CN112967393B

CN112967393B - Correction method and device for vehicle movement track, electronic equipment and storage medium

Info

Publication number: CN112967393B
Application number: CN202110282941.9A
Authority: CN
Inventors: 单国航; 朱磊; 贾双成; 李倩; 李成军
Original assignee: Zhidao Network Technology Beijing Co Ltd
Current assignee: Zhidao Network Technology Beijing Co Ltd
Priority date: 2021-03-16
Filing date: 2021-03-16
Publication date: 2024-02-13
Anticipated expiration: 2041-03-16
Also published as: CN112967393A

Abstract

The application relates to a method and a device for correcting a vehicle movement track, electronic equipment and a storage medium. The method comprises the following steps: constructing an SLAM moving track by using a picture sequence shot when the vehicle runs; calculating a first scale factor by using the predicted longitude and the predicted latitude of the vehicle when at least two frames of first target pictures are shot and the positioning longitude and the positioning latitude correspondingly measured by the positioning system; performing scale transformation on the predicted height of the vehicle when each frame of picture is shot according to the first scale factor to obtain SLAM track height; correcting the track height measured by the positioning system by utilizing the SLAM track height; calculating correction parameters by using the predicted longitude, the predicted latitude and the predicted height of the vehicle when at least two frames of second target pictures are shot and the positioning longitude, the positioning latitude and the corrected positioning height which are correspondingly measured by the positioning system; and correcting the SLAM moving track according to the correction parameters. The method and the device can improve the accuracy of the moving track of the vehicle.

Description

Correction method and device for vehicle movement track, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of navigation technologies, and in particular, to a method and apparatus for correcting a movement track of a vehicle, an electronic device, and a storage medium.

Background

Positioning systems such as GPS (Global Positioning System ), RTK (Real-time kinematic) and the like are widely used in positioning and tracking of vehicles due to their high accuracy and good performance. However, in practical applications, it is found that sometimes, an unreasonable jump occurs in the positioning height measured by the positioning system, especially in a position where positioning signals are poor, such as under a bridge, in a culvert, in a tunnel or between dense buildings, etc., the measured positioning height deviation is larger, so that the accuracy of the positioning height measurement result of the vehicle is poor.

SLAM (Simultaneous Localization And Mapping, instant positioning and map construction) is mainly used for solving the problems of positioning navigation and map construction when mobile equipment runs in an unknown environment, and has higher positioning precision. However, the movement locus obtained by the positioning navigation by SLAM is relative and not a true movement locus. Therefore, to obtain a high-precision movement trajectory, the relative trajectory needs to be corrected.

Disclosure of Invention

In order to solve or partially solve the problems in the related art, the application provides a method, a device, an electronic device and a storage medium for correcting a vehicle movement track, which can improve the accuracy of the vehicle movement track.

The first aspect of the present application provides a method for correcting a movement track of a vehicle, including:

acquiring a picture sequence shot by a vehicle in a driving process, and acquiring shooting time of each frame of picture in the picture sequence;

constructing a SLAM moving track of the vehicle by using the picture sequence, wherein the SLAM moving track comprises a combination of predicted positions of the vehicle when each frame of picture is taken, and the predicted positions comprise a predicted longitude, a predicted latitude and a predicted altitude;

calculating a first scale factor by using the predicted longitude and the predicted latitude of the vehicle when at least two frames of first target pictures are shot in the SLAM moving track and the positioning longitude and the positioning latitude which are correspondingly measured by a positioning system of the vehicle at the shooting time of the at least two frames of first target pictures;

performing scale transformation on the predicted height of the vehicle when each frame of picture is shot in the SLAM moving track according to the first scale factor to obtain SLAM track height;

correcting the track height measured by the positioning system by utilizing the SLAM track height to obtain the corrected track height of the positioning system;

calculating correction parameters of the SLAM moving track by using the predicted longitude, the predicted latitude and the predicted height of the vehicle when at least two frames of second target pictures are shot on the SLAM moving track and the positioning longitude, the positioning latitude and the corrected positioning height which are correspondingly measured by the positioning system at the shooting time of the at least two frames of second target pictures, wherein the correction parameters comprise at least one of a second scale factor, a rotation matrix and a translation matrix, and the corrected positioning height is the positioning height corresponding to the shooting time in the track height of the corrected positioning system;

And correcting the SLAM moving track according to the correction parameters to obtain a corrected moving track.

Preferably, the correcting the track height measured by the positioning system by using the SLAM track height to obtain the corrected track height of the positioning system includes:

respectively acquiring a weighting coefficient of the position height of the vehicle in the SLAM track height and a weighting coefficient of the positioning height measured by the positioning system at each shooting time; the position height of the vehicle is obtained by scaling the predicted height of the vehicle by using the first scale factor;

and weighting the position height of the vehicle and the positioning height at each shooting time by using a weighting coefficient to obtain the corrected track height of the positioning system.

Preferably, the step of obtaining the weighting coefficient of the position height of the vehicle and the weighting coefficient of the positioning height measured by the positioning system at each photographing time respectively includes:

identifying pictures acquired at each shooting time, and respectively acquiring the position environment of the vehicle;

when the environment of the position of the vehicle, which is identified by the picture, meets the preset condition, a first weighting coefficient of the position height of the vehicle at the shooting time of the picture and a second weighting coefficient of the positioning height measured by the positioning system are obtained, wherein the first weighting coefficient is larger than the second weighting coefficient;

When the environment where the vehicle is located and identified by the picture does not meet the preset condition, a third weighting coefficient of the position height of the vehicle and a fourth weighting coefficient of the positioning height measured by the positioning system at the shooting time of the picture are obtained, wherein the third weighting coefficient is different from the first weighting coefficient, and the fourth weighting coefficient is different from the second weighting coefficient.

acquiring an initial positioning height measured by the positioning system;

calculating the height difference between the positioning height measured by the positioning system and the initial positioning height at each shooting time;

when the difference between the positioning height measured by the positioning system at the shooting time and the initial positioning height is larger than a preset value, a first weighting coefficient of the position height of the vehicle at the shooting time and a second weighting coefficient of the positioning height measured by the positioning system are obtained, wherein the first weighting coefficient is larger than the second weighting coefficient;

And when the height difference between the positioning height measured by the positioning system and the initial positioning height at the shooting time is smaller than or equal to the preset value, acquiring a third weighting coefficient of the position height of the vehicle at the shooting time and a fourth weighting coefficient of the positioning height measured by the positioning system, wherein the third weighting coefficient is different from the first weighting coefficient, and the fourth weighting coefficient is different from the second weighting coefficient.

Preferably, the number of the at least two second target pictures is greater than the number of the at least two first target pictures, the calculating the correction parameters of the SLAM moving track by using the predicted longitude, the predicted latitude and the predicted altitude of the vehicle when the at least two second target pictures are taken on the SLAM moving track, and the positioning longitude, the positioning latitude and the correction positioning altitude correspondingly measured by the positioning system at the time of taking the at least two second target pictures includes:

and calculating the correction parameters of the SLAM moving track by using a least square optimization algorithm according to the predicted longitude, the predicted latitude and the predicted height of the vehicle when at least two frames of second target pictures are shot on the SLAM moving track and the positioning longitude, the positioning latitude and the correction positioning height which are correspondingly measured by the positioning system at the shooting time of the at least two frames of second target pictures.

Preferably, the correction parameters include a second scale factor, a rotation matrix and a translation matrix, and the correcting the SLAM movement track according to the correction parameters to obtain a corrected movement track includes:

performing scale transformation on the SLAM moving track by using the second scale factor to obtain a new SLAM moving track;

and rotating and translating the new SLAM movement track according to the rotation matrix and the translation matrix to obtain a corrected movement track.

A second aspect of the present application provides a correction device for a movement track of a vehicle, including:

the image acquisition unit is used for acquiring a picture sequence shot by the vehicle in the driving process and acquiring shooting time of each frame of picture in the picture sequence;

a track construction unit configured to construct a SLAM movement track of the vehicle using the picture sequence, wherein the SLAM movement track includes a combination of predicted positions of the vehicle when each of the frames of pictures is taken, the predicted positions including a predicted longitude, a predicted latitude, and a predicted altitude;

a first calculating unit, configured to calculate a first scale factor by using a predicted longitude and a predicted latitude of the vehicle when at least two frames of first target pictures are taken in the SLAM movement track, and a positioning longitude and a positioning latitude measured correspondingly by a positioning system of the vehicle at a time of taking the at least two frames of first target pictures;

The scale transformation unit is used for performing scale transformation on the predicted height of the vehicle when each frame of picture is shot in the SLAM moving track according to the first scale factor to obtain SLAM track height;

the height correction unit is used for correcting the track height measured by the positioning system by utilizing the SLAM track height to obtain the corrected track height of the positioning system;

the second calculating unit is used for calculating correction parameters of the SLAM moving track by using the predicted longitude, the predicted latitude and the predicted height of the vehicle when at least two frames of second target pictures are shot on the SLAM moving track and the positioning longitude, the positioning latitude and the corrected positioning height which are correspondingly measured by the positioning system at the shooting time of the at least two frames of second target pictures, wherein the correction parameters comprise at least one of a second scale factor, a rotation matrix and a translation matrix, and the corrected positioning height is the positioning height corresponding to the shooting time in the track height of the corrected positioning system;

and the track correction unit is used for correcting the SLAM moving track according to the correction parameters to obtain a corrected moving track.

Preferably, the method for obtaining the corrected track height of the positioning system by the height correction unit using the track height of the SLAM includes:

the height correction unit obtains a weighting coefficient of the position height of the vehicle in the SLAM track height under each shooting time and a weighting coefficient of the positioning height measured by the positioning system respectively, and performs weighting processing on the position height of the vehicle and the positioning height under each shooting time by using the weighting coefficient to obtain the corrected track height of the positioning system, wherein the position height of the vehicle is obtained by scaling the predicted height of the vehicle by using the first scale factor.

A third aspect of the present application provides an electronic device, comprising:

a processor; and

a memory having executable code stored thereon which, when executed by the processor, causes the processor to perform the method as described above.

A fourth aspect of the present application provides a non-transitory machine-readable storage medium having stored thereon executable code, which when executed by a processor of an electronic device, causes the processor to perform the method as described above.

According to the technical scheme, the jump of the height of the moving track measured by the positioning system is considered frequently, when the moving track measured by the positioning system is used for correcting the relative SLAM moving track of the vehicle constructed by the picture, the track height measured by the positioning system can be corrected first, the influence of the positioning height can be eliminated, and the inaccurate final track correction result caused by the positioning height deviation is avoided. Further, the moving track of the positioning system after the positioning height is corrected is used as a basis for correcting the relative SLAM moving track, so that the relative SLAM moving track is corrected to the real moving track, and the accuracy of the moving track of the vehicle can be improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Drawings

The foregoing and other objects, features and advantages of the application will be apparent from the following more particular descriptions of exemplary embodiments of the application as illustrated in the accompanying drawings wherein like reference numbers generally represent like parts throughout the exemplary embodiments of the application.

Fig. 1 is a flowchart of a method for correcting a vehicle movement track according to an embodiment of the present application;

FIG. 2a is a graph of the fluctuation of SLAM track height and GPS track height on the same road segment as shown in the embodiments of the present application;

FIG. 2b is a schematic diagram illustrating a comparison of a GPS movement track and a modified SLAM movement track on the same road segment according to an embodiment of the present application;

fig. 3 is a schematic structural view of a device for correcting a movement track of a vehicle according to an embodiment of the present application;

fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.

It should be understood that although the terms "first," "second," "third," etc. may be used herein to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first message may also be referred to as a second message, and similarly, a second message may also be referred to as a first message, without departing from the scope of the present application. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise. The following describes the technical scheme of the embodiments of the present application in detail with reference to the accompanying drawings.

Referring to fig. 1, an embodiment of the present application provides a method for correcting a movement track of a vehicle. As shown in fig. 1, the method may include the steps of:

110. and acquiring a picture sequence shot by the vehicle in the driving process, and acquiring shooting time of each frame of picture in the picture sequence.

In this embodiment of the present application, video data in a driving process may be collected by a camera device, where the camera device may include, but is not limited to, a device with a camera function, such as a driving recorder, a camera, or a mobile phone of a driver, which are installed on a vehicle. The image pickup device may be provided at the head of the vehicle to collect video of the front thereof, or may be provided at the tail of the vehicle to collect video of the rear thereof, which is not limited herein. In order to obtain a picture, it is necessary to extract frames from video data acquired by an image pickup device. Typically, the video is framed at a frame rate of 30 frames per second, and the video may be decimated according to preset rules, for example, 10 frames per second, 15 frames per second, 20 frames per second, 30 frames per second, or other values, to obtain a plurality of captured frames of pictures, which may form a sequence of pictures. The time interval of any two adjacent frames of pictures in the picture sequence is a frame extraction time interval. In addition, the image pickup device can record the shooting time of the picture while shooting the picture.

The method provided by the embodiment of the application can be applied to a vehicle and a machine, and can also be applied to other devices with calculation and processing functions, such as a computer, a mobile phone and the like. Taking the car machine as an example, the camera device and the positioning system can be arranged in the car machine or outside the car machine, and communication connection is established between the camera device and the car machine.

120. And constructing the SLAM moving track of the vehicle by using the picture sequence.

In the embodiment of the application, the SLAM positioning is performed by using the acquired picture sequence, so that the SLAM positioning position of the vehicle when each frame of picture is shot can be obtained, and the SLAM positioning position is regarded as the prediction position. The SLAM movement track of the vehicle may be drawn by taking a predicted position of the vehicle at each frame of picture, i.e., the SLAM movement track includes a combination of the predicted positions of the vehicle at each frame of picture, which may include a predicted longitude, a predicted latitude, and a predicted altitude. Since the SLAM movement track of the vehicle is a relative track of the vehicle, not a real movement track of the vehicle, the SLAM movement track of the vehicle needs to be corrected in order to obtain the real movement track of the vehicle.

It will be appreciated that the predicted position of the vehicle when each frame of picture is taken by SLAM is generally represented by UTM (Universal Transverse Mercator Grid System, universal transverse ink card grid system) coordinates, where the UTM coordinates are converted into latitude and longitude coordinates, so as to facilitate unification of the latitude and longitude coordinates with the latitude and longitude coordinates measured by the positioning system in the same coordinate system. If the positioning coordinates measured by the positioning system are the coordinates in the UTM coordinate system, the predicted position obtained by SLAM does not need to be converted into longitude and latitude coordinates.

In an alternative embodiment, the specific embodiment of constructing the SLAM movement track of the vehicle using the picture sequence in step 120 may include the steps of:

11 Determining the size of a sliding window, wherein the sliding window can comprise at least two frames of pictures with adjacent shooting time in a picture sequence;

12 Constructing three-dimensional space coordinates according to the at least two frames of pictures;

13 Acquiring a next frame of picture positioned behind the at least two frames of pictures in the picture sequence;

14 Determining the pose of the monocular camera device when the next frame of picture is shot according to the next frame of picture and the three-dimensional space coordinates;

15 According to the pose of the monocular camera device when the next frame of picture is shot, obtaining the predicted position of the vehicle when the next frame of picture is shot;

16 Sliding the sliding window in a picture sequence with a preset step length, and repeatedly executing the steps 11) to 15) to respectively obtain the predicted position of the vehicle when each frame of picture is shot;

17 A SLAM moving track of the vehicle is generated according to the predicted position of the vehicle when each frame of picture is taken.

The specific embodiment of step 12) of constructing the three-dimensional space coordinate according to the at least two frames of pictures may include: acquiring characteristic points of each frame of pictures in the at least two frames of pictures; matching the characteristic points of the at least two frames of pictures to obtain a target characteristic point set successfully matched in the at least two frames of pictures; and constructing three-dimensional space coordinates according to the target feature point set.

Optionally, when the picture is collected, the time watermark is often displayed on the picture, and part of the car body of the vehicle is also photographed due to the problem of photographing angle of the photographing device, and even the influence factors such as light reflection and aperture in the picture can be caused due to weather or light. These factors are hardly changed during forward travel of the vehicle, and when the picture feature point matching is performed, these factors are matched in a large amount. Therefore, when the three-dimensional space coordinates are constructed by using the characteristic points in the follow-up process, the calculated amount is greatly increased, and the result is inaccurate. Therefore, the above factors need to be removed to exclude the influence of the above factors on the result. Specifically, it is assumed that two frames of pictures are utilized to construct three-dimensional space coordinates, and a successfully matched target feature point set in the two frames of pictures can be regarded as a target feature point pair. And acquiring pixel coordinates of all the target feature points in the two pictures respectively, calculating the distance between the two pixel coordinates in each target feature point pair, deleting the target feature point pairs with the distance between the pixel coordinates smaller than the preset distance, and constructing three-dimensional space coordinates by using the residual target feature point pairs.

130. And calculating a first scale factor by using the predicted longitude and the predicted latitude of the vehicle when at least two frames of first target pictures are shot in the SLAM moving track and the positioning longitude and the positioning latitude which are correspondingly measured by a positioning system of the vehicle when at least two frames of first target pictures are shot.

Because the positioning height of the positioning system can often generate unreasonable jump, especially in the position with poor positioning signals, such as under the bridge, between culverts, tunnels or dense buildings, the jump amplitude is larger. If the movement track measured by the positioning system is directly used for correcting the SLAM movement track, the track height in the SLAM movement track is inaccurate, so that the track height of the positioning system needs to be corrected first. The track height in the SLAM moving track constructed by the pictures is stable and high in accuracy, so that the track height of the positioning system can be corrected by utilizing the SLAM track height. However, the track height in the SLAM moving track is a relative height, and therefore, it is necessary to first scale it to be converted into an actual height.

Specifically, to scale the height of the SLAM moving track of the vehicle, the predicted longitude and the predicted latitude of the vehicle when at least two frames of the first target pictures are taken on the SLAM moving track may be obtained. And, the positioning system may acquire the positioning position of the vehicle measured at the shooting time of the at least two frames of target pictures, where the positioning position may include a positioning longitude, a positioning latitude, and a positioning altitude. The positioning system may include, but is not limited to, at least one of a GPS, a beidou satellite positioning system, an RTK positioning system, and the like.

The positioning system defaults to a positioning position of the vehicle measured by the shooting time of the at least two frames of first target pictures, namely the positioning position is an accurate positioning position when the positioning system is in a positioning position measured by the signal with good signal. When the positioning system is more accurate in positioning at the starting navigation time and the ending navigation time, the vehicle positioning positions of at least two points can be obtained by the positioning system, and correspondingly, the at least two frames of first target pictures are pictures shot at the at least two points; or the vehicle positioning position of at least two points can be obtained by the positioning system, and correspondingly, the at least two frames of first target pictures are pictures shot at the at least two points; or the positioning system can acquire the vehicle positioning position of the initial point or points and the vehicle positioning position of the final point or points, and correspondingly, the at least two frames of first target pictures are pictures shot at the points; or the positioning system acquires the vehicle positioning positions of points with better signals, and correspondingly, the at least two frames of first target pictures are pictures shot at the points.

Because the positioning height measured by the positioning system is inaccurate, the influence of the positioning height can be eliminated when the first scale factor is calculated, so that the calculation result is more accurate.

In an alternative embodiment, when the at least two first target pictures include only two first target pictures, the step 130 may use the predicted longitude and the predicted latitude of the vehicle when the at least two first target pictures are taken in the SLAM moving track, and the positioning longitude and the positioning latitude measured by the positioning system of the vehicle corresponding to the time of taking the at least two first target pictures, and the specific embodiment of calculating the first scale factor may include the following steps:

13a) Obtaining a first moving distance of the vehicle according to the predicted longitude and the predicted latitude of the vehicle when the two frames of first target pictures are shot in the SLAM moving track;

13b) Obtaining a second moving distance of the vehicle according to the positioning longitude and the positioning latitude correspondingly measured by the positioning system when the two frames of first target pictures are shot;

13c) And calculating the ratio of the second moving distance to the first moving distance, and determining the ratio as a first scale factor of the SLAM moving track.

For example, assume that the two first target pictures are a start frame picture P1 and an end frame picture P2, respectively, and the predicted longitude and latitude coordinates of the vehicle when the picture P1 is taken are P1 _slam (x 1, y 1), the predicted longitude and latitude coordinates of the vehicle at the time of taking the picture P2 are P2 _slam (x 2, y 2). According to the two predicted longitude and latitude coordinates, a first moving distance d1 between the two coordinates can be obtained. Specifically, longitude and latitude coordinates P1 _slam (x 1, y 1) is converted into UTM coordinates to obtain P1 _{s_u} (x 1', y 1') and longitude and latitude coordinates P2 _slam (x 2, y 2) is converted into UTM coordinates to obtain P2 _{s_u} (x 2', y 2'), d1=sqrt ((x 2'-x 1') 2+ (y 2'-y 1')2). The longitude and latitude coordinates of the vehicle are P1 when the picture P1 is taken _gps (x 3, y 3) to UTM coordinates to obtain P1 _{g_u} (x 3', y 3') the longitude and latitude coordinates of the vehicle at the time of taking the picture P2 are P2 _gps (x 4, y 4) to UTM coordinates to obtain P2 _{g_u} (x 4', y 4'), according to the two UTM coordinates, the second movement distance d2=sqrt ((x 4'-x 3')2+ (y 4'-y 3')2) between the two can be obtained. The first scale factor can be obtained according to the ratio of the second moving distance d2 to the first moving distance d1s1, i.e. the first scale factor s1=d2/d 1.

In an alternative embodiment, when the at least two first target pictures include more than two first target pictures, the step 130 may use the predicted longitude and the predicted latitude of the vehicle when the at least two first target pictures are taken in the SLAM moving track, and the positioning longitude and the positioning latitude measured by the positioning system of the vehicle corresponding to the time of taking the at least two first target pictures, and the specific embodiment of calculating the first scale factor may include the following steps:

13d) And calculating a first scale factor of the SLAM moving track by using a least square optimization algorithm according to the predicted longitude and the predicted latitude of the vehicle when the more than two frames of first target pictures are shot in the SLAM moving track and the positioning longitude and the positioning latitude which are correspondingly measured by the positioning system.

For example, when the more than two first target pictures are three first target pictures, it is assumed that the three first target pictures are a picture P1, a picture P2 and a picture P3, respectively, and the predicted longitude and latitude coordinates of the vehicle when the picture P1 is taken are P1 _slam (x 1, y 1), the predicted longitude and latitude coordinates of the vehicle at the time of taking the picture P2 are P2 _slam (x 2, y 2), the predicted longitude and latitude coordinates of the vehicle at the time of taking the picture P3 are P3 _slam (x 3, y 3). The longitude and latitude coordinates of the vehicle are P1 when the picture P1 is taken _gps (x 4, y 4), the longitude and latitude coordinates of the vehicle at the time of taking the picture P2 are P2 _gps (x 5, y 5), the longitude and latitude coordinates of the vehicle at the time of taking the picture P3 are P3 _gps (x 6, y 6). The first scale factor s1 cannot be determined solely by the distance ratio due to the influence of positioning errors. The error equation can thus be established using a least squares optimization algorithm:

error = s1 * Pi _{s_u} –Pi _{g_u}

wherein Pi is _{s_u} Refers to UTM coordinates and Pi converted from predicted longitude and latitude coordinates of a vehicle when an ith frame of picture is taken _{g_u} The UTM coordinate is converted from the positioning longitude and latitude coordinate of the vehicle when the ith frame of picture is taken. Substituting these coordinates into the error equation, an optimal solution can be obtained, which contains the minimum positioningError, and a first scale factor s1 corresponding to the minimum positioning error.

It should be understood that the above-mentioned more than two frames of the first target picture are exemplified by three frames, but not limited thereto, and the above-mentioned more than two frames of the first target picture may be more than three frames of pictures, such as 4 frames, 5 frames, 6 frames or other values, which are not limited herein.

140. And performing scale transformation on the predicted height of the vehicle when each frame of picture is shot in the SLAM moving track according to the first scale factor to obtain the SLAM track height.

150. And correcting the track height measured by the positioning system by utilizing the SLAM track height to obtain the corrected track height of the positioning system.

In the embodiment of the application, after the first scale factor s1 is obtained, the predicted height of the vehicle when each frame of picture is shot in the SLAM moving track can be stretched according to the first scale factor s1, and when the first scale factor s1 is a number larger than 1, the size of the predicted height can be stretched to be s1 times of the original size; when the first scale factor s1 is a number smaller than 1, the size of the predicted height can be reduced to s1 times as large as the original. And the predicted height corresponding to each frame of picture stretches and contracts according to the mode, and the stretched predicted heights are combined into SLAM track height.

Further, the SLAM track height obtained through the scale transformation can be used for correcting the track height measured by the positioning system. The track height measured by the GPS positioning system will be described as an example. Fig. 2a shows the track height and SLAM track height measured by GPS on the same flatter road segment over the same time period, where the abscissa is time in milliseconds (ms) and the ordinate is height in meters (m). In the figure, the waveform curve represented by the dashed line bar is the track height measured by the GPS, and the waveform curve represented by the solid line bar is the SLAM track height. As can be seen from fig. 2a, the fluctuation of the GPS track height is large, the fluctuation height difference can even reach 30m, the measurement result is unstable, and the accuracy is poor. The SLAM track has small fluctuation, the whole waveform curve is nearly similar to a straight line, and the measurement result is stable. It should be noted that fig. 2a shows only the measurement result taken for a certain period of time, and not the measurement result of the whole driving process.

There are a number of ways to use SLAM track height to correct the track height measured by the positioning system. For example, the SLAM track height may be directly replaced by the track height measured by the positioning system, i.e., the SLAM track height is used as the track height of the positioning system after correction. For another example, the track height of the SLAM and the track height measured by the positioning system may be averaged, and the obtained average track height may be used as the track height of the positioning system after correction.

In an alternative embodiment, the step 150 of correcting the track height measured by the positioning system by using the SLAM track height, and the specific embodiment of obtaining the corrected track height of the positioning system may include the following steps:

15a) Respectively acquiring a weighting coefficient of the position height of the vehicle in the SLAM track height at each shooting time and a weighting coefficient of the positioning height measured by a positioning system; the position height of the vehicle is obtained by scaling the predicted height of the vehicle by using a first scale factor;

15b) And weighting the position height and the positioning height of the vehicle at each shooting time by using a weighting coefficient to obtain the track height of the positioning system after correction.

Specifically, after the predicted height of the vehicle in a certain shooting time stretches and contracts through the first scale factor, the position height of the vehicle in the shooting time is obtained. The weighting coefficients of the position heights of the vehicles at different photographing times may be all the same or partially the same or all different, and similarly, the weighting coefficients of the positioning heights of the positioning systems at different photographing times may be all the same or partially the same or all different. The weighting coefficient of the position height of the vehicle at the same photographing time may be the same as or different from the weighting coefficient of the positioning height. The range of the weighting coefficient may be greater than or equal to 0 and less than or equal to 1.

For example, it is assumed that the weighting coefficients of the position heights of the vehicles at different photographing times are the same, and the weighting coefficients of the position heights of the vehicles at different photographing times are also the same. If the weighting coefficient of the position height of the vehicle is 1 and the weighting coefficient of the positioning height of the vehicle is 0, the position height of the vehicle at each shooting time can be regarded as replacing the positioning height of the vehicle, namely, the SLAM track height is directly replaced by the track height measured by the positioning system, so that the SLAM track height is taken as the track height of the positioning system after correction. If the weighting coefficient of the position height of the vehicle is 0.5 and the weighting coefficient of the positioning height of the vehicle is also 0.5, the position height and the positioning height of the vehicle at each photographing time can be considered as an average value, that is, the SLAM track height and the track height measured by the positioning system are averaged, and the obtained average track height is taken as the track height of the positioning system after correction. If the weighting coefficient of the position height of the vehicle is 0.8 and the weighting coefficient of the positioning height of the vehicle is 0.2, the position height and the positioning height of the vehicle at each shooting time can be weighted according to the weighting coefficient corresponding to the position height and the positioning height of the vehicle, and the track height of the positioning system after correction is obtained.

Optionally, in step 15 a), the weighting coefficient of the position height of the vehicle in the SLAM track height and the weighting coefficient of the positioning height measured by the positioning system may be determined by acquiring the target parameter at each photographing time, where the target parameter at each photographing time may include at least one of the position environment where the vehicle is located at each photographing time, the positioning height measured by the positioning system at each photographing time, the signal intensity of the positioning system at each photographing time, and so on.

In an alternative embodiment, the step 15 a) of obtaining the weighting coefficient of the position height of the vehicle in the SLAM track height at each photographing time and the weighting coefficient of the positioning height measured by the positioning system respectively may include the following steps:

identifying pictures acquired at each shooting time to respectively acquire the position environment of the vehicle;

when the position environment of the vehicle identified by the picture meets the preset condition, acquiring a first weighting coefficient of the position height of the vehicle at the shooting time of the picture and a second weighting coefficient of the positioning height measured by the positioning system, wherein the first weighting coefficient is larger than the second weighting coefficient;

when the environment of the position of the vehicle identified by the picture does not meet the preset condition, a third weighting coefficient of the position height of the vehicle at the shooting time of the picture and a fourth weighting coefficient of the positioning height measured by the positioning system are obtained, wherein the third weighting coefficient is different from the first weighting coefficient, and the fourth weighting coefficient is different from the second weighting coefficient.

Specifically, scene recognition can be performed on each acquired frame of picture to identify the current position environment of the vehicle. The condition that the environment of the vehicle is satisfied with the preset condition may include that the environment of the vehicle is a high-rise dense place, a tunnel, a culvert, a overpass under or near, and the like. The positioning signals of a typical positioning system are not good in these circumstances, thus affecting the measurement of the positioning height.

For example, the pictures acquired from time t1 to time t2 (including time t 2) identify that the vehicle is under the overpass, and the pictures acquired from time t2 (excluding time t 2) to time t3 identify that the vehicle is on the clear road. Assuming that the first weighting coefficient of the position height of the vehicle from the time t1 to the time t2 is 1, the second weighting coefficient of the position height measured by the positioning system is 0, and the position height of the vehicle can be regarded as being replaced by the position height measured by the positioning system from the time t1 to the time t 2. the third weight coefficient of the position height of the vehicle from the time t2 to the time t3 is 0, the fourth weight coefficient of the position height measured by the positioning system is 1, and the position height measured by the positioning system can be regarded as reserved from the time t2 to the time t3, namely, the track height of the positioning system in the time period is not corrected. Alternatively, the third weight coefficient of the position height of the vehicle from the time t2 to the time t3 is 0.5, and the fourth weight coefficient of the positioning height measured by the positioning system is 0.5, and the obtained average track height can be regarded as the track height of the positioning system in the time period by taking the average value of the position height and the positioning height of the vehicle from the time t2 to the time t 3. And combining the track height corrected from the time t1 to the time t2 to obtain the track height of the positioning system corrected from the time t1 to the time t 3.

acquiring an initial positioning height measured by a positioning system;

when the difference between the positioning height measured by the positioning system under the shooting time and the initial positioning height is larger than a preset value, a first weighting coefficient of the position height of the vehicle under the shooting time and a second weighting coefficient of the positioning height measured by the positioning system are obtained, wherein the first weighting coefficient is larger than the second weighting coefficient;

when the difference between the positioning height measured by the positioning system under the shooting time and the initial positioning height is smaller than or equal to a preset value, a third weighting coefficient of the position height of the vehicle under the shooting time and a fourth weighting coefficient of the positioning height measured by the positioning system are obtained, wherein the third weighting coefficient is different from the first weighting coefficient, and the fourth weighting coefficient is different from the second weighting coefficient.

Specifically, since the initial positioning height of the positioning system is accurate, the positioning system can be used as a basis for height judgment. If the vehicle is traveling on a relatively flat road, the positioning height difference of the vehicle should be small in theory. When the difference between the measured positioning height and the initial positioning height at a certain moment is larger than a preset value, the measurement result at the moment can be considered to have larger jump, the result is inaccurate, and correction is needed. When the difference between the measured positioning height and the initial positioning height at a certain moment is smaller than or equal to a preset value, the measurement result at the moment can be considered to be more accurate, and appropriate correction or no correction can be performed. The preset value may be set according to the actual scene requirement, for example, the preset value is 1 meter, 1.5 meters, 2 meters, 3 meters, 5 meters, or other values.

For example, the difference between the positioning height measured by the positioning system from time t1 to time t2 (including time t 2) and the initial positioning height is greater than a preset value, and the difference between the positioning height measured from time t2 (excluding time t 2) to time t3 and the initial positioning height is less than the preset value. Assuming that the first weighting coefficient of the position height of the vehicle from the time t1 to the time t2 is 1, the second weighting coefficient of the position height measured by the positioning system is 0, and the position height of the vehicle can be regarded as being replaced by the position height measured by the positioning system from the time t1 to the time t 2. the third weight coefficient of the position height of the vehicle from the time t2 to the time t3 is 0, the fourth weight coefficient of the position height measured by the positioning system is 1, and the position height measured by the positioning system can be regarded as reserved from the time t2 to the time t3, namely, the track height of the positioning system in the time period is not corrected. Alternatively, the third weight coefficient of the position height of the vehicle from the time t2 to the time t3 is 0.5, and the fourth weight coefficient of the positioning height measured by the positioning system is 0.5, and the obtained average track height can be regarded as the track height of the positioning system in the time period by taking the average value of the position height and the positioning height of the vehicle from the time t2 to the time t 3. And combining the track height corrected from the time t1 to the time t2 to obtain the track height of the positioning system corrected from the time t1 to the time t 3.

160. And calculating correction parameters of the SLAM moving track by using the predicted longitude, the predicted latitude and the predicted height of the vehicle when at least two frames of second target pictures are shot on the SLAM moving track and the positioning longitude, the positioning latitude and the correction positioning height which are correspondingly measured by a shooting time positioning system of the at least two frames of second target pictures.

Wherein, the correction parameter of the SLAM movement track may include at least one of a second scale factor, a rotation matrix, and a translation matrix. The corrected positioning height is the positioning height corresponding to the shooting time in the track height of the corrected positioning system.

In this embodiment of the present application, after the track height measured by the positioning system is corrected, the three-dimensional SLAM movement track may be further corrected by using the corrected movement track of the three-dimensional positioning system. The second target picture may be the same as or different from the first target picture. Preferably, the number of second target pictures is greater than the number of first target pictures. With more pictures as reference points, the result accuracy is better. If the positioning system has better signals and more accurate positioning in the whole driving road section, the correction parameters of the SLAM moving track can be determined by taking all positioning points of the positioning system as the basis; if the positioning system positions more accurately on some road sections (such as a starting road section, an ending road section and the like), and some road sections are positioned inaccurately, the positioning point with more accurate positioning can be used as a basis to determine the correction parameters of the SLAM moving track, so that the point with inaccurate positioning is eliminated.

In an alternative embodiment, when the number of the at least two second target pictures is greater than the number of the at least two first target pictures, the step 160 uses the predicted longitude, the predicted latitude, and the predicted altitude of the vehicle when the at least two second target pictures are taken on the SLAM moving track, and the positioning longitude, the positioning latitude, and the corrected positioning altitude measured by the time positioning system for taking the at least two second target pictures, and the specific embodiment of calculating the corrected parameter of the SLAM moving track may include the following steps:

16a) And calculating the correction parameters of the SLAM moving track by using a least square optimization algorithm according to the predicted longitude, the predicted latitude and the predicted height of the vehicle when at least two frames of second target pictures are shot on the SLAM moving track and the positioning longitude, the positioning latitude and the correction positioning height correspondingly measured by a shooting time positioning system of the at least two frames of second target pictures.

For example, assume that the number of the at least two frames of the second target pictures is three, namely, a picture P1, a picture P2 and a picture P3, and the predicted position of the vehicle when the picture P1 is taken is P1 _slam (x 1, y1, z 1), the predicted position of the vehicle when taking picture P2 is P2 _slam (x 2, y2, z 2), the predicted position of the vehicle when taking picture P3 is P3 _slam (x 3, y3, z 3). The positioning position of the vehicle when taking the picture P1 is P1 _gps (x 4, y4, z 4), the positioning position after the height correction is P1' _gps (x 4, y4, z 4'); the positioning position of the vehicle when taking the picture P2 is P2 _gps (x 5, y5, z 5) by highThe positioning position after the degree correction is P2' _gps (x 5, y5, z 5'); the positioning position of the vehicle when taking the picture P3 is P3 _gps (x 6, y6, z 6), the positioning position after the height correction is P3' _gps (x 6, y6, z 6'). Establishing an error equation by using a least squares optimization algorithm:

error=R(s2*Pi _{s_u} )+t-Pi' _{g_u}

wherein s2 is a second scale factor, R is a rotation matrix, t is a translation matrix, and Pi _{s_u} Refers to UTM coordinates, pi 'converted from the predicted position coordinates of the vehicle when taking the ith frame of picture' _{g_u} The UTM coordinates are converted from the positioning position coordinates of the vehicle subjected to the height correction when the ith frame of picture is shot. Nine equations can be obtained by substituting these position coordinates into the error equations, respectively, while the second scale factor s2 is unknown, and the rotation matrix R and the translation matrix t are added to include six degrees of freedom, and total seven unknowns are included. The nine equations are used to solve the seven unknowns to obtain an optimal solution, which includes the minimum positioning error and the correction parameters (i.e., s2, R, and t) corresponding to the minimum positioning error. The correction parameter corresponding to the minimum positioning error is used for correcting the subsequent SLAM moving track.

170. And correcting the SLAM moving track according to the correction parameters to obtain a corrected moving track.

In this embodiment of the present application, when the correction parameter includes only the second scale factor s2, the SLAM movement track may be scaled and contracted in terms of longitude, latitude, and altitude according to the second scale factor s 2. When the correction parameters include the second scale factor s2 and the rotation matrix R, the SLAM movement track may be scaled in terms of longitude, latitude and altitude according to the second scale factor s2, and then rotated according to the rotation matrix R. When the correction parameters include the second scale factor s2 and the translation matrix t, the SLAM moving track can be scaled and contracted in terms of longitude, latitude and altitude according to the second scale factor s2, and then track translation is performed according to the translation matrix t.

In an alternative embodiment, the step 170 of correcting the SLAM movement track according to the correction parameter, and the specific embodiment of obtaining the corrected movement track may include the following steps:

17a) Performing scale transformation on the SLAM moving track by using a second scale factor to obtain a new SLAM moving track;

17b) And rotating and translating the new SLAM moving track according to the rotation matrix and the translation matrix to obtain a corrected moving track.

Specifically, after the second scale factor s2 is obtained, the SLAM moving track can be stretched according to the second scale factor s2, and when the second scale factor s2 is greater than 1, the length of the SLAM moving track can be stretched to be s2 times of the original length; when the second scale factor s2 is smaller than 1, the length of the SLAM moving track can be reduced to s2 times of the original length. After the scale transformation is performed, the SLAM moving track after the scale transformation can be rotated and translated according to the rotation matrix R and the translation matrix t, so that the SLAM moving track is corrected to the real moving track. Fig. 2b is a schematic diagram showing a comparison of a GPS movement track and a corrected SLAM movement track on the same road section. As shown in fig. 2b, the darker track is the corrected SLAM movement track, and the lighter track is the GPS movement track. As can be seen from the figure, the GPS moving track is positioned more accurately at the starting road section and the ending road section, and has partial poor positioning and serious drift at the middle road section. The corrected SLAM moving track is higher in accuracy than the GPS moving track on the whole, and the real moving track of the vehicle can be reflected better.

In summary, in the embodiment of the application, when the moving track measured by the positioning system is used for correcting the relative SLAM moving track of the vehicle constructed by the picture, the track height measured by the positioning system can be corrected first, so that the influence of the positioning height can be eliminated, and the inaccurate final track correction result caused by the positioning height deviation is avoided. Further, the moving track of the positioning system after the positioning height is corrected is used as a basis for correcting the relative SLAM moving track, so that the relative SLAM moving track is corrected to the real moving track, and the accuracy of the moving track of the vehicle can be improved.

Referring to fig. 3, an embodiment of the present application provides a device for correcting a vehicle movement track, which may be used to execute the method for correcting a vehicle movement track provided in the foregoing embodiment. As shown in fig. 3, the apparatus may include:

a picture obtaining unit 310, configured to obtain a picture sequence taken by the vehicle during driving, and obtain a photographing time of each frame of picture in the picture sequence;

a track construction unit 320 for constructing a SLAM moving track of the vehicle using the picture sequence, wherein the SLAM moving track may include a combination of predicted positions of the vehicle at the time of taking each frame of picture, the predicted positions may include a predicted longitude, a predicted latitude, and a predicted altitude;

a first calculating unit 330, configured to calculate a first scale factor using a predicted longitude and a predicted latitude of the vehicle when the at least two frames of the first target pictures are taken in the SLAM moving track, and a positioning longitude and a positioning latitude measured correspondingly by a positioning system of the vehicle at a time of taking the at least two frames of the first target pictures;

the scale transformation unit 340 is configured to scale-transform the predicted height of the vehicle when each frame of picture is taken in the SLAM moving track according to the first scale factor, so as to obtain a SLAM track height;

A height correction unit 350, configured to correct the track height measured by the positioning system by using the SLAM track height, so as to obtain a corrected track height of the positioning system;

a second calculating unit 360, configured to calculate a correction parameter of the SLAM moving track by using the predicted longitude, the predicted latitude, and the predicted altitude of the vehicle when the at least two frames of the second target pictures are taken on the SLAM moving track, and the positioning longitude, the positioning latitude, and the corrected positioning altitude measured by the positioning system corresponding to the time of taking the at least two frames of the second target pictures, where the correction parameter may include at least one of a second scale factor, a rotation matrix, and a translation matrix, and the corrected positioning altitude is a positioning altitude corresponding to the time of taking in the track altitude of the corrected positioning system;

the track correction unit 370 is configured to correct the SLAM movement track according to the correction parameter, and obtain a corrected movement track.

Optionally, the embodiment of the height correction unit 350 for correcting the track height measured by the positioning system by using the SLAM track height to obtain the corrected track height of the positioning system may include:

the height correction unit 350 obtains a weighting coefficient of the position height of the vehicle in the SLAM track height at each photographing time and a weighting coefficient of the positioning height measured by the positioning system, and performs weighting processing on the position height and the positioning height of the vehicle at each photographing time by using the weighting coefficient to obtain a corrected track height of the positioning system, wherein the position height of the vehicle is obtained by scaling the predicted height of the vehicle by using the first scale factor.

The weighting coefficients of the position heights of the vehicles at different shooting times can be all the same or partially the same or all different, and similarly, the weighting coefficients of the positioning heights of the positioning systems at different shooting times can be all the same or partially the same or all different. The weighting coefficient of the position height of the vehicle at the same photographing time may be the same as or different from the weighting coefficient of the positioning height.

Optionally, the specific embodiment of the height correction unit 350 to obtain the weighting coefficient of the position height of the vehicle in the SLAM track height at each photographing time and the weighting coefficient of the positioning height measured by the positioning system respectively may include:

the height correction unit 350 recognizes the pictures acquired at each photographing time, and respectively obtains the position environment of the vehicle; when the position environment of the vehicle identified by the picture meets the preset condition, acquiring a first weighting coefficient of the position height of the vehicle at the shooting time of the picture and a second weighting coefficient of the positioning height measured by the positioning system; when the environment of the position of the vehicle identified by the picture does not meet the preset condition, a third weighting coefficient of the position height of the vehicle at the shooting time of the picture and a fourth weighting coefficient of the positioning height measured by the positioning system are obtained, wherein the first weighting coefficient is larger than the second weighting coefficient, the third weighting coefficient is different from the first weighting coefficient, and the fourth weighting coefficient is different from the second weighting coefficient.

the height correction unit 350 obtains the initial positioning height measured by the positioning system, calculates a height difference between the positioning height measured by the positioning system and the initial positioning height at each photographing time, and obtains a first weighting coefficient of the position height of the vehicle at the photographing time and a second weighting coefficient of the positioning height measured by the positioning system when the height difference between the positioning height measured by the positioning system and the initial positioning height at the photographing time is greater than a preset value; and when the height difference between the positioning height measured by the positioning system under the shooting time and the initial positioning height is smaller than or equal to a preset value, acquiring a third weighting coefficient of the position height of the vehicle under the shooting time and a fourth weighting coefficient of the positioning height measured by the positioning system, wherein the first weighting coefficient is larger than the second weighting coefficient, the third weighting coefficient is different from the first weighting coefficient, and the fourth weighting coefficient is different from the second weighting coefficient.

Optionally, the number of the at least two second target pictures is greater than the number of the at least two first target pictures, the second calculating unit 360 uses the predicted longitude, the predicted latitude, and the predicted altitude of the vehicle when the at least two second target pictures are taken on the SLAM moving track, and the positioning longitude, the positioning latitude, and the corrected positioning altitude measured by the time positioning system for taking the at least two second target pictures, and the specific embodiment of calculating the corrected parameter of the SLAM moving track may include:

The second calculating unit 360 calculates the correction parameters of the SLAM moving track by using a least square optimization algorithm according to the predicted longitude, the predicted latitude and the predicted height of the vehicle when the at least two frames of the second target pictures are shot on the SLAM moving track, and the positioning longitude, the positioning latitude and the correction positioning height correspondingly measured by the shooting time positioning system of the at least two frames of the second target pictures.

Optionally, the correction parameters include a second scale factor, a rotation matrix, and a translation matrix, and the track correction unit 370 corrects the SLAM movement track according to the correction parameters, so that a specific embodiment of the corrected movement track may include:

the track correction unit 370 performs scale transformation on the SLAM moving track by using the second scale factor to obtain a new SLAM moving track; and rotating and translating the new SLAM moving track according to the rotation matrix and the translation matrix to obtain a corrected moving track.

The specific manner in which the respective unit modules perform the operations in the above-described embodiments have been described in detail in relation to the embodiments of the method, and will not be explained in detail here.

When the device shown in fig. 3 is implemented and the moving track measured by the positioning system is used for correcting the relative SLAM moving track of the vehicle constructed by the picture, the track height measured by the positioning system can be corrected first, the influence of the positioning height can be eliminated, and the inaccurate final track correction result caused by the positioning height deviation is avoided. Further, the moving track of the positioning system after the positioning height is corrected is used as a basis for correcting the relative SLAM moving track, so that the relative SLAM moving track is corrected to the real moving track, and the accuracy of the moving track of the vehicle can be improved.

Referring to fig. 4, an embodiment of the present application provides an electronic device that may be used to execute the method for correcting the movement track of the vehicle provided in the foregoing embodiment. As shown in fig. 4, the electronic device 400 may include: a processor 410 and a memory 420. Wherein the processor 410 is communicatively coupled to the memory 420. It will be appreciated that the architecture of the electronic device 400 shown in fig. 4 is not limiting to embodiments of the present application, and may include more components than illustrated, such as communication interfaces (e.g., bluetooth modules, WIFI modules, etc.), input-output interfaces (e.g., keys, touch screen, speakers, microphones, etc.), sensors, etc. Wherein:

the processor 410 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

Memory 420 may include various types of storage units, such as system memory, read Only Memory (ROM), and persistent storage. Wherein the ROM may store static data or instructions that are required by the processor 410 or other modules of the computer. The persistent storage may be a readable and writable storage. The persistent storage may be a non-volatile memory device that does not lose stored instructions and data even after the computer is powered down. In some embodiments, the persistent storage device employs a mass storage device (e.g., magnetic or optical disk, flash memory) as the persistent storage device. In other embodiments, the persistent storage may be a removable storage device (e.g., diskette, optical drive). The system memory may be a read-write memory device or a volatile read-write memory device, such as dynamic random access memory. The system memory may store instructions and data that are required by some or all of the processors at runtime. Furthermore, memory 420 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), magnetic disks, and/or optical disks may also be employed. In some embodiments, memory 420 may include a readable and/or writable removable storage device, such as a Compact Disc (CD), a read-only digital versatile disc (e.g., DVD-ROM, dual layer DVD-ROM), a read-only blu-ray disc, an super-density optical disc, a flash memory card (e.g., SD card, min SD card, micro-SD card, etc.), a magnetic floppy disk, and the like. The computer readable storage medium does not contain a carrier wave or an instantaneous electronic signal transmitted by wireless or wired transmission.

The memory 420 has stored thereon executable code that, when processed by the processor 410, causes the processor 410 to perform some or all of the steps of the methods described above.

Furthermore, the method according to the present application may also be implemented as a computer program or computer program product comprising computer program code instructions for performing part or all of the steps of the above-described method of the present application.

Alternatively, the present application may also be embodied as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) having stored thereon executable code (or a computer program, or computer instruction code) that, when executed by a processor of an electronic device (or electronic device, server, etc.), causes the processor to perform some or all of the steps of the above-described methods according to the present application.

The embodiments of the present application have been described above, the foregoing description is exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for correcting a movement locus of a vehicle, comprising:

calculating a first scale factor by using the predicted longitude and the predicted latitude of the vehicle when at least two frames of first target pictures are shot in the SLAM moving track and the positioning longitude and the positioning latitude which are correspondingly measured by the positioning system of the vehicle at the shooting time of the at least two frames of first target pictures, so that the track height which is correspondingly measured by the positioning system of the vehicle is excluded from participating in the calculation of the first scale factor;

2. The method of claim 1, wherein correcting the track height measured by the positioning system using the SLAM track height to obtain a corrected track height of the positioning system comprises:

3. The method according to claim 2, wherein the obtaining of the weighting coefficients of the position height of the vehicle and the weighting coefficients of the positioning height measured by the positioning system in the SLAM track heights at the respective photographing times, respectively, includes:

4. The method according to claim 2, wherein the obtaining of the weighting coefficients of the position height of the vehicle and the weighting coefficients of the positioning height measured by the positioning system in the SLAM track heights at the respective photographing times, respectively, includes:

acquiring an initial positioning height measured by the positioning system;

5. The method according to any one of claims 1 to 4, wherein the number of the at least two second target pictures is larger than the number of the at least two first target pictures, wherein the calculating the correction parameters of the SLAM moving trajectory using the predicted longitude, the predicted latitude, and the predicted altitude of the vehicle when the at least two second target pictures are taken on the SLAM moving trajectory, and the positioning system corresponding to the measured positioning longitude, the measured positioning latitude, and the corrected positioning altitude at the time of the at least two second target pictures, comprises:

6. The method according to any one of claims 1-4, wherein the correction parameters include a second scale factor, a rotation matrix, and a translation matrix, and the correcting the SLAM movement track according to the correction parameters to obtain a corrected movement track includes:

7. A correction device for a vehicle movement locus, comprising:

a first calculation unit, configured to calculate a first scale factor by using a predicted longitude and a predicted latitude of the vehicle when at least two frames of first target pictures are taken in the SLAM movement track, and a positioning longitude and a positioning latitude measured correspondingly by the positioning system of the vehicle at a time of taking the at least two frames of first target pictures, so that a track height measured correspondingly by the positioning system excluding the vehicle participates in calculation of the first scale factor;

8. The apparatus of claim 7, wherein the means for correcting the track height measured by the positioning system using the SLAM track height comprises:

9. An electronic device, comprising:

a processor; and

a memory having executable code stored thereon, which when executed by the processor, causes the processor to perform the method of any of claims 1-6.

10. A non-transitory machine-readable storage medium having stored thereon executable code, which when executed by a processor of an electronic device, causes the processor to perform the method of any of claims 1-6.