CN105389777A - Unmanned aerial vehicle sequential image rapid seamless splicing system - Google Patents
Unmanned aerial vehicle sequential image rapid seamless splicing system Download PDFInfo
- Publication number
- CN105389777A CN105389777A CN201510697762.6A CN201510697762A CN105389777A CN 105389777 A CN105389777 A CN 105389777A CN 201510697762 A CN201510697762 A CN 201510697762A CN 105389777 A CN105389777 A CN 105389777A
- Authority
- CN
- China
- Prior art keywords
- splicing
- image
- unmanned plane
- aerial vehicle
- unmanned aerial
- 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
Links
- 238000000034 method Methods 0.000 claims abstract description 17
- 230000008569 process Effects 0.000 claims description 9
- 230000008878 coupling Effects 0.000 claims description 6
- 238000010168 coupling process Methods 0.000 claims description 6
- 238000005859 coupling reaction Methods 0.000 claims description 6
- 230000008901 benefit Effects 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 5
- 230000009471 action Effects 0.000 claims description 4
- 238000005192 partition Methods 0.000 claims 1
- 238000012545 processing Methods 0.000 abstract description 3
- 230000000007 visual effect Effects 0.000 abstract description 3
- 238000009825 accumulation Methods 0.000 abstract 1
- 230000004438 eyesight Effects 0.000 description 5
- 230000008030 elimination Effects 0.000 description 3
- 238000003379 elimination reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000003595 mist Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 238000001303 quality assessment method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000004304 visual acuity Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention is named as an unmanned aerial vehicle sequential image rapid seamless splicing system, which aims at the problem of long processing cycle of unmanned aerial vehicle images, and provides an emergency data source for earthquake relief in sudden natural disasters and the like. The unmanned aerial vehicle sequential image rapid seamless splicing system provides a method for performing rapid seamless splicing on task region images just by utilizing sequential images of an unmanned aerial vehicle and recorded GPS information thereof when no other control point exists. Firstly, the task region images are partitioned according to GPS coordinate information so as to reduce accumulation of splicing errors; then a SIFT (Scale Invariant Feature Transform) algorithm is used for image matching, removing wrong matching points and acquiring homonymy points; finally, disclosing a ''power distance ratio stretching" splicing seam removing algorithm which has small time overhead. Take the unmanned aerial vehicle images of Hanwang in Sichuan after the earthquake for example, the unmanned aerial vehicle sequential image rapid seamless splicing system only needs 3 hours to complete the splicing of 678 images of the overall task region, has good visual effect of the splicing result, can meet the urgent demand of acquiring real-time high-resolution images timely under emergency conditions of natural disasters, and assists in the planning of post-disaster emergency measures.
Description
Technical field
The present invention relates to a whole set of unmanned plane image joint treatment scheme, be mainly divided into image block, images match, Seamlines removing three parts.
The present invention proposes a kind of new error hiding elimination method: can produce some error matching points after carrying out GPU-SIFT coupling, set about from unmanned aerial vehicle remote sensing platform and its own sequence imaging characteristic, propose a kind of error hiding elimination method based on " vector consistency ".
The present invention also proposes a kind ofly fast splicing seams place inconsistent phenomenon to be distributed to adaptively that whole overlay region seamlessly transits to reach vision, dislocation-free, method of seam-line elimination without ghost effect.
Background technology
As a kind of new remote-sensing flatform, unmanned plane has maneuverability, low cost, high resolving power, high timeliness, operation and safeguards the features such as simple, in buildings City Regions, dangerous operation district, hills with a varied topography and cloudy mist area relative to the Aerial Photogrammetry of routine, there is stronger adaptability.Its range of application is also continuing to widen, and in national defence, environmental protection, the disaster relief etc., plays more and more important effect.But by the restriction of self remote-sensing flatform and its non-scalability sensor carried, obtain image data and have following features:
1) individual image area coverage is little, and image quantity is many;
2) geometric distortion is larger;
3) ship's control and sidelapping degree all very high.
The process of current unmanned aerial vehicle remote sensing images can be divided into two large classes: a class merges after carrying out images match to unmanned plane sequential images again, finally carries out geometric correction process, this is unmanned plane image processing mode comparatively widely, as the unmanned plane image processing scheme that Tian Fuqin company proposes.Another kind of is that traditionally photogrammetric image joint flow process processes, this mode requires all higher to the precision of attitude parameter and the quality of image, result precision affects comparatively large by fuselage carrying equipment, the algorithm proposed as people such as Wang Conghua and the software systems of exploitation.These all cannot meet the demand that unmanned plane image splices fast, such as, when Emergency decision formulation is badly in need of in the disaster burst that happens suddenly.Because traditional aeroplane photography treatment scheme limits by raw data and efficiency and is not suitable for the process of unmanned plane image, therefore, the method merged again after selecting image registration is the quick seamless spliced preferred option of unmanned plane image.And in the quick seamless spliced process of unmanned plane image, choose the key that a kind of suitable image matching algorithm has been image registration.
Images match refers to the aligning of two width images on locus of same target.Image matching technology is the focus that people study in recent decades always, and image matching technology application is very extensive, as fields such as remote sensing image stereopsis, computer vision, motion analysis and medical science.It can be divided into the semi-automatic coupling of man-machine interaction and the complete full-automatic coupling by computing machine complete independently.Full-automatic coupling can be divided into feature based and two kinds of modes based on gray scale.
Although the precision comparison mated based on the images match of gray scale is high, this mode is usually out of shape grey scale change, image geometry and prevents penetrating deformation sensitive, high, the consuming time length of its computation complexity in addition.Therefore, to be generally lessly applied in the middle of Practical Project.The image matching method of feature based can overcome above-mentioned shortcoming usually.This mode is few with matching primitives amount, and coupling is simple and affect less by rotation, translation, dimensional variation and be subject to the advantages such as lighting conditions hardly, is widely used in images match field.
The SIFT (ScaleInvariantFeatureTransformation) adopted herein is proposed by DavidLowe for 1999, and a kind of local feature description algorithm based on metric space perfect in 04 year.Mikolajczyk is for situations such as exposure level, geometry deformation, motion blur, compressions, and describing algorithm to 11 kinds of characteristic features carries out Contrast on effect, and result display SIFT algorithm performance is optimum.Therefore, consider unmanned plane imaging characteristic, select the SIFT algorithm situations such as illumination variation, image rotation, convergent-divergent, affine deformation being had to better resistance.
Unmanned aerial vehicle remote sensing images has that quantity is many, geometric distortion is large, expose the features such as uneven, these problems cause unmanned plane image can produce obvious splicing seams effect in splicing, and splicing seams phenomenon can not get effective control and the rear generation of splicing continuously can be caused significantly to splice dislocation, merge ' ghost ' phenomenon.Seamlines removing algorithm is the vision requirement in order to meet image mosaic, and namely splice result overall brightness, tone is consistent, clean mark, is convenient to visual interpretation.At present, two large classes can be divided in the achievement in research of computer vision and photogrammetric field Seamlines removing: a class is search splicing line, eliminates splicing seams in photogrammetric measurement and remote sensing fields mainly through which.Another kind of is image co-registration, mainly eliminates splicing seams by the method at computer vision field.
, geometric distortion many in conjunction with unmanned plane image quantity be large, expose the features such as uneven, and above-mentioned algorithm application is in the quick seamless spliced process of unmanned plane image or operand is larger, can not meet the requirement of splicing fast; Be subject to geometric distortion restriction that is large, splicing generation add up error continuously, lack certain practicality and dirigibility.In addition, above-mentioned algorithm, in the continuous splicing of a large amount of unmanned plane images, all can produce image co-registration " ghost ", and this will directly affect the improvement of visual effect of spliced panoramic figure.Therefore, in conjunction with unmanned plane image own characteristic, proposing a kind of algorithm of Seamlines removing is fast ensure that unmanned aerial vehicle remote sensing platform can play the key of maneuverability advantage.
Summary of the invention
Native system, on the quick seamless spliced theoretical research foundation of unmanned plane image, designs and develops the quick splicing system of a set of unmanned plane image.This software, under window7 environment, using OpenCV2.0, GSL1.8, ArcEngine10.0 kit as support, uses VisualStudio2010 to develop.This software major function is described below:
1. survey district image intelligence piecemeal: the ratio calculating the distance along heading and vertical flight direction, using this ratio as ground floor block count, then each block is segmented by quaternary tree piecemeal rule.
2. survey the emergent splicing of district image: surveying district's splicing of meeting an urgent need is utilize the longitude and latitude of existing gps data and course angle, this functional module can complete at unmanned plane the splicing image generating rapidly whole flight range after boat takes the photograph task, after Sudden Natural Disasters, this function has positive booster action for responding Emergency decision in time.
3. the quick seamless distributed splicing of image: splice according to the image that user selects.By intelligent piecemeal, whole mission area is divided into several sub-blocks, user is undertaken manually selecting image joint by the image of this function to point good block, so that can carry out multicomputer point tasks in parallel process to the image after piecemeal, this is also the mode of the large long problem consuming time of a kind of effective solution data volume.
4. the quick seamless one-touch splicing of whole survey district image: the core splicing function that " one-touch splicing " and " distributed splicing " adopt is consistent, but " one-touch " does not need manual intervention whole test site can be spliced into a width image, but it is longer to do the stand-by period like this.
Accompanying drawing explanation
Fig. 1 different Seamlines removing algorithm comparing result figure
Fig. 2 system is with multiple unmanned plane image joint results to many row
Fig. 3 system main interface sectional drawing
Embodiment
The operation of native system is as follows: GPS auxiliary data is imported unmanned plane during flying quality assessment and quick splicing system.System presses air strips grouping according to video number to GPS.Image splices to comprise fast surveys the emergent splicing of district's image, distributed splicing, one-touch splicing, survey district meet an urgent need splicing be utilize the longitude and latitude of existing gps data and course angle, this functional module can complete at unmanned plane the splicing image generating whole flight range after boat takes the photograph task rapidly, after Sudden Natural Disasters, this function has positive booster action for responding Emergency decision in time.The partial result of splicing image depends on the precision of GPS." distributed splicing " manually selects image, splices according to the image that user selects.By intelligent piecemeal, whole mission area is divided into several sub-blocks, user carries out manually selecting image joint to the image after piecemeal by this function, the benefit done like this is can multitask multiple stage computing machine co-operation, is all helpful to solution splicing speed and large count issue.Core that " one-touch splicing " and " distributed splicing " adopt splicing function is consistent, and only " one-touch " does not need manual intervention whole mission area can be spliced into a width image, but it is longer to do the stand-by period like this.
The above; be only the embodiment of invention; but protection scope of the present invention is not limited thereto; anyly be familiar with within technical scope that those skilled in the art disclose in the present invention; the change that can expect easily or replacement; all should be encompassed within protection scope of the present invention, therefore, the protection domain that protection scope of the present invention should define with claim is as the criterion.
Claims (5)
1. the quick seamless spliced system of unmanned plane sequential images mainly comprises image and splices fast and comprise intelligent piecemeal, survey the emergent splicing in district, the distributed splicing of image, one-touch splicing four partial function:
S1, has close relationship between image overlap degree and stitching error, and Tang's Jin etc. has carried out detailed discussion to best overlapped ratio.The optimum overlapping calculated by two kinds of stitching error models is respectively 0.25 and 0.35, in conjunction with the feature of unmanned plane image, can be defined as optimum overlapping scope by 0.25 ~ 0.35.Therefore sometimes according to optimum overlapping requirement, image may be done " vacuate " process, namely every one, one be got to the image on same air strips.For identical survey area, the image quantity of splicing will reduce half, the splicing efficiency so not only improved but also can make moderate progress to splicing effect.According to analysis above, the image chosen should be distributed in two adjacent air strips.If the image of piecemeal to be regarded as a Controling network, consider from network structure and stability, foursquare network structure is more excellent than rectangular network structure.Therefore when determining piecemeal, should first-selected foursquare method of partition.
S2, survey district meet an urgent need splicing be utilize the longitude and latitude of existing gps data and course angle, this functional module can complete at unmanned plane the splicing image generating rapidly whole flight range after boat takes the photograph task, after Sudden Natural Disasters, this function has positive booster action for responding Emergency decision in time.The partial result of splicing image depends on the precision of GPS.
S3, " distributed splicing " manually selects image, and the image selected according to user carries out splicing.By intelligent piecemeal, whole mission area is divided into several sub-blocks, user carries out manually selecting image joint to the image after piecemeal by this function, the benefit done like this is can multitask multiple stage computing machine co-operation, is all helpful to solution splicing speed and large count issue.
S4, core that " one-touch splicing " and " distributed splicing " adopt splicing function is consistent, and only " one-touch " does not need manual intervention whole mission area can be spliced into a width image, but it is longer to do the stand-by period like this.
2. the quick seamless spliced intelligent piecemeal part of unmanned plane sequential images according to claim 1, is characterized in that, described in have employed square optimum piecemeal rule carry out survey district image block, this mode can improve efficiency and the precision of coupling.
3. meet an urgent need splicing part in the quick seamless spliced survey district of unmanned plane sequential images according to claim 1, it is characterized in that, this functional module can complete at unmanned plane the splicing image generating rapidly whole flight range after boat takes the photograph task, after Sudden Natural Disasters, this function has positive booster action for responding Emergency decision in time.
4. the distributed splicing part of the quick seamless spliced image of unmanned plane sequential images according to claim 1, it is characterized in that, user carries out manually selecting image joint to the image after piecemeal by this function, the benefit done like this is can multitask multiple stage computing machine co-operation, is all helpful to solution splicing speed and large count issue.
5. the quick seamless spliced one-touch splicing part of unmanned plane sequential images according to claim 1, is characterized in that, carries out integrated, decrease artificial intervention to above-mentioned 3 kinds of functions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510697762.6A CN105389777A (en) | 2015-10-23 | 2015-10-23 | Unmanned aerial vehicle sequential image rapid seamless splicing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510697762.6A CN105389777A (en) | 2015-10-23 | 2015-10-23 | Unmanned aerial vehicle sequential image rapid seamless splicing system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105389777A true CN105389777A (en) | 2016-03-09 |
Family
ID=55422030
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510697762.6A Pending CN105389777A (en) | 2015-10-23 | 2015-10-23 | Unmanned aerial vehicle sequential image rapid seamless splicing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105389777A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106355555A (en) * | 2016-10-24 | 2017-01-25 | 北京林业大学 | Image stitching method and device |
| CN107371040A (en) * | 2017-08-28 | 2017-11-21 | 荆门程远电子科技有限公司 | A kind of unmanned plane image efficient process system |
| CN112161973A (en) * | 2020-08-31 | 2021-01-01 | 中国水利水电科学研究院 | Unmanned aerial vehicle-based rapid detection method for water pollution |
| CN112907486A (en) * | 2021-03-18 | 2021-06-04 | 国家海洋信息中心 | Remote sensing image color matching method based on deep learning and color mapping |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100245571A1 (en) * | 2006-04-24 | 2010-09-30 | Northrop Grumman Corporation | Global hawk image mosaic |
| US20120114229A1 (en) * | 2010-01-21 | 2012-05-10 | Guoqing Zhou | Orthorectification and mosaic of video flow |
| CN102707289A (en) * | 2012-06-15 | 2012-10-03 | 哈尔滨工程大学 | Course angle rotation-based multi-beam side-scan sonar image real-time splicing method |
| CN103376455A (en) * | 2012-04-23 | 2013-10-30 | 中国科学院、水利部成都山地灾害与环境研究所 | Sensor posture coordinate recording device applicable to low-altitude unpiloted remote sensing platform |
| CN103868504A (en) * | 2014-03-25 | 2014-06-18 | 许凯华 | Autonomous surveying and mapping machine |
| CN104280036A (en) * | 2013-07-05 | 2015-01-14 | 北京四维图新科技股份有限公司 | Traffic information detection and positioning method, device and electronic equipment |
-
2015
- 2015-10-23 CN CN201510697762.6A patent/CN105389777A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100245571A1 (en) * | 2006-04-24 | 2010-09-30 | Northrop Grumman Corporation | Global hawk image mosaic |
| US20120114229A1 (en) * | 2010-01-21 | 2012-05-10 | Guoqing Zhou | Orthorectification and mosaic of video flow |
| CN103376455A (en) * | 2012-04-23 | 2013-10-30 | 中国科学院、水利部成都山地灾害与环境研究所 | Sensor posture coordinate recording device applicable to low-altitude unpiloted remote sensing platform |
| CN102707289A (en) * | 2012-06-15 | 2012-10-03 | 哈尔滨工程大学 | Course angle rotation-based multi-beam side-scan sonar image real-time splicing method |
| CN104280036A (en) * | 2013-07-05 | 2015-01-14 | 北京四维图新科技股份有限公司 | Traffic information detection and positioning method, device and electronic equipment |
| CN103868504A (en) * | 2014-03-25 | 2014-06-18 | 许凯华 | Autonomous surveying and mapping machine |
Non-Patent Citations (3)
| Title |
|---|
| 唐琎 等: "图象拼接误差的理论分析", 《小型微型计算机系统》 * |
| 狄颖辰: "无人机遥感图像拼接系统设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 袁媛 等: "无人机序列影像快速无缝拼接方法研究", 《计算机工程与应用》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106355555A (en) * | 2016-10-24 | 2017-01-25 | 北京林业大学 | Image stitching method and device |
| CN106355555B (en) * | 2016-10-24 | 2019-06-18 | 北京林业大学 | A kind of image split-joint method and device |
| CN107371040A (en) * | 2017-08-28 | 2017-11-21 | 荆门程远电子科技有限公司 | A kind of unmanned plane image efficient process system |
| CN107371040B (en) * | 2017-08-28 | 2020-05-15 | 荆门程远电子科技有限公司 | High-efficient processing system of unmanned aerial vehicle image |
| CN112161973A (en) * | 2020-08-31 | 2021-01-01 | 中国水利水电科学研究院 | Unmanned aerial vehicle-based rapid detection method for water pollution |
| CN112161973B (en) * | 2020-08-31 | 2022-04-08 | 中国水利水电科学研究院 | Unmanned aerial vehicle-based rapid detection method for water pollution |
| CN112907486A (en) * | 2021-03-18 | 2021-06-04 | 国家海洋信息中心 | Remote sensing image color matching method based on deep learning and color mapping |
| CN112907486B (en) * | 2021-03-18 | 2022-12-09 | 国家海洋信息中心 | Remote sensing image toning method based on deep learning and color mapping |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Strecha et al. | Dynamic and scalable large scale image reconstruction | |
| CN108168521A (en) | One kind realizes landscape three-dimensional visualization method based on unmanned plane | |
| CN104156968B (en) | Large-area complex-terrain-region unmanned plane sequence image rapid seamless splicing method | |
| CN104330074B (en) | Intelligent surveying and mapping platform and realizing method thereof | |
| CN106157304A (en) | A kind of Panoramagram montage method based on multiple cameras and system | |
| CN110717861B (en) | Image splicing method and device, electronic equipment and computer readable storage medium | |
| CN109615698A (en) | Multiple no-manned plane SLAM map blending algorithm based on the detection of mutual winding | |
| CN103649998A (en) | Method for determining a parameter set designed for determining the pose of a camera and/or for determining a three-dimensional structure of the at least one real object | |
| CN105389777A (en) | Unmanned aerial vehicle sequential image rapid seamless splicing system | |
| CN114332360A (en) | Collaborative three-dimensional mapping method and system | |
| CN104574278B (en) | Based on the Aerial Images joining method of LOCAL FEEDBACK mechanism with sparse global adaptation | |
| Beall et al. | Bundle adjustment in large-scale 3d reconstructions based on underwater robotic surveys | |
| KR20200110120A (en) | A system implementing management solution of road facility based on 3D-VR multi-sensor system and a method thereof | |
| CN108733711B (en) | Distribution line space distance obtaining method based on three-dimensional GIS technology | |
| JP2012137933A (en) | Position specifying method of planimetric features to be photographed, program thereof, display map, photographic position acquiring method, program thereof and photographic position acquiring device | |
| Orthuber et al. | 3D building reconstruction from lidar point clouds by adaptive dual contouring | |
| CN108253942B (en) | Method for improving oblique photography measurement space-three quality | |
| Moussa et al. | A fast approach for stitching of aerial images | |
| Burkard et al. | User-aided global registration method using geospatial 3D data for large-scale mobile outdoor augmented reality | |
| Woo et al. | Vision-based UAV Navigation in Mountain Area. | |
| CN104318540A (en) | Aerial image online splicing method capable of using synergy of CPU (central processing unit) and GPU (graphics processing unit) | |
| CN111861873A (en) | Method and device for generating simulation image | |
| US20220276046A1 (en) | System and method for providing improved geocoded reference data to a 3d map representation | |
| CN114757834B (en) | Panoramic image processing method and panoramic image processing device | |
| CN106709897B (en) | Optimal splicing line finding method and system between orthography based on gradient field |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160309 |