JP2022550188A - Positioning method, device, electronic device, storage medium and computer program - Google Patents

Abstract

The present invention relates to positioning methods and devices, electronic devices, and storage media. The method includes obtaining first position data of a reference object of a target object based on an electronic map and obtaining second position data of the reference object based on a target image captured with an image acquisition device. , positioning the target object based on the first position data and the second position data. [Selection drawing] Fig. 1

Description

TECHNICAL FIELD The present invention relates to the field of computer technology, and more particularly to positioning methods and devices, electronic equipment, and storage media.

Positioning is an important technology in fields such as autonomous driving. Without being able to pinpoint the exact location of the vehicle, true autonomous driving cannot be achieved. In general, the global positioning system (GPS) is currently the most widely applied positioning technology, but the positioning error of GPS is large, for example, the positioning error is usually about 10m, so it is difficult to operate autonomous driving. It is difficult to meet the accuracy requirements of In the related technology, laser radar may be used to improve positioning accuracy, but the cost of laser radar is soaring, which is disadvantageous to the spread of automatic driving technology.

The present invention provides a positioning method and device, an electronic device, a storage medium, and a computer program.

One aspect of the present invention provides a positioning method. The positioning method includes obtaining first position data of a reference object of a target object based on an electronic map, and obtaining second position data of the reference object based on a target image captured by an image acquisition device. and positioning the target object based on the first position data and the second position data.

One aspect of the present invention provides a positioning device. The positioning device comprises a first acquisition module for acquiring first position data of a reference object of a target object based on an electronic map; a second acquisition module for acquiring position data; and a positioning module for positioning the target object based on the first position data and the second position data.

One aspect of the present invention provides an electronic device. The electronic device comprises a processor and a memory for storing processor-executable instructions, the processor being configured to perform the positioning method.

One aspect of the invention provides a computer-readable storage medium. Computer program instructions are stored on the computer readable storage medium, and the positioning method is performed when the computer program instructions are executed by the processor.

One aspect of the invention provides a computer program. The computer program is stored in a storage medium, and the positioning method is performed when the computer program is executed by a processor.

It is to be understood that the above general description and the following detailed description are merely exemplary and interpretive and are not intended to limit the invention.

Other features and aspects of the invention will become apparent based on the following detailed description of exemplary embodiments with reference to the drawings.

The drawings herein are incorporated into and constitute a part of the specification. These drawings are used to explain the solution of the invention together with the specification, showing an embodiment consistent with the invention.
4 is a flow chart of a positioning method according to an embodiment of the present invention; 1 is a schematic diagram of an electronic map according to an embodiment of the present invention; FIG. FIG. 4 is a schematic diagram of a target image according to an embodiment of the present invention; FIG. 5 is a schematic diagram of a position correction amount according to an embodiment of the present invention; FIG. 4 is an application schematic diagram of a positioning method according to an embodiment of the present invention; 1 is a block diagram of a positioning device according to an embodiment of the present invention; FIG. 1 is a block diagram of an electronic device according to an embodiment of the invention; FIG. 1 is a block diagram of an electronic device according to an embodiment of the invention; FIG.

Various illustrative embodiments, features, and aspects of the invention are described in detail below with reference to the drawings. The same reference numbers in the drawings indicate elements with the same or similar function. Although the drawings show various aspects of the embodiments, they are not necessarily drawn to scale unless otherwise indicated.

The term "exemplary" as used herein means "exemplary, exemplary, or illustrative." Any embodiment described herein as "exemplary" is not necessarily to be construed as superior or better than other embodiments.

The term "and/or" in the text simply describes the related relationship of the related objects and indicates that there can be three types of relationships. For example, A and/or B can represent three cases: A existing alone, A and B existing simultaneously, and B existing alone. In addition, the term "at least one" in the text indicates any one of a plurality of types or any combination of at least two of a plurality of types. For example, including at least one of A, B, and C may indicate selecting any one or more elements from the set formed by A, B, and C.

Also, a great deal of specific detail is provided in the specific embodiments below in order that the present invention may be better described. As will be appreciated by those skilled in the art, the present invention may be practiced as well without some of the specific details. In some instances, methods, means, devices and circuits that are well known to those skilled in the art have not been described in detail so as to obscure the subject matter of the present invention.

FIG. 1 is a flow chart of a positioning method according to an embodiment of the present invention. As shown in FIG. 1, the method includes steps S11 to S13.

In step S11, the first position data of the reference object of the target object is obtained based on the electronic map.

In step S12, second position data of the reference object is obtained based on the target image captured by the image acquisition device.

In step S13, the target object is positioned based on the first position data and the second position data.

In the positioning method according to the embodiment of the present invention, the target object can be positioned using the first position data of the reference object in the electronic map and the second position data of the reference object in the target image. Relying on the position data of the object, the positioning accuracy of the target object can be enhanced so that the positioning accuracy can meet the accuracy requirements of automatic driving. In addition, since the positioning accuracy is enhanced by the target image and the electronic map collected by the image collecting device, the cost of use is low, and the use and popularization are facilitated.

In one possible implementation, the positioning method may be performed by terminal equipment or other processing equipment. Terminal equipment includes user equipment (UE), mobile equipment, user terminal, mobile phone, cordless phone, personal digital assistant (PDA), handheld equipment, computing equipment, in-vehicle equipment, wearable equipment, and the like. may Other processing equipment may be a server, a cloud-side server, or the like. In some possible implementations, the positioning method may be implemented by a processor invoking computer readable instructions stored in memory.

In one possible implementation, the electronic map may be a map that is digitally stored and viewed, and the electronic map includes location data of multiple points, roads, objects, etc., such as Baidu ) maps, google maps, etc.; In an example, the electronic map may be a high-precision electronic map (hereinafter referred to as a high-precision map). Ordinary maps shown to drivers do not have lane-level road information, but high-definition maps are maps that are commonly used for devices such as vehicles, so they contain richer road information such as lane levels, And the recognition accuracy is higher, and it has the accuracy for recognizing lane information. A high-definition map contains a wealth of information, for example, a high-definition map may contain information of reference objects, and said reference objects may include lanes, road signs, traffic lights, etc. In the present invention, reference Objects are not limited. The information of the reference object may include lane information (eg, lane position), lane restriction information (eg, lane restriction information indicated by road signs or traffic lights, such as travel restriction information, etc.), and the like. In addition, high definition maps contain a wealth of other information, for example, high definition maps contain traffic flow information and traffic control information. The present invention does not limit the information contained in the high definition map.

In an example, the lane information may be a marking line for indicating the driving lane. The lane information may include types of lanes, such as one-way lanes, straight lanes, right-turn lanes, left-turn lanes, etc., and may also include center lines for separating opposing lanes. Alternatively, the lane information may include attributes of lanes, such as solid lines, dashed lines, double solid lines, double dashed lines, stop lines, road marking lines in the direction of travel, and the like. In an example, the lane information may include lane geographic coordinate information, eg, lane latitude and longitude coordinates. In the present invention, the type of information included in lane information is not limited.

FIG. 2 is a schematic diagram of an electronic map according to an embodiment of the present invention. As shown in FIG. 2, the lane information may include, for example, straight lanes, right turn lanes, left turn lanes, and the like. In an example, the lane information identifies the number of lanes included in the road (eg, may include 2 or 3 lanes, etc.), and then determines the location of the target object (eg, vehicle) based on the number of lanes. You may specify the lane to For example, the lane in which the target object is located may be identified based on the positioning information of the target object. For example, the target object's positioning information may assist the driver in identifying the driving policy by indicating that the target object is located in the second lane, or rely on the driving policy in automated driving (e.g. straight ahead). or turn etc.). Further, the electronic map may include the location of each lane, eg the geographical coordinates of the lane. In an example, a lane may be a line formed by a plurality of points (eg, point cloud), and the geographical coordinates of each point may indicate the geographical coordinates of the lane. That is, the geographic coordinates of a lane may include the geographic coordinates (eg, latitude and longitude coordinates) of points that make up the lane.

In an example, the lane geographic coordinates may be offset latitude and longitude coordinates. In an electronic map, geolocation may be encrypted to improve the security of using the electronic map. For example, by offsetting the latitude and longitude coordinates of the electronic map, the geographic position is encrypted. In addition, since an offset also appears when converting latitude and longitude coordinates on the earth (coordinates in a spherical coordinate system) to coordinates on a planar electronic map, when using the geographical coordinates of the lane, coordinate offset correction is first performed. may For example, a coordinate offset correction may be performed based on the mapping relationship between spherical coordinates and planar coordinates, and then the latitude and longitude coordinates after the offset correction may be used to represent the geographical coordinates of the lane.

In one possible implementation, the target object may include a vehicle traveling on a road (eg, a driverless vehicle), a mobile device such as a robot, or the like. The target object may run in the lane and perform operations such as going straight, turning, and reversing according to the lane and/or the running command. Furthermore, the image acquisition device (for example, a camera head of a drive recorder, a camera, etc.) is provided on the target object, and an image of the target object while it is running (for example, the camera head of the image acquisition device is That is, the camera head can capture a target image whose orientation matches the direction of travel of the target object and is directly in front of the target object.

In one possible implementation, after obtaining first position data of the reference object (e.g., lane) in the electronic map and second position data of the reference object in the target image, the first position data and the second position data are obtained. may be used to locate the target object. For example, the target object may be positioned by merging the first position data and the second position data. In an example, the first position data may indicate position coordinates of a lane near the target object. For example, the geographic coordinates of a plurality of lanes near the target object on the electronic map are determined, and the approximate geographic position of the target object (for example, the target object is located at the intersection of Street A and Street B) is determined based on the geographic coordinates. ), and the lane in which the target object is located based on the second position data of the lanes in the target image (e.g., one lane on the right side of the target image and three lanes on the left side). , representing that the target object is located within the first lane). This improves the positioning accuracy, that is, improves the positioning accuracy to the lane level.

In one possible implementation, a precise positioning of the target object is obtained by determining an approximate position of the target object and then correcting the approximate position using the first and second position data of the reference object, e.g. Lane level positioning may be obtained. Positioning the target object based on the first position data and the second position data includes obtaining first positioning data of the target object; obtaining second positioning data for indicating a positioning result of the target object by correcting the first positioning data according to the method.

In one possible implementation, the first positioning data of the target object includes satellite positioning data, such as GPS positioning data, Beidou positioning data, etc., and the first positioning data is not limited in the present invention. Although the first positioning data can determine the geolocation of the target object, the first positioning data may not be sufficiently accurate. For example, the error of the first positioning data may reach about 10m. In an example, the first positioning data can be used to retrieve the road on which the target object is located, but the first positioning data cannot accurately identify which lane in the road the target object is located. For example, the first positioning data may determine that the target object is located on a three-lane road, and the first positioning data may determine that the target object is located on the second lane, but the first positioning data may determine that the target object is located on the second lane. There may be errors in the data. For example, the lane in which the target object is actually located and the lane identified by the first positioning data may not match.

In one possible implementation, the first positioning data may be corrected by the first position data and the second position data to obtain the second positioning data with higher accuracy. For example, the first position data and the second position data are position data of the same lane, but the first position data is the position data of the lane in the electronic map, and the second position data is the position data of the lane in the target image. This is the position data of the lane. The above two types of position data represent positions in the same lane. If there is a deviation in the positions indicated by the two types of position data, it may be indicated that the positioning of the target object is not accurate, and the deviation may be used to correct the first positioning data of the target object.

In an example, the first location data is location data retrieved in an electronic map based on the first positioning data of the target object. For example, if the first positioning data is X1 degree east longitude and X2 degree north latitude, the first position data is the position data of the lane near the latitude and longitude. The second position data is the position data of the lane of the target object captured by the image acquisition device provided on the target object. between the first position data and the second position data when the first position data and the second position data are position data of the same lane and the second position data are the position data in the captured real image; is the same as the deviation between the first positioning data and the actual position of the target object. Therefore, by correcting the first positioning data using the position deviation between the first position data and the second position data, the second positioning data, that is, the positioning data with higher positioning accuracy may be obtained. .

In this manner, the deviation between the first positioning data in the electronic map of the reference object and the second position data in the target object of the reference object represents the deviation between the first positioning data and the real position. Further, by correcting the first positioning data using the deviation, the accuracy of the first positioning data can be improved.

In one possible implementation, step S11 includes: obtaining the geographic coordinates of the reference object in the electronic map; performing a coordinate transformation process on the geographic coordinates of the reference object; obtaining first position data of the reference object in the target coordinate system. The target coordinate system is a coordinate system established based on the target object.

In one possible implementation, the electronic map may contain the geographic coordinates of the reference objects (eg, lanes), and the geographic coordinate information of the lanes may be retrieved in the electronic map. In an example, when the electronic map is in use (e.g., the vehicle (target object) is activated, or the vehicle initiates a navigation or positioning maneuver), or when the electronic map is updated, the lane geographic coordinate information is retrieved, cached, or cached. The geographic coordinates of the lanes may be stored on a hard disk and deleted from the cache or hard disk when the electronic map is no longer in use (eg, after the vehicle has stopped or a navigation or positioning operation has been terminated). This allows the space occupied in the storage space to be cleared for storage of other data when the electronic map is no longer needed, improving the efficiency of utilization of storage resources. Or, to simplify the operation, the lane geographic coordinate information may not be deleted, and the geographic coordinate information may not be retrieved each time a navigation or positioning operation is initiated. Furthermore, when updating the electronic map, the geographic coordinates in the cache or hard disk may be updated by retrieving the geographic coordinate information again. In an example, the geographic coordinates of the reference object may be retrieved based on the first positioning data, for example, the geographic coordinates of the lane near the coordinates may be retrieved based on the latitude and longitude coordinates of the first positioning data.

In one possible implementation, a target coordinate system may be established based on the target object. For example, a target coordinate system may be established with the position of the target object identified by the first positioning data as the origin. For example, with the position of the target object specified by the first positioning data as the origin, the running direction of the target object as one coordinate axis direction, and the direction orthogonal to the running direction as another coordinate axis direction, the target coordinate system is defined as: Establish.

In one possible implementation, a coordinate transformation is performed on the geographical coordinate information of the lanes, i.e., a coordinate transformation process is performed from the geographical coordinate system to the target coordinate system, so that the lanes in the electronic map are converted to the target coordinate system. may be obtained. For example, the latitude and longitude coordinates of each point of the lane are converted from the geographic coordinate system to the target coordinate system, and the coordinates of each point in the target coordinate system are obtained. You may acquire the 1st position data in a target coordinate system.

In an example, first, a coordinate transformation matrix between the geographic coordinate system and the target coordinate system may be identified. For example, the target coordinate system may be a coordinate system whose origin is the position of the target object specified by the first positioning data, and the relative positional relationship between the target coordinate system and the geographic coordinate system may be specified. Also, since the target coordinate system has the running direction of the target object as the coordinate axis direction, the relative angle between the target coordinate system and the geographic coordinate system may be specified. Furthermore, the coordinate transformation matrix between the geographic coordinate system and the target coordinate system is specified by the relative positional relationship between the target coordinate system and the geographic coordinate system and the relative angle between the target coordinate system and the geographic coordinate system. good too. Thus, the first position data may be acquired by performing coordinate conversion processing on the latitude and longitude coordinates of each point on the lane in the electronic map based on the coordinate conversion matrix. In an example, the first position data may include point cloud data. For example, a lane's location on an electronic map may be indicated by a plurality of points (eg, point cloud) on the lane in geographic coordinates. After the coordinate transformation process is performed, the geographical coordinates of the points on the lane are transformed into the coordinates of the points on the target coordinate system to generate point cloud data including the coordinates of the points, that is, the first position data. may be obtained.

In one possible implementation, there is an error in the first position data of the lane, because there may be an error in the first positioning data, and the geographical coordinates of the lane are obtained by searching based on the first positioning data. and the error in the first positioning data can be determined based on the error in the first position data of the lane. For example, if the error of the first position data of the lane matches the error of the first positioning data, then the error of the first position data of the lane can be identified, and the error of the first positioning data is based on the error of the first position data. Errors can be corrected.

With such a scheme, the geographic coordinates of the reference object can be transformed into the target coordinate system, making it convenient to identify the positioning error in the target coordinate system and favoring the correction to the first positioning data.

In one possible implementation, a target object (eg, vehicle, robot, etc.) may be moving and a target image directly in front of the target object may be captured via a drive recorder camera head, camera, or the like. The target image may include reference objects (eg, lanes).

In one possible implementation, step S12 includes: identifying image coordinate information of the reference object in the target image; , obtaining second position data in the target coordinate system.

FIG. 3 is a schematic diagram of a target image according to an embodiment of the present invention; As shown in FIG. 3, the target image was taken with an image acquisition device provided on the target object. In the target image, directly in front of the target object is the third lane from the left, and the target image may include multiple lanes.

In one possible implementation, a semantic segmentation process may be performed on the target image to obtain the position coordinates of the reference object in the target image. For example, when the reference object is a lane, the position of the lane in the target image may be specified by a method such as pixel detection or edge detection, and the position of the lane in the target image may be defined by a method such as a neural network. may For example, the target image is input to the neural network, and the position coordinates of the lane in the target image are output by the semantic segmentation processing of the neural network. In an example, the position of the lane in the target image may be detected via a neural network. For example, the position where the lane is located may include a plurality of pixel points (eg, point cloud), and the position coordinates in the target image of each pixel point on the lane may be detected.

In one possible implementation, a coordinate transformation operation may be performed on the position coordinates of the reference object in the target image to obtain second position data of the reference object in the target image in said target coordinate system. For example, the coordinates of each pixel point of the lane in the target image are transformed into the target coordinate system, and the coordinates of each pixel point of the lane in the target coordinate system are obtained, that is, the target coordinate system of the lane in the target image may obtain second position data at. In an example, the second position data may include point cloud data. For example, the position of the lane in the target image may be indicated by position coordinates of a plurality of points (eg, point cloud) on the lane. After the coordinate transformation process is performed, the position coordinates of the plurality of points on the lane in the target image are transformed into the coordinates of the plurality of points in the target coordinate system, and point cloud data including the coordinates of the plurality of points, that is, the first Two position data may be obtained.

By converting the positional coordinates of the reference object in the target image into the target coordinate system and obtaining the second positional data by such a method, the positional coordinates of the reference object in the target image and the geographic coordinates of the reference object in the electronic map are converted. You may unify with a coordinate system. In this way, the error between the first position data and the second position data can be conveniently obtained, which is advantageous for correction to the first positioning data.

In one possible implementation, performing a coordinate transformation operation on the position coordinates to obtain second position data in a target coordinate system of a reference object in the target image is captured by an image acquisition device. identifying a homography matrix based on position coordinates of at least some pixel points in a reference image and position coordinates of points corresponding to the at least some pixel points in the target coordinate system; and obtaining the second position data by performing a coordinate transformation process on the position coordinates of the reference object in the target image based on the graphy matrix.

In one possible implementation, first, the homography matrix between the target image and the target coordinate system, i.e., between the position coordinates of the pixel points in the target image and the position coordinates of the corresponding points in the target coordinate system A coordinate transformation matrix may be specified and used to transform the position coordinates of pixel points in the target image to the target coordinate system.

In one possible implementation, based on the position coordinates of at least some pixel points in a reference image and the position coordinates of points corresponding to said at least some pixel points in said target coordinate system, a homography matrix may be specified. That is, each pixel point of the lane in the target image may be converted to the coordinates in the target coordinate system by the homography matrix, and further, the second position data of the lane in the target image in the target coordinate system may be acquired. good.

In one possible implementation, the reference image may be any image taken with the image acquisition equipment. At least some pixel points in the reference image may be marked. For example, the position coordinates of the pixel points in the reference image may be marked to specify the position coordinates of the pixel points in the target coordinate system. good. A homography matrix H, that is, a transformation matrix obtained by transforming the position coordinates in the reference image to the target coordinate system may be specified based on the position coordinates in the reference image and the position coordinates in the target coordinate system of the pixel points. The homography matrix H may be used to transform the position coordinates of any point in the captured image into position coordinates in the target coordinate system.

In one possible implementation, performing a coordinate transformation process on the position coordinates of the reference object in the target image according to the homography matrix to obtain the second position data. In an example, the position coordinates of each pixel point of the lane in the target image may be respectively multiplied by the homography matrix to obtain the position coordinates of each pixel point in the target coordinate system. For example, the coordinates of each pixel point in the target coordinate system may be specified based on the following formula (1).

However, (u, v) are the position coordinates of any one pixel point on the lane in the target image, and (x, y) are the position coordinates of the pixel point in the target coordinate system. The second position data may be acquired by performing a coordinate conversion process on the coordinates of each pixel point of the lane in the target image using Equation (1).

By obtaining the homography matrix using the reference image by such a method, it is possible to obtain the correspondence between the target image and the target coordinate system, and the position coordinates of the pixel points in the target image can be obtained in the target coordinate system. It can be conveniently converted into the position coordinates in the space, improving the efficiency of coordinate conversion.

In one possible implementation, the second location data is location information identified based on the actual image captured by the image acquisition device, and the second location data is considered to be highly accurate location information. Alternatively, an error between the first position data and the second position data may be identified as an error between the first positioning data and the actual position of the target object, and the error may be used to correct the first positioning data. It may be used to specify the position correction amount and correct the first positioning data.

In one possible implementation, the execution order of step S11, ie obtaining the first position data, and step S12, ie obtaining the second position data, is not restricted. In FIG. 1, executing step S11 and then executing step S12 is merely an example. After executing step S12, step S11 may be executed, or step S11 and step S12 may be executed simultaneously.

In one possible implementation, step S13 includes: determining a position correction amount based on a positional relationship in a target coordinate system between the first position data and the second position data of the reference object; obtaining the second positioning data for indicating the positioning result of the target object by correcting the first positioning data based on a quantity. The target coordinate system is a coordinate system established based on the target object.

With such a method, the position correction amount can be specified using the first position data and the second position data of the reference object. That is, the error between the first positioning data and the actual geographic location may be obtained and used to correct the first positioning data. Thus, the positioning accuracy is improved.

In one possible implementation, the position correction amount includes a rotation matrix, and the position correction amount is determined based on the positional relationship between the first position data and the second position data of the reference object in a target coordinate system. Doing includes obtaining a rotation angle between the first position data and the second position data, and determining the rotation matrix based on the rotation angle.

In one possible implementation, the first position data and the second position data comprise point cloud data. For example, each of the first position data and the second position data may be a line composed of a plurality of coordinate points. The first position data may be the first vector, the second position data may be the second vector, and an included angle between the first vector and the second vector may be identified, i.e., the rotation angle may be identified. .

In one possible implementation, the rotation matrix may be determined based on the rotation angle, i.e. multiplying the vector corresponding to the second position data with the rotation matrix yields the vector corresponding to the second position data It may be rotated, and the vector after rotation is parallel to the first position data. Alternatively, the vector corresponding to the first position data may be rotated by multiplying the vector corresponding to the first position data by the rotation matrix, and the vector after rotation is parallel to the second position data. The rotation matrix may be identified based on Equation (2) below.

where R is the rotation matrix and α is the rotation angle. The rotation may be performed by multiplying the vector corresponding to the second position data by the rotation matrix R, that is, using the rotation matrix R, multiplying the vector corresponding to the second position data by the A vector parallel to the vector may be obtained or multiplied by the vector corresponding to the first position data to obtain a vector parallel to the vector corresponding to the second position data. For example, R*l ₂ is parallel to l ₁ . where _l2 is a vector corresponding to the second position data and _l1 is a vector corresponding to the first position data.

In one possible implementation, a method such as an approximation algorithm may identify the rotation matrix step by step and then identify the rotation angle. In an example, the vector _l2 corresponding to the second position data may be multiplied by a rotation matrix corresponding to an angle to rotate _l2 and reduce the angle between _l1 and _l2 . If _l2 is no longer parallel to _l1 after being rotated, continue to multiply _l2 after rotation with the rotation matrix corresponding to an angle, and continue to rotate _l2 until _l2 is parallel to _l1 . For example, at the start of the approximation algorithm, the larger angle can be chosen, but as the included angle between _l2 and _l1 becomes smaller, the smaller angle can be chosen. For example, if the included angle between l ₂ and l ₁ is 52°, and at the start of the approximation algorithm said angle can be chosen to be 20°, and after two iterations of the approximation algorithm the included angle is reduced to 12°, The angle can be selected to be 5°, after running the approximation algorithm two more times, the included angle is reduced to 2°, the angle can be selected to be 1°, and after running the approximation algorithm two more times , l ₂ are parallel to l ₁ . Further, the rotation matrix may be obtained based on all matrices for rotating _l2 , for example, by multiplying all matrices for rotating _l2 to obtain the rotation matrix. Alternatively, the rotation angle may be specified based on the values of the elements of the rotation matrix. For example, the rotation angle may be determined based on an inverse trigonometric function. The present invention does not limit the method of obtaining the rotation angle and rotation matrix.

With such a method, the direction of the first positioning data can be corrected using the angle error (that is, the specified rotation angle) between the first position data and the second position data, and the positioning accuracy can be improved. Improve.

In one possible implementation, the position correction amount comprises a first translation component and a second translation component, the first translation component being perpendicular to the second translation component and the reference The object is parallel to the first translation component. Identifying a position correction amount based on the first position data and the second position data of the reference object includes obtaining a rotation angle between the first position data and the second position data; determining the first translation component and the second translation component based on the rotation angle and position data to be adjusted. However, the position data to be adjusted is the first position data or the second position data.

In one possible realization, the error between the first position data and the second position data may be an angle error as well as a position error. That is, after rotating the vector corresponding to the second position data so that it is parallel to the vector corresponding to the first position data, the two vectors may not overlap. That is, there is position error. The position error may be corrected by translation: a first translation component parallel to the lane corresponding to the position data to be adjusted and a second parallel component perpendicular to the lane corresponding to the position data to be adjusted. The displacement component corrects the position error. The position data to be adjusted may be the first position data or the second position data. When the position data to be adjusted is the first position data, a vector corresponding to the first position data after rotation (parallel to the vector corresponding to the second position data) is generated by the first translation component and the second translation component. ) is translated so that it overlaps the vector corresponding to the second position data (in such cases, the second position data is also referred to as the target position data). When the position data to be adjusted is the second position data, a vector corresponding to the second position data after rotation (parallel to the vector corresponding to the first position data) is generated by the first translation component and the second translation component. ) is translated so that it overlaps the vector corresponding to the first position data (in such cases, the second position data is also referred to as the target position data). In some embodiments, when the data to be adjusted is the first position data, the target position data is the second position data, and when the data to be adjusted is the second position data, the target position data is , become the first position data.

In one possible implementation, the first translation component may be specified by the rotation angle α and the position data to be adjusted. In an example, the second position data is the position in the target coordinate system of the lane in the target image. Identify the included angle ε between the second position data and the running direction (that is, the direction of the coordinate axis in the target coordinate system, and the direction of the coordinate axis is the same as the running direction) based on the vector corresponding to the second position data. and the first translation component may be determined based on the rotation angle α and the included angle ε. For example, the first translation component may be identified based on Equation (3) below.
v=(cos(α+ε), sin(α+ε)) (3)

However, ve is the first translation component. In the example, ε can be close to 0 if the target object travels along the lane.

In one possible implementation, the second translation component pe may be determined based on the first translation component ve. In an example, a vector orthogonal to ve may be chosen as the second translation component pe.

In one possible implementation, the first translation component and the second translation component are unit vectors. That is, both the first translation component and the second translation component are vectors with a length of one. In this way, it becomes easy to specify the adjustment width of the position data to be adjusted. For example, the adjustment distance in the direction of the first translation component is 3, the adjustment distance in the direction of the second translation component is 2, and the adjustment width is not limited in the present invention.

Such a method makes it convenient to store the first translational component and the second translational component, and also makes it easy to specify the adjustment width of the position data to be adjusted by the unit vector.

In one possible implementation, it makes no sense to move along a direction parallel to the lane corresponding to the target position data if the lane is straight. That is, after rotating and moving along the direction perpendicular to the lane corresponding to the target position data, there is no need to move along the direction parallel to the lane corresponding to the target position data. The lane may overlap with the lane corresponding to the position data to be adjusted. Therefore, the adjustment width in the direction of the first translation component may be set to zero. If the lane is curved, it makes sense to move along a direction parallel to the lane corresponding to the first position data.

In one possible implementation, storage space may be saved by storing only the rotation angle α, the first translation component and the second translation component after the position correction amount has been determined.

FIG. 4 is a schematic diagram of the position correction amount according to the embodiment of the present invention. As shown in FIG. 4, the position data to be adjusted is the second position data, _l2 is the vector corresponding to the second position data, and _l1 is the vector corresponding to the first position data. . We may rotate l ₂ to be parallel to l ₁ by a rotation matrix R corresponding to the rotation angle α to obtain R*l ₂ . Also, by adjusting the position of R*l ₂ with the first translation component ve and the second translation component pe, R*l ₂ and l ₁ after the position adjustment may overlap. .

In one possible implementation, the angle and position of _l2 are stepwise adjusted by a method such as an approximation algorithm so that the adjusted _l2 and _l1 overlap, and a position correction amount is specified. good too. In an example, the position data to be adjusted is the second position data, and the vector _l2 corresponding to the second position data is multiplied by the rotation matrix corresponding to an angle to rotate _l2 , and _l1 and The angle between _l2 may be small. If l ₂ is no longer parallel to l ₁ after being rotated, continue l ₂ by continuing to multiply l ₂ after rotation with the rotation matrix corresponding to an angle until l ₂ is parallel to l ₁ rotate. Further, the rotation matrix may be obtained by all matrices that rotate _l2 . For example, all matrices that rotate _l2 may be multiplied to obtain the rotation matrix. The rotation angle may be specified based on the values of the elements of the rotation matrix. For example, the rotation angle may be specified by an inverse trigonometric function. After obtaining the rotation angle, the first translation component ve and the second translation component pe may be determined based on the rotation angle and the second position data. The present invention does not limit the method of specifying the position correction amount.

In one possible implementation, the first translation component ve and the second translation component pe may be determined simultaneously. For example, the first translation component ve may be specified by Equation (3), and the second translation component pe may be specified directly by Equation (4).
pe = (sin (α + ε), -cos (α + ε)) (4)

With such a method, the first translation component and the second translation component can be obtained using the rotation angle, the position error of the first positioning data can be corrected, and the positioning accuracy can be improved.

In one possible implementation, the first positioning data may be corrected based on the position correction amount. For example, the direction of the first positioning data is corrected based on the rotation angle of the position correction amount, and the position of the first positioning data is corrected based on the first translation component and the second translation component of the position correction amount. can be corrected. Thereby, accurate second positioning data is obtained. The accuracy of the second positioning data is high, and the lane in which the target object is located can be accurately recognized.

In the positioning method according to the embodiment of the present invention, the position correction amount is specified using the first position data and the second position data, the first positioning data is corrected by the position correction amount, the second positioning data is acquired, The positioning accuracy for the target object can be improved. The position correction amount may also include a rotation angle or rotation matrix for correcting the running direction of the target object. The position correction amount may include a first translation component and a second translation component for correcting the position of the target object. Furthermore, obtaining the second position data with the target image collected from the target object has a low cost of use and is easy to use and disseminate.

FIG. 5 is an application schematic diagram of a positioning method according to an embodiment of the present invention. As shown in FIG. 5, the high-definition map may include information of a reference object, the reference object including lanes, the first positioning data including satellite positioning data, and the image collection device comprising: provided to the target object. The geographic coordinate information of lanes in the high-definition map may be retrieved. A target coordinate system is established based on the first positioning data (eg, GPS positioning information). The establishment of the target coordinate system can refer to the previous description and will not be repeated here.

In one possible implementation, look up the geographical coordinates of the lanes in the high-definition map, perform coordinate transformation operations on each of the points (e.g., point cloud) of the lanes, and obtain the point cloud Q{q1 , q2, . . . , qm}, ie the first position data in the target coordinate system of the lane. m is a positive integer. The coordinate transformation process can refer to the previous description and will not be repeated here.

In one possible implementation, the target image may be a straight-ahead image captured by an image acquisition device while the vehicle is in motion, the target image may include lanes on the road, and the semantic By performing the segmentation process, the position coordinates of the lane in the target image may be obtained, the position where the lane is located may include a plurality of pixel points (for example, a point group), and each pixel point on the lane may be A point group P{p1, p2, . . . , pn }, that is, the second position data in the target coordinate system of the lane may be obtained. n is a positive integer. The coordinate transformation process can refer to the previous description and will not be repeated here.

In one possible implementation, a point cloud Q{q1, q2, . . . , qm} and the point group P{p1, p2, . . . , pn}, i.e. identify the lane formed by the corresponding points in the first position data and the second position data. For example, points pk-pl (where i, j are positive integers less than m and k, l are positive integers less than n) corresponding to points qi-qj may be identified. qi-qj are points in a lane and pk-pl are points in a lane. Then, the position correction amount is specified according to the corresponding lane.

In one possible implementation, the position correction amount may include the rotation angle α. That is, the vector _l2 corresponding to the second position data may be rotated so that _l2 is parallel to the vector _l1 corresponding to the first position data. The rotation angle is α.

In one possible implementation, the position correction amount may further comprise a first translation component and a second translation component. The rotated l _{2 ,} ie, R*l ₂ may be translated. For example, R* _l2 may be translated along a direction parallel to _l1 . The first translation component in that direction is ve. Also, translation processing along a direction perpendicular to _l1 may be performed on R* _l2 . The second translation component in that direction is pe. After the translation process, R*l ₂ after translation is made to overlap l ₁ .

In one possible implementation, the rotation matrix R, the first translation component ve and the second translation component pe may be the position correction amount. Further, the positioning accuracy of the target object may be improved by correcting the first positioning data using the position correction amount. In some embodiments, it is possible to acquire highly accurate second positioning data by correcting the first positioning data, and it is possible to accurately recognize the lane in which the vehicle is located from the second positioning data.

In one possible implementation, the method further comprises determining a relative positional relationship between the target object and the reference object based on second positioning data of the target object. The relative positional relationship between the target object and the reference object may include at least one of a lane in which the target object is located, a distance between the target object and the lane, and an included angle between the target object and the lane. good.

In an example, the positioning method is applicable to the field of autonomous driving and is used to determine the precise position of a vehicle. The positioning method is applicable to driving assistance systems, and is used to identify the lane in which the vehicle is located and the distance between the vehicle and the lane. The positioning method is applicable to the navigation of devices such as driverless devices or robots, and is used to determine the exact position of the device and the orientation of the device (e.g., the angle of the device with respect to the lane). The present invention does not limit the application fields of the positioning method.

FIG. 6 is a block diagram of a positioning device according to an embodiment of the invention. As shown in FIG. 6, the device includes a first acquisition module 11 for acquiring first position data of a reference object of a target object based on an electronic map; , a second acquisition module 12 for acquiring second position data of the reference object; and a positioning module 13 for positioning the target object based on the first position data and the second position data. Prepare.

In one possible implementation, the positioning module 13 further obtains first positioning data of the target object, and corrects the first positioning data based on the first position data and the second position data. to obtain second positioning data for indicating a positioning result of the target object.

In one possible implementation, the positioning module 13 further determines a position correction amount based on a positional relationship in a target coordinate system between the first position data and the second position data of the reference object, and The second positioning data is obtained by correcting the first positioning data based on the position correction amount. The target coordinate system is a coordinate system established based on the target object.

In one possible implementation, the position correction amount includes a rotation matrix, and the positioning module 13 further obtains a rotation angle between the first position data and the second position data, configured to determine the rotation matrix based on angles;

In one possible implementation, the position correction amount comprises a first translation component and a second translation component, the first translation component being perpendicular to the second translation component and the reference The object is parallel to the first translation component, and the positioning module 13 further obtains a rotation angle between the first position data and the second position data, and adjusts the rotation angle and It is configured to identify the first translation component and the second translation component based on position data, and the position data to be adjusted is the first position data or the second position data.

In one possible implementation, the first translation component and the second translation component are unit vectors.

In one possible implementation, the first obtaining module 11 further obtains the geographic coordinates of the reference object in the electronic map, performs coordinate transformation processing on the geographic coordinates of the reference object, and converts the electronic It is configured to obtain first position data of said reference object in a map in a target coordinate system, said target coordinate system being a coordinate system established based on said target object.

In one possible implementation, the second acquisition module 12 further performs a semantic segmentation process on the target image to obtain the position coordinates in the target image of the reference object, and for the position coordinates configured to perform a coordinate transformation process to obtain second position data of a reference object in the target image in a target coordinate system, the target coordinate system being a coordinate system established based on the target object; .

In one possible implementation, the second acquisition module 12 further comprises position coordinates of at least some pixel points in a reference image captured by the image acquisition device and the at least one pixel point in the target coordinate system. a homography matrix is specified based on the positional coordinates of points corresponding to pixel points of the part, and coordinate transformation processing is performed on the positional coordinates of the reference object in the target image based on the homography matrix; configured to obtain the second position data;

In one possible implementation, the first position data and the second position data comprise point cloud data.

In one possible realization, the reference object comprises a lane, the first positioning data comprises satellite positioning data, and the image acquisition device is located at the target object.

In one possible realization, the device further comprises a relative localization module for determining a relative positional relationship between the target object and the reference object based on second positioning data of the target object. .

It will be appreciated that any of the above method embodiments referred to in the present invention may be combined with each other to form combined embodiments without contradicting the underlying logic. Due to space limitations, the description will not be repeated in the present invention.

Moreover, the present invention further provides an electronic device, a computer-readable storage medium, and a program. Any of the above may be used to implement any one method according to the present invention. For the corresponding technical solutions and descriptions, please refer to the relevant descriptions in the method section and will not be repeated.

As can be appreciated by those skilled in the art, in the above methods of specific embodiments, the order of steps does not imply a strict execution order and does not impose any limitations on the implementation procedure. The specific order of execution for each step should be specified in its function and possible underlying logic.

In some embodiments, the functions possessed by or the modules included in the apparatus according to embodiments of the present invention may be used to perform the methods described in the above method embodiments. For its specific implementation, please refer to the description of the method embodiment above. For the sake of simplicity, they are not repeated here.

Embodiments of the present invention further provide a computer-readable storage medium. The computer readable storage medium stores computer program instructions, and the method is performed when the computer program instructions are executed by the processor. The computer-readable storage medium may be a non-volatile computer-readable storage medium.

An embodiment of the invention further provides a computer program product. The computer program is stored in a storage medium, and the method is performed when the computer program is executed by a processor. The storage medium may be a non-volatile computer-readable storage medium.

An embodiment of the present invention further provides an electronic device. The electronic device comprises a processor and memory for storing processor-executable instructions. The processor is configured to perform the positioning method described above. An electronic device may be provided as a terminal, server or other form of device.

FIG. 7 is a block diagram of electronic device 800 according to one illustrative embodiment. For example, the electronic device 800 may be a terminal such as a mobile phone, computer, digital broadcasting terminal, message sending/receiving device, game console, tablet PC, medical device, fitness device, personal digital assistant, or the like.

Referring to FIG. 7, electronic device 800 includes one or more of the following units: processing unit 802, memory 804, power supply unit 806, multimedia unit 808, audio unit 810, input/output (I/O) An interface 812, a sensor unit 814 and a communication unit 816 may be provided.

The processing unit 802 typically controls the general operation of the electronic device 800, such as operations related to display, telephone calls, data communications, camera operations and recording operations. The processing unit 802 may comprise one or more processors 820 that execute instructions to perform all or part of the method steps described above. Processing unit 802 may also comprise one or more modules to facilitate interaction between processing unit 802 and other units. For example, processing unit 802 may include multimedia modules to facilitate interaction between multimedia unit 808 and processing unit 802 .

Memory 804 is configured to store each type of data to support operations on electronic device 800 . Examples of this data include any application program or method instructions for operating electronic device 800, contact data, phone book data, messages, pictures, videos, and the like. Memory 804 may be any type of volatile or nonvolatile storage device or combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable programmable read only memory. (EPROM), programmable read only memory (PROM), read only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

Power supply unit 806 provides power to each of the units of electronic device 800 . Power supply unit 806 may include a power management system, one or more power supplies, and other units involved in the generation, management and distribution of power for electronic device 800 .

A multimedia unit 808 comprises a screen that provides one output interface between the electronic device 800 and the user. In some examples, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, it may be implemented as a touch screen to receive input signals from the user. A touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor can not only sense the boundaries of a touch or slide action, but also detect the duration and pressure associated with the touch or slide action. In some embodiments, multimedia unit 808 includes one front and/or back camera head. The front camera head and/or the back camera head can receive external multimedia data when the electronic device 800 is in an operating mode, such as a photography mode or a video mode. Each of the front and back camera heads may be one fixed optical lens system or may have a focal length and optical zoom capability.

Audio unit 810 is configured to output and/or input audio signals. For example, the audio unit 810 comprises a microphone (MIC), which is configured to receive external audio signals when the electronic device 800 is in operating modes, such as calling mode, recording mode and voice recognition mode. be. The received audio signal can also be stored in memory 804 or transmitted via communication unit 816 . In some embodiments, audio unit 810 further includes a speaker for outputting audio signals.

I/O interface 812 provides an interface between processing unit 802 and peripheral interface modules, which may be keyboards, click wheels, buttons, and the like. These buttons may include, but are not limited to, home page button, volume button, boot button and lock button.

Sensor unit 814 includes one or more sensors for providing state estimates to electronic device 800 on various aspects. For example, the sensor unit 814 can detect the on/off state of the electronic device 800 , the relative position of the unit, for example, the unit is the display and numeric keypad of the electronic device 800 . The sensor unit 814 also detects changes in the position of the electronic device 800 or a unit of the electronic device 800, the presence or absence of contact between the user and the electronic device 800, the orientation or acceleration/deceleration of the electronic device 800, and the temperature change of the electronic device 800. can be further detected. Sensor unit 814 may include a proximity sensor for detecting the presence of nearby objects when there is no physical contact. The sensor unit 814 may also include optical sensors used for imaging applications, such as CMOS or CCD image sensors. In some embodiments, the sensor unit 814 may further include an acceleration sensor, gyro sensor, magnetic sensor, pressure sensor or temperature sensor.

Communication unit 816 is configured to facilitate wireless or wired communications between electronic device 800 and other user devices. The electronic device 800 can access wireless networks based on communication standards, such as WiFi, 2G, 3G, or a combination thereof. In one exemplary embodiment, communication unit 816 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication unit 816 may also include a near-field communication (NFC) module to facilitate short-range communication. For example, in the NFC module, it may be implemented by Radio Frequency Identification (RFID) technology, Infrared Data Association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

In an exemplary embodiment, the electronic device 800 includes one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic to perform the methods described above. It may be implemented by a device (PLD), field programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic components.

The illustrative embodiment further provides a non-volatile computer-readable storage medium, such as memory 804, containing computer program instructions. The computer program instructions may be executed by processor 820 of electronic device 800 to implement the method.

FIG. 8 is a block diagram of electronic device 1900 according to one illustrative embodiment. For example, electronic device 1900 may be provided as a server. Referring to FIG. 8, the electronic device 1900 includes a processing unit 1922, and the processing unit 1922 further includes one or more processors and memory resources represented by a memory 1932, the memory 1932 for processing. Stores instructions that may be executed by unit 1922, such as application programs. An application program stored in memory 1932 may comprise one or more modules, each module corresponding to a set of instructions. The processing unit 1922 is also configured to implement the method by executing instructions.

The electronic device 1900 includes a power supply unit 1926 configured to perform power management of the electronic device 1900; a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network; /O) interface 1958. Electronic device 1900 may operate an operating system stored in memory 1932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, or others.

Exemplary embodiments further provide a non-volatile computer-readable storage medium, eg, memory 1932 containing computer program instructions. The computer program instructions are executed by the processing unit 1922 of the electronic device 1900 to implement the method.

The present invention provides systems, methods and/or computer program products. A computer program product may include a computer-readable storage medium. A computer readable storage medium carries computer readable program instructions for causing a processor to implement aspects of the present invention.

A computer-readable storage medium may be a tangible device that retains and stores instructions for use with a command-executing device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (non-exhaustive list) of computer readable storage media are portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory). ), Static Random Access Memory (SRAM), Portable Compressed Disk Read Only Memory (CD-ROM), Digital Versatile Disk (DVD), Memory Stick, Floppy Disk, Mechanical Encoding Devices, e.g. Including punch cards or protrusion-in-channel structures, and any suitable combination of the above. Computer-readable storage media, as used herein, refers to instantaneous signals themselves, e.g., radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagated through waveguides or other transmission media (e.g., fiber optic cables) light pulses over wires), or as electrical signals transmitted over wires.

The computer readable program instructions described herein may be downloaded from a computer readable storage medium to each computing/processing device, or transferred to an external computer or externally via networks such as the Internet, local area networks, wide area networks and/or wireless networks. It may be downloaded to a storage device. A network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. A network adapter or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage on a computer-readable storage medium in each computing/processing device.

Computer program instructions for carrying out the operations of the present invention may be assembly instructions, Instruction Set Architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or one or more of It may be source code or target code written in any combination of programming languages. The programming languages include object-oriented programming languages (eg, Smalltalk, C++, etc.) and conventional process programming languages (eg, "C" language) or similar programming languages. The computer-readable program instructions may be executed entirely on the user computer, partially executed on the user computer, executed as a separate software package, or partially executed on the user computer. but partly may be executed on the remote computer, or may be executed entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user computer via any kind of network, including a local area network (LAN) or a wide area network (WAN), or to an external computer. (eg, connected to the Internet using an Internet Service Provider). In some embodiments, state information in computer readable program instructions is used to customize electronic circuits, such as programmable logic circuits, field programmable gate arrays (FPGAs), or programmable logic arrays (PLAs) with personalization. The electronic circuitry is capable of implementing aspects of the invention by executing computer readable program instructions.

Aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented in computer readable program instructions.

These computer readable program instructions can be supplied to a processor of a general purpose computer, special purpose computer or other programmable data processing apparatus to produce a machine. As such, an apparatus that, when executed by a processor of a computer or other programmable data processing apparatus, implements the functions/acts specified in one or more of the blocks in the flowchart illustrations and/or block diagrams. , is generated. These computer readable program instructions may be stored on a computer readable storage medium. These instructions cause computers, programmable data processing devices, and/or other equipment to operate in specific manners. As such, a computer-readable medium having instructions stored thereon may comprise an article of manufacture, which includes instructions for each aspect of implementing the functions/acts specified in one or more blocks in the flowcharts and/or block diagrams. including.

The computer readable program instructions may be loaded into a computer, other programmable data processing device, or other equipment. Thus, a series of operational steps are performed on a computer, other programmable data processing device, or other machine to produce a computer-implemented process. The instructions executed on the computer, other programmable data processing device, or other device, thereby implement the functions/acts specified in one or more of the blocks in the flowchart illustrations and/or block diagrams.

The flowcharts and block diagrams in the drawings illustrate the possible architectural architecture, functionality, and operation of systems, methods and computer program products according to several embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent part of a module, program segment or instruction. A portion of said module, program segment or instruction contains one or more executable instructions for performing a defined logical function. In some alternative implementations, the functions marked in the block may occur out of the order noted in the figures. For example, two consecutive blocks may indeed be executed essentially in parallel, and sometimes in reverse order, depending on their functionality. It should be noted that each block in the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, are implemented in dedicated hardware-based systems that perform the specified functions or acts. Alternatively, it may be implemented in a combination of dedicated hardware and computer instructions.

Above, each embodiment of the present invention was described. The above description is illustrative, not exhaustive, and not limited to each disclosed embodiment. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of each described embodiment. The terms in this text are chosen to best interpret the principle, practical application, or technical improvement over the technology in the market of each embodiment, or to enable those skilled in the art to understand each embodiment disclosed herein. be.

This application is filed with the Patent Office of China on April 21, 2020, with application number CN. 202010316617. X and entitled "Positioning method and device, electronic equipment and storage medium", the entire content of which is incorporated herein by reference.

Claims (20)

obtaining first position data of the reference object of the target object based on the electronic map;
obtaining second position data of the reference object based on a target image captured with an image acquisition device;
positioning the target object based on the first position data and the second position data. Positioning the target object based on the first position data and the second position data comprises:
obtaining first positioning data of the target object;
obtaining second positioning data for indicating a positioning result of the target object by correcting the first positioning data based on the first position data and the second position data. The positioning method according to claim 1. Acquiring the second positioning data by correcting the first positioning data based on the first position data and the second position data,
specifying a position correction amount based on a positional relationship in a target coordinate system between the first position data and the second position data of the reference object;
Acquiring the second positioning data by correcting the first positioning data based on the position correction amount,
3. The positioning method according to claim 2, wherein the target coordinate system is a coordinate system established based on the target object. The position correction amount includes a rotation matrix,
Specifying the position correction amount based on the positional relationship in the target coordinate system between the first position data and the second position data of the reference object includes:
obtaining a rotation angle between the first position data and the second position data;
and determining the rotation matrix based on the rotation angle. The position correction amount includes a first translation component and a second translation component, wherein the first translation component is perpendicular to the second translation component, and the reference object has the first translation component. is parallel to the component and
Identifying a position correction amount based on the first position data and the second position data of the reference object includes:
obtaining a rotation angle between the first position data and the second position data;
determining the first translation component and the second translation component based on the rotation angle and position data to be adjusted;
5. The positioning method according to claim 3, wherein said position data to be adjusted is said first position data or said second position data. The positioning method according to claim 5, wherein the first translation component and the second translation component are unit vectors. The step of obtaining first position data of a reference object based on the electronic map comprises:
obtaining geographic coordinates of the reference object in the electronic map;
performing a coordinate transformation process on the geographic coordinates of the reference object to obtain first position data of the reference object in the electronic map in a target coordinate system;
The positioning method according to any one of claims 1 to 6, wherein the target coordinate system is a coordinate system established based on the target object. obtaining second position data of the reference object based on a target image captured by the image acquisition device;
performing a semantic segmentation process on the target image to obtain position coordinates of the reference object in the target image;
performing coordinate transformation processing on the position coordinates to obtain second position data in the target coordinate system of the reference object in the target image;
The positioning method according to any one of claims 1 to 7, wherein the target coordinate system is a coordinate system established based on the target object. performing coordinate transformation processing on the position coordinates to obtain second position data of the reference object in the target image in the target coordinate system,
homography based on the positional coordinates of at least some pixel points in the reference image captured by the image acquisition device and the positional coordinates of points corresponding to the at least some pixel points in the target coordinate system; identifying a matrix;
9. The method according to claim 8, further comprising performing coordinate transformation processing on position coordinates of the reference object in the target image based on the homography matrix to obtain the second position data. positioning method. The positioning method according to any one of claims 1 to 9, wherein the first position data and the second position data include point cloud data. 11. The reference object of any one of claims 1 to 10, wherein the reference object comprises a lane, the first positioning data comprises satellite positioning data, and the image acquisition device is provided at the target object. The positioning method described in . 12. A method as claimed in any preceding claim, further comprising determining a relative positional relationship between the target object and the reference object based on second positioning data of the target object. positioning method. a first acquisition module for acquiring first position data of the reference object of the target object based on the electronic map;
a second acquisition module for acquiring second position data of the reference object based on a target image captured by an image acquisition device;
a positioning module for positioning the target object based on the first position data and the second position data. The positioning module further comprises:
obtaining first positioning data of the target object;
configured to obtain second positioning data for indicating a positioning result of the target object by correcting the first positioning data based on the first position data and the second position data; 14. The positioning device according to claim 13. The positioning module further comprises:
specifying a position correction amount based on a positional relationship in a target coordinate system between the first position data and the second position data of the reference object;
configured to acquire the second positioning data by correcting the first positioning data based on the position correction amount;
15. The positioning device according to claim 14, wherein the target coordinate system is a coordinate system established based on the target object. The position correction amount includes a rotation matrix,
The positioning module further comprises:
obtaining a rotation angle between the first position data and the second position data;
16. A positioning device according to claim 15, configured to determine the rotation matrix based on the rotation angle. The position correction amount includes a first translation component and a second translation component, wherein the first translation component is perpendicular to the second translation component, and the reference object has the first translation component. is parallel to the component and
The positioning module further comprises:
obtaining a rotation angle between the first position data and the second position data;
configured to identify the first translation component and the second translation component based on the rotation angle and position data to be adjusted;
17. The positioning device according to claim 15, wherein the position data to be adjusted is the first position data or the second position data. an electronic device,
a processor;
a memory for storing instructions executable by the processor;
An electronic device, wherein the processor is configured to perform the positioning method according to any one of claims 1-12. A computer readable storage medium on which computer program instructions are stored, comprising:
A computer readable storage medium characterized in that, when said computer program instructions are executed by a processor, a positioning method according to any one of claims 1 to 12 is implemented. A computer program stored on a storage medium,
A computer program, characterized in that a positioning method according to any one of claims 1 to 12 is implemented when said computer program is executed by a processor.

Images