CN111932637A - Vehicle body camera external parameter self-adaptive calibration method and device - Google Patents
Vehicle body camera external parameter self-adaptive calibration method and device Download PDFInfo
- Publication number
- CN111932637A CN111932637A CN202010839449.2A CN202010839449A CN111932637A CN 111932637 A CN111932637 A CN 111932637A CN 202010839449 A CN202010839449 A CN 202010839449A CN 111932637 A CN111932637 A CN 111932637A
- Authority
- CN
- China
- Prior art keywords
- vehicle body
- camera
- inertial navigation
- relative
- plane
- 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
- 238000000034 method Methods 0.000 title claims abstract description 71
- 238000004364 calculation method Methods 0.000 claims abstract description 37
- 230000006870 function Effects 0.000 claims abstract description 13
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 9
- 238000012216 screening Methods 0.000 claims description 29
- 230000000007 visual effect Effects 0.000 claims description 25
- 238000013519 translation Methods 0.000 claims description 22
- 238000005457 optimization Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 14
- 239000011159 matrix material Substances 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 12
- 230000003044 adaptive effect Effects 0.000 claims description 11
- 238000005070 sampling Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 9
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000007774 longterm Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 239000002245 particle Substances 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 238000012805 post-processing Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000013500 data storage Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Navigation (AREA)
Abstract
The embodiment of the invention provides a self-adaptive calibration method and a device for external parameters of a vehicle body camera, which do not need manual intervention in the whole process, perform parameter decoupling on the constraint strength of the external parameters of the camera according to vehicle body motion, and respectively establish constraint cost functions in a targeted manner. Meanwhile, the method does not need an additional control field or a calibration plate, data acquisition and parameter calculation can be automatically completed on line, and the reliability of the calibration algorithm is further improved by redundant observation of a large amount of real vehicle data.
Description
Technical Field
The embodiment of the invention relates to the technical field of automatic driving navigation and high-precision maps, in particular to a method and a device for self-adaptive calibration of external parameters of a vehicle body camera.
Background
In the related fields of automatic driving navigation, high-precision maps and the like, the camera has low cost compared with a laser radar, can provide abundant environmental information, becomes the standard configuration of an automatic driving sensor, and is widely applied to the fields of vehicle map building and positioning.
In order to effectively fuse the perception data of the camera, the camera is generally combined with the vehicle body inertial navigation when being used for map building and positioning, so that an absolute reference is provided for relative measurement values under a camera coordinate system, the perception measurement data of different time periods are unified under the absolute coordinate system, the relative pose relation between the camera and the vehicle body inertial navigation is accurately solved, and the premise of ensuring high-precision positioning of the vehicle is provided.
At present, two methods are mainly used for solving the external reference calibration from a camera to a vehicle body, one method is to utilize prior information of the environment, a calibration field is selected in advance, some control points are manually marked or an artificial target plate is manufactured, the method needs manual supervision in the calibration process, manual intervention and adjustment are carried out on the distribution of the control points according to the position of a view field of the control points in the camera, a good net shape is screened out, the calibration precision can be ensured, but the actual effect is better or better depending on the professional skill level of an operator, the automation degree and the stability of the manual operation mode are not ideal, great inconvenience is brought to actual application, the standard operation is difficult, particularly, in the long-term service operation of the camera, the deflection of the camera relative to the vehicle body is easy to occur due to the jolt of the vehicle in the long-term driving process, the original calibration parameters are invalid, and the calibration is needed again, the requirement of automation of mass production solutions cannot be met, and the actual use of such methods is also limited because the condition of the prior information of the external environment cannot always be met in time. In another method based on sensor motion constraint, a calibration field does not need to be prepared in advance, the principle of the method is that the motion tracks of all sensors on a motion platform are calculated respectively by fully translating and rotating the motion platform, and further based on the similarity of the motion tracks of rigid bodies of different sensors, the calibration operation is relatively simple, the automation degree is high, manual intervention is basically not needed in the whole process, however, due to the inevitable scale drift problem of a single camera, the scale of the motion track obtained by a visual odometer is constantly changed, and the difficulty is brought to the alignment calibration of the inertial navigation from the camera to a vehicle body based on the track.
Considering that a vehicle mainly performs near-plane motion on the ground, and sufficient motion constraint is difficult to perform on three degree-of-freedom parameters, namely offset, roll angle and pitch angle of a camera along the right upper side (Z axis) of the vehicle, the conventional sensor-based motion calibration method needs a motion platform to perform sufficient disturbance in the three-dimensional translation and rotation directions, is relatively suitable for calibration between sensors of the unmanned aerial vehicle motion platform, and is not completely suitable for motion constraint estimation of the vehicle under the near-plane condition.
The existing calibration method for the external parameters of the camera is difficult to simultaneously meet the requirements of automation, precision and reliability, the internal and external parameter calibration of the camera is the basis for constructing the automatic driving high-precision positioning application service taking vision as the core, and the limitation of the existing calibration method provides a greater challenge for the mapping positioning solution of mass production application.
Disclosure of Invention
The embodiment of the invention provides a self-adaptive calibration method and device for external parameters of a vehicle body camera, solves the problem that the weights of all parameters of the relative pose from the camera to a vehicle body in a traditional pose optimization constraint equation are difficult to balance effectively, and improves the precision of external parameter calibration.
In a first aspect, an embodiment of the present invention provides a vehicle body camera external parameter adaptive calibration method, including:
acquiring inclination and elevation calculation of a camera relative to a datum plane based on monocular visual sequence data; acquiring inclination and elevation calculation of vehicle body inertial navigation relative to a datum plane based on inertial navigation data;
obtaining translation amount, yaw angle and proportional coefficient of the camera relative to the vehicle body inertial navigation based on the corresponding relation between the vehicle body inertial navigation and the track of the camera on the reference surface in time alignment; and calculating the elevation of the camera relative to the reference surface based on the proportional coefficient and the non-proportional coefficient to obtain the external reference of the camera with 6 degrees of freedom relative to the vehicle body inertial navigation.
Preferably, the method further comprises the following steps:
and screening a plurality of road sections based on a track section screening strategy of the RANSAC model, carrying out nonlinear optimization on the external parameters of different movement tracks, and screening out the optimal external parameter component.
Preferably, before acquiring the inclination and elevation solution of the camera with respect to the reference plane based on the monocular visual sequence data, the method further includes:
the method comprises the steps of obtaining vehicle body inertial navigation data based on a 6-degree-of-freedom vehicle body motion model, carrying out dead reckoning, obtaining video data at the same time, and obtaining monocular visual sequence data without scale constraint of a vehicle body camera based on an improved orb-slam algorithm.
Preferably, the inclination and elevation calculation of the camera relative to the datum plane is obtained based on the monocular visual sequence data; the method comprises the following steps of acquiring inclination and elevation calculation of the vehicle body inertial navigation relative to a datum plane based on inertial navigation data, and specifically comprises the following steps:
respectively constructing constraint equations of attitude components of upward offset, roll angle and pitch angle of the camera and the vehicle body inertial navigation relative to a reference plane;
resolving an information matrix corresponding to each parameter component based on the constraint equation, and obtaining the information quantity of different track sections based on the information matrix;
carrying out dead reckoning based on the track segment with the highest information quantity, and solving the upward offset Z of the camera relative to the normal vector of the reference planeocRoll angle Roll relative to the reference planeocAnd Pitch angle PitchocSolving the upward offset Z of the vehicle body inertial navigation relative to the normal vector of the reference planeovRoll angle Roll relative to the reference planeovAnd Pitch angle Pitchov。
Preferably, before obtaining the translation amount, the yaw angle and the scaling factor of the camera relative to the vehicle body inertial navigation based on the time alignment of the vehicle body inertial navigation and the track corresponding relation of the camera on the reference plane, the method further includes:
and (3) a two-dimensional plane motion component projected to the datum plane by the camera and the vehicle body inertial navigation based on the inclination and the elevation of the decoupled camera and vehicle body inertial navigation relative to the datum plane is interpolated in the two-dimensional plane motion component of the vehicle body inertial navigation by taking the vehicle body inertial navigation time with the highest sampling frequency as a datum.
Preferably, the obtaining of the translation amount, the yaw angle and the proportional coefficient of the camera relative to the vehicle body inertial navigation based on the time alignment of the vehicle body inertial navigation and the track corresponding relation of the camera on the reference plane specifically includes:
based on the corresponding relation between the vehicle body inertial navigation under the time alignment and the two-dimensional plane motion of the camera, a plane hand-eye calibration constraint equation of the camera relative to the vehicle body inertial navigation under the constraint of a reference plane is constructed, meanwhile, an uncertainty matrix of parameters is solved, and the translation amount, the yaw angle and the proportional coefficient of the camera relative to the vehicle body inertial navigation are solved.
Preferably, a plurality of road sections are screened based on a track section screening strategy of a RANSAC model, the extrinsic parameters of different motion tracks are subjected to nonlinear optimization, and the optimal extrinsic parameter component is screened out, which specifically comprises the following steps:
screening out a plurality of monocular vision mileage track sections, solving the initial value of the external parameter component of each monocular vision mileage track section, establishing a cost function, carrying out nonlinear optimization on the external parameters of different movement tracks based on the cost function, and screening out the optimal external parameter component.
In a second aspect, an embodiment of the present invention provides a vehicle body camera external parameter adaptive calibration apparatus, including:
the inclination and elevation calculation module is used for acquiring inclination and elevation calculation of the camera relative to a datum plane based on monocular visual sequence data; acquiring inclination and elevation calculation of vehicle body inertial navigation relative to a datum plane based on inertial navigation data;
the external reference initial value acquisition module is used for acquiring the translation amount, the yaw angle and the proportional coefficient of the camera relative to the vehicle body inertial navigation based on the corresponding relation between the vehicle body inertial navigation and the track of the camera on the reference surface in time alignment; based on the proportional coefficient and elevation calculation of the camera relative to a datum plane without the proportional coefficient, obtaining external parameters of 6 degrees of freedom of the camera relative to the vehicle body inertial navigation;
and the external parameter optimization module screens a plurality of road sections based on a track section screening strategy of the RANSAC model, performs nonlinear optimization on external parameters of different motion tracks, and screens out optimized external parameter components.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the method for adaptively calibrating vehicle body camera external parameters according to the embodiment of the first aspect of the present invention when executing the program.
In a fourth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the vehicle body external parameter adaptive calibration method according to an embodiment of the first aspect of the present invention.
According to the self-adaptive calibration method and device for the external parameters of the vehicle body camera, manual intervention is not needed in the whole process, parameter decoupling is carried out on the external parameters of the camera according to the constraint strength of vehicle body motion, and constraint cost functions are respectively established in a targeted manner. Meanwhile, the method does not need an additional control field or a calibration plate, data acquisition and parameter calculation can be automatically completed on line, and the reliability of the calibration algorithm is further improved by redundant observation of a large amount of real vehicle data.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a flow chart of a vehicle body camera external parameter adaptive calibration method according to an embodiment of the invention;
FIG. 2 is a detailed flowchart of a vehicle body camera external parameter adaptive calibration method according to an embodiment of the invention;
FIG. 3 is a view of a visual odometer recursion resolving pose effect according to an embodiment of the invention;
FIG. 4 is a schematic diagram of a camera inertial navigation system eye calibration flat plate according to an embodiment of the present invention;
fig. 5 is a schematic physical structure diagram according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the embodiment of the present application, the term "and/or" is only one kind of association relationship describing an associated object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone.
The terms "first" and "second" in the embodiments of the present application are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, the terms "comprise" and "have", as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a system, product or apparatus that comprises a list of elements or components is not limited to only those elements or components but may alternatively include other elements or components not expressly listed or inherent to such product or apparatus. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless explicitly specifically limited otherwise.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
The existing calibration method for the external parameters of the camera is difficult to simultaneously meet the requirements of automation, precision and reliability, the internal and external parameter calibration of the camera is the basis for constructing the automatic driving high-precision positioning application service taking vision as the core, and the limitation of the existing calibration method provides a greater challenge for the mapping positioning solution of mass production application.
Therefore, the embodiment of the invention provides a self-adaptive calibration method and a device for external parameters of a vehicle body camera, which do not need manual intervention in the whole process, perform parameter decoupling according to the constraint strength of the external parameters of the vehicle body motion, and respectively establish a constraint cost function in a targeted manner. Meanwhile, the method does not need an additional control field or a calibration plate, data acquisition and parameter calculation can be automatically completed on line, and the reliability of the calibration algorithm is further improved by redundant observation of a large amount of real vehicle data. The following description and description will proceed with reference being made to various embodiments.
Fig. 1 and fig. 2 provide a vehicle body camera external parameter adaptive calibration method according to an embodiment of the present invention, including:
acquiring inclination and elevation calculation of a camera relative to a datum plane based on monocular visual sequence data; acquiring inclination and elevation calculation of vehicle body inertial navigation relative to a datum plane based on inertial navigation data;
obtaining translation amount, yaw angle and proportional coefficient of the camera relative to the vehicle body inertial navigation based on the corresponding relation between the vehicle body inertial navigation and the track of the camera on the reference surface in time alignment; and calculating the elevation of the camera relative to the reference surface based on the proportional coefficient and the non-proportional coefficient to obtain the external reference of the camera with 6 degrees of freedom relative to the vehicle body inertial navigation.
In the embodiment, as a preferred implementation mode, the vehicle body motion is correspondingly decomposed according to the observability characteristics of the parameters, different parts of the parameters are fully constrained according to respective characteristics, and in addition, the vehicle body motion section is subjected to self-adaptive screening based on the uncertainty characteristics of the parameters, so that the precision and the effectiveness of the overall parameter estimation are improved; the patent technical support of the automatic calibration of the camera relative to the vehicle body is expanded to the external reference calibration of other types of vehicle body sensors such as a multi-camera and a laser radar, and the requirement of common view of different sensors in the traditional multi-camera external reference calibration is reduced; the automatic calibration patent technology of the camera relative to the vehicle body supports the on-line calibration of vehicle body parameters, can dynamically monitor the state parameters of the vehicle body multi-sensor system in time, avoids the influence of parameter change in long-term business operation on the result quality, and improves the stability of the vehicle body sensor system.
On the basis of the above embodiment, the method further includes:
and screening a plurality of road sections based on a track section screening strategy of the RANSAC model, carrying out nonlinear optimization on the external parameters of different movement tracks, and screening out the optimal external parameter component.
On the basis of the above embodiments, before acquiring the inclination and elevation solution of the camera with respect to the reference plane based on the monocular visual sequence data, the method further includes:
the method comprises the steps of obtaining vehicle body inertial navigation data based on a 6-degree-of-freedom vehicle body motion model, carrying out dead reckoning, obtaining video data at the same time, and obtaining monocular visual sequence data without scale constraint of a vehicle body camera based on an improved orb-slam algorithm.
The concept of degrees of freedom is derived from the analytic geometry: the lowest number of independent coordinates that mathematically determine the position of a point requires one coordinate on one axis, two coordinates on one plane, and three coordinates in three-dimensional space, which is the degree of freedom of the particle in the corresponding physical problem. For the particles, a minimum of three coordinates (X, Y, Z three coordinate axes perpendicular to each other, X-direction movement, Y-direction movement, and Z-direction movement) are required in space, i.e., three degrees of freedom.
For a rigid body, since it is no longer a particle, the three-dimensional problem may be in a different state with the position of the centroid unchanged, which is called a pose, and which also needs to be represented by three coordinates. The rigid body needs to determine the posture and the position, three posture coordinates and three position coordinates respectively exist in three dimensions, and the total number of the coordinates is six, namely, the problem of the space rigid body is that six degrees of freedom exist. The position coordinates can be three space coordinates of any point on the rigid body and are used for describing the translation of the rigid body; the attitude coordinate is used for describing rotation, and the rotation takes the X axis as the axis, the rotation takes the Y axis as the axis and the rotation takes the Z axis as the axis.
In the embodiment, as a preferred implementation mode, firstly, vehicle body inertial navigation data is acquired from a general 6-degree-of-freedom vehicle body motion model hypothesis to perform dead reckoning, video data is acquired, and monocular visual mileage information without scale constraint of a vehicle body camera is acquired based on an improved orb-slam algorithm;
step 1: visual odometer
VO (Visual odometer) is to continuously capture a sequence of images by a camera in a scene, calculate a relative position relationship between adjacent frames by a change in a position of a scene feature on the sequence of images, and progressively recur a current position of the camera by associating with an image of the camera at a previous time, as shown in fig. 3, where T is Tk＝argmin∫∫ρ[Ik(π(T·π-1(u,du)))-Ik-1(u)]du, here, IkAnd Ik-1Respectively representing adjacent images, u being the image position of the feature point, pi and pi-1Respectively representing the projection of the scene characteristic points to the image and the back projection of the image characteristic points to the scene space.
The trajectory calculated by the single-camera VO is free-scale and generally needs to be used in combination with other sensors with scale constraints (such as inertial measurement units, lidar), and the absolute scale in the embodiment of the present invention is determined by the scale constraints of the vehicle-end inertial navigation.
And in consideration of the resolving efficiency of the VO of the vehicle-end camera, the position of the vehicle-end camera is progressively calculated by associating the common-view characteristics in the sliding window through an ORB-SLAM algorithm with improved performance.
On the basis of the above embodiments, inclination and elevation calculation of the camera relative to the reference plane are obtained based on monocular visual sequence data; the method comprises the following steps of acquiring inclination and elevation calculation of the vehicle body inertial navigation relative to a datum plane based on inertial navigation data, and specifically comprises the following steps:
respectively constructing constraint equations of attitude components of upward offset, roll angle and pitch angle of the camera and the vehicle body inertial navigation relative to a reference plane;
resolving an information matrix corresponding to each parameter component based on the constraint equation, and obtaining the information quantity of different track sections based on the information matrix;
carrying out dead reckoning based on the track segment with the highest information quantity, and solving the upward offset Z of the camera relative to the normal vector of the reference planeocRoll angle Roll relative to the reference planeocAnd Pitch angle PitchocSolving the upward offset Z of the vehicle body inertial navigation relative to the normal vector of the reference planeovRoll angle Roll relative to the reference planeovAnd Pitch angle Pitchov。
In this embodiment, as a preferred implementation manner, constraint equations of attitude components of the camera and the vehicle inertial navigation with respect to the ground plane upward offset component, the roll angle and the pitch angle are constructed, information matrixes solved corresponding to the parameter components are solved, information quantities of different track sections are solved according to the information matrixes and are filtered in a self-adaptive manner, corresponding track calculation is finally performed based on the track sections with high information quantities, and upward offset Z of the camera vehicle inertial navigation with respect to the ground plane normal vector is respectively solvedocRoll angle Roll relative to ground levelocAnd Pitch angle PitchocUpward offset Z of vehicle inertial navigation relative to normal vector of ground planeovRoll angle Roll relative to ground levelovAnd Pitch angle PitchovFurther calculating and solving external parameter (lambda Z) of the camera relative to the vehicle body inertial navigationvc，Rollvc，Pitchvc) Ratio of hereThe example coefficient lambda is to be solved later.
On the basis of the above embodiments, before obtaining the translation amount, yaw angle, and scaling factor of the camera relative to the inertial navigation of the vehicle body based on the time alignment of the inertial navigation of the vehicle body and the trajectory corresponding relationship of the camera on the reference plane, the method further includes:
and (3) a two-dimensional plane motion component projected to the datum plane by the camera and the vehicle body inertial navigation based on the inclination and the elevation of the decoupled camera and vehicle body inertial navigation relative to the datum plane is interpolated in the two-dimensional plane motion component of the vehicle body inertial navigation by taking the vehicle body inertial navigation time with the highest sampling frequency as a datum.
In this embodiment, as a preferred implementation, the influence of the respective components of upward offset separation, roll angle and pitch angle relative to the ground plane is decoupled from the 6-degree-of-freedom motion commonly used by the camera and the vehicle body inertial navigation, the two-dimensional motion projected to the reference ground plane is established, and the camera plane relative motion component corresponding to the time is interpolated with the vehicle body inertial navigation time with higher sampling frequency as a reference.
Step 2: inclination and elevation calculation of sensor relative to datum plane
To effectively separate planar motion from 6 degrees of freedom platform motion, the inclination of the sensor i relative to the reference plane and the height difference from the reference plane need to be resolvedix＝(xpoll，xpitch，xz) Here, the parameter xzRepresents the vertical height, x, of the reference planepollAnd xpitchRoll and pitch angles of the sensor with respect to the reference plane, respectively, can be defined more specifically as follows:
Ri＝Ry(xpitch)Rx(xroll)，ti＝[00xz]T (1.1)
in addition, define mj iFor the jth feature point observed by sensor i, then the following relationship holds:
the visual odometer based on the steps of the embodiment of the invention can construct a series of feature points in the camera field of view, and defines the following cost function based on the field of view points:
here, ,
representing the normal distance, w, of a feature point within the camera's field of view to a reference ground planejRepresenting the corresponding weight.
On the basis of the above embodiments, the obtaining of the translation amount, the yaw angle, and the proportional coefficient of the camera relative to the inertial navigation of the vehicle body based on the time alignment of the inertial navigation of the vehicle body and the trajectory corresponding relationship of the camera on the reference plane specifically includes:
based on the corresponding relation between the vehicle body inertial navigation under the time alignment and the two-dimensional plane motion of the camera, a plane hand-eye calibration constraint equation of the camera relative to the vehicle body inertial navigation under the constraint of a reference plane is constructed, meanwhile, an uncertainty matrix of parameters is solved, and the translation amount, the yaw angle and the proportional coefficient of the camera relative to the vehicle body inertial navigation are solved.
In this embodiment, as a preferred implementation, based on the correspondence between inertial navigation under time alignment and a camera plane track, a plane hand-eye calibration constraint equation of the camera relative to vehicle inertial navigation under ground plane constraint is constructed, meanwhile, an uncertainty matrix of parameters is solved, a road section with a large amount of information is adaptively screened, and translation, yaw angle and a proportionality coefficient of the camera relative to vehicle inertial navigation are solved.
And step 3: planar motion projection and time alignment
Incremental movement from 3D in step 1 (R) for each sensorI k,ti k) Decoupling the inclination and elevation of the corresponding reference plane in element SE (3) to obtain the two-dimensional plane motion of the sensor motion relative to the reference plane:
and 4, step 4: camera inertial navigation plane hand-eye calibration
Currently, in the existing visual guidance system, calibration is a basic and critical problem. The calibration is divided into two categories: firstly, calibrating hands and eyes in a three-dimensional space, directly calibrating a relation matrix of a camera coordinate system and a robot coordinate system, and converting position information of visual identification into the robot coordinate system; and secondly, converting the problem of the three-dimensional space into the problem of a two-dimensional plane, calibrating the working plane, calibrating the relation between the image plane and the working plane, and converting the image coordinate into the robot coordinate. The embodiment of the invention adopts a second type scheme.
The planar projection solves the problem that the constraint of the vehicle body motion on the unobservable parameters is weak, and for the motion after projection, a planar version of the hand-eye calibration problem needs to be solved, as shown in fig. 4, namely, the camera motion and the vehicle body motion are linked through camera-vehicle body transformation, and the transformation relation from the camera to the vehicle body is estimatedo xc＝(xx,xy,xθ,xscale)∈Sim(2)。
Starting from the well-known hand-eye calibration problem, quaternion is used for representation:
wherein,
and
respectively representing the rotational and translational components of the camera from the i-th frame to the i + 1-th frame,
and
respectively representing the rotation component and the translation component of the corresponding time, R (q) represents the rotation matrix corresponding to q, I represents the unit matrix of 3 x 3, given
In the embodiment of the invention, the formula is utilized to obtainOqCAndOtCi.e. byoxc。
On the basis of the above embodiments, a plurality of road segments are screened based on a track segment screening strategy of a RANSAC model, and the extrinsic parameters of different motion tracks are subjected to nonlinear optimization to screen out an optimal extrinsic parameter component, which specifically includes:
screening out a plurality of monocular vision mileage track sections, solving the initial value of the external parameter component of each monocular vision mileage track section, establishing a cost function, carrying out nonlinear optimization on the external parameters of different movement tracks based on the cost function, and screening out the optimal external parameter component.
In this embodiment, as a preferred embodiment, post-processing adjustment calculation is performed on all the road segments with large information amount after screening, so as to further obtain the optimized translation amount and yaw angle (X)vc，Yvc，Yawvc) And a proportionality coefficient lambda is applied to the elevation of the camera without the proportionality coefficient calculated in the step 2 relative to the ground plane, and finally the external parameter (X) with 6 degrees of freedom of the camera relative to the vehicle body inertial navigation is obtainedvc,Yvc,Zvc,Rollvc,Pitchvc,Yawvc)。
And 5: post-processing external parameter optimization
Step 4 can calculate the initial value of the camera relative to the vehicle body parameters, but considering that different motion tracks have different information amounts for parameter estimation, especially different influences on single-camera scale errors, in order to improve the effectiveness of parameter estimation, the whole suitable road section is screened to carry out nonlinear extrinsic parameter optimization, assuming that n VO track sections are screened in total, each track section has n track sections1≥2,…,nmNot less than 2, overall establishment
Solving m initial values by using an equation, introducing a RANSAC strategy, and establishing a cost function shown as follows:
the optimized extrinsic parameter components are screened accordingly.
The embodiment of the invention also provides a self-adaptive calibration device for the external parameters of the vehicle body camera, which is based on the self-adaptive calibration method for the external parameters of the vehicle body camera in the embodiments and comprises the following steps:
the inclination and elevation calculation module is used for acquiring inclination and elevation calculation of the camera relative to a datum plane based on monocular visual sequence data; acquiring inclination and elevation calculation of vehicle body inertial navigation relative to a datum plane based on inertial navigation data;
the external reference initial value acquisition module is used for acquiring the translation amount, the yaw angle and the proportional coefficient of the camera relative to the vehicle body inertial navigation based on the corresponding relation between the vehicle body inertial navigation and the track of the camera on the reference surface in time alignment; based on the proportional coefficient and elevation calculation of the camera relative to a datum plane without the proportional coefficient, obtaining external parameters of 6 degrees of freedom of the camera relative to the vehicle body inertial navigation;
and the external parameter optimization module screens a plurality of road sections based on a track section screening strategy of the RANSAC model, performs nonlinear optimization on external parameters of different motion tracks, and screens out optimized external parameter components.
Based on the same concept, an embodiment of the present invention further provides an entity structure schematic diagram, as shown in fig. 5, the server may include: a processor (processor)810, a communication Interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication Interface 820 and the memory 830 communicate with each other via the communication bus 840. The processor 810 may call logic instructions in the memory 830 to perform the following method:
acquiring inclination and elevation calculation of a camera relative to a datum plane based on monocular visual sequence data; acquiring inclination and elevation calculation of vehicle body inertial navigation relative to a datum plane based on inertial navigation data;
obtaining translation amount, yaw angle and proportional coefficient of the camera relative to the vehicle body inertial navigation based on the corresponding relation between the vehicle body inertial navigation and the track of the camera on the reference surface in time alignment; based on the proportional coefficient and elevation calculation of the camera relative to a datum plane without the proportional coefficient, obtaining external parameters of 6 degrees of freedom of the camera relative to the vehicle body inertial navigation;
and screening a plurality of road sections based on a track section screening strategy of the RANSAC model, carrying out nonlinear optimization on the external parameters of different movement tracks, and screening out the optimal external parameter component.
In addition, the logic instructions in the memory 830 may be implemented in software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Based on the same conception, the embodiment of the present invention further provides a non-transitory computer-readable storage medium, which stores a computer program, where the computer program includes at least one code, where the at least one code is executable by a main control device to control the main control device to implement the steps of the vehicle body camera external parameter adaptive calibration method according to the embodiments. Examples include:
acquiring inclination and elevation calculation of a camera relative to a datum plane based on monocular visual sequence data; acquiring inclination and elevation calculation of vehicle body inertial navigation relative to a datum plane based on inertial navigation data;
obtaining translation amount, yaw angle and proportional coefficient of the camera relative to the vehicle body inertial navigation based on the corresponding relation between the vehicle body inertial navigation and the track of the camera on the reference surface in time alignment; based on the proportional coefficient and elevation calculation of the camera relative to a datum plane without the proportional coefficient, obtaining external parameters of 6 degrees of freedom of the camera relative to the vehicle body inertial navigation;
and screening a plurality of road sections based on a track section screening strategy of the RANSAC model, carrying out nonlinear optimization on the external parameters of different movement tracks, and screening out the optimal external parameter component.
Based on the same technical concept, the embodiment of the present application further provides a computer program, which is used to implement the above method embodiment when the computer program is executed by the main control device.
The program may be stored in whole or in part on a storage medium packaged with the processor, or in part or in whole on a memory not packaged with the processor.
Based on the same technical concept, the embodiment of the present application further provides a processor, and the processor is configured to implement the above method embodiment. The processor may be a chip.
In summary, according to the method and the device for self-adaptive calibration of the external parameters of the vehicle body camera provided by the embodiment of the invention, manual intervention is not required in the whole process, parameter decoupling is performed according to the constraint strength of the external parameters of the camera by vehicle body motion, and constraint cost functions are respectively established in a targeted manner. Meanwhile, the method does not need an additional control field or a calibration plate, data acquisition and parameter calculation can be automatically completed on line, and the reliability of the calibration algorithm is further improved by redundant observation of a large amount of real vehicle data.
The embodiments of the present invention can be arbitrarily combined to achieve different technical effects.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the procedures or functions described in accordance with the present application are generated, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (e.g., coaxial cable, fiber optic, digital subscriber line) or wirelessly (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid state disk), among others.
One of ordinary skill in the art will appreciate that all or part of the processes in the methods of the above embodiments may be implemented by hardware related to instructions of a computer program, which may be stored in a computer-readable storage medium, and when executed, may include the processes of the above method embodiments. And the aforementioned storage medium includes: various media capable of storing program codes, such as ROM or RAM, magnetic or optical disks, etc.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A self-adaptive calibration method for external parameters of a vehicle body camera is characterized by comprising the following steps:
acquiring inclination and elevation calculation of a camera relative to a datum plane based on monocular visual sequence data; acquiring inclination and elevation calculation of vehicle body inertial navigation relative to a datum plane based on inertial navigation data;
obtaining translation amount, yaw angle and proportional coefficient of the camera relative to the vehicle body inertial navigation based on the corresponding relation between the vehicle body inertial navigation and the track of the camera on the reference surface in time alignment; and calculating the elevation of the camera relative to the reference surface based on the proportional coefficient and the non-proportional coefficient to obtain the external reference of the camera with 6 degrees of freedom relative to the vehicle body inertial navigation.
2. The self-adaptive calibration method for the external parameters of the vehicle body camera according to claim 1, characterized by further comprising:
and screening a plurality of road sections based on a track section screening strategy of the RANSAC model, carrying out nonlinear optimization on the external parameters of different movement tracks, and screening out the optimal external parameter component.
3. The vehicle body camera external parameter adaptive calibration method according to claim 1, wherein before obtaining the inclination and elevation solution of the camera relative to the reference plane based on the monocular visual sequence data, the method further comprises:
the method comprises the steps of obtaining vehicle body inertial navigation data based on a 6-degree-of-freedom vehicle body motion model, carrying out dead reckoning, obtaining video data at the same time, and obtaining monocular visual sequence data without scale constraint of a vehicle body camera based on an improved orb-slam algorithm.
4. The vehicle body camera external parameter self-adaptive calibration method according to claim 1, characterized in that inclination and elevation calculation of a camera relative to a datum plane are obtained based on monocular visual sequence data; the method comprises the following steps of acquiring inclination and elevation calculation of the vehicle body inertial navigation relative to a datum plane based on inertial navigation data, and specifically comprises the following steps:
respectively constructing constraint equations of attitude components of upward offset, roll angle and pitch angle of the camera and the vehicle body inertial navigation relative to a reference plane;
resolving an information matrix corresponding to each parameter component based on the constraint equation, and obtaining the information quantity of different track sections based on the information matrix;
carrying out dead reckoning based on the track segment with the highest information quantity, and solving the upward offset Z of the camera relative to the normal vector of the reference planeocRoll angle Roll relative to the reference planeocAnd Pitch angle PitchocSolving the upward offset Z of the vehicle body inertial navigation relative to the normal vector of the reference planeovRoll angle Roll relative to the reference planeovAnd Pitch angle Pitchov。
5. The vehicle body camera external parameter self-adaptive calibration method according to claim 1, wherein before obtaining the translation amount, yaw angle and scale coefficient of the camera relative to the vehicle body inertial navigation based on the corresponding relation between the vehicle body inertial navigation and the track of the camera on the reference surface under time alignment, the method further comprises:
and (3) a two-dimensional plane motion component projected to the datum plane by the camera and the vehicle body inertial navigation based on the inclination and the elevation of the decoupled camera and vehicle body inertial navigation relative to the datum plane is interpolated in the two-dimensional plane motion component of the vehicle body inertial navigation by taking the vehicle body inertial navigation time with the highest sampling frequency as a datum.
6. The vehicle body camera external parameter self-adaptive calibration method according to claim 5, wherein the translation amount, the yaw angle and the proportional coefficient of the camera relative to the vehicle body inertial navigation are obtained based on the corresponding relation between the vehicle body inertial navigation and the track of the camera on the reference surface under time alignment, and specifically comprises the following steps:
based on the corresponding relation between the vehicle body inertial navigation under the time alignment and the two-dimensional plane motion of the camera, a plane hand-eye calibration constraint equation of the camera relative to the vehicle body inertial navigation under the constraint of a reference plane is constructed, meanwhile, an uncertainty matrix of parameters is solved, and the translation amount, the yaw angle and the proportional coefficient of the camera relative to the vehicle body inertial navigation are solved.
7. The vehicle body camera external parameter adaptive calibration method according to claim 1, wherein a plurality of road sections are screened based on a track section screening strategy of a RANSAC model, external parameters of different motion tracks are subjected to nonlinear optimization, and an optimal external parameter component is screened out, and the method specifically comprises the following steps:
screening out a plurality of monocular vision mileage track sections, solving the initial value of the external parameter component of each monocular vision mileage track section, establishing a cost function, carrying out nonlinear optimization on the external parameters of different movement tracks based on the cost function, and screening out the optimal external parameter component.
8. The utility model provides a car body camera external parameter self-adaptation calibration device which characterized in that includes:
the inclination and elevation calculation module is used for acquiring inclination and elevation calculation of the camera relative to a datum plane based on monocular visual sequence data; acquiring inclination and elevation calculation of vehicle body inertial navigation relative to a datum plane based on inertial navigation data;
the external reference initial value acquisition module is used for acquiring the translation amount, the yaw angle and the proportional coefficient of the camera relative to the vehicle body inertial navigation based on the corresponding relation between the vehicle body inertial navigation and the track of the camera on the reference surface in time alignment; based on the proportional coefficient and elevation calculation of the camera relative to a datum plane without the proportional coefficient, obtaining external parameters of 6 degrees of freedom of the camera relative to the vehicle body inertial navigation;
and the external parameter optimization module screens a plurality of road sections based on a track section screening strategy of the RANSAC model, performs nonlinear optimization on external parameters of different motion tracks, and screens out optimized external parameter components.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method for adaptive calibration of vehicle body camera external parameters according to any one of claims 1 to 7 when executing the program.
10. A non-transitory computer readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps of the vehicle body camera external parameter adaptive calibration method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010839449.2A CN111932637B (en) | 2020-08-19 | 2020-08-19 | Vehicle body camera external parameter self-adaptive calibration method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010839449.2A CN111932637B (en) | 2020-08-19 | 2020-08-19 | Vehicle body camera external parameter self-adaptive calibration method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111932637A true CN111932637A (en) | 2020-11-13 |
| CN111932637B CN111932637B (en) | 2022-12-13 |
Family
ID=73305471
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010839449.2A Active CN111932637B (en) | 2020-08-19 | 2020-08-19 | Vehicle body camera external parameter self-adaptive calibration method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111932637B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113093740A (en) * | 2021-03-29 | 2021-07-09 | 杭州海康威视数字技术股份有限公司 | Parameter calibration method, system, device and equipment |
| CN113327294A (en) * | 2021-06-18 | 2021-08-31 | 北京云迹科技有限公司 | Camera dynamic calibration method and device, electronic equipment and storage medium |
| CN113340334A (en) * | 2021-07-29 | 2021-09-03 | 新石器慧通（北京）科技有限公司 | Sensor calibration method and device for unmanned vehicle and electronic equipment |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090248304A1 (en) * | 2008-03-28 | 2009-10-01 | Regents Of The University Of Minnesota | Vision-aided inertial navigation |
| CN102269813A (en) * | 2011-06-23 | 2011-12-07 | 中国电子科技集团公司第三十八研究所 | Interference processing technology of airborne non-vertical dual-antenna InSAR system |
| CN202549080U (en) * | 2012-03-16 | 2012-11-21 | 中国民用航空总局第二研究所 | Fusion system of radar data, flight plan data and ADS-B data |
| CN105469386A (en) * | 2015-11-11 | 2016-04-06 | 浙江大华技术股份有限公司 | Method and device for determining height and pitch angle of stereo camera |
| CN106803271A (en) * | 2016-12-23 | 2017-06-06 | 成都通甲优博科技有限责任公司 | A kind of camera marking method and device of vision guided navigation unmanned plane |
| WO2017101437A1 (en) * | 2015-12-15 | 2017-06-22 | 华为技术有限公司 | Inertial navigation cooperative locating method and locating device |
| CN106910223A (en) * | 2016-11-02 | 2017-06-30 | 北京信息科技大学 | A kind of Robotic Hand-Eye Calibration method based on convex lax global optimization approach |
| CN107516326A (en) * | 2017-07-14 | 2017-12-26 | 中国科学院计算技术研究所 | Merge monocular vision and the robot localization method and system of encoder information |
| CN108717712A (en) * | 2018-05-29 | 2018-10-30 | 东北大学 | A kind of vision inertial navigation SLAM methods assumed based on ground level |
| CN109029433A (en) * | 2018-06-28 | 2018-12-18 | 东南大学 | Join outside the calibration of view-based access control model and inertial navigation fusion SLAM on a kind of mobile platform and the method for timing |
| CN109696663A (en) * | 2019-02-21 | 2019-04-30 | 北京大学 | A kind of vehicle-mounted three-dimensional laser radar scaling method and system |
| CN110136208A (en) * | 2019-05-20 | 2019-08-16 | 北京无远弗届科技有限公司 | A kind of the joint automatic calibration method and device of Visual Servoing System |
| CN110332945A (en) * | 2019-08-01 | 2019-10-15 | 北京眸星科技有限公司 | Navigation method and device based on traffic route graticule visual identity |
| US20190370997A1 (en) * | 2018-06-01 | 2019-12-05 | TuSimple | Smoothness constraint for camera pose estimation |
-
2020
- 2020-08-19 CN CN202010839449.2A patent/CN111932637B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090248304A1 (en) * | 2008-03-28 | 2009-10-01 | Regents Of The University Of Minnesota | Vision-aided inertial navigation |
| CN102269813A (en) * | 2011-06-23 | 2011-12-07 | 中国电子科技集团公司第三十八研究所 | Interference processing technology of airborne non-vertical dual-antenna InSAR system |
| CN202549080U (en) * | 2012-03-16 | 2012-11-21 | 中国民用航空总局第二研究所 | Fusion system of radar data, flight plan data and ADS-B data |
| CN105469386A (en) * | 2015-11-11 | 2016-04-06 | 浙江大华技术股份有限公司 | Method and device for determining height and pitch angle of stereo camera |
| WO2017101437A1 (en) * | 2015-12-15 | 2017-06-22 | 华为技术有限公司 | Inertial navigation cooperative locating method and locating device |
| CN106910223A (en) * | 2016-11-02 | 2017-06-30 | 北京信息科技大学 | A kind of Robotic Hand-Eye Calibration method based on convex lax global optimization approach |
| CN106803271A (en) * | 2016-12-23 | 2017-06-06 | 成都通甲优博科技有限责任公司 | A kind of camera marking method and device of vision guided navigation unmanned plane |
| CN107516326A (en) * | 2017-07-14 | 2017-12-26 | 中国科学院计算技术研究所 | Merge monocular vision and the robot localization method and system of encoder information |
| CN108717712A (en) * | 2018-05-29 | 2018-10-30 | 东北大学 | A kind of vision inertial navigation SLAM methods assumed based on ground level |
| US20190370997A1 (en) * | 2018-06-01 | 2019-12-05 | TuSimple | Smoothness constraint for camera pose estimation |
| CN109029433A (en) * | 2018-06-28 | 2018-12-18 | 东南大学 | Join outside the calibration of view-based access control model and inertial navigation fusion SLAM on a kind of mobile platform and the method for timing |
| CN109696663A (en) * | 2019-02-21 | 2019-04-30 | 北京大学 | A kind of vehicle-mounted three-dimensional laser radar scaling method and system |
| CN110136208A (en) * | 2019-05-20 | 2019-08-16 | 北京无远弗届科技有限公司 | A kind of the joint automatic calibration method and device of Visual Servoing System |
| CN110332945A (en) * | 2019-08-01 | 2019-10-15 | 北京眸星科技有限公司 | Navigation method and device based on traffic route graticule visual identity |
Non-Patent Citations (1)
| Title |
|---|
| 王勇等: "一种相机标定辅助的单目视觉室内定位方法", 《测绘通报》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113093740A (en) * | 2021-03-29 | 2021-07-09 | 杭州海康威视数字技术股份有限公司 | Parameter calibration method, system, device and equipment |
| CN113327294A (en) * | 2021-06-18 | 2021-08-31 | 北京云迹科技有限公司 | Camera dynamic calibration method and device, electronic equipment and storage medium |
| CN113340334A (en) * | 2021-07-29 | 2021-09-03 | 新石器慧通（北京）科技有限公司 | Sensor calibration method and device for unmanned vehicle and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111932637B (en) | 2022-12-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111932637B (en) | Vehicle body camera external parameter self-adaptive calibration method and device | |
| CN108629831B (en) | Three-dimensional human body reconstruction method and system based on parameterized human body template and inertial measurement | |
| CN107516326B (en) | Robot positioning method and system fusing monocular vision and encoder information | |
| WO2022042184A1 (en) | Method and apparatus for estimating position of tracking target, and unmanned aerial vehicle | |
| JP2020030204A (en) | Distance measurement method, program, distance measurement system and movable object | |
| CN109544630B (en) | Pose information determination method and device and visual point cloud construction method and device | |
| CN107941217A (en) | A kind of robot localization method, electronic equipment, storage medium, device | |
| CN113551665B (en) | High-dynamic motion state sensing system and sensing method for motion carrier | |
| CN111783679A (en) | Real-time whole body dynamic capture system and method based on data mixing of camera and IMU | |
| CN110728716B (en) | Calibration method and device and aircraft | |
| CN113029128A (en) | Visual navigation method and related device, mobile terminal and storage medium | |
| CN114111776A (en) | Positioning method and related device | |
| CN115272452A (en) | Target detection positioning method and device, unmanned aerial vehicle and storage medium | |
| CN114018291A (en) | Calibration method and device for parameters of inertial measurement unit | |
| CN115218906A (en) | Indoor SLAM-oriented visual inertial fusion positioning method and system | |
| CN111998870B (en) | Calibration method and device of camera inertial navigation system | |
| CN117392241B (en) | Sensor calibration method and device in automatic driving and electronic equipment | |
| CN114529585A (en) | Mobile equipment autonomous positioning method based on depth vision and inertial measurement | |
| CN110598370A (en) | Robust attitude estimation of multi-rotor unmanned aerial vehicle based on SIP and EKF fusion | |
| CN112284381B (en) | Visual inertia real-time initialization alignment method and system | |
| CN112258582B (en) | Camera attitude calibration method and device based on road scene recognition | |
| CN117115252A (en) | Bionic ornithopter space pose estimation method based on vision | |
| CN110530400A (en) | Gyroscopic drift modification method, device, photoelectric nacelle and aircraft | |
| CN115560744A (en) | Robot, multi-sensor-based three-dimensional mapping method and storage medium | |
| CN113790711B (en) | Unmanned aerial vehicle low-altitude flight pose uncontrolled multi-view measurement method and storage medium |
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 |