CN107170003A - The model matching method and system of a kind of sail shape outside plate - Google Patents

The model matching method and system of a kind of sail shape outside plate Download PDF

Info

Publication number
CN107170003A
CN107170003A CN201710316974.4A CN201710316974A CN107170003A CN 107170003 A CN107170003 A CN 107170003A CN 201710316974 A CN201710316974 A CN 201710316974A CN 107170003 A CN107170003 A CN 107170003A
Authority
CN
China
Prior art keywords
checked
outside plate
drafting board
shape outside
sail shape
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.)
Pending
Application number
CN201710316974.4A
Other languages
Chinese (zh)
Inventor
程良伦
林嘉华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong University of Technology
Original Assignee
Guangdong University of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangdong University of Technology filed Critical Guangdong University of Technology
Priority to CN201710316974.4A priority Critical patent/CN107170003A/en
Publication of CN107170003A publication Critical patent/CN107170003A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/30Determination of transform parameters for the alignment of images, i.e. image registration
    • G06T7/33Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
    • G06T7/344Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods involving models

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

The invention discloses a kind of model matching method of sail shape outside plate and system, this method comprises the following steps:Obtain the cloud data of drafting board to be checked;The default characteristic value of drafting board to be checked is extracted in cloud data, and sets up the geometrical model of drafting board to be checked;By geometrical model combination k nearest neighbor algorithm and historical data, the template of drafting board to be checked is matched.Such a method can accurately determine whether the type of outside plate is sail shape outside plate before processing, more than 97% matching rate can specifically be reached, in process without planning flue again, the processing efficiency of sail shape outside plate can be improved, shorten the duration needed for processing, so as to improve the operating efficiency of the automatic machine-shaping system of outside plate, the complexity of whole control system is reduced, with certain actual production meaning.

Description

The model matching method and system of a kind of sail shape outside plate
Technical field
The present invention relates to ship hull plate automatic forming technical field, more particularly to a kind of Model Matching side of sail shape outside plate Method.Moreover, it relates to a kind of Model Matching system of the sail shape outside plate of application above method.
Background technology
In the automatic machine-shaping of ship hull plate, because architectural difference is regular not unite than larger between each template type One, there are saddle shaped plate, twisted board, conical plate, sail shape outside plate etc..It is ship hull plate water for automatic detection and the differentiation for being molded curved surface The key technology of fiery machine-shaping.
At present, in the actual production of shipyard, the experience that detection depends primarily on workman with differentiating uses model or sample Case is completed, and detection difficulty is larger, and especially for sail shape outside plate, it is more similar to the geometrical model of twisted board, easily causes The erroneous judgement of sail shape outside plate, increases the complexity of the automatic moulding machining control of sail shape outside plate, process time is by significantly Elongate, processing efficiency is relatively low.
Therefore, the processing efficiency of sail shape outside plate how is improved, is that those skilled in the art need the technology solved to ask at present Topic.
The content of the invention
In view of this, it is an object of the invention to provide a kind of model matching method of sail shape outside plate, sail shape outside plate is improved Processing efficiency.It is a further object of the present invention to provide a kind of Model Matching system of the sail shape outside plate of application above method, carry The high processing efficiency of sail shape outside plate.
To achieve the above object, the present invention provides following technical scheme:
A kind of model matching method of sail shape outside plate, comprises the following steps:
Obtain the cloud data of drafting board to be checked;
The default characteristic value of the drafting board to be checked is extracted in the cloud data, and sets up the geometry of the drafting board to be checked Model;
By the geometrical model combination k nearest neighbor algorithm and historical data, the template of the drafting board to be checked is matched.
Preferably, the default characteristic value includes:
The curvature η 1 of first end face;
The curvature η 2 of second end face;
Torsion resistance δ;
The long L of axis;
The wide W1 of the first end face;
The wide W2 of the second end face;
High H.
Preferably, it is described by the geometrical model combination k nearest neighbor algorithm and historical data, match the drafting board to be checked Template is specifically included:
According to the default characteristic value construction feature vector of extraction, calculate between the drafting board to be checked and history template data Euclidean distance;
The preceding K value closest with the drafting board to be checked is chosen, and matches the type of the drafting board to be checked.
A kind of Model Matching system of sail shape outside plate, including:
Acquisition device, the cloud data for obtaining drafting board to be checked;
Model building device, extracts the default characteristic value of the drafting board to be checked in the cloud data, and sets up described to be checked The geometrical model of drafting board;
Coalignment, by the geometrical model combination k nearest neighbor algorithm and historical data, matches the plate of the drafting board to be checked Type.
Preferably, the acquisition device is 3D laser scanners.
Preferably, the coalignment includes:
Computing module, for the default characteristic value construction feature vector according to extraction, calculates the drafting board to be checked with going through Euclidean distance between history template data;
Judge module, for choosing the preceding K value closest with the drafting board to be checked, and matches the class of the drafting board to be checked Type.
In the model matching method for the sail shape outside plate that the present invention is provided, before processing, the cloud data of outside plate is first obtained, And extract default characteristic value.For sail shape outside plate, the geometrical model between each sail shape outside plate is with necessarily similar Spending, and processing flue can overlap substantially in sail type outside plate.Using this characteristic of sail shape outside plate, according to the default of extraction Characteristic value, k nearest neighbor algorithm and historical data, carry out classified calculating, the fitting of data, draw the type of outside plate to be detected, Accurately to judge whether the outside plate is sail shape outside plate.
If it is determined that being sail shape outside plate, directly the outside plate can be carried out using the process data of existing sail shape outside plate in processing Processing, the flame intensity fired due to the sail shape outside plate of every kind of specification, process velocity process the change of flue for outside each All it is similar for plate, the outer template variable after processing each time, which can be assumed that, to be more or less the same, and need to only be finely adjusted.
Such a method is by the accurate type for determining outside plate before processing, in process without planning flue again, The processing efficiency of sail shape outside plate can be improved, shortens the duration needed for processing, so as to improve the automatic machine-shaping system of outside plate Operating efficiency, reduce the complexity of whole control system.
The Model Matching system of the sail shape outside plate of the model matching method of the application that the present invention the is provided sail shape outside plate, passes through The accurate type for determining outside plate before processing, in process without plan flue again, it is possible to increase sail shape outside plate plus Work efficiency rate, shortens the duration needed for processing, so that the operating efficiency of the automatic machine-shaping system of outside plate is improved, the whole control of reduction The complexity of system processed.
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 There is the accompanying drawing used required in technology description to be 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 provided the flow chart of the body embodiment one of the model matching method of sail shape outside plate by invention;
The sail type outside plate geometrical model figure that Fig. 2 is set up by method provided by the present invention;
Fig. 3 is set up the first end face view of sail type outside plate geometrical model by method provided by the present invention;
Fig. 4 is set up the second end face view of sail type outside plate geometrical model by method provided by the present invention;
Fig. 5 is the flow chart of the body embodiment two of the model matching method of sail shape outside plate provided by the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made Embodiment, belongs to the scope of protection of the invention.
The core of the present invention is to provide a kind of model matching method of sail shape outside plate, improves the processing effect of sail shape outside plate Rate.Another core of the present invention is to provide a kind of Model Matching system of the sail shape outside plate of application above method, improves sail shape The processing efficiency of outside plate.
Fig. 1 is refer to, Fig. 1 is provided the flow chart of the body embodiment one of the model matching method of sail shape outside plate by invention.
Step S1:Obtain the cloud data of drafting board to be checked;
Step S2:The default characteristic value of drafting board to be checked is extracted in cloud data, and sets up the geometrical model of drafting board to be checked;
Step S3:By geometrical model combination k nearest neighbor (k-Nearest Neighbour, KNN) algorithm and historical data, Match the template of drafting board to be checked.
A kind of model matching method of sail shape outside plate is present embodiments provided, before processing, the point cloud of outside plate is first obtained Data, and extract default characteristic value.For sail shape outside plate, the geometrical model between each sail shape outside plate is with certain Similarity, and process flue and can be overlapped substantially in sail type outside plate.Using this characteristic of sail shape outside plate, according to extraction Default characteristic value, k nearest neighbor algorithm and historical data, carry out classified calculating, the fitting of data, draw the class of outside plate to be detected Type, accurately to judge whether the outside plate is sail shape outside plate.
If can determine before processing as sail shape outside plate, the processing number of existing sail shape outside plate can be directly utilized in processing It is processed according to the outside plate, flame intensity, process velocity due to the sail shape outside plate firing of every kind of specification process the change of flue It is similar to change for each outside plate, and the outer template variable after processing each time, which can be assumed that, to be more or less the same, only It need to be finely adjusted.
It can be seen that, such a method can accurately determine whether the type of outside plate is sail shape outside plate, can specifically be reached before processing To more than 97% matching rate, in process without planning flue again, it is possible to increase the processing efficiency of sail shape outside plate, contracting Duration needed for short processing, so as to improve the operating efficiency of the automatic machine-shaping system of outside plate, reduces whole control system Complexity, with certain actual production meaning.
In a kind of specific embodiment, the default characteristic value in step S2 can specifically include the curvature η 1 of first end face; The curvature η 2 of second end face;Torsion resistance δ;The long L of axis;The wide W1 of first end face;The wide W2 of second end face;High H.
Wherein, above-mentioned default characteristic value is extracted from drafting board cloud data to be checked.The first end face of drafting board to be checked and second End face is sector, the two ends positioned at axis, and the wide W1 of first end face is the distance between two summits of first end face, The wide W2 of second end face is the distance between two summits of second end face.The fan-shaped center of circle and axis of a height of first end face Line in, the length value of the part between the line on two summits and axis, everywhere high substantially on drafting board to be checked Unanimously.
It refer to Fig. 2 to Fig. 4, the curvature of first end face and second end face, which can specifically pass through equation below and calculate, to be obtained:
Torsion resistance δ computational methods are specifically as follows:Summit V1 using the first end face of drafting board to be checked does one as initial point Parallel to bottom axis, an extended line for crossing summit V2 for second end face is handed in V3, the two of connection outside plate curved surface the same side Individual summit V1, V2, calculate torsion resistance δ:
In the present embodiment, by the extraction to above-mentioned default characteristic value, corresponding characteristic vector can be accurately obtained, Improve the accuracy for treating the judgement of detection plate type.
In a kind of specific embodiment, Fig. 5 is refer to, step S3 may comprise steps of:
Step S31:According to the default characteristic value construction feature of extraction vector, the drafting board to be checked and history template data are calculated Between Euclidean distance;
Step S32:The preceding K value closest with the drafting board to be checked is chosen, and matches the type of drafting board to be checked.Wherein, K For positive integer.
Specifically, so that K takes 7 as an example, comprise the following steps that:
A) construction feature vector, the geometric data using drafting board to be checked is used as feature vector, X i=<η 1, η 2, δ, L, W1, W2, H>, Xi={ ar(Xi), r ∈ 1,2 ..., 7, wherein ar(Xi) represent instance X i r-th of property value, Xj={ ar(Xj) be The characteristic vector value of history template data, calculates Xi, Xj Euclidean distances:
B) the preceding K value closest with Xi is chosen, judges which classification is these Xj values belong to, so as to to be detected Plate is classified.
Above formula represents to take the set of the K value closest with Xi;
Xj→d(Xi,Xj)→N→ψ
Above formula represents the mapping relations between each value, and being embodied as the outside plate type nearest apart from drafting board Xi to be checked is Sail shape outside plate, ψ represents that outside plate type is sail shape outside plate.
Certainly, K value is not limited to 7, or 5,8 or other numerical value.
In the present embodiment, using various template geometric datas in historical data, the number of detection plate is treated with reference to k nearest neighbor algorithm According to Euclidean distance, selection and the closest preceding K numerical value of drafting board data to be checked is calculated, same type of quantity is calculated, tool is taken There is the type of most quantity as the type belonging to drafting board to be checked, so as to accurately know whether the outside plate is sail shape outside plate.
Except the model matching method of above-mentioned sail shape outside plate, present invention also offers the above-mentioned model matching method of one kind application Sail shape outside plate Model Matching system, specifically include:
Acquisition device, the cloud data for obtaining drafting board to be checked;
Model building device, extracts the default characteristic value of drafting board to be checked in cloud data, and sets up the geometry mould of drafting board to be checked Type;
Coalignment, by geometrical model combination k nearest neighbor algorithm and historical data, matches the template of drafting board to be checked.
This system can accurately determine the type of outside plate, can specifically reach before processing due to applying the above method More than 97% matching rate, in process without planning flue again, it is possible to increase the processing efficiency of sail shape outside plate, shortens Duration needed for processing, so as to improve the operating efficiency of the automatic machine-shaping system of outside plate, reduces answering for whole control system Polygamy, with certain actual production meaning.
In a kind of specific embodiment, acquisition device is specifically as follows 3D laser scanners, is swept using 3D laser scanners Drafting board to be checked is retouched, the three-dimensional coordinate information of plate to be matched is obtained, it is more accurate to measure, and obtained cloud data is more comprehensive.
In a kind of specific embodiment, coalignment can specifically include:
Computing module, for the default characteristic value construction feature vector according to extraction, calculates the drafting board to be checked and history plate Euclidean distance between type data;
Judge module, for choosing the preceding K value closest with the drafting board to be checked, and matches the type of drafting board to be checked. Wherein, K is positive integer.
Pass through the setting of computing module and computing module in the present embodiment, it is possible to use various template geometry in historical data Data, and Euclidean distance is calculated with reference to the data that k nearest neighbor algorithm treats detection plate, selection and drafting board data to be checked are closest Preceding K numerical value, calculates same type of quantity, takes the type with most quantity as the type belonging to drafting board to be checked, so that Whether accurately know the outside plate is sail shape outside plate.
The embodiment of each in this specification is described by the way of progressive, and what each embodiment was stressed is and other Between the difference of embodiment, each embodiment identical similar portion mutually referring to.
The model matching method and system of sail shape outside plate provided by the present invention are described in detail above.Herein Apply specific case to be set forth the principle and embodiment of the present invention, the explanation of above example is only intended to help Understand the method and its core concept of the present invention.It should be pointed out that for those skilled in the art, not taking off On the premise of from the principle of the invention, some improvement and modification can also be carried out to the present invention, these are improved and modification also falls into this In invention scope of the claims.

Claims (6)

1. a kind of model matching method of sail shape outside plate, it is characterised in that comprise the following steps:
Obtain the cloud data of drafting board to be checked;
The default characteristic value of the drafting board to be checked is extracted in the cloud data, and sets up the geometry mould of the drafting board to be checked Type;
By the geometrical model combination k nearest neighbor algorithm and historical data, the template of the drafting board to be checked is matched.
2. the model matching method of sail shape outside plate according to claim 1, it is characterised in that the default characteristic value bag Include:
The curvature η 1 of first end face;
The curvature η 2 of second end face;
Torsion resistance δ;
The long L of axis;
The wide W1 of the first end face;
The wide W2 of the second end face;
High H.
3. the model matching method of sail shape outside plate according to claim 2, it is characterised in that described by the geometrical model With reference to k nearest neighbor algorithm and historical data, the template for matching the drafting board to be checked is specifically included:
According to the default characteristic value construction feature vector of extraction, the Europe between the drafting board to be checked and history template data is calculated Family name's distance;
The preceding K value closest with the drafting board to be checked is chosen, and matches the type of the drafting board to be checked.
4. a kind of Model Matching system of sail shape outside plate, it is characterised in that including:
Acquisition device, the cloud data for obtaining drafting board to be checked;
Model building device, extracts the default characteristic value of the drafting board to be checked in the cloud data, and sets up the drafting board to be checked Geometrical model;
Coalignment, by the geometrical model combination k nearest neighbor algorithm and historical data, matches the template of the drafting board to be checked.
5. the Model Matching system of sail shape outside plate according to claim 4, it is characterised in that the acquisition device swashs for 3D Optical scanner.
6. the Model Matching system of sail shape outside plate according to claim 4, it is characterised in that the coalignment includes:
Computing module, for the default characteristic value construction feature vector according to extraction, calculates the drafting board to be checked and history plate Euclidean distance between type data;
Judge module, for choosing the preceding K value closest with the drafting board to be checked, and matches the type of the drafting board to be checked.
CN201710316974.4A 2017-05-08 2017-05-08 The model matching method and system of a kind of sail shape outside plate Pending CN107170003A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710316974.4A CN107170003A (en) 2017-05-08 2017-05-08 The model matching method and system of a kind of sail shape outside plate

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710316974.4A CN107170003A (en) 2017-05-08 2017-05-08 The model matching method and system of a kind of sail shape outside plate

Publications (1)

Publication Number Publication Date
CN107170003A true CN107170003A (en) 2017-09-15

Family

ID=59813506

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710316974.4A Pending CN107170003A (en) 2017-05-08 2017-05-08 The model matching method and system of a kind of sail shape outside plate

Country Status (1)

Country Link
CN (1) CN107170003A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109300192A (en) * 2018-09-03 2019-02-01 常鹏 Exterior trim virtual experience system and method based on 3D scanning

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103810271A (en) * 2014-01-29 2014-05-21 辽宁师范大学 Three-dimensional point cloud object shape feature matching method based on path following
CN103810751A (en) * 2014-01-29 2014-05-21 辽宁师范大学 Three-dimensional auricle point cloud shape feature matching method based on IsoRank algorithm
CN104143189A (en) * 2014-07-16 2014-11-12 华北电力大学 Method for extracting spatial features of 3D point cloud data of power transmission equipment
CN104636762A (en) * 2015-01-20 2015-05-20 辽宁师范大学 Auricle identification method based on unite alpha entropy
CN106023156A (en) * 2016-05-10 2016-10-12 中国商用飞机有限责任公司 Point-cloud model and CAD model registering method based on detection features
CN106021550A (en) * 2016-05-27 2016-10-12 湖南拓视觉信息技术有限公司 Hair style designing method and system
CN106126816A (en) * 2016-06-24 2016-11-16 南京林业大学 Repeat the extensive ALS building point cloud modeling method building under automatic sensing

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103810271A (en) * 2014-01-29 2014-05-21 辽宁师范大学 Three-dimensional point cloud object shape feature matching method based on path following
CN103810751A (en) * 2014-01-29 2014-05-21 辽宁师范大学 Three-dimensional auricle point cloud shape feature matching method based on IsoRank algorithm
CN104143189A (en) * 2014-07-16 2014-11-12 华北电力大学 Method for extracting spatial features of 3D point cloud data of power transmission equipment
CN104636762A (en) * 2015-01-20 2015-05-20 辽宁师范大学 Auricle identification method based on unite alpha entropy
CN106023156A (en) * 2016-05-10 2016-10-12 中国商用飞机有限责任公司 Point-cloud model and CAD model registering method based on detection features
CN106021550A (en) * 2016-05-27 2016-10-12 湖南拓视觉信息技术有限公司 Hair style designing method and system
CN106126816A (en) * 2016-06-24 2016-11-16 南京林业大学 Repeat the extensive ALS building point cloud modeling method building under automatic sensing

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
YONGTAO YU 等: "Three-Dimensional Object Matching in Mobile Laser Scanning Point Clouds", 《IEEE GEOSCIENCE AND REMOTE SENSING LETTERS》 *
ZONGLIANG ZHANG 等: "A FAST METHOD FOR MEASURING THE SIMILARITY BETWEEN 3D MODEL AND 3D POINT CLOUD", 《THE INTERNATIONAL ARCHIVES OF THE PHOTOGRAMMETRY, REMOTE SENSING AND SPATIAL INFORMATION SCIENCES》 *
宋卫东 等著: "《金属矿山采空区灾害防治技术》", 30 September 2015, 北京:冶金工业出版社 *
熊风光 等: "三维点云模型中特征点描述子及其匹配算法研究", 《小型微型计算机***》 *
谭志国 等: "基于点云-模型匹配的激光雷达目标识别", 《计算机工程与科学》 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109300192A (en) * 2018-09-03 2019-02-01 常鹏 Exterior trim virtual experience system and method based on 3D scanning

Similar Documents

Publication Publication Date Title
KR900008555B1 (en) Method and apparatus for for on-line recognizing handwritten patterns
CN102930525B (en) Line matching method based on affine invariant feature and homography
CN103927532B (en) Person&#39;s handwriting method for registering based on stroke feature
CN100590644C (en) Fingerprint identification method combining point with line
CN105303224B (en) A kind of capacity is big, the coded target and its coding/decoding method of strong robustness
CN108010116A (en) Point cloud feature point detecting method and point cloud feature extracting method
CN103400109B (en) A kind of cartographical sketching identified off-line and shaping methods
CN105069093A (en) Embedded index based hydrological time series similarity searching method
CN104076743B (en) A kind of interpolation control method of self-identifying interpolation kind
CN108022232B (en) Aircraft surface rivet detection method
CN103247041A (en) Local sampling-based multi-geometrical characteristic point cloud data splitting method
CN104392223A (en) Method for recognizing human postures in two-dimensional video images
CN108830888B (en) Coarse matching method based on improved multi-scale covariance matrix characteristic descriptor
CN106679667A (en) Method for planning paths of moving bodies for relay navigation of multiple navigation stations
CN109376586B (en) Road boundary line interactive automatic extraction method based on laser point cloud
CN104008257A (en) Reversal design method for component with complex curved surface
CN100412869C (en) Improved file similarity measure method based on file structure
CN103679721A (en) Image contour simplifying method adopting nearest neighbor method Hough transform
CN103954280A (en) Rapid, high-robustness and autonomous fixed star identification method
CN103927056A (en) Stroke segmentation method based on mixing feature for intelligent free-hand input
CN108364257A (en) The joining method and system of 3-D scanning point cloud data
CN107170003A (en) The model matching method and system of a kind of sail shape outside plate
CN106203278B (en) The method and device of two-track road on a kind of extraction map
CN104021372A (en) Face recognition method and device thereof
CN104793492B (en) A kind of indoor environmental characteristic extracting method based on entropy and gray relation grades

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20170915

RJ01 Rejection of invention patent application after publication