CN107705269A - A kind of denoising method in three-dimensional modeling - Google Patents

A kind of denoising method in three-dimensional modeling Download PDF

Info

Publication number
CN107705269A
CN107705269A CN201711023643.8A CN201711023643A CN107705269A CN 107705269 A CN107705269 A CN 107705269A CN 201711023643 A CN201711023643 A CN 201711023643A CN 107705269 A CN107705269 A CN 107705269A
Authority
CN
China
Prior art keywords
dimensional modeling
denoising
image
water
region
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
CN201711023643.8A
Other languages
Chinese (zh)
Inventor
许志海
饶成成
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 Power Grid Co Ltd Patrol Operation Center
Original Assignee
Guangdong Power Grid Co Ltd Patrol Operation Center
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 Power Grid Co Ltd Patrol Operation Center filed Critical Guangdong Power Grid Co Ltd Patrol Operation Center
Priority to CN201711023643.8A priority Critical patent/CN107705269A/en
Publication of CN107705269A publication Critical patent/CN107705269A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00Image enhancement or restoration
    • G06T5/001Image restoration
    • G06T5/002Denoising; Smoothing
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
    • G06K9/46Extraction of features or characteristics of the image
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T15/003D [Three Dimensional] image rendering
    • G06T15/04Texture mapping
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00Three dimensional [3D] modelling, e.g. data description of 3D objects

Abstract

The present invention relates to dimensional Modeling Technology field, more particularly, to the denoising method in a kind of three-dimensional modeling.The present invention is pre-processed by treating the image in modeling region, identify water-surface areas and remove, avoid water-surface areas when carrying out feature extraction and the homotopy mapping of mistake occur, from influenceing to eliminate most noises during three-dimensional modeling in root, make the three-dimensional information to be formed more accurate.The present invention solves the problems, such as part denoising in transmission line of electricity, improves the degree of accuracy of characteristic matching in three-dimensional modeling, shortens the time of characteristic matching, improves engineering efficiency.

Description

A kind of denoising method in three-dimensional modeling
Technical field
The present invention relates to dimensional Modeling Technology field, more particularly, to the denoising method in a kind of three-dimensional modeling.
Background technology
In the maintenance work of transmission line of electricity, the distance of wire and its periphery object such as trees, building etc. is to influence transmission of electricity And an important factor for social personal security, it is main for accurate, the timely actual trend for finding transmission line of electricity, scissors crossing thing etc. The trend of transmission line of electricity is intuitively reacted by establishing the three-dimensional model of power transmission system of complete display.It is right in three-dimensional modeling It is the most key link that the image in region to be modeled, which carries out characteristic matching, and the water-surface areas in image lacks characteristic feature, line Reason also constantly repeats, and causes the characteristic point of extraction very few, can not be correctly correctly same at matching during homotopy mapping Famous cake, the excessive calculating time is consumed, while also generate many noises, easily form the three-dimensional information of mistake.
The content of the invention
The present invention is to overcome at least one defect described in above-mentioned prior art, there is provided the denoising side in a kind of three-dimensional modeling Method, the water-surface areas in area image to be modeled is avoided in feature extraction, reduce the generation of noise, ensure the three-dimensional letter to be formed The accuracy of breath.
In order to solve the above technical problems, present invention employs following technical scheme:
A kind of denoising method in three-dimensional modeling, comprises the following steps:
S1:Flight job platform gathers the striograph in region to be modeled;
S2:The striograph collected is identified, removes the water-surface areas in picture;
S3:Same place detection is carried out to the picture after execution step S2 and matched;
S4:Utilize Extraction of Image high density cloud data;
S5:Utilize high density cloud data structure threedimensional model and mapping textures;
S6:Build real threedimensional model.
Further, it is as follows to the specific identification step of water-surface areas in step S2:
S21:The pool profile in image is detected using Edge Detection;
S22:Pool region is removed by image processing software.
Further, flight job platform includes four oblique photograph cameras and a vertical photography camera, for obtaining One group is just being penetrated and the photo of all around four direction, and combine GPS receiver and, high-precision IMU obtain photography point position and Coordinate information.
Further, high density cloud data is extracted by Pix4D softwares in step S4.
The present invention is pre-processed by treating the image in modeling region, is identified water-surface areas and is removed, avoids Carry out water-surface areas during feature extraction and the homotopy mapping of mistake occur, the noise of the overwhelming majority is eliminated from influence root, Make the three-dimensional information to be formed more accurate.
Compared with prior art, beneficial effect is:Image is identified, eliminates water-surface areas therein, is reduced special The error rate of sign point extraction, reduces the generation of noise from image before characteristic matching, improves formed three-dimensional information Accuracy rate, while the time of characteristic matching is also shortened, effectively increase engineering efficiency.
Brief description of the drawings
Fig. 1 is the flow chart of one embodiment of the invention.
Embodiment
Below in conjunction with the accompanying drawings, the present invention is described further.It should be noted that being given for example only property of accompanying drawing is said It is bright, it is impossible to be interpreted as the limitation to this patent.
As shown in figure 1, the denoising method in a kind of three-dimensional modeling, comprises the following steps:
S1:Flight job platform gathers the striograph in region to be modeled;
S2:The striograph collected is identified, removes the water-surface areas in picture;
S3:Same place detection is carried out to the picture after execution step S2 and matched;
S4:Extraction of Image high density cloud data is utilized by Pix4D softwares;
S5:Utilize high density cloud data structure threedimensional model and mapping textures;
S6:Build real threedimensional model.
Further, it is as follows to the specific identification step of water-surface areas in step S2:
S21:The pool profile in image is detected using Edge Detection;
S22:Pool region is removed by image processing software.
In the present embodiment, flight job platform includes four oblique photograph cameras and a vertical photography camera, is used for One group is obtained just to penetrate and the photo of all around four direction, and combine GPS receiver and, high-precision IMU obtain the position of photography point Put and coordinate information, in Data Post, use aerial triangulation method to provide accurate position and attitude for every photo Information.The present embodiment obtains the image at multiple viewpoints and visual angle using oblique photograph technology, obtains more similar side-information, With higher resolving power and larger field visual angle.
The present invention carries out water-surface areas to the image of acquisition and removes pretreatment, when carrying out same place detection, reduces water The influence of pool light reflection, and wrong homotopy mapping will not be produced near the water surface, the matching of mistake is reduced, in three-dimensional The noise of the overwhelming majority is eliminated in modeling, is improved using transmission line of electricity three-dimensional modeling to carry out the success of potential faults identification Rate, while improve operating efficiency.
Obviously, the above embodiment of the present invention is only intended to clearly illustrate example of the present invention, and is not pair The restriction of embodiments of the present invention.For those of ordinary skill in the field, may be used also on the basis of the above description To make other changes in different forms.There is no necessity and possibility to exhaust all the enbodiments.It is all this All any modification, equivalent and improvement made within the spirit and principle of invention etc., should be included in the claims in the present invention Protection domain within.

Claims (4)

1. the denoising method in a kind of three-dimensional modeling, it is characterised in that comprise the following steps:
S1:Flight job platform gathers the striograph in region to be modeled;
S2:The striograph collected is identified, removes the water-surface areas in picture;
S3:Same place detection is carried out to the picture after execution step S2 and matched;
S4:Utilize Extraction of Image high density cloud data;
S5:Utilize high density cloud data structure threedimensional model and mapping textures;
S6:Build real threedimensional model.
2. the denoising method in a kind of three-dimensional modeling according to claim 1, it is characterised in that to water in the step S2 The specific identification step in face region is as follows:
S21:The pool profile in image is detected using Edge Detection;
S22:Pool region is removed by image processing software.
3. the denoising method in a kind of three-dimensional modeling according to claim 1, it is characterised in that the flight job platform Including four oblique photograph cameras and a vertical photography camera.
4. the denoising method in a kind of three-dimensional modeling according to claim 1, it is characterised in that pass through in the step S4 Pix4D softwares extract high density cloud data.
CN201711023643.8A 2017-10-27 2017-10-27 A kind of denoising method in three-dimensional modeling Pending CN107705269A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711023643.8A CN107705269A (en) 2017-10-27 2017-10-27 A kind of denoising method in three-dimensional modeling

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711023643.8A CN107705269A (en) 2017-10-27 2017-10-27 A kind of denoising method in three-dimensional modeling

Publications (1)

Publication Number Publication Date
CN107705269A true CN107705269A (en) 2018-02-16

Family

ID=61183223

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711023643.8A Pending CN107705269A (en) 2017-10-27 2017-10-27 A kind of denoising method in three-dimensional modeling

Country Status (1)

Country Link
CN (1) CN107705269A (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101286241A (en) * 2008-04-17 2008-10-15 西北工业大学 Three-dimensional architecture rapid modelling approach based on stereopair
CN103606151A (en) * 2013-11-15 2014-02-26 南京师范大学 A wide-range virtual geographical scene automatic construction method based on image point clouds
CN104330074A (en) * 2014-11-03 2015-02-04 熊友谊 Intelligent surveying and mapping platform and realizing method thereof
CN105354883A (en) * 2015-11-25 2016-02-24 武汉大学 3ds Max fast and precise three-dimensional modeling method and system based on point cloud
CN106228609A (en) * 2016-07-09 2016-12-14 武汉广图科技有限公司 A kind of oblique photograph three-dimensional modeling method based on spatial signature information
CN106327573A (en) * 2016-08-25 2017-01-11 成都慧途科技有限公司 Real scene three-dimensional modeling method for urban building
CN106780712A (en) * 2016-10-28 2017-05-31 武汉市工程科学技术研究院 Joint laser scanning and the three-dimensional point cloud generation method of Image Matching
CN107064954A (en) * 2017-05-24 2017-08-18 云南省交通规划设计研究院 A kind of highway topography mapping method and system based on vehicle-mounted and airborne cloud

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101286241A (en) * 2008-04-17 2008-10-15 西北工业大学 Three-dimensional architecture rapid modelling approach based on stereopair
CN103606151A (en) * 2013-11-15 2014-02-26 南京师范大学 A wide-range virtual geographical scene automatic construction method based on image point clouds
CN104330074A (en) * 2014-11-03 2015-02-04 熊友谊 Intelligent surveying and mapping platform and realizing method thereof
CN105354883A (en) * 2015-11-25 2016-02-24 武汉大学 3ds Max fast and precise three-dimensional modeling method and system based on point cloud
CN106228609A (en) * 2016-07-09 2016-12-14 武汉广图科技有限公司 A kind of oblique photograph three-dimensional modeling method based on spatial signature information
CN106327573A (en) * 2016-08-25 2017-01-11 成都慧途科技有限公司 Real scene three-dimensional modeling method for urban building
CN106780712A (en) * 2016-10-28 2017-05-31 武汉市工程科学技术研究院 Joint laser scanning and the three-dimensional point cloud generation method of Image Matching
CN107064954A (en) * 2017-05-24 2017-08-18 云南省交通规划设计研究院 A kind of highway topography mapping method and system based on vehicle-mounted and airborne cloud

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
SKYLINEGLOBE: "实景三维公开课丨倾斜摄影航摄数据处理和三维模型等成果生产标准制定", 《SKYLINEGLOBE》 *
邹小丹: "基于半全局优化的多视影像匹配方法与应用", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Similar Documents

Publication Publication Date Title
AU2019272032B2 (en) Statistical point pattern matching technique
CN103913131B (en) Free curve method vector measurement method based on binocular vision
Zhou et al. Seamless fusion of LiDAR and aerial imagery for building extraction
CN102521884B (en) Three-dimensional roof reconstruction method based on LiDAR data and ortho images
CN108764048B (en) Face key point detection method and device
Kim et al. Semiautomatic reconstruction of building height and footprints from single satellite images
CN104063702A (en) Three-dimensional gait recognition based on shielding recovery and partial similarity matching
CN104050715A (en) High-precision three-dimensional reconstruction method for power transmission line and corridor
US20150110385A1 (en) Photograph localization in a three-dimensional model
CN106157219B (en) Road center line extraction method and device based on vehicle-mounted scanning system
CN109685886A (en) A kind of distribution three-dimensional scenic modeling method based on mixed reality technology
CN107767453B (en) Building LIDAR point cloud reconstruction optimization method based on rule constraint
TW201022708A (en) Method of change detection for building models
Xu et al. Reconstruction of scaffolds from a photogrammetric point cloud of construction sites using a novel 3D local feature descriptor
Dhiman et al. Pothole detection using computer vision and learning
Wang et al. A method for detecting windows from mobile LiDAR data
CN103886289A (en) Direction self-adaptive method and system for identifying on-water bridge targets
CN107978017B (en) Indoor structure rapid modeling method based on frame line extraction
Yoonseok et al. Railway track extraction from mobile laser scanning data
CN107705269A (en) A kind of denoising method in three-dimensional modeling
CN110675449B (en) Binocular camera-based offshore flow detection method
Abdullah et al. LIDAR SEGMENTATION USING SUITABLE SEED POINTS FOR 3D BUILDING EXTRACTION.
Nex et al. New integration approach of Photogrammetric and LIDAR techniques for architectural surveys
CN104236518B (en) A kind of antenna main beam sensing method based on optical imagery and pattern-recognition
CN104616262A (en) H alpha cloud removing method based on quite sun chromospheres background processing

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