CN111553936A - Point cloud registration method, system, device and storage medium - Google Patents
Point cloud registration method, system, device and storage medium Download PDFInfo
- Publication number
- CN111553936A CN111553936A CN202010288588.0A CN202010288588A CN111553936A CN 111553936 A CN111553936 A CN 111553936A CN 202010288588 A CN202010288588 A CN 202010288588A CN 111553936 A CN111553936 A CN 111553936A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- wolf
- rotation angle
- determining
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/60—Rotation of a whole image or part thereof
-
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Abstract
The invention discloses a point cloud registration method, a system, a device and a storage medium, wherein the method comprises the following steps: acquiring a first point cloud and a second point cloud; obtaining a translation matrix according to the first point cloud and the second point cloud; determining a first wolf set and a second wolf set according to a preset population, the first point cloud and the second point cloud; updating according to the first wolf set and the second wolf set to obtain a final rotation angle; registering the first point cloud and the second point cloud according to the final rotation angle and the translation matrix. According to the method, the first wolf set and the second wolf set are determined and updated by presetting the preset population including the initial rotation angle, the final rotation angle parameter is solved, the convergence speed is high, the operation time is reduced, and the registration precision of the first point cloud and the second point cloud is high. The method can be widely applied to the field of three-dimensional reconstruction.
Description
Technical Field
The invention relates to the field of three-dimensional reconstruction, in particular to a point cloud registration method, a point cloud registration system, a point cloud registration device and a point cloud registration storage medium.
Background
In recent years, three-dimensional reconstruction techniques are widely used in the fields of medical images, industrial detection, cultural relic reconstruction, and the like. The three-dimensional model of the target is obtained by the steps of point cloud filtering, point cloud registration, point cloud fusion and the like of the three-dimensional point cloud data obtained by the scanner. The point cloud registration technology refers to registering point cloud models of different angles acquired by a three-dimensional scanner into the same coordinate system, is a key link in the three-dimensional reconstruction technology, and has a great influence on the final effect of the three-dimensional model. However, there are many methods for Point cloud registration, such as a registration algorithm based on Fast Point Feature Histogram (FPFH) features, a 4-PCS (4-points consistent sets, 4-Point set) algorithm, a Normal Distribution Transform (NDT) algorithm, and an Iterative Closest Point (ICP) algorithm. However, in point cloud registration, time and registration accuracy are two most important performance measurement indexes, the existing registration algorithm for the FPFH features is long in processing time and very sensitive to noise, the 4PCS method can cause registration failure in point clouds with more planes and unobvious features, the NDT method is too dependent on parameter setting, the registration accuracy is low, the ICP method has high requirement on the initial position of registration, and the calculation is complex. Therefore, a point cloud registration method with high speed and high precision needs to be designed.
Disclosure of Invention
In view of the above, in order to solve the above technical problems, an object of the present invention is to provide a method, a system, an apparatus and a storage medium for point cloud registration with high speed and high precision.
The technical scheme adopted by the invention is as follows: a point cloud registration method, comprising the steps of:
acquiring a first point cloud and a second point cloud;
obtaining a translation matrix according to the first point cloud and the second point cloud;
determining a first wolf set and a second wolf set according to a preset population, the first point cloud and the second point cloud;
updating according to the first wolf set and the second wolf set to obtain a final rotation angle;
registering the first point cloud and the second point cloud according to the final rotation angle and the translation matrix;
the first point cloud is a point cloud to be registered, the second point cloud is a target point cloud, the preset population comprises a first wolf set and a second wolf set, the first wolf set comprises a plurality of first wolfs, the second wolf set comprises a plurality of second wolfs, and each first wolf and each second wolf comprise an initial rotation angle.
Further, the step of obtaining a translation matrix according to the first point cloud and the second point cloud comprises the following steps:
determining a first center coordinate of the first point cloud according to the first point cloud;
determining a second center coordinate of the second point cloud according to the second point cloud;
and calculating the difference value of the first central coordinate and the second central coordinate to obtain the translation matrix.
Further, each of the initial rotation angles includes an initial first rotation angle, an initial second rotation angle, and an initial third rotation angle, and further includes the steps of:
determining a value space of the initial rotation angle according to preset value ranges of the initial first rotation angle, the initial second rotation angle and the initial third rotation angle;
dividing the value space by a preset number of parts to obtain a divided space of the preset number of parts;
at least one of the initial rotation angles is determined within each of the partitioned spaces.
Further, the step of determining the first wolf set and the second wolf set according to the preset population, the first point cloud and the second point cloud includes the following steps:
selecting feature points of the first point cloud and the second point cloud, and determining a plurality of feature point pairs, wherein each feature point pair comprises a first feature point and a second feature point corresponding to the first feature point, the first point cloud comprises a plurality of first feature points, and the second point cloud comprises a plurality of second feature points;
determining a fitness value according to the feature point pairs, each initial rotation angle and the translation matrix;
determining the first wolf set and the second wolf set according to fitness values;
the fitness value is arranged in the order from big to small, the first wolf is corresponding to the last three names, and the second wolf is corresponding to the last three names.
Further, the step of selecting the feature points of the first point cloud and the second point cloud and determining a plurality of feature point pairs specifically comprises:
selecting characteristic points of the first point cloud and the second point cloud to obtain first characteristic values of the first characteristic points and second characteristic values of the second characteristic points and the second characteristic points corresponding to the first characteristic points;
respectively calculating the difference value of each first characteristic value and each second characteristic value;
and if the difference is larger than or equal to a preset threshold value, filtering the first characteristic points and the corresponding second characteristic points, otherwise, reserving the first characteristic points and the corresponding second characteristic points to obtain a plurality of characteristic point pairs.
Further, the step of updating according to the first wolf set and the second wolf set to obtain the final rotation angle includes the following steps:
respectively calculating the distance between each first wolf and a second wolf to obtain a first distance, a second distance and a third distance;
updating the position of the second wolf according to the first distance, the second distance and the third distance, taking the rest second wolfs in the second wolf set as new second wolfs, returning to the step of respectively calculating the distance between each first wolf and one second wolf until the second wolfs in the second wolf set are updated, and finishing one iteration;
if the iteration times do not reach the preset iteration times, determining a new fitness value according to the first wolf and the updated second wolf, determining a new first wolf set and a new second wolf set according to the new fitness value, and returning to the step of respectively calculating the distance between each first wolf and one second wolf;
and if the iteration times reach the preset iteration times, taking the first wolf corresponding to the current minimum new fitness value as the final rotation angle.
Further, the step of registering the first point cloud and the second point cloud according to the final rotation angle and the translation matrix includes the following steps:
obtaining a final rotation matrix according to the final rotation angle;
and according to the final rotation matrix and the translation matrix, performing rotation and translation transformation on the first point cloud to obtain a registration point cloud registered with the second point cloud.
The present invention also provides a system comprising:
the acquisition module is used for acquiring a first point cloud and a second point cloud;
the translation module is used for obtaining a translation matrix according to the first point cloud and the second point cloud;
the determining module is used for determining a first wolf set and a second wolf set according to a preset population, the first point cloud and the second point cloud;
the updating module is used for updating according to the first wolf set and the second wolf set to obtain a final rotating angle;
the registration module is used for registering the first point cloud and the second point cloud according to the final rotation angle and the translation matrix;
the first point cloud is a point cloud to be registered, the second point cloud is a target point cloud, the preset population comprises a first wolf set and a second wolf set, the first wolf set comprises a plurality of first wolfs, the second wolf set comprises a plurality of second wolfs, and each first wolf and each second wolf comprise an initial rotation angle.
The present invention also provides an apparatus comprising:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the point cloud registration method.
The invention also provides a storage medium storing a program executed by a processor to perform the point cloud registration method.
The invention has the beneficial effects that: determining a first wolf set and a second wolf set according to a preset population, the first point cloud and the second point cloud, updating according to the first wolf set and the second wolf set to obtain a final rotation angle, and registering the first point cloud and the second point cloud according to a translation matrix and the final rotation angle obtained by using the first point cloud and the second point cloud; according to the method, the first wolf set and the second wolf set are determined and updated by presetting the preset population including the initial rotation angle, the final rotation angle parameter is solved, the convergence speed is high, the operation time is reduced, and the registration precision of the first point cloud and the second point cloud is high.
Drawings
FIG. 1 is a schematic flow chart of the steps of the method of the present invention;
FIG. 2 is a block diagram of the system of the present invention.
Detailed Description
The invention will be further explained and explained with reference to the drawings and the embodiments in the description. The step numbers in the embodiments of the present invention are set for convenience of illustration only, the order between the steps is not limited at all, and the execution order of each step in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.
As shown in fig. 1, the present embodiment provides a point cloud registration method, including the following steps:
s1, acquiring a first point cloud and a second point cloud;
s2, obtaining a translation matrix according to the first point cloud and the second point cloud;
s3, determining a first wolf set and a second wolf set according to a preset population, the first point cloud and the second point cloud;
s4, updating according to the first wolf set and the second wolf set to obtain a final rotation angle;
s5, registering the first point cloud and the second point cloud according to the final rotation angle and the translation matrix;
the first point cloud is a point cloud to be registered, the second point cloud is a target point cloud, the preset population comprises a first wolf set and a second wolf set, the first wolf set comprises a plurality of first wolfs, the second wolf set comprises a plurality of second wolfs, and each first wolf and each second wolf comprise an initial rotation angle.
In an embodiment, a gray wolf optimization algorithm is used to solve the relevant parameters, the population includes a plurality of wolfs, and the wolfs include a first wolf and a second wolf.
In this embodiment, step S2 includes the following steps:
determining a first center coordinate of the first point cloud according to the first point cloud P
Determining a second center coordinate of the second point cloud according to the second point cloud Q
And calculating the difference value of the first central coordinate and the second central coordinate to obtain the translation matrix.
Specifically, the method comprises the following steps: translation matrix
In this embodiment, the step S3 of determining the first wolf set and the second wolf set according to the preset population, the first point cloud, and the second point cloud includes the following steps:
s31, initializing a population;
setting the number of the initial population as n, wherein the initial rotation angles comprise an initial first rotation angle a, an initial second rotation angle b and an initial third rotation angle c, and represent rotation angles along the directions of x, y and z respectively.
The value ranges of the three rotation angles are [ -pi, pi ], so that the value space of the initial rotation angle is determined to be a sphere with pi as a radius, assuming that the center of the sphere is located at the origin of coordinates, dividing the value space by a preset number of parts (8 in the embodiment, the plane is used as a coordinate axis plane) by using a plane to obtain 8 divided spaces, randomly selecting n/8 groups of values in each interval to obtain a preset population, the value taking method can ensure the uniformity of the value taking, wherein each group of values is an initial rotation angle, for example, n is 8, that is, an initial rotation angle is taken in each of the 8 divided spaces, which is 8 groups of initial rotation angles, each group of initial rotation angles represents a wolf, specifically, a position where the wolf is located, and in other embodiments, the dividing manner or the number of parts can be set as required.
S32, selecting feature points of the first point cloud and the second point cloud, and determining a plurality of feature point pairs, wherein each feature point pair comprises a first feature point and a second feature point corresponding to the first feature point, the first point cloud comprises a plurality of first feature points, and the second point cloud comprises a plurality of second feature points;
the method specifically comprises the following steps: s321,Selecting characteristic points of the first point cloud and the second point cloud to obtain first characteristic values of the first characteristic points and second characteristic values of the second characteristic points and the second characteristic points corresponding to the first characteristic points; in the present embodiment, the feature point selection uses HKS (Heat kernel signature), and therefore the first feature value is HKS1The second characteristic value is HKS2(ii) a The corresponding point can be obtained by searching a K-D tree structure, and the second feature point corresponding to the first feature point is a point closest to the first feature point, for example, may be a point closest to the first feature point of the first point cloud, or may be a point closest to the first feature point after the first point cloud is transformed by using a rotation and translation matrix generated in the iteration during the iteration and then is transformed.
S322, respectively calculating a difference between each first characteristic value and each second characteristic value, if the difference is greater than or equal to a preset threshold, filtering the first characteristic points and the corresponding second characteristic points, otherwise, retaining the difference, and obtaining a plurality of characteristic point pairs. For example: HKS1－HKS2<If sigma is a preset threshold value, reserving the first characteristic point and a second characteristic point corresponding to the first characteristic point, otherwise, filtering; obtaining a plurality of characteristic point pairs p according to the reserved first characteristic points and second characteristic points corresponding to the first characteristic pointsi、qiWherein p isi、qiRespectively, the coordinate representation of the reserved first characteristic point and the second characteristic point corresponding to the first characteristic point. Through the processing, the filtering error point pairs can be eliminated, and the accuracy of subsequent processing is improved.
S33, determining a fitness value according to the feature point pairs, each initial rotation angle and the translation matrix, wherein the method comprises the following steps:
using equation (1):
wherein F (R, T) is a fitness value, piIs the coordinates of the ith point in the first point cloud P, qiFor the target point cloud Q and piThe coordinates of the corresponding points, m is the number of the characteristic point pairs, R is a rotation matrix, each initial rotation angle is correspondingly calculated to obtain an R (at this time, an initial rotation matrix), T is a translation matrix, wherein:
therefore, each fitness value corresponding to each initial rotation angle can be obtained by substituting the initial rotation matrix R corresponding to each initial rotation angle into a formula;
s34, determining the first wolf set and the second wolf set according to the fitness value;
specifically, the method comprises the following steps: arranging the fitness values in the order from big to small, taking the wolfs (initial rotation angles) corresponding to the three lowest fitness values as the first wolfs, namely alpha wolfs, beta wolfs and gamma wolfs, and the wolfs before the last three wolfs as the second wolfs, namely omega wolfs, thereby determining the first wolf set and the second wolf set. Wherein, alpha wolf is the leader of wolf group, the position of beta wolf in wolf group is only next to alpha wolf, assist alpha wolf to make decision, gamma wolf hears the command of alpha wolf and beta wolf; the omega wolf is the lowest layer wolf in the wolf group. Wherein, the fitness values corresponding to the alpha wolf, the beta wolf and the gamma wolf are increased in sequence.
Step S4, updating according to the first wolf set and the second wolf set to obtain a final rotation angle;
in this embodiment, optionally, the method includes:
s41, calculating the distance between each first wolf and a second wolf to obtain a first distance, a second distance and a third distance;
specifically, the method comprises the following steps: respectively calculating a first distance, a second distance and a third distance between the alpha wolf, the beta wolf and the gamma wolf and the current omega wolf;
Dα＝|C1·Xα(t)-X(t)|
Dβ＝|C2·Xβ(t)-X(t)|
Dγ＝|C3·Xγ(t)-X(t)|
Dαis a first distance, DβIs a second distance, DγIs a third distance, Xα(t)、Xβ(t)、Xγ(t) α wolf, β wolf and gamma wolf current positions, X (t) omega wolf current position, CjIs a first parameter (j ═ 1,2,3), t denotes the t-th iteration, where ω wolf is chosen randomly;
s42, updating the positions of the second wolves according to the first distance, the second distance and the third distance, taking the rest of the second wolves in the second wolve set as new second wolves, returning to the step of calculating the distance between each first wolve and a second wolve, until the second wolves in the second wolve set are updated, and completing an iteration;
specifically, the method comprises the following steps:
X1＝|Xα(t)-A1·Dα|
X2＝|Xβ(t)-A2·Dβ|
X3＝|Xγ(t)-A3·Dγ|
x (t +1) is the updated position of the current omega wolf, AjIs the second parameter (j ═ 1,2,3), X1、X2、X3Is a third parameter;
after the first omega wolf is updated, update AjAnd CjContinuously selecting another omega wolf as a new omega wolf to return to the S41 until all the omega wolfs are updated;
specifically, update AjAnd Cj：：
Aj＝2a·r1-a，j∈{1，2，3}
Cj＝2r2，j∈{1，2，3}
Wherein the content of the first and second substances,a is a convergence factor which gradually decreases from 2 to 0 as the number of iterations increases, r1And r2Is a random vector with a modulo value of [0,1]。
S43, if the iteration number does not reach the preset iteration number, determining a new fitness value according to the first wolf and the updated second wolf, determining a new first wolf set and a new second wolf set according to the new fitness value, and returning to the step of respectively calculating the distance between each first wolf and each second wolf until the preset iteration number is reached;
specifically, the method comprises the following steps: judging whether the current iteration times reach the preset iteration times, if not, determining new fitness values according to the characteristic point pairs and the translation matrix T by using the current alpha wolf, the beta wolf and the gamma wolf and the updated omega wolf by using a formula (1), arranging wolfs corresponding to three fitness values which are arranged in the last three names and are the smallest in the sequence from big to small according to the new fitness values, taking the wolfs which are arranged in the last three names and are arranged in the front of the last three names as a new first wolf set, and returning to S41;
and if the iteration times reach the preset iteration times, taking the first wolf corresponding to the current minimum new fitness value as the final rotation angle.
Specifically, the method comprises the following steps: the first wolf (α wolf) corresponding to the last updated, i.e., the current minimum new fitness value is used as the final rotation angle, which includes the first rotation angle a ', the second rotation angle b ', and the third rotation angle c '.
S5, registering the first point cloud and the second point cloud according to the final rotation angle and the translation matrix;
specifically, S51, calculating according to the final rotation angle to obtain a final rotation matrix R';
and S52, according to the final rotation matrix and the translation matrix, performing rotation and translation transformation on the first point cloud to obtain a registration point cloud registered with the second point cloud.
Specifically, the method comprises the following steps: and (3) registering the point cloud P '((R')) P + T, namely finishing the registration of the first point cloud and the second point cloud.
As shown in fig. 2, the present invention also provides a system comprising:
the acquisition module is used for acquiring a first point cloud and a second point cloud;
the translation module is used for obtaining a translation matrix according to the first point cloud and the second point cloud;
the determining module is used for determining a first wolf set and a second wolf set according to a preset population, the first point cloud and the second point cloud;
the updating module is used for updating according to the first wolf set and the second wolf set to obtain a final rotating angle;
the registration module is used for registering the first point cloud and the second point cloud according to the final rotation angle and the translation matrix;
the first point cloud is a point cloud to be registered, the second point cloud is a target point cloud, the preset population comprises a first wolf set and a second wolf set, the first wolf set comprises a plurality of first wolfs, the second wolf set comprises a plurality of second wolfs, and each first wolf and each second wolf comprise an initial rotation angle.
The contents in the above method embodiments are all applicable to the present system embodiment, the functions specifically implemented by the present system embodiment are the same as those in the above method embodiment, and the beneficial effects achieved by the present system embodiment are also the same as those achieved by the above method embodiment.
An embodiment of the present invention further provides an apparatus, including:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the point cloud registration method.
The contents in the above method embodiments are all applicable to the present apparatus embodiment, the functions specifically implemented by the present apparatus embodiment are the same as those in the above method embodiments, and the advantageous effects achieved by the present apparatus embodiment are also the same as those achieved by the above method embodiments.
In some alternative embodiments, the embodiments presented and described in the context of the steps of the present invention are provided by way of example in order to provide a more thorough understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and in which sub-operations described as part of larger operations are performed independently.
Furthermore, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the described functions and/or features may be integrated in a single physical device and/or software module, or one or more functions and/or features may be implemented in a separate physical device or software module. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary for an understanding of the present invention. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be understood within the ordinary skill of an engineer, given the nature, function, and internal relationship of the modules. Accordingly, those skilled in the art can, using ordinary skill, practice the invention as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative of and not intended to limit the scope of the invention, which is defined by the appended claims and their full scope of equivalents.
The embodiment of the invention also provides a storage medium, wherein the storage medium stores a program, and the program is executed by a processor to complete the point cloud registration method.
It can also be seen that the contents in the above method embodiments are all applicable to the present storage medium embodiment, and the realized functions and advantageous effects are the same as those in the method embodiments.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The steps of an embodiment represent or are otherwise described herein as logic and/or steps, e.g., a sequential list of executable instructions that can be thought of as implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
In the description herein, references to the description of the term "one embodiment," "the present embodiment," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While the preferred embodiments of the present invention have been illustrated and described, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A point cloud registration method is characterized by comprising the following steps:
acquiring a first point cloud and a second point cloud;
obtaining a translation matrix according to the first point cloud and the second point cloud;
determining a first wolf set and a second wolf set according to a preset population, the first point cloud and the second point cloud;
updating according to the first wolf set and the second wolf set to obtain a final rotation angle;
registering the first point cloud and the second point cloud according to the final rotation angle and the translation matrix;
the first point cloud is a point cloud to be registered, the second point cloud is a target point cloud, the preset population comprises a first wolf set and a second wolf set, the first wolf set comprises a plurality of first wolfs, the second wolf set comprises a plurality of second wolfs, and each first wolf and each second wolf comprise an initial rotation angle.
2. The point cloud registration method of claim 1, wherein: the step of obtaining a translation matrix according to the first point cloud and the second point cloud comprises the following steps:
determining a first center coordinate of the first point cloud according to the first point cloud;
determining a second center coordinate of the second point cloud according to the second point cloud;
and calculating the difference value of the first central coordinate and the second central coordinate to obtain the translation matrix.
3. The point cloud registration method of claim 1, wherein: each initial rotation angle comprises an initial first rotation angle, an initial second rotation angle and an initial third rotation angle, and the method further comprises the following steps:
determining a value space of the initial rotation angle according to preset value ranges of the initial first rotation angle, the initial second rotation angle and the initial third rotation angle;
dividing the value space by a preset number of parts to obtain a divided space of the preset number of parts;
at least one of the initial rotation angles is determined within each of the partitioned spaces.
4. The point cloud registration method of claim 1, wherein: the step of determining the first wolf set and the second wolf set according to the preset population, the first point cloud and the second point cloud comprises the following steps:
selecting feature points of the first point cloud and the second point cloud, and determining a plurality of feature point pairs, wherein each feature point pair comprises a first feature point and a second feature point corresponding to the first feature point, the first point cloud comprises a plurality of first feature points, and the second point cloud comprises a plurality of second feature points;
determining a fitness value according to the feature point pairs, each initial rotation angle and the translation matrix;
determining the first wolf set and the second wolf set according to fitness values;
the fitness value is arranged in the order from big to small, the first wolf is corresponding to the last three names, and the second wolf is corresponding to the last three names.
5. The point cloud registration method of claim 4, wherein: the step of selecting the characteristic points of the first point cloud and the second point cloud and determining a plurality of characteristic point pairs specifically comprises the following steps:
selecting characteristic points of the first point cloud and the second point cloud to obtain first characteristic values of the first characteristic points and second characteristic values of the second characteristic points and the second characteristic points corresponding to the first characteristic points;
respectively calculating the difference value of each first characteristic value and each second characteristic value;
and if the difference is larger than or equal to a preset threshold value, filtering the first characteristic points and the corresponding second characteristic points, otherwise, reserving the first characteristic points and the corresponding second characteristic points to obtain a plurality of characteristic point pairs.
6. The point cloud registration method of claim 4, wherein: the step of updating according to the first wolf set and the second wolf set to obtain the final rotation angle includes the following steps:
respectively calculating the distance between each first wolf and a second wolf to obtain a first distance, a second distance and a third distance;
updating the position of the second wolf according to the first distance, the second distance and the third distance, taking the rest second wolfs in the second wolf set as new second wolfs, returning to the step of respectively calculating the distance between each first wolf and one second wolf until the second wolfs in the second wolf set are updated, and finishing one iteration;
if the iteration times do not reach the preset iteration times, determining a new fitness value according to the first wolf and the updated second wolf, determining a new first wolf set and a new second wolf set according to the new fitness value, and returning to the step of respectively calculating the distance between each first wolf and one second wolf;
and if the iteration times reach the preset iteration times, taking the first wolf corresponding to the current minimum new fitness value as the final rotation angle.
7. The point cloud registration method of claim 1, wherein: the step of registering the first point cloud and the second point cloud according to the final rotation angle and the translation matrix comprises the following steps:
obtaining a final rotation matrix according to the final rotation angle;
and according to the final rotation matrix and the translation matrix, performing rotation and translation transformation on the first point cloud to obtain a registration point cloud registered with the second point cloud.
8. A system, comprising:
the acquisition module is used for acquiring a first point cloud and a second point cloud;
the translation module is used for obtaining a translation matrix according to the first point cloud and the second point cloud;
the determining module is used for determining a first wolf set and a second wolf set according to a preset population, the first point cloud and the second point cloud;
the updating module is used for updating according to the first wolf set and the second wolf set to obtain a final rotating angle;
the registration module is used for registering the first point cloud and the second point cloud according to the final rotation angle and the translation matrix;
the first point cloud is a point cloud to be registered, the second point cloud is a target point cloud, the preset population comprises a first wolf set and a second wolf set, the first wolf set comprises a plurality of first wolfs, the second wolf set comprises a plurality of second wolfs, and each first wolf and each second wolf comprise an initial rotation angle.
9. An apparatus, comprising:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the point cloud registration method of any of claims 1-7.
10. Storage medium, characterized in that it stores a program executed by a processor to perform the point cloud registration method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010288588.0A CN111553936B (en) | 2020-04-14 | 2020-04-14 | Point cloud registration method, system, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010288588.0A CN111553936B (en) | 2020-04-14 | 2020-04-14 | Point cloud registration method, system, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111553936A true CN111553936A (en) | 2020-08-18 |
| CN111553936B CN111553936B (en) | 2023-04-25 |
Family
ID=72003907
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010288588.0A Active CN111553936B (en) | 2020-04-14 | 2020-04-14 | Point cloud registration method, system, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111553936B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111951314A (en) * | 2020-08-21 | 2020-11-17 | 贝壳技术有限公司 | Point cloud registration method and device, computer readable storage medium and electronic equipment |
| CN112330661A (en) * | 2020-11-24 | 2021-02-05 | 交通运输部公路科学研究所 | Multi-period vehicle-mounted laser point cloud road change monitoring method |
| CN113689476A (en) * | 2021-08-26 | 2021-11-23 | 中国科学院植物研究所 | Point cloud registration method and device, storage medium and computer equipment |
| CN114387319A (en) * | 2022-01-13 | 2022-04-22 | 北京百度网讯科技有限公司 | Point cloud registration method, device, equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109345578A (en) * | 2018-10-15 | 2019-02-15 | 深圳步智造科技有限公司 | Point cloud registration method, system and readable storage medium storing program for executing based on Bayes's optimization |
| CN110473175A (en) * | 2019-07-26 | 2019-11-19 | 长春工程学院 | A kind of train axle space linearity measurement method |
-
2020
- 2020-04-14 CN CN202010288588.0A patent/CN111553936B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109345578A (en) * | 2018-10-15 | 2019-02-15 | 深圳步智造科技有限公司 | Point cloud registration method, system and readable storage medium storing program for executing based on Bayes's optimization |
| CN110473175A (en) * | 2019-07-26 | 2019-11-19 | 长春工程学院 | A kind of train axle space linearity measurement method |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111951314A (en) * | 2020-08-21 | 2020-11-17 | 贝壳技术有限公司 | Point cloud registration method and device, computer readable storage medium and electronic equipment |
| CN111951314B (en) * | 2020-08-21 | 2021-08-31 | 贝壳找房(北京)科技有限公司 | Point cloud registration method and device, computer readable storage medium and electronic equipment |
| CN112330661A (en) * | 2020-11-24 | 2021-02-05 | 交通运输部公路科学研究所 | Multi-period vehicle-mounted laser point cloud road change monitoring method |
| CN113689476A (en) * | 2021-08-26 | 2021-11-23 | 中国科学院植物研究所 | Point cloud registration method and device, storage medium and computer equipment |
| CN114387319A (en) * | 2022-01-13 | 2022-04-22 | 北京百度网讯科技有限公司 | Point cloud registration method, device, equipment and storage medium |
| CN114387319B (en) * | 2022-01-13 | 2023-11-14 | 北京百度网讯科技有限公司 | Point cloud registration method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111553936B (en) | 2023-04-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111553936B (en) | Point cloud registration method, system, device and storage medium | |
| CN106462963B (en) | System and method for being sketched outline automatically in adaptive radiation therapy | |
| WO2020211243A1 (en) | Behavior identification method and apparatus based on deep network technology, and storage medium | |
| Mora et al. | Computational analysis of distance operators for the iterative closest point algorithm | |
| CN111553985B (en) | O-graph pairing European three-dimensional reconstruction method and device | |
| CN112395886B (en) | Similar text determination method and related equipment | |
| CN111429494A (en) | Biological vision-based point cloud high-precision automatic registration method | |
| Wu et al. | Image edge detection based on local dimension: A complex networks approach | |
| CN113449724A (en) | Image text correction method, device, equipment and storage medium | |
| CN112364881B (en) | Advanced sampling consistency image matching method | |
| CN113065525A (en) | Age recognition model training method, face age recognition method and related device | |
| CN112884820A (en) | Method, device and equipment for training initial image registration and neural network | |
| CN116012241A (en) | Image distortion correction method, apparatus, computer device, and storage medium | |
| CN108597589B (en) | Model generation method, target detection method and medical imaging system | |
| CN115294086A (en) | Medical image segmentation method, segmentation model training method, medium, and electronic device | |
| CN116071404A (en) | Image registration method, device, computer equipment and storage medium | |
| CN114298999A (en) | Method for detecting vascular structure variation, readable storage medium, and program product | |
| CN115661218B (en) | Virtual super-point-based laser point cloud registration method and system | |
| CN117274072A (en) | Point cloud denoising method and device based on two-dimensional multi-modal range image | |
| CN109767468B (en) | Visceral volume detection method and device | |
| CN116228753A (en) | Tumor prognosis evaluation method, device, computer equipment and storage medium | |
| CN108205805B (en) | Automatic establishment method for dense correspondence of cone beam CT image intermediate pixels | |
| CN115641324A (en) | Cervical vertebra key point prediction method and system, electronic equipment and storage medium | |
| CN111009029B (en) | Data processing method and device for three-dimensional reconstruction, electronic equipment and storage medium | |
| CN114119952A (en) | Image matching method and device based on edge information |
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 |