CN105513051B - A kind of Processing Method of Point-clouds and equipment - Google Patents
A kind of Processing Method of Point-clouds and equipment Download PDFInfo
- Publication number
- CN105513051B CN105513051B CN201510843574.XA CN201510843574A CN105513051B CN 105513051 B CN105513051 B CN 105513051B CN 201510843574 A CN201510843574 A CN 201510843574A CN 105513051 B CN105513051 B CN 105513051B
- Authority
- CN
- China
- Prior art keywords
- point
- model
- test
- cloud data
- subset
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Abstract
Inventor provides a kind of loose type point cloud data segmentation method and equipment, the present invention relates to the segmentation of radar cloud data, more particularly to loose type cloud data segmentation;Dividing method comprises the steps:S101, input cloud data A, and initial interior point subset B, the subset B of interior point is also the subset of cloud data A, and cloud data A is the set of the point with spatial coherence that radar scanning is formed;S102, by random sample consensus algorithm, calculate for the model b being most consistent with subset B;The all of point of subset B points is not belonging in S103, cloud data A all as test point a, with test point a test model b, and test point will be divided into by interior point, exterior point and unknown point according to test result.For setting up the cloud data fastened in standard cartesian coordinate, we can go to process this group of cloud data and can select to carry out the operation of data compression using above-mentioned dividing method, improve operation efficiency.
Description
Technical field
The present invention relates to the segmentation of radar cloud data, more particularly to loose type cloud data segmentation.
Background technology
In unmanned vehicle (or other robot) field, three-dimensional laser radar (or three-dimensional laser distance measuring sensor) generation
Three-dimensional point cloud accurate detection scanning, the foundation of high-resolution environmental map and vehicle are carried out to environment in unmanned vehicle
In itself positioning in the environment, become important all the more.Therefore, for the treatment of point cloud model, such as curved surface weight of cloud data
Build, split, the research such as feature extraction has turned into study hotspot.
Cloud data segmentation is to determine in a cloud there is same alike result (locus, geometry, laser intensity, spectrum
Feature etc.) region process.Used as the one important work of unmanned vehicle environment sensing, it is the global density according to cloud data
Distribution and local aggregation properties, are clustered and are separated into independent subset, and each subset both corresponds to currently have physical significance
Perceptive object (vehicle such as in environment, trees, building etc.), reflects the geometry and position feature of perceptive object.
Inventor realize it is of the invention during find, loose type cloud data segmentation be a challenging work
Make, because radar data renewal frequency is up to 5-15 hertz, every frame data amount about 400,000, while also having in real-time
Property require, it is therefore necessary to propose the more targetedly partitioning algorithm for loose type cloud data.
The content of the invention
It is given below that one or more aspects are simplified general introduction to try hard to provide the basic comprehension to such aspect.This
The extensive overview of the not all aspect for contemplating of general introduction, and be both not intended to identify the key or decisive of all aspects
Key element is also non-to be attempted to define the scope in terms of any or all.Its unique purpose is to provide one or more in simplified form
Some concepts of individual aspect are as more specifically bright sequence given later.
The present invention provides a kind of loose type point cloud data segmentation method and solves to be directed to the segmentation of loose type cloud data
The problem of big data quantity and requirement of real-time.
To achieve the above object, a kind of loose type point cloud data segmentation method is inventor provided to comprise the steps:
S101, input cloud data A, and initial interior point subset B, the subset B of interior point is also the subset of cloud data A, put cloud
Data A is the set of the point with spatial coherence that radar scanning is formed;
S102, by random sample consensus algorithm, calculate for the model b being most consistent with subset B;
The all of point of subset B points is not belonging in S103, cloud data A all as test point a, mould is tested with test point a
Type b, and test point will be divided into by interior point, exterior point and unknown point according to test result.
Further, the use test point a test model b, and will according to test result by test point be divided into interior point, exterior point and
Unknown point is:
σmodel< tmodelFormula 1
Formula 2
If a test point can not set up formula 1, then the test point can be judged as unknown point;For making formula
1 point set up, if it can set up formula 2, then it will be judged as interior point, will otherwise be judged as exterior point;
Wherein, x is values of the test point a in model b, σmodelIt is the Noise estimation of cloud data, tmodelIt is model b's '
Certainty estimates, model b ' is the model after model b adds test point a, and model is predicted as μmodel, tdataIt is the mark of model b
Quasi- distance estimations, σdataIt is the Noise estimation of data in model b.X can be the data of test point a.
Further, after step s 103, the subset B of point in the test point a additions of interior point will also be belonged to including step
In, repeat step S103 no longer increases until number of repetition reaches preset value c or interior quantity.
Further, step was included before step S101:
S401, the fixed three dimensional network structure that a cell size is r*r*r is set up, and according to cloud data A to net
Cell assignment in lattice, the value of each cell is exactly the expected value of the cloud data in cell;From the adjacent d in space
It is the cloud data E of unit data by expected value that an expected value composition is extracted in individual expected value;
S402, the seed equation screening cloud data E acquisition subset B using setting, subset B is most possibly to belong to ground
The set of the expected value in face;And the cloud data A in step S102-S103 is entered as the calculating of cloud data E participations;
Also include step after step s 103:Interior point, exterior point are divided into cloud data E according to what step S103 was obtained
And unknown point, and cloud data E and cloud data A corresponding relation, by the point in cloud data A be divided into interior point, exterior point,
Unknown point.
Inventor also provides a kind of Point Cloud Processing equipment, point cloud acquisition module, model computation module, model measurement
Module;
Described cloud acquisition module is used to obtaining input cloud data A, and initial interior point subset B, the son of interior point
Collection B is also the subset of cloud data A, and cloud data A is the set of the point with spatial coherence that radar scanning is formed;
The model computation module is used to, by random sample consensus algorithm, calculate for the mould being most consistent with subset B
Type b;
The model measurement module is used to be not belonging in cloud data A all of point of subset B points all as test point
A, with test point a test model b, and will be divided into interior point, exterior point and unknown point according to test result by test point.
Further, the model measurement module is used for
σmodel< tmodelFormula 1
Formula 2
If a test point can not set up formula 1, then the test point can be judged as unknown point;For making formula
1 point set up, if it can set up formula 2, then it will be judged as interior point, will otherwise be judged as exterior point;
Wherein, x is values of the test point a in model b, σmodelIt is the Noise estimation of cloud data, tmodelIt is model b's '
Certainty estimates, model b ' is the model after model b adds test point a, and model is predicted as μmodel, tdataIt is the mark of model b
Quasi- distance estimations, σdataIt is the Noise estimation of data in model b.
Further, the model measurement module is used to belong in the subset B of the interior point of test point a additions of interior point, repeats
Step S103, no longer increases until number of repetition reaches preset value c or interior quantity.
Further, the model measurement module is used to set up the fixed three-dimensional grid knot that a cell size is r*r*r
Structure, and according to cloud data A to the cell assignment in grid, the value of each cell is exactly the cloud data in cell
Expected value;It is the point cloud number of unit data by expected value that an expected value composition is extracted from d adjacent expected value of space
According to E;
Subset B is obtained for the seed equation screening cloud data E using setting, subset B is most possibly to belong to ground
The set of the expected value in face;And cloud data A is entered as the calculating that cloud data E participates in dividing interior point, exterior point and unknown point;
For being divided into interior point, exterior point and unknown point, and cloud data E and point cloud to cloud data E according to what is obtained
The corresponding relation of data A, interior point, exterior point, unknown point are divided into by the point in cloud data A.
Be different from prior art, for setting up the cloud data fastened in standard cartesian coordinate, no matter cloud data
Source be where, or even cloud data can come from multiple sources, and we can go to process this group of point using above-mentioned dividing method
Cloud data, and in a model process in can select to carry out the operation of data compression, to improve operation efficiency.
The above method can be with iteration " search " cloud data to find interior point, and that model will not be brought by unknown point is negative
Face rings.
The segmentation on ground can be can be applied to by the above method, and effectively loose data group can be built
Mould.The above method is to by probability property pair, therefore we can scrupulously define the Decision boundaries of segmentation.The above method is
Continuously, therefore we can be avoided in some dividing methods such as intensive cloud data by using structural grid institute band
The limitation for coming.To address related purpose before reaching, this one or more aspect is included in and is hereinafter fully described and in institute
The feature particularly pointed out in attached claim.The following description and drawings illustrate this one or more aspect some say
Bright property feature.But, these features be only indicate can using various aspects principle various modes in it is several, and
And this description is intended to all such aspects and its equivalent aspect.
Brief description of the drawings
Disclosed aspect is described below with reference to accompanying drawing, there is provided accompanying drawing is non-limiting disclosed side in order to illustrate
Face, label sign similar elements similar in accompanying drawing, and wherein:
Fig. 1 is the iteration result treatment schematic diagram of this method;;
Fig. 2 is the segmentation result that the method for the invention is applied to point cloud data after a specific color dot cloud data input
Schematic diagram;
Fig. 3, this method step schematic diagram.
Specific embodiment
To describe technology contents, structural feature, the objects and the effects of technical scheme in detail, below in conjunction with specific reality
Apply example and coordinate accompanying drawing to be explained in detail.In the following description, elaborate that numerous details are right to provide for explanatory purposes
The thorough understanding of one or more aspects.It will be evident that can also put into practice such aspect without these details.
Interior point refers to the point in segmentation object data.The application of this method can be the classification to original input data,
Interior point (belonging to ground), exterior point (belonging to non-ground object) and unknown point will a little be divide into (cannot be in certain determination
Property under be classified) three classes, it is also possible to be applied to for cloud data to be divided into cluster shown in Fig. 2, cluster ID different in figure are used
Different color marks.
Inventor provides a kind of loose type point cloud data segmentation method, as shown in figure 3, comprising the steps:
S101, input cloud data A, and initial interior point subset B, the subset B of interior point is also the son of cloud data A
Collection, cloud data A is the set of the point with spatial coherence that radar scanning is formed;
S102, by random sample consensus algorithm, calculate for the model b being most consistent with subset B;
The all of point of subset B points is not belonging in S103, cloud data A all as test point a, mould is tested with test point a
Type b, and test point will be divided into by interior point, exterior point and unknown point according to test result.
Above method pseudo table is shown as:
Input:Data, types of models, iseed
Output:I, o, u, model
Parameter:tdata, tmodel
1 i=o=u={ };
2 inew=iseed;
3 work as inewSize>When 0, carry out
4 i=i ∪ inew;
5 model=determine best model (types of models, i);
6 test=data-i;
7 {inew,onew,unew}=detection (model, test, tdata, tmodel);
8 o=o ∪ onew;
9 u=u ∪ unew;
I, o, u and t represent interior point, exterior point, unknown point and threshold values, i respectivelyseedTest point is represented, the number in false code
Conjunction is converged according to point is represented.tmodelFor the certainty of model b is estimated, and tdataFor the gauged distance of model b is estimated, σdataIt is model
The Noise estimation of b, σmodelIt is the Noise estimation of cloud data.
For setting up the cloud data fastened in standard cartesian coordinate, no matter the source of cloud data be where, or even
Cloud data can come from multiple sources, and we can go to process this group of cloud data using above-mentioned dividing method.
And the block of some loose cloud datas can be attributed to terrain environment by common dividing method, or by it
Be attributed to exterior point (outlier) in data group, rather than " the non-ground object " that classifies as them in environment, such as car
, electric pole etc..
Random sample consensus algorithm is RANSAC, and RANSAC is " RANdom SAmple Consensus (random samplings
Abbreviation unanimously) ".It can estimate Mathematical Modeling from one group of observation data set comprising " point not in the know " by iterative manner
Parameter.
The use test point a test model b, and test point will be divided into by interior point, exterior point and unknown point according to test result
For:
σmodel< tmodelFormula 1
Formula 2
If a test point can not set up formula 1, then the test point can be judged as unknown point;For making formula
1 point set up, if it can set up formula 2, then it will be judged as interior point, will otherwise be judged as exterior point;
Wherein, x is values of the test point a in model b, σmodelIt is the Noise estimation of cloud data, tmodelIt is model b's '
Certainty estimates, model b ' is the model after model b adds test point a, and model is predicted as μmodel, tdataIt is the mark of model b
Gauged distance between the prediction (μm odel) of quasi- distance estimations, i.e. test point a and model needs the estimation of many " neighbouring ", σdataFor
The Noise estimation of data in model b.
Preferably, after step s 103, the subset B of point in the test point a additions of interior point will also be belonged to including step
In, repeat step S103 no longer increases until number of repetition reaches preset value c or interior quantity.
So that dividing method can be with " search " data to find interior point, and the negative shadow that model will not be brought by unknown point
Ring.Algorithm can continue iteration, and preset value c is reached until can not again find point or number of repetition in more.
In further embodiments, step was included before step S101:
S401, the fixed three dimensional network structure that a cell size is r*r*r is set up, and according to cloud data A to net
Cell assignment in lattice, the value of each cell is exactly the expected value of the cloud data in cell;From the adjacent d in space
It is the cloud data E of unit data by expected value that an expected value composition is extracted in individual expected value;
S402, the seed equation screening cloud data E acquisition subset B using setting, subset B is most possibly to belong to ground
The set of the expected value in face;And the cloud data A in step S102-S103 is entered as the calculating of cloud data E participations;
Also include step after step s 103:Interior point, exterior point are divided into cloud data E according to what step S103 was obtained
And unknown point, and cloud data E and cloud data A corresponding relation, by the point in cloud data A be divided into interior point, exterior point,
Unknown point.
Above method pseudo table is shown as:
I, o, u and t represent interior point, exterior point, unknown point and threshold values respectively.
Step S401 actually has the data compression of two steps, and is reached come the data in expression unit lattice by with expected value
First compression, the second second compression is reached by extracting an expected value from d adjacent expected value of space.
Seed equation is used for the series of points for going to determine to be most likely to be interior point, used as the seed subset of interior point.This some
It is all to think R in sensor in embodimentsIn the range of radius and less than the substructure height B of sensorsPoint (| x |<RsAnd xz
<Bs) it is chosen as seed subset.
The ability of above method treatment unstructured data enables us to the operation for selecting to carry out data compression, to improve computing
Efficiency.
The above method can be applied to the segmentation on ground.The above method effectively can be modeled to loose data group.And
And based on point, exterior point and unfiled point in probability screening, therefore we can scrupulously define the Decision boundaries of segmentation.It is above-mentioned
Method is continuous, therefore we can be avoided in some dividing methods such as intensive cloud datas due to using structural net
The limitation that lattice are brought.It is the specific calculating process of this method with reference to Fig. 1, initial seed subset is artificial setting, with green
It is marked.A () is output after the first iteration, (b) is the output after three iteration, and (c) is the 16th
It is secondary, be also last time iteration after output.
Inventor also provides a kind of Point Cloud Processing equipment, for performing the above method, Point Cloud Processing equipment bag
Include a cloud acquisition module, model computation module, model measurement module;
Described cloud acquisition module is used to obtaining input cloud data A, and initial interior point subset B, the son of interior point
Collection B is also the subset of cloud data A, and cloud data A is the set of the point with spatial coherence that radar scanning is formed;
The model computation module is used to, by random sample consensus algorithm, calculate for the mould being most consistent with subset B
Type b;
The model measurement module is used to be not belonging in cloud data A all of point of subset B points all as test point
A, with test point a test model b, and will be divided into interior point, exterior point and unknown point according to test result by test point.
In certain embodiments, the model measurement module is used for
σmodel< tmodelFormula 1
Formula 2
If a test point can not set up formula 1, then the test point can be judged as unknown point;For making formula
1 point set up, if it can set up formula 2, then it will be judged as interior point, will otherwise be judged as exterior point;
In certain embodiments, the model measurement module is used to belong to the subset B of the interior point of test point a additions of interior point
In, repeat step S103 no longer increases until number of repetition reaches preset value c or interior quantity.
In certain embodiments, the model measurement module fixes three for setting up a cell size for r*r*r
Dimension network, and according to cloud data A to the cell assignment in grid, the value of each cell is exactly in cell
The expected value of cloud data;It is unit data by expected value that an expected value composition is extracted from d adjacent expected value of space
Cloud data E;
Subset B is obtained for the seed equation screening cloud data E using setting, subset B is most possibly to belong to ground
The set of the expected value in face;And cloud data A is entered as the calculating that cloud data E participates in dividing interior point, exterior point and unknown point;
For being divided into interior point, exterior point and unknown point, and cloud data E and point cloud to cloud data E according to what is obtained
The corresponding relation of data A, interior point, exterior point, unknown point are divided into by the point in cloud data A.
It should be noted that herein, such as first and second or the like relational terms are used merely to a reality
Body or operation make a distinction with another entity or operation, and not necessarily require or imply these entities or deposited between operating
In any this actual relation or order.And, term " including ", "comprising" or its any other variant be intended to
Nonexcludability is included, so that process, method, article or terminal device including a series of key elements not only include those
Key element, but also other key elements including being not expressly set out, or also include being this process, method, article or end
The intrinsic key element of end equipment.In the absence of more restrictions, limited by sentence " including ... " or " including ... "
Key element, it is not excluded that also there is other key element in the process including the key element, method, article or terminal device.This
Outward, herein, " it is more than ", " being less than ", " exceeding " etc. are interpreted as not including this number;" more than ", " below ", " within " etc. understand
It is to include this number.
It should be understood by those skilled in the art that, the various embodiments described above can be provided as method, device or computer program producing
Product.These embodiments can be using the embodiment in terms of complete hardware embodiment, complete software embodiment or combination software and hardware
Form.All or part of step in the method that the various embodiments described above are related to can be instructed by program correlation hardware come
Complete, described program can be stored in the storage medium that computer equipment can read, for performing the various embodiments described above side
All or part of step described in method.The computer equipment, including but not limited to:Personal computer, server, general-purpose computations
Machine, special-purpose computer, the network equipment, embedded device, programmable device, intelligent mobile terminal, intelligent home device, Wearable
Smart machine, vehicle intelligent equipment etc.;Described storage medium, including but not limited to:RAM, ROM, magnetic disc, tape, CD, sudden strain of a muscle
Deposit, USB flash disk, mobile hard disk, storage card, memory stick, webserver storage, network cloud storage etc..
The various embodiments described above are with reference to the method according to embodiment, equipment (system) and computer program product
Flow chart and/or block diagram are described.It should be understood that every during flow chart and/or block diagram can be realized by computer program instructions
The combination of flow and/or square frame in one flow and/or square frame and flow chart and/or block diagram.These computers can be provided
Programmed instruction is to the processor of computer equipment producing a machine so that by the finger of the computing device of computer equipment
Order is produced for realizing what is specified in one flow of flow chart or multiple one square frame of flow and/or block diagram or multiple square frames
The device of function.
These computer program instructions may be alternatively stored in the computer that computer equipment can be guided to work in a specific way and set
In standby readable memory so that instruction of the storage in the computer equipment readable memory is produced and include the manufacture of command device
Product, the command device is realized in one flow of flow chart or multiple one square frame of flow and/or block diagram or multiple square frame middle fingers
Fixed function.
These computer program instructions can be also loaded on computer equipment so that performed on a computing device a series of
Operating procedure is to produce computer implemented treatment, so that the instruction for performing on a computing device is provided for realizing in flow
The step of function of being specified in one flow of figure or multiple one square frame of flow and/or block diagram or multiple square frames.
Although being described to the various embodiments described above, those skilled in the art once know basic wound
The property made concept, then can make other change and modification to these embodiments, so embodiments of the invention are the foregoing is only,
Not thereby scope of patent protection of the invention, the equivalent structure that every utilization description of the invention and accompanying drawing content are made are limited
Or equivalent flow conversion, or other related technical fields are directly or indirectly used in, similarly it is included in patent of the invention
Within protection domain.
Claims (2)
1. a kind of loose type point cloud data segmentation method, it is characterised in that comprise the steps:
S101, input cloud data A, and initial interior point subset B, the subset B of interior point is also the subset of cloud data A,
Cloud data A is the set of the point with spatial coherence that radar scanning is formed;
S102, by random sample consensus algorithm, calculate the model b being most consistent with subset B;
The all of point of subset B points is not belonging in S103, cloud data A all as test point a, with test point a test model b,
And test point will be divided into by interior point, exterior point and unknown point according to test result;
The use test point a test model b, and test point will be divided into by interior point, exterior point and unknown point according to test result and be:
σmodel< tmodelFormula 1
If a test point can not set up formula 1, then the test point can be judged as unknown point;For making 1 one-tenth of formula
Vertical point, if it can set up formula 2, then it will be judged as interior point, will otherwise be judged as exterior point;
Wherein, x is values of the test point a in model b, σmodelIt is the Noise estimation of cloud data, tmodelIt is the determination of model b '
Property estimate, model b ' is the model after model b adds test point a, and model b's is predicted as μmodel, tdataIt is the normal pitch of model b
From estimation, the gauged distance is estimated as the gauged distance between the prediction μm odel of test point a and model b, σxFor in model b
The Noise estimation of data;
After step s 103, also including step, will belong in the test point a additions of interior point in the subset B of point, repeat step
S103, no longer increases until number of repetition reaches preset value c or interior quantity.
2. a kind of Point Cloud Processing equipment, it is characterised in that point cloud acquisition module, model computation module, model measurement module;
Described cloud acquisition module is used to obtaining input cloud data A, and initial interior point subset B, the subset B of interior point
It is the subset of cloud data A, cloud data A is the set of the point with spatial coherence that radar scanning is formed;
The model computation module is used to, by random sample consensus algorithm, calculate the model b being most consistent with subset B;
The model measurement module is used to be not belonging in cloud data A all of point of subset B points all as test point a, uses
Test point a test model b, and test point will be divided into by interior point, exterior point and unknown point according to test result;
The model measurement module is used for
σmodel< tmodelFormula 1
If a test point can not set up formula 1, then the test point can be judged as unknown point;For making 1 one-tenth of formula
Vertical point, if it can set up formula 2, then it will be judged as interior point, will otherwise be judged as exterior point;
Wherein, x is values of the test point a in model b, σmodelIt is the Noise estimation of cloud data, tmodelIt is the determination of model b '
Property estimate, model b ' is the model after model b adds test point a, and model b's is predicted as μmodel, tdataIt is the normal pitch of model b
From estimation, the gauged distance is estimated as the gauged distance between the prediction μm odel of test point a and model b, σxFor in model b
The Noise estimation of data;
The model measurement module is used to belong in the subset B of the interior point of test point a additions of interior point, in repetition cloud data A
The all of point of subset B points is not belonging to all as test point a, with test point a test model b, and will will be surveyed according to test result
Pilot is divided into interior point, exterior point and unknown point, no longer increases until number of repetition reaches preset value c or interior quantity.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510843574.XA CN105513051B (en) | 2015-11-26 | 2015-11-26 | A kind of Processing Method of Point-clouds and equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510843574.XA CN105513051B (en) | 2015-11-26 | 2015-11-26 | A kind of Processing Method of Point-clouds and equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105513051A CN105513051A (en) | 2016-04-20 |
CN105513051B true CN105513051B (en) | 2017-06-20 |
Family
ID=55721008
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510843574.XA Active CN105513051B (en) | 2015-11-26 | 2015-11-26 | A kind of Processing Method of Point-clouds and equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105513051B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107133966B (en) * | 2017-03-30 | 2020-04-14 | 浙江大学 | Three-dimensional sonar image background segmentation method based on sampling consistency algorithm |
CN107220658B (en) * | 2017-05-10 | 2019-05-31 | 中国人民解放军军械工程学院 | A kind of images match point is to screening technique |
US10600199B2 (en) * | 2017-06-27 | 2020-03-24 | Toyota Research Institute, Inc. | Extending object detection and identification capability for an object sensor device |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102915558A (en) * | 2011-08-01 | 2013-02-06 | 李慧盈 | Method for quickly extracting building three-dimensional outline information in onboard LiDAR (light detection and ranging) data |
CN102855663B (en) * | 2012-05-04 | 2015-04-01 | 北京建筑工程学院 | Method for building CSG (Constructive Solid Geometry) model according to laser radar grid point cloud |
CN103236064B (en) * | 2013-05-06 | 2016-01-13 | 东南大学 | A kind of some cloud autoegistration method based on normal vector |
-
2015
- 2015-11-26 CN CN201510843574.XA patent/CN105513051B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN105513051A (en) | 2016-04-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103870845B (en) | Novel K value optimization method in point cloud clustering denoising process | |
CN104573705B (en) | A kind of clustering method of building Point Cloud of Laser Scanner | |
Arbin et al. | Comparative analysis between k-means and k-medoids for statistical clustering | |
CN107392875A (en) | A kind of cloud data denoising method based on the division of k neighbours domain | |
CN102890828B (en) | Point cloud data compacting method based on normal included angle | |
CN112347854A (en) | Rolling bearing fault diagnosis method and system, storage medium, equipment and application | |
CN105118090B (en) | A kind of point cloud filtering method of adaptive complicated landform structure | |
CN105404898B (en) | A kind of loose type point cloud data segmentation method and equipment | |
CN110346654B (en) | Electromagnetic spectrum map construction method based on common kriging interpolation | |
CN105513051B (en) | A kind of Processing Method of Point-clouds and equipment | |
KR20160042126A (en) | Target positioning method and system | |
CN107563653A (en) | Multi-robot full-coverage task allocation method | |
CN103455612B (en) | Based on two-stage policy non-overlapped with overlapping network community detection method | |
CN104866840A (en) | Method for recognizing overhead power transmission line from airborne laser point cloud data | |
CN114723149A (en) | Soil moisture content prediction method and device, electronic equipment and storage medium | |
Song et al. | A continuous space location model and a particle swarm optimization-based heuristic algorithm for maximizing the allocation of ocean-moored buoys | |
CN104038792A (en) | Video content analysis method and device for IPTV (Internet Protocol Television) supervision | |
CN113902861A (en) | Three-dimensional geological modeling method based on machine learning | |
CN106022359A (en) | Fuzzy entropy space clustering analysis method based on orderly information entropy | |
Alburshaid et al. | Palm trees detection using the integration between gis and deep learning | |
CN104951752A (en) | Method for extracting houses from airborne laser point cloud data | |
CN106897705B (en) | Ocean observation big data distribution method based on incremental learning | |
CN115546116A (en) | Method and system for extracting and calculating spacing of discontinuous surface of fully-covered rock mass | |
Raith et al. | Visual Eddy Analysis of the Agulhas Current. | |
CN105279320B (en) | A kind of method for generating FDTD grids |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |