CN112764004B - Point cloud processing method, device, equipment and storage medium - Google Patents
Point cloud processing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112764004B CN112764004B CN202011534220.4A CN202011534220A CN112764004B CN 112764004 B CN112764004 B CN 112764004B CN 202011534220 A CN202011534220 A CN 202011534220A CN 112764004 B CN112764004 B CN 112764004B
- Authority
- CN
- China
- Prior art keywords
- point cloud
- cloud data
- voxel space
- space
- original 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.)
- Active
Links
- 238000003672 processing method Methods 0.000 title abstract description 10
- 238000002310 reflectometry Methods 0.000 claims abstract description 74
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000012545 processing Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 9
- 230000003287 optical effect Effects 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000005484 gravity Effects 0.000 description 4
- 238000002203 pretreatment Methods 0.000 description 4
- 239000013307 optical fiber Substances 0.000 description 3
- 230000002093 peripheral effect Effects 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 229910052739 hydrogen Inorganic materials 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000000280 densification Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000002542 deteriorative effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
- G01S7/4802—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a point cloud processing method, a device, equipment and a storage medium. The method comprises the following steps: determining position information and reflectivity of point clouds in the original point cloud data in space according to the point cloud original data; dividing the space where the point cloud is located to obtain at least one voxel space; acquiring first original point cloud data with a distance greater than or equal to a first set threshold value from a radar self coordinate system, and performing downsampling operation on the first original point cloud data according to a first voxel, position information and reflectivity; acquiring second original point cloud data with a distance smaller than a second set threshold value from a radar self coordinate system, and performing downsampling operation on the second original point cloud data according to a second voxel, the position information and the reflectivity; and determining point cloud data obtained by downsampling the first original point cloud data, the first original point cloud data and the point cloud data obtained by downsampling the second original point cloud data as target point cloud data.
Description
Technical Field
The embodiment of the invention relates to a data processing technology, in particular to a point cloud processing method, a device, equipment and a storage medium.
Background
The laser radar is a safe and intelligent core high-end sensor for vehicles, and has the advantages of all-weather operation, long measurement distance and high ranging precision. Lidar sensors are capable of feeding back millions of points in the real world to the perception system in real time. There are many methods for processing point cloud data, which are roughly classified into three types: voxelization, conversion to an image, direct point cloud operation. The voxelization is a method for converting point cloud data into a space grid and then calculating the point cloud data in the space grid by using a convolution method; after converting the laser radar into an image, a mature image processing tool exists, but a part of information is sacrificed when converting the point cloud into the image; the method of direct point cloud operation has yet to be studied due to the unordered feasibility of point clouds.
The laser radar is an indispensable sensor for finally realizing automatic driving, however, in the process of using the laser radar, the laser radar is found to have extremely high density of near point clouds, but the problem that the number of the point clouds decays rapidly along with the distance, so that the far point clouds are sparse. If the original point cloud is directly used for target identification, excessive computing power is distributed to process the near point cloud, and the near point cloud has excessive density, so that the computing power and the algorithm operation efficiency are wasted. Conversely, the sparseness of the far point cloud can cause the missing detection phenomenon of target identification.
The current point cloud preprocessing works to reduce the amount of data mainly in the form of downsampling. In general, the downsampling is performed by constructing a three-dimensional voxel grid, and then displaying other points in the voxels by using the centers of gravity of all points in the voxels in each voxel, so that all points in the voxels are represented by a center of gravity point, and the downsampling is performed to achieve the filtering effect, thereby greatly reducing the data volume, simultaneously maintaining the shape characteristics of the point cloud, and improving the running speed of the program without obviously deteriorating the final recognition effect. The existing point cloud preprocessing method does not enrich the remote sparse point cloud.
Disclosure of Invention
The embodiment of the invention provides a point cloud processing method, a device, equipment and a storage medium, which can be used for respectively adopting different pretreatment methods for near and far point clouds and simultaneously solving the problems that the quantity of the near point clouds is huge, the efficiency is influenced, and the remote point clouds are sparse and easy to miss.
In a first aspect, an embodiment of the present invention provides a point cloud processing method, including:
Determining position information and reflectivity of point clouds in the original point cloud data in space according to the point cloud original data;
dividing the space in which the point cloud is located to obtain at least one voxel space, wherein the voxel space comprises a first voxel space and a second voxel space, the first voxel space is larger than the second voxel space, the first voxel space is a voxel space with a distance from a self coordinate system of the radar being larger than or equal to a first set threshold value, the second voxel space is a voxel space with a distance from the self coordinate system of the radar being smaller than a second set threshold value, and the second set threshold value is smaller than or equal to the first set threshold value;
Acquiring first original point cloud data with a distance greater than or equal to a first set threshold value from a radar self coordinate system, and performing downsampling operation on the first original point cloud data according to a first voxel space, the position information and the reflectivity;
Acquiring second original point cloud data with a distance smaller than a second set threshold value from a radar self coordinate system, and performing downsampling operation on the second original point cloud data according to a second voxel space, the position information and the reflectivity;
and determining point cloud data obtained by downsampling the first original point cloud data, the first original point cloud data and the point cloud data obtained by downsampling the second original point cloud data as target point cloud data.
In a second aspect, an embodiment of the present invention further provides a point cloud processing apparatus, where the apparatus includes:
The first determining module is used for determining the position information and the reflectivity of the point cloud in the original point cloud data in space according to the point cloud original data;
the division module is used for dividing the space where the point cloud is located to obtain at least one voxel space, wherein the voxel space comprises a first voxel space and a second voxel space, the first voxel space is larger than the second voxel space, the first voxel space is a voxel space with a distance from a self coordinate system of the radar being larger than or equal to a first set threshold value, the second voxel space is a voxel space with a distance from the self coordinate system of the radar being smaller than a second set threshold value, and the second set threshold value is smaller than or equal to the first set threshold value;
The first acquisition module is used for acquiring first original point cloud data with the distance from a radar self coordinate system being greater than or equal to a first set threshold value, and performing downsampling operation on the first original point cloud data according to a first voxel space, the position information and the reflectivity;
The second acquisition module is used for acquiring second original point cloud data with the distance from a radar self coordinate system smaller than a second set threshold value, and performing downsampling operation on the second original point cloud data according to a second voxel space, the position information and the reflectivity;
And the second determining module is used for determining the point cloud data obtained by downsampling the first original point cloud data, the first original point cloud data and the point cloud data obtained by downsampling the second original point cloud data as target point cloud data.
In a third aspect, embodiments of the present invention further provide a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing a method according to any of the embodiments of the present invention when executing the program.
In a fourth aspect, embodiments of the present invention also provide a computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, implements a method according to any of the embodiments of the present invention.
According to the embodiment of the invention, the position information and the reflectivity of the point cloud in the original point cloud data in space are determined according to the point cloud original data; dividing the space in which the point cloud is located to obtain at least one voxel space, wherein the voxel space comprises a first voxel space and a second voxel space, the first voxel space is larger than the second voxel space, the first voxel space is a voxel space with a distance from a self coordinate system of the radar being larger than or equal to a first set threshold value, the second voxel space is a voxel space with a distance from the self coordinate system of the radar being smaller than a second set threshold value, and the second set threshold value is smaller than or equal to the first set threshold value; acquiring first original point cloud data with a distance greater than or equal to a first set threshold value from a radar self coordinate system, and performing downsampling operation on the first original point cloud data according to a first voxel space, the position information and the reflectivity; acquiring second original point cloud data with a distance smaller than a second set threshold value from a radar self coordinate system, and performing downsampling operation on the second original point cloud data according to a second voxel space, the position information and the reflectivity; and determining point cloud data obtained by downsampling the first original point cloud data, the first original point cloud data and the point cloud data obtained by downsampling the second original point cloud data as target point cloud data, so as to realize that different pretreatment methods can be respectively adopted for near and far part point clouds to simultaneously solve the problems that the quantity of near point clouds is huge, the efficiency is influenced, and the remote point clouds are sparse and easy to miss.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a point cloud processing method according to a first embodiment of the present invention;
FIG. 1a is a schematic view of a first target voxel space and a second target voxel space in a first embodiment of the invention;
fig. 2 is a schematic structural diagram of a point cloud processing device in a second embodiment of the present invention;
Fig. 3 is a schematic structural diagram of a computer device in a third embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
Example 1
Fig. 1 is a flowchart of a point cloud processing method according to an embodiment of the present invention, where the method may be applied to a point cloud processing case, and the method may be performed by a point cloud processing device according to an embodiment of the present invention, where the point cloud processing device may be implemented in a software and/or hardware manner, as shown in fig. 1, and the method specifically includes the following steps:
s110, determining position information and reflectivity of point clouds in the original point cloud data in space according to the point cloud original data.
For example, the manner of determining the position information and the reflectivity of the point cloud in the space in the original point cloud data according to the point cloud original data may be to parse the point cloud original data into PointCloud format, pointCloud format is (x, y, z), and int (respectively representing the position and the reflectivity intensity of the point cloud in the space).
S120, dividing the space where the point cloud is located to obtain at least one voxel space, wherein the voxel space comprises a first voxel space and a second voxel space, the first voxel space is larger than the second voxel space, the first voxel space is a voxel space with a distance from a self coordinate system of the radar being larger than or equal to a first set threshold, the second voxel space is a voxel space with a distance from the self coordinate system of the radar being smaller than a second set threshold, and the second set threshold is smaller than or equal to the first set threshold.
Wherein the first set threshold may be 70, and the second set threshold may be 30, and exemplary, a voxel space having a distance of less than 30 from the radar self coordinate system is determined as a near voxel space, and a voxel space having a distance of greater than or equal to 70 from the radar self coordinate system is determined as a far voxel space.
The size of the voxel space is related to the distance between the voxel space and the radar self-coordinate system, and the farther the distance between the voxel space and the radar self-coordinate system is, the smaller the voxel space is, and the closer the distance between the voxel space and the radar self-coordinate system is, the larger the voxel space is.
Wherein the voxel space comprises a first voxel space and a second voxel space.
S130, acquiring first original point cloud data with the distance from a radar self coordinate system being greater than or equal to a first set threshold value, and performing downsampling operation on the first original point cloud data according to a first voxel space, the position information and the reflectivity.
The first voxel space is a far voxel space, and the number of far point clouds is small.
For example, first original point cloud data with a distance greater than or equal to a first set threshold value from a radar self coordinate system is obtained, and downsampling operation is performed on the first original point cloud data according to a first voxel space, the position information and the reflectivity, for example, position information and reflectivity of a point cloud in space, which are included in the first original point cloud data, are obtained, a voxel space in which the point cloud is located is determined according to the position information and the reflectivity, and if voxel spaces determined by the point cloud 11 and the point cloud 12 are the same and are all voxel spaces Q, center-of-gravity coordinates of the voxel space Q are obtained, and center-of-gravity coordinates of the voxel space Q, the point cloud 11 and the point cloud 12 are obtained.
S140, obtaining second original point cloud data with the distance from a radar self coordinate system smaller than a second set threshold value, and performing downsampling operation on the second original point cloud data according to a second voxel space, the position information and the reflectivity.
The second voxel space is a near voxel space, and the number of near point clouds is large, so that the near point clouds need to be filtered through a downsampling operation.
For example, the second original point cloud data with the distance from the radar self coordinate system smaller than the second set threshold is obtained, the downsampling operation is performed on the second original point cloud data according to the second voxel space, the position information and the reflectivity, for example, the position information and the reflectivity of the point cloud in the space, which are included in the second original point cloud data, are obtained, the voxel space in which the point cloud is located is determined according to the position information and the reflectivity, if the voxel spaces determined by the point cloud 1, the point cloud 2, the point cloud 3 and the point cloud 4 are all the same, and are all voxel space a, the barycentric coordinates of the voxel space a are obtained, and the barycentric coordinates of the voxel space a are used for representing the point cloud 1, the point cloud 2, the point cloud 3 and the point cloud 4.
And S150, determining the point cloud data obtained by performing downsampling operation on the first original point cloud data, the point cloud data obtained by performing downsampling operation on the second original point cloud data and the second original point cloud data as target point cloud data.
For example, the point cloud data obtained by performing the downsampling operation on the first original point cloud data, the point cloud data obtained by performing the downsampling operation on the second original point cloud data, and the second original point cloud data are determined as target point cloud data, for example, may be that position information and reflectivity of a point cloud in a space included in the first original point cloud data are obtained, a voxel space in which the point cloud is located is determined according to the position information and the reflectivity, if the voxel spaces determined by the point cloud 11 and the point cloud 12 are the same, a barycentric coordinate of the voxel space Q is obtained, the barycentric coordinate of the voxel space Q, the position information and the reflectivity of the point cloud in the space included in the second original point cloud data are obtained, the voxel space in which the point cloud is located is determined according to the position information and the reflectivity, if the voxel spaces determined by the point cloud 1, the point cloud 2, the point cloud 3 and the point cloud 4 are the same, the barycentric coordinate of the voxel space a is obtained, and the barycentric coordinate of the voxel space a is represented by the barycentric coordinate of the voxel space a, and the point cloud 1, the point cloud 2, the point cloud 3 and the point cloud 4 are obtained. The barycentric coordinates of voxel space a, the barycentric coordinates of voxel space Q, point cloud 11, and point cloud 12.
As shown in fig. 1a, acquiring second original point cloud data with a distance from a radar self coordinate system smaller than a second set threshold value; determining at least one first target voxel space according to the position information and the reflectivity of the point cloud in the space in the second original point cloud data; acquiring first original point cloud data with a distance from a radar self coordinate system being greater than or equal to a first set threshold value; and determining at least one second target voxel space according to the position information and the reflectivity of the point cloud in the space in the first original point cloud data.
Optionally, acquiring second original point cloud data with a distance from a radar self coordinate system smaller than a second set threshold, and performing downsampling operation on the second original point cloud data according to a second voxel space, the position information and the reflectivity, including:
Acquiring second original point cloud data with a distance from a radar self coordinate system smaller than a second set threshold value;
Determining at least one first target voxel space according to the position information and the reflectivity of the point cloud in the space in the second original point cloud data;
and representing the point cloud corresponding to the first target voxel space through the barycentric coordinates of the first target voxel space.
For example, second original point cloud data with a distance from a radar self coordinate system smaller than a second set threshold is obtained, at least one first target voxel space is determined according to position information and reflectivity of point clouds in the second original point cloud data in space, point clouds corresponding to the first target voxel space are represented by barycentric coordinates of the first target voxel space, for example, the position information and reflectivity of the point clouds included in the second original point cloud data in space are obtained, and at least one first target voxel space is determined according to the position information and the reflectivity: and if the first target voxel space determined by the point cloud 1, the point cloud 2, the point cloud 3 and the point cloud 4 is the first target voxel space A, acquiring the barycenter coordinate of the first target voxel space A, and using the barycenter coordinate of the first target voxel space A to represent the point cloud 1, the point cloud 2, the point cloud 3 and the point cloud 4.
Optionally, the step of representing the point cloud corresponding to the first target voxel space by the barycentric coordinates of the first target voxel space includes:
determining barycentric coordinates of the first target voxel space according to the position information of the point cloud in the first target voxel space in the space;
And representing the point cloud corresponding to the first target voxel space through the barycentric coordinates of the first target voxel space.
For example, the barycentric coordinates of the first target voxel space are determined according to the position information of the point cloud in the first target voxel space in space, for example, if the point cloud in the first target voxel space a includes: and determining the average value of x, y and z of the point cloud 1, the point cloud 2, the point cloud 3 and the point cloud 4 as the barycentric coordinate of the first target voxel space A.
Optionally, determining at least one first target voxel space according to the position information and the reflectivity of the point cloud in the space in the second original point cloud data includes:
The first target voxel space Pos3D (i, j, k) is calculated according to the following formula:
Wherein, (x, y, z) is the position information of the point cloud in the second original point cloud data in space, (VD, VW, VH) is the length, width and height of the first target voxel space, and int is the reflectivity.
Optionally, acquiring first original point cloud data with a distance from a radar self coordinate system greater than or equal to a first set threshold, and performing downsampling operation on the first original point cloud data according to a first voxel space, the position information and the reflectivity, including:
acquiring first original point cloud data with a distance from a radar self coordinate system being greater than or equal to a first set threshold value;
determining at least one second target voxel space according to the position information and the reflectivity of the point cloud in the space in the first original point cloud data;
and acquiring barycentric coordinates of each second target voxel space.
Illustratively, the manner of determining the at least one second target voxel space according to the position information and the reflectivity of the point cloud in the space in the first original point cloud data may be to calculate a second target voxel space Pos3D (o, p, q) according to the following formula: Wherein, (a, b, c) is the position information of the point cloud in the first original point cloud data in space, (r, t, s) is the length, width and height of the second target voxel space, and λ is the reflectivity of the point cloud in the first original point cloud data.
For example, the manner of acquiring the barycentric coordinates of each second target voxel space may be to determine the barycentric coordinates of the second target voxel space according to the position information of the point cloud in the space in the second target voxel space, for example, the position information and the reflectivity of the point cloud in the space included in the first original point cloud data may be acquired, the voxel space in which the point cloud is located is determined according to the position information and the reflectivity, and if the voxel spaces determined by the point cloud 11 and the point cloud 12 are the same and are all the voxel space Q, the barycentric coordinates of the voxel space Q are determined according to the average values of x, y and z of the point cloud 11 and the point cloud 12.
In a specific example, the preprocessing method based on the laser radar point cloud specifically includes the following steps:
Step one: acquiring point cloud original data (raw data) through radar driving and analyzing the point cloud original data into PointCloud format, wherein the data format is (x, y, z), and int (respectively representing the position and reflectivity intensity of the point cloud in space);
step two: voxel space is partitioned. For the space where the input point cloud is located, the length, the width and the height of the space are expressed by D, H and W; the length, width and height of each small voxel are defined as VD, VH, VW. The authors assume here that D, H, W are integer multiples of VD, VH, VW, respectively, and that the size of the voxel space is related to the distance from the radar's own coordinate system, the voxel space at near is slightly larger and the voxel space at far is smaller, since we have to treat the near and far point clouds differently. The size of the voxel space in the practical application is also determined specifically according to the point cloud characteristics of the laser radar and the practical application scene;
Step three: for the near point cloud, the point cloud sparsification processing is carried out through the downsampling operation, wherein the downsampling process is to put the point cloud into a voxel space with a specified size, if a certain point coordinate is (x, y, z), and the voxel space number is Pos3D (i, j, k), the corresponding relation exists Solving the barycentric coordinates of the voxel space, namely solving the mean value of all points (x, y, z) in the voxel space. If a local cluster of points falls within a voxel space, then all points in the grid are represented by the coordinates of the center of gravity of the voxel space. Through the process, the point cloud data can be greatly filtered, but the morphological characteristics of the model still keep integrity;
Step four: the fourth step and the third step should be performed simultaneously, and one step is a fourth step for distinguishing single columns. For the far point cloud we have chosen a smaller voxel space for downsampling, this part of the added operation has substantially no impact on the efficiency of the algorithm because the number of point clouds at the far point is small. And then the remote original point cloud is not abandoned to be replaced by the downsampling result, and on the contrary, the original point cloud and the downsampling result are reserved, so that the effects of enhancing the point cloud data and enriching the point cloud characteristics are achieved. We do nothing else about the point cloud of the middle region.
Step five: and sending the preprocessed point cloud into a back-end algorithm.
According to the embodiment of the invention, voxel spaces with different sizes are divided according to the distance from the voxel space, and the point cloud data enhancement is performed by superposing the gravity center of the down-sampled voxel space and the original point cloud.
In addition, the upsampling is a surface reconstruction method, and the effect of data enhancement can be obtained by performing interpolation operation on the original point cloud data. And thus, the remote sparse point cloud densification can also be completed by adopting an upsampling mode.
According to the technical scheme of the embodiment, position information and reflectivity of point clouds in the original point cloud data in space are determined according to the point cloud original data; dividing the space in which the point cloud is located to obtain at least one voxel space, wherein the voxel space comprises a first voxel space and a second voxel space, the first voxel space is larger than the second voxel space, the first voxel space is a voxel space with a distance from a self coordinate system of the radar being larger than or equal to a first set threshold value, the second voxel space is a voxel space with a distance from the self coordinate system of the radar being smaller than a second set threshold value, and the second set threshold value is smaller than or equal to the first set threshold value; acquiring first original point cloud data with a distance greater than or equal to a first set threshold value from a radar self coordinate system, and performing downsampling operation on the first original point cloud data according to a first voxel space, the position information and the reflectivity; acquiring second original point cloud data with a distance smaller than a second set threshold value from a radar self coordinate system, and performing downsampling operation on the second original point cloud data according to a second voxel space, the position information and the reflectivity; and determining point cloud data obtained by downsampling the first original point cloud data, the first original point cloud data and the point cloud data obtained by downsampling the second original point cloud data as target point cloud data, so as to realize that different pretreatment methods can be respectively adopted for near and far part point clouds to simultaneously solve the problems that the quantity of near point clouds is huge, the efficiency is influenced, and the remote point clouds are sparse and easy to miss.
Example two
Fig. 2 is a schematic structural diagram of a point cloud processing device according to a second embodiment of the present invention. The embodiment may be applicable to the case of point cloud processing, and the device may be implemented in a software and/or hardware manner, and may be integrated in any device that provides a function of point cloud processing, as shown in fig. 2, where the point cloud processing device specifically includes: the first determination module 210, the division module 220, the first acquisition module 230, the second acquisition module 240, and the second determination module 250.
The first determining module 210 is configured to determine, according to the original point cloud data, position information and reflectivity of a point cloud in the original point cloud data in space;
The dividing module 220 is configured to divide the space in which the point cloud is located to obtain at least one voxel space, where the voxel space includes a first voxel space and a second voxel space, the first voxel space is greater than the second voxel space, the first voxel space is a voxel space with a distance from a self coordinate system of the radar being greater than or equal to a first set threshold, the second voxel space is a voxel space with a distance from the self coordinate system of the radar being less than a second set threshold, and the second set threshold is less than or equal to the first set threshold;
A first obtaining module 230, configured to obtain first original point cloud data with a distance from a coordinate system of the radar being greater than or equal to a first set threshold, and perform a downsampling operation on the first original point cloud data according to a first voxel space, the position information and the reflectivity;
a second obtaining module 240, configured to obtain second original point cloud data with a distance from a radar own coordinate system smaller than a second set threshold, and perform a downsampling operation on the second original point cloud data according to a second voxel space, the position information and the reflectivity;
The second determining module 250 is configured to determine, as target point cloud data, point cloud data obtained by performing a downsampling operation on the first original point cloud data, and point cloud data obtained by performing a downsampling operation on the second original point cloud data.
Optionally, the second obtaining module is specifically configured to:
Acquiring second original point cloud data with a distance from a radar self coordinate system smaller than a second set threshold value;
Determining at least one first target voxel space according to the position information and the reflectivity of the point cloud in the space in the second original point cloud data;
and representing the point cloud corresponding to the first target voxel space through the barycentric coordinates of the first target voxel space.
Optionally, the second obtaining module is specifically configured to:
determining barycentric coordinates of the first target voxel space according to the position information of the point cloud in the first target voxel space in the space;
And representing the point cloud corresponding to the first target voxel space through the barycentric coordinates of the first target voxel space.
The product can execute the method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
According to the technical scheme of the embodiment, position information and reflectivity of point clouds in the original point cloud data in space are determined according to the point cloud original data; dividing the space in which the point cloud is located to obtain at least one voxel space, wherein the voxel space comprises a first voxel space and a second voxel space, the first voxel space is larger than the second voxel space, the first voxel space is a voxel space with a distance from a self coordinate system of the radar being larger than or equal to a first set threshold value, the second voxel space is a voxel space with a distance from the self coordinate system of the radar being smaller than a second set threshold value, and the second set threshold value is smaller than or equal to the first set threshold value; acquiring first original point cloud data with a distance greater than or equal to a first set threshold value from a radar self coordinate system, and performing downsampling operation on the first original point cloud data according to a first voxel space, the position information and the reflectivity; acquiring second original point cloud data with a distance smaller than a second set threshold value from a radar self coordinate system, and performing downsampling operation on the second original point cloud data according to a second voxel space, the position information and the reflectivity; and determining point cloud data obtained by downsampling the first original point cloud data, the first original point cloud data and the point cloud data obtained by downsampling the second original point cloud data as target point cloud data, so as to realize that different pretreatment methods can be respectively adopted for near and far part point clouds to simultaneously solve the problems that the quantity of near point clouds is huge, the efficiency is influenced, and the remote point clouds are sparse and easy to miss.
Example III
Fig. 3 is a schematic structural diagram of a computer device according to a third embodiment of the present invention. FIG. 3 illustrates a block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention. The computer device 12 shown in fig. 3 is merely an example and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.
As shown in FIG. 3, computer device 12 is in the form of a general purpose computing device. Components of computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, a bus 18 that connects the various system components, including the system memory 28 and the processing units 16.
Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, and a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include industry standard architecture (Industry Standard Architecture, ISA) bus, micro channel architecture (Micro Channel Architecture, MCA) bus, enhanced ISA bus, video electronics standards association (Video Electronics Standards Association, VESA) local bus, and peripheral component interconnect (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus.
Computer device 12 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by computer device 12 and includes both volatile and nonvolatile media, removable and non-removable media.
The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (Random Access Memory, RAM) 30 and/or cache memory 32. The computer device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from or write to non-removable, nonvolatile magnetic media (not shown in FIG. 3, commonly referred to as a "hard disk drive"). Although not shown in fig. 3, a disk drive for reading from and writing to a removable nonvolatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable nonvolatile optical disk (Compact Disc-Read Only Memory, CD-ROM), digital versatile disk (Digital Video Disc-Read Only Memory, DVD-ROM), or other optical media, may be provided. In such cases, each drive may be coupled to bus 18 through one or more data medium interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored in, for example, memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Program modules 42 generally perform the functions and/or methods of the embodiments described herein.
The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), one or more devices that enable a user to interact with the computer device 12, and/or any devices (e.g., network card, modem, etc.) that enable the computer device 12 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 22. In addition, in the computer device 12 of the present embodiment, the display 24 is not present as a separate body but is embedded in the mirror surface, and the display surface of the display 24 and the mirror surface are visually integrated when the display surface of the display 24 is not displayed. Moreover, computer device 12 may also communicate with one or more networks such as a local area network (Local Area Network, LAN), a wide area network Wide Area Network, WAN) and/or a public network such as the Internet via network adapter 20. As shown, network adapter 20 communicates with other modules of computer device 12 via bus 18. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with computer device 12, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, disk array (Redundant Arrays of INDEPENDENT DISKS, RAID) systems, tape drives, data backup storage systems, and the like.
The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, for example, implementing the point cloud processing method provided by the embodiment of the present invention:
Determining position information and reflectivity of point clouds in the original point cloud data in space according to the point cloud original data;
dividing the space in which the point cloud is located to obtain at least one voxel space, wherein the voxel space comprises a first voxel space and a second voxel space, the first voxel space is larger than the second voxel space, the first voxel space is a voxel space with a distance from a self coordinate system of the radar being larger than or equal to a first set threshold value, the second voxel space is a voxel space with a distance from the self coordinate system of the radar being smaller than a second set threshold value, and the second set threshold value is smaller than or equal to the first set threshold value;
Acquiring first original point cloud data with a distance greater than or equal to a first set threshold value from a radar self coordinate system, and performing downsampling operation on the first original point cloud data according to a first voxel space, the position information and the reflectivity;
Acquiring second original point cloud data with a distance smaller than a second set threshold value from a radar self coordinate system, and performing downsampling operation on the second original point cloud data according to a second voxel space, the position information and the reflectivity;
and determining point cloud data obtained by downsampling the first original point cloud data, the first original point cloud data and the point cloud data obtained by downsampling the second original point cloud data as target point cloud data.
Example IV
A fourth embodiment of the present application provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the point cloud processing method as provided in all the embodiments of the present application:
Determining position information and reflectivity of point clouds in the original point cloud data in space according to the point cloud original data;
dividing the space in which the point cloud is located to obtain at least one voxel space, wherein the voxel space comprises a first voxel space and a second voxel space, the first voxel space is larger than the second voxel space, the first voxel space is a voxel space with a distance from a self coordinate system of the radar being larger than or equal to a first set threshold value, the second voxel space is a voxel space with a distance from the self coordinate system of the radar being smaller than a second set threshold value, and the second set threshold value is smaller than or equal to the first set threshold value;
Acquiring first original point cloud data with a distance greater than or equal to a first set threshold value from a radar self coordinate system, and performing downsampling operation on the first original point cloud data according to a first voxel space, the position information and the reflectivity;
Acquiring second original point cloud data with a distance smaller than a second set threshold value from a radar self coordinate system, and performing downsampling operation on the second original point cloud data according to a second voxel space, the position information and the reflectivity;
and determining point cloud data obtained by downsampling the first original point cloud data, the first original point cloud data and the point cloud data obtained by downsampling the second original point cloud data as target point cloud data.
Any combination of one or more computer readable media may be employed. The computer readable medium may be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
In some embodiments, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (Hyper Text Transfer Protocol ), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.
The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device.
The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: receiving a source text input by a user, and translating the source text into a target text corresponding to a target language; acquiring the historical correction behavior of the user; correcting the target text according to the history correction behavior to obtain a translation result, and pushing the translation result to a client where the user is located.
Computer program code for carrying out operations of the present invention may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units involved in the embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.
The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a Complex Programmable Logic Device (CPLD), and the like.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.
Claims (5)
1. A method of point cloud processing, comprising:
determining position information and reflectivity of point clouds in the original point cloud data in space according to the original point cloud data;
dividing the space in which the point cloud is located to obtain at least one voxel space, wherein the voxel space comprises a first voxel space and a second voxel space, the first voxel space is larger than the second voxel space, the first voxel space is a voxel space with a distance from a self coordinate system of the radar being larger than or equal to a first set threshold value, the second voxel space is a voxel space with a distance from the self coordinate system of the radar being smaller than a second set threshold value, and the second set threshold value is smaller than or equal to the first set threshold value;
Acquiring first original point cloud data with a distance greater than or equal to a first set threshold value from a radar self coordinate system, and performing downsampling operation on the first original point cloud data according to a first voxel, the position information and the reflectivity;
Acquiring second original point cloud data with a distance smaller than a second set threshold value from a radar self coordinate system, and performing downsampling operation on the second original point cloud data according to a second voxel, the position information and the reflectivity;
Determining point cloud data obtained by downsampling the first original point cloud data, the first original point cloud data and the point cloud data obtained by downsampling the second original point cloud data as target point cloud data;
Acquiring second original point cloud data with a distance from a radar self coordinate system smaller than a second set threshold value, and performing downsampling operation on the second original point cloud data according to a second voxel space, the position information and the reflectivity, wherein the downsampling operation comprises the following steps:
Acquiring second original point cloud data with a distance from a radar self coordinate system smaller than a second set threshold value;
Determining at least one first target voxel space according to the position information and the reflectivity of the point cloud in the space in the second original point cloud data;
determining barycentric coordinates of the first target voxel space according to the position information of the point cloud in the first target voxel space in the space;
the point cloud corresponding to the first target voxel space is represented by the barycentric coordinates of the first target voxel space;
Wherein determining at least one first target voxel space from the position information and the reflectivity of the point cloud in the second original point cloud data in space comprises:
The first target voxel space Pos3D (i, j, k) is calculated according to the following formula:
Wherein, (x, y, z) is the position information of the point cloud in the second original point cloud data in space, (VD, VW, VH) is the length, width and height of the first target voxel space, and int is the reflectivity.
2. The method according to claim 1, wherein acquiring first origin cloud data having a distance from a radar own coordinate system greater than or equal to a first set threshold value, and downsampling the first origin cloud data according to a first voxel space, the position information, and the reflectivity, comprises:
acquiring first original point cloud data with a distance from a radar self coordinate system being greater than or equal to a first set threshold value;
determining at least one second target voxel space according to the position information and the reflectivity of the point cloud in the space in the first original point cloud data;
and acquiring barycentric coordinates of each second target voxel space.
3. A point cloud processing apparatus, comprising:
the first determining module is used for determining the position information and the reflectivity of the point cloud in the original point cloud data in space according to the original point cloud data;
the division module is used for dividing the space where the point cloud is located to obtain at least one voxel space, wherein the voxel space comprises a first voxel space and a second voxel space, the first voxel space is larger than the second voxel space, the first voxel space is a voxel space with a distance from a self coordinate system of the radar being larger than or equal to a first set threshold value, the second voxel space is a voxel space with a distance from the self coordinate system of the radar being smaller than a second set threshold value, and the second set threshold value is smaller than or equal to the first set threshold value;
The first acquisition module is used for acquiring first original point cloud data with the distance from a radar self coordinate system being greater than or equal to a first set threshold value, and performing downsampling operation on the first original point cloud data according to a first voxel space, the position information and the reflectivity;
The second acquisition module is used for acquiring second original point cloud data with the distance from a radar self coordinate system smaller than a second set threshold value, and performing downsampling operation on the second original point cloud data according to a second voxel space, the position information and the reflectivity;
The second determining module is used for determining point cloud data obtained by downsampling the first original point cloud data, the first original point cloud data and the point cloud data obtained by downsampling the second original point cloud data as target point cloud data;
the second obtaining module is specifically configured to:
Acquiring second original point cloud data with a distance from a radar self coordinate system smaller than a second set threshold value;
Determining at least one first target voxel space according to the position information and the reflectivity of the point cloud in the space in the second original point cloud data;
determining barycentric coordinates of the first target voxel space according to the position information of the point cloud in the first target voxel space in the space;
the point cloud corresponding to the first target voxel space is represented by the barycentric coordinates of the first target voxel space;
Wherein determining at least one first target voxel space from the position information and the reflectivity of the point cloud in the second original point cloud data in space comprises:
The first target voxel space Pos3D (i, j, k) is calculated according to the following formula:
Wherein, (x, y, z) is the position information of the point cloud in the second original point cloud data in space, (VD, VW, VH) is the length, width and height of the first target voxel space, and int is the reflectivity.
4. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 1-2 when the program is executed by the processor.
5. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any of claims 1-2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011534220.4A CN112764004B (en) | 2020-12-22 | 2020-12-22 | Point cloud processing method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011534220.4A CN112764004B (en) | 2020-12-22 | 2020-12-22 | Point cloud processing method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112764004A CN112764004A (en) | 2021-05-07 |
| CN112764004B true CN112764004B (en) | 2024-05-03 |
Family
ID=75695239
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011534220.4A Active CN112764004B (en) | 2020-12-22 | 2020-12-22 | Point cloud processing method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112764004B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113836484B (en) * | 2021-08-11 | 2023-05-16 | 浙江省测绘科学技术研究院 | Self-adaptive point cloud thinning method based on path point adjacent domain and ground filtering |
| CN113674425B (en) * | 2021-10-25 | 2022-02-15 | 深圳市信润富联数字科技有限公司 | Point cloud sampling method, device, equipment and computer readable storage medium |
| CN116168366B (en) * | 2023-01-19 | 2023-12-05 | 北京百度网讯科技有限公司 | Point cloud data generation method, model training method, target detection method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3620817A1 (en) * | 2018-09-07 | 2020-03-11 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for generating object detection box, device, storage medium, and vehicle |
| CN111127563A (en) * | 2019-12-18 | 2020-05-08 | 北京万集科技股份有限公司 | Combined calibration method and device, electronic equipment and storage medium |
| CN111199206A (en) * | 2019-12-30 | 2020-05-26 | 上海眼控科技股份有限公司 | Three-dimensional target detection method and device, computer equipment and storage medium |
| CN111815707A (en) * | 2020-07-03 | 2020-10-23 | 北京爱笔科技有限公司 | Point cloud determining method, point cloud screening device and computer equipment |
| WO2020248614A1 (en) * | 2019-06-10 | 2020-12-17 | 商汤集团有限公司 | Map generation method, drive control method and apparatus, electronic equipment and system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8994818B2 (en) * | 2012-07-26 | 2015-03-31 | Raytheon Company | Method and apparatus for detecting minimum post spacing in imaging applications |
| US9734595B2 (en) * | 2014-09-24 | 2017-08-15 | University of Maribor | Method and apparatus for near-lossless compression and decompression of 3D meshes and point clouds |
-
2020
- 2020-12-22 CN CN202011534220.4A patent/CN112764004B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3620817A1 (en) * | 2018-09-07 | 2020-03-11 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for generating object detection box, device, storage medium, and vehicle |
| WO2020248614A1 (en) * | 2019-06-10 | 2020-12-17 | 商汤集团有限公司 | Map generation method, drive control method and apparatus, electronic equipment and system |
| CN111127563A (en) * | 2019-12-18 | 2020-05-08 | 北京万集科技股份有限公司 | Combined calibration method and device, electronic equipment and storage medium |
| CN111199206A (en) * | 2019-12-30 | 2020-05-26 | 上海眼控科技股份有限公司 | Three-dimensional target detection method and device, computer equipment and storage medium |
| CN111815707A (en) * | 2020-07-03 | 2020-10-23 | 北京爱笔科技有限公司 | Point cloud determining method, point cloud screening device and computer equipment |
Non-Patent Citations (4)
| Title |
|---|
| 基于3维点云欧氏聚类和RANSAC边界拟合的目标物体尺寸和方位识别;薛连杰;齐臣坤;张彪;张霄远;吴长征;;机械设计与研究(第05期);全文 * |
| 基于RANSAC分割的点云数据K-近邻去噪算法研究;郭宁博;陈向宁;何艳华;;电子测量技术(第12期);全文 * |
| 基于体素下采样和关键点提取的点云自动配准;张彬;熊传兵;;激光与光电子学进展(第04期);全文 * |
| 基于高斯过程回归与马尔科夫随机场的三维深度图像重构算法;吴倩倩;蔡艳;;应用激光(第06期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112764004A (en) | 2021-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112764004B (en) | Point cloud processing method, device, equipment and storage medium | |
| CN109300190B (en) | Three-dimensional data processing method, device, equipment and storage medium | |
| CN108629231B (en) | Obstacle detection method, apparatus, device and storage medium | |
| WO2022017147A1 (en) | Point cloud data processing method and apparatus, radar apparatus, electronic device, and computer readable storage medium | |
| CN112771573A (en) | Depth estimation method and device based on speckle images and face recognition system | |
| Hoppe et al. | Incremental Surface Extraction from Sparse Structure-from-Motion Point Clouds. | |
| Cambuim et al. | An FPGA-based real-time occlusion robust stereo vision system using semi-global matching | |
| CN111311663B (en) | Real-time large-scene three-dimensional semantic modeling method | |
| CN107464286B (en) | Method, device, equipment and readable medium for repairing holes in three-dimensional city model | |
| US8587586B2 (en) | Electronic device and method for meshing curved surface | |
| CN113129352A (en) | Sparse light field reconstruction method and device | |
| CN115330940A (en) | Three-dimensional reconstruction method, device, equipment and medium | |
| US20220375164A1 (en) | Method and apparatus for three dimensional reconstruction, electronic device and storage medium | |
| CN113421217A (en) | Method and device for detecting travelable area | |
| CN114170596A (en) | Posture recognition method and device, electronic equipment, engineering machinery and storage medium | |
| US20230169680A1 (en) | Beijing baidu netcom science technology co., ltd. | |
| Mateo et al. | Hierarchical, Dense and Dynamic 3D Reconstruction Based on VDB Data Structure for Robotic Manipulation Tasks | |
| CN113763468B (en) | Positioning method, device, system and storage medium | |
| CN113610856A (en) | Method and device for training image segmentation model and image segmentation | |
| CN113920446A (en) | 3D target detection algorithm based on original point cloud processing | |
| CN110825803B (en) | Ocean current visualization method based on parallel search set and parallel computation | |
| CN112541535B (en) | Three-dimensional point cloud classification method based on complementary multi-branch deep learning | |
| Menzel et al. | City Reconstruction and Visualization from Public Data Sources. | |
| CN113537602B (en) | Vehicle behavior prediction method, device, equipment and medium | |
| CN116385612B (en) | Global illumination representation method and device under indoor scene 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 |