CN113674353B - Accurate pose measurement method for space non-cooperative target - Google Patents
Accurate pose measurement method for space non-cooperative target Download PDFInfo
- Publication number
- CN113674353B CN113674353B CN202110948038.1A CN202110948038A CN113674353B CN 113674353 B CN113674353 B CN 113674353B CN 202110948038 A CN202110948038 A CN 202110948038A CN 113674353 B CN113674353 B CN 113674353B
- Authority
- CN
- China
- Prior art keywords
- dimensional
- cooperative target
- straight line
- space non
- pose
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000691 measurement method Methods 0.000 title claims description 3
- 238000000034 method Methods 0.000 claims abstract description 18
- 239000011159 matrix material Substances 0.000 claims description 10
- 238000013519 translation Methods 0.000 claims description 10
- 230000009466 transformation Effects 0.000 claims description 4
- 238000003384 imaging method Methods 0.000 abstract description 4
- 238000005259 measurement Methods 0.000 description 7
- 238000001514 detection method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000011160 research 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
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/06—Topological mapping of higher dimensional structures onto lower dimensional surfaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a method for measuring the accurate pose of a space non-cooperative target, which comprises the steps of utilizing a TOF camera and a color camera to realize the accurate relative pose estimation of the space non-cooperative target: acquiring a three-dimensional point cloud of a space non-cooperative target by utilizing TOF, and splicing according to an ICP algorithm to obtain a complete three-dimensional point cloud of the space non-cooperative target; extracting three-dimensional characteristic points and three-dimensional straight lines from a complete three-dimensional point cloud of a space non-cooperative target; and acquiring a sequence two-dimensional image of the space non-cooperative target by using a color camera, extracting two-dimensional characteristic points and two-dimensional straight lines from the sequence two-dimensional image, and solving the relative pose of the space non-cooperative target according to the corresponding relation of the 2D-3D characteristic points and the straight lines. The method combines the imaging advantages of the TOF camera and the color camera, can accurately solve the pose of the space non-cooperative target, and can be applied to space tasks such as deep space exploration, situation awareness and the like.
Description
Technical Field
The invention relates to the field of image measurement, in particular to a method for measuring the accurate pose of a space non-cooperative target.
Background
With the progress of science and technology and the development of aerospace industry, deep space exploration and situation awareness become important links for human exploration on space roads. In space exploration, more and more task objects are spatially non-cooperative objects that lack cooperative signatures and do not provide valid a priori information. Therefore, under a complex space environment, the problem of accurate pose estimation of a completely unknown space target is widely focused by students, and has important research value and engineering practice significance.
Common spatial target pose measurement devices include color cameras, binocular cameras, lidar, and the like. The color camera cannot directly acquire the target depth information; the measurement precision of the binocular camera is limited by a base line; the laser three-dimensional imaging is limited by the technical level, and the resolution ratio is not high. Therefore, the method for fusion measurement of multiple sensors can effectively combine the imaging technical advantages of each sensor and make up for the inherent defects of a single sensor. The invention provides a space non-cooperative target accurate pose measurement scheme based on TOF and a color camera, which can fully utilize imaging advantages of the TOF and the color camera to realize accurate pose measurement of the space non-cooperative target.
Disclosure of Invention
Aiming at the problems, the invention provides a method for measuring the accurate pose of a space non-cooperative target.
The technical scheme adopted for solving the technical problems is as follows: a method for measuring the accurate pose of a space non-cooperative target comprises the following steps:
step 1, acquiring a complete three-dimensional point cloud of a space non-cooperative target by using a TOF camera;
step 2, extracting three-dimensional characteristic points and straight lines from the acquired complete three-dimensional point cloud of the space non-cooperative target;
step 3, acquiring image data of the moving space non-cooperative target by using a color camera to obtain a sequence two-dimensional image of the space non-cooperative target;
step 4, extracting two-dimensional characteristic points and two-dimensional straight lines of the space non-cooperative targets from the obtained sequence two-dimensional images;
and 5, projecting the three-dimensional characteristic points and the three-dimensional straight lines onto a two-dimensional plane, and solving pose parameters of the space non-cooperative targets according to the corresponding relation of the characteristic points and the straight lines.
Preferably, the step 5 specifically includes:
step 5.1, calibrating the color camera to obtain the equivalent focal length f of the color camera x ,f y ；
Step 5.2, assuming that the pose initial value of the spatial non-cooperative target is known, projecting a three-dimensional straight line onto a two-dimensional plane according to the pose initial value, matching with the extracted spatial non-cooperative target two-dimensional straight line, and enabling a three-dimensional straight line endpoint P and a projection point p= (P) x ,p y ) The relationship of (2) can be described by a pinhole camera model:
wherein the rotation matrix R and translation vector t describe a rigid transformation from the world coordinate system to the camera coordinate system, the three-dimensional linear equation can be expressed in polar coordinates as:
p x cosθ+p y sinθ-ρ d ＝0 (9)
step 5.3, calculating the distance from the three-dimensional straight line end point to the two-dimensional straight line, and combining equations (8) and (9) to obtain the following:
N＝(f x cosθ,f y sinθ,-ρ d ) T (11)
where N is the normal vector of the projection plane, and the distance d of the projection of the three-dimensional straight line end point to the corresponding plane and the two-dimensional straight line is expressed as:
step 5.4,2D-3D straight line represents the corresponding distance as
Wherein d is l1 ,d l2 Respectively representing two end points p projected from a three-dimensional straight line to a plane 1 ,p 2 Distance to a two-dimensional straight line;
step 5.5, projecting the three-dimensional feature points onto the two-dimensional plane according to the pose initial values, and setting the three-dimensional points and the two-dimensional feature points projected onto the plane to be respectively represented as Q, and q= [ Q x ,q y ]The projection relationship between the two can be expressed as:
step 5.6, projecting the three-dimensional feature points onto the two-dimensional plane, wherein the two-dimensional feature points q ' = [ q ' ] corresponding to the two-dimensional feature points on the image ' x ,q′ y ]Matching, and setting the distance between the projection point and the two-dimensional characteristic point as d q ：
Step 5.7, the feature points and the linear features of the space non-cooperative targets are projected onto a two-dimensional plane, and the i-th pair of 2D-3D corresponding point pair distances are set as
N pairs of corresponding points are shared, and the distance between the j-th pair and the 2D-3D corresponding straight line pair is set as +.>
And (3) sharing M pairs of 2D-3D corresponding straight line pairs, and solving the target pose by a minimization formula 16:
solving a formula (16) through a least square method to solve the pose of the space non-cooperative target: the rotation matrix R and the translation vector t.
Compared with the prior art, the invention has the following beneficial effects:
1. according to the invention, a TOF camera and a color camera are combined, a clear sequence two-dimensional image is obtained by using the color camera, the TOF camera directly obtains the advantage of target depth information, so that accurate pose estimation of a space non-cooperative target is realized, specifically, a TOF camera is used for obtaining a target point cloud, three-dimensional reconstruction of the target is realized, three-dimensional structure information of the space non-cooperative target can be obtained, a high-resolution sequence two-dimensional image in a target motion state is obtained by using the color camera, two-dimensional characteristic points and two-dimensional linear information are extracted from the two-dimensional sequence two-dimensional image, and the three-dimensional characteristic points and the three-dimensional linear information are combined to solve the motion pose of the space non-cooperative target;
2. aiming at the completely unknown space non-cooperative target, the method realizes accurate pose estimation of the space non-cooperative target, can be applied to space tasks such as deep space detection and situation awareness, and can provide effective information for space tasks such as subsequent capturing, attack and defense.
3. Compared with the paper Relative pose estimation of uncooperative spacecraft using 2D-3D line correspondences, the method not only utilizes the linear characteristics, but also utilizes the point characteristics of the space non-cooperative targets, and has the advantages that the point and line characteristics of the target structure and the edges are fully utilized, the linear characteristics of the space non-cooperative targets are difficult to stably extract under the conditions of shielding, background interference and the like, and pose solving can still be carried out by utilizing the corresponding key characteristic points when pose settlement is difficult. The invention optimizes the objective function, gives different weights to the key points and the straight lines, and ensures that pose measurement is more accurate.
Drawings
Fig. 1 is a flow chart of the method of the present invention.
Detailed Description
The present invention will be described in detail below with reference to fig. 1, wherein the exemplary embodiments of the present invention and the description are for explaining the present invention, but are not limiting.
A method for measuring the accurate pose of a space non-cooperative target comprises the following steps:
step 1, acquiring a complete three-dimensional point cloud of a space non-cooperative target by utilizing a TOF camera, and specifically comprising the following steps:
step 1.1, calibrating the TOF camera by adopting a Zhang Zhengyou calibration method (A flexible new technique for camera calibration, published in IEEE Transactions on Pattern Analysis and Machine Intelligence in 2000), wherein calibration can be performed by utilizing a checkerboard calibration plate to obtain an internal parameter K of the TOF camera;
step 1.2, shooting around each angle of a space non-cooperative target by using a TOF camera to obtain a sequence depth map;
step 1.3, mapping the depth map to a space according to internal parameters of a camera to obtain a local point cloud of a space non-cooperative target;
step 1.4, denoising the space non-cooperative target point cloud, and removing noise points to obtain a fine local point cloud of the space non-cooperative target;
step 1.5, providing an initial value for local point cloud registration by using a Fast Point Feature Histogram (FPFH) algorithm;
step 1.6, after the initial value is obtained, matching point clouds of two adjacent frames of the space non-cooperative target by utilizing an ICP algorithm, and assuming that adjacent point sets to be matched are respectively expressed as A and B:
A＝{a 1 ,...,a i ,...,a n },B＝{b 1 ,...,b j ,...,b m }
wherein a is i ,b j Respectively representing three-dimensional points in the point sets A and B, n and m respectively representing the quantity of the point sets A and B, and the ICP algorithm realizes the matching of point clouds by minimizing the distance between the two point sets and using a rotation matrix R t And translation vector T t The rigid transformation from point set a to point set B is described as follows:
step 1.6.1, searching the corresponding relation of three-dimensional points in the adjacent point sets A and B, and marking the corresponding point pair as a by using two three-dimensional points with nearest Euclidean distance as corresponding points by the ICP method i ，b i ，
Step 1.6.2, solving the rotation matrix R by minimizing the distance of the corresponding point pairs in the point set t And translation vector T t ：
Step 1.6.3, calculating centroid coordinates of the point sets a and B:
step 1.6.4, calculating the barycenter coordinates of each point in the point sets a and B:
a i ′＝a i -μ a ，b i ′＝b i -μ b (3)
step 1.6.5, solving the rotation matrix R by SVD method t ：
W＝UΣV T (5)
R t ＝UV T (6)
Step 1.6.6 solving for translation vector T t ：
T t ＝μ b -R t μ a (7)
Repeating the steps 1.6.1-1.6.6 until the distance meets the threshold requirement to obtain the optimal rotation matrix R t And translation vector T t Splicing the two frames of point clouds;
step 1.7, repeating the step 1.6, and splicing all the point clouds to obtain a complete three-dimensional point cloud of the space non-cooperative target;
step 2, extracting three-dimensional characteristic points and three-dimensional straight lines from the acquired complete three-dimensional point cloud of the space non-cooperative target;
step 3, acquiring image data of the moving space non-cooperative target by using a color camera to obtain a sequence two-dimensional image of the space non-cooperative target;
step 4, extracting two-dimensional characteristic points and two-dimensional straight lines of the space non-cooperative targets from the obtained sequence two-dimensional images by using an EDlines two-dimensional straight line detection algorithm and a SIFT characteristic point extraction algorithm;
and 5, matching the solved two-dimensional characteristic points and the solved two-dimensional straight lines with the three-dimensional characteristic points and the three-dimensional straight lines, and correspondingly solving pose parameters of the space non-cooperative target by utilizing the 2D-3D straight lines, wherein the specific steps are as follows:
step 5.1, calibrating the color camera by adopting a Zhang Zhengyou calibration method to obtain the equivalent focal length f of the color camera x ,f y ；
Step 5.2, assuming that the pose initial value of the spatial non-cooperative target is known, projecting a three-dimensional straight line onto a two-dimensional plane according to the pose initial value, matching with the extracted spatial non-cooperative target two-dimensional straight line, and enabling a three-dimensional straight line endpoint P and a projection point p= (P) x ,p y ) The relationship of (2) can be described by a pinhole camera model:
wherein the rotation matrix R and translation vector t describe a rigid transformation from the world coordinate system to the camera coordinate system, the three-dimensional linear equation can be expressed in polar coordinates as:
p x cosθ+p y sinθ-ρ d ＝0 (9)
step 5.3, calculating the distance from the three-dimensional straight line end point to the two-dimensional straight line, and combining equations (8) and (9) to obtain the following:
N＝(f x cosθ,f y sinθ,-ρ d ) T (11)
where N is the normal vector of the projection plane, and the distance d of the projection of the three-dimensional straight line end point to the corresponding plane and the two-dimensional straight line is expressed as:
step 5.4,2D-3D straight line represents the corresponding distance as
Wherein d is l1 ,d l2 Respectively representing two end points p projected from a three-dimensional straight line to a plane 1 ,p 2 Distance to a two-dimensional straight line;
step 5.5, projecting the three-dimensional feature points onto the two-dimensional plane according to the pose initial values, and setting the three-dimensional feature points and the two-dimensional feature points projected onto the plane to be respectively represented as Q, and q= [ Q x ,q y ]The projection relationship between the two can be expressed as:
step 5.6, projecting the three-dimensional feature points onto the two-dimensional plane, wherein the two-dimensional feature points q ' = [ q ' ] corresponding to the two-dimensional feature points on the image ' x ,q′ y ]Matching, and setting the distance between the projection point and the two-dimensional characteristic point as d q :
Step 5.7, the feature points and the linear features of the space non-cooperative targets are projected onto a two-dimensional plane, and the i-th pair of 2D-3D corresponding point pair distances are set as
N pairs of corresponding points are shared, and the distance between the j-th pair and the 2D-3D corresponding straight line pair is set as +.>
And (3) sharing M pairs of 2D-3D corresponding straight line pairs, and solving the target pose by a minimization formula 16:
solving a formula (16) through a least square method to solve the pose of the space non-cooperative target: the rotation matrix R and the translation vector t.
The foregoing has described in detail the technical solutions provided by the embodiments of the present invention, and specific examples have been applied to illustrate the principles and implementations of the embodiments of the present invention, where the above description of the embodiments is only suitable for helping to understand the principles of the embodiments of the present invention; meanwhile, as for those skilled in the art, according to the embodiments of the present invention, there are variations in the specific embodiments and the application scope, and the present description should not be construed as limiting the present invention.
Claims (1)
1. The accurate pose measurement method for the space non-cooperative target is characterized by comprising the following steps of:
step 1, acquiring a complete three-dimensional point cloud of a space non-cooperative target by using a TOF camera;
step 2, extracting three-dimensional characteristic points and three-dimensional straight lines from the acquired complete three-dimensional point cloud of the space non-cooperative target;
step 3, acquiring image data of the moving space non-cooperative target by using a color camera to obtain a sequence two-dimensional image of the space non-cooperative target;
step 4, extracting two-dimensional characteristic points and two-dimensional straight lines of the space non-cooperative targets from the obtained sequence two-dimensional images;
step 5, matching is carried out according to the solved 2D-3D characteristic points and the straight lines respectively, and pose parameters of the space non-cooperative targets are solved by utilizing the corresponding relation:
step 5.1, calibrating the color camera to obtain the equivalent focal length f of the color camera x ,f y ；
Step 5.2, assuming that the pose initial value of the spatial non-cooperative target is known, projecting a three-dimensional straight line onto a two-dimensional plane according to the pose initial value, matching with the extracted spatial non-cooperative target two-dimensional straight line, and enabling a three-dimensional straight line endpoint P and a projection point p= (P) x ,p y ) The relationship of (2) can be described as:
wherein the pose of the object, i.e. the rigid transformation from the world coordinate system to the camera coordinate system, is described by a rotation matrix R and a translation vector t, the three-dimensional linear equation can be expressed in polar coordinates as:
p x cosθ+p y sinθ-ρ d ＝0 (2)
step 5.3, calculating the distance from the three-dimensional straight line end point to the two-dimensional straight line, and combining equations (1) and (2) to obtain the following:
N＝(f x cosθ,f y sinθ,-ρ d ) T (4)
where N is the normal vector of the projection plane, and the distance d of the projection of the three-dimensional straight line end point to the corresponding plane and the two-dimensional straight line is expressed as:
step 5.4,2D-3D straight line represents the corresponding distance as
Wherein d l1 ,d l2 Respectively representing two end points p projected from a three-dimensional straight line to a plane 1 ,p 2 Distance to a two-dimensional straight line;
step 5.5, projecting the three-dimensional feature points onto the two-dimensional plane according to the pose initial values, and setting the three-dimensional feature points and the two-dimensional feature points projected onto the plane to be respectively represented as Q, and q= [ Q x ,q y ]The projection relationship between the two can be expressed as:
step 5.6, projecting the three-dimensional feature points onto the two-dimensional plane, wherein the two-dimensional feature points q ' = [ q ' ] corresponding to the two-dimensional feature points on the image ' x ,q′ y ]Matching, and setting the distance between the projection point and the two-dimensional characteristic point as d q ：
Step 5.7, the feature points and the linear features of the space non-cooperative targets are projected onto a two-dimensional plane, and the i-th pair of 2D-3D corresponding point pair distances are set as
N pairs of corresponding points are shared, and the distance between the j-th pair and the 2D-3D corresponding straight line pair is set as +.>
And (3) sharing M pairs of 2D-3D corresponding straight line pairs, and solving the target pose by a minimization formula (9):
solving a formula (9) through a least square method to solve the pose of the space non-cooperative target: the rotation matrix R and the translation vector t.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110948038.1A CN113674353B (en) | 2021-08-18 | 2021-08-18 | Accurate pose measurement method for space non-cooperative target |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110948038.1A CN113674353B (en) | 2021-08-18 | 2021-08-18 | Accurate pose measurement method for space non-cooperative target |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113674353A CN113674353A (en) | 2021-11-19 |
| CN113674353B true CN113674353B (en) | 2023-05-16 |
Family
ID=78543640
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110948038.1A Active CN113674353B (en) | 2021-08-18 | 2021-08-18 | Accurate pose measurement method for space non-cooperative target |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113674353B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115661493B (en) * | 2022-12-28 | 2023-07-04 | 航天云机(北京)科技有限公司 | Method, device, equipment and storage medium for determining object pose |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109242873A (en) * | 2018-08-22 | 2019-01-18 | 浙江大学 | A method of 360 degree of real-time three-dimensionals are carried out to object based on consumer level color depth camera and are rebuild |
| CN111243002A (en) * | 2020-01-15 | 2020-06-05 | 中国人民解放军国防科技大学 | Monocular laser speckle projection system calibration and depth estimation method applied to high-precision three-dimensional measurement |
| CN112179357A (en) * | 2020-09-25 | 2021-01-05 | 中国人民解放军国防科技大学 | Monocular camera-based visual navigation method and system for plane moving target |
| CN112284293A (en) * | 2020-12-24 | 2021-01-29 | 中国人民解放军国防科技大学 | Method for measuring space non-cooperative target fine three-dimensional morphology |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011175477A (en) * | 2010-02-24 | 2011-09-08 | Canon Inc | Three-dimensional measurement apparatus, processing method and program |
-
2021
- 2021-08-18 CN CN202110948038.1A patent/CN113674353B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109242873A (en) * | 2018-08-22 | 2019-01-18 | 浙江大学 | A method of 360 degree of real-time three-dimensionals are carried out to object based on consumer level color depth camera and are rebuild |
| CN111243002A (en) * | 2020-01-15 | 2020-06-05 | 中国人民解放军国防科技大学 | Monocular laser speckle projection system calibration and depth estimation method applied to high-precision three-dimensional measurement |
| CN112179357A (en) * | 2020-09-25 | 2021-01-05 | 中国人民解放军国防科技大学 | Monocular camera-based visual navigation method and system for plane moving target |
| CN112284293A (en) * | 2020-12-24 | 2021-01-29 | 中国人民解放军国防科技大学 | Method for measuring space non-cooperative target fine three-dimensional morphology |
Non-Patent Citations (4)
| Title |
|---|
| 单目相机位姿估计的稳健正交迭代方法;张雄锋，刘海波，尚洋;光学学报;第39卷(第9期);262-267 * |
| 基于多级直线表述和M-估计的三维目标位姿跟踪优化算法;张跃强,苏昂 刘海波,尚洋,于起峰;光学学报;第35卷(第1期);256-265 * |
| 基于广义成像模型的Scheimpflug相机标定方法;孙聪，刘海波，陈圣义，尚洋;光学学报;第38卷(第8期);114-122 * |
| 多星近距离绕飞观测任务姿轨耦合控制研究;徐影，张进，于沫尧，许丹丹;中国空间科学技术;第39卷(第6期);21-29 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113674353A (en) | 2021-11-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109146980B (en) | Monocular vision based optimized depth extraction and passive distance measurement method | |
| CN109035320B (en) | Monocular vision-based depth extraction method | |
| RU2609434C2 (en) | Detection of objects arrangement and location | |
| Alismail et al. | Automatic calibration of a range sensor and camera system | |
| CN109919911B (en) | Mobile three-dimensional reconstruction method based on multi-view photometric stereo | |
| CN107729893B (en) | Visual positioning method and system of die spotting machine and storage medium | |
| CN109559355B (en) | Multi-camera global calibration device and method without public view field based on camera set | |
| CN107560592B (en) | Precise distance measurement method for photoelectric tracker linkage target | |
| CN107084680B (en) | Target depth measuring method based on machine monocular vision | |
| CN108362205B (en) | Space distance measuring method based on fringe projection | |
| CN108171715B (en) | Image segmentation method and device | |
| CN104880176A (en) | Moving object posture measurement method based on prior knowledge model optimization | |
| CN103971378A (en) | Three-dimensional reconstruction method of panoramic image in mixed vision system | |
| CN109255818B (en) | Novel target and extraction method of sub-pixel level angular points thereof | |
| CN113050074B (en) | Camera and laser radar calibration system and calibration method in unmanned environment perception | |
| Nagy et al. | Online targetless end-to-end camera-LiDAR self-calibration | |
| CN112365545B (en) | Calibration method of laser radar and visible light camera based on large-plane composite target | |
| CN111524174A (en) | Binocular vision three-dimensional construction method for moving target of moving platform | |
| CN113674353B (en) | Accurate pose measurement method for space non-cooperative target | |
| CN104504691A (en) | Camera position and posture measuring method on basis of low-rank textures | |
| WO2020133080A1 (en) | Object positioning method and apparatus, computer device, and storage medium | |
| Han et al. | Target positioning method in binocular vision manipulator control based on improved canny operator | |
| Miled et al. | Hybrid online mobile laser scanner calibration through image alignment by mutual information | |
| Xiao et al. | A new three-dimensional laser scanner design and its performance analysis | |
| CN112017259A (en) | Indoor positioning and image building method based on depth camera and thermal imager |
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 |