CN114494456A - Multiphase external parameter calibration method, system, medium and terminal based on mobile calibration board - Google Patents
Multiphase external parameter calibration method, system, medium and terminal based on mobile calibration board Download PDFInfo
- Publication number
- CN114494456A CN114494456A CN202210026375.XA CN202210026375A CN114494456A CN 114494456 A CN114494456 A CN 114494456A CN 202210026375 A CN202210026375 A CN 202210026375A CN 114494456 A CN114494456 A CN 114494456A
- Authority
- CN
- China
- Prior art keywords
- calibration
- checkerboard
- camera
- pose
- cameras
- 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.)
- Pending
Links
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
Abstract
The invention provides a multiphase external parameter calibration method based on a mobile calibration plate, which comprises the following steps: the calibration vehicle carrying the calibration board moves in the visual field of the multiple RGB-D cameras; acquiring checkerboard angular points in each camera image, and solving the position and posture of each checkerboard and each camera; establishing a checkerboard and pose graphs of all cameras based on the poses, and optimizing the pose graphs; and obtaining global external reference calibration of all cameras based on the optimized pose graph. The invention establishes the pose graphs of the plurality of cameras and the checkerboards, solves and optimizes the pose graphs to obtain the optimal camera pose, and improves the calibration precision.
Description
Technical Field
The invention relates to the technical field of camera external parameter calibration in the field of image processing, in particular to a multi-phase external parameter calibration method, a multi-phase external parameter calibration system and a multi-phase external parameter calibration terminal based on a mobile calibration board.
Background
Autonomous Valet Parking (AVP) is a research hotspot, and compared with a single-vehicle intelligent Parking scheme, the field-oriented intelligent Parking scheme has the advantages of rich global information, interactive communication in a Parking lot and the like. The low-cost RGB-D camera promotes the landing of the field-side intelligent AVP scheme.
The distributed RGB-D camera captures color and depth images of the indoor parking lot from different positions and angles, and reconstructs color and geometric information of a scene. Accurate and fast landmark camera outliners (translation and rotation) are fundamental steps in building a network of cameras that can capture large scenes and merge multiple camera views into the same coordinates.
Generally, the external reference calibration method of the multi-camera may be classified into a method using a calibration object and a method not using a calibration object. The method without using the calibration object has strong dependence on the scene, and inaccurate understanding of unknown scene characteristics, which leads to low calibration precision and a plurality of incorrect corresponding relations; by using calibration objects such as calibration plates, calibration balls and the like, a stable and accurate detection algorithm needs to be designed, and a better error function needs to be designed.
Although many calibration objects are used for calibrating a plurality of cameras, most of the calibration objects are not suitable for the situation that the cameras in the indoor parking lot are sparsely arranged, and when the number of the cameras is large, calibration errors and calibration complexity are greatly improved.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a multi-phase external parameter calibration method and system based on a mobile calibration plate.
According to one aspect of the invention, a multi-phase external parameter calibration method based on a mobile calibration board is provided, wherein a calibration vehicle carrying the calibration board moves in the visual field of a multi-RGB-D camera;
acquiring checkerboard angular points in each camera image, and solving the positions of the checkerboard and a single camera;
establishing a position and posture graph of the checkerboard and all cameras based on the position and posture of the single camera, and optimizing the position and posture graph;
and obtaining global external reference calibration of all cameras based on the optimized pose graph.
Preferably, the stay time of the calibration vehicle is not less than 10 seconds when moving into the common view of the plurality of cameras.
Preferably, the acquiring the checkerboard corner points in each camera image and solving the pose of the checkerboard and the pose of the single camera includes:
detecting all corner points of the checkerboard in the image plane by using a findChessboardCorrerSB () method in an OpenCV4 image processing library;
based on all the angular points, the PnP (Passive-n-Point) problem is solved to obtain the relative position of the checkerboard and the camera,
in the formula: kCFor internal reference of camera, dCAs a camera distortion parameter, B' is the position of all corner points of the checkerboard detected in the image,Bb is the total corner points of the checkerboard in space;
defining a reprojection error function:
in the formula: (r, c) is epsilon I as a checkerboard corner point index with length and width r and c, b'r,cFor the detected corner positions in the image plane,Bbr,cfor the position, rep, of each point of the checkerboard in the checkerboard coordinate systemC() is a reprojection function of the 3D point in space projected to the image plane calculated by the internal parameter and the distortion parameter;
and minimizing the reprojection error function to obtain internal parameters of a single camera, namely obtaining the poses of the checkerboard and the single camera.
Preferably, the establishing a pose graph of the checkerboard and all the cameras based on the pose of the checkerboard and the pose of a single camera, and the optimizing the pose graph includes:
constructing a pose graph, wherein the vertexes of the pose graph store the poses of the camera and the calibration plate under the global coordinate system, and each edge is used for storing the relative pose transformation of the vertex of the camera and the vertex of the calibration plate
Converting the pose constraints in the position resource graph into an error function:
in the formula (I), the compound is shown in the specification,
for observing the coefficients, during the calibration phase k, if the camera CiA checkerboard is detected, then
Otherwise
For regularization factor, camera C is representediError in the estimated position of the corner points in the image provided, typically taking 0.5 or 1, reprojection error function
The method can be expanded into a checkerboard angular point expression form, the inner parts of the checkerboard grids are re-projected to a pixel plane, and a projection error is obtained by the difference value of the detected angular points;
as a camera pose of AND
Is a checkerboard pose.
And minimizing the error function, solving by using a Lewenberg-Marquardt method, and calculating by using a Ceres Solver nonlinear optimization library to obtain an optimized pose graph.
Preferably, the obtaining of the pose estimate of the camera global based on the optimized pose graph includes:
based on the global coordinate system of the ground plane hypothesis, the calibration plate is placed at different positions on the ground, the position of the checkerboard relative to the ground is obtained, the position of the checkerboard relative to the ground is two-dimensional constraint of the position of the plane, and the translation amount (t)x,ty) And rotation amount θ constitutes:
adding the pose two-dimensional constraint of the checkerboard into the error function, and transforming the pose relationship of the calibration board into:
the above expression converts the pose of the calibration plate relative to the world coordinate system into a two-dimensional plane pose and a pose of the calibration plate relative to the two-dimensional plane.
And (4) obtaining the external parameters of the multiple RGB-D cameras through calculation, namely obtaining the global external parameter calibration of all the cameras.
Based on the second aspect of the present invention, a multi-phase external parameter calibration method based on a mobile calibration board is provided, which includes:
a calibration vehicle having a wifi module, a motor drive and a controller,
the calibration plate is arranged on the top of the calibration vehicle and moves along with the calibration vehicle;
the RGB-D cameras are distributed in a plurality of directions and are used for shooting the calibration board;
a switch that receives data information of the RGB-D camera;
and the server receives the data information processed by the switch.
Preferably, the RGB-D camera is capable of obtaining color images and depth images, wherein the depth map can be computationally converted into point cloud information.
Preferably, the plurality of RGB-D camera data is transmitted to the server for calculation and analysis by an edge calculation unit,
and synchronizing the time of the edge computing units by using a chrono time synchronization method, and taking the server time as a reference.
According to a third aspect of the present invention, there is provided a terminal comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor being operable to perform any of the methods described herein or to operate any of the systems described herein when the program is executed by the processor.
According to a fourth aspect of the invention, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, is operable to perform any of the methods described herein or to run any of the systems described herein.
Compared with the prior art, the invention has the following beneficial effects:
(1) the distributed multi-RGB-D camera external parameter calibration method based on pose graph optimization establishes pose graphs of a plurality of cameras and a checkerboard, solves and optimizes the pose graphs to obtain the optimal camera pose, and improves the calibration precision;
(2) the method can realize the automatic calibration of field-end multi-RGB-D camera external parameters, has low cost, simple operation, reduced manual participation and low calculation complexity;
(3) the distributed multi-RGB-D camera external parameter calibration system based on pose graph optimization widens the solution idea of the problems in the similar fields, is realized in the field for the first time, and has higher research value;
(4) the distributed multi-RGB-D camera external reference calibration system based on pose graph optimization has the function of remote image return, helps a user to intuitively perceive the position of a vehicle and remotely control the motion function of the vehicle, moves different positions of a calibration plate in the visual field of a camera, reduces the consumption of time and physical strength caused by manual movement of the calibration plate, and improves the calibration efficiency;
drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
FIG. 1 is a schematic flow chart of a multi-phase external parameter calibration method based on a mobile calibration plate according to an embodiment of the present invention;
FIG. 2 is a system diagram of a mobile calibration board according to an embodiment of the present invention, which is composed of a user end and a calibration cart;
FIG. 3 is a flow diagram of distributed RGB-D camera extrinsic calibration according to one embodiment of the present invention;
FIG. 4 is an abstract view of a camera and calibration plate pose diagram of one embodiment of the present invention;
FIG. 5 is a global external reference calibration for all cameras according to one embodiment of the present invention.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that variations and modifications can be made by persons skilled in the art without departing from the concept of the invention. All falling within the scope of the present invention.
As shown in fig. 1, a flowchart of a method for calibrating an external parameter of a multi-phase machine based on a mobile calibration plate according to an embodiment of the present invention includes:
s100, moving a calibration vehicle carrying a calibration plate in the visual field of the multi-RGB-D camera;
s200, obtaining checkerboard angular points in each camera image, and solving the position and posture of each checkerboard and each camera;
s300, establishing a checkerboard and pose graphs of all cameras based on the poses, and optimizing the pose graphs;
and S400, obtaining global external reference calibration of all cameras based on the optimized pose graph.
Based on the foregoing embodiments, the present invention provides a preferred embodiment, as shown in fig. 2, which is a flowchart of a multi-phase external parameter calibration method based on a mobile calibration board according to this embodiment. In this embodiment, a field-end distributed multi-RGB-D camera system is used as a platform to analyze and calculate an acquired image, and explore how to efficiently and simply calibrate external parameters between cameras, where an adopted calibration object is a calibration plate, and a calibration algorithm is mainly a multi-RGB-D camera external parameter calibration method based on pose graph optimization.
For complicated field-end distributed RGB-D camera extrinsic parameter calibration, in this embodiment, a mobile calibration board is designed as a calibration reference, as shown in fig. 3, the mobile calibration board includes a calibration car and a user operation interface, a user mobile phone and the calibration car are connected through a local WIFI technology, a car-mounted camera is calibrated, an image is acquired and transmitted back to a user end, the calibration car is placed on the calibration board, and the camera moves in the field of view, and correlates the pose of the camera. And a calibration algorithm is designed, images obtained by the cameras are processed, external parameters among the cameras are solved, and preparation is made for using a plurality of RGB-D cameras at the subsequent field end.
In this embodiment, the method for calibrating the external parameters of the multiple phases based on the mobile calibration plate includes:
s11, starting a plurality of cameras in the central server through remote login;
s12, acquiring real-time image data of a plurality of RGB-D cameras, collecting the image data through a low-cost edge computing unit such as a raspberry pi, compressing the image data, and transmitting the image data to a central server through a network to reduce the network transmission bandwidth;
and S13, operating the calibration vehicle to move in the camera view and stay longer at key positions such as the camera common view and the like so as to obtain more effective constraints among the cameras, and then detecting the checkerboard corner points in each camera image.
To obtain the checkerboard corners more completely, a preferred embodiment is provided, which uses the findchessboardcorrnersb () method in the OpenCV4 image processing library to detect all the corners of the checkerboard in the image plane;
and S14, estimating the position and pose of the checkerboard of the camera, wherein when a complete checkerboard corner point is detected, the relative position and pose of the checkerboard and the camera need to be estimated.
In order to more accurately obtain the relative positions of the checkerboard and the camera, a preferred embodiment is provided, and a corresponding solution is obtained by solving a PnP (Passive-n-Point) problem:
in the formula: kCFor internal reference of camera, dCIs a phase ofThe machine distortion parameter, B' is the position of all corner points of the checkerboard detected in the image,Band B is the position of all corner points of the checkerboard in space.
To solve the above PnP problem, a reprojection error function needs to be defined:
in the formula: (r, c) is epsilon I as a checkerboard corner point index with length and width r and c, b'r,cFor the detected corner positions in the image plane,Bbr,cfor the position, rep, of each point of the checkerboard in the checkerboard coordinate systemCThe projection function is a reprojection function of the 3D point in the space projected to the image plane, and is obtained through calculation of internal parameters and distortion parameters.
And S15, establishing a pose graph, moving the calibration vehicle in a public view, adding more pose data along with the calibration process after obtaining the relative pose of the camera and the checkerboard, processing the relationship of the data, and providing constraint for the precision of external reference calibration.
In order to make the pose graph more accurate, the present invention provides a preferred embodiment, as shown in fig. 3, which is an abstract of the pose graph of the camera and the calibration board, wherein the vertices in the pose graph are used to store the poses of the camera and the calibration board in the global coordinate system, and each edge is used to store the relative pose transformation between the vertex of the camera and the vertex of the calibration board
And S16, solving the pose graph, and converting the pose constraint into an error function for numerical calculation after the pose graph is established. Further, the error function is as follows:
in the formula (I), the compound is shown in the specification,
to observe the coefficients, in calibration phase k (calibration phase k representing time, k frame image), if camera CiA checkerboard is detected, then
Otherwise
For regularization factor, camera C is representediError in the estimated position of the corner points in the image provided, typically taking 0.5 or 1, reprojection error function
The method can be expanded into a checkerboard angular point expression form, the inner parts of the checkerboard grids are re-projected to a pixel plane, and a projection error is obtained by the difference value of the detected angular points;
as a camera pose of AND
Is a checkerboard pose.
In order to obtain an optimal multi-camera pose, the error function needs to be minimized.
Further, the solution was performed by Levenberg-Marquardt (Levenberg-Marquardt, LM) method, and the calculation analysis was performed by using Ceres Solver nonlinear optimization library. The relative poses among the multiple cameras are associated by establishing a pose graph of the multiple cameras and the checkerboard, errors in a calibration stage are accumulated by collecting multi-frame data, and the external parameters among the multiple cameras are obtained by finding out a global optimal solution.
S17, extracting a global coordinate system based on the ground plane hypothesis, placing the calibration board at different positions on the ground, and expressing the relative position of the checkerboard relative to the ground as follows:
the checkerboard is changed into planar two-dimensional motion by the translation amount (t)x,ty) And the rotation amount theta, then adding the two-dimensional pose constraint of the checkerboard into an error function, and transforming the pose relationship of the calibration board into a relationship of:
the expression converts the position and the posture of the calibration plate relative to the world coordinate system into the two-dimensional plane position and the posture of the calibration plate relative to the two-dimensional plane, reduces the parameter quantity and improves the operation efficiency.
In the actual calibration process, in order to find the ground as a world coordinate system, a large-area calibration plate is often not suitable as a calibration reference object, and through the global coordinate extraction method of the ground plane assumption, the calibration plate is only required to be placed at a plurality of positions on the ground, and a plurality of checkerboards are constrained to be on the same plane in the algorithm, so that the global ground extraction has higher consistency.
And S18, calculating to obtain and store the multiple RGB-D camera extrinsic parameters, as shown in FIG. 5, showing the global extrinsic parameter calibration results of all cameras of the present embodiment, which are composed of camera poses, checkerboard poses and ground.
In other embodiments of the present invention, in combination with the calibration flow shown in fig. 1 and the multi-phase extrinsic parameter calibration of the pose graph optimization method shown in fig. 3, ten RGB-D cameras installed at the end of an indoor parking lot are calibrated, data is transmitted to the central server through a raspberry group, a calibration vehicle is moved within the field of view of the cameras, the camera poses are associated, a camera and checkerboard pose graph is established, an error function is periodically optimized, multiple RGB-D camera extrinsic parameters are obtained by solving, and the actual calibration result is shown in fig. 4.
The present invention provides another embodiment based on the same concept of the above-described embodiments. A multi-phase external parameter calibration method based on a mobile calibration plate comprises the following steps: the calibration vehicle is provided with a wifi module, a motor drive and a controller, and the calibration plate is mounted at the top of the calibration vehicle and moves along with the calibration vehicle; the RGB-D cameras are distributed in a plurality of directions, and the calibration plate is shot; the switch receives data information of the RGB-D camera; and the server receives the data information processed by the switch.
Further, the RGB-D camera can obtain color images and depth images, wherein the depth images can be computationally converted into point cloud information.
Based on the same idea of the foregoing embodiments, in other embodiments of the present invention, a terminal is provided, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor, when executing the program, may be configured to perform any one of the methods described above, or to execute any one of the systems.
Based on the same idea of the above embodiments, in other embodiments of the invention, a computer-readable storage medium is provided, on which a computer program is stored, which, when being executed by a processor, is operable to perform any one of the above methods or to run any one of the above systems.
The foregoing description of specific embodiments of the present invention has been presented. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes and modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the invention. The above-described preferred features may be used in any combination without conflict with each other.
Claims (10)
1. A multi-phase external parameter calibration method based on a mobile calibration plate is characterized in that,
the calibration vehicle carrying the checkerboards moves in the visual fields of the RGB-D cameras;
acquiring checkerboard angular points in each camera image, and solving the positions of the checkerboard and a single camera;
establishing a checkerboard and pose graphs of all cameras based on the checkerboard and the poses of the single camera, and optimizing the pose graphs;
and obtaining global external reference calibration of all cameras based on the optimized pose graph.
2. The method for calibrating the external parameters of the multiple phases based on the mobile calibration plate as claimed in claim 1, wherein the staying time of the calibration cart is not less than 10 seconds when the calibration cart moves to the common visual field of the multiple cameras.
3. The method for multi-phase external parameter calibration based on the mobile calibration plate of claim 1, wherein the obtaining of the checkerboard angular points in each camera image and the solving of the poses of the checkerboard and the single camera comprise:
detecting all corner points of the checkerboard in the image plane by using a findChessboardCorrerSB () method in an OpenCV4 image processing library;
solving a PnP (Passive-n-Point) problem based on all the angular points to obtain the relative pose of the checkerboard and the camera,
in the formula: kCFor internal reference of camera, dCAs a camera distortion parameter, B' is the position of all corner points of the checkerboard detected in the image,Bb is the total corner points of the checkerboard in space;
a re-projection error function is defined,
in the formula: (r, c) is epsilon I as a checkerboard corner point index with length and width r and c, b'r,cFor the detected corner positions in the image plane,Bbr,cfor the position, rep, of each point of the checkerboard in the checkerboard coordinate systemC() is a reprojection function of the 3D point in space projected to the image plane calculated by the internal parameter and the distortion parameter;
and minimizing the reprojection error function to obtain internal parameters of a single camera, namely obtaining the poses of the checkerboard and the single camera.
4. The method for multi-phase external parameter calibration based on the mobile calibration plate of claim 1, wherein the establishing a pose graph of a checkerboard and all cameras based on the checkerboard and the pose of a single camera, and optimizing the pose graph comprises:
constructing a pose graph, wherein the vertexes of the pose graph store the poses of the camera and the calibration plate under the global coordinate system, and each edge is used for storing the relative pose transformation of the vertex of the camera and the vertex of the checkerboard
Converting pose constraints in the pose graph into an error function:
in the formula (I), the compound is shown in the specification,
for observing the coefficients, during the calibration phase k, if the camera CiA checkerboard is detected, then
Otherwise
For regularization factor, camera C is representediError of the estimated position of the corner point in the provided image is 0.5 or 1, and an error function is reprojected
Expanding the image into a checkerboard angular point expression form, re-projecting the inner part of the checkerboard to a pixel plane, and obtaining a projection error by comparing the difference value of the inner part of the checkerboard with the detected angular point;
as a camera pose of AND
Is a checkerboard pose;
and minimizing the error function, solving by using a Lewenberg-Marquardt method, and calculating by using a Ceres Solver nonlinear optimization library to obtain an optimized pose graph.
5. The method for multi-phase machine external parameter calibration based on the mobile calibration plate according to claim 1, wherein the obtaining of the pose estimation of the camera global based on the optimized pose graph comprises:
based on the global coordinate system of the ground plane hypothesis, the calibration plate is placed at different positions on the ground, the position of the checkerboard relative to the ground is obtained, the position of the checkerboard relative to the ground is two-dimensional constraint of the position of the plane, and the translation amount (t)x,ty) And rotation amount θ constitutes:
adding the pose two-dimensional constraint of the checkerboard into the error function, and transforming the pose relationship of the calibration board into:
position and pose of calibration plate relative to world coordinate system
Converted into the pose of the calibration plate relative to the two-dimensional plane
And optimizing the error function, and calculating to obtain a plurality of RGB-D camera external parameters, namely obtaining global external parameter calibration of all cameras.
6. A system for implementing a field-end multi RGB-D camera extrinsic reference calibration method of a mobile calibration plate according to any one of claims 1 to 5, comprising:
the calibration vehicle is provided with a wifi module, a motor drive and a controller;
the calibration plate is arranged on the top of the calibration vehicle and moves along with the calibration vehicle;
the RGB-D cameras are distributed in a plurality of directions and are used for shooting the calibration board;
a switch that receives data information of the RGB-D camera;
and the server receives the data information processed by the switch.
7. The multi-phase machine external parameter calibration system based on the mobile calibration plate of claim 6, wherein the RGB-D camera can obtain color images and depth images, wherein the depth images are converted into point cloud information through calculation.
8. The multi-phase machine external reference calibration system based on the mobile calibration plate of claim 6, wherein a plurality of RGB-D camera data are transmitted to the server through an edge calculation unit for calculation and analysis, the time of a plurality of edge calculation units is synchronized using a chrono time synchronization method, and the server time is used as a reference.
9. A terminal comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program is operable to perform the method of any one of claims 1 to 5 or to operate the system of any one of claims 6 to 8.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, is adapted to carry out the method of any one of claims 1 to 5 or to carry out the system of any one of claims 6 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210026375.XA CN114494456A (en) | 2022-01-11 | 2022-01-11 | Multiphase external parameter calibration method, system, medium and terminal based on mobile calibration board |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210026375.XA CN114494456A (en) | 2022-01-11 | 2022-01-11 | Multiphase external parameter calibration method, system, medium and terminal based on mobile calibration board |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114494456A true CN114494456A (en) | 2022-05-13 |
Family
ID=81510543
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210026375.XA Pending CN114494456A (en) | 2022-01-11 | 2022-01-11 | Multiphase external parameter calibration method, system, medium and terminal based on mobile calibration board |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114494456A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI798098B (en) * | 2022-05-31 | 2023-04-01 | 鴻海精密工業股份有限公司 | Method for detecting three-dimensional target object, electronic device and storage medium |
| CN116543057A (en) * | 2023-06-27 | 2023-08-04 | 华南理工大学 | Underwater multi-camera and IMU integrated calibration method |
| EP4345751A1 (en) * | 2022-09-28 | 2024-04-03 | Guangzhou Xiaopeng Autopilot Technology Co., Ltd. | System and method for online camera calibration in vehicles based on vanishing point and pose graph |
-
2022
- 2022-01-11 CN CN202210026375.XA patent/CN114494456A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI798098B (en) * | 2022-05-31 | 2023-04-01 | 鴻海精密工業股份有限公司 | Method for detecting three-dimensional target object, electronic device and storage medium |
| EP4345751A1 (en) * | 2022-09-28 | 2024-04-03 | Guangzhou Xiaopeng Autopilot Technology Co., Ltd. | System and method for online camera calibration in vehicles based on vanishing point and pose graph |
| CN116543057A (en) * | 2023-06-27 | 2023-08-04 | 华南理工大学 | Underwater multi-camera and IMU integrated calibration method |
| CN116543057B (en) * | 2023-06-27 | 2023-10-10 | 华南理工大学 | Underwater multi-camera and IMU integrated calibration method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114494456A (en) | Multiphase external parameter calibration method, system, medium and terminal based on mobile calibration board | |
| CN108986161B (en) | Three-dimensional space coordinate estimation method, device, terminal and storage medium | |
| CN110111388B (en) | Three-dimensional object pose parameter estimation method and visual equipment | |
| CN109029444B (en) | Indoor navigation system and method based on image matching and space positioning | |
| US11816810B2 (en) | 3-D reconstruction using augmented reality frameworks | |
| US8259994B1 (en) | Using image and laser constraints to obtain consistent and improved pose estimates in vehicle pose databases | |
| US20160178728A1 (en) | Indoor Positioning Terminal, Network, System and Method | |
| US20170140540A1 (en) | Pose estimation apparatus and vacuum cleaner system | |
| WO2006083297A2 (en) | Method and apparatus for aligning video to three-dimensional point clouds | |
| KR101885961B1 (en) | Method of estimating the location of object image-based and apparatus therefor | |
| CN112083403B (en) | Positioning tracking error correction method and system for virtual scene | |
| CN112116655A (en) | Method and device for determining position information of image of target object | |
| CN112799096A (en) | Map construction method based on low-cost vehicle-mounted two-dimensional laser radar | |
| CN113361365A (en) | Positioning method and device, equipment and storage medium | |
| Wang et al. | Isprs benchmark on multisensory indoor mapping and positioning | |
| CN114812558A (en) | Monocular vision unmanned aerial vehicle autonomous positioning method combined with laser ranging | |
| CN115423863B (en) | Camera pose estimation method and device and computer readable storage medium | |
| US10580208B2 (en) | Ceiling map building method, ceiling map building device, and ceiling map building program | |
| CN111581322B (en) | Method, device and equipment for displaying region of interest in video in map window | |
| CN112868049B (en) | Efficient self-motion estimation using patch-based projection correlation | |
| CN114387532A (en) | Boundary identification method and device, terminal, electronic equipment and unmanned equipment | |
| WO2024083010A1 (en) | Visual localization method and related apparatus | |
| Shen et al. | A fast and robust scan-line search algorithm for object-to-image projection of airborne pushbroom images | |
| CN110580703B (en) | Distribution line detection method, device, equipment and storage medium | |
| CN110966988B (en) | Three-dimensional distance measurement method, device and equipment based on double-panoramic image automatic matching |
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 |