CN110084743A - Image mosaic and localization method based on more air strips starting track constraint - Google Patents
Image mosaic and localization method based on more air strips starting track constraint Download PDFInfo
- Publication number
- CN110084743A CN110084743A CN201910071912.0A CN201910071912A CN110084743A CN 110084743 A CN110084743 A CN 110084743A CN 201910071912 A CN201910071912 A CN 201910071912A CN 110084743 A CN110084743 A CN 110084743A
- Authority
- CN
- China
- Prior art keywords
- image
- air strips
- frame
- kth
- point
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000004807 localization Effects 0.000 title claims abstract description 10
- 238000012545 processing Methods 0.000 claims abstract description 6
- 238000013461 design Methods 0.000 claims abstract description 5
- 239000011159 matrix material Substances 0.000 claims description 36
- 238000004422 calculation algorithm Methods 0.000 claims description 17
- 238000000605 extraction Methods 0.000 claims description 8
- 239000013598 vector Substances 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 2
- 238000013507 mapping Methods 0.000 abstract description 7
- 238000012417 linear regression Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 6
- 230000005856 abnormality Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910002056 binary alloy Inorganic materials 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000004088 simulation Methods 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- 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
- G06T2207/10016—Video; Image sequence
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention belongs to Computer Image Processing and ground mapping field, it is specially a kind of based on more air strips starting track constraint image mosaic and localization method, to overcome more waterway designs occur often two even a plurality of air strips intersect, be overlapped the problems such as.The present invention originates track according to each air strips, use linear regression, determining fitting a straight line, according to fitting a straight line, correct the stitching image after the air strips, reduce accumulated error, subsequent stitching image and starting stitching image is set to generate dependence, the appearance of phenomena such as to avoid the occurrence of air strips intersection or bifurcated, it is adapted to more complicated flight track simultaneously, as long as single air strips are straight line, to be not limited solely to box-shaped flight path, image mosaic quality and panorama sketch positioning accuracy between air strips are improved.
Description
Technical field
The present invention relates to Computer Image Processing and ground mapping field, specially a kind of to originate track about based on more air strips
The image mosaic and localization method of beam are mainly used for the joining quality of image and the positioning accuracy of panorama sketch between raising air strips.
Background technique
UAV (Unmanned Aerial Vehicle unmanned plane) is simple with operation, is swift in response, flexible, cost of flying
The features such as low, has been widely used in fighting calamities and providing relief, military surveillance, marine detection, the technical field of mapping such as environmental protection.Wherein
Most of demands all directly translate into obtain the GPS information of each point in flight operation area panorama sketch and figure.
Unmanned plane image split-joint method is mainly the joining method based on characteristics of image at present, and this method is to single air strips
The splicing effect of image is more satisfactory, but more waterway designs occur two even a plurality of air strips often and intersect, the feelings such as overlapping
Condition；Traditional unmanned plane image position method mainly passes through the central point GPS of a frame image, utilizes ground resolution and scale bar
Recursion goes out the GPS information of other each points in the frame image, but when this method calculates the resolution ratio of every frame image, scale bar can go out
Existing error, and global error can gradually add up with splicing.
How problem that air strips between the joining quality of image and the positioning accuracy of panorama sketch be urgent need to resolve is improved.
Summary of the invention
It is an object of the invention in view of the above technical problems, provide a kind of image based on more air strips starting track constraint
Splicing and localization method, for improving image mosaic quality and panorama sketch positioning accuracy between air strips.
To achieve the above object, the technical solution adopted by the present invention are as follows:
Image mosaic and localization method based on more air strips starting track constraint, comprising the following steps:
Step 1. air strips image mosaic
Step 1-1. completes the splicing of preceding K frame image in air strips in accordance with the following methods:
Step 1-1-1. image preprocessing: gray processing is carried out to the every frame video image received；
Step 1-1-2. image characteristics extraction: every frame image obtains feature point set with SURF operator detection image feature, and
Characteristic point is calculated using BRISK Feature Descriptor and generates feature description vectors；
Step 1-1-3. Image Feature Matching: -1 frame of kth obtained in step 1-1-2 and the feature of kth frame image are retouched
It states vector and carries out BF and match to obtain initial matching as a result, k=1,2,3 ... K；Pass through RANSAC algorithm again for initial matching result
Middle rejecting abnormalities matching value obtains obtaining optimal matching points collection；Finally, passing through least square according to optimal matching points collection
The perspective transform homography matrix H of method calculating -1 frame of kth and kth framek-1；
Step 1-1-4. image mosaic: homography matrix of the kth frame relative to the 1st frame is calculated:
Hk=Hk-1*Hk-2*...*H0；
Four angle points of kth frame image are passed through into homography matrix HkIt is transformed to new coordinate update and corresponds to position to panorama sketch
It sets, and the pixel center of stitching image point is stored to point set P1；
In the 1st article of air strips step 1-2. K+1 frame to last 1 frame image splicing
K frame image mosaic before being completed by step 1, and according to element in point set P, it is fitted to obtain straight line L；
For kth frame image, k=K+1, K+2, K+3 ..., K1；K1For the total video number of image frames of air strips；
Using step 1-1-1 to step 1-1-3 same treatment, the homography matrix H of kth frame image is obtainedk-1, according to list
Answering property matrix Hk-1Calculate kth frame image center A (xa, ya)；Point A is projected to straight line L, subpoint B (x is obtainedb,
yb)；And then obtain the excursion matrix of kth frame image: Bk=[1,0, xb-xa；0,1,yb-ya]；
Update H 'k-1=Hk-1*Bk, and then obtain accumulative homography matrix of the kth frame relative to the 1st frame:
Hk=H 'k-1*H′k-2*...*H′K+1*H′K*HK-1*...*H0
Four angle points of kth frame image are passed through into homography matrix HkIt is transformed to new coordinate update and corresponds to position to panorama sketch
It sets；
Splice at the 1st hovering of step 2.: using step 1-1 same process, completing hovering place has image mosaic；
Step 3. repeats step 1~2, be sequentially completed the 2nd article of air strips, at the 2nd hovering, the 3rd article of air strips, the 3rd hovering
Place, until last 1 waterway design；Complete the splicing of panoramic picture；
Step 4, panorama sketch arbitrary point GPS positioning
The UTM of the pixel center point of splicing frames all in panoramic picture and pixel coordinate are stored in UTM by step 4-1. respectively
Point set and pixel center point set, the mapped function relation of UTM point set Yu pixel center point set is found out using perspective transform；
The pixel coordinate of arbitrary point is calculated pair according to mapped function relation in step 4-1 in step 4-2. panorama sketch
UTM coordinate is answered, realizes positioning.
Further, in step 4-1, if mapped function relation can not be found out, successively equiprobable reduction point set quantity,
Until finding out.
The beneficial effects of the present invention are:
The present invention provides image mosaic and localization method based on more air strips starting track constraint, is risen according to each air strips
Beginning track, using linear regression, determining fitting a straight line corrects the stitching image after the air strips according to fitting a straight line, reduces
Accumulated error makes subsequent stitching image and starting stitching image generate dependence, intersects or divides to avoid the occurrence of air strips
The appearance of phenomena such as fork, while it being adapted to more complicated flight track, as long as single air strips are straight line, thus not only
It is confined to box-shaped flight path and improves the joining quality of image and the positioning accuracy of panorama sketch between air strips.
Detailed description of the invention
Fig. 1 is that vector schematic diagram is corrected in present invention offset.
Fig. 2 is the result figure that three row bands originate track constraint in the embodiment of the present invention.
Specific embodiment
The present invention is described in further details with reference to the accompanying drawings and examples；It is first for convenience of description the content of present invention
First necessary explanation is carried out to being related to term:
SURF:SURF (Speeded Up Robust Features accelerates robust feature) is that a steady image is known
Not and algorithm is described, is the succession and development of SIFT algorithm；The extraction of SURF feature includes: building Hessian matrix, generates institute
There is characteristic point, building scale space, characteristic point is positioned, the distribution of characteristic point principal direction, generates feature point description, feature
Point matching and etc., the SURF characteristic matching point pair of adjacent image is calculated by these steps, but SURF algorithm is in feature
Description stage and characteristic matching stage time-consuming are more, it is difficult to meet the high occasion of requirement of real-time；The present invention uses SURF operator
The character point of detection image simultaneously determines principal direction.
BRISK:Binary Robust Invariant Scalable Keypoints proposes a kind of feature extraction calculation
Method and binary features describe operator, and when to there is larger fuzzy image registration, BRISK algorithm shows most in numerous algorithms
To be outstanding, but the algorithm characteristics detective operators are FAST operator, and the character point fineness of the operator extraction and accuracy are not
Such as SIFT and S URF operator；In view of the robustness of detection speed and fuzzy splicing, the present invention is using BRISK operator as special
Sign description.
BF:BF algorithm, i.e. storm wind (Brute Force) algorithm, is common pattern matching algorithm, the thought of BF algorithm is just
It is to match the first character of target strings S with the first character of pattern string T, if equal, continues compare S second
Second character of a character and T；If unequal, compare the first character of second character and T of S, under successively comparing
It goes, until obtaining last matching result.
RANSAC:Random Sample Consensus is the sample data set according to one group comprising abnormal data, is calculated
The mathematical model parameter of data out obtains the algorithm of effective sample data.
Homography matrix: in computer vision, the homography of plane is defined as a plane to another plane
Projection mapping, homography matrix be describe the mapping relations mapping matrix.
UTM coordinate: UTM (UNIVERSAL TRANSVERSE MERCARTOR GRID SYSTEM, Universal Trans Meridian lattice
Net system) coordinate is a kind of plane rectangular coordinates, this coordinate axiom system and its based on projection be widely used for ground
Shape figure, as satellite image and natural resources database grid of reference and require pinpoint other application；Because of figure
As being two-dimensional image after the completion of splicing, therefore original GPS coordinate must be converted into UTM coordinate and could be applicable in.
The present embodiment provides a kind of image mosaics and localization method based on more air strips starting track constraint, can be improved boat
The joining quality of interband image and the positioning accuracy of panorama sketch, including image preprocessing, image characteristics extraction, characteristics of image
Match, five track constraint, panorama sketch arbitrary point GPS positioning steps；It is specific as follows:
The 1st article of air strips image mosaic of step 1.
Step 1-1. completes the splicing of preceding K frame image in the 1st article of air strips in accordance with the following methods:
Step 1-1-1. image preprocessing: gray processing is carried out to every frame video image
Gray processing: tri- components of RGB of color image are weighted and averaged with corresponding weight；In the present embodiment, press
Following formula, which is weighted and averaged RGB three-component, can obtain more reasonable gray level image:
F (i, j)=0.30R (i, j)+0.59G (i, j)+0.11B (i, j)；
Step 1-1-2. image characteristics extraction
SURF detects characteristic point using approximation Hessian matrix, and carries out convolution algorithm using integral image, reduces operation
To improve feature extraction speed；BRISK binary system descriptor is straight to simple intensity contrast by characteristic point surrounding pixel point
It practices midwifery raw binary bits string, the similarity distance calculated between characteristic point is simple and effective, and committed memory is few；The present invention uses SURF
Characteristic point is detected, feature descriptor is calculated using BRISK；Detailed process is as follows:
A) construct Hessian matrix, tectonic scale space: certain point is X (x, y), the matrix under σ scale on setting image
M is defined as:
Wherein, Lxx be gaussian filtering second order lead same X convolution as a result, the meaning of Lxy etc. is similar, σ is space scale；Work as H
When the discriminate of essian matrix obtains local maximum, it is believed that navigate to the position of key point；
B) characteristic point is detected:, will be by each pixel and two of Hessian matrix disposal in obtained scale space
26 points in dimension image space and scale space neighborhood are compared, and Primary Location goes out key point, remove energy using filtering off
The key point of weak key point and location of mistake filters out final invariant feature point；
C) BRISK calculates feature descriptor: by invariant feature point by BRISk descriptor algorithm, obtaining corresponding BRISK
Binary features descriptor (feature description vectors)；
Step 1-1-3. Image Feature Matching, and homography matrix is calculated to matching result:
A) BRISK descriptor is the binary bits string of 1 and 0 composition, uses Hamming distance (xor operation) in the present invention
The matching of its high speed may be implemented, efficiency is prominent；The feature of -1 frame of kth obtained in step 1-1-2 and kth frame image is described
Vector carries out BF and matches to obtain initial matching as a result, k=1, and 2,3 ... K；
B) RANSAC algorithm fault-tolerant ability is strong, to noise spot and Mismatching point strong robustness, can preferably reject mistake
With point pair；By RANSAC algorithm to the initial matching result rejecting abnormalities matching value in a), obtain obtaining that stable, precision is high
Optimal matching points collection；
C) according to optimal matching points collection, the perspective transform homography of -1 frame of kth and kth frame is calculated by least square method
Matrix Hk-1；
Step 1-1-4. image mosaic；
Calculate homography matrix of the kth frame relative to the 1st frame: Hk=Hk-1*Hk-2*...*H0；By the four of kth frame image
A angle point passes through homography matrix HkIt is transformed to new coordinate to update to panorama sketch corresponding position, and will be in the pixel of stitching image
Heart point is stored to point set P1；
In the 1st article of air strips step 1-2. K+1 frame to last 1 frame image splicing
K frame image mosaic before being completed by step 1, and according to point set P1Middle element is fitted to obtain straight line L1；
For kth frame image, k=K+1, K+2, K+3 ..., K1；K1For the total video number of image frames of the 1st article of air strips；
Using step 1-1-1 to step 1-1-3 same treatment, the homography matrix H of kth frame image is obtainedk-1, according to list
Answering property matrix Hk-1Kth frame image center, as A point are calculated, coordinate representation is (xa, ya), as shown in Figure 1；A point is projected
To straight line L1On, subpoint, as B point are obtained, coordinate representation is (xb, yb), as shown in Figure 1；And then obtain kth frame image
Excursion matrix: Bk=[1,0, xb-xa；0,1,yb-ya]；Update H 'k-1=Hk-1*Bk；
And then obtain accumulative homography matrix of the kth frame relative to the 1st frame:
Hk=H 'k-1*H′k-2*...*H′K+1*H′K*HK-1*...*H0
Four angle points of kth frame image are passed through into homography matrix HkIt is transformed to new coordinate update and corresponds to position to panorama sketch
It sets；
Splice at the 1st hovering of step 2.
After step 1 completes the 1st article of all frame image mosaics in air strips, accumulative homography matrix is obtained are as follows:
HA1=H 'K1-1*H′K1-2*...*H′K+1*H′K*HK-1*...*H0；
Using step 1-1 same process, completing hovering place has image mosaic；
Step 3. repeats step 1~2, be sequentially completed the 2nd article of air strips, at the 2nd hovering, the 3rd article of air strips, the 3rd hovering
Place, until last 1 waterway design；Complete the splicing of panoramic picture；
Step 4, panorama sketch arbitrary point GPS positioning
After the completion of splicing, in order to improve positioning accuracy, avoided imaging space geometry process, directly to anamorphose into
Row mathematical simulation, the specific steps are as follows:
After step 4-1. splices, by the UTM and pixel coordinate of the pixel center point of splicing frames all in panoramic picture
Deposit UTM point set and pixel center point set respectively, the mapping function of UTM point set Yu pixel center point set is found out using perspective transform
Relationship, and consider empty matrix problem that may be present, if mapped function relation can not be found out, successively equiprobable reduction point
Collect quantity, until finding out；
The pixel coordinate of arbitrary point is calculated pair according to mapped function relation in step 4-1 in step 4-2. panorama sketch
UTM coordinate is answered, realizes positioning.
In the present embodiment, using the result of three air strips of above method starting track constraint as shown in Fig. 2, by that can be seen in figure
Out, track print degree of agreement it is higher, error is minimum in the lateral direction for image mosaic effect, according to this method can obtain compared with
For accurate stitching image, so as to realize that unmanned plane during flying image mosaic is big map, and lay for big map positioning good
Good basis
The above description is merely a specific embodiment, any feature disclosed in this specification, except non-specifically
Narration, can be replaced by other alternative features that are equivalent or have similar purpose；Disclosed all features or all sides
Method or in the process the step of, other than mutually exclusive feature and/or step, can be combined in any way.
Claims (2)
1. image mosaic and localization method based on more air strips starting track constraint, comprising the following steps:
Step 1. air strips image mosaic
Step 1-1. completes the splicing of preceding K frame image in air strips in accordance with the following methods:
Step 1-1-1. image preprocessing: gray processing is carried out to the every frame video image received；
Step 1-1-2. image characteristics extraction: every frame image obtains feature point set with SURF operator detection image feature, and uses
BRISK Feature Descriptor calculates characteristic point and generates feature description vectors；
Step 1-1-3. Image Feature Matching: to the feature of -1 frame of kth obtained in step 1-1-2 and kth frame image describe to
Amount carries out BF and matches to obtain initial matching as a result, k=1, and 2,3 ... K；It will be picked in initial matching result by RANSAC algorithm again
Except abnormal matching value, obtain obtaining optimal matching points collection；Finally, passing through least square method meter according to optimal matching points collection
Calculate the perspective transform homography matrix H of -1 frame of kth and kth framek-1；
Step 1-1-4. image mosaic: homography matrix of the kth frame relative to the 1st frame is calculated:
Hk=Hk-1*Hk-2*...*H0；
Four angle points of kth frame image are passed through into homography matrix HkIt is transformed to new coordinate to update to panorama sketch corresponding position, and will
The pixel center point of stitching image is stored to point set P1；
In the 1st article of air strips step 1-2. K+1 frame to last 1 frame image splicing
K frame image mosaic before being completed by step 1, and according to element in point set P, it is fitted to obtain straight line L；
For kth frame image, k=K+1, K+2, K+3 ..., K1；K1For the total video number of image frames of air strips；
Using step 1-1-1 to step 1-1-3 same treatment, the homography matrix H of kth frame image is obtainedk-1, according to homography
Matrix Hk-1Calculate kth frame image center A (xa, ya)；Point A is projected to straight line L, subpoint B (x is obtainedb, yb)；Into
And obtain the excursion matrix of kth frame image: Bk=[1,0, xb-xa；0,1,yb-ya]；
Update H 'k-1=Hk-1*Bk, and then obtain accumulative homography matrix of the kth frame relative to the 1st frame:
Hk=H 'k-1*H′k-2*...*H′K+1*H′K*HK-1*...*H0
Four angle points of kth frame image are passed through into homography matrix HkNew coordinate is transformed to update to panorama sketch corresponding position；
Splice at the 1st hovering of step 2.: using step 1-1 same process, completing hovering place has image mosaic；
Step 3. repeats step 1~2, be sequentially completed the 2nd article of air strips, at the 2nd hovering, the 3rd article of air strips, at the 3rd hovering, directly
To last 1 waterway design；Complete the splicing of panoramic picture；
Step 4, panorama sketch arbitrary point GPS positioning
The UTM of the pixel center point of splicing frames all in panoramic picture and pixel coordinate are stored in UTM point set by step 4-1. respectively
With pixel center point set, the mapped function relation of UTM point set Yu pixel center point set is found out using perspective transform；
Correspondence is calculated according to mapped function relation in step 4-1 in the pixel coordinate of arbitrary point in step 4-2. panorama sketch
UTM coordinate realizes positioning.
2. by image mosaic and localization method based on more air strips starting track constraint described in claim 1, which is characterized in that institute
It states in step 4-1, if mapped function relation can not be found out, successively equiprobable reduction point set quantity, until finding out.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910071912.0A CN110084743B (en) | 2019-01-25 | 2019-01-25 | Image splicing and positioning method based on multi-flight-zone initial flight path constraint |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910071912.0A CN110084743B (en) | 2019-01-25 | 2019-01-25 | Image splicing and positioning method based on multi-flight-zone initial flight path constraint |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110084743A true CN110084743A (en) | 2019-08-02 |
| CN110084743B CN110084743B (en) | 2023-04-14 |
Family
ID=67413012
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910071912.0A Active CN110084743B (en) | 2019-01-25 | 2019-01-25 | Image splicing and positioning method based on multi-flight-zone initial flight path constraint |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110084743B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111461986A (en) * | 2020-04-01 | 2020-07-28 | 深圳市科卫泰实业发展有限公司 | Unmanned aerial vehicle night real-time two-dimensional image splicing method |
| CN111461013A (en) * | 2020-04-01 | 2020-07-28 | 深圳市科卫泰实业发展有限公司 | Real-time fire scene situation sensing method based on unmanned aerial vehicle |
| CN111507901A (en) * | 2020-04-15 | 2020-08-07 | 中国电子科技集团公司第五十四研究所 | Aerial image splicing and positioning method based on aerial belt GPS and scale invariant constraint |
| CN112884767A (en) * | 2021-03-26 | 2021-06-01 | 长鑫存储技术有限公司 | Image fitting method |
Citations (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0987873A2 (en) * | 1998-09-15 | 2000-03-22 | Hewlett-Packard Company | Navigation system for handheld scanner |
| US20040239885A1 (en) * | 2003-04-19 | 2004-12-02 | University Of Kentucky Research Foundation | Super-resolution overlay in multi-projector displays |
| CN101442619A (en) * | 2008-12-25 | 2009-05-27 | 武汉大学 | Method for splicing non-control point image |
| CN101777129A (en) * | 2009-11-25 | 2010-07-14 | 中国科学院自动化研究所 | Image matching method based on feature detection |
| US20100194851A1 (en) * | 2009-02-03 | 2010-08-05 | Aricent Inc. | Panorama image stitching |
| CN102201115A (en) * | 2011-04-07 | 2011-09-28 | 湖南天幕智能科技有限公司 | Real-time panoramic image stitching method of aerial videos shot by unmanned plane |
| JP2012242321A (en) * | 2011-05-23 | 2012-12-10 | Topcon Corp | Aerial photograph imaging method and aerial photograph imaging device |
| CN102967859A (en) * | 2012-11-14 | 2013-03-13 | 电子科技大学 | Forward-looking scanning radar imaging method |
| CN103020934A (en) * | 2012-12-12 | 2013-04-03 | 武汉大学 | Seamless automatic image splicing method resistant to subtitle interference |
| US20140035906A1 (en) * | 2012-08-02 | 2014-02-06 | Earthmine, Inc. | Plane Panorama Location Correction in Three-Dimensional Mapping |
| CN104156968A (en) * | 2014-08-19 | 2014-11-19 | 山东临沂烟草有限公司 | Large-area complex-terrain-region unmanned plane sequence image rapid seamless splicing method |
| US20150071567A1 (en) * | 2013-09-06 | 2015-03-12 | Kabushiki Kaisha Toshiba | Image processing device, image processing method and non-transitory computer readable medium |
| CN104574347A (en) * | 2013-10-24 | 2015-04-29 | 南京理工大学 | On-orbit satellite image geometric positioning accuracy evaluation method on basis of multi-source remote sensing data |
| WO2015075700A1 (en) * | 2013-11-25 | 2015-05-28 | First Resource Management Group Inc. | Apparatus for and method of forest-inventory management |
| US20150170405A1 (en) * | 2013-12-16 | 2015-06-18 | Futurewei Technologies, Inc. | High resolution free-view interpolation of planar structure |
| US20160292821A1 (en) * | 2015-04-03 | 2016-10-06 | Electronics And Telecommunications Research Institute | System and method for displaying panoramic image using single look-up table |
| GB201620652D0 (en) * | 2016-12-05 | 2017-01-18 | Gaist Solutions Ltd | Method and system for creating images |
| CN106485655A (en) * | 2015-09-01 | 2017-03-08 | 张长隆 | A kind of taken photo by plane map generation system and method based on quadrotor |
| CN106934795A (en) * | 2017-01-23 | 2017-07-07 | 陕西师范大学 | The automatic testing method and Forecasting Methodology of a kind of glue into concrete beam cracks |
| CN107016646A (en) * | 2017-04-12 | 2017-08-04 | 长沙全度影像科技有限公司 | One kind approaches projective transformation image split-joint method based on improved |
| US20170243069A1 (en) * | 2016-02-23 | 2017-08-24 | Semiconductor Components Industries, Llc | Methods and apparatus for an imaging system |
| US20170301098A1 (en) * | 2016-04-15 | 2017-10-19 | Lockheed Martin Corporation | Passive underwater odometry using a video camera |
| CN107274336A (en) * | 2017-06-14 | 2017-10-20 | 电子科技大学 | A kind of Panorama Mosaic method for vehicle environment |
| CN107808362A (en) * | 2017-11-15 | 2018-03-16 | 北京工业大学 | A kind of image split-joint method combined based on unmanned plane POS information with image SURF features |
| CN108596982A (en) * | 2018-04-24 | 2018-09-28 | 深圳市航盛电子股份有限公司 | A kind of easy vehicle-mounted multi-view camera viewing system scaling method and device |
| CN108921847A (en) * | 2018-08-08 | 2018-11-30 | 长沙理工大学 | Bridge floor detection method based on machine vision |
| CN109087244A (en) * | 2018-07-26 | 2018-12-25 | 贵州火星探索科技有限公司 | A kind of Panorama Mosaic method, intelligent terminal and storage medium |
-
2019
- 2019-01-25 CN CN201910071912.0A patent/CN110084743B/en active Active
Patent Citations (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0987873A2 (en) * | 1998-09-15 | 2000-03-22 | Hewlett-Packard Company | Navigation system for handheld scanner |
| US20040239885A1 (en) * | 2003-04-19 | 2004-12-02 | University Of Kentucky Research Foundation | Super-resolution overlay in multi-projector displays |
| CN101442619A (en) * | 2008-12-25 | 2009-05-27 | 武汉大学 | Method for splicing non-control point image |
| US20100194851A1 (en) * | 2009-02-03 | 2010-08-05 | Aricent Inc. | Panorama image stitching |
| CN101777129A (en) * | 2009-11-25 | 2010-07-14 | 中国科学院自动化研究所 | Image matching method based on feature detection |
| CN102201115A (en) * | 2011-04-07 | 2011-09-28 | 湖南天幕智能科技有限公司 | Real-time panoramic image stitching method of aerial videos shot by unmanned plane |
| JP2012242321A (en) * | 2011-05-23 | 2012-12-10 | Topcon Corp | Aerial photograph imaging method and aerial photograph imaging device |
| US20140035906A1 (en) * | 2012-08-02 | 2014-02-06 | Earthmine, Inc. | Plane Panorama Location Correction in Three-Dimensional Mapping |
| CN102967859A (en) * | 2012-11-14 | 2013-03-13 | 电子科技大学 | Forward-looking scanning radar imaging method |
| CN103020934A (en) * | 2012-12-12 | 2013-04-03 | 武汉大学 | Seamless automatic image splicing method resistant to subtitle interference |
| US20150071567A1 (en) * | 2013-09-06 | 2015-03-12 | Kabushiki Kaisha Toshiba | Image processing device, image processing method and non-transitory computer readable medium |
| CN104574347A (en) * | 2013-10-24 | 2015-04-29 | 南京理工大学 | On-orbit satellite image geometric positioning accuracy evaluation method on basis of multi-source remote sensing data |
| WO2015075700A1 (en) * | 2013-11-25 | 2015-05-28 | First Resource Management Group Inc. | Apparatus for and method of forest-inventory management |
| US20150170405A1 (en) * | 2013-12-16 | 2015-06-18 | Futurewei Technologies, Inc. | High resolution free-view interpolation of planar structure |
| CN104156968A (en) * | 2014-08-19 | 2014-11-19 | 山东临沂烟草有限公司 | Large-area complex-terrain-region unmanned plane sequence image rapid seamless splicing method |
| US20160292821A1 (en) * | 2015-04-03 | 2016-10-06 | Electronics And Telecommunications Research Institute | System and method for displaying panoramic image using single look-up table |
| CN106485655A (en) * | 2015-09-01 | 2017-03-08 | 张长隆 | A kind of taken photo by plane map generation system and method based on quadrotor |
| US20170243069A1 (en) * | 2016-02-23 | 2017-08-24 | Semiconductor Components Industries, Llc | Methods and apparatus for an imaging system |
| US20170301098A1 (en) * | 2016-04-15 | 2017-10-19 | Lockheed Martin Corporation | Passive underwater odometry using a video camera |
| GB201620652D0 (en) * | 2016-12-05 | 2017-01-18 | Gaist Solutions Ltd | Method and system for creating images |
| CN106934795A (en) * | 2017-01-23 | 2017-07-07 | 陕西师范大学 | The automatic testing method and Forecasting Methodology of a kind of glue into concrete beam cracks |
| CN107016646A (en) * | 2017-04-12 | 2017-08-04 | 长沙全度影像科技有限公司 | One kind approaches projective transformation image split-joint method based on improved |
| CN107274336A (en) * | 2017-06-14 | 2017-10-20 | 电子科技大学 | A kind of Panorama Mosaic method for vehicle environment |
| CN107808362A (en) * | 2017-11-15 | 2018-03-16 | 北京工业大学 | A kind of image split-joint method combined based on unmanned plane POS information with image SURF features |
| CN108596982A (en) * | 2018-04-24 | 2018-09-28 | 深圳市航盛电子股份有限公司 | A kind of easy vehicle-mounted multi-view camera viewing system scaling method and device |
| CN109087244A (en) * | 2018-07-26 | 2018-12-25 | 贵州火星探索科技有限公司 | A kind of Panorama Mosaic method, intelligent terminal and storage medium |
| CN108921847A (en) * | 2018-08-08 | 2018-11-30 | 长沙理工大学 | Bridge floor detection method based on machine vision |
Non-Patent Citations (2)
| Title |
|---|
| 余清洲等: "基于约束逼近投影变换的全景图像拼接方法", 《集美大学学报(自然科学版)》 * |
| 卢官明等: "全景视图泊车辅助系统中的多视点视频拼接", 《南京邮电大学学报(自然科学版)》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111461986A (en) * | 2020-04-01 | 2020-07-28 | 深圳市科卫泰实业发展有限公司 | Unmanned aerial vehicle night real-time two-dimensional image splicing method |
| CN111461013A (en) * | 2020-04-01 | 2020-07-28 | 深圳市科卫泰实业发展有限公司 | Real-time fire scene situation sensing method based on unmanned aerial vehicle |
| CN111461986B (en) * | 2020-04-01 | 2023-11-03 | 深圳市科卫泰实业发展有限公司 | Night real-time two-dimensional image stitching method for unmanned aerial vehicle |
| CN111461013B (en) * | 2020-04-01 | 2023-11-03 | 深圳市科卫泰实业发展有限公司 | Unmanned aerial vehicle-based real-time fire scene situation awareness method |
| CN111507901A (en) * | 2020-04-15 | 2020-08-07 | 中国电子科技集团公司第五十四研究所 | Aerial image splicing and positioning method based on aerial belt GPS and scale invariant constraint |
| CN111507901B (en) * | 2020-04-15 | 2023-08-15 | 中国电子科技集团公司第五十四研究所 | Aerial image splicing and positioning method based on aerial GPS and scale invariant constraint |
| CN112884767A (en) * | 2021-03-26 | 2021-06-01 | 长鑫存储技术有限公司 | Image fitting method |
| CN112884767B (en) * | 2021-03-26 | 2022-04-26 | 长鑫存储技术有限公司 | Image fitting method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110084743B (en) | 2023-04-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110966991B (en) | Single unmanned aerial vehicle image positioning method without control point | |
| CN109740665B (en) | Method and system for detecting ship target with occluded image based on expert knowledge constraint | |
| CN110211043B (en) | Registration method based on grid optimization for panoramic image stitching | |
| CN110084743A (en) | Image mosaic and localization method based on more air strips starting track constraint | |
| CN107993263B (en) | Automatic calibration method for panoramic system, automobile, calibration device and storage medium | |
| CN104200461B (en) | The remote sensing image registration method of block and sift features is selected based on mutual information image | |
| CN111507901B (en) | Aerial image splicing and positioning method based on aerial GPS and scale invariant constraint | |
| CN110992263B (en) | Image stitching method and system | |
| CN109766887A (en) | A kind of multi-target detection method based on cascade hourglass neural network | |
| CN109858527B (en) | Image fusion method | |
| CN112254656B (en) | Stereoscopic vision three-dimensional displacement measurement method based on structural surface point characteristics | |
| Urban et al. | Finding a good feature detector-descriptor combination for the 2D keypoint-based registration of TLS point clouds | |
| CN109712071B (en) | Unmanned aerial vehicle image splicing and positioning method based on track constraint | |
| CN109711242A (en) | Modification method, device and the storage medium of lane line | |
| CN105654421A (en) | Projection transform image matching method based on transform invariant low-rank texture | |
| CN114255197A (en) | Infrared and visible light image self-adaptive fusion alignment method and system | |
| CN110929782B (en) | River channel abnormity detection method based on orthophoto map comparison | |
| CN113793266A (en) | Multi-view machine vision image splicing method, system and storage medium | |
| CN110176041B (en) | Novel train auxiliary assembly method based on binocular vision algorithm | |
| Huang et al. | SAR and optical images registration using shape context | |
| Bellavia et al. | Image orientation with a hybrid pipeline robust to rotations and wide-baselines | |
| CN114897676A (en) | Unmanned aerial vehicle remote sensing multispectral image splicing method, device and medium | |
| Huang et al. | Multimodal image matching using self similarity | |
| JP3863014B2 (en) | Object detection apparatus and method | |
| CN117765039A (en) | Point cloud coarse registration method, device and equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |