CN111951314A - Point cloud registration method and device, computer readable storage medium and electronic equipment - Google Patents

Point cloud registration method and device, computer readable storage medium and electronic equipment Download PDF

Info

Publication number
CN111951314A
CN111951314A CN202010848942.0A CN202010848942A CN111951314A CN 111951314 A CN111951314 A CN 111951314A CN 202010848942 A CN202010848942 A CN 202010848942A CN 111951314 A CN111951314 A CN 111951314A
Authority
CN
China
Prior art keywords
pose
increment
point
determining
point cloud
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
Application number
CN202010848942.0A
Other languages
Chinese (zh)
Other versions
CN111951314B (en
Inventor
赵靖
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Seashell Housing Beijing Technology Co Ltd
Original Assignee
Beike Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beike Technology Co Ltd filed Critical Beike Technology Co Ltd
Priority to CN202010848942.0A priority Critical patent/CN111951314B/en
Publication of CN111951314A publication Critical patent/CN111951314A/en
Application granted granted Critical
Publication of CN111951314B publication Critical patent/CN111951314B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
    • G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
    • 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
    • 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)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)

Abstract

The embodiment of the disclosure discloses a point cloud registration method and device, a computer readable storage medium and an electronic device, wherein the method comprises the following steps: determining an initial pose increment based on corresponding point pairs in two point clouds to be registered; the corresponding point pair set comprises a plurality of pairs of corresponding point pairs; decomposing the initial pose increment into at least one dimension of a pose to obtain pose increment component values respectively corresponding to the at least one dimension; determining an object pose increment based on the at least one pose increment component value; judging whether the target pose increment meets a set convergence condition, and registering the two point clouds to be registered by the target pose increment in response to the set convergence condition being met; the pose of the obtained object pose incremental component is adjusted only in a stable direction through the pose incremental component value, so that the pose adjustment error is reduced, the point cloud registration method provided by the embodiment has robustness, and the point cloud registration method can be suitable for point cloud registration of more scenes.

Description

Point cloud registration method and device, computer readable storage medium and electronic equipment
Technical Field
The disclosure relates to the technical field of point cloud registration, and in particular to a point cloud registration method and device, a computer-readable storage medium and an electronic device.
Background
Point cloud registration is a process of estimating the relative pose (i.e., translation and rotation between the two) of two or more point clouds, and is commonly used in computer vision and graphics related fields, such as three-dimensional object matching, object localization and three-dimensional reconstruction, and the like.
A Point cloud registration method commonly used in the prior art is an Iterative Closest Point (ICP) algorithm. The algorithm depends on the initial pose among a group of point clouds, then homonymous points (coreespondence) among the point clouds are selected through the initial pose (namely p points on the point cloud A and q points on the point cloud B are the same point in a three-dimensional space), and the distance between the homonymous points is reduced through optimizing the relative pose among the point clouds. And then according to the optimized pose, reselecting the homonymy point, re-optimizing, and repeating (iterating) the process until convergence (which can be understood that the change of the pose after each iteration approaches to zero).
Disclosure of Invention
The present disclosure is proposed to solve the above technical problems. The embodiment of the disclosure provides a point cloud registration method and device, a computer-readable storage medium and an electronic device.
According to an aspect of an embodiment of the present disclosure, there is provided a point cloud registration method, including:
determining an initial pose increment based on corresponding point pairs in two point clouds to be registered; the corresponding point pair set comprises a plurality of pairs of corresponding point pairs;
decomposing the initial pose increment into at least one dimension of a pose to obtain pose increment component values respectively corresponding to the at least one dimension;
determining an object pose increment based on the at least one pose increment component value;
and determining whether the target pose increment meets a set convergence condition, and registering the two point clouds to be registered by the target pose increment in response to meeting the set convergence condition.
Optionally, at least one dimension of the pose comprises six degrees of freedom;
decomposing the initial pose increment into at least one dimension of the pose to obtain pose increment component values respectively corresponding to the at least one dimension, comprising:
determining a coefficient matrix based on an optimization problem of the corresponding point pair set;
decomposing the initial pose increment to six degrees of freedom of a pose based on the coefficient matrix to obtain a pose increment component value corresponding to at least one degree of freedom in the six degrees of freedom.
Optionally, decomposing the initial pose increment to six degrees of freedom of a pose based on the coefficient matrix to obtain a pose increment component value corresponding to at least one degree of freedom of the six degrees of freedom includes:
solving six eigenvectors of the coefficient matrix and an eigenvalue corresponding to each eigenvector; wherein each of the eigenvectors and the eigenvalues corresponds to one degree of freedom;
determining the at least one pose delta component value based on the feature values and the feature vectors.
Optionally, said determining said at least one pose delta component value based on said feature value and said feature vector comprises:
determining a stable value corresponding to each characteristic value based on the maximum value of the six characteristic values;
judging whether the stable value corresponding to each characteristic value is smaller than a set threshold value or not, and setting a pose increment component value corresponding to the degree of freedom corresponding to the characteristic value smaller than the set threshold value to zero; and determining pose increment component values corresponding to the characteristic values not less than the set threshold value based on the characteristic vectors.
Optionally, the determining, based on the feature vector, a pose incremental component value corresponding to the feature value not less than the set threshold includes:
and performing point multiplication on the eigenvector corresponding to the eigenvalue not less than the set threshold and the initial pose increment to obtain a product which is used as a pose increment component value corresponding to the eigenvalue.
Optionally, said determining an object pose increment based on said at least one pose increment component value comprises:
determining a feature vector corresponding to at least one feature value corresponding to the at least one pose incremental component value;
determining the object pose delta based on the at least one pose delta component value and the at least one feature vector.
Optionally, the two point clouds to be registered comprise a first point cloud and a second point cloud;
determining an initial pose increment based on corresponding point pairs sets included in two point clouds to be registered, including:
determining all corresponding point pairs according to the pose information corresponding to the first point cloud and the pose information corresponding to the second point cloud; wherein each pair of said corresponding points comprises a point in one said first point cloud and a point in one second point cloud;
determining the initial pose increment according to the optimization problem of the corresponding point pair set and the coordinates of each point in the corresponding point pair; wherein the optimization problem aims to make the distance sum after operating on the second point cloud approach to zero; the distance sum is determined based on distances between all corresponding point pairs in the set of corresponding point pairs.
Optionally, the method further comprises:
in response to the set convergence condition not being satisfied, determining updated pose information of the point cloud to be registered based on the target pose increment and the pose information of the point cloud to be registered;
taking the point cloud with the updated pose information and the other point cloud to be registered as two point clouds to be registered;
determining an initial pose increment based on corresponding point pairs in two point clouds to be registered;
decomposing the initial pose increment into at least one dimension of a pose to obtain pose increment component values respectively corresponding to the at least one dimension;
determining an object pose increment based on the at least one pose increment component value;
and determining whether the target pose increment meets a set convergence condition or not until the target pose increment meets the set convergence condition, and registering the two point clouds to be registered by the target pose increment.
According to another aspect of the embodiments of the present disclosure, there is provided a point cloud registration apparatus including:
the initial increment determining module is used for determining an initial pose increment based on corresponding point pairs in the two to-be-registered point clouds; the corresponding point pair set comprises a plurality of pairs of corresponding point pairs;
the increment decomposition module is used for decomposing the initial pose increment into at least one dimension of a pose to obtain pose increment component values respectively corresponding to the at least one dimension;
an object increment determination module to determine an object pose increment based on the at least one pose increment component value;
and the registration module is used for determining whether the target pose increment meets a set convergence condition or not, and registering the two point clouds to be registered by the target pose increment in response to meeting the set convergence condition.
Optionally, at least one dimension of the pose comprises six degrees of freedom;
the incremental decomposition module comprises:
a matrix determination unit, configured to determine a coefficient matrix based on the optimization problem of the corresponding point pair set;
and the component determining unit is used for decomposing the initial pose increment to six degrees of freedom of a pose based on the coefficient matrix to obtain a pose increment component value corresponding to at least one degree of freedom in the six degrees of freedom.
Optionally, the component determining unit is specifically configured to solve six eigenvectors of the coefficient matrix and an eigenvalue corresponding to each eigenvector; wherein each of the eigenvectors and the eigenvalues corresponds to one degree of freedom; determining the at least one pose delta component value based on the feature values and the feature vectors.
Optionally, when determining the at least one pose incremental component value based on the feature value and the feature vector, the component determining unit is configured to determine a stable value corresponding to each feature value based on a maximum value of the six feature values; judging whether the stable value corresponding to each characteristic value is smaller than a set threshold value or not, and setting a pose increment component value corresponding to the degree of freedom corresponding to the characteristic value smaller than the set threshold value to zero; and determining pose increment component values corresponding to the characteristic values not less than the set threshold value based on the characteristic vectors.
Optionally, when determining the pose increment component value corresponding to the feature value not less than the set threshold based on the feature vector, the component determining unit is configured to perform a point multiplication on the feature vector corresponding to the feature value not less than the set threshold and the initial pose increment, and use the resultant product as the pose increment component value corresponding to the feature value.
Optionally, the object increment determining module is specifically configured to determine a feature vector corresponding to at least one feature value corresponding to the at least one pose increment component value; determining the object pose delta based on the at least one pose delta component value and the at least one feature vector.
Optionally, the two point clouds to be registered comprise a first point cloud and a second point cloud;
the initial increment determining module is specifically configured to determine all corresponding point pairs according to the pose information corresponding to the first point cloud and the pose information corresponding to the second point cloud; wherein each pair of said corresponding points comprises a point in one said first point cloud and a point in one second point cloud; determining the initial pose increment according to the optimization problem of the corresponding point pair set and the coordinates of each point in the corresponding point pair; wherein the optimization problem aims to make the distance sum after operating on the second point cloud approach to zero; the distance sum is determined based on distances between all corresponding point pairs in the set of corresponding point pairs.
Optionally, the apparatus further comprises:
an adjustment iteration module, configured to determine, in response to the set convergence condition not being satisfied, updated pose information of the point cloud to be registered based on the target pose increment and the pose information of the point cloud to be registered; and taking the point cloud with the updated pose information and the other point cloud to be registered as two point clouds to be registered.
According to yet another aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium storing a computer program for executing the point cloud registration method according to any of the above embodiments.
According to still another aspect of the embodiments of the present disclosure, there is provided an electronic apparatus including:
a processor;
a memory for storing the processor-executable instructions;
the processor is configured to read the executable instructions from the memory and execute the instructions to implement the point cloud registration method according to any of the above embodiments.
Based on the point cloud registration method and device, the computer-readable storage medium and the electronic device provided by the above embodiments of the present disclosure, an initial pose increment is determined based on corresponding point pairs sets included in two point clouds to be registered; the corresponding point pair set comprises a plurality of pairs of corresponding point pairs; decomposing the initial pose increment into at least one dimension of a pose to obtain pose increment component values respectively corresponding to the at least one dimension; determining an object pose increment based on the at least one pose increment component value; judging whether the target pose increment meets a set convergence condition, and registering the two point clouds to be registered by the target pose increment in response to the set convergence condition being met; the pose of the obtained object pose incremental component is adjusted only in a stable direction through the pose incremental component value, so that the pose adjustment error is reduced, the point cloud registration method provided by the embodiment has robustness, and the point cloud registration method can be suitable for point cloud registration of more scenes.
The technical solution of the present disclosure is further described in detail by the accompanying drawings and examples.
Drawings
The above and other objects, features and advantages of the present disclosure will become more apparent by describing in more detail embodiments of the present disclosure with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of the embodiments of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the principles of the disclosure and not to limit the disclosure. In the drawings, like reference numbers generally represent like parts or steps.
Fig. 1 is a schematic flow chart of a point cloud registration method according to an exemplary embodiment of the present disclosure.
Fig. 2 is a schematic flow chart of step 104 in the embodiment shown in fig. 1 of the present disclosure.
Fig. 3 is a schematic flowchart of step 1042 in the embodiment shown in fig. 2.
Fig. 4 is a schematic flow chart of step 302 in the embodiment shown in fig. 3 of the present disclosure.
Fig. 5 is a schematic flow chart of step 106 in the embodiment shown in fig. 1 of the present disclosure.
FIG. 6 is a schematic flow chart of step 102 in the embodiment shown in FIG. 1 of the present disclosure.
Fig. 7 is a schematic flow chart of a point cloud registration method according to another exemplary embodiment of the present disclosure.
Fig. 8 is a schematic structural diagram of a point cloud registration apparatus provided in an exemplary embodiment of the present disclosure.
Fig. 9 is a block diagram of an electronic device provided in an exemplary embodiment of the present disclosure.
Detailed Description
Hereinafter, example embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. It is to be understood that the described embodiments are merely a subset of the embodiments of the present disclosure and not all embodiments of the present disclosure, with the understanding that the present disclosure is not limited to the example embodiments described herein.
It should be noted that: the relative arrangement of the components and steps, the numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.
It will be understood by those of skill in the art that the terms "first," "second," and the like in the embodiments of the present disclosure are used merely to distinguish one element from another, and are not intended to imply any particular technical meaning, nor is the necessary logical order between them.
It is also understood that in embodiments of the present disclosure, "a plurality" may refer to two or more and "at least one" may refer to one, two or more.
It is also to be understood that any reference to any component, data, or structure in the embodiments of the disclosure, may be generally understood as one or more, unless explicitly defined otherwise or stated otherwise.
In addition, the term "and/or" in the present disclosure is only one kind of association relationship describing an associated object, and means that three kinds of relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" in the present disclosure generally indicates that the former and latter associated objects are in an "or" relationship.
It should also be understood that the description of the various embodiments of the present disclosure emphasizes the differences between the various embodiments, and the same or similar parts may be referred to each other, so that the descriptions thereof are omitted for brevity.
Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
The disclosed embodiments may be applied to electronic devices such as terminal devices, computer systems, servers, etc., which are operational with numerous other general purpose or special purpose computing system environments or configurations. Examples of well known terminal devices, computing systems, environments, and/or configurations that may be suitable for use with electronic devices, such as terminal devices, computer systems, servers, and the like, include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, hand-held or laptop devices, microprocessor-based systems, set top boxes, programmable consumer electronics, network pcs, minicomputer systems, mainframe computer systems, distributed cloud computing environments that include any of the above systems, and the like.
Electronic devices such as terminal devices, computer systems, servers, etc. may be described in the general context of computer system-executable instructions, such as program modules, being executed by a computer system. Generally, program modules may include routines, programs, objects, components, logic, data structures, etc. that perform particular tasks or implement particular abstract data types. The computer system/server may be practiced in distributed cloud computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules may be located in both local and remote computer system storage media including memory storage devices.
Summary of the application
In the process of implementing the present disclosure, the inventors found that, in the prior art, usually, the closest point iterative algorithm implements point cloud registration, and this technical solution has at least the following problems: in measuring the distance between the same-name points, a point-to-plane error metric (point-to-plane error metric) is often used. The ICP algorithm often causes the final result to be very erroneous and unstable when the two point clouds are not sufficient in themselves to define the relative pose between them (e.g. two points in a long corridor are scanned: the two point clouds can slide in the direction along the corridor because no limit is placed on that direction because no two ends of the corridor can be captured).
Exemplary method
Fig. 1 is a schematic flow chart of a point cloud registration method according to an exemplary embodiment of the present disclosure. The embodiment can be applied to an electronic device, as shown in fig. 1, and includes the following steps:
and 102, determining an initial pose increment based on corresponding point pairs in the two point clouds to be registered.
Wherein the corresponding point pair set comprises a plurality of pairs of corresponding point pairs.
Optionally, the method for acquiring a corresponding point pair in this embodiment may be implemented by using a closest point iterative algorithm in the prior art, where the corresponding point pair may be a closest point pair, that is, two corresponding closest points in two point clouds; the initial pose increment obtained based on the corresponding point pair set can also be realized by adopting a closest point iterative algorithm, and the embodiment does not limit the specific mode of determining the corresponding point pair set and the initial pose increment.
And 104, decomposing the initial pose increment into at least one dimension of the pose to obtain pose increment component values respectively corresponding to the at least one dimension.
Optionally, the pose usually includes 6 degrees of freedom, and by decomposing the initial pose increment into at least one dimension (e.g., degree of freedom), it is possible to obtain the pose increment in the dimension where the change is relatively stable, and the direction in which a small disturbance is added to generate a larger error is minimized (e.g., the pose increment in the direction is made zero), so as to reduce the error generated by the pose increment and improve the robustness of the point cloud registration method.
And 106, determining the pose increment of the object based on the at least one pose increment component value.
In this embodiment, the pose increment determined by the pose increment component values in at least one more stable direction better meets the requirement of point cloud registration, and a large error of the pose increment due to noise in a certain direction is avoided.
And 108, determining whether the target pose increment meets a set convergence condition, and registering the two point clouds to be registered by the target pose increment in response to meeting the set convergence condition.
Optionally, setting the convergence condition may include, but is not limited to, that a variation between two consecutive determined target pose increments is smaller than a first set value (a value may be set according to an actual situation), the target pose increment is smaller than a second set value (a value may be set according to an actual situation), and the like; and obtaining a target pose increment with a better registration effect through finite iterations by using a convergence condition, and registering the two point clouds by using the target pose increment.
According to the point cloud registration method provided by the embodiment of the disclosure, based on corresponding point pairs sets included in two point clouds to be registered, initial pose increment is determined; the corresponding point pair set comprises a plurality of pairs of corresponding point pairs; decomposing the initial pose increment into at least one dimension of a pose to obtain pose increment component values respectively corresponding to the at least one dimension; determining an object pose increment based on the at least one pose increment component value; judging whether the target pose increment meets a set convergence condition, and registering the two point clouds to be registered by the target pose increment in response to the set convergence condition being met; the pose of the obtained object pose incremental component is adjusted only in a stable direction through the pose incremental component value, so that the pose adjustment error is reduced, the point cloud registration method provided by the embodiment has robustness, and the point cloud registration method can be suitable for point cloud registration of more scenes.
As shown in fig. 2, based on the embodiment shown in fig. 1, step 104 may include the following steps:
step 1041, determining a coefficient matrix based on the optimization problem of the corresponding point pair set.
And 1042, decomposing the initial pose increment to six degrees of freedom of the pose based on the coefficient matrix to obtain a pose increment component value corresponding to at least one degree of freedom in the six degrees of freedom.
Optionally, at least one dimension of the pose may include six degrees of freedom, including 3 translational directions and 3 rotational directions; in this embodiment, the optimization problem corresponding to the corresponding point pair set is solved to obtain the attitude increment, and the optimization problem corresponding to the corresponding point pair set is converted to determine a coefficient matrix; the optimization problem is to make the distance between each pair of corresponding point pairs in the corresponding point pair set as small as possible, the sum of the distances between all corresponding point pairs (for example, the sum of the distances is the sum of the squares of the distances between all the point pairs or the sum of the absolute values of the distances between all the point pairs) is used as an index for measuring the optimization effect, when the sum of the distances is minimized, the position increment value can be used as an initial position increment value, the optimization problem can be simplified and expressed as Ax ═ B, wherein x represents the initial position increment value, a is a corresponding coefficient matrix, and when the coordinates of the corresponding point pairs and the position information of two point clouds are known, the coefficient matrix can be obtained.
As shown in fig. 3, based on the embodiment shown in fig. 2, step 1042 may include the following steps:
step 301, solving six eigenvectors of the coefficient matrix and an eigenvalue corresponding to each eigenvector.
Wherein each eigenvector and eigenvalue corresponds to one degree of freedom.
Step 302, determining at least one pose increment component value based on the feature value and the feature vector.
In this embodiment, the coefficient matrix may be a 6 by 6 matrix, and 6 eigenvectors v may be obtained by performing eigen decomposition on the coefficient matrixiEigenvalue λ corresponding to 6 eigenvectorsiWherein i is an integer from 1 to 6 (i.e., 1,2,3,4,5, 6); and determining at least one pose incremental component value by combining the eigenvalue and the eigenvector, wherein which directions have the pose incremental component values can be determined based on the eigenvalues, and the size of the specific pose incremental component value in the direction having the pose incremental component value is determined based on the eigenvector. Optionally, at least one pose delta component value may be determined with reference to the embodiment shown in FIG. 4.
As shown in fig. 4, based on the embodiment shown in fig. 3, step 302 may include the following steps:
step 3021, determining a stable value corresponding to each feature value based on the maximum value of the six feature values.
Step 3022, determining whether the stable value corresponding to each feature value is smaller than a set threshold, and setting a pose incremental component value corresponding to the degree of freedom corresponding to the feature value smaller than the set threshold to zero; and determining a pose increment component value corresponding to the characteristic value not less than the set threshold value based on the characteristic vector.
Optionally, a new probability is introduced in this embodiment: and the stable value is used for indicating whether the pose is stable in the direction, and when the stable value in a certain direction of the pose is smaller, the stable value indicates that even smaller disturbance is added in the direction, larger errors can be generated, and the registration between the point clouds can be influenced. Optionally, the stable value in this embodiment may be based on an eigenvalue λ obtained by coefficient matrix decompositioniDetermining that the maximum value of the 6 characteristic values is represented as lambdamaxAt this time, the ratio of each eigenvalue to the maximum eigenvalue is taken as a stable value, that is,
Figure BDA0002644073090000111
in this embodiment, when the stable value corresponding to a certain direction is smaller than the set threshold (for example, the set threshold is 0.1, etc., and a specific value can be set according to an actual situation), the pose increment component value in the direction (degree of freedom) is set to zero, so that it is directly ensured that no disturbance occurs in the direction, and the error of pose change is reduced; the pose incremental component values are calculated and determined only in the direction in which the stable value is greater than or equal to the set threshold value, so that the pose of the object determined based on at least one pose incremental component value obtained in the embodiment is adjusted only in the relatively stable direction, and the method is more robust.
Optionally, the step 3022 of determining, based on the feature vector, a pose incremental component value corresponding to the feature value not less than the set threshold value may include:
and performing point multiplication on the eigenvector corresponding to the eigenvalue not less than the set threshold and the initial pose increment to obtain a product which is used as a pose increment component value corresponding to the eigenvalue.
This embodiment can be expressed as formula (1):
Δxi＝<x，vi>formula (1)
Wherein i is 1,2,3,4,5, and 6, < a, b > represents a vector a dot-by-dot vector b), and x is an initial pose increment, and pose increment component values corresponding to 6 directions (including pose increment component values of some directions being 0) can be determined by the present embodiment.
As shown in fig. 5, based on the embodiment shown in fig. 1, step 106 may include the following steps:
step 1061, determining a feature vector corresponding to at least one feature value corresponding to at least one pose increment component value.
Step 1062, determining the pose increment of the object based on the at least one pose increment component value and the at least one feature vector.
In this embodiment, since the pose incremental component values of some of the 6 directions are zero, only the pose incremental component value Δ x that is not zero is obtainediCorresponding at least one feature vector viBy fitting each feature vector viAnd multiplying and adding the pose increment component values corresponding to the pose increment component values to obtain the object pose increment, wherein the process can be expressed as the following formula (2):
x’＝Δx1*v1+Δx2*v2+Δx3*v3+Δx4*v4+Δx5*v5+Δx6*v6
formula (2)
Wherein, due to arbitrary Δ xiPossibly 0, then the term is 0.
As shown in fig. 6, based on the embodiment shown in fig. 1, step 102 may include the following steps:
and 1021, determining all corresponding point pairs according to the pose information corresponding to the first point cloud and the pose information corresponding to the second point cloud.
The two point clouds to be registered comprise a first point cloud and a second point cloud; each pair of corresponding points includes a point in one first point cloud and a point in one second point cloud.
Alternatively, the corresponding point pairs are desirably points in different point clouds at the same position in space, but are often replaced with the closest points in actual acquisition, i.e., the corresponding point pairs are sets of closest points in the first and second point clouds.
And 1022, determining an initial pose increment according to the optimization problem of the corresponding point pair set and the coordinates of each point in the corresponding point pair.
Wherein the optimization problem aims to make the distance sum after the operation on the second point cloud approach to zero; the distance sum is determined based on distances between all corresponding point pairs in the set of corresponding point pairs.
Alternatively, the optimization problem in this embodiment is to rotate and translate (adjust 6 degrees of freedom) the second point cloud, so that the distance sum (e.g., the sum of the distances is the sum of the squares of the distances between all the point pairs or the sum of the absolute values of the distances between all the point pairs) corresponding to the corresponding point pair set is minimum, because there is a problem that the corresponding point pair is inaccurate (only the closest point, not the same position in space), when the distance between some point pairs is reduced, the distance between other point pairs may be increased, therefore, the present embodiment determines the optimization degree by the size of the distance sum, and ideally, the distance sum is 0, but the actual situation is usually hard to achieve, therefore, the optimization problem in this embodiment is to make the distance sum as small as possible, determine the initial position increment (expressed as one 6-dimensional vector, the value of each dimension corresponds to an increment of one degree of freedom).
Fig. 7 is a schematic flow chart of a point cloud registration method according to another exemplary embodiment of the present disclosure. As shown in fig. 7, the method of this embodiment includes the following steps:
step 702, determining an initial pose increment based on corresponding point pairs sets included in the two point clouds to be registered.
Wherein the corresponding point pair set comprises a plurality of pairs of corresponding point pairs.
And 704, decomposing the initial pose increment into at least one dimension of the pose to obtain pose increment component values corresponding to the at least one dimension respectively.
At step 706, an object pose increment is determined based on the at least one pose increment component value.
Step 708, judging whether the target pose increment meets a set convergence condition, if so, executing step 710; otherwise, step 712 is performed.
And 710, registering the two point clouds to be registered according to the target pose increment, and ending.
Step 712, determining updated pose information of the point cloud to be registered based on the target pose increment and the pose information of the point cloud to be registered, and taking the point cloud with the updated pose information and the other point cloud to be registered as two point clouds to be registered; return to perform step 702.
In order to realize the registration of two point clouds, the pose adjustment only by one target pose increment may not achieve a better registration effect, and the distance between the corresponding point pairs in the two point clouds after one adjustment may not be the minimum, so steps 702 to 708 need to be iteratively executed on the basis of the adjusted pose information until the obtained target pose increment meets the set convergence condition, the pose of any point cloud (e.g., the second point cloud) in the point clouds to be registered is adjusted by the target pose increment, at this time, the pose of the second point cloud is equal to the initial pose (or the pose after the last adjustment) + the target pose increment, at this time, the pose of the second point cloud is similar to the pose of the first point cloud, at this time, the distance between the corresponding point pairs is the minimum (0 in an ideal case), that is, the registration of the two point clouds is realized.
Any of the point cloud registration methods provided by the embodiments of the present disclosure may be performed by any suitable device having data processing capabilities, including but not limited to: terminal equipment, a server and the like. Alternatively, any of the point cloud registration methods provided by the embodiments of the present disclosure may be executed by a processor, such as the processor executing any of the point cloud registration methods mentioned by the embodiments of the present disclosure by calling corresponding instructions stored in a memory. And will not be described in detail below.
Exemplary devices
Fig. 8 is a schematic structural diagram of a point cloud registration apparatus provided in an exemplary embodiment of the present disclosure. As shown in fig. 8, the apparatus provided in this embodiment includes:
and the initial increment determining module 81 is configured to determine an initial pose increment based on corresponding point pairs sets included in the two to-be-registered point clouds.
Wherein the corresponding point pair set comprises a plurality of pairs of corresponding point pairs.
And the increment decomposition module 82 is configured to decompose the initial pose increment into at least one dimension of the pose to obtain pose increment component values corresponding to the at least one dimension respectively.
An object increment determination module 83 for determining an object pose increment based on the at least one pose increment component value.
And the registration module 84 is configured to determine whether the target pose increment meets a set convergence condition, and register the two point clouds to be registered with the target pose increment in response to meeting the set convergence condition.
The point cloud registration device provided by the above embodiment of the present disclosure determines an initial pose increment based on corresponding point pairs sets included in two point clouds to be registered; the corresponding point pair set comprises a plurality of pairs of corresponding point pairs; decomposing the initial pose increment into at least one dimension of a pose to obtain pose increment component values respectively corresponding to the at least one dimension; determining an object pose increment based on the at least one pose increment component value; judging whether the target pose increment meets a set convergence condition, and registering the two point clouds to be registered by the target pose increment in response to the set convergence condition being met; the pose of the obtained object pose incremental component is adjusted only in a stable direction through the pose incremental component value, so that the pose adjustment error is reduced, the point cloud registration method provided by the embodiment has robustness, and the point cloud registration method can be suitable for point cloud registration of more scenes.
In some alternative embodiments, at least one dimension of the pose includes six degrees of freedom;
an incremental decomposition module 82, comprising:
a matrix determination unit, configured to determine a coefficient matrix based on an optimization problem of the corresponding point pair set;
and the component determining unit is used for decomposing the initial pose increment to six degrees of freedom of the pose based on the coefficient matrix to obtain a pose increment component value corresponding to at least one degree of freedom in the six degrees of freedom.
Optionally, the component determining unit is specifically configured to solve six eigenvectors of the coefficient matrix and an eigenvalue corresponding to each eigenvector; at least one pose delta component value is determined based on the eigenvalues and the eigenvectors.
Wherein each eigenvector and eigenvalue corresponds to one degree of freedom.
Optionally, when determining at least one pose incremental component value based on the feature value and the feature vector, the component determining unit is configured to determine a stable value corresponding to each feature value based on a maximum value of the six feature values; judging whether the stable value corresponding to each characteristic value is smaller than a set threshold value or not, and setting a pose increment component value corresponding to the degree of freedom corresponding to the characteristic value smaller than the set threshold value to zero; and determining a pose increment component value corresponding to the characteristic value not less than the set threshold value based on the characteristic vector.
Optionally, the component determining unit is configured to, when determining the pose incremental component value corresponding to the feature value not less than the set threshold based on the feature vector, perform point multiplication on the feature vector corresponding to the feature value not less than the set threshold and the initial pose increment, and use the obtained product as the pose incremental component value corresponding to the feature value.
In some optional embodiments, the object increment determining module 83 is specifically configured to determine a feature vector corresponding to at least one feature value corresponding to at least one pose increment component value; an object pose increment is determined based on the at least one pose increment component value and the at least one feature vector.
In some optional embodiments, the two point clouds to be registered comprise a first point cloud and a second point cloud;
an initial increment determining module 81, configured to determine all corresponding point pairs according to the pose information corresponding to the first point cloud and the pose information corresponding to the second point cloud; wherein each pair of corresponding points comprises a point in a first point cloud and a point in a second point cloud; determining an initial pose increment according to the optimization problem of the corresponding point pair set and the coordinates of each point in the corresponding point pair; wherein the optimization problem aims to make the distance sum after the operation on the second point cloud approach to zero; the distance sum is determined based on distances between all corresponding point pairs in the set of corresponding point pairs.
In some optional embodiments, the apparatus provided in this embodiment further includes:
the adjustment iteration module is used for responding to the situation that the set convergence condition is not met, and determining the updated pose information of the point cloud to be registered based on the target pose increment and the pose information of the point cloud to be registered; and taking the point cloud with the updated pose information and the other point cloud to be registered as two point clouds to be registered.
Exemplary electronic device
Next, an electronic apparatus according to an embodiment of the present disclosure is described with reference to fig. 9. The electronic device may be either or both of the first device 100 and the second device 200, or a stand-alone device separate from them that may communicate with the first device and the second device to receive the collected input signals therefrom.
FIG. 9 illustrates a block diagram of an electronic device in accordance with an embodiment of the disclosure.
As shown in fig. 9, the electronic device 90 includes one or more processors 91 and memory 92.
The processor 91 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 90 to perform desired functions.
Memory 92 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, Random Access Memory (RAM), cache memory (cache), and/or the like. The non-volatile memory may include, for example, Read Only Memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium and executed by the processor 91 to implement the point cloud registration methods of the various embodiments of the present disclosure described above and/or other desired functions. Various contents such as an input signal, a signal component, a noise component, etc. may also be stored in the computer-readable storage medium.
In one example, the electronic device 90 may further include: an input device 93 and an output device 94, which are interconnected by a bus system and/or other form of connection mechanism (not shown).
For example, when the electronic device is the first device 100 or the second device 200, the input device 93 may be a microphone or a microphone array as described above for capturing an input signal of a sound source. When the electronic device is a stand-alone device, the input means 93 may be a communication network connector for receiving the acquired input signals from the first device 100 and the second device 200.
The input device 93 may also include, for example, a keyboard, a mouse, and the like.
The output device 94 may output various information including the determined distance information, direction information, and the like to the outside. The output devices 94 may include, for example, a display, speakers, a printer, and a communication network and remote output devices connected thereto, among others.
Of course, for simplicity, only some of the components of the electronic device 90 relevant to the present disclosure are shown in fig. 9, omitting components such as buses, input/output interfaces, and the like. In addition, the electronic device 90 may include any other suitable components, depending on the particular application.
Exemplary computer program product and computer-readable storage Medium
In addition to the above-described methods and apparatus, embodiments of the present disclosure may also be a computer program product comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in the point cloud registration method according to various embodiments of the present disclosure described in the "exemplary methods" section of this specification above.
The computer program product may write program code for carrying out operations for embodiments of the present disclosure in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present disclosure may also be a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, cause the processor to perform the steps in the point cloud registration method according to various embodiments of the present disclosure described in the "exemplary methods" section above in this specification.
The computer-readable storage medium may take any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The foregoing describes the general principles of the present disclosure in conjunction with specific embodiments, however, it is noted that the advantages, effects, etc. mentioned in the present disclosure are merely examples and are not limiting, and they should not be considered essential to the various embodiments of the present disclosure. Furthermore, the foregoing disclosure of specific details is for the purpose of illustration and description and is not intended to be limiting, since the disclosure is not intended to be limited to the specific details so described.
In the present specification, the embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts in the embodiments are referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The block diagrams of devices, apparatuses, systems referred to in this disclosure are only given as illustrative examples and are not intended to require or imply that the connections, arrangements, configurations, etc. must be made in the manner shown in the block diagrams. These devices, apparatuses, devices, systems may be connected, arranged, configured in any manner, as will be appreciated by those skilled in the art. Words such as "including," "comprising," "having," and the like are open-ended words that mean "including, but not limited to," and are used interchangeably therewith. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".
The methods and apparatus of the present disclosure may be implemented in a number of ways. For example, the methods and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless specifically stated otherwise. Further, in some embodiments, the present disclosure may also be embodied as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.
It is also noted that in the devices, apparatuses, and methods of the present disclosure, each component or step can be decomposed and/or recombined. These decompositions and/or recombinations are to be considered equivalents of the present disclosure.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the disclosure. Thus, the present disclosure is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit embodiments of the disclosure to the form disclosed herein. While a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, alterations, additions and sub-combinations thereof.

Claims (10)

1. A point cloud registration method, comprising:
determining an initial pose increment based on corresponding point pairs in two point clouds to be registered; the corresponding point pair set comprises a plurality of pairs of corresponding point pairs;
decomposing the initial pose increment into at least one dimension of a pose to obtain pose increment component values respectively corresponding to the at least one dimension;
determining an object pose increment based on the at least one pose increment component value;
and determining whether the target pose increment meets a set convergence condition, and registering the two point clouds to be registered by the target pose increment in response to meeting the set convergence condition.
2. The method of claim 1, wherein at least one dimension of the pose comprises six degrees of freedom;
decomposing the initial pose increment into at least one dimension of the pose to obtain pose increment component values respectively corresponding to the at least one dimension, comprising:
determining a coefficient matrix based on an optimization problem of the corresponding point pair set;
decomposing the initial pose increment to six degrees of freedom of a pose based on the coefficient matrix to obtain a pose increment component value corresponding to at least one degree of freedom in the six degrees of freedom.
3. The method according to claim 2, wherein the decomposing the initial pose increment to six degrees of freedom of a pose based on the coefficient matrix to obtain a pose increment component value corresponding to at least one degree of freedom of the six degrees of freedom comprises:
solving six eigenvectors of the coefficient matrix and an eigenvalue corresponding to each eigenvector; wherein each of the eigenvectors and the eigenvalues corresponds to one degree of freedom;
determining the at least one pose delta component value based on the feature values and the feature vectors.
4. The method according to claim 3, wherein said determining the at least one pose delta component value based on the feature value and the feature vector comprises:
determining a stable value corresponding to each characteristic value based on the maximum value of the six characteristic values;
judging whether the stable value corresponding to each characteristic value is smaller than a set threshold value or not, and setting a pose increment component value corresponding to the degree of freedom corresponding to the characteristic value smaller than the set threshold value to zero; and determining pose increment component values corresponding to the characteristic values not less than the set threshold value based on the characteristic vectors.
5. The method according to claim 4, wherein the determining, based on the feature vector, the pose incremental component value corresponding to the feature value not less than the set threshold value comprises:
and performing point multiplication on the eigenvector corresponding to the eigenvalue not less than the set threshold and the initial pose increment to obtain a product which is used as a pose increment component value corresponding to the eigenvalue.
6. The method according to any one of claims 1-5, wherein said determining an object pose increment based on said at least one pose increment component value comprises:
determining a feature vector corresponding to at least one feature value corresponding to the at least one pose incremental component value;
determining the object pose delta based on the at least one pose delta component value and the at least one feature vector.
7. The method according to any one of claims 1 to 6, wherein the two point clouds to be registered comprise a first point cloud and a second point cloud;
determining an initial pose increment based on corresponding point pairs sets included in two point clouds to be registered, including:
determining all corresponding point pairs according to the pose information corresponding to the first point cloud and the pose information corresponding to the second point cloud; wherein each pair of said corresponding points comprises a point in one said first point cloud and a point in one second point cloud;
determining the initial pose increment according to the optimization problem of the corresponding point pair set and the coordinates of each point in the corresponding point pair; wherein the optimization problem aims to make the distance sum after operating on the second point cloud approach to zero; the distance sum is determined based on distances between all corresponding point pairs in the set of corresponding point pairs.
8. A point cloud registration apparatus, comprising:
the initial increment determining module is used for determining an initial pose increment based on corresponding point pairs in the two to-be-registered point clouds; the corresponding point pair set comprises a plurality of pairs of corresponding point pairs;
the increment decomposition module is used for decomposing the initial pose increment into at least one dimension of a pose to obtain pose increment component values respectively corresponding to the at least one dimension;
an object increment determination module to determine an object pose increment based on the at least one pose increment component value;
and the registration module is used for determining whether the target pose increment meets a set convergence condition or not, and registering the two point clouds to be registered by the target pose increment in response to meeting the set convergence condition.
9. A computer-readable storage medium, characterized in that the storage medium stores a computer program for executing the point cloud registration method of any of the above claims 1-7.
10. An electronic device, characterized in that the electronic device comprises:
a processor;
a memory for storing the processor-executable instructions;
the processor is used for reading the executable instructions from the memory and executing the instructions to realize the point cloud registration method of any one of the claims 1-7.
CN202010848942.0A 2020-08-21 2020-08-21 Point cloud registration method and device, computer readable storage medium and electronic equipment Active CN111951314B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010848942.0A CN111951314B (en) 2020-08-21 2020-08-21 Point cloud registration method and device, computer readable storage medium and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010848942.0A CN111951314B (en) 2020-08-21 2020-08-21 Point cloud registration method and device, computer readable storage medium and electronic equipment

Publications (2)

Publication Number Publication Date
CN111951314A true CN111951314A (en) 2020-11-17
CN111951314B CN111951314B (en) 2021-08-31

Family

ID=73359324

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010848942.0A Active CN111951314B (en) 2020-08-21 2020-08-21 Point cloud registration method and device, computer readable storage medium and electronic equipment

Country Status (1)

Country Link
CN (1) CN111951314B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114862922A (en) * 2022-04-13 2022-08-05 成都飞机工业（集团）有限责任公司 Depth image registration method based on coupling geometry and curvature consistency constraint
CN117689698A (en) * 2024-02-04 2024-03-12 安徽蔚来智驾科技有限公司 Point cloud registration method, intelligent device and storage medium

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105976353A (en) * 2016-04-14 2016-09-28 南京理工大学 Spatial non-cooperative target pose estimation method based on model and point cloud global matching
EP3086283A1 (en) * 2015-04-21 2016-10-26 Hexagon Technology Center GmbH Providing a point cloud using a surveying instrument and a camera device
CN107194964A (en) * 2017-05-24 2017-09-22 电子科技大学 A kind of VR social intercourse systems and its method based on real-time body's three-dimensional reconstruction
CN108876862A (en) * 2018-07-13 2018-11-23 北京控制工程研究所 A kind of noncooperative target point cloud position and attitude calculation method
CN109724586A (en) * 2018-08-21 2019-05-07 南京理工大学 A kind of spacecraft relative pose measurement method of fusion depth map and point cloud
CN110264502A (en) * 2019-05-17 2019-09-20 华为技术有限公司 Point cloud registration method and device
CN110544279A (en) * 2019-08-26 2019-12-06 华南理工大学 pose estimation method combining image identification and genetic algorithm fine registration
CN110782496A (en) * 2019-09-06 2020-02-11 深圳市道通智能航空技术有限公司 Calibration method, calibration device, aerial photographing equipment and storage medium
CN111553936A (en) * 2020-04-14 2020-08-18 北京理工大学珠海学院 Point cloud registration method, system, device and storage medium

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3086283A1 (en) * 2015-04-21 2016-10-26 Hexagon Technology Center GmbH Providing a point cloud using a surveying instrument and a camera device
CN105976353A (en) * 2016-04-14 2016-09-28 南京理工大学 Spatial non-cooperative target pose estimation method based on model and point cloud global matching
CN107194964A (en) * 2017-05-24 2017-09-22 电子科技大学 A kind of VR social intercourse systems and its method based on real-time body's three-dimensional reconstruction
CN108876862A (en) * 2018-07-13 2018-11-23 北京控制工程研究所 A kind of noncooperative target point cloud position and attitude calculation method
CN109724586A (en) * 2018-08-21 2019-05-07 南京理工大学 A kind of spacecraft relative pose measurement method of fusion depth map and point cloud
CN110264502A (en) * 2019-05-17 2019-09-20 华为技术有限公司 Point cloud registration method and device
CN110544279A (en) * 2019-08-26 2019-12-06 华南理工大学 pose estimation method combining image identification and genetic algorithm fine registration
CN110782496A (en) * 2019-09-06 2020-02-11 深圳市道通智能航空技术有限公司 Calibration method, calibration device, aerial photographing equipment and storage medium
CN111553936A (en) * 2020-04-14 2020-08-18 北京理工大学珠海学院 Point cloud registration method, system, device and storage medium

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
KEIJI NAGATANI等: ""Scan-point Planning and 3-D Map Building for a 3-D Laser Range Scanner in an Outdoor Environment"", 《FIELD AND SERVICE ROBOTICS. SPRINGER BERLIN HEIDELBERG》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114862922A (en) * 2022-04-13 2022-08-05 成都飞机工业（集团）有限责任公司 Depth image registration method based on coupling geometry and curvature consistency constraint
CN117689698A (en) * 2024-02-04 2024-03-12 安徽蔚来智驾科技有限公司 Point cloud registration method, intelligent device and storage medium
CN117689698B (en) * 2024-02-04 2024-04-19 安徽蔚来智驾科技有限公司 Point cloud registration method, intelligent device and storage medium

Also Published As

Publication number Publication date
CN111951314B (en) 2021-08-31

Similar Documents

Publication Publication Date Title
CN112180362B (en) Method and device for determining conversion pose between radar and camera and electronic equipment
CN111951314B (en) Point cloud registration method and device, computer readable storage medium and electronic equipment
JP7052788B2 (en) Camera parameter estimation device, camera parameter estimation method, and program
US11688177B2 (en) Obstacle detection method and device, apparatus, and storage medium
JP7099627B2 (en) Camera parameter estimation device, camera parameter estimation method, and program
CN114047823B (en) Three-dimensional model display method, computer-readable storage medium and electronic device
El Akkad et al. Camera self-calibration having the varying parameters and based on homography of the plane at infinity
CN112489114A (en) Image conversion method and device, computer readable storage medium and electronic equipment
CN112037279A (en) Article position identification method and device, storage medium and electronic equipment
CN114329743B (en) House type optimization method, device and storage medium
CN114187588B (en) Data processing method, device and storage medium
CN113689508B (en) Point cloud labeling method and device, storage medium and electronic equipment
CN114615641A (en) High-altitude platform equipment cooperative management method and system and electronic equipment
Hunyadi et al. Constrained quadratic errors-in-variables fitting
CN114241029B (en) Image three-dimensional reconstruction method and device
CN115936974A (en) Image data processing method, apparatus and medium based on homography transformation
Torr et al. Invariant fitting of two view geometry
WO2020144757A1 (en) Camera parameter estimation device, camera parameter estimation method, and computer-readable recording medium
CN114004874B (en) Acquisition method and device of occupied grid map
CN112489111B (en) Camera external parameter calibration method and device and camera external parameter calibration system
CN114170439A (en) Gesture recognition method and device, storage medium and electronic equipment
CN113628283B (en) Parameter calibration method and device of image pickup device, medium and electronic equipment
WO2012160787A1 (en) Position/posture estimation device, position/posture estimation method and position/posture estimation program
CN111723926A (en) Training method and training device for neural network model for determining image parallax
CN113109763B (en) Sound source position determining method and device, readable storage medium and electronic equipment

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
TA01 Transfer of patent application right
TA01 Transfer of patent application right

Effective date of registration: 20210414

Address after: 100085 Floor 101 102-1, No. 35 Building, No. 2 Hospital, Xierqi West Road, Haidian District, Beijing

Applicant after: Seashell Housing (Beijing) Technology Co.,Ltd.

Address before: Unit 05, room 112, 1st floor, office building, Nangang Industrial Zone, economic and Technological Development Zone, Binhai New Area, Tianjin 300457

Applicant before: BEIKE TECHNOLOGY Co.,Ltd.

GR01 Patent grant
GR01 Patent grant