CN113344123B - Point cloud frame matching method, device, equipment and storage medium - Google Patents
Point cloud frame matching method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113344123B CN113344123B CN202110729474.XA CN202110729474A CN113344123B CN 113344123 B CN113344123 B CN 113344123B CN 202110729474 A CN202110729474 A CN 202110729474A CN 113344123 B CN113344123 B CN 113344123B
- Authority
- CN
- China
- Prior art keywords
- point cloud
- detection
- frame
- matched
- ray
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000001514 detection method Methods 0.000 claims abstract description 303
- 238000004590 computer program Methods 0.000 claims description 14
- 238000000638 solvent extraction Methods 0.000 claims description 10
- 238000005192 partition Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 7
- 239000011159 matrix material Substances 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 101100517651 Caenorhabditis elegans num-1 gene Proteins 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The application relates to the technical field of point cloud processing, and provides a point cloud frame matching method, a device, equipment and a storage medium. The method specifically comprises the following steps: acquiring a plurality of point cloud frames obtained by detection of detection ray beams emitted by a detection source; carrying out distance distribution statistics on point clouds obtained by detecting each detection ray in the detection ray bundle in each point cloud frame based on the distance between each point and the detection source, and obtaining a point cloud distance distribution statistical result corresponding to each detection ray in each point cloud frame; and matching each point Yun Zhen based on the inter-frame comparison of the point cloud distance distribution statistical result corresponding to the point cloud frame of the same detection ray in the same detection ray bundle.
Description
Technical Field
The present application relates to the field of point cloud processing technologies, and in particular, to a method, an apparatus, a computer device, and a storage medium for matching point cloud frames.
Background
With the development of the point cloud processing technology, the construction technology of the point cloud high-precision map appears. One part of the point cloud high-precision map is constructed by detecting the surrounding environment and obtaining corresponding point clouds; in order to detect the surrounding environment and obtain a corresponding point cloud, a detection source can be utilized to emit a detection ray beam to the surrounding environment; and, as the detection continues, point cloud frames corresponding to different detection times may be formed.
To determine whether the current detection environment is the same as the previous detection environment, the point cloud frame at the current detection time may be matched with the point cloud frame at the historical detection time. How to guarantee the accuracy of the point cloud frame matching is a technical problem to be solved.
Disclosure of Invention
Based on the foregoing, it is necessary to provide a point cloud frame matching method, a device, a computer device and a storage medium for solving the above technical problems.
A method of point cloud frame matching, the method comprising:
Acquiring a plurality of point cloud frames obtained by detection of detection ray beams emitted by a detection source;
Respectively carrying out distance distribution statistics on point clouds obtained by detecting each detection ray in the detection ray bundle in each point cloud frame based on the distance between the point in each point cloud frame and the detection source, and obtaining a point cloud distance distribution statistical result corresponding to each detection ray in each point cloud frame;
And matching each point Yun Zhen based on the inter-frame comparison of the point cloud distance distribution statistical result corresponding to the point cloud frame of the same detection ray in the detection ray bundle.
In one embodiment, the calculating the distance distribution of the point clouds detected by each detection ray in the detection ray bundle in each point cloud frame based on the distance between the point in each point cloud frame and the detection source to obtain the statistical result of the distance distribution of the point clouds corresponding to each detection ray in each point cloud frame includes:
Determining a plurality of statistical distance segments of the pre-partition;
Obtaining the number of points of the point cloud of each point cloud frame corresponding to each statistical distance section based on the distance between the points in the point cloud frame and the detection source;
And obtaining the point cloud distance distribution statistical result according to the number of points of the point cloud frame corresponding to each statistical distance segment.
In one embodiment, the determining the pre-divided plurality of statistical distance segments includes:
Dividing the plurality of statistical distance segments for each detection ray according to the wire harness density state corresponding to the position of each detection ray in the detection ray beam.
In one embodiment, the detection beam includes dense detection rays and sparse detection rays; the dense detection rays have a smaller statistical distance partitioning interval than the statistical distance partitioning interval of the sparse detection rays.
In one embodiment, the obtaining the statistical result of the distance distribution of the point cloud according to the number of points of the point cloud frame corresponding to each statistical distance segment includes:
Aiming at the point cloud of each detection ray in each point cloud frame, taking the ratio of the number of points of the point cloud corresponding to each statistical distance section to the total number of points of a single frame as the statistical result of the point cloud distance distribution;
wherein the Shan Zhen total points are the sum of the number of points of each detection ray in each point cloud frame.
In one embodiment, the matching the each point Yun Zhen based on the inter-frame comparison of the statistical result of the distribution of the point cloud distances corresponding to the point cloud frames of the same detection ray in the detection ray bundle includes:
Based on the inter-frame comparison of the point cloud distance distribution statistical result corresponding to the same detection ray in the detection ray bundle at each point cloud frame, obtaining a point cloud frame similarity comparison result corresponding to each detection ray in the detection ray bundle;
counting a first number of dense detection rays with similar point cloud frame similarity comparison results of point cloud frames to be matched, and counting a second number of sparse detection rays with similar point cloud frame similarity comparison results of the point cloud frames to be matched;
and determining whether the point cloud frames to be matched are matched according to the first quantity and the second quantity.
In one embodiment, the determining whether the point cloud frames to be matched are matched according to the first number and the second number includes:
and determining whether the point cloud frames to be matched are matched according to a first ratio of the first quantity to the total number of the dense detection rays contained in the detection ray beams and a second ratio of the second quantity to the total number of the sparse detection rays contained in the detection ray beams.
A point cloud frame matching apparatus, the apparatus comprising:
The point cloud frame acquisition module is used for acquiring a plurality of point cloud frames obtained by detection of detection ray beams sent by the detection source;
The point cloud distance distribution statistics module is used for respectively carrying out distance distribution statistics on point clouds obtained by detecting each detection ray in the detection ray bundle in each point cloud frame based on the distance between the point in each point cloud frame and the detection source, and obtaining a point cloud distance distribution statistics result corresponding to each detection ray in each point cloud frame;
And the inter-frame comparison module is used for matching the points Yun Zhen based on inter-frame comparison of the distribution statistical result of the point cloud distance corresponding to the point cloud frame of the same detection ray in the detection ray bundle.
A computer device comprising a memory storing a computer program and a processor implementing the method described above when executing the computer program.
A computer readable storage medium having stored thereon a computer program which when executed by a processor implements the method described above.
The method, the device, the computer equipment and the storage medium for matching the point cloud frame mainly comprise the following steps: acquiring a plurality of point cloud frames obtained by detection of detection ray beams emitted by a detection source; respectively carrying out distance distribution statistics on point clouds obtained by detecting each detection ray in the detection ray bundle in each point cloud frame based on the distance between the point in each point cloud frame and the detection source, and obtaining a point cloud distance distribution statistical result corresponding to each detection ray in each point cloud frame; and matching each point Yun Zhen based on the inter-frame comparison of the point cloud distance distribution statistical result corresponding to the point cloud frame of the same detection ray in the detection ray bundle. According to the application, from the processing angle of each detection ray in the detection ray bundle, the distance distribution statistics is respectively carried out on the point clouds obtained by detecting each detection ray in each point cloud frame based on the distance between each point and the detection source, and the inter-frame comparison of the point cloud distance distribution statistics results corresponding to each point cloud frame based on the same detection ray is carried out, so that finer matching among the point cloud frames is realized, and the accuracy of the matching of the point cloud frames is improved.
Drawings
FIG. 1 is a schematic diagram of a detection beam emitted by a detection source in one embodiment;
FIG. 2 is a flow chart of a method for matching point cloud frames according to an embodiment;
FIG. 3 is a schematic diagram of a distance matrix corresponding to a point cloud frame in one embodiment;
FIG. 4 is a schematic diagram of a statistical result of a point cloud distance distribution corresponding to each detected ray in each point cloud frame in an embodiment;
FIG. 5 is a distance distribution histogram for characterizing point cloud distance distribution statistics R a1 in one embodiment;
FIG. 6 is a schematic diagram of a detection beam including sparse detection rays and dense detection rays in one embodiment;
FIG. 7 is a histogram of distance distribution for densely detected rays and a histogram of distance distribution for densely detected rays in one embodiment;
FIG. 8 is a statistical diagram of a distribution of the point cloud distances corresponding to the 64 detected rays in the point cloud frame t a in one embodiment;
FIG. 9 is a block diagram of a point cloud frame matching device in one embodiment;
fig. 10 is an internal structural view of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the described embodiments of the application may be combined with other embodiments.
The application provides a point cloud frame matching method which can be applied to computer equipment; the method comprises the steps of:
Step S201, a plurality of point cloud frames obtained by detection of detection ray beams emitted by a detection source are obtained;
As shown in fig. 1, in the process of performing point cloud acquisition by using a detection device such as a laser radar, a detection source O of the detection device emits a detection beam; the detection beam includes at least one detection ray, and the detection angle of each detection ray included in the detection beam in the vertical direction is different (the vertical direction may be a direction perpendicular to a preset plane such as the ground, for example, a z-axis direction shown in fig. 1), that is, a detection ray emitted from the detection source toward a certain detection angle in the vertical direction may be regarded as one detection ray.
More specifically, the detection source O of the detection device continuously rotates around the z-axis to emit a detection beam and obtain a point cloud; the point cloud obtained by rotating the detection source O around the z axis once can be regarded as one point cloud frame, and a plurality of point cloud frames can be obtained under the condition that the detection source O rotates around the z axis for a plurality of times.
One rotation of the detection source O around the z-axis corresponds to a 360 rotation of the detection beam in a horizontal plane perpendicular to the z-axis. Based on the distance between the point of each point cloud frame and the detection source O, a distance matrix corresponding to each point cloud frame can be formed, wherein the distance between the point obtained by rotating the same detection ray from 0 to 360 degrees in the horizontal direction and the detection source O can be in the same row; as shown in fig. 3, distances (m, 1) and … … between a point obtained when the rotation angle of the detection ray m in the horizontal direction is 0 ° and the detection source O, distances (m, e) and … … between a point obtained when the rotation angle of the detection ray in the horizontal direction is 180 ° and the detection source O, and distances (m, g) between a point obtained when the rotation angle of the detection ray in the horizontal direction is 360 ° exist in the same line.
Step S202, respectively carrying out distance distribution statistics on point clouds obtained by detecting each detection ray in the detection ray bundle in each point cloud frame based on the distance between the point in each point cloud frame and the detection source, and obtaining a point cloud distance distribution statistical result corresponding to each detection ray in each point cloud frame;
Because the points in the point cloud frames are detected by the detection rays of the detection ray beams, the points in the point cloud frames can be divided according to the angles of the detection rays, so that the point cloud detected by the detection rays is obtained; for example, if the detection beam includes detection rays 1 to m shown in fig. 1, and the points of the points Yun Zhen t a are divided according to the angles of the detection rays, then the point cloud detected by the detection ray 1, the point cloud detected by the detection ray i, and the point cloud detected by the detection ray m in the point cloud frame t a may be determined.
Then, respectively carrying out distance distribution statistics on the point cloud obtained by detecting each detection ray in the point cloud frame t a to obtain a point cloud distance distribution statistical result corresponding to each detection ray in the point cloud frame t a; for example, as shown in fig. 4, the statistical results of the distribution of the point cloud distances corresponding to the point cloud frame t a of the detected ray 1, the detected ray i, and the detected ray m are R a1、Rai、Ram respectively.
More specifically, in the case that the point cloud frame t a has a corresponding Distance matrix, the distances of each row in the Distance matrix may be respectively counted in a distribution manner, for example, the distances (m, 1) to (m, g) of the mth row are counted in a distribution manner, so as to obtain a point cloud Distance distribution statistic result R am corresponding to the point cloud frame t a of the detected ray m.
Step S203, matching the points Yun Zhen based on the inter-frame comparison of the distribution statistics result of the point cloud distance corresponding to the point cloud frame of the same detection ray in the detection ray bundle.
Taking the point cloud frame t a and the point cloud frame t b as examples, the following steps are described: as shown in fig. 4, after the statistics of the distribution of the point cloud distances of each detection ray of the detection ray bundle corresponding to the point cloud frame t a and the point cloud frame t b is obtained according to the above step S202, the statistics of the distribution of the point cloud distances of the same detection ray corresponding to the point cloud frame t a and the point cloud frame t b are compared, for example, the statistics of the distribution of the point cloud distance R a1 and the statistics of the distribution of the point cloud distance R b1 are compared, and the statistics of the distribution of the point cloud distance R am and the statistics of the distribution of the point cloud distance R bm are compared; note that, since the comparison of the point cloud distance distribution statistics results is between the point cloud frames, the comparison may be referred to as an inter-frame comparison.
Based on the comparison of the statistical results of the point cloud distance distribution of the same detection ray corresponding to the point cloud frame t a and the point cloud frame t b, whether the point cloud obtained by detecting the same detection ray in the point cloud frame t a is similar to the point cloud distance distribution obtained by detecting the same detection ray in the point cloud frame t b or not can be determined, and the point cloud frame similarity comparison result corresponding to the same detection ray is obtained. And then, counting the similarity comparison results of the point cloud frames corresponding to the detection rays, and determining whether the point cloud frames t a and t b are matched.
According to the point cloud frame matching method, from the processing angle of each detection ray in the detection ray bundle, the distance distribution statistics is respectively carried out on the point clouds obtained by detecting each detection ray in each point cloud frame based on the distance between the point of each point cloud frame and the detection source, and based on the inter-frame comparison of the point cloud distance distribution statistics results corresponding to the same detection ray in each point cloud frame, finer matching among the point cloud frames is realized, and the accuracy of the point cloud frame matching is improved.
In one embodiment, step S202 may further include the steps of: determining a plurality of statistical distance segments of the pre-partition; obtaining the number of points of the point cloud of each point cloud frame corresponding to each statistical distance section based on the distance between the points in the point cloud frame and the detection source; and obtaining the point cloud distance distribution statistical result according to the number of points of the point cloud frame corresponding to each statistical distance segment.
Taking the statistical result R a1 of the point cloud distance distribution corresponding to the point cloud frame t a of the detected ray 1 as an example description: dividing a preset statistical total distance according to a preset statistical distance dividing interval to obtain a plurality of statistical distance segments S 1 to S n; next, for the point cloud detected by the detection ray 1 in the point cloud frame t a, the number of points of each of the statistical distance segments S 1 to S n is determined based on the distance between the point of the point cloud and the detection source O, and a point cloud distance distribution statistical result R a1 represented by the distance distribution histogram shown in fig. 5 is formed.
In the above embodiment, the corresponding point cloud distance distribution statistical result is formed based on the number of points of the point cloud frame, where the point cloud corresponds to each statistical distance segment, so that the accuracy of the point cloud distance distribution statistics can be improved.
In the detection ray beams of some scenes, the detection rays are uniformly distributed (i.e. the detection angle difference between any two adjacent detection rays in the vertical direction is the same), and the positions of the detection rays in the detection ray beams correspond to the uniform state of the wire harness, so that each detection ray can be called as uniform detection ray; for example, if the detection angle difference between each detection ray and the detection ray adjacent to each detection ray shown in fig. 1 in the vertical direction is θ, the detection ray beam of fig. 1 may be said to correspond to a wire harness uniformity state.
In the detection beams of some scenes, as shown in fig. 6, a part of detection rays are sparsely distributed (that is, the detection angle difference between any two adjacent detection rays in the vertical direction is large), and the positions of the detection rays of the part of detection rays in the detection beams correspond to the sparse state of the wire harness, so that the part of detection rays can be called sparse detection rays; the other part of the detection rays are densely distributed (namely, the detection angle difference between any two adjacent detection rays in the vertical direction is smaller), and the positions of the detection rays of the part of the detection rays in the detection ray bundle correspond to the dense state of the wire bundles, so that the part of the detection rays can be called as dense detection rays.
For a detection ray bundle comprising dense detection rays and sparse detection, when determining a plurality of statistical distance segments which are divided in advance, dividing the plurality of statistical distance segments for each detection ray according to a wire bundle density state corresponding to the position of each detection ray in the detection ray bundle.
In the above embodiment, different statistical distance segments are respectively divided for the dense detection rays and the sparse detection rays, so that the point cloud distance statistics are adapted to the wire harness sparse and dense state of the detection rays, and the accuracy of the point cloud distance distribution statistics and the accuracy of the point cloud frame matching are further improved.
Still further, the dense detection rays have a smaller statistical distance partitioning interval than the statistical distance partitioning interval of the sparse detection rays.
That is, the statistical distance dividing interval of the densely detected rays is smaller than the statistical distance dividing interval of the sparsely detected rays; as shown in fig. 7, the distance statistical range of the statistical distance segment S m1 formed at the smaller statistical distance division interval is smaller than the distance statistical range of S x1 formed at the larger statistical distance division interval.
In the above embodiment, the statistical distance dividing interval of the densely detected rays is smaller than the statistical distance dividing interval of the sparsely detected rays, so that the distance statistics of the point clouds obtained by detecting the densely detected rays is finer, and the accuracy of the point cloud distance distribution statistics and the accuracy of the point cloud frame matching are further improved.
In an embodiment, the step of obtaining the statistical result of the distance distribution of the point cloud according to the number of points of the point cloud frame corresponding to each statistical distance segment may further include the following steps: aiming at the point cloud of each detection ray in each point cloud frame, taking the ratio of the number of points of the point cloud corresponding to each statistical distance section to the total number of points of a single frame as the statistical result of the point cloud distance distribution; wherein the Shan Zhen total points are the sum of the number of points of each detection ray in each point cloud frame.
The above embodiment is described in connection with fig. 5: for the point cloud obtained by detecting the point Yun Zhen t a by the detection ray 1, the number of the points in the statistical distance segments S 1 to S n can be determined based on the distance between the point of the point cloud and the detection source O and respectively marked as Num1, … … and Numn, correspondingly, the sum of the number of the points of the detection ray 1 in the point cloud frame t a, namely the total number of single-frame points of the detection ray 1 corresponding to the Yu Dianyun frame t a is Nums =num 1+ … … + Numn; then, the ratio of the number of the points of each statistical distance section to the total point number of the single frame is determined, and a point cloud distance distribution statistical result of the corresponding distance distribution histogram is formed.
In the above embodiment, since the detection rays of the detection beam are independent from each other, the detection rays are normalized by taking the detection rays as units, so that the inter-frame comparison between the statistical results of the point cloud distance distribution is within a certain numerical range, and the inter-frame comparison efficiency is improved.
When the point cloud frame similarity comparison result corresponding to each detection ray is counted and whether the point cloud frames to be matched are matched or not is determined, the method can be realized by the following steps: if the point cloud frame similarity comparison results corresponding to the detection rays larger than or equal to the number threshold are similar, the point cloud frame to be matched can be determined to be matched.
Further, for the detection ray bundles shown in fig. 6, when counting the similarity comparison result of the point cloud frames corresponding to each detection ray bundle, determining whether the point cloud frames to be matched are matched or not can be realized in the following manner: based on the inter-frame comparison of the point cloud distance distribution statistical result corresponding to the same detection ray in the detection ray bundle at each point cloud frame, obtaining a point cloud frame similarity comparison result corresponding to each detection ray in the detection ray bundle; counting a first number of dense detection rays with similar point cloud frame similarity comparison results of point cloud frames to be matched, and counting a second number of sparse detection rays with similar point cloud frame similarity comparison results of the point cloud frames to be matched; and determining whether the point cloud frames to be matched are matched according to the first quantity and the second quantity.
In the above manner, a first number of dense detection rays with similar point cloud frame similarity comparison results and a second number of sparse detection rays with similar point cloud frame similarity comparison results are respectively counted; if the first number is greater than the second number, then it may be determined that the point cloud frames to be matched match.
Further, whether the point cloud frames to be matched are matched can be determined according to a first ratio of the first quantity to the total number of the dense detection rays contained in the detection ray beams and a second ratio of the second quantity to the total number of the sparse detection rays contained in the detection ray beams.
The above manner is described taking the example that the detection beam includes 70 dense detection rays and 30 sparse detection rays: if the first number of the dense detection rays with similar point cloud frame similarity comparison results is 65 and the second number of the sparse detection rays with similar point cloud frame similarity comparison results is 25, the first ratio can be determined to be 65/70, and the second ratio can be determined to be 25/30. Then, determining whether the point cloud frames to be matched are matched according to the first ratio and the second ratio; for example, if the first ratio is greater than the second ratio, it may be determined that the point cloud frames to be matched match; for another example, if the first ratio is greater than the first ratio threshold and the second ratio is greater than the second ratio threshold, it may be determined that the point cloud frames to be matched match.
In the embodiment, whether the point cloud frames to be matched are matched or not is determined by combining the wire harness sparse and dense state corresponding to the detection rays, so that the accuracy of the point cloud frame matching is further improved.
In order to better understand the above method, an application example of the point cloud frame matching method of the present application is described below. In the application example, the detection ray beam emitted by the detection source comprises 64 detection rays, the statistical distance dividing interval is 0.5 meter, and 128 statistical distance segments are recorded as S 1、……、S128 respectively.
After the point clouds detected by each detected ray in the point cloud frame t a are obtained, the distance distribution statistics is performed on the point clouds detected by the same detected ray, so that the number of points of the point clouds detected by the same detected ray corresponding to each statistical distance segment, for example, the number of points of the point clouds detected by the detected ray 1 corresponding to each statistical distance segment, can be determined. Next, according to the number of points of the point cloud corresponding to each statistical distance segment obtained by detecting each detection ray, a statistical result of the point cloud distance distribution as shown in fig. 8 can be formed; wherein,The number of points characterized by these 4 different lattices is gradually increased.
Then, the statistical result of the point cloud distance distribution of the point cloud frame t a may be stored, and based on the comparison of the statistical result of the point cloud distance distribution of the same detection ray corresponding to the point cloud frame ta and other point cloud frames, it is determined whether the point cloud frame t a is matched with other point cloud frames.
According to the embodiment, from the processing angle of each detection ray in the detection ray bundle, the distance distribution statistics is respectively carried out on the point clouds obtained by detecting each detection ray in each point cloud frame based on the distance between the point of each point cloud frame and the detection source, and based on the inter-frame comparison of the point cloud distance distribution statistics results corresponding to the same detection ray in each point cloud frame, finer matching among the point cloud frames is realized, and the accuracy of the matching of the point cloud frames is improved.
It should be understood that, although the steps of the flowchart of fig. 2 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least a portion of the steps in fig. 2 may include a plurality of steps or stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily sequential, but may be performed in rotation or alternatively with at least a portion of the steps or stages in other steps or other steps.
In one embodiment, as shown in fig. 9, there is provided a point cloud frame matching apparatus, including:
the point cloud frame acquisition module 901 is used for acquiring a plurality of point cloud frames obtained by detection of detection ray beams sent by a detection source;
The point cloud distance distribution statistics module 902 is configured to respectively perform distance distribution statistics on a point cloud obtained by detecting each detection ray in the detection ray bundle in each point cloud frame based on a distance between a point in each point cloud frame and the detection source, so as to obtain a point cloud distance distribution statistics result corresponding to each detection ray in each point cloud frame;
the inter-frame comparison module 903 is configured to match the points Yun Zhen based on inter-frame comparison of the distribution statistics result of the point cloud distance corresponding to the point cloud frame of the same detection ray in the detection ray bundle.
In one embodiment, the point cloud distance distribution statistics module 902 is further configured to determine a plurality of pre-divided statistical distance segments; obtaining the number of points of the point cloud of each point cloud frame corresponding to each statistical distance section based on the distance between the points in the point cloud frame and the detection source; and obtaining the point cloud distance distribution statistical result according to the number of points of the point cloud frame corresponding to each statistical distance segment.
In one embodiment, the point cloud distance distribution statistics module 902 is further configured to divide the plurality of statistical distance segments for each detected ray according to a wire harness density state corresponding to a position of the detected ray in the detected ray bundle.
In one embodiment, the detection beam includes dense detection rays and sparse detection rays; the dense detection rays have a smaller statistical distance partitioning interval than the statistical distance partitioning interval of the sparse detection rays.
In one embodiment, the inter-frame comparison module 903 is further configured to, for each point cloud frame of each detected ray, use a ratio of a number of points of the point cloud corresponding to each statistical distance segment to a total number of points of a single frame as the statistical result of the distribution of the distance between the point clouds; wherein the Shan Zhen total points are the sum of the number of points of each detection ray in each point cloud frame.
In one embodiment, the inter-frame comparison module 903 is further configured to obtain a similar comparison result of the point cloud frame corresponding to each detection ray in the detection ray bundle based on an inter-frame comparison of the statistical result of the distribution of the point cloud distances of the same detection ray in the detection ray bundle corresponding to the point cloud frames; counting a first number of dense detection rays with similar point cloud frame similarity comparison results of point cloud frames to be matched, and counting a second number of sparse detection rays with similar point cloud frame similarity comparison results of the point cloud frames to be matched; and determining whether the point cloud frames to be matched are matched according to the first quantity and the second quantity.
In one embodiment, the inter-frame comparison module 903 is further configured to determine whether the point cloud frame to be matched is matched according to a first ratio of the first number to a total number of dense detection rays contained in the detection beam and a second ratio of the second number to a total number of sparse detection rays contained in the detection beam.
For specific limitation of the point cloud frame matching device, reference may be made to the limitation of the point cloud frame matching method hereinabove, and no further description is given here. The modules in the point cloud frame matching device can be all or partially realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, the internal structure of which may be as shown in FIG. 10. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing point cloud frame matching data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by a processor implements a point cloud frame matching method.
It will be appreciated by those skilled in the art that the structure shown in FIG. 10 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory storing a computer program and a processor implementing the steps of the method embodiments described above when the processor executes the computer program.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of the respective method embodiments described above.
Those skilled in the art will appreciate that implementing all or part of the above-described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, or the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration, and not limitation, RAM can be in various forms such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (10)
1. A method for matching point cloud frames, the method comprising:
Acquiring a plurality of point cloud frames obtained by detection of detection ray beams emitted by a detection source;
Determining a plurality of statistical distance segments of the pre-partition;
Obtaining the number of points of the point cloud of each point cloud frame corresponding to each statistical distance section based on the distance between the points in the point cloud frame and the detection source;
Aiming at the point cloud of each detection ray in each point cloud frame, taking the ratio of the number of points of the point cloud corresponding to each statistical distance section to the total number of points of a single frame as a point cloud distance distribution statistical result; wherein the Shan Zhen total points are the sum of the points of each detection ray in each point cloud frame;
Based on the inter-frame comparison of the point cloud distance distribution statistical result corresponding to the same detection ray in the detection ray bundle at each point cloud frame, obtaining a point cloud frame similarity comparison result corresponding to each detection ray in the detection ray bundle;
counting a first number of dense detection rays with similar point cloud frame similarity comparison results of point cloud frames to be matched, and counting a second number of sparse detection rays with similar point cloud frame similarity comparison results of the point cloud frames to be matched;
determining whether the point cloud frames to be matched are matched according to the first quantity and the second quantity comprises the following steps: and if the first quantity is larger than the second quantity, determining that the point cloud frames to be matched are matched.
2. The method of claim 1, wherein the determining the pre-partitioned plurality of statistical distance segments comprises:
Dividing the plurality of statistical distance segments for each detection ray according to the wire harness density state corresponding to the position of each detection ray in the detection ray beam.
3. The method of claim 2, wherein the detection beam comprises dense detection rays and sparse detection rays; the dense detection rays have a smaller statistical distance partitioning interval than the statistical distance partitioning interval of the sparse detection rays.
4. The method of claim 1, wherein determining whether the point cloud frames to be matched match according to the first number and the second number further comprises:
acquiring a first ratio of the first number to the total number of dense detection rays contained in the detection beam and a second ratio of the second number to the total number of sparse detection rays contained in the detection beam;
if the first ratio is larger than the second ratio, determining that the point cloud frames to be matched are matched;
Or if the first ratio is greater than a first ratio threshold and the second ratio is greater than a second ratio threshold, determining that the point cloud frames to be matched are matched.
5. A point cloud frame matching apparatus, the apparatus comprising:
The point cloud frame acquisition module is used for acquiring a plurality of point cloud frames obtained by detection of detection ray beams sent by the detection source;
The point cloud distance distribution statistical module is used for determining a plurality of pre-divided statistical distance segments; obtaining the number of points of the point cloud of each point cloud frame corresponding to each statistical distance section based on the distance between the points in the point cloud frame and the detection source; aiming at the point cloud of each detection ray in each point cloud frame, taking the ratio of the number of points of the point cloud corresponding to each statistical distance section to the total number of points of a single frame as a point cloud distance distribution statistical result; wherein the Shan Zhen total points are the sum of the points of each detection ray in each point cloud frame;
The inter-frame comparison module is used for obtaining a point cloud frame similarity comparison result corresponding to each detection ray in the detection ray bundle based on inter-frame comparison of the point cloud distance distribution statistical result corresponding to the same detection ray in the detection ray bundle at each point cloud frame; counting a first number of dense detection rays with similar point cloud frame similarity comparison results of point cloud frames to be matched, and counting a second number of sparse detection rays with similar point cloud frame similarity comparison results of the point cloud frames to be matched; determining whether the point cloud frames to be matched are matched according to the first quantity and the second quantity;
According to the first quantity and the second quantity, determining whether the point cloud frames to be matched are matched comprises: and if the first quantity is larger than the second quantity, determining that the point cloud frames to be matched are matched.
6. The apparatus of claim 5, wherein the point cloud distance distribution statistics module is further configured to: dividing the plurality of statistical distance segments for each detection ray according to the wire harness density state corresponding to the position of each detection ray in the detection ray beam.
7. The apparatus of claim 6, wherein the detection beam comprises dense detection rays and sparse detection rays; the dense detection rays have a smaller statistical distance partitioning interval than the statistical distance partitioning interval of the sparse detection rays.
8. The apparatus of claim 5, wherein the determining whether the point cloud frames to be matched match according to the first number and the second number further comprises:
acquiring a first ratio of the first number to the total number of dense detection rays contained in the detection beam and a second ratio of the second number to the total number of sparse detection rays contained in the detection beam;
if the first ratio is larger than the second ratio, determining that the point cloud frames to be matched are matched;
Or if the first ratio is greater than a first ratio threshold and the second ratio is greater than a second ratio threshold, determining that the point cloud frames to be matched are matched.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the method of any one of claims 1 to 4 when executing the computer program.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110729474.XA CN113344123B (en) | 2021-06-29 | 2021-06-29 | Point cloud frame matching method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110729474.XA CN113344123B (en) | 2021-06-29 | 2021-06-29 | Point cloud frame matching method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113344123A CN113344123A (en) | 2021-09-03 |
| CN113344123B true CN113344123B (en) | 2024-05-14 |
Family
ID=77481470
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110729474.XA Active CN113344123B (en) | 2021-06-29 | 2021-06-29 | Point cloud frame matching method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113344123B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111275715A (en) * | 2020-01-14 | 2020-06-12 | 深圳前海达闼云端智能科技有限公司 | Point cloud segmentation method and device, electronic equipment, storage medium and robot |
| CN112105950A (en) * | 2019-09-27 | 2020-12-18 | 深圳市大疆创新科技有限公司 | Detection method of detection object, detection equipment and millimeter wave radar |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10762776B2 (en) * | 2016-12-21 | 2020-09-01 | Here Global B.V. | Method, apparatus, and computer program product for determining vehicle lane speed patterns based on received probe data |
| JP7263521B2 (en) * | 2019-03-22 | 2023-04-24 | テンセント・アメリカ・エルエルシー | Method and its apparatus and computer program for inter-frame point cloud attribute encoding |
-
2021
- 2021-06-29 CN CN202110729474.XA patent/CN113344123B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112105950A (en) * | 2019-09-27 | 2020-12-18 | 深圳市大疆创新科技有限公司 | Detection method of detection object, detection equipment and millimeter wave radar |
| CN111275715A (en) * | 2020-01-14 | 2020-06-12 | 深圳前海达闼云端智能科技有限公司 | Point cloud segmentation method and device, electronic equipment, storage medium and robot |
Non-Patent Citations (1)
| Title |
|---|
| 一种城市环境三维点云配准的预处理方法;赵凯;徐友春;王任栋;;光电工程;20181210(12);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113344123A (en) | 2021-09-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111950329B (en) | Target detection and model training method, device, computer equipment and storage medium | |
| CN112669463B (en) | Method for reconstructing curved surface of three-dimensional point cloud, computer device and computer-readable storage medium | |
| US9165179B1 (en) | Feature reduction based on local densities for bundle adjustment of images | |
| US10495761B2 (en) | Smart satellite distribution into ARAIM clusters for use in monitoring integrity of computed navigation solutions | |
| CN110766088B (en) | Method and device for analyzing vehicles in the same class and storage device | |
| CN109978006B (en) | Face image clustering method and device | |
| CN112684490B (en) | Energy spectrum partitioning method, device, computer equipment and storage medium | |
| CN113947206A (en) | Deep neural network quantification method, system, device and medium | |
| CN113344123B (en) | Point cloud frame matching method, device, equipment and storage medium | |
| CN111582378B (en) | Training generation method, position detection method and device of positioning recognition model | |
| US20170109462A1 (en) | System and a method for determining approximate set of visible objects in beam tracing | |
| CN112286780B (en) | Method, device, equipment and storage medium for testing recognition algorithm | |
| CN116137061A (en) | Training method and device for quantity statistical model, electronic equipment and storage medium | |
| CN108133234B (en) | Sparse subset selection algorithm-based community detection method, device and equipment | |
| CN113705270B (en) | Method, device, equipment and storage medium for identifying two-dimensional code positioning code area | |
| US20240143495A1 (en) | Method and apparatus for updating raid 5 check value, and medium | |
| CN113778518B (en) | Data processing method, device, computer equipment and storage medium | |
| US20150146877A1 (en) | System and a method for determining approximate set of visible objects in beam tracing | |
| CN115409070A (en) | Method, device and equipment for determining critical point of discrete data sequence | |
| CN115272248A (en) | Intelligent detection method for fan attitude and electronic equipment | |
| CN113902959A (en) | Image recognition method and device, computer equipment and storage medium | |
| CN112488528A (en) | Data set processing method, device, equipment and storage medium | |
| CN114693052A (en) | Risk prediction model training method and device, computing equipment and medium | |
| CN109490824B (en) | Position fingerprint information matching method and device, storage medium and terminal equipment | |
| CN113744331B (en) | Energy determination method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |