CN110779511A - Pose variation determination method, device and system and vehicle - Google Patents
Pose variation determination method, device and system and vehicle Download PDFInfo
- Publication number
- CN110779511A CN110779511A CN201910900478.2A CN201910900478A CN110779511A CN 110779511 A CN110779511 A CN 110779511A CN 201910900478 A CN201910900478 A CN 201910900478A CN 110779511 A CN110779511 A CN 110779511A
- Authority
- CN
- China
- Prior art keywords
- variation
- wheel
- vehicle
- determining
- pose
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The disclosure relates to a method, a device and a system for determining pose variation and a vehicle, which are applied to the vehicle, wherein the method comprises the following steps: determining a first attitude change quantity corresponding to each camera according to two image frames acquired by each camera arranged at different positions of a vehicle body of the vehicle at two adjacent moments; determining a second position change quantity corresponding to each wheel according to the pulse reading difference of each pulse encoder at the two moments and the wheel parameters of the vehicle; and screening the plurality of first posture variation according to the plurality of second posture variation, so as to determine the actual posture variation of the vehicle between the two moments according to the screened third posture variation. The pose variation amount detected by the camera can be checked and screened according to the pose variation amount calculated by the vehicle pulse reading, so that the accuracy of the pose variation amount of the vehicle at two adjacent moments is improved.
Description
Technical Field
The disclosure relates to the field of positioning and navigation, in particular to a method, a device and a system for determining pose variation and a vehicle.
Background
The position of the vehicle is constantly changed with time during the running process. In order to determine the position of the vehicle at each moment and determine whether the vehicle deviates from the route in the preset driving plan according to the position of the vehicle at each moment, the vehicle needs to be accurately positioned in real time. The SLAM (Simultaneous Localization And Mapping) technology is applied to the vehicle positioning And navigation technology, so that the positioning dimension And precision can be improved, namely the vehicle positioning dimension is expanded from a two-dimensional plane to a three-dimensional space (so as to meet the positioning requirements of uphill And downhill or small-range moving). In the related art, the vehicle is positioned by SLAM, the pose change of the vehicle can be determined by a vision sensor (such as a camera), and then the position of the vehicle can be determined. Specifically, in the process of determining the pose change of the vehicle through the vision sensor, one or more vision sensors arranged on the vehicle body can be used for continuously acquiring image information of the surrounding environment of the vehicle, comparing the image information acquired at each moment after the vehicle is started with the image information acquired at the last moment, and further determining the pose change amount of each moment relative to the last moment through a vision positioning algorithm. Therefore, the real-time position change of the vehicle in the three-dimensional space can be determined according to the pose change amount. However, the above method is limited by the accuracy of the image collected by the vision sensor, so that the detected pose change amount of each time relative to the previous time is deviated from the actual pose change amount of the vehicle. Along with the time, the accumulated pose variation deviation is larger and larger, and the accuracy of vehicle positioning is further seriously influenced.
Disclosure of Invention
In order to overcome the problems in the related art, the present disclosure provides a method, an apparatus, a system and a vehicle for determining a pose change amount.
According to a first aspect of the embodiments of the present disclosure, there is provided a method for determining a pose change amount, which is applied to a vehicle, where a plurality of cameras are provided at different portions of a vehicle body of the vehicle, and a pulse encoder is provided on each wheel of the vehicle, the method including:
determining a first attitude variation corresponding to each camera according to two image frames acquired by each camera at two adjacent moments;
determining a second attitude change quantity corresponding to each wheel according to the pulse reading difference of each pulse encoder at the two moments and the wheel parameters of the vehicle;
and screening the plurality of first posture variation quantities according to the plurality of second posture variation quantities so as to determine the actual posture variation quantity of the vehicle between the two moments according to the screened third posture variation quantity.
Optionally, the pose variation includes: displacement volume and longitudinal angle difference, it is a plurality of according to a plurality of second position appearance variation is to a plurality of first position appearance variation filters to confirm according to the third position appearance variation who screens out the vehicle is in the actual position appearance variation between two moments includes:
determining one or more of the third attitude change amounts from the plurality of first attitude change amounts; the third posture variation comprises the same displacement amount as any one of the second posture variation, and the longitudinal angle difference of the third posture variation is the same as the longitudinal angle difference of any one of the second posture variation;
and determining the actual pose variation quantity according to one or more third pose variation quantities and the position of the camera corresponding to each third pose variation quantity relative to the vehicle through a preset positioning algorithm.
Optionally, the determining, according to the difference between the pulse readings of each pulse encoder at the two time instants and the wheel parameter of the vehicle, a second attitude change amount corresponding to each wheel includes:
determining the moving distance and the course angle of each wheel between the two moments according to the pulse reading difference and the wheel parameters;
determining the displacement of each wheel according to the moving distance and the course angle through a preset displacement calculation formula;
determining the longitudinal angle difference of each wheel according to the course angle through a preset longitudinal angle difference calculation formula;
and determining the second position change amount according to the displacement amount and the longitudinal angle difference of each wheel.
Optionally, the determining the second attitude change amount according to the displacement amount and the longitudinal angle difference of each wheel includes:
taking the moving distance and the displacement of each wheel as the input of a first cost function to obtain a first cost function value output by the first cost function;
taking the difference between the course angle and the longitudinal angle of each wheel as the input of a second cost function to obtain a second cost function value output by the second cost function;
acquiring a displacement amount and a longitudinal angle difference of a target wheel as the second position and posture variation amount; and the first valence function value corresponding to the displacement of the target wheel and the second valence function value corresponding to the longitudinal angle difference of the target wheel both meet preset function value conditions.
According to a second aspect of the embodiments of the present disclosure, there is provided an apparatus for determining a pose change amount, the apparatus being applied to a vehicle, a plurality of cameras being provided at different portions of a vehicle body of the vehicle, a pulse encoder being provided on each wheel of the vehicle, the apparatus including:
the first variation determining module is used for determining a first attitude variation corresponding to each camera according to two image frames acquired by each camera at two adjacent moments;
the second variable quantity determining module is used for determining a second attitude variable quantity corresponding to each wheel according to the pulse reading difference of each pulse encoder at the two moments and the wheel parameters of the vehicle;
and the variation screening module is used for screening the plurality of first attitude variation according to the plurality of second attitude variation to determine the actual attitude variation of the vehicle between the two moments according to the screened third attitude variation.
Optionally, the pose variation includes: displacement amount and longitudinal angle difference, the variation screening module is used for:
determining one or more of the third attitude change amounts from the plurality of first attitude change amounts; the third posture variation comprises the same displacement amount as any one of the second posture variation, and the longitudinal angle difference of the third posture variation is the same as the longitudinal angle difference of any one of the second posture variation;
and determining the actual pose variation quantity according to one or more third pose variation quantities and the position of the camera corresponding to each third pose variation quantity relative to the vehicle through a preset positioning algorithm.
Optionally, the second variation determining module is configured to:
determining the moving distance and the course angle of each wheel between the two moments according to the pulse reading difference and the wheel parameters;
determining the displacement of each wheel according to the moving distance and the course angle through a preset displacement calculation formula;
determining the longitudinal angle difference of each wheel according to the course angle through a preset longitudinal angle difference calculation formula;
and determining the second position change amount according to the displacement amount and the longitudinal angle difference of each wheel.
Optionally, the second variation determining module is configured to:
taking the moving distance and the displacement of each wheel as the input of a first cost function to obtain a first cost function value output by the first cost function;
taking the difference between the course angle and the longitudinal angle of each wheel as the input of a second cost function to obtain a second cost function value output by the second cost function;
acquiring a displacement amount and a longitudinal angle difference of a target wheel as the second position and posture variation amount; and the first valence function value corresponding to the displacement of the target wheel and the second valence function value corresponding to the longitudinal angle difference of the target wheel both meet preset function value conditions.
According to a third aspect of the embodiments of the present disclosure, there is provided a system for determining a pose change amount, the system including:
the pose change amount determination device according to the second aspect of the embodiment of the present disclosure;
a plurality of cameras disposed at different portions of a vehicle body of the vehicle; and the number of the first and second groups,
a pulse encoder disposed on each wheel of the vehicle.
According to a fourth aspect of the embodiments of the present disclosure, there is provided a vehicle including the system for determining an amount of change in pose as set forth in the third aspect of the embodiments of the present disclosure.
In summary, the present invention provides a method, an apparatus, a system and a vehicle for determining a pose variation, which can determine a first pose variation corresponding to each camera according to two image frames acquired by each camera disposed at different positions of a vehicle body of the vehicle at two adjacent moments; determining a second position change quantity corresponding to each wheel according to the pulse reading difference of each pulse encoder at the two moments and the wheel parameters of the vehicle; and screening the plurality of first posture variation according to the plurality of second posture variation, so as to determine the actual posture variation of the vehicle between the two moments according to the screened third posture variation. The pose variation amount detected by the camera can be checked and screened according to the pose variation amount calculated by the vehicle pulse reading, so that the accuracy of the pose variation amount of the vehicle at two adjacent moments is improved.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure without limiting the disclosure. In the drawings:
FIG. 1 is a flow chart illustrating a method of determining an amount of pose change in accordance with an exemplary embodiment;
FIG. 2 is a flow chart of a method for screening pose change amount according to the method shown in FIG. 1;
fig. 3 is a flowchart of another pose change amount determination method according to fig. 2;
fig. 4 is a flowchart of an adjustment method of the pose change amount according to fig. 3;
fig. 5 is a block diagram illustrating a pose change amount determination apparatus according to an exemplary embodiment.
Detailed Description
The following detailed description of specific embodiments of the present disclosure is provided in connection with the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present disclosure, are given by way of illustration and explanation only, not limitation.
Fig. 1 is a flowchart illustrating a method for determining an amount of change in pose according to an exemplary embodiment, as shown in fig. 1, applied to a vehicle having a body with a plurality of cameras disposed at different locations of the body, and a pulse encoder disposed on each wheel of the vehicle, the method including the steps of:
in step 110, a first pose change amount corresponding to each camera is determined according to two image frames acquired by each camera at two adjacent moments.
For example, cameras at different parts of the vehicle body typically capture image frames containing image information about the vehicle at a fixed frequency. From two image frames at two adjacent time points, the pose change amount (i.e., the first pose change amount) of each camera between the two adjacent time points can be measured by the SLAM algorithm.
In step 120, a second attitude change amount corresponding to each wheel is determined based on the difference between the pulse readings of each pulse encoder at the two times and the wheel parameter of the vehicle.
For example, the pose change amount (i.e., the second pose change amount) of each wheel of the vehicle between two adjacent time instants can be calculated by a preset pose calculation formula according to the reading of the pulse encoder arranged on the wheel at the two adjacent time instants. The second position posture variation obtained by the method is a relatively accurate ideal value and can be used for verifying the accuracy of the first position posture variation.
In step 130, the plurality of first posture variation amounts are filtered according to the plurality of second posture variation amounts, so as to determine the actual posture variation amount of the vehicle between the two moments according to the filtered third posture variation amount.
For example, in a general case, 4 cameras are arranged on a vehicle body of a vehicle, the 4 cameras are respectively distributed near two rear-view mirrors of the vehicle and on the left and right sides of a tail portion of the vehicle, a first pose change amount corresponding to each camera is determined by a SLAM algorithm according to two image frames acquired by each camera at two adjacent moments, and then the pose change amount of the vehicle between the two adjacent moments is calculated by combining the positions of the 4 cameras. The second posture change amount of each wheel (typically including 4 wheels) between the same two times calculated in the step 120 is compared with the set of the first posture change amounts, the intersecting portion (i.e., the equal posture change amount) of the two sets is used as the third posture change amount, and the actual posture change amount of the vehicle between the two times is determined according to one or more third posture change amounts. The vehicle can be positioned in the three-dimensional space through accumulation of the actual pose variation at multiple moments.
In summary, the method for determining pose variation provided by the present invention can determine the first pose variation corresponding to each camera according to two image frames acquired by each camera disposed at different positions of the vehicle body at two adjacent moments; determining a second position change quantity corresponding to each wheel according to the pulse reading difference of each pulse encoder at the two moments and the wheel parameters of the vehicle; and screening the plurality of first posture variation according to the plurality of second posture variation, so as to determine the actual posture variation of the vehicle between the two moments according to the screened third posture variation. The pose variation amount detected by the camera can be checked and screened according to the pose variation amount calculated by the vehicle pulse reading, so that the accuracy of the pose variation amount of the vehicle at two adjacent moments is improved.
Fig. 2 is a flowchart of a method for screening pose change amounts according to fig. 1, where the pose change amounts include: displacement and longitudinal angle difference, step 130 comprising:
in step 131, one or more third posture change amounts are determined from the plurality of first posture change amounts.
The third posture variation includes a displacement amount identical to a displacement amount included in any one of the second posture variation, and a longitudinal angle difference included in the third posture variation is identical to a longitudinal angle difference included in any one of the second posture variation.
Illustratively, the set of the first posture change amounts includes a first displacement amount set and a first longitudinal angle difference set, and each displacement amount in the set of the first displacement amounts corresponds to each longitudinal angle difference in the first longitudinal angle difference set in a one-to-one manner. Similarly, the set of the second posture change amounts includes a second displacement set and a second longitudinal angle difference set, and each displacement amount in the set of the second displacement amounts corresponds to each longitudinal angle difference in the second longitudinal angle difference set in a one-to-one manner. When the first attitude change amounts (i.e., the set of first attitude change amounts) are filtered according to the second attitude change amounts (i.e., the set of second attitude change amounts), the intersection (one or more displacement amounts) of the displacement amounts of the first set of displacement amounts and the second set of displacement amounts may be filtered, and then the intersection (one or more longitudinal angle differences) of the longitudinal angle differences of the first set of longitudinal angle differences and the second set of longitudinal angle differences may be filtered. And then, screening one or more groups of target displacement and target longitudinal angle differences which have corresponding relations in the displacement intersection part and the longitudinal angle difference intersection part, wherein the one or more groups of target displacement and longitudinal angle differences are one or more third posture variation quantities.
In step 132, the actual pose change amount is determined according to one or more third pose change amounts and the position of the camera corresponding to each third pose change amount relative to the vehicle through a preset positioning algorithm.
For example, after determining one or more third posture change amounts, a camera that acquires an image frame corresponding to the third posture change amount may be determined accordingly. And then, determining the actual pose variation of the vehicle between the two moments according to the one or more third pose variations and the position of the camera corresponding to each third pose variation relative to the vehicle by a preset SLAM algorithm.
Fig. 3 is a flowchart of another pose change amount determination method according to fig. 2, where step 120 includes, as shown in fig. 3:
in step 121, a moving distance and a heading angle of each wheel between the two time instants are determined according to the pulse reading difference and the wheel parameter.
Illustratively, reading the pulse readings of the pulse encoder on each wheel at the above two time instants (i time instant and j time instant, where i time instant and j time instant are any two adjacent time instants, and j time instant is after i time instant) and calculating the pulse reading difference, and taking the pulse reading difference and the radius of the wheel as the preset input of a determined wheel travel length formula (1) to obtain the length traveled by the wheel between the above two time instants, where the determined wheel travel length formula (1) can be expressed as:
wherein, aiming at any wheel, L is the running length of the wheel, L
ijThe pulse reading difference between the time i and the time j of the pulse encoder on the wheel is obtained, r is the radius of the wheel (namely the wheel parameter), and PPR is a preset calibration coefficient of the corresponding relation between the radius of the wheel and the running length. After the running length of the wheel between the two moments is determined, the moving distance d of the wheel between the moment i and the moment j is determined according to a preset formula
ijAnd a heading angle yaw.
In step 122, the displacement of each wheel is determined according to the moving distance and the heading angle by a preset displacement calculation formula.
Exemplarily, the heading angle and the moving distance of each wheel between the time i and the time j are used as the input of a preset displacement determination formula (2) to obtain the displacement of each wheel output by the displacement determination formula (2); wherein the displacement amount determination formula (2) can be expressed as:
wherein, T
ijIs the displacement of any wheel between time i and time j, yaw is the heading angle of the wheel between time i and time j, d
ijFor the distance traveled by the wheel between time i and time j, T
1、T
2And R are both preset calibration coefficients.
In step 123, the longitudinal angle difference of each wheel is determined according to the heading angle through a preset longitudinal angle difference calculation formula.
Exemplarily, the heading angle of each wheel between the time i and the time j is used as an input of a preset longitudinal angle difference determination formula (3) to obtain the longitudinal angle difference between the time i and the time j of the wheel output by the longitudinal angle difference determination formula (3); wherein the longitudinal angle difference determination formula (3) may be expressed as:
wherein R is
ijIs the longitudinal angle difference of any wheel between the moment i and the moment j, yaw is the heading angle of the wheel between the moment i and the moment j, and R is a preset calibration coefficient.
In step 124, the second posture change amount is determined according to the displacement amount and the longitudinal angle difference of each wheel.
Fig. 4 is a flowchart of an adjustment method for the pose change amount according to fig. 3, where, as shown in fig. 4, the step 124 includes:
in step 1241, the moving distance and the displacement amount of each wheel are used as the input of the first cost function to obtain the first cost function value output by the first cost function.
In step 1242, the heading angle and the longitudinal angle difference of each wheel are used as the input of the second cost function to obtain the second cost function value output by the second cost function.
In step 1243, the displacement amount and the longitudinal angle difference of the target wheel are acquired as the second attitude change amount.
And the first cost function value corresponding to the displacement of the target wheel and the second cost function value corresponding to the longitudinal angle difference of the target wheel both meet preset function value conditions.
For example, before the plurality of first attitude change amounts are filtered through the plurality of second attitude change amounts, first, the second attitude change amount corresponding to each wheel determined according to the reading difference of each pulse encoder is preliminarily filtered to obtain the second attitude change amount corresponding to one or more target wheels. Thus, a first cost function (4) for screening the one or more target second displacement amounts and a second cost function (5) for screening the one or more target second longitudinal angle differences are constructed.
Exemplarily, the moving distance of each wheel and the displacement of the wheel determined according to the moving distance of the wheel are used as the input of the first cost function (4) to obtain the function value output by the first cost function (4), and the first cost function (4) can be represented as:
wherein d is
ijDistance traveled by any wheel between time i and time j, T
ijAccording to the moving distance d of the wheel at the time i and the time j
ijDetermining the displacement, σ, of the wheel at time i and j
1Is a preset weight factor, and the function value f (T) is output when the first cost function is output
ij,d
ij) When the preset function value condition is satisfied, one or more displacement T corresponding to the function value
ijI.e. the one or more target second displacement amounts.
Taking the heading angle of each wheel and the longitudinal angle difference of the wheel determined from the heading angle of the wheel as inputs to the second cost function (5) to obtain a function value of the output of the second cost function (5), the second cost function (5) may be expressed as:
wherein the heading angle, R, of any one wheel at yaw between time i and time j
ijFor the longitudinal angular difference between the wheel at time i and time j, σ, determined from the heading angle yaw of the wheel between time i and time j
2A function value f (R) output by the second cost function as a preset weight factor
ijYaw) satisfies a predetermined function value condition, one or more longitudinal angle differences R corresponding to the function value
ijI.e. the one or more target second longitudinal angle differences.
And screening the displacement amount and the longitudinal angle difference of the same tire from the one or more target second displacement amounts and the target second longitudinal angle difference, wherein the tire (which may be one or more tires) is the target tire, and the displacement amount and the longitudinal angle difference of the target wheel are the second attitude change amounts.
In summary, the method for determining pose variation provided by the present invention can determine the first pose variation corresponding to each camera according to two image frames acquired by each camera disposed at different positions of the vehicle body at two adjacent moments; determining a second position change quantity corresponding to each wheel according to the pulse reading difference of each pulse encoder at the two moments and the wheel parameters of the vehicle; and screening the plurality of first posture variation according to the plurality of second posture variation, so as to determine the actual posture variation of the vehicle between the two moments according to the screened third posture variation. The pose variation amount detected by the camera can be checked and screened according to the pose variation amount calculated by the vehicle pulse reading, so that the accuracy of the pose variation amount of the vehicle at two adjacent moments is improved, and the accuracy of vehicle positioning is improved.
Fig. 5 is a block diagram illustrating an apparatus for determining an amount of change in posture according to an exemplary embodiment, as shown in fig. 5, applied to a vehicle having a body provided with a plurality of cameras at different portions thereof, and each wheel of the vehicle being provided with a pulse encoder, the apparatus 500 including:
a first variation determining module 510, configured to determine a first attitude variation corresponding to each camera according to two image frames acquired by each camera at two adjacent moments;
a second variation determining module 520, configured to determine a second attitude variation corresponding to each wheel according to a difference between the pulse readings of each pulse encoder at the two times and a wheel parameter of the vehicle;
and a variation screening module 530, configured to screen the plurality of first attitude variations according to the plurality of second attitude variations, so as to determine, according to a third attitude variation screened, an actual attitude variation of the vehicle between the two moments.
Optionally, the pose variation includes: displacement and longitudinal angle difference, the variation filtering module 530 is configured to:
determining one or more third posture change amounts from the plurality of first posture change amounts; the third posture variation comprises the same displacement amount as any one of the second posture variation, and the longitudinal angle difference of the third posture variation is the same as the longitudinal angle difference of any one of the second posture variation;
and determining the actual pose variation quantity according to one or more third pose variation quantities and the position of the camera corresponding to each third pose variation quantity relative to the vehicle through a preset positioning algorithm.
Optionally, the second variation determining module 520 is configured to:
determining the moving distance and the course angle of each wheel between the two moments according to the pulse reading difference and the wheel parameters;
determining the displacement of each wheel according to the moving distance and the course angle through a preset displacement calculation formula;
determining the longitudinal angle difference of each wheel according to the course angle through a preset longitudinal angle difference calculation formula;
and determining the second position posture variation according to the displacement and the longitudinal angle difference of each wheel.
Optionally, the second variation determining module 520 is configured to:
taking the moving distance and the displacement of each wheel as the input of a first cost function to obtain a first cost function value output by the first cost function;
taking the difference between the course angle and the longitudinal angle of each wheel as the input of a second cost function to obtain a second cost function value output by the second cost function;
acquiring the displacement and the longitudinal angle difference of the target wheel as the second position variation; and the first cost function value corresponding to the displacement of the target wheel and the second cost function value corresponding to the longitudinal angle difference of the target wheel both meet preset function value conditions.
The present disclosure also provides a pose change amount determination system, including:
at least one determination apparatus 500 for determining a pose change amount provided by the embodiment of the present disclosure;
a plurality of cameras disposed at different portions of a vehicle body of the vehicle; and the number of the first and second groups,
a pulse encoder disposed on each wheel of the vehicle.
The present disclosure also provides a vehicle including at least one system for determining an amount of pose change provided by the embodiments of the present disclosure.
In summary, according to the method, the device and the system for determining pose variation and the vehicle provided by the invention, the first pose variation corresponding to each camera can be determined according to two image frames acquired by each camera arranged at different positions of the vehicle body at two adjacent moments; determining a second position change quantity corresponding to each wheel according to the pulse reading difference of each pulse encoder at the two moments and the wheel parameters of the vehicle; and screening the plurality of first posture variation according to the plurality of second posture variation, so as to determine the actual posture variation of the vehicle between the two moments according to the screened third posture variation. The pose variation amount detected by the camera can be checked and screened according to the pose variation amount calculated by the vehicle pulse reading, so that the accuracy of the pose variation amount of the vehicle at two adjacent moments is improved, and the accuracy of vehicle positioning is improved.
The preferred embodiments of the present disclosure are described in detail with reference to the accompanying drawings, however, the present disclosure is not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solution of the present disclosure within the technical idea of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.
It should be noted that, in the foregoing embodiments, various features described in the above embodiments may be combined in any suitable manner, and in order to avoid unnecessary repetition, various combinations that are possible in the present disclosure are not described again.
In addition, any combination of various embodiments of the present disclosure may be made, and the same should be considered as the disclosure of the present disclosure, as long as it does not depart from the spirit of the present disclosure.
Claims (10)
1. A method for determining pose variation is applied to a vehicle, a plurality of cameras are arranged on different parts of a vehicle body of the vehicle, and a pulse encoder is arranged on each wheel of the vehicle, and the method comprises the following steps:
determining a first attitude variation corresponding to each camera according to two image frames acquired by each camera at two adjacent moments;
determining a second attitude change quantity corresponding to each wheel according to the pulse reading difference of each pulse encoder at the two moments and the wheel parameters of the vehicle;
and screening the plurality of first posture variation quantities according to the plurality of second posture variation quantities so as to determine the actual posture variation quantity of the vehicle between the two moments according to the screened third posture variation quantity.
2. The method of claim 1, wherein the pose change amount comprises: displacement volume and longitudinal angle difference, it is a plurality of according to a plurality of second position appearance variation is to a plurality of first position appearance variation filters to confirm according to the third position appearance variation who screens out the vehicle is in the actual position appearance variation between two moments includes:
determining one or more of the third attitude change amounts from the plurality of first attitude change amounts; the third posture variation comprises the same displacement amount as any one of the second posture variation, and the longitudinal angle difference of the third posture variation is the same as the longitudinal angle difference of any one of the second posture variation;
and determining the actual pose variation quantity according to one or more third pose variation quantities and the position of the camera corresponding to each third pose variation quantity relative to the vehicle through a preset positioning algorithm.
3. The method according to claim 2, wherein the determining a second change amount of attitude of each wheel according to the difference between the pulse readings of each pulse encoder at the two time instants and the wheel parameter of the vehicle comprises:
determining the moving distance and the course angle of each wheel between the two moments according to the pulse reading difference and the wheel parameters;
determining the displacement of each wheel according to the moving distance and the course angle through a preset displacement calculation formula;
determining the longitudinal angle difference of each wheel according to the course angle through a preset longitudinal angle difference calculation formula;
and determining the second position change amount according to the displacement amount and the longitudinal angle difference of each wheel.
4. The method according to claim 3, wherein the determining the second attitude change amount according to the displacement amount and the longitudinal angle difference of each of the wheels comprises:
taking the moving distance and the displacement of each wheel as the input of a first cost function to obtain a first cost function value output by the first cost function;
taking the difference between the course angle and the longitudinal angle of each wheel as the input of a second cost function to obtain a second cost function value output by the second cost function;
acquiring a displacement amount and a longitudinal angle difference of a target wheel as the second position and posture variation amount; and the first valence function value corresponding to the displacement of the target wheel and the second valence function value corresponding to the longitudinal angle difference of the target wheel both meet preset function value conditions.
5. An apparatus for determining a posture change amount, applied to a vehicle having a plurality of cameras provided at different portions of a vehicle body, each wheel of the vehicle having a pulse encoder provided thereon, the apparatus comprising:
the first variation determining module is used for determining a first attitude variation corresponding to each camera according to two image frames acquired by each camera at two adjacent moments;
the second variable quantity determining module is used for determining a second attitude variable quantity corresponding to each wheel according to the pulse reading difference of each pulse encoder at the two moments and the wheel parameters of the vehicle;
and the variation screening module is used for screening the plurality of first attitude variation according to the plurality of second attitude variation to determine the actual attitude variation of the vehicle between the two moments according to the screened third attitude variation.
6. The apparatus according to claim 5, wherein the pose change amount includes: displacement amount and longitudinal angle difference, the variation screening module is used for:
determining one or more of the third attitude change amounts from the plurality of first attitude change amounts; the third posture variation comprises the same displacement amount as any one of the second posture variation, and the longitudinal angle difference of the third posture variation is the same as the longitudinal angle difference of any one of the second posture variation;
and determining the actual pose variation quantity according to one or more third pose variation quantities and the position of the camera corresponding to each third pose variation quantity relative to the vehicle through a preset positioning algorithm.
7. The apparatus of claim 6, wherein the second variance determining module is configured to:
determining the moving distance and the course angle of each wheel between the two moments according to the pulse reading difference and the wheel parameters;
determining the displacement of each wheel according to the moving distance and the course angle through a preset displacement calculation formula;
determining the longitudinal angle difference of each wheel according to the course angle through a preset longitudinal angle difference calculation formula;
and determining the second position change amount according to the displacement amount and the longitudinal angle difference of each wheel.
8. The apparatus of claim 7, wherein the second variation determining module is configured to:
taking the moving distance and the displacement of each wheel as the input of a first cost function to obtain a first cost function value output by the first cost function;
taking the difference between the course angle and the longitudinal angle of each wheel as the input of a second cost function to obtain a second cost function value output by the second cost function;
acquiring a displacement amount and a longitudinal angle difference of a target wheel as the second position and posture variation amount; and the first valence function value corresponding to the displacement of the target wheel and the second valence function value corresponding to the longitudinal angle difference of the target wheel both meet preset function value conditions.
9. A system for determining a pose change amount, the system comprising:
the determination device of the amount of pose change of any one of claims 5-8;
a plurality of cameras disposed at different portions of a vehicle body of the vehicle; and the number of the first and second groups,
a pulse encoder disposed on each wheel of the vehicle.
10. A vehicle characterized by comprising the system for determining a pose change amount according to claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910900478.2A CN110779511B (en) | 2019-09-23 | 2019-09-23 | Pose variation determination method, device and system and vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910900478.2A CN110779511B (en) | 2019-09-23 | 2019-09-23 | Pose variation determination method, device and system and vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110779511A true CN110779511A (en) | 2020-02-11 |
| CN110779511B CN110779511B (en) | 2021-09-21 |
Family
ID=69383656
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910900478.2A Active CN110779511B (en) | 2019-09-23 | 2019-09-23 | Pose variation determination method, device and system and vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110779511B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113739819A (en) * | 2021-08-05 | 2021-12-03 | 上海高仙自动化科技发展有限公司 | Verification method and device, electronic equipment, storage medium and chip |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150186004A1 (en) * | 2012-08-17 | 2015-07-02 | Google Inc. | Multimode gesture processing |
| CN106123908A (en) * | 2016-09-08 | 2016-11-16 | 北京京东尚科信息技术有限公司 | Automobile navigation method and system |
| CN108279014A (en) * | 2017-01-05 | 2018-07-13 | 武汉四维图新科技有限公司 | Automatic Pilot map data collecting apparatus and system, map Intelligent Production System |
| CN108665488A (en) * | 2018-04-27 | 2018-10-16 | 北京汽车集团有限公司 | Global motion estimating method and device |
| CN108733039A (en) * | 2017-04-18 | 2018-11-02 | 广东工业大学 | The method and apparatus of navigator fix in a kind of robot chamber |
| CN109087359A (en) * | 2018-08-30 | 2018-12-25 | 网易（杭州）网络有限公司 | Pose determines method, pose determining device, medium and calculates equipment |
| CN109579844A (en) * | 2018-12-04 | 2019-04-05 | 电子科技大学 | Localization method and system |
| CN109710724A (en) * | 2019-03-27 | 2019-05-03 | 深兰人工智能芯片研究院（江苏）有限公司 | A kind of method and apparatus of building point cloud map |
| CN109900274A (en) * | 2019-03-25 | 2019-06-18 | 哈尔滨工业大学 | A kind of image matching method and system |
| CN109900264A (en) * | 2017-12-08 | 2019-06-18 | 浙江师范大学 | A kind of outdoor SLAM intelligent carriage |
-
2019
- 2019-09-23 CN CN201910900478.2A patent/CN110779511B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150186004A1 (en) * | 2012-08-17 | 2015-07-02 | Google Inc. | Multimode gesture processing |
| CN106123908A (en) * | 2016-09-08 | 2016-11-16 | 北京京东尚科信息技术有限公司 | Automobile navigation method and system |
| CN108279014A (en) * | 2017-01-05 | 2018-07-13 | 武汉四维图新科技有限公司 | Automatic Pilot map data collecting apparatus and system, map Intelligent Production System |
| CN108733039A (en) * | 2017-04-18 | 2018-11-02 | 广东工业大学 | The method and apparatus of navigator fix in a kind of robot chamber |
| CN109900264A (en) * | 2017-12-08 | 2019-06-18 | 浙江师范大学 | A kind of outdoor SLAM intelligent carriage |
| CN108665488A (en) * | 2018-04-27 | 2018-10-16 | 北京汽车集团有限公司 | Global motion estimating method and device |
| CN109087359A (en) * | 2018-08-30 | 2018-12-25 | 网易（杭州）网络有限公司 | Pose determines method, pose determining device, medium and calculates equipment |
| CN109579844A (en) * | 2018-12-04 | 2019-04-05 | 电子科技大学 | Localization method and system |
| CN109900274A (en) * | 2019-03-25 | 2019-06-18 | 哈尔滨工业大学 | A kind of image matching method and system |
| CN109710724A (en) * | 2019-03-27 | 2019-05-03 | 深兰人工智能芯片研究院（江苏）有限公司 | A kind of method and apparatus of building point cloud map |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113739819A (en) * | 2021-08-05 | 2021-12-03 | 上海高仙自动化科技发展有限公司 | Verification method and device, electronic equipment, storage medium and chip |
| CN113739819B (en) * | 2021-08-05 | 2024-04-16 | 上海高仙自动化科技发展有限公司 | Verification method, verification device, electronic equipment, storage medium and chip |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110779511B (en) | 2021-09-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6821712B2 (en) | Calibration of integrated sensor in natural scene | |
| Gehrig et al. | Dead reckoning and cartography using stereo vision for an autonomous car | |
| CN108886606B (en) | Mounting angle detection device, mounting angle calibration device, and mounting angle detection method for in-vehicle camera | |
| WO2019116687A1 (en) | Road map generation system and road map generation method | |
| CN112629544B (en) | Vehicle positioning method and device based on lane line | |
| US11662741B2 (en) | Vehicle visual odometry | |
| KR102542377B1 (en) | Autonomous method and device for determining a global inclination of a motor vehicle | |
| KR20200043006A (en) | Method and device to estimate position | |
| WO2012129421A2 (en) | Dynamic stereo camera calibration system and method | |
| JP2004125795A (en) | Calibration method and device of imaging sensor system | |
| CN114167470A (en) | Data processing method and device | |
| CN111902700A (en) | Method, computer program, storage device, control device and calibration path for calibrating a position sensor in a vehicle | |
| CN112862899A (en) | External parameter calibration method, device and system for image acquisition equipment | |
| CN110779511B (en) | Pose variation determination method, device and system and vehicle | |
| CN114764138A (en) | Multi-sensor sequential calibration system | |
| CN113805145A (en) | Dynamic lidar alignment | |
| CN114943952A (en) | Method, system, device and medium for obstacle fusion under multi-camera overlapped view field | |
| CN110426011A (en) | Vehicular turn angle measuring system and method | |
| CN114841188A (en) | Vehicle fusion positioning method and device based on two-dimensional code | |
| CN112577479A (en) | Multi-sensor fusion vehicle positioning method and device based on map element data | |
| CN106796126A (en) | Method and system for providing the dynamic error value of dynamic measurement in real time | |
| CN111238490A (en) | Visual positioning method and device and electronic equipment | |
| CN106716176A (en) | Method and system for adapting a navigation system | |
| CN114889606B (en) | Low-cost high-precision positioning method based on multi-sensor fusion | |
| CN114910085A (en) | Vehicle fusion positioning method and device based on road administration facility identification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |