WO2022205642A1 - 一种道路数据处理的方法、装置、电子设备、介质和程序 - Google Patents

一种道路数据处理的方法、装置、电子设备、介质和程序 Download PDF

Info

Publication number
WO2022205642A1
WO2022205642A1 PCT/CN2021/103072 CN2021103072W WO2022205642A1 WO 2022205642 A1 WO2022205642 A1 WO 2022205642A1 CN 2021103072 W CN2021103072 W CN 2021103072W WO 2022205642 A1 WO2022205642 A1 WO 2022205642A1
Authority
WO
WIPO (PCT)
Prior art keywords
route
trajectory
vehicle
route segment
data
Prior art date
Application number
PCT/CN2021/103072
Other languages
English (en)
French (fr)
Inventor
林逸群
王哲
石建萍
Original Assignee
上海商汤智能科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 上海商汤智能科技有限公司 filed Critical 上海商汤智能科技有限公司
Publication of WO2022205642A1 publication Critical patent/WO2022205642A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29Geographical information databases
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/21Design, administration or maintenance of databases
    • G06F16/215Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/23Updating
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10Services
    • G06Q50/26Government or public services
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40Business processes related to the transportation industry

Definitions

  • the present disclosure relates to the technical field of automatic driving, and relates to, but is not limited to, a road data processing method, apparatus, electronic device, computer-readable storage medium and computer program product.
  • vehicle data may be collected by a device (such as a radar detector) mounted on the collection vehicle.
  • a device such as a radar detector
  • multiple collection vehicles can also be used to collect more road data to completely cover the planned route.
  • the embodiments of the present disclosure provide at least a method, apparatus, electronic device, computer-readable storage medium, and computer program product for processing road data, determining whether to update the trajectory route set and corresponding road data based on the current trajectory route through positioning data.
  • the redundancy is low and easy to store.
  • Embodiments of the present disclosure provide a method for processing road data, the method comprising:
  • a route segment in the current trajectory route that does not overlap with the route segments in the trajectory route set is used as a target route segment;
  • the target route segment is merged into the trajectory route set, and the road data corresponding to the target route segment is merged into the road data corresponding to the trajectory route set.
  • the above road data processing method when the positioning data of the current vehicle in the process of collecting road data is obtained, the current trajectory route passed by the vehicle in the process of collecting road data can be determined, and then the current trajectory route can be determined from the current trajectory route.
  • the route segments in the route set are not repeated, and are merged into the track route set as the target route segment and merge the road data.
  • the above-mentioned road data processing method can update the trajectory route set based on the positioning data in the road data collection process.
  • the route segment that does not overlap with the trajectory route set is updated.
  • the road data is screened to achieve the purpose of deduplication of the road data.
  • the subsequent data storage space is saved, and it is also convenient to guide the subsequent route collection work.
  • the positioning data includes position information of a plurality of vehicle trajectory points; the target route segment is determined according to the following steps:
  • the trajectory route is obtained from the trajectory route. Find the target vehicle trajectory point closest to the route segment in the collection;
  • the route segment is determined to be the target route segment.
  • the embodiment of the present disclosure provides a solution for determining whether the route segment appears in the track route set based on the distance limitation method for each route segment, and the solution can be used when a route segment does not appear in the track In the case of a set of routes, the subsequent route merge operation is performed.
  • the position information of the vehicle trajectory point includes a lateral coordinate value and a longitudinal coordinate value; the distance between the target vehicle trajectory point and the route segment is determined according to the following steps:
  • the distance between the target vehicle trajectory point and the route segment is determined.
  • the positioning data further includes a collection timestamp corresponding to each location information; the determining, based on the obtained positioning data, a current trajectory route passed by the current vehicle in the process of collecting road data includes:
  • each vehicle trajectory point set For each vehicle trajectory point set, connect each vehicle trajectory point included in the vehicle trajectory point set to generate a route segment that constitutes the current trajectory route;
  • the current trajectory route is obtained by combining a route segment that is generated for each of the vehicle trajectory point sets and composing the current trajectory route.
  • the trajectory route can be a time-continuous trajectory route. Therefore, firstly, multiple vehicle trajectory points can be sorted according to the collection timestamp, and then the point set can be divided based on the sorted multiple vehicle trajectory points to determine each of the current trajectory routes. route segments, so as to obtain the current trajectory route, which is continuous in time, thereby facilitating the comparison of subsequent route segments.
  • the determining, based on the acquired positioning data, the current trajectory route passed by the current vehicle in the process of collecting road data includes:
  • the current trajectory route passed by the current vehicle in the process of collecting road data is determined.
  • the amount of positioning data actually collected by the current vehicle is huge, if it is directly applied to the construction of the current trajectory route, it will take up a large amount of calculation to a certain extent. In actual scenarios, especially for some To smooth the driving trajectory, fewer vehicle trajectory points can be used to represent the current trajectory route. Therefore, before determining the current trajectory route in the embodiment of the present disclosure, the obtained positioning data can be down-sampled to ensure the integrity of the trajectory route. At the same time, the amount of subsequent data calculation is reduced.
  • performing down-sampling processing on the acquired positioning data to obtain processed positioning data including:
  • the filtered data corresponding to the plurality of vehicle track points is used as the processed positioning data.
  • performing down-sampling processing on the acquired positioning data to obtain processed positioning data including:
  • the local downsampling operation of the positioning data can be implemented based on the determination of the direction vector, and the last vehicle trajectory point in the two route segments with the smaller angle corresponding to the direction vector is deleted, that is, the last vehicle trajectory point is It is considered that the redundant trajectory points among the three continuously collected vehicle trajectory points will not affect the integrity of the entire trajectory route after deletion, and the subsequent calculation amount can also be reduced.
  • the method further includes:
  • the polyline display information corresponding to each route segment is correspondingly displayed in the map of the current vehicle.
  • polyline display information corresponding to each route segment included in the trajectory route may be generated, so as to display the vehicle map. Based on the displayed map information, data collectors can be reminded to avoid road sections where road data collection has been completed, thereby improving the efficiency of the entire data collection process.
  • the road data includes at least one of the following data:
  • Image data collected by the image sensor on the current vehicle is
  • Embodiments of the present disclosure also provide an apparatus for processing road data, the apparatus comprising:
  • an acquisition module configured to acquire the positioning data of the current vehicle in the process of collecting road data
  • a determination module configured to determine the current trajectory route passed by the current vehicle in the process of collecting road data based on the acquired positioning data
  • a screening module configured to, based on the current trajectory route and the trajectory route set, use a route segment in the current trajectory route that does not overlap with the route segment in the trajectory route set as a target route segment;
  • the merging module is configured to merge the target route segment into the trajectory route set, and merge the road data corresponding to the target route segment into the road data corresponding to the trajectory route set.
  • Embodiments of the present disclosure further provide an electronic device, including: a processor, a memory, and a bus, where the memory stores machine-readable instructions executable by the processor, and when the electronic device runs, the processor and the The memory communicates through a bus, and when the machine-readable instruction is executed by the processor, the method described in any one of the embodiments of the present disclosure is executed.
  • An embodiment of the present disclosure further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium.
  • a computer program is stored on the computer-readable storage medium.
  • the electronic device executes any one of the embodiments of the present disclosure. the method described.
  • An embodiment of the present disclosure further provides a computer program product, where the computer program product carries a program code, and the instructions included in the program code can be used to execute the method described in any one of the embodiments of the present disclosure.
  • FIG. 1 is a flowchart of a method for processing road data provided by an embodiment of the present disclosure
  • FIG. 2 is a schematic diagram of an apparatus for processing road data provided by an embodiment of the present disclosure
  • FIG. 3 is a schematic diagram of an electronic device provided by an embodiment of the present disclosure.
  • the present disclosure provides a method, device, electronic device, computer-readable storage medium and computer program product for processing road data, determining whether to update the trajectory route set and corresponding road data based on the current trajectory route through positioning data,
  • the road data thus obtained has low redundancy and is easy to store.
  • Equipment the electronic equipment for example includes: terminal equipment or server or other processing equipment, the terminal equipment can be user equipment (User Equipment, UE), mobile equipment, user terminal, terminal, cellular phone, cordless phone, Personal Digital Processing (Personal Digital Assistant, PDA), handheld devices, computing devices, in-vehicle devices, wearable devices, etc.
  • the method for processing road data may be implemented by the processor calling computer-readable instructions stored in the memory.
  • the following describes the road data processing method provided by the embodiment of the present disclosure by taking the execution subject as the server as an example.
  • FIG. 1 is a flowchart of a method for processing road data provided by an embodiment of the present disclosure, the method includes steps S101 to S104, wherein:
  • Step S101 obtaining the positioning data of the current vehicle in the process of collecting road data
  • Step S102 based on the obtained positioning data, determine the current trajectory route passed by the current vehicle in the process of collecting road data;
  • Step S103 based on the current trajectory route and the trajectory route set, use the route segment in the current trajectory route that does not overlap with the route segment in the trajectory route set as the target route segment;
  • Step S104 merging the target route segment into the trajectory route set, and merging the road data corresponding to the target route segment into the road data corresponding to the trajectory route set.
  • the above-mentioned road data processing method can be mainly applied to the field of automatic driving technology. To operate a motor vehicle safely, it is necessary to detect the road data around the vehicle in advance for subsequent applications. For example, it can be used for training and tuning of target object recognition models, and can also be used for map creation.
  • the embodiments of the present disclosure can also be applied to any application scenario that requires road data collection, and no specific limitation is made here.
  • the embodiments of the present disclosure provide a road data processing method for eliminating road data redundancy by using positioning data. Subsequent applications.
  • the positioning data obtained in the embodiments of the present disclosure may be collected by a positioning device mounted on a vehicle, and the positioning device may be positioning based on a global positioning system (Global Positioning System, GPS), or may be based on Galileo satellite navigation System (Galileo Satellite Navigation System, GSNS), global satellite navigation system (GLOBAL NAVIGATION SATELLITE SYSTEM, GNSS) and other systems to achieve positioning, can also be based on other positioning technology positioning, no specific restrictions are made here.
  • GPS Global Positioning System
  • Galileo Satellite Navigation System Galileo Satellite Navigation System
  • GLOBAL NAVIGATION SATELLITE SYSTEM global satellite navigation system
  • GNSS global satellite navigation system
  • the road data processing method provided by the embodiments of the present disclosure may also collect road data based on a road data detection device mounted on a vehicle, where the road data detection device may be a radar device, which is used to detect point cloud data related to the road, It may also be an image sensor, which is used to detect image data related to the road.
  • the road data detection device may be a radar device, which is used to detect point cloud data related to the road, It may also be an image sensor, which is used to detect image data related to the road.
  • other detection devices may also be selected based on actual application requirements in this embodiment of the present disclosure, which is not specifically limited here.
  • the positioning data in the embodiment of the present disclosure may be acquired during the process of collecting road data, so that there is a certain dependency between the road data and the positioning data. Identify the road data collected at that particular location.
  • the embodiments of the present disclosure provide a solution for deduplicating road data based on positioning data by using the dependency between the above two pieces of data.
  • the current trajectory route passed by the vehicle in the process of road data collection can be determined, and the current trajectory route can be compared with the trajectory route set to determine whether there is duplication between the routes.
  • the repeated route segment can be used as the target route segment to realize the update of the trajectory route set and the update of the corresponding road data.
  • route merging can be performed. Since there is no duplication in the entire trajectory route, the redundancy of the determined road data is low.
  • the set of trajectory routes here may be the set of trajectory routes corresponding to the road data collected by the vehicle (such as the current vehicle and/or other vehicles), for example, it may be the original trajectory route, or it may be the original trajectory route
  • the trajectory route obtained after deduplication, here, can be used as a trajectory route set before the update.
  • the current track and route set can be updated based on the current track route determined by the obtained positioning data, and the next update can be performed on the basis of the current update. , until the requirements for road data collection in the application scenario are met, for example, all urban roads in a collection area are traversed.
  • the road data processing method provided by the embodiment of the present disclosure can also visually display the merged track and route set, and based on the visual result, it is possible to avoid data collectors going to the collected road sections to collect road data again, further reducing route repetition. It is convenient for subsequent collection route design.
  • polyline display information corresponding to each route segment may be generated based on each route segment included in the merged trajectory route set, and then the polyline display information corresponding to each route segment is correspondingly displayed on the map of the current vehicle.
  • the broken line display information corresponding to the route segment may be generated based on the connection between the vehicle track points included in the route segment, so that the map display effect is more intuitive.
  • the current trajectory route may be divided into smaller granularity, which may be divided into multiple route segments.
  • each route segment of the current trajectory route appears in the trajectory route set, if not, this route segment can be merged into the trajectory route set as a target route segment , so that the updated trajectory route set can be obtained. If it appears, the road data collected corresponding to this route segment can be deleted. At the same time, the road data collected corresponding to the target route segment can also be merged into the road corresponding to the trajectory route set. In the data, there is no duplication of road data collected in this way.
  • the determination process of the target route segment plays a key role in the determination of the subsequent trajectory route set and the corresponding road data, the following steps can be used to specifically describe the determination process of the target route segment:
  • Step 1 For each route segment included in the current track route, based on the position information of the multiple vehicle track points included in the route segment and the position information of each vehicle track point included in the track route set, search from the track route set. The target vehicle trajectory point closest to the route segment;
  • Step 2 judging whether the distance between the target vehicle trajectory point and the route segment is greater than the preset distance
  • Step 3 If yes, determine the route segment as the target route segment.
  • the method for processing road data may firstly be based on the location information of multiple vehicle trajectory points included in the route segment and the location of each vehicle trajectory point included in the trajectory route set The relative position relationship between the information, find the target vehicle trajectory point closest to this route segment from the trajectory route set. Then, it can be judged whether the distance between the target vehicle trajectory point and the route segment is greater than the preset distance. This is mainly considering that when the target vehicle trajectory point is closer to the route segment, it will explain to a certain extent this in the current trajectory route. The route segment and the trajectory route set corresponding to the target vehicle trajectory point are more likely to be repeated.
  • this route in the current trajectory route is explained to a certain extent.
  • the segment and the trajectory route set corresponding to the target vehicle trajectory point are less likely to overlap. Therefore, here, it can be determined whether this route segment does not overlap the target route segment with the trajectory route set based on the distance judgment result.
  • a preset distance of an appropriate size can be selected based on the needs of the actual application scenario. For example, it can be determined based on the positioning accuracy of the positioning device. When the positioning accuracy is relatively high, a smaller preset distance can be selected, and when the positioning accuracy is relatively low, a larger preset distance can be selected.
  • the route segments in the route S that are repeated with the route database R can be filtered out, and then the route S The route segments that do not overlap with the route database R are inserted into the route database R.
  • the route S is composed of a plurality of consecutive route segments: route segment AB, route segment BC, route segment CD, route segment DE, ...;
  • route segment For each route segment to be inserted into the route S, it is judged whether the route segment is duplicated with the route database R, and if it is duplicated, it is filtered out; otherwise, it is inserted into the route database R.
  • a point P that is, the target vehicle trajectory point
  • the road data processing method provided by the embodiment of the present disclosure may determine the distance between the target vehicle trajectory point and the route segment according to the distance formula, and may include the following steps:
  • Step 1 Determine the line equation corresponding to the route segment based on the horizontal coordinate value and the longitudinal coordinate value of each vehicle trajectory point in any two vehicle trajectory points included in the route segment;
  • Step 2 Determine the distance between the target vehicle trajectory point and the route segment based on the horizontal coordinate value and the vertical coordinate value of the target vehicle trajectory point and the determined straight line equation.
  • the straight line equation corresponding to the route segment can be determined, that is, the two-point coordinate value can be used to determine The straight line equation of the straight line formed by the two points, in this way, the distance between the target vehicle trajectory point and the route segment can be determined based on the distance formula from the point to the straight line.
  • the current trajectory route in the embodiment of the present disclosure may be obtained based on the connection of each vehicle trajectory point arranged in chronological order.
  • each route segment that constitutes the current trajectory route can be determined first, and then the current trajectory route can be determined based on the combination of each route segment, which can be implemented according to the following steps:
  • Step 1 Sort the multiple vehicle trajectory points in the ascending order of the collection timestamps
  • Step 2 Divide the multiple vehicle track points into multiple vehicle track point sets according to the preset route segment length
  • Step 3 For each vehicle trajectory point set, connect each vehicle trajectory point included in the vehicle trajectory point set to generate a route segment forming the current trajectory route;
  • Step 4 Combine a route segment that forms the current trajectory route generated for each vehicle trajectory point set to obtain the current trajectory route.
  • each vehicle trajectory point is first sorted according to the collection timestamp of each vehicle trajectory point, and each vehicle trajectory point after sorting has continuity in time.
  • the trajectory points are divided into multiple vehicle trajectory point sets, each vehicle trajectory point set can correspond to a route segment, and the current trajectory route can be determined by combining each route segment.
  • the length of the preset route segment may be determined based on related parameters such as the collection frequency of the positioning device.
  • the collection frequency is high, the vehicle trajectory points obtained per unit time are also denser.
  • the length of the preset route segment can be set to be smaller at this time.
  • the vehicle trajectory points obtained per unit time are also sparser, and in this case, the length of the preset route segment can be set to be larger.
  • the present disclosure implements the For example, a downsampling processing method can be provided to first downsample the positioning data, and then determine the current trajectory route based on the sampled positioning data, thereby reducing the amount of subsequent calculation while ensuring the integrity of the trajectory.
  • the two down-sampling processing methods provided by the embodiments of the present disclosure can be respectively described in the following two aspects.
  • Aspect 1 The implementation of the present disclosure may implement downsampling based on trajectory point screening, and may include the following steps:
  • Step 1 Screening out a plurality of vehicle trajectory points that meet the preset downsampling ratio from the plurality of vehicle trajectory points included in the obtained positioning data;
  • Step 2 Use the data corresponding to the selected multiple vehicle track points as the processed positioning data.
  • multiple vehicle trajectory points can be screened based on a preset downsampling ratio. For example, a single batch of positioning data has N vehicle trajectory points. Given a downsampling ratio p (such as 30%), Np points can be randomly selected. , it can also be traversed and screened based on the distribution of vehicle trajectory points.
  • p such as 30%
  • the implementation of the present disclosure may implement downsampling based on the direction vector, which may include the following steps:
  • Step 1 Determine two adjacent route segments for any three consecutively collected vehicle trajectory points included in the obtained positioning data, and determine the direction vector corresponding to each route segment in the two adjacent route segments. ;
  • Step 2 Determine whether the included angle between the direction vectors corresponding to two adjacent route segments is less than a preset angle
  • Step 3 If yes, delete the last vehicle track point in any three continuously collected vehicle track points, and determine the data corresponding to the remaining vehicle track points as the processed positioning data.
  • the embodiment of the present disclosure provides a three- The direction vector between two adjacent route segments formed by two consecutive vehicle trajectory points realizes the down-sampling scheme.
  • the angle between the direction vectors corresponding to two adjacent route segments is smaller, it means that the three consecutive vehicle trajectory points are more likely to be located on a straight line.
  • the vehicle trajectory points are deleted; in the case where the included angle between the direction vectors corresponding to two adjacent route segments is larger, it means that three consecutive vehicle trajectory points are less likely to be located on a straight line, and the first The three vehicle trajectory points are more likely to be turned, and at this time, the third vehicle trajectory point can be reserved.
  • the continuous vehicle trajectory points are recorded as point A1, point B1, point C1, and point D1.
  • the direction vector corresponding to the two line segments of line segment A1B1 and line segment B1C1 can be calculated, and then the clip between the direction vectors of line segment A1B1 and line segment B1C1 can be calculated.
  • Angle size if the included angle is smaller than the preset angle ⁇ (such as 90°), discard point C1, and continue to calculate the angle between line segment A1B1 and line segment C1D1; if it is greater than the preset angle ⁇ , keep point C1, and continue to calculate line segment B1C1 and line segment C1D1.
  • the included angle of the line segment C1D1 further determines whether to retain the point D1, and so on, until the processed positioning data is obtained.
  • the target object detection model trained by the above road data can avoid overfitting the trained target object detection model to the training data as much as possible due to the low redundancy of the road data.
  • the training efficiency can be improved on the premise of ensuring the training effect of the target object detection model.
  • the cost of labeling is also greatly reduced.
  • the writing order of each step does not mean a strict execution order but constitutes any limitation on the implementation process, and the specific execution order of each step should be based on its function and possible Internal logic is determined.
  • an apparatus for processing road data corresponding to the method for processing road data is also provided in the embodiments of the present disclosure, because the principle of the apparatus in the embodiments of the present disclosure for solving problems is the same as the above-mentioned method for processing road data in the embodiments of the present disclosure Similar, therefore, the implementation of the apparatus may refer to the implementation of the method, and repeated descriptions will not be repeated.
  • the apparatus includes: an acquisition module 201, a determination module 202, a screening module 203, and a merging module 204; wherein,
  • the obtaining module 201 is configured to obtain the positioning data of the current vehicle in the process of collecting road data
  • the determining module 202 is configured to, based on the acquired positioning data, determine the current trajectory route passed by the current vehicle in the process of collecting the road data;
  • the screening module 203 is configured to, based on the current trajectory route and the trajectory route set, use the route segment in the current trajectory route that does not overlap with the route segment in the trajectory route set as the target route segment;
  • the merging module 204 is configured to merge the target route segment into the trajectory route set, and merge the road data corresponding to the target route segment into the road data corresponding to the trajectory route set.
  • the current trajectory route passed by the vehicle in the process of collecting road data can be determined, and then the current trajectory route can be determined from the current trajectory route and the trajectory route set.
  • the route segment of the route segment is not repeated, and it is merged into the track route set as the target route segment and the road data is merged.
  • the above-mentioned road data processing method can update the trajectory route set based on the positioning data in the road data collection process, and what is updated here is the route segment that does not overlap with the trajectory route set, so that a large batch of data can be quickly updated.
  • the road data is screened to achieve the purpose of deduplication of the road data. On the premise of ensuring the integrity of the road data, the subsequent data storage space is saved, and it is also convenient to guide the subsequent route collection work.
  • the positioning data includes position information of multiple vehicle trajectory points; the screening module 203 is configured to determine the target route segment according to the following steps:
  • the position information of the vehicle trajectory point includes a horizontal coordinate value and a vertical coordinate value; the screening module 203 is configured to determine the distance between the target vehicle trajectory point and the route segment according to the following steps:
  • the distance between the target vehicle trajectory point and the route segment is determined.
  • the positioning data further includes a collection time stamp corresponding to each position information; the determining module 202 is configured to determine the current trajectory route passed by the current vehicle in the process of collecting road data based on the obtained positioning data according to the following steps :
  • each vehicle trajectory point set For each vehicle trajectory point set, connect each vehicle trajectory point included in the vehicle trajectory point set to generate a route segment that constitutes the current trajectory route;
  • a route segment that forms the current trajectory route generated for each vehicle trajectory point set is combined to obtain the current trajectory route.
  • the determining module 202 is configured to determine the current trajectory route passed by the current vehicle in the process of collecting road data based on the acquired positioning data according to the following steps:
  • the current trajectory route passed by the current vehicle in the process of collecting road data is determined.
  • the determining module 202 is configured to perform down-sampling processing on the acquired positioning data according to the following steps to obtain processed positioning data:
  • the data corresponding to the selected multiple vehicle track points are used as the processed positioning data.
  • the determining module 202 is configured to perform down-sampling processing on the acquired positioning data according to the following steps to obtain processed positioning data:
  • the above-mentioned apparatus further comprises:
  • the display module 205 is configured to, after merging the target route segment into the trajectory route set, generate polyline display information corresponding to each route segment based on each route segment included in the merged trajectory route set; The polyline display information is correspondingly displayed on the map of the current vehicle.
  • the road data includes at least one of the following data:
  • Image data collected by the image sensor on the current vehicle is
  • FIG. 3 a schematic structural diagram of the electronic device provided by the embodiment of the present disclosure includes: a processor 301 , a memory 302 , and a bus 303 .
  • the memory 302 stores machine-readable instructions executable by the processor 301 (for example, the execution instructions corresponding to the obtaining module 201, the determining module 202, the screening module 203, the merging module 204 in the apparatus in FIG. 2, etc.), when the electronic device is running , the processor 301 communicates with the memory 302 through the bus 303, and the machine-readable instruction is executed by the processor 301 to perform the following processing:
  • a route segment in the current trajectory route that does not overlap with the route segments in the trajectory route set is used as the target route segment;
  • the target route segment is merged into the trajectory route set, and the road data corresponding to the target route segment is merged into the road data corresponding to the trajectory route set.
  • the positioning data includes position information of multiple vehicle trajectory points; in the instructions executed by the processor 301, the target route segment is determined according to the following steps:
  • the position information of the vehicle trajectory point includes a horizontal coordinate value and a vertical coordinate value; in the instructions executed by the processor 301, the distance between the target vehicle trajectory point and the route segment is determined according to the following steps:
  • the distance between the target vehicle trajectory point and the route segment is determined.
  • the positioning data further includes a collection time stamp corresponding to each position information; in the instructions executed by the processor 301, based on the obtained positioning data, determine the current trajectory route passed by the current vehicle in the process of collecting road data ,include:
  • each vehicle trajectory point set For each vehicle trajectory point set, connect each vehicle trajectory point included in the vehicle trajectory point set to generate a route segment that constitutes the current trajectory route;
  • a route segment that forms the current trajectory route generated for each vehicle trajectory point set is combined to obtain the current trajectory route.
  • the current trajectory route passed by the current vehicle in the process of collecting road data is determined.
  • down-sampling processing is performed on the acquired positioning data to obtain the processed positioning data, including:
  • the data corresponding to the selected multiple vehicle track points are used as the processed positioning data.
  • down-sampling processing is performed on the acquired positioning data to obtain the processed positioning data, including:
  • the instructions executed by the processor 301 further include:
  • the polyline display information corresponding to each route segment is correspondingly displayed in the map of the current vehicle.
  • the road data includes at least one of the following data:
  • Image data collected by the image sensor on the current vehicle is
  • Embodiments of the present disclosure further provide a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is run by a processor, the method for processing road data described in the foregoing method embodiments is executed.
  • the storage medium may be a volatile or non-volatile computer-readable storage medium.
  • Embodiments of the present disclosure further provide a computer program product, where the computer program product carries program codes, and the instructions included in the program codes can be used to execute the road data processing methods described in the above method embodiments.
  • the computer program product carries program codes
  • the instructions included in the program codes can be used to execute the road data processing methods described in the above method embodiments.
  • please refer to the above The method embodiments are not repeated here.
  • the above-mentioned computer program product can be specifically implemented by means of hardware, software or a combination thereof.
  • the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK), etc. Wait.
  • the units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
  • each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.
  • the functions, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a processor-executable non-volatile computer-readable storage medium.
  • the computer software products are stored in a storage medium, including Several instructions are used to cause an electronic device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present disclosure.
  • the aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program codes .
  • the present disclosure relates to a method, device, electronic device, computer-readable storage medium and computer program product for processing road data, wherein the method includes: acquiring positioning data of a current vehicle in the process of collecting road data; data, determine the current trajectory route passed by the current vehicle in the process of collecting road data; based on the current trajectory route and the trajectory route set, take the route segment in the current trajectory route that does not overlap with the route segment in the trajectory route set as the target route segment; The target route segment is merged into the trajectory route set, and the road data corresponding to the target route segment is merged into the road data corresponding to the trajectory route set.
  • the present disclosure determines whether to update the trajectory route set and the corresponding road data based on the current trajectory route through the positioning data, and the road data has low redundancy and is easy to store.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Tourism & Hospitality (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • General Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • Primary Health Care (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • Quality & Reliability (AREA)
  • Remote Sensing (AREA)
  • Educational Administration (AREA)
  • Navigation (AREA)
  • Traffic Control Systems (AREA)

Abstract

本公开提供了一种道路数据处理的方法、装置、电子设备、计算机可读存储介质和计算机程序产品,其中,该方法包括:获取当前车辆在采集道路数据的过程中的定位数据;基于获取的定位数据,确定当前车辆采集道路数据的过程中经过的当前轨迹路线;基于当前轨迹路线以及轨迹路线集合,将当前轨迹路线中与轨迹路线集合中的路线段不重复的路线段作为目标路线段;将目标路线段合并到轨迹路线集合中,并将目标路线段对应的道路数据合并到轨迹路线集合对应的道路数据。本公开通过定位数据确定是否基于当前轨迹路线更新轨迹路线集合及对应的道路数据,道路数据的冗余度较低,便于存储。

Description

一种道路数据处理的方法、装置、电子设备、介质和程序
相关申请的交叉引用
本公开基于申请号为202110347032.9、申请日为2021年03月31日的中国专利申请提出,申请人为商汤集团有限公司,申请名称为“一种道路数据处理的方法、装置、电子设备及存储介质”的技术方案,并要求该中国专利申请的优先权,该中国专利申请的全部内容在此引入本公开作为参考。
技术领域
本公开涉及自动驾驶技术领域,涉及但不限于一种道路数据处理的方法、装置、电子设备、计算机可读存储介质和计算机程序产品。
背景技术
在自动驾驶技术领域中,往往需要采集大量的车辆数据用于后续应用,例如,可以用于模型的训练、调优等,还可以用于地图创建等。这里的车辆数据可以是采集车上搭载的设备(如雷达探测器)所采集的。为了能够采集到更为完整的道路信息,还可以采用多辆采集车,采集更多的道路数据,以完全覆盖计划路线。
不管是多辆采集车进行数据采集,还是单个采集车进行数据采集,针对同一道路往往存在一定程度上的数据冗余,这为数据存储带来了压力。
发明内容
本公开实施例至少提供一种道路数据处理的方法、装置、电子设备、计算机可读存储介质和计算机程序产品,通过定位数据确定是否基于当前轨迹路线更新轨迹路线集合及对应的道路数据,道路数据的冗余度较低,便于存储。
本公开实施例提供了一种道路数据处理的方法,所述方法包括:
获取当前车辆在采集道路数据的过程中的定位数据;
基于获取的所述定位数据,确定当前车辆采集道路数据的过程中经过的当前轨迹路线;
基于所述当前轨迹路线以及轨迹路线集合,将所述当前轨迹路线中与所述轨迹路线集合中的路线段不重复的路线段作为目标路线段;
将所述目标路线段合并到所述轨迹路线集合中,并将所述目标路线段对应的道路数据合并到所述轨迹路线集合对应的道路数据。
采用上述道路数据处理的方法,在获取到当前车辆在采集道路数据的过程中的定位数据的情况下,可以确定车辆在采集过程中经过的当前轨迹路线,进而可以从当前轨迹路线中确定与轨迹路线集合中的路线段不重复的路线段,并作为目标路线段合并到轨迹路线集合以及进行道路数据的合并。可知的是,上述道路数据处理的方法可以基于道路数据采集过程中的 定位数据对轨迹路线集合进行更新,这里更新的是没有与轨迹路线集合发生重复的路线段,进而可以快速的对大批量的道路数据进行筛选以达到道路数据去重的目的,在确保了道路数据完整性的前提下,节省了后续的数据存储空间,还能够便于指导后续的路线采集工作。
在一些实施例中,所述定位数据包括多个车辆轨迹点的位置信息;所述目标路线段按照以下步骤确定:
针对所述当前轨迹路线包含的每个路线段,基于该路线段所包括的多个车辆轨迹点的位置信息以及所述轨迹路线集合所包括的各个车辆轨迹点的位置信息,从所述轨迹路线集合中查找与该路线段距离最近的目标车辆轨迹点;
判断所述目标车辆轨迹点与所述路线段之间的距离是否大于预设距离;
若是,则确定所述路线段为所述目标路线段。
这里,考虑到当前轨迹路线与轨迹路线集合越是接近,一定程度上也说明当前车辆采集的道路数据存在重复的可能性越大,而两条路线越是远离,一定程度上则说明存在重复的可能性越小,因而,本公开实施例提供了一种针对每个路线段,基于距离限定方式来确定该路线段是否出现在轨迹路线集合的方案,该方案能够在一个路线段未出现在轨迹路线集合的情况下,执行后续的路线合并操作。
在一些实施例中,所述车辆轨迹点的位置信息包括横向坐标值和纵向坐标值;按照如下步骤确定所述目标车辆轨迹点与所述路线段之间的距离:
基于所述路线段所包括的任意两个车辆轨迹点中每个车辆轨迹点的横向坐标值和纵向坐标值,确定该路线段所对应的直线方程;
基于所述目标车辆轨迹点的横向坐标值和纵向坐标值、以及确定的所述直线方程,确定所述目标车辆轨迹点与所述路线段之间的距离。
在一些实施例中,所述定位数据还包括与每个位置信息对应的采集时间戳;所述基于获取的所述定位数据,确定当前车辆采集道路数据的过程中经过的当前轨迹路线,包括:
按照采集时间戳由小到大的顺序对所述多个车辆轨迹点进行排序;
按照预设路线段长度将所述多个车辆轨迹点划分为多个车辆轨迹点集;
针对每个所述车辆轨迹点集,将该车辆轨迹点集包括的各个车辆轨迹点进行连线,生成组成所述当前轨迹路线的一个路线段;
将针对每个所述车辆轨迹点集生成的组成所述当前轨迹路线的一个路线段进行组合,得到所述当前轨迹路线。
这里,考虑到在实际的定位数据采集过程中,可能会受到数据传输速度等因素的影响,而导致实际采集的各个车辆轨迹点在时间上并非连续的,又考虑到本公开实施例中的当前轨迹路线可以是时间连续的轨迹路线,因而,这里首先可以按照采集时间戳对多个车辆轨迹点进行排序,进而基于排序后的多个车辆轨迹点进行点集划分以确定当前轨迹路线包括的各个路 线段,从而得到当前轨迹路线,该当前轨迹路线在时间上连续的,从而便于进行后续的路线段比对。
在一些实施例中,所述基于获取的所述定位数据,确定当前车辆采集道路数据的过程中经过的当前轨迹路线,包括:
对获取的所述定位数据进行下采样处理,得到处理后的定位数据;
基于处理后的定位数据,确定当前车辆采集道路数据的过程中经过的当前轨迹路线。
这里,考虑到当前车辆所实际采集到的定位数据的量是巨大的,如果直接应用于当前轨迹路线的构建,一定程度上会需要占用大量的计算量,而在实际场景中,特别是针对一些平滑行驶轨迹,较少的车辆轨迹点即可以用以表征当前轨迹路线,因而,本公开实施例在确定当前轨迹路线之前,可以先对获取的定位数据进行下采样处理,以在确保轨迹路线完整性的同时,降低后续的数据计算量。
在一些实施例中,所述对获取的所述定位数据进行下采样处理,得到处理后的定位数据,包括:
从获取的所述定位数据所包括的多个车辆轨迹点中筛选出符合预设下采样比例的多个车辆轨迹点;
将筛选出的所述多个车辆轨迹点对应的数据作为所述处理后的定位数据。
在一些实施例中,所述对获取的所述定位数据进行下采样处理,得到处理后的定位数据,包括:
针对获取的所述定位数据包括的任意三个连续采集的车辆轨迹点,确定两个相邻的路线段,并确定该两个相邻的路线段中的每个路线段所对应的方向向量;
确定所述两个相邻的路线段所对应的方向向量之间的夹角是否小于预设角度;
若是,则删除所述任意三个连续采集的车辆轨迹点中的最后一个车辆轨迹点,并将剩余的各个车辆轨迹点对应的数据,确定为所述处理后的定位数据。
这里,可以基于方向向量的确定实现定位数据的局部下采样操作,将对应方向向量的夹角较小的两个路线段中的最后一个车辆轨迹点进行删除,也即,最后一个车辆轨迹点被认为是三个连续采集的车辆轨迹点中的冗余轨迹点,在删除后不会影响整个轨迹路线的完整性,还可以降低后续的计算量。
在一些实施例中,所述将所述目标路线段合并到所述轨迹路线集合中之后,还包括:
基于合并后的所述轨迹路线集合包括的各个路线段,生成与每个路线段对应的折线展示信息;
将每个路线段对应的折线展示信息对应展示在当前车辆的地图中。
本公开实施例中,针对更新的轨迹路线集合可以生成与该轨迹路线包括的每个路线段对应的折线展示信息,以进行车辆地图的展示。以基于展示的地图信息可以提醒数据采集员避开已完成道路数据采集的路段,进而可以提升整个数据采集流程的效率。
在一些实施例中,所述道路数据包括以下数据中的至少一种:
当前车辆上的雷达设备采集的点云数据;
当前车辆上的图像传感器采集的图像数据。
本公开实施例还提供了一种道路数据处理的装置,所述装置包括:
获取模块,配置为获取当前车辆在采集道路数据的过程中的定位数据;
确定模块,配置为基于获取的所述定位数据,确定当前车辆采集道路数据的过程中经过的当前轨迹路线;
筛选模块,配置为基于所述当前轨迹路线以及轨迹路线集合,将所述当前轨迹路线中与所述轨迹路线集合中的路线段不重复的路线段作为目标路线段;
合并模块,配置为将所述目标路线段合并到所述轨迹路线集合中,并将所述目标路线段对应的道路数据合并到所述轨迹路线集合对应的道路数据。
本公开实施例还提供了一种电子设备,包括:处理器、存储器和总线,所述存储器存储有所述处理器可执行的机器可读指令,当电子设备运行时,所述处理器与所述存储器之间通过总线通信,所述机器可读指令被所述处理器执行时执行本公开实施例任意一项所述的方法。
本公开实施例还提供了一种计算机可读存储介质,所述计算机可读存储介质上存储有计算机程序,所述计算机程序被电子设备运行时,所述电子设备执行本公开实施例任意一项所述的方法。
本公开实施例还提供了一种计算机程序产品,所述计算机程序产品承载有程序代码,所述程序代码包括的指令可用于执行本公开实施例任意一项所述的方法。
关于上述道路数据处理的装置、电子设备、及计算机可读存储介质的效果描述参见上述道路数据处理的方法的说明,这里不再赘述。
为使本公开的上述目的、特征和优点能更明显易懂,下文特举较佳实施例,并配合所附附图,作详细说明如下。
附图说明
为了更清楚地说明本公开实施例的技术方案,下面将对实施例中所需要使用的附图作简单地介绍,此处的附图被并入说明书中并构成本说明书中的一部分,这些附图示出了符合本公开的实施例,并与说明书一起用于说明本公开的技术方案。应当理解,以下附图仅示出了本公开的某些实施 例,因此不应被看作是对范围的限定,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他相关的附图。
图1是本公开实施例提供的一种道路数据处理的方法的流程图;
图2是本公开实施例提供的一种道路数据处理的装置的示意图;
图3是本公开实施例提供的一种电子设备的示意图。
具体实施方式
为使本公开实施例的目的、技术方案和优点更加清楚,下面将结合本公开实施例中附图,对本公开实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本公开一部分实施例,而不是全部的实施例。通常在此处描述和示出的本公开实施例的组件可以以各种不同的配置来布置和设计。因此,以下对本公开的实施例的详细描述并非旨在限制要求保护的本公开的范围,而是仅仅表示本公开的选定实施例。基于本公开的实施例,本领域技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例,都属于本公开保护的范围。
经研究发现,不管是多辆采集车进行数据采集,还是单个采集车进行数据采集,针对同一道路往往存在一定程度上的数据冗余,这为数据存储带来了压力。
基于上述研究,本公开提供了一种道路数据处理的方法、装置、电子设备、计算机可读存储介质和计算机程序产品,通过定位数据确定是否基于当前轨迹路线更新轨迹路线集合及对应的道路数据,由此得到的道路数据的冗余度较低,便于存储。
针对以上方案所存在的缺陷,均是发明人在经过实践并仔细研究后得出的结果,因此,上述问题的发现过程以及下文中本公开针对上述问题所提出的解决方案,都应该是发明人在本公开过程中对本公开做出的贡献。
应注意到:相似的标号和字母在下面的附图中表示类似项,因此,一旦某一项在一个附图中被定义,则在随后的附图中不需要对其进行进一步定义和解释。
为便于对本实施例进行理解,首先对本公开实施例所公开的一种道路数据处理的方法进行详细介绍,本公开实施例所提供的道路数据处理的方法的执行主体一般为具有一定计算能力的电子设备,该电子设备例如包括:终端设备或服务器或其它处理设备,终端设备可以为用户设备(User Equipment,UE)、移动设备、用户终端、终端、蜂窝电话、无绳电话、个人数字处理(Personal Digital Assistant,PDA)、手持设备、计算设备、车载设备、可穿戴设备等。在一些可能的实现方式中,该道路数据处理的方法可以通过处理器调用存储器中存储的计算机可读指令的方式来实现。
下面以执行主体为服务器为例对本公开实施例提供的道路数据处理的方法加以说明。
参见图1所示,为本公开实施例提供的道路数据处理的方法的流程图,方法包括步骤S101~步骤S104,其中:
步骤S101、获取当前车辆在采集道路数据的过程中的定位数据;
步骤S102、基于获取的定位数据,确定当前车辆采集道路数据的过程中经过的当前轨迹路线;
步骤S103、基于当前轨迹路线以及轨迹路线集合,将当前轨迹路线中与轨迹路线集合中的路线段不重复的路线段作为目标路线段;
步骤S104、将目标路线段合并到轨迹路线集合中,并将目标路线段对应的道路数据合并到轨迹路线集合对应的道路数据。
为了便于理解本公开实施例提供的道路数据处理的方法,接下来首先对该道路数据处理的方法的应用场景进行详细描述。上述道路数据处理的方法主要可以应用于自动驾驶技术领域中,这主要是考虑到自动驾驶技术作为一种通过电脑系统实现无人驾驶的技术,为了使得电脑可以在没有主动操作的情况下,自动安全地操作机动车辆,这就需要预先对车辆周边的道路数据进行检测以用于后续应用,例如,可以用于目标对象识别模型的训练、调优等,还可以用于地图创建等。除此之外,本公开实施例还可以应用于任何需要进行道路数据采集的应用场景中,在此不做具体的限制。
为了能够采集到更为完整的道路数据,在相关技术中往往可以采用多量采集车进行一个待检测区域的道路数据采集,多辆采集车之间由于缺乏相应的数据共享机制而导致针对同一道路存在不同程度的数据冗余,这为后续的数据存储带来了压力,且在道路数据存在冗余的情况下,不便于进行后续应用。
正是为了解决上述问题,本公开实施例才提供了一种通过定位数据实现道路数据冗余消除的道路数据处理的方法,由此得到的道路数据的冗余度较低,便于存储,且便于后续应用。
其中,本公开实施例所获取的定位数据可以是搭载在车辆上的定位设备采集的,该定位设备可以是基于全球定位系统(Global Positioning System,GPS)实现的定位,还可以是基于伽利略卫星导航系统(Galileo Satellite Navigation System,GSNS)、全球卫星导航系统(GLOBAL NAVIGATION SATELLITE SYSTEM,GNSS)等系统实现的定位,还可以是基于其它定位技术实现的定位,在此不做具体的限制。
另外,本公开实施例提供的道路数据处理的方法还可以基于车辆搭载的道路数据检测设备进行道路数据的采集,这里的道路数据检测设备可以是雷达设备,用于检测有关道路的点云数据,还可以是图像传感器,用于检测有关道路的图像数据,除此之外,本公开实施例还可以基于实际的应用需求选择其它的检测设备,在此不做具体的限制。
本公开实施例中的定位数据可以是在进行道路数据采集的过程中获取的,这样,道路数据与定位数据之间存在一定的依赖性,例如,在确定车 辆到达一个特定位置的情况下,可以确定在该特定位置所采集到的道路数据。
本公开实施例正是利用上述两份数据之间的依赖性,提供了一种基于定位数据来对道路数据去重的方案。
这里,首先可以基于获取的定位数据,确定在进行道路数据采集的过程中车辆经过的当前轨迹路线,将该当前轨迹路线与轨迹路线集合进行比对,可以确定路线之间是否存在重复,对于不重复的路线段可以作为目标路线段以实现轨迹路线集合的更新以及对应的道路数据的更新。在路线之间不存在重复的情况下,可以进行路线合并,由于整个轨迹路线不存在重复,从而使得所确定出的道路数据的冗余度较低。
需要说明的是,这里的轨迹路线集合可以是车辆(如当前车辆和/或其他车辆)已采集的道路数据对应的轨迹路线的集合,例如可以是原始轨迹路线,还可以是在对原始轨迹路线进行去重后得到的轨迹路线,这里,可以作为更新前的一个轨迹路线集合。这样,在当前车辆采集道路数据的过程中,即可以基于获取的定位数据所确定的当前轨迹路线对轨迹路线集合进行当前次的更新,在当前次的更新的基础上还可以进行下一次的更新,直至满足应用场景下对道路数据采集的需求,例如,遍历了一个采集区域内所有的城市道路。
本公开实施例提供的道路数据处理的方法还可以对合并后的轨迹路线集合进行可视化展示,基于可视化结果可以避免数据采集员去往已采集的路段再次进行道路数据的采集,进一步减少路线重复,便于后续的采集路线设计。
这里,可以基于合并后的轨迹路线集合包括的各个路线段,生成与每个路线段对应的折线展示信息,然后将每个路线段对应的折线展示信息对应展示在当前车辆的地图中。其中,路线段对应的折线展示信息可以是基于路线段包括的各个车辆轨迹点之间的连线所生成的,使得地图展示效果更为直观。
为了更好的进行路线比对,本公开实施例中,可以对当前轨迹路线进行更小粒度的划分,这里可以划分为多个路线段。这样,即可以基于当前轨迹路线以及轨迹路线集合确定当前轨迹路线的每个路线段是否出现在轨迹路线集合中,若没有出现,则可以将这一路线段作为目标路线段合并到轨迹路线集合中,从而可以得到更新后的轨迹路线集合,若出现,则可以删除这一路线段对应采集的道路数据,与此同时,还可以将目标路线段对应采集的道路数据合并到轨迹路线集合对应的道路数据中,这样所采集得到的道路数据是不存在重复的。
考虑到目标路线段的确定过程对于后续轨迹路线集合及对应的道路数据的确定的关键作用,接下来可以通过如下步骤具体说明目标路线段的确定过程:
步骤一、针对当前轨迹路线包含的每个路线段,基于该路线段所包括的多个车辆轨迹点的位置信息以及轨迹路线集合所包括的各个车辆轨迹点的位置信息,从轨迹路线集合中查找与该路线段距离最近的目标车辆轨迹点;
步骤二、判断目标车辆轨迹点与路线段之间的距离是否大于预设距离;
步骤三、若是,则确定路线段为目标路线段。
针对当前轨迹路线的一个路线段,本公开实施例提供的道路数据处理的方法首先可以基于该路线段所包括的多个车辆轨迹点的位置信息以及轨迹路线集合所包括的各个车辆轨迹点的位置信息之间的相对位置关系,从轨迹路线集合中查找与这一路线段最近的目标车辆轨迹点。进而可以判断目标车辆轨迹点与路线段之间的距离是否大于预设距离,这主要是考虑到在目标车辆轨迹点距离路线段越近的情况下,一定程度上说明当前轨迹路线中的这一路线段与目标车辆轨迹点所对应的轨迹路线集合发生重复的可能性较大,同理,在目标车辆轨迹点距离路线段越远的情况下,一定程度上说明当前轨迹路线中的这一路线段与目标车辆轨迹点所对应的轨迹路线集合发生重复的可能性较小,因而,这里,可以基于距离判断结果来确定这一路线段是否与轨迹路线集合不重复的目标路线段。
其中,上述预设距离的选取不宜过大,也不宜过小,过大的预设距离将导致判断结果存在较大的误差,而过小的预设距离则会忽视噪声干扰等情况所带来的合理轨迹扰动,导致判断结果不准确,因而,这里可以基于实际应用场景的需求,选取适宜大小的预设距离。例如,可以基于定位设备的定位精度来确定,在定位精度比较高的情况下,可以选取较小的预设距离,在定位精度比较低的情况下,可以选取较大的预设距离。
为了便于进一步理解上述目标路线段的确定过程,接下来可以结合一个具体的示例进行说明。
首先,假设已有一个路线数据库R(对应轨迹路线集合),需要插入一段新的路线S(对应当前轨迹路线),则可以筛除路线S中与路线数据库R重复的路线段,再将路线S中与路线数据库R不重复的路线段插入路线数据库R中。这里,可以记路线S由多个连续的路线段组成:路线段AB,路线段BC,路线段CD,路线段DE,……;
然后,针对待插入路线S中的每个路线段,判断该路线段是否与路线数据库R重复,如果重复,则筛除;否则插入路线数据库R中。
这里,可以先判断路线段AB与路线数据库R是否重复,在路线数据库R中找到距离路线段AB最近的一个点P(即目标车辆轨迹点),如果点P与路线段AB的距离大于预设距离δ,则认为路线段AB与路线数据库R不重复,确定路线段AB为目标路线段,合并路线段AB和路线数据库R;如果小于预设距离δ,则认为路线段AB被路线数据库R覆盖,确定路线段AB为非目标路线段,删除路线段AB及该路线段AB对应的道路数据, 继续计算下一个路线段。
本公开实施例提供的道路数据处理的方法可以按照距离公式确定目标车辆轨迹点与路线段之间的距离,可以包括如下步骤:
步骤一、基于路线段所包括的任意两个车辆轨迹点中每个车辆轨迹点的横向坐标值和纵向坐标值,确定该路线段所对应的直线方程;
步骤二、基于目标车辆轨迹点的横向坐标值和纵向坐标值、以及确定的直线方程,确定目标车辆轨迹点与路线段之间的距离。
这里,首先可以基于路线段所包括的任意两个车辆轨迹点中每个车辆轨迹点的横向坐标值和纵向坐标值,确定路线段所对应的直线方程,也即,利用两点坐标值可以确定这两点所形成直线的直线方程,这样,即可以基于点到直线的距离公式,确定目标车辆轨迹点与路线段之间的距离。
为了便于进行当前轨迹路线与轨迹路线集合之间的比对,本公开实施例中的当前轨迹路线可以是基于时间先后顺序排列的各个车辆轨迹点连线所得到的。
在具体应用中,可以先确定组成当前轨迹路线的各个路线段,进而基于各个路线段的组合来确定当前轨迹路线,具体可以按照如下步骤来实现:
步骤一、按照采集时间戳由小到大的顺序对多个车辆轨迹点进行排序;
步骤二、按照预设路线段长度将多个车辆轨迹点划分为多个车辆轨迹点集;
步骤三、针对每个车辆轨迹点集,将该车辆轨迹点集包括的各个车辆轨迹点进行连线,生成组成当前轨迹路线的一个路线段;
步骤四、将针对每个车辆轨迹点集生成的组成当前轨迹路线的一个路线段进行组合,得到当前轨迹路线。
这里,首先按照各个车辆轨迹点的采集时间戳对各个车辆轨迹点进行排序,排序后的各个车辆轨迹点在时间上是具有连续性的,这样,可以基于按照预设路线段长度将多个车辆轨迹点划分为多个车辆轨迹点集,每一个车辆轨迹点集可以对应一个路线段,将各个路线段进行组合,即可以确定当前轨迹路线。
其中,有关预设路线段长度可以是基于定位设备的采集频率等相关参数确定的。在采集频率较高的情况下,单位时间内获取的车辆轨迹点也越密集,为了确保路线对比效果,这时可以将预设路线段长度设定的更小一些,而在采集频率较低的情况下,单位时间内获取的车辆轨迹点也越稀疏,这时则可以将预设路线段长度设定的更大一些。
本公开实施例在基于定位数据确定当前轨迹路线的过程中,由于采集车采集的数据较为密集,这为后续的轨迹点之间的距离比对带来了一定的计算量,因而,本公开实施例可以提供一种下采样处理方式先对定位数据进行下采样处理,再基于采样处理后的定位数据来确定当前轨迹路线,从而能够在确保轨迹完整性的前提下,降低后续计算量。
本公开实施例中,可以通过以下两个方面分别描述本公开实施例提供的两种下采样处理方法。
第一方面:本公开实施可以基于轨迹点筛选实现下采样,可以包括如下步骤:
步骤一、从获取的定位数据所包括的多个车辆轨迹点中筛选出符合预设下采样比例的多个车辆轨迹点;
步骤二、将筛选出的多个车辆轨迹点对应的数据作为处理后的定位数据。
这里,可以基于预设下采样比例对多个车辆轨迹点进行筛选,例如,单批定位数据有N个车辆轨迹点,给定下采样比例p(如30%),可以随机筛选出Np个点,也可以基于车辆轨迹点的分布遍历筛选。
第二方面:本公开实施可以基于方向向量实现下采样,可以包括如下步骤:
步骤一、针对获取的定位数据包括的任意三个连续采集的车辆轨迹点,确定两个相邻的路线段,并确定该两个相邻的路线段中的每个路线段所对应的方向向量;
步骤二、确定两个相邻的路线段所对应的方向向量之间的夹角是否小于预设角度;
步骤三、若是,则删除任意三个连续采集的车辆轨迹点中的最后一个车辆轨迹点,并将剩余的各个车辆轨迹点对应的数据,确定为处理后的定位数据。
这里,考虑到在实际的应用中,不同车辆轨迹点对当前轨迹路线的影响程度并不相同,例如,针对连续的多个车辆轨迹点而言,在车辆进行拐弯时的车辆轨迹点往往比较重要,这些车辆轨迹点是需要保留的,而对于沿直线行驶的车辆而言,一些车辆轨迹点的有无不会对当前轨迹路线产生太大的影响,因而,本公开实施例提供了一种基于三个连续的车辆轨迹点所形成的两个相邻的路线段之间的方向向量实现下采样的方案。
在两个相邻的路线段所对应的方向向量之间的夹角越小的情况下,说明三个连续的车辆轨迹点位于一条直线上的可能性较大,这时,可以对第三个车辆轨迹点进行删除;在两个相邻的路线段所对应的方向向量之间的夹角越大的情况下,说明三个连续的车辆轨迹点位于一条直线上的可能性较小,且第三个车辆轨迹点发生转向的可能性更大,这时,可以保留第三个车辆轨迹点。
为了便于进一步理解上述下采样处理过程,接下来可以结合一个具体的示例进行说明。
记连续的车辆轨迹点分别为点A1、点B1、点C1、点D1。可以基于点A1、点B1、点C1这三个车辆轨迹点的横向坐标值和纵向坐标值,计算线段A1B1与线段B1C1两条线段对应的方向向量,再计算线段A1B1、线段 B1C1方向向量的夹角大小,如果夹角小于预设角度θ(如90°),则丢弃点C1,继续计算线段A1B1与线段C1D1的夹角;如果大于预设角度θ,则保留点C1,继续计算线段B1C1与线段C1D1的夹角,进一步确定是否保留点D1,依此类推,直至得到处理后的定位数据。
考虑到基于本公开实施例提供的上述道路数据处理的方法所确定的道路数据冗余度较低,在将处理后的道路数据应用到具体场景时,将具有很大的优势。
例如,针对目标对象检测场景,利用上述道路数据所训练目标对象检测模型,由于道路数据的冗余度较低,这样,可以尽可能避免所训练出来的目标对象检测模型过拟合到训练数据的场景中,且少量的数据样本涵盖了各个路线段的道路数据,从而能够在确保目标对象检测模型的训练效果的前提下,提升训练效率。再如,针对需要预先进行道路数据标注的应用场景中,标注的成本也大大降低。
本领域技术人员可以理解,在具体实施方式的上述方法中,各步骤的撰写顺序并不意味着严格的执行顺序而对实施过程构成任何限定,各步骤的具体执行顺序应当以其功能和可能的内在逻辑确定。
基于同一发明构思,本公开实施例中还提供了与道路数据处理的方法对应的道路数据处理的装置,由于本公开实施例中的装置解决问题的原理与本公开实施例上述道路数据处理的方法相似,因此装置的实施可以参见方法的实施,重复之处不再赘述。
参照图2所示,为本公开实施例提供的一种道路数据处理的装置的示意图,装置包括:获取模块201、确定模块202、筛选模块203、合并模块204;其中,
获取模块201,配置为获取当前车辆在采集道路数据的过程中的定位数据;
确定模块202,配置为基于获取的定位数据,确定当前车辆采集道路数据的过程中经过的当前轨迹路线;
筛选模块203,配置为基于当前轨迹路线以及轨迹路线集合,将当前轨迹路线中与轨迹路线集合中的路线段不重复的路线段作为目标路线段;
合并模块204,配置为将目标路线段合并到轨迹路线集合中,并将目标路线段对应的道路数据合并到轨迹路线集合对应的道路数据。
本公开实施例,在获取到当前车辆在采集道路数据的过程中的定位数据的情况下,可以确定车辆在采集过程中经过的当前轨迹路线,进而可以从当前轨迹路线中确定与轨迹路线集合中的路线段不重复的路线段,并作为目标路线段合并到轨迹路线集合以及进行道路数据的合并。可知的是,上述道路数据处理的方法可以基于道路数据采集过程中的定位数据对轨迹路线集合进行更新,这里更新的是没有与轨迹路线集合发生重复的路线段, 进而可以快速的对大批量的道路数据进行筛选以达到道路数据去重的目的,在确保了道路数据完整性的前提下,节省了后续的数据存储空间,还能够便于指导后续的路线采集工作。
在一些实施例中,定位数据包括多个车辆轨迹点的位置信息;筛选模块203,配置为按照以下步骤确定目标路线段:
针对当前轨迹路线包含的每个路线段,基于该路线段所包括的多个车辆轨迹点的位置信息以及轨迹路线集合所包括的各个车辆轨迹点的位置信息,从轨迹路线集合中查找与该路线段距离最近的目标车辆轨迹点;
判断目标车辆轨迹点与路线段之间的距离是否大于预设距离;
若是,则确定路线段为目标路线段。
在一些实施例中,车辆轨迹点的位置信息包括横向坐标值和纵向坐标值;筛选模块203,配置为按照如下步骤确定目标车辆轨迹点与路线段之间的距离:
基于路线段所包括的任意两个车辆轨迹点中每个车辆轨迹点的横向坐标值和纵向坐标值,确定该路线段所对应的直线方程;
基于目标车辆轨迹点的横向坐标值和纵向坐标值、以及确定的直线方程,确定目标车辆轨迹点与路线段之间的距离。
在一些实施例中,定位数据还包括与每个位置信息对应的采集时间戳;确定模块202,配置为按照以下步骤基于获取的定位数据,确定当前车辆采集道路数据的过程中经过的当前轨迹路线:
按照采集时间戳由小到大的顺序对多个车辆轨迹点进行排序;
按照预设路线段长度将多个车辆轨迹点划分为多个车辆轨迹点集;
针对每个车辆轨迹点集,将该车辆轨迹点集包括的各个车辆轨迹点进行连线,生成组成当前轨迹路线的一个路线段;
将针对每个车辆轨迹点集生成的组成当前轨迹路线的一个路线段进行组合,得到当前轨迹路线。
在一些实施例中,确定模块202,配置为按照以下步骤基于获取的定位数据,确定当前车辆采集道路数据的过程中经过的当前轨迹路线:
对获取的定位数据进行下采样处理,得到处理后的定位数据;
基于处理后的定位数据,确定当前车辆采集道路数据的过程中经过的当前轨迹路线。
在一些实施例中,确定模块202,配置为按照以下步骤对获取的定位数据进行下采样处理,得到处理后的定位数据:
从获取的定位数据所包括的多个车辆轨迹点中筛选出符合预设下采样比例的多个车辆轨迹点;
将筛选出的多个车辆轨迹点对应的数据作为处理后的定位数据。
在一些实施例中,确定模块202,配置为按照以下步骤对获取的定位数据进行下采样处理,得到处理后的定位数据:
针对获取的定位数据包括的任意三个连续采集的车辆轨迹点,确定两个相邻的路线段,并确定该两个相邻的路线段中的每个路线段所对应的方向向量;
确定两个相邻的路线段所对应的方向向量之间的夹角是否小于预设角度;
若是,则删除任意三个连续采集的车辆轨迹点中的最后一个车辆轨迹点,并将剩余的各个车辆轨迹点对应的数据,确定为处理后的定位数据。
在一些实施例中,上述装置还包括:
展示模块205,配置为将目标路线段合并到轨迹路线集合中之后,基于合并后的轨迹路线集合包括的各个路线段,生成与每个路线段对应的折线展示信息;将每个路线段对应的折线展示信息对应展示在当前车辆的地图中。
在一些实施例中,道路数据包括以下数据中的至少一种:
当前车辆上的雷达设备采集的点云数据;
当前车辆上的图像传感器采集的图像数据。
关于装置中的各模块的处理流程、以及各模块之间的交互流程的描述可以参照上述方法实施例中的相关说明,这里不再详述。
本公开实施例还提供了一种电子设备,如图3所示,为本公开实施例提供的电子设备结构示意图,包括:处理器301、存储器302、和总线303。存储器302存储有处理器301可执行的机器可读指令(比如,图2中的装置中获取模块201、确定模块202、筛选模块203、合并模块204对应的执行指令等),当电子设备运行时,处理器301与存储器302之间通过总线303通信,机器可读指令被处理器301执行时执行如下处理:
获取当前车辆在采集道路数据的过程中的定位数据;
基于获取的定位数据,确定当前车辆采集道路数据的过程中经过的当前轨迹路线;
基于当前轨迹路线以及轨迹路线集合,将当前轨迹路线中与轨迹路线集合中的路线段不重复的路线段作为目标路线段;
将目标路线段合并到轨迹路线集合中,并将目标路线段对应的道路数据合并到轨迹路线集合对应的道路数据。
在一些实施例中,定位数据包括多个车辆轨迹点的位置信息;上述处理器301执行的指令中,目标路线段按照以下步骤确定:
针对当前轨迹路线包含的每个路线段,基于该路线段所包括的多个车辆轨迹点的位置信息以及其它车辆已采集的道路数据对应的轨迹路线集合所包括的各个车辆轨迹点的位置信息,从轨迹路线集合中查找与该路线段距离最近的目标车辆轨迹点;
判断目标车辆轨迹点与路线段之间的距离是否大于预设距离;
若是,则确定路线段为目标路线段。
在一些实施例中,车辆轨迹点的位置信息包括横向坐标值和纵向坐标值;上述处理器301执行的指令中,按照如下步骤确定目标车辆轨迹点与路线段之间的距离:
基于路线段所包括的任意两个车辆轨迹点中每个车辆轨迹点的横向坐标值和纵向坐标值,确定该路线段所对应的直线方程;
基于目标车辆轨迹点的横向坐标值和纵向坐标值、以及确定的直线方程,确定目标车辆轨迹点与路线段之间的距离。
在一些实施例中,定位数据还包括与每个位置信息对应的采集时间戳;上述处理器301执行的指令中,基于获取的定位数据,确定当前车辆采集道路数据的过程中经过的当前轨迹路线,包括:
按照采集时间戳由小到大的顺序对多个车辆轨迹点进行排序;
按照预设路线段长度将多个车辆轨迹点划分为多个车辆轨迹点集;
针对每个车辆轨迹点集,将该车辆轨迹点集包括的各个车辆轨迹点进行连线,生成组成当前轨迹路线的一个路线段;
将针对每个车辆轨迹点集生成的组成当前轨迹路线的一个路线段进行组合,得到当前轨迹路线。
在一些实施例中,上述处理器301执行的指令中,基于获取的定位数据,确定当前车辆采集道路数据的过程中经过的当前轨迹路线,包括:
对获取的定位数据进行下采样处理,得到处理后的定位数据;
基于处理后的定位数据,确定当前车辆采集道路数据的过程中经过的当前轨迹路线。
在一些实施例中,上述处理器301执行的指令中,对获取的定位数据进行下采样处理,得到处理后的定位数据,包括:
从获取的定位数据所包括的多个车辆轨迹点中筛选出符合预设下采样比例的多个车辆轨迹点;
将筛选出的多个车辆轨迹点对应的数据作为处理后的定位数据。
在一些实施例中,上述处理器301执行的指令中,对获取的定位数据进行下采样处理,得到处理后的定位数据,包括:
针对获取的定位数据包括的任意三个连续采集的车辆轨迹点,确定两个相邻的路线段,并确定该两个相邻的路线段中的每个路线段所对应的方向向量;
确定两个相邻的路线段所对应的方向向量之间的夹角是否小于预设角度;
若是,则删除任意三个连续采集的车辆轨迹点中的最后一个车辆轨迹点,并将剩余的各个车辆轨迹点对应的数据,确定为处理后的定位数据。
在一些实施例中,将目标路线段合并到轨迹路线集合中之后,上述处理器301执行的指令还包括:
基于合并后的轨迹路线集合包括的各个路线段,生成与每个路线段对应的折线展示信息;
将每个路线段对应的折线展示信息对应展示在当前车辆的地图中。
在一些实施例中,道路数据包括以下数据中的至少一种:
当前车辆上的雷达设备采集的点云数据;
当前车辆上的图像传感器采集的图像数据。
上述指令的具体执行过程可以参考本公开实施例中所述的道路数据处理的方法,此处不再赘述。
本公开实施例还提供一种计算机可读存储介质,该计算机可读存储介质上存储有计算机程序,该计算机程序被处理器运行时执行上述方法实施例中所述的道路数据处理的方法。其中,该存储介质可以是易失性或非易失的计算机可读取存储介质。
本公开实施例还提供了一种计算机程序产品,该计算机程序产品承载有程序代码,所述程序代码包括的指令可用于执行上述方法实施例中所述的道路数据处理的方法,具体可参见上述方法实施例,在此不再赘述。
其中,上述计算机程序产品可以具体通过硬件、软件或其结合的方式实现。在一个可选实施例中,所述计算机程序产品具体体现为计算机存储介质,在另一个可选实施例中,计算机程序产品具体体现为软件产品,例如软件开发包(Software Development Kit,SDK)等等。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的系统和装置的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。在本公开所提供的几个实施例中,应该理解到,所揭露的系统、装置和方法,可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,又例如,多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些通信接口,装置或单元的间接耦合或通信连接,可以是电性,机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外,在本公开各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个处理器可执行的非易失的计算机可读取存储介质中。 基于这样的理解,本公开的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干指令用以使得一台电子设备(可以是个人计算机,服务器,或者网络设备等)执行本公开各个实施例所述方法的全部或部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是:以上所述实施例,仅为本公开的具体实施方式,用以说明本公开的技术方案,而非对其限制,本公开的保护范围并不局限于此,尽管参照前述实施例对本公开进行了详细的说明,本领域的普通技术人员应当理解:任何熟悉本技术领域的技术人员在本公开揭露的技术范围内,其依然可以对前述实施例所记载的技术方案进行修改或可轻易想到变化,或者对其中部分技术特征进行等同替换;而这些修改、变化或者替换,并不使相应技术方案的本质脱离本公开实施例技术方案的精神和范围,都应涵盖在本公开的保护范围之内。因此,本公开的保护范围应所述以权利要求的保护范围为准。
工业实用性
本公开涉及一种道路数据处理的方法、装置、电子设备、计算机可读存储介质和计算机程序产品,其中,该方法包括:获取当前车辆在采集道路数据的过程中的定位数据;基于获取的定位数据,确定当前车辆采集道路数据的过程中经过的当前轨迹路线;基于当前轨迹路线以及轨迹路线集合,将当前轨迹路线中与轨迹路线集合中的路线段不重复的路线段作为目标路线段;将目标路线段合并到轨迹路线集合中,并将目标路线段对应的道路数据合并到轨迹路线集合对应的道路数据。本公开通过定位数据确定是否基于当前轨迹路线更新轨迹路线集合及对应的道路数据,道路数据的冗余度较低,便于存储。

Claims (21)

  1. 一种道路数据处理的方法,应用于电子设备中,所述方法包括:
    获取当前车辆在采集道路数据的过程中的定位数据;
    基于获取的所述定位数据,确定当前车辆采集道路数据的过程中经过的当前轨迹路线;
    基于所述当前轨迹路线以及轨迹路线集合,将所述当前轨迹路线中与所述轨迹路线集合中的路线段不重复的路线段作为目标路线段;
    将所述目标路线段合并到所述轨迹路线集合中,并将所述目标路线段对应的道路数据合并到所述轨迹路线集合对应的道路数据。
  2. 根据权利要求1所述的方法,其中,所述定位数据包括多个车辆轨迹点的位置信息;所述目标路线段按照以下步骤确定:
    针对所述当前轨迹路线包含的每个路线段,基于所述每个路线段所包括的多个车辆轨迹点的位置信息以及所述轨迹路线集合所包括的各个车辆轨迹点的位置信息,从所述轨迹路线集合中查找与所述每个路线段距离最近的目标车辆轨迹点;
    判断所述目标车辆轨迹点与所述每个路线段之间的距离是否大于预设距离;
    若是,则确定所述每个路线段为所述目标路线段。
  3. 根据权利要求2所述的方法,其中,所述车辆轨迹点的位置信息包括横向坐标值和纵向坐标值;按照如下步骤确定所述目标车辆轨迹点与所述每个路线段之间的距离:
    基于所述每个路线段所包括的任意两个车辆轨迹点中每个车辆轨迹点的横向坐标值和纵向坐标值,确定所述每个路线段所对应的直线方程;
    基于所述目标车辆轨迹点的横向坐标值和纵向坐标值、以及确定的所述直线方程,确定所述目标车辆轨迹点与所述每个路线段之间的距离。
  4. 根据权利要求2或3所述的方法,其中,所述定位数据还包括与每个位置信息对应的采集时间戳;所述基于获取的所述定位数据,确定当前车辆采集道路数据的过程中经过的当前轨迹路线,包括:
    按照采集时间戳由小到大的顺序对所述多个车辆轨迹点进行排序;
    按照预设路线段长度将所述多个车辆轨迹点划分为多个车辆轨迹点集;
    针对每个所述车辆轨迹点集,将每个所述车辆轨迹点集包括的各个车辆轨迹点进行连线,生成组成所述当前轨迹路线的一个路线段;
    将针对每个所述车辆轨迹点集生成的组成所述当前轨迹路线的一个路线段进行组合,得到所述当前轨迹路线。
  5. 根据权利要求1-4任一所述的方法,其中,所述基于获取的所述定位数据,确定当前车辆采集道路数据的过程中经过的当前轨迹路线,包括:
    对获取的所述定位数据进行下采样处理,得到处理后的定位数据;
    基于处理后的定位数据,确定当前车辆采集道路数据的过程中经过的当前轨迹路线。
  6. 根据权利要求5所述的方法,其中,所述对获取的所述定位数据进行下采样处理,得到处理后的定位数据,包括:
    从获取的所述定位数据所包括的多个车辆轨迹点中筛选出符合预设下采样比例的多个车辆轨迹点;
    将筛选出的所述多个车辆轨迹点对应的数据作为所述处理后的定位数据。
  7. 根据权利要求5所述的方法,其中,所述对获取的所述定位数据进行下采样处理,得到处理后的定位数据,包括:
    针对获取的所述定位数据包括的任意三个连续采集的车辆轨迹点,确定两个相邻的路线段,并确定所述两个相邻的路线段中的每个路线段所对应的方向向量;
    确定所述两个相邻的路线段所对应的方向向量之间的夹角是否小于预 设角度;
    若是,则删除所述任意三个连续采集的车辆轨迹点中的最后一个车辆轨迹点,并将剩余的各个车辆轨迹点对应的数据,确定为所述处理后的定位数据。
  8. 根据权利要求1-7任一所述的方法,其中,将所述目标路线段合并到所述轨迹路线集合中之后,还包括:
    基于合并后的所述轨迹路线集合包括的各个路线段,生成与每个路线段对应的折线展示信息;
    将每个路线段对应的折线展示信息对应展示在当前车辆的地图中。
  9. 根据权利要求1-8任一所述的方法,其中,所述道路数据包括以下数据中的至少一种:
    当前车辆上的雷达设备采集的点云数据;
    当前车辆上的图像传感器采集的图像数据。
  10. 一种道路数据处理的装置,应用于电子设备中,所述装置包括:
    获取模块,配置为获取当前车辆在采集道路数据的过程中的定位数据;
    确定模块,配置为基于获取的所述定位数据,确定当前车辆采集道路数据的过程中经过的当前轨迹路线;
    筛选模块,配置为基于所述当前轨迹路线以及轨迹路线集合,将所述当前轨迹路线中与所述轨迹路线集合中的路线段不重复的路线段作为目标路线段;
    合并模块,配置为将所述目标路线段合并到所述轨迹路线集合中,并将所述目标路线段对应的道路数据合并到所述轨迹路线集合对应的道路数据。
  11. 根据权利要求10所述的装置,其中,所述定位数据包括多个车辆轨迹点的位置信息;筛选模块,配置为按照以下步骤确定所述目标路线段:
    针对所述当前轨迹路线包含的每个路线段,基于所述每个路线段所包 括的多个车辆轨迹点的位置信息以及所述轨迹路线集合所包括的各个车辆轨迹点的位置信息,从所述轨迹路线集合中查找与所述每个路线段距离最近的目标车辆轨迹点;
    判断所述目标车辆轨迹点与所述每个路线段之间的距离是否大于预设距离;
    若是,则确定所述每个路线段为所述目标路线段。
  12. 根据权利要求11所述的装置,其中,所述车辆轨迹点的位置信息包括横向坐标值和纵向坐标值;筛选模块,配置为按照如下步骤确定所述目标车辆轨迹点与所述每个路线段之间的距离:
    基于所述每个路线段所包括的任意两个车辆轨迹点中每个车辆轨迹点的横向坐标值和纵向坐标值,确定所述每个路线段所对应的直线方程;
    基于所述目标车辆轨迹点的横向坐标值和纵向坐标值、以及确定的所述直线方程,确定所述目标车辆轨迹点与所述每个路线段之间的距离。
  13. 根据权利要求11或12所述的装置,其中,所述定位数据还包括与每个位置信息对应的采集时间戳;所述确定模块,配置为基于获取的所述定位数据,确定当前车辆采集道路数据的过程中经过的当前轨迹路线,包括:
    按照采集时间戳由小到大的顺序对所述多个车辆轨迹点进行排序;
    按照预设路线段长度将所述多个车辆轨迹点划分为多个车辆轨迹点集;
    针对每个所述车辆轨迹点集,将每个所述车辆轨迹点集包括的各个车辆轨迹点进行连线,生成组成所述当前轨迹路线的一个路线段;
    将针对每个所述车辆轨迹点集生成的组成所述当前轨迹路线的一个路线段进行组合,得到所述当前轨迹路线。
  14. 根据权利要求11-13任一所述的装置,其中,所述确定模块,配置为基于获取的所述定位数据,确定当前车辆采集道路数据的过程中经过的当前轨迹路线,包括:
    对获取的所述定位数据进行下采样处理,得到处理后的定位数据;
    基于处理后的定位数据,确定当前车辆采集道路数据的过程中经过的当前轨迹路线。
  15. 根据权利要求14所述的装置,其中,所述确定模块,配置为对获取的所述定位数据进行下采样处理,得到处理后的定位数据,包括:
    从获取的所述定位数据所包括的多个车辆轨迹点中筛选出符合预设下采样比例的多个车辆轨迹点;
    将筛选出的所述多个车辆轨迹点对应的数据作为所述处理后的定位数据。
  16. 根据权利要求14所述的装置,其中,所述确定模块,配置为对获取的所述定位数据进行下采样处理,得到处理后的定位数据,包括:
    针对获取的所述定位数据包括的任意三个连续采集的车辆轨迹点,确定两个相邻的路线段,并确定所述两个相邻的路线段中的每个路线段所对应的方向向量;
    确定所述两个相邻的路线段所对应的方向向量之间的夹角是否小于预设角度;
    若是,则删除所述任意三个连续采集的车辆轨迹点中的最后一个车辆轨迹点,并将剩余的各个车辆轨迹点对应的数据,确定为所述处理后的定位数据。
  17. 根据权利要求10-16任一所述的装置,其中,所述装置还包括:
    展示模块,配置为基于合并后的所述轨迹路线集合包括的各个路线段,生成与每个路线段对应的折线展示信息;将每个路线段对应的折线展示信息对应展示在当前车辆的地图中。
  18. 根据权利要求10-17任一所述的装置,其中,所述道路数据包括以下数据中的至少一种:
    当前车辆上的雷达设备采集的点云数据;
    当前车辆上的图像传感器采集的图像数据。
  19. 一种电子设备,包括:处理器、存储器和总线,所述存储器存储有所述处理器可执行的机器可读指令,当电子设备运行时,所述处理器与所述存储器之间通过总线通信,所述机器可读指令被所述处理器执行时执行如权利要求1至9任一所述的道路数据处理的方法。
  20. 一种计算机可读存储介质,其中,所述计算机可读存储介质上存储有计算机程序,所述计算机程序被电子设备运行时,所述电子设备执行如权利要求1至9任一所述的道路数据处理的方法。
  21. 一种计算机程序产品,所述计算机程序产品承载有程序代码,所述程序代码包括的指令可用于执行权利要求1至9中任意一项所述的道路数据处理的方法。
PCT/CN2021/103072 2021-03-31 2021-06-29 一种道路数据处理的方法、装置、电子设备、介质和程序 WO2022205642A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110347032.9 2021-03-31
CN202110347032.9A CN113076386A (zh) 2021-03-31 2021-03-31 一种道路数据处理的方法、装置、电子设备及存储介质

Publications (1)

Publication Number Publication Date
WO2022205642A1 true WO2022205642A1 (zh) 2022-10-06

Family

ID=76614047

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/103072 WO2022205642A1 (zh) 2021-03-31 2021-06-29 一种道路数据处理的方法、装置、电子设备、介质和程序

Country Status (2)

Country Link
CN (1) CN113076386A (zh)
WO (1) WO2022205642A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115510263A (zh) * 2022-11-22 2022-12-23 北京理工大学深圳汽车研究院(电动车辆国家工程实验室深圳研究院) 一种循迹轨迹生成方法、系统、终端设备以及存储介质
CN115991235A (zh) * 2023-03-22 2023-04-21 禾多科技(北京)有限公司 车辆转向控制方法、装置、电子设备和计算机可读介质
CN117082453A (zh) * 2023-10-17 2023-11-17 深圳市麦谷科技有限公司 车辆电子围栏告警方法、装置、设备及存储介质

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114677570B (zh) * 2022-03-14 2023-02-07 北京百度网讯科技有限公司 道路信息更新方法、装置、电子设备以及存储介质
CN115223358B (zh) * 2022-06-01 2024-04-02 北京四维图新科技股份有限公司 一种交通信息动态更新方法、装置及车路协同系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106528589A (zh) * 2016-09-14 2017-03-22 北京航空航天大学 数据管理方法及装置
CN109270927A (zh) * 2017-07-17 2019-01-25 高德软件有限公司 道路数据的生成方法及装置
CN110196440A (zh) * 2018-05-22 2019-09-03 腾讯大地通途(北京)科技有限公司 重合轨迹的识别方法及装置、电子设备、存储介质
WO2020201243A1 (fr) * 2019-04-02 2020-10-08 Continental Automotive Gmbh Procédé de mise à jour d'une carte routière à partir d'un réseau de contributeurs
CN111859167A (zh) * 2019-04-29 2020-10-30 北京四维图新科技股份有限公司 路径获取方法、装置、系统和存储介质

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105225510B (zh) * 2014-06-27 2018-04-17 国际商业机器公司 用于验证地图的路网的方法和系统
CN110069585B (zh) * 2017-12-05 2022-04-26 腾讯科技(深圳)有限公司 轨迹点数据的处理方法和装置、存储介质及电子装置
CN112509356B (zh) * 2020-10-30 2022-04-05 深圳市跨越新科技有限公司 一种车辆行驶路线生成方法及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106528589A (zh) * 2016-09-14 2017-03-22 北京航空航天大学 数据管理方法及装置
CN109270927A (zh) * 2017-07-17 2019-01-25 高德软件有限公司 道路数据的生成方法及装置
CN110196440A (zh) * 2018-05-22 2019-09-03 腾讯大地通途(北京)科技有限公司 重合轨迹的识别方法及装置、电子设备、存储介质
WO2020201243A1 (fr) * 2019-04-02 2020-10-08 Continental Automotive Gmbh Procédé de mise à jour d'une carte routière à partir d'un réseau de contributeurs
CN111859167A (zh) * 2019-04-29 2020-10-30 北京四维图新科技股份有限公司 路径获取方法、装置、系统和存储介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
HUANG YAOHUI;FAN WENTAO;LIU LIUYANG: "Research on Road Network Updataing and Trajectory Integratory Based Trajectory Data", BULLETIN OF SURVEYING AND MAPPING, no. 8, 25 August 2018 (2018-08-25), pages 119 - 123, XP055974127, ISSN: 0494-0911, DOI: 10.13474/j.cnki.11-2246.2018.0258 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115510263A (zh) * 2022-11-22 2022-12-23 北京理工大学深圳汽车研究院(电动车辆国家工程实验室深圳研究院) 一种循迹轨迹生成方法、系统、终端设备以及存储介质
CN115991235A (zh) * 2023-03-22 2023-04-21 禾多科技(北京)有限公司 车辆转向控制方法、装置、电子设备和计算机可读介质
CN117082453A (zh) * 2023-10-17 2023-11-17 深圳市麦谷科技有限公司 车辆电子围栏告警方法、装置、设备及存储介质
CN117082453B (zh) * 2023-10-17 2024-01-30 深圳市麦谷科技有限公司 车辆电子围栏告警方法、装置、设备及存储介质

Also Published As

Publication number Publication date
CN113076386A (zh) 2021-07-06

Similar Documents

Publication Publication Date Title
WO2022205642A1 (zh) 一种道路数据处理的方法、装置、电子设备、介质和程序
CN106323301B (zh) 一种道路情报的获取方法及装置
US20140164390A1 (en) Mining trajectory for spatial temporal analytics
CN112017447B (zh) 一种基于gps位置信息判定车辆逆行违规的方法及系统
US11244177B2 (en) Methods and systems for roadwork zone identification
Uduwaragoda et al. Generating lane level road data from vehicle trajectories using kernel density estimation
CN109612474B (zh) 一种地图道路匹配方法、装置、服务器及存储介质
US11062063B2 (en) System and method for generating vehicle travel data
US11353328B2 (en) Navigation system, apparatus and method for associating a probe point with a road segment
CN107403550B (zh) 公交路网数据采集方法、装置和终端设备
EP3207335B1 (en) Diverging and converging road geometry generation from sparse data
WO2018058888A1 (zh) 一种街景图像的识别方法、装置、服务器及存储介质
CN105806351A (zh) 一种道路信息推测方法及装置
CN107917716B (zh) 固定线路导航方法、装置、终端及计算机可读存储介质
CN110967018A (zh) 停车场定位方法、装置、电子设备及计算机可读介质
US11423660B2 (en) Methods and systems for determining emergency data for a vehicle
US20140044317A1 (en) Incremental network generation providing seamless network of large geographical areas
CN111854766A (zh) 一种道路信息确定方法、装置、电子设备及存储介质
CN113742437A (zh) 地图更新方法、装置、电子设备和存储介质
US11428534B2 (en) Method, apparatus, and computer program product for map matching location data to a map
Elleuch et al. Mining road map from big database of GPS data
CN114782926B (zh) 驾驶场景识别方法、装置、设备、存储介质和程序产品
CN102881182A (zh) 一种交通信息显示方法及其装置
Eftelioglu et al. RING-Net: Road inference from gps trajectories using a deep segmentation network
Cho et al. Multimedia sensor dataset for the analysis of vehicle movement

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21934291

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE