WO2020135325A1

WO2020135325A1 - Mobile device positioning method, device and system, and mobile device

Info

Publication number: WO2020135325A1
Application number: PCT/CN2019/127398
Authority: WO
Inventors: 邓欢军; 张硕
Original assignee: 阿里巴巴集团控股有限公司
Priority date: 2018-12-28
Filing date: 2019-12-23
Publication date: 2020-07-02
Also published as: CN111380529B; CN111380529A

Abstract

Provided are a mobile device positioning method, device and system, and a mobile device. Wherein the method comprises: collecting spatial point cloud data of a driving road through a three-dimensional space scanning device (S101), taking the point cloud data as the point cloud data of the current frame, and extracting road structured features and road strength features from the point cloud data (S103), estimating track data according to the track of the mobile device, and converting the road structured features and road strength features of an accumulated frame before the current frame into features in a coordinate system of the current frame (S105), then according to the converted road structured features and road strength features of the accumulated frame in the coordinate system, the road structured features and road strength features of the current frame, and road feature map data, determining position data of the mobile device. The processing method not only enhances the road feature expression capability, but also avoids the problem of inability to position when road structured features and road strength features cannot be obtained effectively; and thus, positioning accuracy and robustness can be effectively improved.

Description

Mobile equipment positioning method, device, system and mobile equipment

This application requires the priority of the Chinese patent application filed on December 28, 2018 with the application number 201811629344.3 and the invention titled "Mobile Device Location Method, Device, System, and Mobile Device", the entire contents of which are incorporated by reference in this application .

Technical field

The present application relates to the technical field of unmanned driving, and in particular to a mobile device positioning method, apparatus and system, and a mobile device.

Background technique

Autonomous driving technology is a major research hotspot in the field of automation in recent years. One of the core technologies of autonomous driving technology is the high-precision positioning of vehicles. In the process of automatic driving, it is usually necessary to achieve the centimeter-level accuracy of the position of the vehicle itself to ensure the accuracy of automatic driving and driving safety.

At present, a typical vehicle positioning method is a laser point cloud positioning method, and its processing procedure is as follows. Laser point cloud positioning generally requires pre-made maps (such as 2D or 3D maps), and then uses real-time point clouds and maps during vehicle travel to match, calculate the position and attitude of the lidar, and then pass the lidar and inertial measurement device (Inertial Measurement) Unit, IMU) external parameters, get the position and attitude of the IMU. In specific implementation, multiple matching methods can be applied, such as ICP method based on 3D point cloud matching, histogram filter matching positioning based on 2D probability map, and so on.

However, in the process of implementing the present invention, the inventor found that the technical solution has at least the following problems: 1) The vehicle positioning is based on only the structural features on both sides of the road extracted from the three-dimensional information of the radar scanning point cloud, which results in the vehicle positioning The accuracy is limited; 2) When structural features are lacking on both sides of the road, vehicle positioning cannot be performed, so the robustness of vehicle positioning is low.

Summary of the invention

This application provides a mobile device positioning system to solve the problems of low positioning accuracy and low robustness in the prior art. The present application additionally provides a mobile device positioning method and apparatus, and a mobile device.

This application provides a mobile device positioning system, including:

The server is used to send road feature map data to the mobile device;

The mobile device is configured to receive the road feature map data sent by the server; collect spatial point cloud data of the driving road through a three-dimensional space scanning device as point cloud data of the current frame; from the point cloud of the current frame Extract road structured features and road strength features from the data; estimate the trajectory data based on the trajectory of the mobile device, convert the road structured features and road strength features of at least one cumulative frame before the current frame into the Features under the coordinate system of the current frame; road structured features and road strength features of the at least one accumulated frame converted according to the coordinate system, road structured features and road strength features of the current frame, and road feature map data To determine the location data of the mobile device; wherein the road structured features and road intensity features of the at least one cumulative frame are extracted from the point cloud data of the at least one cumulative frame; the trajectory estimation trajectory The data is obtained by way of track estimation.

This application also provides a mobile device positioning method, including:

Receive road feature map data sent by the server;

Collect the spatial point cloud data of the driving road through the three-dimensional space scanning device as the point cloud data of the current frame;

Extract road structural features and road strength features from the point cloud data of the current frame;

Estimate the trajectory data based on the mobile device's trajectory, convert the road structured features and road strength features of at least one cumulative frame before the current frame into features in the coordinate system of the current frame; The road structural features and road strength features of the at least one cumulative frame are extracted from the point cloud data of the at least one cumulative frame; the track estimation track data is obtained by the track estimation method;

Determine the mobile device’s data based on the road structured features and road strength features of the at least one cumulative frame after the coordinate system conversion, the road structured features and road strength features of the current frame, and the road feature map data Location data.

This application also provides a mobile device positioning device, including:

The map data receiving unit is used to receive road feature map data sent by the server;

The point cloud data collection unit is used to collect the spatial point cloud data of the driving road through the three-dimensional space scanning device as the point cloud data of the current frame;

A current frame road feature extraction unit for extracting road structured features and road strength features from the point cloud data of the current frame;

A cumulative frame road feature conversion unit, used to estimate the trajectory data based on the trajectory of the mobile device, and convert the road structured features and road intensity features of at least one cumulative frame before the current frame into the current frame Features under the coordinate system; wherein, the road structural features and road strength features of the at least one cumulative frame are extracted from the point cloud data of the at least one cumulative frame; the track estimation track data passes the track Obtain by estimation method;

A position determining unit, configured to convert the road structured features and road strength features of the at least one accumulated frame according to the coordinate system, the road structured features and road strength features of the current frame, and the road feature map data, Determine location data of the mobile device.

This application also provides a mobile device, including:

Three-dimensional space scanning device;

Processor; and

The memory is used to store a program that implements the positioning method of the mobile device. After the device is powered on and runs the program of the positioning method of the mobile device through the processor, the following steps are performed: receiving road feature map data sent by the server; scanning by three-dimensional space The device collects the spatial point cloud data of the driving road as point cloud data of the current frame; extracts the road structure features and road strength features from the point cloud data of the current frame; estimates the track data according to the track of the mobile device , Converting the road structured features and road intensity features of at least one cumulative frame before the current frame into features in the coordinate system of the current frame; wherein, the road structured features and roads of the at least one cumulative frame The intensity feature is extracted from the point cloud data of the at least one cumulative frame; the trajectory estimation trajectory data is obtained by the trajectory estimation method; the road structure of the at least one cumulative frame after the coordinate system conversion Features and road strength features, road structured features and road strength features of the current frame, and road feature map data to determine location data of the mobile device.

This application also provides a mobile device positioning method, including:

Estimate the trajectory data according to the trajectory of the mobile device, and convert the road structural features and road strength features of at least one cumulative frame before the current frame into features in the coordinate system of the current frame;

Determine the location data of the mobile device according to the road structured features and road strength features of the at least one accumulated frame after the coordinate system conversion, the road structured features and road strength features of the current frame, and road feature map data ;

Wherein, the road structural features and road intensity features of the at least one cumulative frame are extracted from the point cloud data of the at least one cumulative frame; the track estimation track data is obtained by the track estimation method; The road feature map data includes feature data of the traveling road.

Optionally, the road intensity feature is extracted as follows:

Selecting road surface point cloud data from the point cloud data of the current frame;

Generate a road intensity image according to the intensity information of the pavement point cloud data;

Perform edge extraction on the road intensity image to obtain the road intensity feature.

Optionally, the structured features of the road are extracted in the following manner:

According to the feature constraint information of the road structured features, road structured features are extracted from the spatial point cloud data.

Optional, also includes:

Obtaining position data corresponding to the current frame according to the track estimation track data of the mobile device and time data corresponding to the current frame; and, estimating the track data and the at least one accumulated frame according to the track Acquiring the time data corresponding to the accumulated frame later in the middle time, and acquiring the position data corresponding to the accumulated frame later in the time;

Determine whether the first distance between the position data corresponding to the current frame and the position data corresponding to the cumulative frame later in time is greater than or equal to a first distance threshold;

If the result of the above judgment is yes, enter the road structured feature and road strength feature of the at least one cumulative frame converted according to the coordinate system, the road structured feature and road strength feature of the current frame, and the road feature Map data and determine location data of the mobile device; and, use the current frame as the accumulated frame.

Optionally, the method further includes:

If the above judgment result is no, the position data of the mobile device is determined according to the road structured feature and road intensity feature of the at least one accumulated frame after the coordinate system conversion, and the road feature map data.

Optional, also includes:

Obtain the number of features of the road structured features and road strength features of the current frame as the first number of features;

Determine whether the number of the first features is greater than or equal to the threshold of the number of the first features;

If the above judgment result is yes, enter the first feature quantity according to the road structured feature and road strength feature of the at least one accumulated frame after the coordinate system conversion, the road structured feature and road strength feature of the current frame And road feature map data to determine the location data of the mobile device; and, use the current frame as the accumulated frame.

Optionally, the method further includes:

Optional, also includes:

Obtaining the position data corresponding to the current frame according to the track estimation track data and the time data corresponding to the current frame; and, according to the track estimation track data and the time dependence in the at least one accumulated frame The time data corresponding to the later accumulated frame, and acquiring the position data corresponding to the later accumulated frame;

Taking the distance between the position data corresponding to the current frame and the position data corresponding to the cumulative frame later in time as the first distance; and obtaining the number of features of the road structured features and road strength features of the current frame, As the first feature quantity;

Determine whether the first distance is greater than or equal to a first distance threshold, and whether the number of first features is greater than or equal to a first feature quantity threshold;

Optionally, after the current frame is used as the accumulated frame, the method further includes:

Acquiring a second feature quantity, the second feature quantity being the total feature quantity of the current frame and the at least one cumulative frame; and, acquiring the first between the current frame and the start frame of the at least one cumulative frame Two distance

If the second feature quantity is greater than the second feature quantity threshold and the second distance is greater than the second distance threshold, the start frame is deleted from the at least one cumulative frame until the second feature quantity is less than or equal to the The second feature quantity threshold, and/or the second distance is less than or equal to the second distance threshold.

Optionally, the trajectory data is estimated according to the trajectory of the mobile device, and the road structural features and road strength features of the at least one cumulative frame are converted to features in the coordinate system of the current frame, include:

Obtaining the position data corresponding to the at least one cumulative frame according to the time data corresponding to the at least one accumulated frame and the track estimation track data respectively; and according to the track estimation and the current track data corresponding to the at least one accumulation frame Obtaining the time data corresponding to the frame to obtain the position data corresponding to the current frame;

For each of the accumulated frames, according to the position data corresponding to the accumulated frame and the position data corresponding to the current frame, the road structured features and road strength features of the accumulated frame are converted into the coordinate system at the current frame Features.

Optionally, the strength characteristics of the road include: strength characteristics of a lane line, strength characteristics of a steering sign, and strength characteristics of a crosswalk.

This application also provides a mobile device positioning device, including:

A cumulative frame road feature conversion unit, used to estimate the trajectory data based on the trajectory of the mobile device, and convert the road structured features and road intensity features of at least one cumulative frame before the current frame into the current frame Features in the coordinate system;

The position determining unit is configured to determine the location based on the road structured features and road strength features of the at least one accumulated frame after the coordinate system conversion, the road structured features and road strength features of the current frame, and the road feature map data Describe the location data of mobile devices;

Optional, also includes:

A position obtaining unit, configured to obtain position data corresponding to the current frame based on the track estimated track data and time data corresponding to the current frame; and, based on the track estimated track data and the at least Acquiring time data corresponding to a cumulative time frame later in a cumulative frame, and acquiring position data corresponding to the cumulative time frame later than the time;

A first data statistical unit, configured to use the distance between the position data corresponding to the current frame and the position data corresponding to the cumulative frame later in time as the first distance; and, obtain the road structure feature of the current frame The number of features with road strength features is used as the first number of features;

A judging unit, used to judge whether the first distance is greater than or equal to a first distance threshold, and whether the number of first features is greater than or equal to a first feature quantity threshold; if so, start the position determining unit;

A cumulative frame increasing unit is used to use the current frame as the cumulative frame.

Optional, also includes:

A second data statistics unit, configured to obtain a second feature quantity, the second feature quantity being the total feature quantity of the current frame and the at least one accumulated frame; and, obtaining the current frame and the at least one accumulated The second distance between the start of the frame;

A cumulative frame deletion unit, configured to delete the start frame from the at least one cumulative frame until the second feature number is greater than the second feature number threshold and the second distance is greater than the second distance threshold, until the The second feature quantity is less than or equal to the second feature quantity threshold, and/or the second distance is less than or equal to the second distance threshold.

This application also provides a mobile device, including:

Three-dimensional space scanning device;

Processor; and

The memory is used to store a program for implementing the positioning method of the mobile device. After the device is powered on and the program for the positioning method of the mobile device is run through the processor, the following steps are performed: collecting spatial point cloud data of the driving road through a three-dimensional space scanning device , As point cloud data of the current frame; extracting road structure features and road strength features from the point cloud data of the current frame; estimating trajectory data based on the trajectory of the mobile device, at least The road structured features and road strength features of one cumulative frame are converted to features in the coordinate system of the current frame; according to the road structured features and road strength features of the at least one accumulated frame converted from the coordinate system, the The road structured feature and road intensity feature of the current frame, and the road feature map data to determine the location data of the mobile device; wherein, the road structured feature and road intensity feature of the at least one cumulative frame are selected from the at least one It is extracted from the point cloud data of the accumulated frame; the trajectory estimation trajectory data is obtained by the trajectory estimation method; and the road feature map data includes feature data of the traveling road.

The present application also provides a computer-readable storage medium having instructions stored therein, which when executed on a computer, causes the computer to execute the various methods described above.

The present application also provides a computer program product including instructions, which, when run on a computer, causes the computer to execute the various methods described above.

Compared with the prior art, this application has the following advantages:

The mobile device positioning system provided by an embodiment of the present application receives road feature map data sent by a server through a mobile device, uses a three-dimensional space scanning device to collect spatial point cloud data of a driving road, and extracts road structure features from the point cloud data And road strength characteristics, and then estimate the trajectory data according to the track of the mobile device, convert the road structured features and road strength features of the accumulated frame before the current frame into the features in the coordinate system of the current frame, and then according to the coordinates After the conversion, the road structured features and road strength features of the accumulated frame, the road structured features and road strength features of the current frame, and the road feature map data determine the location data of the mobile device; this processing method, Therefore, the vehicle positioning is combined with the structural features and road strength features on both sides of the road accumulated in multiple frames, which enhances the ability to express road features; therefore, the positioning accuracy can be effectively improved. At the same time, this processing method can avoid the problem of inlocation that cannot be obtained when the structured features or strength features of the road cannot be obtained effectively; therefore, the robustness of positioning can be effectively improved. At the same time, because the positioning can be performed when each frame of point cloud data is obtained, thereby real-time positioning is achieved; therefore, the real-time nature of vehicle positioning can be effectively improved.

BRIEF DESCRIPTION

1 is a flowchart of an embodiment of a mobile device positioning method provided by this application;

2 is a schematic diagram of structured feature points on both sides of a road according to an embodiment of a mobile device positioning method provided by this application;

3 is a schematic diagram of a road intensity image of an embodiment of a mobile device positioning method provided by this application;

4 is a schematic diagram of road strength characteristics of an embodiment of a mobile device positioning method provided by this application;

5 is a specific flowchart of a multi-frame accumulation feature of an embodiment of a mobile device positioning method provided by this application;

6 is a schematic diagram of a multi-frame accumulation feature of an embodiment of a mobile device positioning method provided by this application;

7 is a specific flowchart of an embodiment of a mobile device positioning method provided by this application;

8 is another schematic diagram of the multi-frame accumulation feature of an embodiment of a mobile device positioning method provided by this application;

9 is a schematic structural diagram of an embodiment of a mobile device positioning apparatus provided by this application;

10 is a specific schematic diagram of an embodiment of a mobile device positioning apparatus provided by this application;

11 is another specific schematic diagram of an embodiment of a mobile device positioning apparatus provided by this application;

12 is a schematic diagram of an embodiment of a mobile device provided by this application;

13 is a schematic diagram of an embodiment of a mobile positioning system provided by the present application;

14 is a flowchart of an embodiment of a mobile device positioning method provided by this application;

15 is a schematic structural diagram of an embodiment of a mobile device positioning apparatus provided by this application;

16 is a schematic diagram of an embodiment of a mobile device provided by the present application.

detailed description

In the following description, many specific details are set forth in order to fully understand the application. However, this application can be implemented in many other ways than those described here. Those skilled in the art can make similar promotion without violating the connotation of this application, so this application is not limited by the specific implementation disclosed below.

In the present application, a method, apparatus and system for positioning a mobile device and a mobile device are provided. The mobile devices include, but are not limited to, unmanned vehicles, mobile robots, and other mobile devices. In the following embodiments, a vehicle will be taken as an example, and various schemes will be described in detail one by one.

First embodiment

Please refer to FIG. 1, which is a flowchart of an embodiment of a mobile device positioning method provided by the present application. The execution body of the method includes a mobile device positioning apparatus, which may be deployed on a mobile device. A mobile device positioning method provided by this application includes:

Step S101: Collect the spatial point cloud data of the driving road through the three-dimensional space scanning device as point cloud data of the current frame.

The method provided in the embodiment of the present application obtains the spatial coordinates of each sampling point on the surface of the space object around the road through the three-dimensional space scanning device installed on the vehicle during the driving process of the vehicle, and obtains a set of points, each The massive point data obtained by the second scan is called a frame of point cloud (Point Cloud) data. In this embodiment, the frame of point cloud data collected at the current moment is called the point cloud data of the current frame. Through the point cloud data, the surface of the scanned object is recorded in the form of points. Each point contains three-dimensional coordinates, and some may contain color information (RGB) or reflection intensity information (Intensity). With point cloud data, the target space can be expressed under the same spatial reference system.

The three-dimensional space scanning device may be a laser radar (Light Detection And Ranging, Lidar), which performs laser detection and measurement through laser scanning to obtain information on the driving road, and the measured data is a digital surface model (Digital Surface) Model, DSM) discrete point representation. In specific implementation, 16-line, 32-line, 64-line and other multi-line lidars can be used. Radars with different numbers of laser beams collect point cloud data at a different frame rate (Frame, Rate). For example, 16, 32 lines generally collect 10 frames per second. Point cloud data. The three-dimensional space scanning device may also be a three-dimensional laser scanner or a photographic scanner.

After the spatial point cloud data of the driving road is collected by the three-dimensional space scanning device, the next step can be entered to extract road features from the spatial point cloud data of the current frame.

Step S103: Extract road structure features and road strength features from the point cloud data of the current frame.

The method provided in the embodiment of the present application performs vehicle positioning according to road features and road feature maps during vehicle travel. To locate the vehicle based on the road features and road feature maps of the vehicle while driving, the road features must first be extracted from the point cloud data of the current frame obtained in the previous step.

The road features include road structured features and road strength features. Among them, the structured features of the road can reflect the structured information on both sides of the road, including but not limited to: roadside features (road roads, etc.), wall features, and so on. Road strength characteristics refer to edge characteristics and can reflect road marking information. Road strength features, including but not limited to: lane line strength features, turn sign strength features, pedestrian crossing strength features, etc.

The structured feature of the road may be extracted from the spatial three-dimensional information included in the point cloud data of the current frame. In this embodiment, the road structured feature is extracted in the following manner: According to the feature constraint information of the road structured feature, the road structured feature is extracted from the point cloud data of the current frame.

The feature constraint information includes feature constraint rules for road structured feature points. Different road structured features correspond to different feature constraint rules, such as roads and walls are both road structured features, but the two correspond to different feature constraint rules.

Please refer to a diagram in FIG. 2, which is a schematic diagram of a road tooth feature point according to an embodiment of a mobile device positioning method provided by this application. It can be seen from the figure a in Figure 2 that the constraint rules of the feature points of the road teeth include: 1) the starting point of the road teeth forms an angle of 90 degrees with the adjacent points, and the end point forms an angle of 90 degrees with the adjacent points; 2) the height of the road (Start point to end point) about 10 cm; 3) The points on the road teeth are on a straight line, and the height of adjacent points increases. It can be seen that the points that meet the above constraint rules in the spatial point cloud data can be used as road feature points.

Please refer to FIG. 2 b, which is a schematic diagram of the feature points of the wall surfaces on both sides of the road according to an embodiment of a mobile device positioning method provided by this application. As can be seen from the figure b in Figure 2, the constraint rules for the feature points of the wall surface include: the wall point is projected on the ground (xy plane) and then on a straight line, and the distance from the point to the straight line

In the spatial point cloud data, the points that meet the above constraint rules can be used as the wall feature points.

The road intensity feature can be extracted from the laser intensity information included in the point cloud data of the current frame.

In one example, the road intensity feature may be extracted by the following steps: 1) selecting road surface point cloud data from the point cloud data of the current frame; 2) generating road intensity according to the intensity information of the road surface point cloud data Image; 3) Perform edge extraction on the road intensity image to obtain the road intensity feature.

To extract road intensity features from the spatial point cloud data is to obtain edge information based on pavement point cloud intensity information. Therefore, first obtain pavement point clouds from radar point clouds and generate intensity using pavement point clouds intensity information Image, as shown in Figure 3, and then extract the edge of the intensity image to obtain the edge information of road signs such as lane lines, turning signs, pedestrian crossings, as shown in Figure 4.

In another example, the road intensity feature can also be extracted in the following manner: that is, instead of generating an intensity image, the edge extraction is directly based on the intensity information of the point cloud, which may be directly using a phase on a line. Gradient calculation is performed on neighboring points to extract edge points, that is, the road surface point cloud data is first selected for each frame, and then the adjacent points are directly used to perform gradient calculation on a line to extract edge points.

Step S105: According to the trajectory estimation trajectory data of the mobile device, the road structured features and road strength features of at least one cumulative frame before the current frame are converted into features in the coordinate system of the current frame.

The trajectory estimation trajectory data includes position data of the vehicle at different times during driving. The trajectory estimation trajectory data is obtained by the trajectory estimation method, for example, the following trajectory estimation method can be used: the odometer is used to measure the driving speed of the vehicle, and the integration can be used to measure the distance traveled by the vehicle; or, the IMU is used to measure the vehicle The linear acceleration and angular speed of driving can also be used to calculate the speed and angle change (heading) through integration. Since the trajectory estimation method is a relatively mature existing technology, it will not be repeated here.

The method provided in the embodiment of the present application needs to combine the structured features and road strength features on both sides of the road accumulated in multiple frames, and the vehicle's trajectory estimation trajectory data to locate the vehicle. First, the trajectory needs to be estimated based on the vehicle's trajectory The data converts the road features of at least one accumulated frame before the current frame into the features in the current frame coordinate system. The road structure feature and road intensity feature of the at least one cumulative frame are extracted from the point cloud data of the at least one cumulative frame. It can be seen from this that the function of the trajectory estimation trajectory data includes that the road features extracted from the radar point cloud at the corresponding moment on one trajectory can be stitched and accumulated according to the trajectory.

In this embodiment, step S105 may include the following sub-steps: 1) acquiring position data corresponding to the at least one cumulative frame according to the time data corresponding to the at least one cumulative frame and the estimated track data respectively ; And, based on the trajectory estimated trajectory data and the time data corresponding to the current frame, obtaining position data corresponding to the current frame; 2) For each accumulated frame, according to the position data corresponding to the accumulated frame The position data corresponding to the current frame converts the road structured features and road intensity features of the accumulated frame into features in the coordinate system of the current frame.

1) Obtain position data corresponding to the at least one cumulative frame according to the time data corresponding to the at least one accumulated frame and the track estimation track data respectively; and, estimate the track data and the corresponding position according to the track Acquiring the time data corresponding to the current frame to obtain the position data corresponding to the current frame.

The trajectory estimation trajectory data includes position information of the vehicle at different times during driving. In this embodiment, according to the time data corresponding to each accumulated frame, the position data corresponding to the matching time is obtained as the position data of the accumulated frame by matching with the time data in the track estimation track data. Similarly, according to the time data corresponding to the current frame, the position data corresponding to the matching moment may be obtained as the position data of the current frame by matching with the time data in the track estimation track data.

2) For each accumulated frame, according to the position data corresponding to the accumulated frame and the position data corresponding to the current frame, convert the road structured features and road intensity features of the accumulated frame into Features in the coordinate system.

After obtaining each accumulated frame and the current frame divided into corresponding position data, for each accumulated frame, you can obtain the rotation matrix and translation matrix of the accumulated frame and the current frame, etc.; then through matrix operation, the accumulated The road structured features and road strength features of the frame are converted into features in the coordinate system of the current frame, and the road features corresponding to the current frame are merged together to form the road features corresponding to the current frame.

In one example, multi-frame accumulation adopts an adaptive sliding window to accumulate the feature points of the multi-frame scan, and adjusts the window size to maintain an appropriate amount of road feature points according to the accumulated feature number and the accumulated motion distance. By adopting this processing method, the number of accumulated multi-frame features is controlled, and vehicle positioning is performed based on the limited accumulated multi-frame features; therefore, the computational complexity can be effectively reduced, thereby improving positioning efficiency. At the same time, it can also effectively save computing resources, thereby reducing hardware costs.

Please refer to FIG. 5, which is a specific flowchart of a multi-frame cumulative feature of an embodiment of a mobile device positioning method provided by this application. In this embodiment, after using the current frame as an accumulated frame, the method further includes the following steps:

Step S501: Acquire a second feature quantity; and acquire a second distance between the current frame and the start frame of the at least one accumulated frame.

The second feature number refers to the sum of the feature number of the current frame and the feature number of the at least one cumulative frame, that is, the cumulative feature number.

The method provided in this embodiment of the present application can accumulate road features of multiple frames up to the current frame, and use the distance between the current frame and the start frame of the accumulated frame (that is, the first accumulated frame) as the second distance. That is, the second distance reflects the distance between the current position of the vehicle and the corresponding position of the first accumulated frame.

Step S503: If the second feature quantity is greater than the second feature quantity threshold and the second distance is greater than the second distance threshold, delete the start frame from the at least one cumulative frame until the second feature quantity Less than or equal to the second feature quantity threshold, and/or the second distance is less than or equal to the second distance threshold.

After obtaining the second feature number and the second distance, the second feature number can be compared with the second feature number threshold, and the second distance and the second distance threshold can be compared, if the second feature number is greater than the second feature number Threshold and the second distance is greater than the second distance threshold, the start frame is deleted from the at least one accumulated frame, that is, the oldest accumulated frame. If one accumulated frame is deleted from the sliding window, the above condition is still satisfied , Then continue to delete the oldest accumulated frame until the second feature quantity is less than or equal to the second feature quantity threshold, or the second distance is less than or equal to the second distance threshold, or the second feature quantity is less than or equal to the second feature quantity A threshold, and the second distance is less than or equal to a second distance threshold.

The second feature quantity threshold and the second distance threshold can be set according to business needs, for example, the second feature quantity threshold is set to several hundred or tens of thousands, and the second distance threshold is set to several meters or tens of meters and many more.

The larger the second feature quantity threshold and the second distance threshold are, the more feature points are involved in the positioning calculation, so the calculation complexity will increase, but because there are more feature points, the positioning accuracy is higher. During specific implementation, the second feature quantity threshold and the second distance threshold may be determined according to business requirements.

Please refer to FIG. 6, which is a schematic diagram of a multi-frame cumulative feature of an embodiment of a mobile device positioning method provided by this application. It can be seen from FIG. 6 that after adding a new frame (current frame) P _{k+w+1 to the} sliding window, if the number of second features is determined

Greater than the second feature quantity threshold nThreshold, and the second distance

If it is greater than the second distance threshold dThreshold, the kth radar scan frame is deleted from the end of the sliding window. If the number of second features continues to be determined

If it is greater than the second distance threshold dThreshold, then the k+1th radar scan frame is deleted from the end of the sliding window, and the window size after deleting the frame is w-1 frames.

After obtaining the road structured features and road strength features of the accumulated frame after coordinate system conversion, the road structured features and road strength features of the current frame, that is, after obtaining the multi-frame accumulated road features, You can proceed to the next step to determine the location data of the vehicle based on the multi-frame accumulated road features and road feature map data.

Step S107: Determine the mobile device according to the road structured features and road strength features of the at least one accumulated frame after the coordinate system conversion, the road structured features and road strength features of the current frame, and road feature map data Location data.

The method provided in the embodiment of the present application determines the vehicle position according to the multi-frame accumulated road feature and road feature map data through the Monte Carlo localization (MCL) algorithm, and can multi-frame accumulated road feature and road feature map The data is matched, and the position data of the feature matching is used as the current position data of the vehicle. The positioning result includes (x, y, yaw (heading angle)) of the vehicle position in the xy plane coordinate system. Since the MCL algorithm is a relatively mature existing technology, it will not be repeated here.

Road feature map, also known as a priori feature map, is a feature map built based on pre-collected road feature data. The map includes at least the structural features on both sides of the road and the road strength features, such as roads, telephone poles, and walls. Structural features and strength features (edge information) of lane lines, turn signs and crosswalks on the road.

The road feature map data can be generated by integrating the road features of all regions on the server side, and the mobile device positioning device can download the map data from the server side and download the updated map from the server again when the map data is updated Data, and update the old map data local to the vehicle.

Please refer to FIG. 7, which is a specific flowchart of an embodiment of a mobile device positioning method provided by this application. In one example, the method may further include the following steps:

Step S701: Obtain location data corresponding to the current frame according to the trajectory estimated trajectory data and time data corresponding to the current frame; and, based on the trajectory estimated trajectory data and the at least one cumulative frame Time data corresponding to the cumulative frame later in the time, and acquiring position data corresponding to the cumulative frame later in the time.

The cumulative frame at a later time may be any cumulative frame at a later time in the at least one cumulative frame, or may be the last cumulative frame in the at least one cumulative frame, that is: multiple cumulative frames The last frame in the frame.

Step S702: use the distance between the position data corresponding to the current frame and the position data corresponding to the cumulative frame later in time as the first distance; and obtain the road structure characteristics and road intensity characteristics of the current frame The number of features serves as the first number of features.

Step S703: determine whether the first distance is greater than or equal to a first distance threshold, and whether the first feature quantity is greater than or equal to a first feature quantity threshold.

The first distance threshold may be set according to business requirements, for example, it may be set to 10 cm, that is, when the vehicle driving interval does not reach 10 cm, there is no need to combine the road features of the current frame for positioning.

The first feature quantity threshold can be set according to business requirements, for example, it can be set to tens or hundreds of feature points, that is: when the road feature of the current frame does not reach tens or hundreds of feature points, no combination is required Car localization based on the road features of the current frame.

As shown in FIG. 7, when the first distance is greater than or equal to the first distance threshold and the first feature quantity is greater than or equal to the first feature quantity threshold, step S107 may be performed to combine the road of the accumulated frame and the current frame Features to locate.

After step S107 is executed, the following steps must be performed:

Step S704: Use the current frame as the accumulated frame.

During specific implementation, if the first distance is less than the first distance threshold and/or the first feature quantity is less than the first feature quantity threshold, the following steps are performed:

Step S705: Determine the location data of the mobile device according to the road structured feature and road intensity feature of the at least one accumulated frame after the coordinate system conversion, and the road feature map data.

In this case, the current frame may not need to be the accumulated frame. For example, according to the trajectory estimation trajectory data, it is determined that the position corresponding to the time t _{cur of the} current frame is l _cur , the position l _pre corresponding to the time t _pre of the last frame in the accumulated frame, and the first distance is d = l _cur- l _pre , if d <the first distance threshold d _th , there is no need to combine the road features of the current frame for positioning, as long as the positioning is based on the road features of the accumulated frame.

As another example, when the road features of the current road on which the vehicle is traveling are few or even absent, such as no roads, walls, road signs, etc., there is no need to combine the road features of the current frame for positioning, as long as the road features of the cumulative frame are used That's it.

Please refer to FIG. 8, which is another schematic diagram of the multi-frame accumulation feature of an embodiment of a vehicle positioning method provided by the present application. It can be seen from Fig. 8 that the sliding window has a size of w frames before adding a new frame (current frame), including the feature sets P _k , P _k+1 , ..., P corresponding to the k th frame to the k+w frame, respectively _k+w if the total number of features of the latest frame (current frame) num(P _k+w+1 ) is greater than or equal to the first feature quantity threshold, and the movement distance d between the latest frame and the previous window frame is greater than or equal to The first distance threshold (for example, 0.1m), the frame is increased, and the window size is w+1, at this time, the vehicle can be positioned according to the characteristics in the window.

The method provided by the embodiment of the present application adopts the steps shown in FIG. 7, which can avoid the problem that the vehicle moves a small distance and causes many duplicate features, and can avoid the problem of insufficient effective feature update; therefore, it can be effectively saved Computing resources effectively improve positioning accuracy and precision, and ensure real-time positioning of vehicles.

In another example, the method provided in this embodiment of the present application determines the position corresponding to the current frame and the position corresponding to the last frame in the accumulated frame by estimating the trajectory data based on the vehicle's track, if the current frame corresponds to If the first distance between the position and the position corresponding to the last frame in the cumulative frame is greater than or equal to the first distance threshold, then the road structured feature and the road intensity feature of the at least one cumulative frame converted according to the coordinate system , The road structured feature and the road intensity feature of the current frame, and the road feature map data, to determine the location data of the vehicle; if the first distance is less than the first distance threshold, according to the coordinate system after conversion The road structured feature and road intensity feature data of the at least one cumulative frame determine the position data of the vehicle; this processing method is such that when the distance traveled by the vehicle is greater than or equal to the first distance threshold, the combined multi-frame cumulative Road features and road features of the current frame are used for vehicle positioning. When the distance traveled by the vehicle is less than the first distance threshold, only the road features accumulated in multiple frames are used for vehicle positioning; therefore, it can effectively save computing resources and ensure timely vehicle positioning .

For example, according to the trajectory estimation trajectory data, it is determined that the position corresponding to the time t _{cur of the} current frame is l _cur , the position l _pre corresponding to the time t _pre of the last frame in the accumulated frame, and the first distance is d = l _cur- l _pre , if d<the first distance threshold d _th , there is no need to locate the road features of the current frame, as long as the positioning is based on the road features of the accumulated frame; if d>=d _th , the accumulated frame and the current frame are combined To locate the road features.

In yet another example, the method provided in this embodiment of the present application provides that if the first feature quantity of the road structured feature and the road strength feature of the current frame is greater than or equal to the first feature quantity threshold, then Road structured features and road strength features of the cumulative frame, road structured features and road strength features of the current frame, and road feature map data to determine vehicle position data; if the number of first features is less than the number of A threshold for the number of features, the vehicle position data is determined according to the road structured features and road strength features of the at least one cumulative frame after the coordinate system conversion, and the road feature map data; this processing method makes the vehicle travel on the road When the position of more features is combined with the road features of the current frame to locate the vehicle, to avoid positioning each frame in combination with the road features of the current frame when the vehicle is driving at a position with fewer road features; therefore, it can effectively save computing resources, At the same time effectively improve the positioning accuracy.

For example, when there are few or no road features of the current road on which the vehicle is traveling, such as no roads, walls, road signs, etc., there is no need to locate the road features of the current frame, as long as the location is based on the road features of the accumulated frame. However, only when there are many current road features, the road features of the accumulated frame and the current frame are combined for positioning.

It can be seen from the above embodiments that the mobile device positioning method provided by the embodiments of the present application collects spatial point cloud data of a driving road through a three-dimensional space scanning device, and extracts road structural features and road strength features from the point cloud data. Estimate the trajectory data according to the track of the mobile device, and convert the road structured features and road strength features of the accumulated frame before the current frame into features in the coordinate system of the current frame, and then according to the converted The road structured features and road strength features of the accumulated frame, the road structured features and road strength features of the current frame, and the road feature map data determine the location data of the mobile device; this processing method makes it possible to combine multi-frame accumulated The structured features and road strength features on both sides of the road are used to locate the mobile device, which enhances the ability to express road features; therefore, the positioning accuracy can be effectively improved. At the same time, this processing method can avoid the problem of inlocation that cannot be obtained when the structured features of the road or the features of the strength of the road cannot be obtained effectively; therefore, the positioning robustness can be effectively improved. At the same time, because the positioning can be performed when each frame of point cloud data is obtained, thereby real-time positioning is achieved; therefore, the real-time nature of vehicle positioning can be effectively improved.

In the above embodiments, a mobile device positioning method is provided, and correspondingly, the present application also provides a mobile device positioning apparatus. This device corresponds to the embodiment of the above method.

Second embodiment

Please refer to FIG. 9, which is a schematic diagram of an embodiment of a mobile device positioning apparatus according to this application. Since the device embodiment is basically similar to the method embodiment, the description is relatively simple, and the relevant part can be referred to the description of the method embodiment. The device embodiments described below are only schematic.

This application additionally provides a mobile device positioning device, including:

The point cloud data collection unit 901 is used to collect the spatial point cloud data of the driving road through the three-dimensional space scanning device as the point cloud data of the current frame;

The current frame road feature extraction unit 903 is used to extract road structured features and road intensity features from the point cloud data of the current frame;

The cumulative frame road feature conversion unit 905 is configured to convert the road structured feature and road intensity feature of at least one cumulative frame before the current frame into the current frame based on the estimated trajectory data of the trajectory of the mobile device Features in the coordinate system of

The position determining unit 907 is configured to determine the road structured features and road strength features of the at least one accumulated frame after the coordinate system conversion, the road structured features and road strength features of the current frame, and the road feature map data Location data of the mobile device;

Please refer to FIG. 10, which is a specific schematic diagram of an embodiment of a mobile device positioning apparatus according to this application. Optional, also includes:

A position obtaining unit 1001, configured to obtain position data corresponding to the current frame based on the track estimated track data and time data corresponding to the current frame; and, based on the track estimated track data and the Acquiring time data corresponding to a cumulative frame at a later time in at least one cumulative frame, and acquiring position data corresponding to the cumulative frame at a later time;

The first data statistics unit 1002 is configured to use the distance between the position data corresponding to the current frame and the position data corresponding to the cumulative frame later in time as the first distance; and, obtain the road structure of the current frame The number of features and road strength features are used as the first number of features;

The judging unit 1003 is used to judge whether the first distance is greater than or equal to the first distance threshold and whether the first feature quantity is greater than or equal to the first feature quantity threshold; if so, start the position determining unit 907;

The cumulative frame increasing unit 1004 is configured to use the current frame as the cumulative frame.

Please refer to FIG. 11, which is a specific schematic diagram of an embodiment of a mobile device positioning apparatus according to this application. Optional, also includes:

A second data statistical unit 1101, configured to obtain a second feature quantity, the second feature quantity being the total feature quantity of the current frame and the at least one accumulated frame; and, obtaining the current frame and the at least one The second distance between the start frames of the accumulated frames;

The cumulative frame deleting unit 1102 is configured to delete the start frame from the at least one cumulative frame until the second feature number is greater than the second feature quantity threshold and the second distance is greater than the second distance threshold, until all The second feature quantity is less than or equal to the second feature quantity threshold, and/or the second distance is less than or equal to the second distance threshold.

It can be seen from the above embodiments that the mobile device positioning apparatus provided by the embodiments of the present application collects spatial point cloud data of the driving road through a three-dimensional space scanning device, and extracts road structural features and road strength features from the point cloud data, and then Estimate the trajectory data according to the track of the mobile device, and convert the road structured features and road strength features of the accumulated frame before the current frame into features in the coordinate system of the current frame, and then according to the converted The road structured features and road strength features of the accumulated frame, the road structured features and road strength features of the current frame, and the road feature map data determine the location data of the mobile device; this processing method makes it possible to combine multi-frame accumulated The structured features and road strength features on both sides of the road are used to locate the mobile device, which enhances the ability to express road features; therefore, the positioning accuracy can be effectively improved. At the same time, this processing method can avoid the problem of inlocation that cannot be obtained when the structured features or strength features of the road cannot be obtained effectively; therefore, the robustness of positioning can be effectively improved. At the same time, because the positioning can be performed when each frame of point cloud data is obtained, thereby real-time positioning is achieved; therefore, the real-time nature of vehicle positioning can be effectively improved.

Third embodiment

Please refer to FIG. 12, which is a schematic diagram of an embodiment of a mobile device according to this application. Since the device embodiment is basically similar to the method embodiment, the description is relatively simple, and the relevant part can be referred to the description of the method embodiment. The device embodiments described below are only schematic.

A mobile device in this embodiment, the device includes: a three-dimensional space scanning device 1201, a processor 1202, and a memory 1203.

The memory is used to store a program for implementing a positioning method for a mobile device. After the device is powered on and the program for the positioning method for a mobile device is run through the processor, the following steps are performed: the spatial points of the driving road are collected by a three-dimensional space scanning device Cloud data as point cloud data of the current frame; extracting road structured features and road strength features from the point cloud data of the current frame; estimating trajectory data based on the track of the mobile device, before the current frame The road structured features and road strength features of at least one cumulative frame of the are converted to features in the coordinate system of the current frame; the road structured features and road strength features of the at least one accumulated frame converted according to the coordinate system, The road structured feature and road intensity feature of the current frame, and the road feature map data, to determine the location data of the mobile device; wherein, the road structured feature and road intensity feature of the at least one cumulative frame, from the It is extracted from the point cloud data of at least one accumulated frame; the trajectory estimation trajectory data is obtained by the trajectory estimation method; and the road feature map data includes feature data of the traveling road.

The processor 1202 may use a main processor chip (vehicle CPU) of the vehicle machine. The chip may be a circuit module that integrates a variety of electronic components on a silicon board to achieve a specific function. It is the most important part of the electronic equipment, which bears the functions of calculation, storage and control.

Fourth embodiment

Please refer to FIG. 13, which is a schematic structural diagram of an embodiment of a mobile device positioning system according to this application. Since the system embodiment is basically similar to the method embodiment, the description is relatively simple, and the relevant part can be referred to the description of the method embodiment. The system implementation embodiments described below are only schematic.

A mobile device positioning system in this embodiment includes a server 1301 and a mobile device 1302. The mobile devices include, but are not limited to, vehicles, mobile robots, and other mobile devices.

The server 1301 is configured to send road feature map data to the mobile device 1302.

The mobile device 1302 is configured to receive the road feature map data sent by the server 1301; collect the spatial point cloud data of the driving road through a three-dimensional space scanning device as point cloud data of the current frame; from the current frame Extract road structured features and road strength features from the point cloud data; estimate track data based on the mobile device’s trajectory, convert the road structured features and road strength features of at least one cumulative frame before the current frame into Features under the coordinate system of the current frame; road structured features and road strength features of the at least one cumulative frame converted according to the coordinate system, road structured features and road strength features of the current frame, and road features Map data to determine the location data of the mobile device.

Wherein, the road structural features and road intensity features of the at least one cumulative frame are extracted from the point cloud data of the at least one cumulative frame; the track estimation track data is obtained by the track estimation method.

For the road feature map data, the server 1301 can integrate the road features of all regions to generate map data. The mobile device 1302 can download the map data from the server 1301 and download the updated map from the server 1301 again when the map data is updated. Data and update the old map data locally on the mobile device.

It can be seen from the above embodiments that the mobile device positioning system provided by the embodiments of the present application collects the spatial point cloud data of the driving road through a three-dimensional space scanning device, and extracts the road structured features and road strength features from the point cloud data, and then Estimate the trajectory data according to the track of the mobile device, and convert the road structured features and road strength features of the accumulated frame before the current frame into features in the coordinate system of the current frame, and then according to the converted The road structured features and road strength features of the accumulated frame, the road structured features and road strength features of the current frame, and the road feature map data determine the location data of the mobile device; this processing method makes it possible to combine multi-frame accumulated The structured features and road strength features on both sides of the road are used to locate the mobile device, which enhances the ability to express road features; therefore, the positioning accuracy can be effectively improved. At the same time, this processing method can avoid the problem of inlocation that cannot be obtained when the structured features or strength features of the road cannot be obtained effectively; therefore, the robustness of positioning can be effectively improved. At the same time, because the positioning can be performed when each frame of point cloud data is obtained, thereby real-time positioning is achieved; therefore, the real-time nature of vehicle positioning can be effectively improved.

Fifth embodiment

Please refer to FIG. 14, which is a schematic flowchart of an embodiment of a mobile device positioning method according to this application. Since the method embodiment is basically similar to the system embodiment, the description is relatively simple, and the relevant part can be referred to the description of the system embodiment. The method embodiments described below are only schematic.

A mobile device positioning method in this embodiment includes the following steps:

Step S1401: Receive road feature map data sent by the server;

Step S1403: Collect the spatial point cloud data of the driving road through the three-dimensional space scanning device as the point cloud data of the current frame;

Step S1405: extract road structural features and road strength features from the point cloud data of the current frame;

Step S1407: According to the trajectory estimation trajectory data of the mobile device, the road structured features and road strength features of at least one cumulative frame before the current frame are converted into features in the coordinate system of the current frame.

Wherein, the road structured features and road intensity features of the at least one cumulative frame are extracted from the point cloud data of the at least one cumulative frame; the track estimation track data is obtained by the track estimation method;

Step S1409: According to the road structured features and road strength features of the at least one accumulated frame after the coordinate system conversion, the road structured features and road strength features of the current frame, and the road feature map data, determine the Mobile device location data.

It can be seen from the above embodiments that the mobile device positioning method provided by the embodiments of the present application receives the road feature map data sent by the server, and collects the spatial point cloud data of the driving road through the three-dimensional space scanning device, and from the point cloud data Extract road structured features and road strength features, and then estimate the trajectory data based on the track of the mobile device, and convert the road structured features and road strength features of the accumulated frame before the current frame into the coordinate system of the current frame Features, and then determine the location data of the mobile device according to the road structured features and road strength features of the accumulated frame after the coordinate system conversion, the road structured features and road strength features of the current frame, and the road feature map data; This processing method enables the positioning of mobile devices in combination with the structured features and road strength features on both sides of the road accumulated in multiple frames, and enhances the ability to express road features; therefore, the positioning accuracy can be effectively improved. At the same time, this processing method can avoid the problem of inlocation that cannot be obtained when the structured features or strength features of the road cannot be obtained effectively; therefore, the robustness of positioning can be effectively improved. At the same time, because the positioning can be performed when each frame of point cloud data is obtained, thereby real-time positioning is achieved; therefore, the real-time nature of vehicle positioning can be effectively improved.

Sixth embodiment

Please refer to FIG. 15, which is a schematic diagram of an embodiment of a mobile device positioning apparatus according to this application. Since the device embodiment is basically similar to the method embodiment, the description is relatively simple, and the relevant part can be referred to the description of the method embodiment. The device embodiments described below are only schematic.

The map data receiving unit 1501 is configured to receive road feature map data sent by the server;

The point cloud data collection unit 1502 is used to collect the spatial point cloud data of the driving road through the three-dimensional space scanning device as the point cloud data of the current frame;

The current frame road feature extraction unit 1503 is used to extract road structured features and road intensity features from the point cloud data of the current frame;

A cumulative frame road feature conversion unit 1504, configured to convert the road structured feature and road intensity feature of at least one cumulative frame before the current frame into the current frame based on the estimated trajectory data of the mobile device's trajectory Features under the coordinate system of; where the road structured features and road intensity features of the at least one cumulative frame are extracted from the point cloud data of the at least one cumulative frame; Obtained by trace estimation method;

The position determining unit 1505 is configured to: according to the coordinated system, the road structured features and road strength features of the at least one accumulated frame, the road structured features and road strength features of the current frame, and the road feature map data To determine the location data of the mobile device.

It can be seen from the above embodiments that the mobile device positioning apparatus provided by the embodiments of the present application receives road feature map data sent by a server, and collects spatial point cloud data of a driving road through a three-dimensional space scanning device, and from the point cloud data Extract road structured features and road strength features, and then estimate trajectory data based on the trajectory of the mobile device, and convert the road structured features and road strength features of the accumulated frame before the current frame into the coordinate system of the current frame Features, and then determine the location data of the mobile device according to the road structured features and road strength features of the accumulated frame after the coordinate system conversion, the road structured features and road strength features of the current frame, and the road feature map data; This processing method enables the positioning of mobile devices in combination with the structured features and road strength features on both sides of the road accumulated in multiple frames, and enhances the ability to express road features; therefore, the positioning accuracy can be effectively improved. At the same time, this processing method can avoid the problem of inlocation that cannot be obtained when the structured features or strength features of the road cannot be obtained effectively; therefore, the robustness of positioning can be effectively improved. At the same time, because the positioning can be performed when each frame of point cloud data is obtained, thereby real-time positioning is achieved; therefore, the real-time nature of vehicle positioning can be effectively improved.

Seventh embodiment

Please refer to FIG. 16, which is a schematic diagram of an embodiment of a mobile device according to this application. Since the device embodiment is basically similar to the method embodiment, the description is relatively simple, and the relevant part can be referred to the description of the method embodiment. The device embodiments described below are only schematic.

A mobile device in this embodiment, the mobile device includes: a three-dimensional space scanning device 1601, a processor 1602, and a memory 1603; the memory is used to store a program for implementing a positioning method of the mobile device, and the device is powered on and passes the processing After running the program of the mobile device positioning method, the device performs the following steps: receiving road feature map data sent by the server; collecting spatial point cloud data of the driving road through a three-dimensional space scanning device as point cloud data of the current frame; Extract road structured features and road strength features from the point cloud data of the current frame; estimate track data based on the track of the mobile device, and combine the road structured features and road strength features of at least one cumulative frame before the current frame Converted into features in the coordinate system of the current frame; wherein the road structured features and road strength features of the at least one cumulative frame are extracted from point cloud data of the at least one cumulative frame; The track estimation track data is obtained by the track estimation method; according to the coordinate system, the road structured features and road strength features of the at least one accumulated frame, the road structured features and road strength features of the current frame, and The road feature map data determines the location data of the mobile device.

Although this application is disclosed as above with preferred embodiments, it is not intended to limit this application. Any person skilled in the art can make possible changes and modifications without departing from the spirit and scope of this application, so this application The scope of protection shall be subject to the scope defined in the claims of this application.

In a typical configuration, the computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include non-permanent memory, random access memory (RAM) and/or non-volatile memory in a computer-readable medium, such as read only memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

1. Computer-readable media, including permanent and non-permanent, removable and non-removable media, can implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, read-only compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, Magnetic tape cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media can be used to store information that can be accessed by computing devices. As defined in this article, computer-readable media does not include non-transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

2. Those skilled in the art should understand that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.

Claims

A mobile device positioning system, which is characterized by comprising:

The server is used to send road feature map data to the mobile device;

The mobile device is configured to receive the road feature map data sent by the server; collect spatial point cloud data of the driving road through a three-dimensional space scanning device as point cloud data of the current frame; from the point cloud of the current frame Extract road structured features and road strength features from the data; estimate the trajectory data based on the trajectory of the mobile device, convert the road structured features and road strength features of at least one cumulative frame before the current frame into the Features under the coordinate system of the current frame; road structured features and road strength features of the at least one accumulated frame converted according to the coordinate system, road structured features and road strength features of the current frame, and road feature map data To determine the location data of the mobile device.
A mobile device positioning method, which is characterized by comprising:

Receive road feature map data sent by the server;

Collect the spatial point cloud data of the driving road through the three-dimensional space scanning device as the point cloud data of the current frame;

Extract road structural features and road strength features from the point cloud data of the current frame;

Estimate the trajectory data according to the trajectory of the mobile device, and convert the road structural features and road strength features of at least one cumulative frame before the current frame into features in the coordinate system of the current frame;

Determine the mobile device’s data based on the road structured features and road strength features of the at least one cumulative frame after the coordinate system conversion, the road structured features and road strength features of the current frame, and the road feature map data Location data.
A positioning device for mobile equipment is characterized by comprising:

The map data receiving unit is used to receive road feature map data sent by the server;

The point cloud data collection unit is used to collect the spatial point cloud data of the driving road through the three-dimensional space scanning device as the point cloud data of the current frame;

A current frame road feature extraction unit for extracting road structured features and road strength features from the point cloud data of the current frame;

A cumulative frame road feature conversion unit, used to estimate the trajectory data based on the trajectory of the mobile device, and convert the road structured features and road intensity features of at least one cumulative frame before the current frame into the current frame Features in the coordinate system;

A position determining unit, configured to convert the road structured features and road strength features of the at least one accumulated frame according to the coordinate system, the road structured features and road strength features of the current frame, and the road feature map data, Determine location data of the mobile device.
A mobile device is characterized by comprising:

Three-dimensional space scanning device;

Processor; and

The memory is used to store a program that implements the positioning method of the mobile device. After the device is powered on and runs the program of the positioning method of the mobile device through the processor, the following steps are performed: receiving road feature map data sent by the server; scanning by three-dimensional space The device collects the spatial point cloud data of the driving road as point cloud data of the current frame; extracts the road structure features and road strength features from the point cloud data of the current frame; estimates the track data according to the track of the mobile device , Converting the road structured features and road intensity features of at least one cumulative frame before the current frame into features in the coordinate system of the current frame; according to the road structure of the at least one cumulative frame after the coordinate system conversion Characteristics and road strength features, road structured features and road strength features of the current frame, and the road feature map data to determine location data of the mobile device.
A mobile device positioning method, which is characterized by comprising:

Collect the spatial point cloud data of the driving road through the three-dimensional space scanning device as the point cloud data of the current frame;

Extract road structural features and road strength features from the point cloud data of the current frame;

Estimate the trajectory data according to the trajectory of the mobile device, and convert the road structural features and road strength features of at least one cumulative frame before the current frame into features in the coordinate system of the current frame;

Determine the location data of the mobile device according to the road structured features and road strength features of the at least one accumulated frame after the coordinate system conversion, the road structured features and road strength features of the current frame, and road feature map data .
The method according to claim 5, wherein the road strength feature is extracted by the following steps:

Selecting road surface point cloud data from the point cloud data of the current frame;

Generate a road intensity image according to the intensity information of the pavement point cloud data;

Perform edge extraction on the road intensity image to obtain the road intensity feature.
The method according to claim 5, wherein the structured features of the road are extracted in the following manner:

According to the feature constraint information of the road structured features, road structured features are extracted from the spatial point cloud data.
The method of claim 5, further comprising:

Obtaining position data corresponding to the current frame according to the track estimation track data of the mobile device and time data corresponding to the current frame; and, estimating the track data and the at least one accumulated frame according to the track Acquiring the time data corresponding to the accumulated frame later in the middle time, and acquiring the position data corresponding to the accumulated frame later in the time;

Determine whether the first distance between the position data corresponding to the current frame and the position data corresponding to the cumulative frame later in time is greater than or equal to a first distance threshold;

If the result of the above judgment is yes, enter the road structured feature and road strength feature of the at least one cumulative frame converted according to the coordinate system, the road structured feature and road strength feature of the current frame, and the road feature Map data and determine location data of the mobile device; and, use the current frame as the accumulated frame.
The method according to claim 8, wherein the method further comprises:

If the above judgment result is no, the position data of the mobile device is determined according to the road structured feature and road intensity feature of the at least one accumulated frame after the coordinate system conversion, and the road feature map data.
The method of claim 5, further comprising:

Obtain the number of features of the road structured features and road strength features of the current frame as the first number of features;

Determine whether the number of the first features is greater than or equal to the threshold of the number of the first features;

If the above judgment result is yes, enter the first feature quantity according to the road structured feature and road strength feature of the at least one accumulated frame after the coordinate system conversion, the road structured feature and road strength feature of the current frame And road feature map data to determine the location data of the mobile device; and, use the current frame as the accumulated frame.
The method of claim 10, further comprising:

If the above judgment result is no, the position data of the mobile device is determined according to the road structured feature and road intensity feature of the at least one accumulated frame after the coordinate system conversion, and the road feature map data.
The method of claim 5, further comprising:

Obtaining the position data corresponding to the current frame according to the track estimation track data and the time data corresponding to the current frame; and, according to the track estimation track data and the time dependence in the at least one accumulated frame The time data corresponding to the later accumulated frame, and acquiring the position data corresponding to the later accumulated frame;

Taking the distance between the position data corresponding to the current frame and the position data corresponding to the cumulative frame later in time as the first distance; and obtaining the number of features of the road structured features and road strength features of the current frame, As the first feature quantity;

Determine whether the first distance is greater than or equal to a first distance threshold, and whether the number of first features is greater than or equal to a first feature quantity threshold;

If the result of the above judgment is yes, enter the road structured feature and road strength feature of the at least one cumulative frame converted according to the coordinate system, the road structured feature and road strength feature of the current frame, and the road feature Map data and determine location data of the mobile device; and, use the current frame as the accumulated frame.
The method according to any one of claims 8-12, wherein after the current frame is used as the accumulated frame, the method further includes:

Acquiring a second feature quantity, the second feature quantity being the total feature quantity of the current frame and the at least one cumulative frame; and, acquiring the first between the current frame and the start frame of the at least one cumulative frame Two distance

If the second feature quantity is greater than the second feature quantity threshold and the second distance is greater than the second distance threshold, the start frame is deleted from the at least one cumulative frame until the second feature quantity is less than or equal to the The second feature quantity threshold, and/or the second distance is less than or equal to the second distance threshold.
The method according to claim 5, wherein the trajectory data is estimated based on the trajectory of the mobile device, and the road structured features and road strength features of the at least one cumulative frame are converted to the Features in the current frame's coordinate system, including:

Obtaining the position data corresponding to the at least one cumulative frame according to the time data corresponding to the at least one accumulated frame and the track estimation track data respectively; and according to the track estimation and the current track data corresponding to the at least one accumulation frame Obtaining the time data corresponding to the frame to obtain the position data corresponding to the current frame;

For each accumulated frame, according to the position data corresponding to the accumulated frame and the position data corresponding to the current frame, the road structured features and road strength features of the accumulated frame are converted into the coordinate system of the current frame feature.
The method according to claim 5, wherein the road strength characteristics include: a lane line strength characteristic, a steering sign strength characteristic, and a pedestrian crossing strength characteristic.
A positioning device for mobile equipment is characterized by comprising:

The point cloud data collection unit is used to collect the spatial point cloud data of the driving road through the three-dimensional space scanning device as the point cloud data of the current frame;

A current frame road feature extraction unit for extracting road structured features and road strength features from the point cloud data of the current frame;

A cumulative frame road feature conversion unit, used to estimate the trajectory data based on the trajectory of the mobile device, and convert the road structured features and road intensity features of at least one cumulative frame before the current frame into the current frame Features in the coordinate system;

The position determining unit is configured to determine the location based on the road structured features and road strength features of the at least one accumulated frame after the coordinate system conversion, the road structured features and road strength features of the current frame, and the road feature map data Describe the location data of the mobile device.
The device according to claim 16, further comprising:

A position obtaining unit, configured to obtain position data corresponding to the current frame based on the track estimated track data and time data corresponding to the current frame; and, based on the track estimated track data and the at least Acquiring time data corresponding to a cumulative time frame later in a cumulative frame, and acquiring position data corresponding to the cumulative time frame later than the time;

A first data statistical unit, configured to use the distance between the position data corresponding to the current frame and the position data corresponding to the cumulative frame later in time as the first distance; and, obtain the road structure feature of the current frame The number of features with road strength features is used as the first number of features;

A judging unit, used to judge whether the first distance is greater than or equal to a first distance threshold, and whether the number of first features is greater than or equal to a first feature quantity threshold; if so, start the position determining unit;

A cumulative frame increasing unit is used to use the current frame as the cumulative frame.
The device according to claim 17, further comprising:

A second data statistics unit, configured to obtain a second feature quantity, the second feature quantity being the total feature quantity of the current frame and the at least one accumulated frame; and, obtaining the current frame and the at least one accumulated The second distance between the start of the frame;

A cumulative frame deletion unit, configured to delete the start frame from the at least one cumulative frame until the second feature number is greater than the second feature number threshold and the second distance is greater than the second distance threshold, until the The second feature quantity is less than or equal to the second feature quantity threshold, and/or the second distance is less than or equal to the second distance threshold.
A mobile device is characterized by comprising:

Three-dimensional space scanning device;

Processor; and

The memory is used to store a program for implementing the positioning method of the mobile device. After the device is powered on and the program for the positioning method of the mobile device is run through the processor, the following steps are performed: collecting spatial point cloud data of the driving road through a three-dimensional space scanning device , As point cloud data of the current frame; extracting road structure features and road strength features from the point cloud data of the current frame; estimating trajectory data based on the trajectory of the mobile device, at least The road structured features and road strength features of one cumulative frame are converted to features in the coordinate system of the current frame; according to the road structured features and road strength features of the at least one accumulated frame converted from the coordinate system, the The road structured feature and the road intensity feature of the current frame, and the road feature map data determine the location data of the mobile device.