CN106951860A - A kind of three-dimensional data intelligent identification Method based on a cloud - Google Patents
A kind of three-dimensional data intelligent identification Method based on a cloud Download PDFInfo
- Publication number
- CN106951860A CN106951860A CN201710165355.XA CN201710165355A CN106951860A CN 106951860 A CN106951860 A CN 106951860A CN 201710165355 A CN201710165355 A CN 201710165355A CN 106951860 A CN106951860 A CN 106951860A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- dimensional point
- substation equipment
- processing
- cloud
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
- G06V20/653—Three-dimensional objects by matching three-dimensional models, e.g. conformal mapping of Riemann surfaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Abstract
The invention discloses a kind of three-dimensional data intelligent identification Method based on a cloud, this method includes:Obtain the three dimensional point cloud of substation equipment;Denoising, the three dimensional point cloud after being handled are carried out to the three dimensional point cloud of substation equipment;The feature of substation equipment is extracted from the three dimensional point cloud after the processing, the feature of the substation equipment extracted is counted;Feature weight is optimized using particle cluster algorithm, the three dimensional point cloud after the processing is classified using distance classification algorithm, classification results are obtained;According to classification results, Attitude estimation is carried out to the three dimensional point cloud after the processing using volume matched method.This method realizes the accuracy for improving data processing.
Description
Technical field
The present invention relates to three-dimensional data identification technology field, more particularly to a kind of three-dimensional data based on a cloud is intelligently known
Other method.
Background technology
At present, 3 D laser scanning can in real time, fast and accurately obtain the point cloud on things surface, can pass through three-dimensional
Laser scanner obtains the profile cloud data of object, and with the development of three-dimensional scanning measurement technology, three dimensional point cloud is three
The application for tieing up the fields such as reconstruct, industrial detection is more and more extensive.In three dimensional point cloud treatment technology, three dimensional point cloud
Classification and Identification is a very important technology, in particular for the Classification and Identification of the three dimensional point cloud of outdoor scene.At present,
Relatively conventional outdoor scene three dimensional point cloud sorting technique mainly passes through the segmentation and the extraction of feature to discrete point
Come what is realized, the sorting technique of conditional random field models is based particularly on, but the sorting technique based on conditional random field models
There is the deficiency of the following aspects:(1) condition random field realizes that the basis of point cloud classifications is the segmentation of a cloud, currently without compared with
For the dividing method of preferable outdoor scene three-dimensional point cloud;(2) it is condition random field minute to put the construction of cloud characteristic vector and calculating
Another important component of class, carried feature is all relatively easy at present, it is impossible to accurately describe the several of object to be sorted
What shape and topological structure, the accuracy of data processing is relatively low.
The content of the invention
It is an object of the invention to provide a kind of three-dimensional data intelligent identification Method based on a cloud, improved with realizing at data
The accuracy of reason.
In order to solve the above technical problems, the present invention provides a kind of three-dimensional data intelligent identification Method based on a cloud, the party
Method includes:
Obtain the three dimensional point cloud of substation equipment;
Denoising, the three dimensional point cloud after being handled are carried out to the three dimensional point cloud of substation equipment;
The feature of substation equipment is extracted from the three dimensional point cloud after the processing, the substation equipment extracted is counted
Feature;
Feature weight is optimized using particle cluster algorithm, using distance classification algorithm to the three-dimensional point after the processing
Cloud data are classified, and obtain classification results;
According to classification results, Attitude estimation is carried out to the three dimensional point cloud after the processing using volume matched method.
It is preferred that, the three dimensional point cloud of substation equipment is obtained using laser scanner.
It is preferred that, the three dimensional point cloud to substation equipment carries out denoising, the three-dimensional point after being handled
Cloud data, including:
In the three dimensional point cloud of substation equipment, substation equipment base and the corresponding three-dimensional of top antenna are removed
Cloud data, obtains remaining three dimensional point cloud.
It is preferred that, the feature of substation equipment is extracted in the three dimensional point cloud from after the processing, statistics is extracted
Substation equipment feature, including:
For the three dimensional point cloud after processing, the projected boundary of three dimensional point cloud is extracted, border curvature is calculated;
Extract the envelope volume and length, width and height of three dimensional point cloud;
The layering projected area of three dimensional point cloud is extracted, statistics with histogram is carried out;
Plan range, point cloud closeness and elevation difference according to three dimensional point cloud are extracted to gray feature.
It is preferred that, remove substation equipment base and the corresponding three-dimensional point of top antenna using delamination area situation of change
Cloud data.
It is preferred that, it is described obtain remaining three dimensional point cloud after, also include:
Remaining three dimensional point cloud is simplified, the data after being simplified.
It is preferred that, it is described according to classification results, the three dimensional point cloud after the processing is carried out using volume matched method
Attitude estimation, including:
Calculate the barycenter of the three dimensional point cloud after the processing;
The barycenter of three dimensional point cloud after the processing is coincided with template particle, volume matched degree is calculated;
Three dimensional point cloud after the processing is rotated in the horizontal direction, volume matched degree is calculated, matter is recorded
The heart, volume matched degree and the anglec of rotation.
A kind of three-dimensional data intelligent identification Method based on a cloud provided by the present invention, obtains the three-dimensional of substation equipment
Cloud data;Denoising, the three dimensional point cloud after being handled are carried out to the three dimensional point cloud of substation equipment;From institute
The feature that substation equipment is extracted in the three dimensional point cloud after processing is stated, the feature of the substation equipment extracted is counted;Utilize
Particle cluster algorithm is optimized to feature weight, and the three dimensional point cloud after the processing is divided using distance classification algorithm
Class, obtains classification results;According to classification results, attitude is carried out to the three dimensional point cloud after the processing using volume matched method
Estimation.It can be seen that, this method can automatically be classified to the three dimensional point cloud of substation equipment, by substation equipment base point cloud
And top antenna is automatically removed, and Attitude estimation can be carried out to cloud data according to classification results, with more preferable robust
Property and higher accuracy, can improve the efficiency and nicety of grading of data processing, can preferably realize transformer station's cloud data
Classification and Identification.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
The accompanying drawing to be used needed for having technology description is briefly described, it should be apparent that, drawings in the following description are only this
The embodiment of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can also basis
The accompanying drawing of offer obtains other accompanying drawings.
Fig. 1 is a kind of flow chart of the three-dimensional data intelligent identification Method based on a cloud provided by the present invention;
Fig. 2 is the specific implementation flow chart of the three-dimensional data intelligent identification Method based on a cloud;
Fig. 3 is the particular flow sheet of data compaction and noise remove;
Fig. 4 is the particular flow sheet of substation equipment feature extraction;
Fig. 5 is the particular flow sheet for levying weight optimization and classifier design;
Fig. 6 is the particular flow sheet of Attitude estimation.
Embodiment
The core of the present invention is to provide a kind of three-dimensional data intelligent identification Method based on a cloud, is improved with realizing at data
The accuracy of reason.
In order that those skilled in the art more fully understand the present invention program, below in conjunction with the embodiment of the present invention
Accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is only
A part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
Fig. 1 is refer to, Fig. 1 is a kind of flow of the three-dimensional data intelligent identification Method based on a cloud provided by the present invention
Figure, this method includes:
S11:Obtain the three dimensional point cloud of substation equipment;
S12:Denoising, the three dimensional point cloud after being handled are carried out to the three dimensional point cloud of substation equipment;
S13:The feature of substation equipment is extracted from the three dimensional point cloud after processing, the substation equipment extracted is counted
Feature;
S14:Feature weight is optimized using particle cluster algorithm, using distance classification algorithm to the three-dimensional point after processing
Cloud data are classified, and obtain classification results;
S15:According to classification results, Attitude estimation is carried out to the three dimensional point cloud after processing using volume matched method.
It can be seen that, this method can automatically be classified to the three dimensional point cloud of substation equipment, by substation equipment base
Point cloud and top antenna are automatically removed, and can carry out Attitude estimation to cloud data according to classification results, with more preferable
Robustness and higher accuracy, can improve the efficiency and nicety of grading of data processing, can preferably realize power transformation site cloud
The Classification and Identification of data.
Based on the above method, specifically, in step S11, the three-dimensional point cloud of substation equipment is obtained using laser scanner
Data.
Further, step S12 process is specially:In the three dimensional point cloud of substation equipment, transformer station is removed
Plant bottom case and the corresponding three dimensional point cloud of top antenna, obtain remaining three dimensional point cloud.Due to removing transformer station
Plant bottom case and the corresponding three dimensional point cloud of top antenna, so as to remove the noise spot larger on classification influence.
Wherein, in step S12, substation equipment base and top antenna correspondence are removed using delamination area situation of change
Three dimensional point cloud.
Wherein, obtain after remaining three dimensional point cloud, also include:Remaining three dimensional point cloud is simplified,
Data after being simplified.
Further, step S13 process is specifically included:
S1:For the three dimensional point cloud after processing, the projected boundary of three dimensional point cloud is extracted, border curvature is calculated;
S2:Extract the envelope volume and length, width and height of three dimensional point cloud;
S3:The layering projected area of three dimensional point cloud is extracted, statistics with histogram is carried out;
S4:Plan range, point cloud closeness and elevation difference according to three dimensional point cloud are carried to gray feature
Take.
Specifically, after step S4, also including:Three dimensional point cloud normal vector is asked for using PCA, is carried out
Statistics with histogram.
Wherein, in step S2, the geometric description features such as the envelope volume and length and width height of cloud data are extracted.
Wherein, step S14 includes:Initial range classifier design;Optimize feature weight using particle cluster algorithm, determine excellent
Grader after change.
Further, step S15 process is specially:The barycenter of three dimensional point cloud after calculating processing;After handling
The barycenter of three dimensional point cloud coincided with template particle, calculate volume matched degree;Three dimensional point cloud after processing is existed
Horizontal direction is rotated, and calculates volume matched degree, record barycenter, volume matched degree and the anglec of rotation.
Wherein, in centroid calculation, three dimensional point cloud barycenter is calculated, horizontal direction is only considered, vertical direction wouldn't can be examined
Consider.In volume matched, the particle of cloud data and template particle are coincided, volume matched degree is calculated, what volume here referred to
The envelope volume of a cloud, volume matched degree be pending cloud and template point cloud common factor volume and the ratio of union volume
Value records ratio and barycenter come what is represented.In three dimensional point cloud rotation, cloud data is rotated in the horizontal direction,
Rotating range is 0-360 degree, it is contemplated that time factor, and angle rotary step is set to 5 degree, after rotation, and barycenter is overlapped, and calculates body
Product matching degree, record.Three dimensional point cloud after processing is rotated in the horizontal direction, calculate volume matched degree it
Afterwards, also to carry out barycenter change, the barycenter variation pattern used herein be using initial barycenter as the center of circle, using certain step-length as
Radius, sets total step-length, on these concentric circles counterclockwise every 45 degree take a point, as the barycenter of pending data, then
Cube ratio, record barycenter, volume matched degree and the anglec of rotation.
Detailed, based on this method, with reference to Fig. 2, specific implementation flow is as follows:
Step A:Cloud data is obtained using vehicle-mounted three-dimensional laser scanner;
Step B:Data compaction and noise remove;
Wherein, such as Fig. 3, step B is specifically included:
Step B1:The removal of substation equipment base and top electric wire;
Wherein, in the cloud data of scanning, the cloud data base and part electric wire for having split completion are still present,
Have influence on the feature extraction to cloud data.Therefore, the first step of data processing, just should remove influence larger using related software
Noise spot.The present invention is according to the intrinsic features of shape of substation equipment, generally, the part of base and equipment connection with
And the coupling part of equipment and electric wire has a situation of sharply changing section, the present invention be exactly using area and area change rate this
Feature removes base and top electric wire;
Step B2:Data compaction.
Wherein, the outstanding feature of Vehicle-borne Laser Scanning is that a cloud is very intensive, and data volume is big, if this data is directly applied
Follow-up Classification and Identification needs huge computer resource and very long calculating time.Therefore, it is necessary to keep certain essence
On the premise of degree, test data is simplified.Different types of cloud can use different point cloud compressing modes.
Step C:Substation equipment feature extraction;
Wherein, cloud data is set according to transformer station and Classification and Identification is carried out to it, it is necessary to from substation equipment point Yun Zhongjin
Row feature extraction, selection is suitable and is capable of the feature of indicator substation equipment essence;
Wherein, with reference to Fig. 4, step C is specifically included:
Step C1:Cloud data projected boundary is extracted, border curvature is calculated;
Step C2:Extract the geometric description features such as the envelope volume and length and width height of cloud data;
Step C3:The layering projected area of cloud data is extracted, statistics with histogram is carried out;
Step C4:Plan range based on cloud data, point cloud closeness and elevation difference are carried to gray feature
Take;
Step C5:Cloud data normal vector is asked for using PCA, statistics with histogram is carried out.
Step D:Feature weight optimizes and classifier design;
Wherein, based on extracted feature, the present invention is improved to particle cluster algorithm, improves accuracy and speed,
And apply improvement particle cluster algorithm and feature weight optimization;
Wherein, with reference to Fig. 5, step D is specifically included:
Step D1:Initial range classifier design;
Step D2:Optimize feature weight using particle cluster algorithm, it is determined that grader after optimization.
Wherein, during optimizing feature weight using particle cluster algorithm, specific Optimization Steps include:1st, initialization is set
Put:Population invariable number 20, iterations 100 searches for dimension 122;2nd, population is evaluated:Calculate the fitness value of particle;3rd, determine individual
Body and global optimum:Particle fitness value is calculated, and is compared with the particle adaptive optimal control angle value, to determine whether to optimal suitable
Response is updated;4th, the renewal of particle position;5th, termination condition is checked, optimizing is terminated if meeting, conversely, and going to step 2.
Step E:Attitude estimation.
The present invention carries out Attitude estimation according to the result of Classification and Identification to cloud data.
Wherein, with reference to Fig. 6, step E is specifically included:
Step E1:Centroid calculation:The barycenter of pending cloud equipment is calculated, wherein, only consider horizontal direction, vertical direction
It can put aside;
Step E2:Volume matched:The particle of pending cloud data and template particle are coincided, volume matched is calculated
Degree, volume here refers to the envelope volume of a cloud, volume matched degree be a process points cloud and template common factor volume
Represented with the ratio of union volume, record ratio and barycenter;
Step E3:Cloud data rotates:Pending cloud is rotated in the horizontal direction, rotating range is 0-360 degree,
In view of time factor, angle rotary step is set to 5 degree, after rotation, and barycenter is overlapped, and calculates volume matched degree, records matter
The heart changes;
Step E4:Change the barycenter of pending cloud data, method employed herein be using initial barycenter as the center of circle, with
Certain step-length is radius, sets total step-length, and every 45 degree counterclockwise take a point on these concentric circles, are used as pending data
Barycenter, then according to above-mentioned steps cube ratio, record barycenter, volume matched degree and the anglec of rotation.
This method is directed to transformer station's scene, and the three dimensional point cloud of transformer station's scene is obtained first with laser scanner,
Then the features such as the length, width and height that can describe substation equipment, point cloud gray scale, layering projected area, point cloud normal vector are extracted, are entered
The construction of row point cloud characteristic vector, while just carrying out selection optimization to the weight of characteristic vector using particle cluster algorithm, and is utilized
Distance classifier carries out Classification and Identification to substation equipment cloud data.This method can improve the efficiency and classification essence of data processing
Degree, can preferably realize the Classification and Identification of transformer station's cloud data.
A kind of three-dimensional data intelligent identification Method based on a cloud provided by the present invention is described in detail above.
Specific case used herein is set forth to the principle and embodiment of the present invention, and the explanation of above example is to use
Understand the method for the present invention and its core concept in help.It should be pointed out that for those skilled in the art,
Under the premise without departing from the principles of the invention, some improvement and modification can also be carried out to the present invention, these improve and modified
Fall into the protection domain of the claims in the present invention.
Claims (7)
1. a kind of three-dimensional data intelligent identification Method based on a cloud, it is characterised in that including:
Obtain the three dimensional point cloud of substation equipment;
Denoising, the three dimensional point cloud after being handled are carried out to the three dimensional point cloud of substation equipment;
The feature of substation equipment is extracted from the three dimensional point cloud after the processing, the spy of the substation equipment extracted is counted
Levy;
Feature weight is optimized using particle cluster algorithm, using distance classification algorithm to the three-dimensional point cloud number after the processing
According to being classified, classification results are obtained;
According to classification results, Attitude estimation is carried out to the three dimensional point cloud after the processing using volume matched method.
2. the method as described in claim 1, it is characterised in that the three-dimensional point cloud of substation equipment is obtained using laser scanner
Data.
3. the method as described in claim 1, it is characterised in that the three dimensional point cloud to substation equipment carries out denoising
Processing, the three dimensional point cloud after being handled, including:
In the three dimensional point cloud of substation equipment, substation equipment base and the corresponding three-dimensional point cloud of top antenna are removed
Data, obtain remaining three dimensional point cloud.
4. method as claimed in claim 3, it is characterised in that extract and become in the three dimensional point cloud from after the processing
The feature of power station equipment, counts the feature of the substation equipment extracted, including:
For the three dimensional point cloud after processing, the projected boundary of three dimensional point cloud is extracted, border curvature is calculated;
Extract the envelope volume and length, width and height of three dimensional point cloud;
The layering projected area of three dimensional point cloud is extracted, statistics with histogram is carried out;
Plan range, point cloud closeness and elevation difference according to three dimensional point cloud are extracted to gray feature.
5. method as claimed in claim 3, it is characterised in that remove substation equipment base using delamination area situation of change
And the corresponding three dimensional point cloud of top antenna.
6. method as claimed in claim 3, it is characterised in that it is described obtain remaining three dimensional point cloud after, also include:
Remaining three dimensional point cloud is simplified, the data after being simplified.
7. the method as described in any one in claim 1 to 6, it is characterised in that described according to classification results, utilizes volume
Matching method carries out Attitude estimation to the three dimensional point cloud after the processing, including:
Calculate the barycenter of the three dimensional point cloud after the processing;
The barycenter of three dimensional point cloud after the processing is coincided with template particle, volume matched degree is calculated;
Three dimensional point cloud after the processing is rotated in the horizontal direction, volume matched degree, record barycenter, body is calculated
Product matching degree and the anglec of rotation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710165355.XA CN106951860A (en) | 2017-03-20 | 2017-03-20 | A kind of three-dimensional data intelligent identification Method based on a cloud |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710165355.XA CN106951860A (en) | 2017-03-20 | 2017-03-20 | A kind of three-dimensional data intelligent identification Method based on a cloud |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106951860A true CN106951860A (en) | 2017-07-14 |
Family
ID=59472030
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710165355.XA Withdrawn CN106951860A (en) | 2017-03-20 | 2017-03-20 | A kind of three-dimensional data intelligent identification Method based on a cloud |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106951860A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107564056A (en) * | 2017-07-26 | 2018-01-09 | 西南交通大学 | A kind of contact net support meanss three dimensional point cloud optimal data frame choosing method |
CN107784666A (en) * | 2017-10-12 | 2018-03-09 | 武汉市工程科学技术研究院 | The detection of terrain and its features three dimensional change and update method based on stereopsis |
CN108053443A (en) * | 2017-11-20 | 2018-05-18 | 中国科学院空间应用工程与技术中心 | A kind of object point cloud pose evaluation method and system based on particle group optimizing |
CN108428219A (en) * | 2018-02-28 | 2018-08-21 | 华南农业大学 | A kind of log diameter measuring method based on three-dimension curved surface |
CN110414351A (en) * | 2019-06-26 | 2019-11-05 | 广东康云科技有限公司 | The intelligent scissor and recognition methods, system and storage medium of substation |
CN110599407A (en) * | 2019-06-21 | 2019-12-20 | 杭州一隅千象科技有限公司 | Human body noise reduction method and system based on multiple TOF cameras in downward inclination angle direction |
CN111310845A (en) * | 2020-02-26 | 2020-06-19 | 广东电网有限责任公司电力科学研究院 | Substation equipment identification method, device and equipment |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101950433A (en) * | 2010-08-31 | 2011-01-19 | 东南大学 | Building method of transformer substation three-dimensional model by using laser three-dimensional scanning technique |
CN106250881A (en) * | 2016-08-25 | 2016-12-21 | 深圳大学 | A kind of target identification method based on three dimensional point cloud and system |
-
2017
- 2017-03-20 CN CN201710165355.XA patent/CN106951860A/en not_active Withdrawn
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101950433A (en) * | 2010-08-31 | 2011-01-19 | 东南大学 | Building method of transformer substation three-dimensional model by using laser three-dimensional scanning technique |
CN106250881A (en) * | 2016-08-25 | 2016-12-21 | 深圳大学 | A kind of target identification method based on three dimensional point cloud and system |
Non-Patent Citations (1)
Title |
---|
李玲侠: "基于三维点云的变电站设备分类识别研究", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107564056A (en) * | 2017-07-26 | 2018-01-09 | 西南交通大学 | A kind of contact net support meanss three dimensional point cloud optimal data frame choosing method |
CN107564056B (en) * | 2017-07-26 | 2020-12-18 | 西南交通大学 | Optimal data frame selection method for three-dimensional point cloud data of contact net supporting device |
CN107784666A (en) * | 2017-10-12 | 2018-03-09 | 武汉市工程科学技术研究院 | The detection of terrain and its features three dimensional change and update method based on stereopsis |
CN108053443A (en) * | 2017-11-20 | 2018-05-18 | 中国科学院空间应用工程与技术中心 | A kind of object point cloud pose evaluation method and system based on particle group optimizing |
CN108053443B (en) * | 2017-11-20 | 2019-08-02 | 中国科学院空间应用工程与技术中心 | A kind of object point cloud pose evaluation method and system based on particle group optimizing |
CN108428219A (en) * | 2018-02-28 | 2018-08-21 | 华南农业大学 | A kind of log diameter measuring method based on three-dimension curved surface |
CN108428219B (en) * | 2018-02-28 | 2021-08-31 | 华南农业大学 | Log diameter measuring and calculating method based on three-dimensional curved surface |
CN110599407A (en) * | 2019-06-21 | 2019-12-20 | 杭州一隅千象科技有限公司 | Human body noise reduction method and system based on multiple TOF cameras in downward inclination angle direction |
CN110414351A (en) * | 2019-06-26 | 2019-11-05 | 广东康云科技有限公司 | The intelligent scissor and recognition methods, system and storage medium of substation |
CN111310845A (en) * | 2020-02-26 | 2020-06-19 | 广东电网有限责任公司电力科学研究院 | Substation equipment identification method, device and equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106951860A (en) | A kind of three-dimensional data intelligent identification Method based on a cloud | |
CN104268539B (en) | A kind of high performance face identification method and system | |
Sahar et al. | Using aerial imagery and GIS in automated building footprint extraction and shape recognition for earthquake risk assessment of urban inventories | |
CN106525000B (en) | Roadmarking automation extracting method based on laser scanning discrete point intensity gradient | |
CN107369161A (en) | A kind of workpiece point cloud segmentation method at random based on the European cluster of improvement | |
CN110807781B (en) | Point cloud simplifying method for retaining details and boundary characteristics | |
CN102324032B (en) | Texture feature extraction method for gray level co-occurrence matrix in polar coordinate system | |
CN107886528A (en) | Distribution line working scene three-dimensional rebuilding method based on a cloud | |
CN103679186B (en) | The method and apparatus of detect and track target | |
CN108121985A (en) | A kind of double pointer meters number reading methods based on machine vision | |
CN113628263A (en) | Point cloud registration method based on local curvature and neighbor characteristics thereof | |
CN102508917B (en) | Multi-dimensional object robust high-speed retrieval and positioning method for some feature images | |
CN111738271B (en) | Method for identifying blocked fruits in natural environment | |
CN106127770A (en) | Contour measuring method and system | |
CN109215112B (en) | Method for marking single-side point cloud model | |
CN104616349A (en) | Local curved surface change factor based scattered point cloud data compaction processing method | |
CN107918953B (en) | Three-dimensional space-based laser scanning power line point cloud extraction method and device | |
CN113327276B (en) | Mobile measurement-oriented general mass point cloud data registration method | |
CN106709500A (en) | Image feature matching method | |
CN115205690B (en) | Method and device for extracting street tree in monomer mode based on MLS point cloud data | |
CN110032936B (en) | Method for extracting maximum circular area of non-parameter hand back vein | |
CN108664733A (en) | Seamed edge characteristic surface topology approaches method for reconstructing | |
CN110288640A (en) | Point cloud registration method based on convex density maximum | |
CN109410265A (en) | A kind of TIN filtering innovatory algorithm based on previous DEM auxiliary | |
CN114663373A (en) | Point cloud registration method and device for detecting surface quality of part |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20170714 |
|
WW01 | Invention patent application withdrawn after publication |