the changing position of the specified traffic environmental element at that time point, and the change of the specified traffic environmental element can be identified. If the changing position of any point of the specified traffic environmental element cannot be projected, it is considered that the camera has not collected the changing position of the specified traffic environmental element, and the change of the specified traffic environmental element cannot be identified.

[0115] It should be noted that if the change of location involves only one location, the above method can be directly implemented. If the change of location involves two locations, namely the location before the change and the location after the change, then when verifying the above method, when projecting at each time point, both the location before and after the change of the specified traffic environment element need to be projected into the camera coordinate system of the data acquisition vehicle. If the projection is successful, it means that the camera at that time point can acquire the location before and after the change and can identify the change of the specified traffic environment element. If either the location before or after the change is not successfully projected, it means that the camera at that time point cannot completely acquire the location before and after the change and cannot identify the change of the specified traffic environment element.

[0116] It should be noted that the target time period includes multiple consecutive time points. In this implementation, for each time point within the target time period, the changed location of the specified traffic environment element can be projected onto the camera coordinate system using the method described above. If the number of successfully projected time points accounts for a preset percentage threshold of the target time period, the verification is considered successful.

[0117] The second method involves obtaining obstacle information around the vehicle from the sensor data collected from the sensor data at each time point within the target time period. This obstacle information is then projected onto the camera coordinate system of the vehicle and the system checks whether the obstacle information at each time point occludes the specified traffic environment elements. If the proportion of unoccluded elements within the target time period is lower than a preset threshold, the verification is considered successful.

[0118] In practical applications, when collecting sensor data from vehicles, obstacle information around a specified traffic environmental element may obscure that element, resulting in the collected sensor data not including it. Consequently, evaluation data cannot be effectively generated based on such sensor data. Therefore, the second method described above is required for verification.

[0119] Specifically, in this implementation, for each time point within the target time period, the obstacle information collected by the vehicle at that time point can be projected onto the camera coordinate system of the vehicle, and then it can be detected whether the obstacle information occludes the specified traffic environment element. For example, it can be detected whether the position of the obstacle information and the position of the specified traffic environment element overlap in the projected camera coordinate system. If so, it can be considered that the obstacle information occludes the specified traffic environment element. This corresponding detection is performed for each time point within the target time period in the same manner. If the proportion of unoccluded elements within the target time period is lower than a preset threshold, it can be considered that there is still a portion of the target time period where the specified traffic environment element can be seen, and the verification is considered successful.

[0120] The preset ratio threshold in this embodiment can be set according to experience or actual needs, such as 0.7, 0.8, etc., and is not limited here.

[0121] S213. Use the intrinsic and extrinsic parameters of the camera of the acquisition vehicle, the video data of the target time period acquired by the camera, the pose information of the positioning system of the acquisition vehicle in the target time period, and the identification information of the first high-precision map as the input data for the evaluation data; execute step S214.

[0122] S214. Use the changes to the specified traffic environment elements as the annotation data for the evaluation data, and then end.

[0123] Specifically, in use, the input data for the evaluation data is fed into the vehicle-side traffic environment element change detection module. Based on the input information, this module outputs a predicted change result. The predicted change result can then be evaluated using the labeled data from this evaluation data. This method allows for the efficient and accurate generation of both input and labeled data for the evaluation data.

[0124] S215. Remove the changed location and changed content of the specified traffic environment element, and end.

[0125] This means that no corresponding evaluation data will be generated based on the changed location and changed content of the specified traffic environment element. In this embodiment, through the above verification, invalid changed location and changed content of the specified traffic environment element can be deleted, which can effectively ensure the accuracy of the generated evaluation data.

[0126] The evaluation data generation method of this embodiment can automatically and efficiently produce evaluation data using the above-described approach. Compared with the existing method of manually generating evaluation data, it can effectively improve the accuracy of the generated evaluation data and increase the efficiency of evaluation data generation.

[0127] Moreover, the evaluation data generated in this embodiment can effectively and efficiently evaluate the vehicle-side traffic environment elements such as lane lines and / or traffic lights detection modules, thereby improving the vehicle-side's detection accuracy and efficiency for changing lane lines and / or traffic lights.

[0128] Figure 3 This is a schematic diagram based on the third embodiment of this disclosure; as shown Figure 3 As shown, the evaluation data generation device 300 of this embodiment includes:

[0129] The change information acquisition module 301 is used to acquire change information of specified traffic environment elements based on the first high-precision map and the second high-precision map; the version update time of the second high-precision map is closer to the current time than the version update time of the first high-precision map.

[0130] The sensor data acquisition module 302 is used to acquire sensor data collected by the vehicle based on the environment of the second high-precision map, based on the change information of the specified traffic environment elements.

[0131] The generation module 303 is used to generate evaluation data based on the sensor data, the identification information of the first high-precision map, and the change information of the specified traffic environment elements.

[0132] The evaluation data generation device 300 in this embodiment achieves the same implementation principle and technical effect as the above-mentioned related method embodiments by using the above-mentioned modules to generate evaluation data. For details, please refer to the description of the above-mentioned related method embodiments, which will not be repeated here.

[0133] Figure 4 This is a schematic diagram based on the fourth embodiment of the present disclosure; as shown Figure 4 As shown, the evaluation data generation device 400 of this embodiment includes the above-described... Figure 3 The modules with the same name and function shown are: Change Information Acquisition Module 401, Sensor Data Acquisition Module 402, and Generation Module 403.

[0134] The change information acquisition module 401 is used for:

[0135] Load the attribute information of traffic environment elements from the first high-precision map and the second high-precision map;

[0136] By comparing the attribute information of traffic environment elements in the same location area in the first high-precision map and the second high-precision map, change information of the specified traffic environment element is obtained.

[0137] Optionally, in one embodiment of this disclosure, the change information acquisition module 401 is used for:

[0138] Based on the attribute information of the first traffic environment element, detect and determine that the same location area in the first high-precision map includes a second traffic environment element corresponding to the first traffic environment element in the second high-precision map. Based on the attribute information of the first traffic environment element, obtain the attribute information of the second traffic environment element corresponding to the first traffic environment element from the same location area in the first high-precision map.

[0139] Based on the attribute information of the first traffic environment element and the attribute information of the second traffic environment element, the first traffic environment element is determined as the change information of the specified traffic environment element. The change information of the specified traffic environment element is used to identify the change information that describes the specified traffic environment element in the second high-precision map relative to the first high-precision map.

[0140] Optionally, in one embodiment of this disclosure, the change information acquisition module 401 is further configured to:

[0141] Based on the attribute information of the first traffic environment element, it is detected and determined that there is no second traffic environment element corresponding to the first traffic environment element in the second high-precision map within the same location area in the first high-precision map. Based on the attribute information of the first traffic environment element in the second high-precision map, the first traffic environment element is determined as the change information of the specified traffic environment element. The change information of the specified traffic environment element is used to identify the change information that describes the specified traffic environment element in the second high-precision map relative to the first high-precision map.

[0142] Optionally, in one embodiment of this disclosure, the change information acquisition module 401 is further configured to:

[0143] Obtain the attribute information of the third traffic environment element from the first high-precision map; wherein, in the second high-precision map, there is no traffic environment element corresponding to the third traffic environment element in the same location area as the third traffic environment element;

[0144] Based on the attribute information of the third traffic environment element, the third traffic environment element is determined as the change information of the designated traffic environment element. The change information of the designated traffic environment element is used to identify the change information that describes the designated traffic environment element relative to the first high-precision map and in the second high-precision map.

[0145] Optionally, in one embodiment of this disclosure, the change information of the specified traffic environment element includes the changed location of the specified traffic environment element, used to identify the location information of the specified traffic environment element that has changed; the changed location of the specified traffic environment element includes the location of the specified traffic environment element before and / or after the change, or includes the location of the specified traffic environment element whose other parameter attribute information besides location has changed.

[0146] Optionally, in one embodiment of this disclosure, the sensor data acquisition module 402 is used for:

[0147] Based on the changed location of the specified traffic environment element, the intrinsic and extrinsic parameters of the camera of the data collection vehicle are obtained, along with the video data collected by the camera during the target time period when the data collection vehicle is collecting data based on the environment of the second high-precision map, and the pose information of the positioning system of the data collection vehicle during the target time period. The target time period identifies the process from when the data collection vehicle detects the changed location of the specified traffic environment element to when it reaches the changed location of the specified traffic environment element or the stop line before the changed location. Optionally, as... Figure 4 As shown, in one embodiment of this disclosure, the evaluation data generation device 400 further includes: a time period determination module 404, used for:

[0148] Based on the changed location of the specified traffic environment element, the driving trajectory of the data collection vehicle based on the environment of the second high-precision map, and the video data collected by the data collection vehicle, the first time point before the data collection vehicle travels to the changed location of the specified traffic environment element and the first time the camera collects the changed location of the specified traffic environment element is obtained.

[0149] Based on the changed location of the specified traffic environment element and the driving trajectory of the data collection vehicle, obtain the second time point corresponding to when the data collection vehicle drives to the changed location of the specified traffic environment element or the stop line before the changed location;

[0150] Based on the first time point and the second time point, the target time period is determined. Optionally, in one embodiment of this disclosure, the generation module 403 is used to:

[0151] The intrinsic and extrinsic parameters of the camera of the acquisition vehicle, the video data of the target time period acquired by the camera, the pose information of the positioning system of the acquisition vehicle in the target time period, and the identification information of the first high-precision map are used as the input data for the evaluation data.

[0152] The changes to the specified traffic environment elements are used as the annotation data for the evaluation data. Optionally, as follows: Figure 4 As shown, in one embodiment of this disclosure, the evaluation data generation apparatus 400 further includes:

[0153] Verification module 405 is used to verify the change information of the specified traffic environment elements based on the target time period and the sensor data of the collected vehicles; determination module 406 is used to determine whether the verification is successful.

[0154] Optionally, in one embodiment of this disclosure, the verification module 405 is configured to:

[0155] Based on the intrinsic and extrinsic parameters of the camera of the data acquisition vehicle and the pose information of the positioning system of the data acquisition vehicle at each time point in the target time period, the changed positions of the specified traffic environment elements are projected onto the camera coordinate system of the data acquisition vehicle at each time point; if the proportion of successful projection within the target time period reaches a preset proportion threshold, the verification is confirmed to be successful; or

[0156] If the sensor data of the acquisition vehicle also includes obstacle information around the acquisition vehicle, the obstacle information around the acquisition vehicle at each time point in the target time period is obtained from the sensor data, the obstacle information at each time point is projected onto the camera coordinate system of the acquisition vehicle, and it is detected whether the obstacle information at each time point occludes the specified traffic environment element; if the proportion of unoccluded elements in the target time period is lower than a preset proportion threshold, the verification is determined to be successful.

[0157] Optionally, such as Figure 4 As shown, in one embodiment of this disclosure, the evaluation data generation apparatus 400 further includes:

[0158] The elimination module 407 is used to eliminate the information of the specified traffic environment element if the verification fails.

[0159] The evaluation data generation device 400 in this embodiment achieves the same implementation principle and technical effect as the above-mentioned related method embodiments by using the above-mentioned modules to generate evaluation data. For details, please refer to the description of the above-mentioned related method embodiments, which will not be repeated here.

[0160] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0161] Figure 5 A schematic block diagram of an example electronic device 500 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.

[0162] like Figure 5 As shown, device 500 includes a computing unit 501, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 502 or a computer program loaded from storage unit 508 into random access memory (RAM) 503. RAM 503 may also store various programs and data required for the operation of device 500. The computing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. Input / output (I / O) interface 505 is also connected to bus 504.

[0163] Multiple components in device 500 are connected to I / O interface 505, including: input unit 506, such as keyboard, mouse, etc.; output unit 507, such as various types of monitors, speakers, etc.; storage unit 508, such as disk, optical disk, etc.; and communication unit 509, such as network card, modem, wireless transceiver, etc. Communication unit 509 allows device 500 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0164] The computing unit 501 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 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 501 performs the various methods and processes described above, such as the methods of this disclosure. For example, in some embodiments, the methods of this disclosure may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on device 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by the computing unit 501, one or more steps of the methods of this disclosure described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the methods of this disclosure by any other suitable means (e.g., by means of firmware).

[0165] 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), complex 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.

[0166] 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.

[0167] 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.

[0168] 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).

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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 generating evaluation data, comprising: Based on the first and second high-precision maps, obtain change information of specified traffic environment elements; The second high-precision map was updated more recently than the first high-precision map. Based on the change information of the specified traffic environment elements, obtain the sensor data collected by the vehicle based on the environment of the second high-precision map; Evaluation data is generated based on the sensor data, the identification information of the first high-precision map, and the change information of the specified traffic environment elements; The change information of the specified traffic environment element includes the changed location of the specified traffic environment element. Based on the change information of the specified traffic environment element, sensor data collected by the data collection vehicle based on the environment of the second high-precision map is obtained, including: When the location of the specified traffic environment element changes, the intrinsic and extrinsic parameters of the camera of the collection vehicle are obtained, the video data collected by the camera in the target time period when the collection vehicle collects data based on the environment of the second high-precision map, and the pose information of the positioning system of the collection vehicle in the target time period are obtained. The target time period can identify the process from when the data collection vehicle collects the changed location of the specified traffic environment element to when it travels to the changed location of the specified traffic environment element or the stop line before the changed location.

2. The method according to claim 1, wherein, Based on the first and second high-definition maps, obtain change information for specified traffic environment elements, including: Load the attribute information of traffic environment elements from the first high-precision map and the second high-precision map; By comparing the attribute information of traffic environment elements in the same location area in the first high-precision map and the second high-precision map, change information of the specified traffic environment element is obtained.

3. The method according to claim 2, wherein, By comparing the attribute information of traffic environment elements in the same location area in the first high-precision map and the second high-precision map, change information of the specified traffic environment element is obtained, including: Based on the attribute information of the first traffic environment element, detect and determine that the same location area in the first high-precision map includes a second traffic environment element corresponding to the first traffic environment element in the second high-precision map. Based on the attribute information of the first traffic environment element, obtain the attribute information of the second traffic environment element corresponding to the first traffic environment element from the same location area in the first high-precision map. Based on the attribute information of the first traffic environment element and the attribute information of the second traffic environment element, the first traffic environment element is determined as the change information of the specified traffic environment element. The change information of the specified traffic environment element is used to identify the change information that describes the specified traffic environment element in the second high-precision map relative to the first high-precision map.

4. The method according to claim 2, wherein, The method further includes: Based on the attribute information of the first traffic environment element, it is detected and determined that the same location area in the first high-precision map does not contain a second traffic environment element corresponding to the first traffic environment element in the second high-precision map. Based on the attribute information of the first traffic environment element in the second high-precision map, the first traffic environment element is determined as the change information of the specified traffic environment element. The change information of the specified traffic environment element is used to identify the change information that describes the specified traffic environment element in the second high-precision map relative to the first high-precision map.

5. The method according to claim 2, wherein, The method further includes: Obtain the attribute information of the third traffic environment element from the first high-precision map; wherein, in the second high-precision map, there is no traffic environment element corresponding to the third traffic environment element in the same location area as the third traffic environment element; Based on the attribute information of the third traffic environment element, the third traffic environment element is determined as the change information of the designated traffic environment element. The change information of the designated traffic environment element is used to identify the change information that describes the designated traffic environment element relative to the first high-precision map and in the second high-precision map.

6. The method according to any one of claims 1-5, wherein, The changed location of the specified traffic environment element includes the location of the specified traffic environment element before and / or after the change, or the location of the specified traffic environment element where other parameter attribute information besides location has changed.

7. The method according to claim 1, wherein, Based on the changed location of the specified traffic environment elements, before acquiring the intrinsic and extrinsic parameters of the camera of the data collection vehicle, the video data collected by the camera during the target time period when the data collection vehicle is collecting data based on the environment of the second high-precision map, and the pose information of the positioning system of the data collection vehicle during the target time period, the method further includes: Based on the changed location of the specified traffic environment element, the driving trajectory of the data collection vehicle based on the environment of the second high-precision map, and the video data collected by the data collection vehicle, the first time point before the data collection vehicle travels to the changed location of the specified traffic environment element and the first time the camera collects the changed location of the specified traffic environment element is obtained. Based on the changed location of the specified traffic environment element and the driving trajectory of the data collection vehicle, obtain the second time point corresponding to when the data collection vehicle drives to the changed location of the specified traffic environment element or the stop line before the changed location; The target time period is determined based on the first time point and the second time point.

8. The method according to claim 1, wherein, The change information of the specified traffic environment element also includes the content of the change of the specified traffic environment element; Based on the sensor data, the identification information of the first high-precision map, and the change information of the specified traffic environment elements, evaluation data is generated, including: The intrinsic and extrinsic parameters of the camera of the acquisition vehicle, the video data of the target time period acquired by the camera, the pose information of the positioning system of the acquisition vehicle in the target time period, and the identification information of the first high-precision map are used as the input data for the evaluation data. The changes to the specified traffic environment elements are used as the annotation data for the evaluation data.

9. The method according to claim 1, wherein, Before generating evaluation data based on the sensor data, the identification information of the first high-precision map, and the change information of the specified traffic environment elements, the method further includes: Based on the target time period and the sensor data of the collected vehicles, the change information of the specified traffic environment elements is verified; And the verification was confirmed to be successful.

10. The method according to claim 9, wherein, Based on the target time period and the sensor data of the collected vehicles, the change information of the specified traffic environment elements is verified, including: Based on the intrinsic and extrinsic parameters of the camera of the data acquisition vehicle and the pose information of the positioning system of the data acquisition vehicle at each time point in the target time period, the changed positions of the specified traffic environment elements are projected onto the camera coordinate system of the data acquisition vehicle at each time point; if the proportion of successful projection within the target time period reaches a preset proportion threshold, the verification is confirmed to be successful; or If the sensor data of the acquisition vehicle also includes obstacle information around the acquisition vehicle, the obstacle information around the acquisition vehicle at each time point in the target time period is obtained from the sensor data, the obstacle information at each time point is projected onto the camera coordinate system of the acquisition vehicle, and it is detected whether the obstacle information at each time point occludes the specified traffic environment element; if the proportion of unoccluded elements in the target time period is lower than a preset proportion threshold, the verification is determined to be successful.

11. An apparatus for generating evaluation data, comprising: The change information acquisition module is used to acquire change information of specified traffic environment elements based on the first high-precision map and the second high-precision map; The second high-precision map was updated more recently than the first high-precision map. The sensor data acquisition module is used to acquire sensor data collected by the vehicle based on the environment of the second high-precision map, based on the change information of the specified traffic environment elements. The generation module is used to generate evaluation data based on the sensor data, the identification information of the first high-precision map, and the change information of the specified traffic environment elements; When the change information of the specified traffic environment element includes the change location of the specified traffic environment element, the sensor data acquisition module is used to acquire, based on the change location of the specified traffic environment element, the intrinsic and extrinsic parameters of the camera of the acquisition vehicle, the video data acquired by the camera in the target time period when the acquisition vehicle is collecting data based on the environment of the second high-precision map, and the pose information of the positioning system of the acquisition vehicle in the target time period. The target time period can identify the process from when the data collection vehicle collects the changed location of the specified traffic environment element to when it travels to the changed location of the specified traffic environment element or the stop line before the changed location.

12. The apparatus according to claim 11, wherein, The change information acquisition module is used for: Load the attribute information of traffic environment elements from the first high-precision map and the second high-precision map; By comparing the attribute information of traffic environment elements in the same location area in the first high-precision map and the second high-precision map, change information of the specified traffic environment element is obtained.

13. The apparatus according to claim 12, wherein, The change information acquisition module is used for: Based on the attribute information of the first traffic environment element, detect and determine that the same location area in the first high-precision map includes a second traffic environment element corresponding to the first traffic environment element in the second high-precision map. Based on the attribute information of the first traffic environment element, obtain the attribute information of the second traffic environment element corresponding to the first traffic environment element from the same location area in the first high-precision map. Based on the attribute information of the first traffic environment element and the attribute information of the second traffic environment element, the first traffic environment element is determined as the change information of the specified traffic environment element. The change information of the specified traffic environment element is used to identify the change information that describes the specified traffic environment element in the second high-precision map relative to the first high-precision map.

14. The apparatus according to claim 12, wherein, The change information acquisition module is also used for: Based on the attribute information of the first traffic environment element, it is detected and determined that the same location area in the first high-precision map does not contain a second traffic environment element corresponding to the first traffic environment element in the second high-precision map. Based on the attribute information of the first traffic environment element in the second high-precision map, the first traffic environment element is determined as the change information of the specified traffic environment element. The change information of the specified traffic environment element is used to identify the change information that describes the specified traffic environment element in the second high-precision map relative to the first high-precision map.

15. The apparatus according to claim 12, wherein, The change information acquisition module is also used for: Obtain the attribute information of the third traffic environment element from the first high-precision map; wherein, in the second high-precision map, there is no traffic environment element corresponding to the third traffic environment element in the same location area as the third traffic environment element; Based on the attribute information of the third traffic environment element, the third traffic environment element is determined as the change information of the designated traffic environment element. The change information of the designated traffic environment element is used to identify the change information that describes the designated traffic environment element relative to the first high-precision map and in the second high-precision map.

16. The apparatus according to any one of claims 11-15, wherein, The changed location of the specified traffic environment element includes the location of the specified traffic environment element before and / or after the change, or the location of the specified traffic environment element where other parameter attribute information besides location has changed.

17. The apparatus according to claim 11, wherein, The device further includes: a time period determination module, used for: Based on the changed location of the specified traffic environment element, the driving trajectory of the data collection vehicle based on the environment of the second high-precision map, and the video data collected by the data collection vehicle, the first time point before the data collection vehicle travels to the changed location of the specified traffic environment element and the first time the camera collects the changed location of the specified traffic environment element is obtained. Based on the changed location of the specified traffic environment element and the driving trajectory of the data collection vehicle, obtain the second time point corresponding to when the data collection vehicle drives to the changed location of the specified traffic environment element or the stop line before the changed location; The target time period is determined based on the first time point and the second time point.

18. The apparatus according to claim 11, wherein, The generation module is used for: The intrinsic and extrinsic parameters of the camera of the acquisition vehicle, the video data of the target time period acquired by the camera, the pose information of the positioning system of the acquisition vehicle in the target time period, and the identification information of the first high-precision map are used as the input data for the evaluation data. The changes to the specified traffic environment elements are used as the annotation data for the evaluation data.

19. The apparatus according to claim 11, wherein, The device further includes: The verification module is used to verify the change information of the specified traffic environment elements based on the target time period and the sensor data of the collected vehicles. The module is identified and used to verify that the validation has passed.

20. The apparatus according to claim 19, wherein, The verification module is used for: Based on the intrinsic and extrinsic parameters of the camera of the data acquisition vehicle and the pose information of the positioning system of the data acquisition vehicle at each time point in the target time period, the changed positions of the specified traffic environment elements are projected onto the camera coordinate system of the data acquisition vehicle at each time point; if the proportion of successful projection within the target time period reaches a preset proportion threshold, the verification is confirmed to be successful; or If the sensor data of the acquisition vehicle also includes obstacle information around the acquisition vehicle, the obstacle information around the acquisition vehicle at each time point in the target time period is obtained from the sensor data, the obstacle information at each time point is projected into the camera coordinate system of the acquisition vehicle, and it is detected whether the obstacle information at each time point occludes the specified traffic environment element. If the proportion of unobstructed areas within the target time period is lower than a preset threshold, the verification is considered successful.

21. 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 executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the method of any one of claims 1-10.

22. 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 1-10.

23. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-10.

Images