CN110458772A - A kind of point cloud filtering method, device and storage medium based on image procossing - Google Patents
A kind of point cloud filtering method, device and storage medium based on image procossing Download PDFInfo
- Publication number
- CN110458772A CN110458772A CN201910692496.6A CN201910692496A CN110458772A CN 110458772 A CN110458772 A CN 110458772A CN 201910692496 A CN201910692496 A CN 201910692496A CN 110458772 A CN110458772 A CN 110458772A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- coordinate
- initial point
- image
- integer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001914 filtration Methods 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000003860 storage Methods 0.000 title claims abstract description 19
- 238000013507 mapping Methods 0.000 claims abstract description 29
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 abstract description 5
- 238000006243 chemical reaction Methods 0.000 abstract description 2
- 230000003116 impacting effect Effects 0.000 abstract description 2
- 230000015654 memory Effects 0.000 description 17
- 238000010586 diagram Methods 0.000 description 11
- 230000000694 effects Effects 0.000 description 10
- 238000004590 computer program Methods 0.000 description 5
- 230000001052 transient effect Effects 0.000 description 5
- 230000000717 retained effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of, and point cloud filtering method, device and storage medium based on image procossing avoid scattered points from impacting subsequent processing acquired initial point cloud progress scattered points filtering;After initial point cloud coordinate unique number corresponding to filtered initial point cloud, since a cloud coordinate being mapped in image coordinate system, and it is usually floating type that initial point cloud, which sits target value, therefore will be integer to the data type conversion of the initial point cloud coordinate, so that mapping is more accurate;Simultaneously, after mapping image zooming-out connected component, retain image coordinate in connected domain and corresponds to the most connected domain of integer point cloud coordinate, remain the unique number of the corresponding initial point cloud coordinate of image coordinate in this connected domain, corresponding data are noise data in other connected domains filtered out at this time, are filtered target point cloud by the point cloud that unique number is restored, and are compared without coordinate one by one, calculation amount is small, realizes and quickly filters out a cloud noise.
Description
Technical field
The present invention relates to technical field of data processing, especially a kind of point cloud filtering method, device based on image procossing
And storage medium.
Background technique
In the fields such as ancient building reconstruct, the reverse-engineering of workpiece or survey engineering, untouchable 3-D measuring apparatus
The topographical information of object can be obtained in the case where not contacting object, it is very widely used, although scanning accuracy steadily improves,
But inevitably will appear lens distortions, camera parameters estimation inaccuracy the problems such as, cause obtain topographical information in comprising compared with
More noises, topographical information are presented usually in the form of cloud, it is therefore desirable to be denoised to a cloud, it is ensured that the standard of follow-up work
True property.Existing scheme is typically based on three-dimensional space and handles a cloud, is made an uproar by the relationship removal calculated between initial point cloud
Sound, but often data volume is huge for the initial point cloud of 3-D measuring apparatus acquisition, directly carries out processing to initial point cloud and there is meter
Calculation amount is big, low efficiency and the high disadvantage of complexity.
Summary of the invention
For overcome the deficiencies in the prior art, the point cloud filtering based on image procossing that the purpose of the present invention is to provide a kind of
Method, apparatus and storage medium, reduce the calculation amount of point cloud denoising, quickly and efficiently complete point cloud filtering.
Technical solution used by the present invention solves the problems, such as it is: in a first aspect, the present invention provides one kind to be based on image
The point cloud filtering method of processing, comprising the following steps:
Client obtains initial point cloud, and the scattered points of the initial point cloud are filtered;
The client obtains corresponding initial point cloud coordinate in initial point Yun Dian cloud coordinate system, to the initial point cloud
Coordinate is numbered, and show that uniquely corresponding coordinate is numbered with the initial point cloud coordinate;
The initial point cloud coordinate is converted into the integer point cloud coordinate that data type is integer by the client, establishes figure
As coordinate system, and the integer point cloud coordinate is mapped in described image coordinate system;
The client obtains the mapping image being made of the data in described image coordinate system, mentions to the mapping image
After taking connected component, target connected domain is set by the connected domain that described image coordinate pair answers the integer point cloud coordinate most,
And other connected domains are filtered out;
Coordinate number included in the target connected domain is obtained, is sat the integer point cloud according to coordinate number
Mark reverts to corresponding initial point cloud coordinate, and maps in described cloud coordinate system, completes point cloud filtering.
Further, the scattered points in the initial point cloud are filtered by k nearest neighbor algorithm.
Further, described image coordinate system is established according to the origin of described cloud coordinate system, x-axis and y-axis.
Further, the coordinate value in the integer point cloud coordinate rounds up for the coordinate value of the initial point cloud coordinate and takes
The value obtained after whole.
Further, it is described to the mapping image zooming-out connected component before, further includes: the mapping image is closed
Operation is to make the region of fracture up.
Second aspect, the present invention provides a kind of for executing the device of the point cloud filtering method based on image procossing, packet
CPU element is included, the CPU element is for executing following steps:
Client obtains initial point cloud, and the scattered points of the initial point cloud are filtered;
The client obtains corresponding initial point cloud coordinate in initial point Yun Dian cloud coordinate system, to the initial point cloud
Coordinate is numbered, and show that uniquely corresponding coordinate is numbered with the initial point cloud coordinate;
The initial point cloud coordinate is converted into the integer point cloud coordinate that data type is integer by the client, establishes figure
As coordinate system, and the integer point cloud coordinate is mapped in described image coordinate system;
The client obtains the mapping image being made of the data in described image coordinate system, mentions to the mapping image
After taking connected component, target connected domain is set by the connected domain that described image coordinate pair answers the integer point cloud coordinate most,
And other connected domains are filtered out;
Coordinate number included in the target connected domain is obtained, is sat the integer point cloud according to coordinate number
Mark reverts to corresponding initial point cloud coordinate, and maps in described cloud coordinate system, completes point cloud filtering.
Further, the CPU element is also used to execute following steps: carrying out closure operation to the mapping image to make up
The region of fracture.
The third aspect, the present invention provides a kind of equipment for executing the point cloud filtering method based on image procossing, packets
Include at least one control processor and the memory for communicating to connect at least one control processor;Memory is stored with can
The instruction executed by least one control processor, instruction are executed by least one control processor, so that at least one is controlled
Processor is able to carry out the point cloud filtering method based on image procossing as described above.
Fourth aspect, the present invention provides a kind of computer readable storage medium, computer-readable recording medium storage has
Computer executable instructions, computer executable instructions are for making computer execute the point cloud based on image procossing as described above
Filtering method.
5th aspect, the present invention also provides a kind of computer program product, the computer program product includes storage
Computer program on computer readable storage medium, the computer program include program instruction, when described program instructs
When being computer-executed, computer is made to execute the point cloud filtering method based on image procossing as described above.
The one or more technical solutions provided in the embodiment of the present invention at least have the following beneficial effects: that the present invention mentions
A kind of point cloud filtering method, device and storage medium based on image procossing has been supplied, acquired initial point cloud has been carried out at random
Point filtering, avoids scattered points from impacting subsequent processing;Only by initial point cloud coordinate corresponding to filtered initial point cloud
After one number, since a cloud coordinate to be mapped in image coordinate system, and it is usually floating type that initial point cloud, which sits target value, because
This will be integer to the data type conversion of the initial point cloud coordinate, so that mapping is more accurate;Meanwhile mapping image is mentioned
After taking connected component, retains image coordinate in connected domain and correspond to the most connected domain of integer point cloud coordinate, that is, remain this company
Lead to the unique number of the corresponding initial point cloud coordinate of image coordinate in domain, corresponding data are in other connected domains filtered out at this time
Noise data is filtered target point cloud by the point cloud that unique number is restored, compares without coordinate one by one that calculation amount is small,
It realizes and quickly filters out a cloud noise.
Detailed description of the invention
The invention will be further described with example with reference to the accompanying drawing.
Fig. 1 is the method flow diagram of the embodiment of the present invention;
Fig. 2 is the initial point cloud exemplary diagram of the embodiment of the present invention;
Fig. 3 is the effect exemplary diagram after the initial point cloud filtering scattered points of the embodiment of the present invention;
Fig. 4 is the effect exemplary diagram of the mapping image of the embodiment of the present invention;
Fig. 5 is that the mapping image of the embodiment of the present invention carries out the effect exemplary diagram after closure operation;
Fig. 6 is the effect exemplary diagram of the acquisition target connected domain of the embodiment of the present invention;
Fig. 7 is the effect exemplary diagram that the embodiment of the present invention completes point cloud filtering;
Fig. 8 is the schematic device that the embodiment of the present invention is used to execute the point cloud filtering method based on image procossing.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.
It should be noted that each feature in the embodiment of the present invention can be combined with each other, in this hair if do not conflicted
Within bright protection scope.In addition, though having carried out functional module division in schematic device, shows patrol in flow charts
Sequence is collected, but in some cases, it can be shown in the sequence execution in the module division being different from device or flow chart
The step of out or describing.
It should be noted that data of the invention can acquire gained by acquisition equipment common on the market, the present invention is not
It is related to the improvement to acquisition equipment, only data acquired in acquisition equipment is handled.
With reference to Fig. 1-Fig. 7, the first embodiment of the present invention provides a kind of point cloud filtering method based on image procossing, packet
Include following steps:
Step S100, client obtains initial point cloud, and the scattered points of the initial point cloud are filtered;
Step S200, the client obtains corresponding initial point cloud coordinate in initial point Yun Dian cloud coordinate system, to institute
It states initial point cloud coordinate to be numbered, show that uniquely corresponding coordinate is numbered with the initial point cloud coordinate;
The initial point cloud coordinate is converted into the integer point cloud that data type is integer and sat by step S300, the client
Mark, establishes image coordinate system, and the integer point cloud coordinate is mapped in described image coordinate system;
Step S400, the client obtains the mapping image being made of the data in described image coordinate system, to described
After mapping image zooming-out connected component, mesh is set by the connected domain that described image coordinate pair answers the integer point cloud coordinate most
Connected domain is marked, and other connected domains are filtered out;
Step S500 obtains coordinate number included in the target connected domain, will be described according to coordinate number
Integer point cloud coordinate reverts to corresponding initial point cloud coordinate, and maps in described cloud coordinate system, completes point cloud filtering.
Wherein, it should be noted that there are institutes in more scattered points, such as Fig. 2 for the point cloud obtained by three dimensional device
The pointing object shown causes the factor of scattered points more, is easy to cause biggish interference, therefore this reality to target point cloud if not filtering out
It applies example and preferably preferentially carries out scattered points after obtaining initial point cloud and filter out, the interference of scattered points can be excluded, obtained after filtering out
Exemplary diagram is as shown in Figure 3.
Wherein, it should be noted that initial point cloud coordinate is three-dimensional coordinate, that is, includes x-axis, y-axis and z-axis, therefore this reality
The initial point cloud coordinate applied in example is represented by (x, y, z), then to initial point cloud after initial point cloud coordinate number in step S200
Coordinate is (xi,yi,zi), unique coordinate number is i, and the value of specific i is determined by the sequence of the initial point cloud coordinate, example
When such as being arranged according to the sequence of the value of x-axis, the smallest coordinate of the value of x-axis is x1, and so on, details are not described herein.
Wherein, in the present embodiment, requirement of the acquisition equipment for precision, the data type of usual resulting initial point cloud
It needs for real-coded GA to be converted into integer data to be mapped for floating type, preferably rounds up in the present embodiment
Method can obtain integer data relatively simplely.
Wherein, it should be noted that after step S300 completes mapping, the point cloud coordinate transformation of floating type is sat at integer
After mark, the case where answering an integer coordinate there are one or more floating type coordinate pair, i.e., integer point cloud coordinate is mapped to
When image coordinate, can there are the case where one or more integer point cloud coordinate pair answers an image coordinate, effect picture such as Fig. 4
It is shown.But the number of coordinate corresponding to integer point cloud coordinate be it is unique, image coordinate also correspond to integer point cloud coordinate and its
Corresponding coordinate number, therefore can distinguish which point the corresponding integer point cloud coordinate of image coordinate is.
Wherein, it should be noted that the present embodiment preferably counts image coordinate pair in each connected domain in step S400
The quantity for the integer point cloud coordinate answered retains image coordinate in connected domain and corresponds to the most connected domain of integer point cloud coordinate quantity,
It remains image coordinate in this connected domain and corresponds to the number of coordinate corresponding to integer point cloud coordinate, filter out other connected domains,
It has filtered out image coordinate in other connected domains and has corresponded to the number of coordinate corresponding to integer point cloud coordinate, effect exemplary diagram is as schemed
Shown in 6.
Wherein, it should be noted that extensive according to the corresponding number of the integer point cloud coordinate being retained in step S400
Multiple extremely corresponding initial point cloud coordinate, i.e., number inconsistent integer point cloud coordinate for coordinate in connected domain and filter out, to realize
Noise spot cloud is filtered out, target point cloud is only retained.Because each initial point cloud coordinate is numbered, according to step
The number being retained in S400 finds its corresponding initial point cloud coordinate in initial point cloud, realizes cloud filtering, effect
Fruit exemplary diagram is as shown in Figure 7.
Further, in another embodiment of the present invention, the scattered points in the initial point cloud by k nearest neighbor algorithm into
Row filtering.
Wherein, it should be noted that the filtering of scattered points can be completed by any particular algorithms, be can be realized and filtered out scattered points
Effect, the present embodiment preferably uses k nearest neighbor algorithm, can be realized efficiently and accurately and filter out scattered points, specifically use
Algorithm is chosen according to actual needs.
Further, in another embodiment of the present invention, described image coordinate system is according to the original of described cloud coordinate system
Point, x-axis and y-axis are established.
Wherein, it should be noted that the long H and width W of the present embodiment further preferably image coordinate system meet following formula respectively:
H=max (yk)-min(yk);K=1,2,3 ..., n;
W=max (xk)-min(xk);K=1,2,3 ..., n.
Wherein, xkThe initial point cloud coordinate for being k for coordinate number subtracts the integer being converted into after coordinate minimum value point cloud seat
Target abscissa value, ykThe initial point cloud coordinate for being k for coordinate number subtracts the integer being converted into after coordinate minimum value point cloud seat
Target ordinate value.
Further, in another embodiment of the present invention, the coordinate value in the integer point cloud coordinate is described initial
The value obtained after the coordinate value round of point cloud coordinate.
Wherein, it should be noted that be rounded to the preferred of the present embodiment, can also use and round up or take downwards
It is the methods of whole, it can be derived that integer data, concrete mode adjusts according to actual needs.
It is further, in another embodiment of the present invention, described to mapping image zooming-out connection point with reference to Fig. 5
Before amount, further includes: carry out closure operation to the mapping image to make the region of fracture up.
Wherein, since the region of fracture for including in mapping image is more, closure operation pair is preferably used in the present embodiment
The region of fracture is made up, and the accuracy of image is improved, and effect diagram is as shown in Figure 5, it should be noted that closure fortune
Calculating is algorithm in the prior art, and the present embodiment is not related to the algorithm improvement to closure operation, and details are not described herein.
Referring to Fig. 8, the second embodiment of the present invention additionally provides a kind of point cloud filtering for executing based on image procossing
The device of method, the device are smart machine, such as smart phone, computer and tablet computer etc., and the present embodiment is with computer
For be illustrated.
In the computer 8000 for being used to execute the point cloud filtering method based on image procossing, including CPU element 8100,
The CPU element 8100 is for executing following steps:
Client obtains initial point cloud, and the scattered points of the initial point cloud are filtered;
The client obtains corresponding initial point cloud coordinate in initial point Yun Dian cloud coordinate system, to the initial point cloud
Coordinate is numbered, and show that uniquely corresponding coordinate is numbered with the initial point cloud coordinate;
The initial point cloud coordinate is converted into the integer point cloud coordinate that data type is integer by the client, establishes figure
As coordinate system, and the integer point cloud coordinate is mapped in described image coordinate system;
The client obtains the mapping image being made of the data in described image coordinate system, mentions to the mapping image
After taking connected component, target connected domain is set by the connected domain that described image coordinate pair answers the integer point cloud coordinate most,
And other connected domains are filtered out;
Coordinate number included in the target connected domain is obtained, is sat the integer point cloud according to coordinate number
Mark reverts to corresponding initial point cloud coordinate, and maps in described cloud coordinate system, completes point cloud filtering.
Further, in another embodiment of the invention, the CPU element 8100 is also used to execute following steps: to institute
It states mapping image and carries out closure operation to make the region of fracture up.
It can be connected by bus or other modes between computer 8000 and CPU element 8100, in computer 8000
It further include memory, the memory can be used for storing non-transient software as a kind of non-transient computer readable storage medium
Program, non-transitory computer executable program and module, as being based on image procossing for executing in the embodiment of the present invention
Point cloud filtering method the corresponding program instruction/module of equipment.Computer 8000 is stored in memory non-by running
Transient state software program, instruction and module execute to control CPU element 8100 for executing the point cloud filter based on image procossing
The various function application and data processing of wave method, i.e. the point cloud filtering based on image procossing of realization above method embodiment
Method.
Memory may include storing program area and storage data area, wherein storing program area can storage program area, extremely
Application program required for a few function;Storage data area, which can be stored, uses created data according to CPU element 8100
Deng.It can also include non-transient memory in addition, memory may include high-speed random access memory, for example, at least one
Disk memory, flush memory device or other non-transient solid-state memories.In some embodiments, the optional packet of memory
The memory remotely located relative to CPU element 8100 is included, these remote memories can pass through network connection to the computer
8000.The example of above-mentioned network includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
One or more of module storages in the memory, when being executed by the CPU element 8100, execute
The point cloud filtering method based on image procossing in above method embodiment.
The embodiment of the invention also provides a kind of computer readable storage medium, the computer-readable recording medium storage
There are computer executable instructions, which is executed by CPU element 8100, realizes described above based on image
The point cloud filtering method of processing.
The apparatus embodiments described above are merely exemplary, wherein described, device can as illustrated by the separation member
It is physically separated with being or may not be, it can it is in one place, or may be distributed over multiple network dresses
It sets.Some or all of the modules therein can be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
It should be noted that by this present embodiment for executing the device for putting cloud filtering method based on image procossing
It is based on identical inventive concept with the above-mentioned point cloud filtering method based on image procossing, it is therefore, corresponding in embodiment of the method
Content is equally applicable to present apparatus embodiment, and and will not be described here in detail.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can borrow
Help software that the mode of general hardware platform is added to realize.It will be appreciated by those skilled in the art that realizing in above-described embodiment method
All or part of the process is relevant hardware can be instructed to complete by computer program, and the program can be stored in meter
In calculation machine read/write memory medium, the program is when being executed, it may include such as the process of the embodiment of the above method.Wherein, described
Storage medium can be magnetic disk, CD, read-only memory (ReadOnly Memory, ROM) or random access memory
(Random Access Memory, RAM) etc..
It is to be illustrated to preferable implementation of the invention, but the invention is not limited to above-mentioned embodiment party above
Formula, those skilled in the art can also make various equivalent variations on the premise of without prejudice to spirit of the invention or replace
It changes, these equivalent deformations or replacement are all included in the scope defined by the claims of the present application.
Claims (8)
1. a kind of point cloud filtering method based on image procossing, which comprises the following steps: client obtains initial point
Cloud, and the scattered points of the initial point cloud are filtered;
The client obtains corresponding initial point cloud coordinate in initial point Yun Dian cloud coordinate system, to the initial point cloud coordinate
It is numbered, show that uniquely corresponding coordinate is numbered with the initial point cloud coordinate;
The initial point cloud coordinate is converted into the integer point cloud coordinate that data type is integer by the client, establishes image seat
Mark system, and the integer point cloud coordinate is mapped in described image coordinate system;
The client obtains the mapping image being made of the data in described image coordinate system, connects to the mapping image zooming-out
After reduction of fractions to a common denominator amount, target connected domain is set by the connected domain that described image coordinate pair answers the integer point cloud coordinate most, and will
Other connected domains filter out;
Coordinate number included in the target connected domain is obtained, is numbered according to the coordinate integer point cloud coordinate is extensive
It again at corresponding initial point cloud coordinate, and maps in described cloud coordinate system, completes point cloud filtering.
2. a kind of point cloud filtering method based on image procossing according to claim 1, it is characterised in that: the initial point
Scattered points in cloud are filtered by k nearest neighbor algorithm.
3. a kind of point cloud filtering method based on image procossing according to claim 1, it is characterised in that: described image is sat
Mark system establishes according to the origin of described cloud coordinate system, x-axis and y-axis.
4. a kind of point cloud filtering method based on image procossing according to claim 1, it is characterised in that: the integer point
Coordinate value in cloud coordinate is by the value that obtains after the coordinate value round of the initial point cloud coordinate.
5. a kind of point cloud filtering method based on image procossing according to claim 1, which is characterized in that described to described
Before mapping image zooming-out connected component, further includes: carry out closure operation to the mapping image to make the region of fracture up.
6. a kind of for executing the device of the point cloud filtering method based on image procossing, which is characterized in that including CPU element, institute
CPU element is stated for executing following steps:
Client obtains initial point cloud, and the scattered points of the initial point cloud are filtered;
The client obtains corresponding initial point cloud coordinate in initial point Yun Dian cloud coordinate system, to the initial point cloud coordinate
It is numbered, show that uniquely corresponding coordinate is numbered with the initial point cloud coordinate;
The initial point cloud coordinate is converted into the integer point cloud coordinate that data type is integer by the client, establishes image seat
Mark system, and the integer point cloud coordinate is mapped in described image coordinate system;
The client obtains the mapping image being made of the data in described image coordinate system, connects to the mapping image zooming-out
After reduction of fractions to a common denominator amount, target connected domain is set by the connected domain that described image coordinate pair answers the integer point cloud coordinate most, and will
Other connected domains filter out;
Coordinate number included in the target connected domain is obtained, is numbered according to the coordinate integer point cloud coordinate is extensive
It again at corresponding initial point cloud coordinate, and maps in described cloud coordinate system, completes point cloud filtering.
7. according to claim 6 a kind of for executing the device of the point cloud filtering method based on image procossing, feature
It is, the CPU element is also used to execute following steps: closure operation is carried out to make the area of fracture up to the mapping image
Domain.
8. a kind of computer readable storage medium, it is characterised in that: the computer-readable recording medium storage has computer can
It executes instruction, the computer executable instructions are for making computer execute a kind of base as described in any one in claim 1-5
In the point cloud filtering method of image procossing.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910692496.6A CN110458772B (en) | 2019-07-30 | 2019-07-30 | Point cloud filtering method and device based on image processing and storage medium |
PCT/CN2020/078288 WO2021017471A1 (en) | 2019-07-30 | 2020-03-06 | Point cloud filtering method based on image processing, apparatus, and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910692496.6A CN110458772B (en) | 2019-07-30 | 2019-07-30 | Point cloud filtering method and device based on image processing and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110458772A true CN110458772A (en) | 2019-11-15 |
CN110458772B CN110458772B (en) | 2022-11-15 |
Family
ID=68483925
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910692496.6A Active CN110458772B (en) | 2019-07-30 | 2019-07-30 | Point cloud filtering method and device based on image processing and storage medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN110458772B (en) |
WO (1) | WO2021017471A1 (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111275633A (en) * | 2020-01-13 | 2020-06-12 | 五邑大学 | Point cloud denoising method, system and device based on image segmentation and storage medium |
CN111275810A (en) * | 2020-01-17 | 2020-06-12 | 五邑大学 | K nearest neighbor point cloud filtering method and device based on image processing and storage medium |
CN111340728A (en) * | 2020-02-26 | 2020-06-26 | 五邑大学 | Point cloud denoising method and device based on 3D point cloud segmentation and storage medium |
WO2021017471A1 (en) * | 2019-07-30 | 2021-02-04 | 五邑大学 | Point cloud filtering method based on image processing, apparatus, and storage medium |
CN112907164A (en) * | 2019-12-03 | 2021-06-04 | 北京京东乾石科技有限公司 | Object positioning method and device |
WO2022233004A1 (en) * | 2021-05-06 | 2022-11-10 | Oppo广东移动通信有限公司 | Point cloud encoding method, point cloud decoding method, encoder, decoder and computer storage medium |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114596196A (en) * | 2022-03-04 | 2022-06-07 | 北京百度网讯科技有限公司 | Method and device for filtering point cloud data, equipment and storage medium |
CN117408913B (en) * | 2023-12-11 | 2024-02-23 | 浙江托普云农科技股份有限公司 | Method, system and device for denoising point cloud of object to be measured |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070253635A1 (en) * | 2006-04-28 | 2007-11-01 | Hon Hai Precision Industry Co., Ltd. | System and method for filtering point clouds |
US7317456B1 (en) * | 2002-12-02 | 2008-01-08 | Ngrain (Canada) Corporation | Method and apparatus for transforming point cloud data to volumetric data |
CN103853840A (en) * | 2014-03-18 | 2014-06-11 | 中国矿业大学(北京) | Filter method of nonuniform unorganized-point cloud data |
US20160027208A1 (en) * | 2014-07-25 | 2016-01-28 | Kabushiki Kaisha Toshiba | Image analysis method |
CN107194962A (en) * | 2017-04-01 | 2017-09-22 | 深圳市速腾聚创科技有限公司 | Point cloud and plane picture fusion method and device |
CN108734772A (en) * | 2018-05-18 | 2018-11-02 | 宁波古德软件技术有限公司 | High accuracy depth image acquisition methods based on Kinect fusion |
CN108986048A (en) * | 2018-07-18 | 2018-12-11 | 大连理工大学 | Based on the quick compound filter processing method of line laser structured light three-dimensional point cloud |
CN109472852A (en) * | 2018-10-29 | 2019-03-15 | 百度在线网络技术(北京)有限公司 | Display methods and device, the equipment and storage medium of point cloud chart picture |
US20190164018A1 (en) * | 2017-11-27 | 2019-05-30 | TuSimple | System and method for drivable road surface representation generation using multimodal sensor data |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8885925B2 (en) * | 2013-03-12 | 2014-11-11 | Harris Corporation | Method for 3D object identification and pose detection using phase congruency and fractal analysis |
CN103996052B (en) * | 2014-05-12 | 2017-05-31 | 深圳市唯特视科技有限公司 | Three-dimensional face gender classification method based on three-dimensional point cloud |
CN107702663B (en) * | 2017-09-29 | 2019-12-13 | 五邑大学 | Point cloud registration method based on rotating platform with mark points |
CN109255813B (en) * | 2018-09-06 | 2021-03-26 | 大连理工大学 | Man-machine cooperation oriented hand-held object pose real-time detection method |
CN110458772B (en) * | 2019-07-30 | 2022-11-15 | 五邑大学 | Point cloud filtering method and device based on image processing and storage medium |
-
2019
- 2019-07-30 CN CN201910692496.6A patent/CN110458772B/en active Active
-
2020
- 2020-03-06 WO PCT/CN2020/078288 patent/WO2021017471A1/en active Application Filing
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7317456B1 (en) * | 2002-12-02 | 2008-01-08 | Ngrain (Canada) Corporation | Method and apparatus for transforming point cloud data to volumetric data |
US20070253635A1 (en) * | 2006-04-28 | 2007-11-01 | Hon Hai Precision Industry Co., Ltd. | System and method for filtering point clouds |
CN103853840A (en) * | 2014-03-18 | 2014-06-11 | 中国矿业大学(北京) | Filter method of nonuniform unorganized-point cloud data |
US20160027208A1 (en) * | 2014-07-25 | 2016-01-28 | Kabushiki Kaisha Toshiba | Image analysis method |
CN107194962A (en) * | 2017-04-01 | 2017-09-22 | 深圳市速腾聚创科技有限公司 | Point cloud and plane picture fusion method and device |
US20190164018A1 (en) * | 2017-11-27 | 2019-05-30 | TuSimple | System and method for drivable road surface representation generation using multimodal sensor data |
CN108734772A (en) * | 2018-05-18 | 2018-11-02 | 宁波古德软件技术有限公司 | High accuracy depth image acquisition methods based on Kinect fusion |
CN108986048A (en) * | 2018-07-18 | 2018-12-11 | 大连理工大学 | Based on the quick compound filter processing method of line laser structured light three-dimensional point cloud |
CN109472852A (en) * | 2018-10-29 | 2019-03-15 | 百度在线网络技术(北京)有限公司 | Display methods and device, the equipment and storage medium of point cloud chart picture |
Non-Patent Citations (1)
Title |
---|
张建民等: "快速数字条纹投影三维测量***的开发", 《现代电子技术》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021017471A1 (en) * | 2019-07-30 | 2021-02-04 | 五邑大学 | Point cloud filtering method based on image processing, apparatus, and storage medium |
CN112907164A (en) * | 2019-12-03 | 2021-06-04 | 北京京东乾石科技有限公司 | Object positioning method and device |
CN111275633A (en) * | 2020-01-13 | 2020-06-12 | 五邑大学 | Point cloud denoising method, system and device based on image segmentation and storage medium |
CN111275633B (en) * | 2020-01-13 | 2023-06-13 | 五邑大学 | Point cloud denoising method, system, device and storage medium based on image segmentation |
CN111275810A (en) * | 2020-01-17 | 2020-06-12 | 五邑大学 | K nearest neighbor point cloud filtering method and device based on image processing and storage medium |
CN111340728A (en) * | 2020-02-26 | 2020-06-26 | 五邑大学 | Point cloud denoising method and device based on 3D point cloud segmentation and storage medium |
CN111340728B (en) * | 2020-02-26 | 2023-03-21 | 五邑大学 | Point cloud denoising method and device based on 3D point cloud segmentation and storage medium |
WO2022233004A1 (en) * | 2021-05-06 | 2022-11-10 | Oppo广东移动通信有限公司 | Point cloud encoding method, point cloud decoding method, encoder, decoder and computer storage medium |
Also Published As
Publication number | Publication date |
---|---|
WO2021017471A1 (en) | 2021-02-04 |
CN110458772B (en) | 2022-11-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110458772A (en) | A kind of point cloud filtering method, device and storage medium based on image procossing | |
CN110363858B (en) | Three-dimensional face reconstruction method and system | |
US20210110599A1 (en) | Depth camera-based three-dimensional reconstruction method and apparatus, device, and storage medium | |
WO2021142995A1 (en) | Image processing-based k-nearest neighbor point cloud filtering method, apparatus, and storage medium | |
US10810718B2 (en) | Method and device for three-dimensional reconstruction | |
CN112686877B (en) | Binocular camera-based three-dimensional house damage model construction and measurement method and system | |
CN111275633B (en) | Point cloud denoising method, system, device and storage medium based on image segmentation | |
CN103235949B (en) | Image point of interest detection method and device | |
WO2018201677A1 (en) | Bundle adjustment-based calibration method and device for telecentric lens-containing three-dimensional imaging system | |
CN109493389B (en) | Camera calibration method and system based on deep learning | |
CN111105452A (en) | High-low resolution fusion stereo matching method based on binocular vision | |
CN109986201A (en) | Tracking detection method, device, storage medium and the laser welding apparatus of weld seam | |
CN112634172A (en) | 3D printing method and device for generating three-dimensional model by using two-dimensional image | |
CN103839233B (en) | Restoration method for blurred image caused by camera shaking | |
CN108151647A (en) | A kind of image processing method, device and mobile terminal | |
CN112233161B (en) | Hand image depth determination method and device, electronic equipment and storage medium | |
CN111145266B (en) | Fisheye camera calibration method and device, fisheye camera and readable storage medium | |
CN116921932A (en) | Welding track recognition method, device, equipment and storage medium | |
CN117058022A (en) | Depth image denoising method and device, computer equipment and storage medium | |
CN115690364A (en) | AR model acquisition method, electronic device and readable storage medium | |
CN112634439A (en) | 3D information display method and device | |
CN113643406B (en) | Image generation method, electronic device, and computer-readable storage medium | |
Li et al. | Overall well-focused catadioptric image acquisition with multifocal images: a model-based method | |
CN116974671B (en) | Vector surface pickup method and device, electronic equipment and storage medium | |
WO2023062706A1 (en) | Information processing device, information processing method, information processing system, and recording 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 |