CN108986030A - A kind of remote sensing image inlays the rapid generation of line - Google Patents
A kind of remote sensing image inlays the rapid generation of line Download PDFInfo
- Publication number
- CN108986030A CN108986030A CN201810735088.XA CN201810735088A CN108986030A CN 108986030 A CN108986030 A CN 108986030A CN 201810735088 A CN201810735088 A CN 201810735088A CN 108986030 A CN108986030 A CN 108986030A
- Authority
- CN
- China
- Prior art keywords
- image
- line
- threshold value
- standard deviation
- mean value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000001914 filtration Methods 0.000 claims abstract description 10
- 238000000034 method Methods 0.000 claims description 9
- 230000007704 transition Effects 0.000 abstract description 3
- 230000006872 improvement Effects 0.000 abstract description 2
- 230000003044 adaptive effect Effects 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- VMXUWOKSQNHOCA-UKTHLTGXSA-N ranitidine Chemical compound [O-][N+](=O)\C=C(/NC)NCCSCC1=CC=C(CN(C)C)O1 VMXUWOKSQNHOCA-UKTHLTGXSA-N 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000006467 substitution reaction 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
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/32—Indexing scheme for image data processing or generation, in general involving image mosaicing
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses the rapid generation that a kind of remote sensing image inlays line, overall steps are as follows: calculates separately the effective coverage of two width input images；The type for judging two width images is then directly handled if panchromatic image, and multispectral each wave band is then calculated as single-range panchromatic image if multispectral image；It calculates overlapping region and calculates the error image of overlapping region；Median filtering is carried out to error image；The mean value and standard deviation of calculating difference image, according to mean value and standard deviation threshold value；Error image is divided into binary map according to threshold value；Optimal path is found using breadth first algorithm in binary map, that is, inlays line.The present invention passes through the modes such as the processing and threshold value selection of improvement differential chart, in the case where not needing manual intervention, produce avoid building or color difference large area substantially inlay line, calculating cost can not only be reduced, the efficiency for inlaying line generation is significantly improved, and can make to inlay result natural color transition, quickly and effectively.
Description
Technical field
The present invention relates to the sides of quickly generating that a kind of generation method for inlaying line more particularly to a kind of remote sensing image inlay line
Method.
Background technique
Two or two or more orthographies are stitched together, the bigger orthography of a width is formed and is known as orthogonal projection
As inlaying, wherein the step of most critical is the generation for inlaying line.Especially in the damascene process of city large scale remote sensing image
In, house or the biggish region of color difference should be avoided by inlaying line, and guarantee, which is inlayed on image, does not have geometric dislocation and natural color transition.
It is traditional inlay algorithm mostly and only considered two adjacent width images inlay line generation in its overlapping range, there is no study
Individually inlay how line is attached to be formed and inlay gauze network, although some business softwares, which can generate, inlays gauze
Network, but its algorithm is not increased income.It at present in the actual production process, is to inlay line by what is automatically generated in business software mostly
Upper plus human-edited mode carries out operation, but this work pattern production efficiency is lower, sharply swollen in current data amount
Stern challenge is faced in the case where swollen.In face of such huge data volume, the effective edge for surveying area's entirety how is quickly generated
Network is embedded the wire, and there are the regions of what all dislocation to be very necessary in bypass house etc. automatically.
Summary of the invention
In order to solve shortcoming present in above-mentioned technology, the present invention provides a kind of remote sensing images to inlay the quick of line
Generation method.
In order to solve the above technical problems, the technical solution adopted by the present invention is that: a kind of remote sensing image inlays the quick of line
Generation method, overall step are as follows:
Step S1, the effective coverage of two width input images is calculated separately, effective coverage background value cannot be generated inlaying line
Region；
Step S2, judge the type of two width images: then going to step S3 if multispectral image, if single-range panchromatic
Image then goes to step S4；
Step S3, multispectral each wave band is calculated as single-range panchromatic image；
It step S4, is foundation calculating overlapping region and the error image for calculating overlapping region with geographical coordinate；
Step S5, median filtering is carried out to error image, reduces the influence of noise；
Step S6, the mean value and standard deviation of calculating difference image, according to the size relation threshold value of mean value and standard deviation；
Step S7, error image is divided into according to threshold value by binary map；
Step S8, breadth first algorithm is utilized in binary map, finds optimal path, and optimal path is to inlay line.
Further, in step S4, when calculating the error image of overlapping region, two width image geographical coordinate of same position is taken
Absolute value of the difference is as error image.
Further, in step S5, median filtering uses multithreads computing to improve calculating speed.
Further, in step S6, according to the concrete mode of mean value and the size relation threshold value of standard deviation are as follows: if
Value is less than standard deviation, shows that two width images are not much different, takes mean value as threshold value；If mean value is greater than standard deviation, show two width shadows
Larger as differing, threshold value takes sum of the two.
The present invention is by modes such as the processing and threshold value selection of improvement differential chart, the case where not needing manual intervention
Under, that is, produce avoid building or color difference large area substantially inlay line, can not only reduce calculating cost, significantly improve
The efficiency of line generation is inlayed, and can make to inlay result natural color transition, quickly and effectively.
Detailed description of the invention
Fig. 1 is overall flow schematic diagram of the invention.
Specific embodiment
The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.
A kind of remote sensing image shown in FIG. 1 inlays the rapid generation of line, and step mainly includes calculating overlapping region
Error image, threshold value, generation inlay line three and walk greatly:
One, the error image of overlapping region is calculated:
First determine whether that image is panchromatic image or multispectral image；If panchromatic image is then directly handled, if mostly light
Spectrum image is then calculated as panchromatic image according to certain method with multispectral each wave band；
It then is according to the overlapping region for calculating two width images with geographical coordinate；Original or be calculated two are panchromatic
Image calculating difference image in overlapping region；Two width image absolute value of the difference of same position is taken when calculating difference image, is calculated
Median filtering is carried out after complete error image to it, reduces influence of the noise to knot fruit is inlayed, median filtering uses multithreading simultaneously
Row is calculated to improve calculating speed.
Two, threshold value:
Do not pass through building or the biggish region of color difference to make to inlay line, it need to be to can not be by region using adaptive
Threshold value guarantees change threshold value that can be adaptive when handling different atural objects, different images, plays the effect for avoiding building
Fruit.By the mean value and standard deviation of calculating difference image, according to the size decision threshold of mean value and standard deviation, if mean value is less than
Standard deviation illustrate two width images be not much different, threshold value takes mean value, if mean value be greater than standard deviation, illustrate two width images differ compared with
Greatly, threshold value takes sum of the two.
Three, it generates and inlays line:
In order to reduce the time complexity for inlaying line when generating, and the efficiency for inlaying line generation is improved, it is excellent using range
A kind of first algorithm (also referred to as breadth first search, breadth-first search are graphic searching algorithms), which generates, inlays line.Specifically,
Then bianry image can not be calculated as error image by region by being determined first by threshold value, range is used in bianry image
Priority algorithm finds optimal path, and optimal path can be identified as inlaying line.
Above-mentioned steps are specifically segmented, can be summarized as:
Step S1, the effective coverage of two width input images is calculated separately, effective coverage background value cannot be generated inlaying line
Region.
Step S2, judge the type of two width images: then going to step S3 if multispectral image, if single-range panchromatic
Image then goes to step S4.
Step S3, multispectral each wave band is calculated as single-range panchromatic image.
It step S4, is foundation calculating overlapping region and the error image for calculating overlapping region with geographical coordinate；Calculate overlapping
When the error image in region, take two width image geographical coordinate absolute value of the difference of same position as error image.
Step S5, median filtering is carried out to error image, reduces the influence of noise；Median filtering uses multi-threaded parallel meter
It calculates to improve calculating speed.
Step S6, the mean value and standard deviation of calculating difference image, according to the size relation threshold value of mean value and standard deviation；
According to the concrete mode of mean value and the size relation threshold value of standard deviation are as follows: if mean value is less than standard deviation, show two width images
It is not much different, takes mean value as threshold value；If mean value is greater than standard deviation, show that two width images difference is larger, threshold value takes sum of the two.
Step S7, error image is divided into according to threshold value by binary map.
Step S8, breadth first algorithm is utilized in binary map, finds optimal path, and optimal path is to inlay line.
Key innovations of the invention are:
The disparity map acquiring principle of (1) two width image, first determine whether image be it is panchromatic or multispectral, if it is it is panchromatic then
It directly handles, if it is multispectral, is calculated as panchromatic image with multispectral each wave band, it is right according to geographical location calculating difference figure
Differential chart carries out median filtering, reduces the influence of noise.
(2) determination of the threshold value of effective coverage, the mean value and standard deviation of calculating difference image, according to mean value and mark can be passed through
The size decision threshold of quasi- difference, if mean value is less than standard deviation and illustrates that two width images are not much different, threshold value takes mean value, if
Value is greater than variance, illustrates that two width images difference is larger, threshold value takes sum of the two.
The present invention calculates the fast speed for inlaying line, is not necessarily to iterative processing in calculating process, is able to satisfy the fast of big data quantity
Speed processing.In addition, the present invention can avoid most of building and the biggish region of color difference when line is inlayed in generation.The present invention passes through
Verification experimental verification is feasible, fast to big data volume processing speed, and can satisfy the generation principle for inlaying line.
Above embodiment is not limitation of the present invention, and the present invention is also not limited to the example above, this technology neck
The variations, modifications, additions or substitutions that the technical staff in domain is made within the scope of technical solution of the present invention, also belong to this hair
Bright protection scope.
Claims (4)
1. the rapid generation that a kind of remote sensing image inlays line, it is characterised in that: the overall step of the method are as follows:
Step S1, the effective coverage of two width input images is calculated separately, effective coverage background value cannot be in the area for inlaying line generation
Domain；
Step S2, judge the type of two width images: then going to step S3 if multispectral image, if single-range panchromatic image
Then go to step S4；
Step S3, multispectral each wave band is calculated as single-range panchromatic image；
It step S4, is foundation calculating overlapping region and the error image for calculating overlapping region with geographical coordinate；
Step S5, median filtering is carried out to error image, reduces the influence of noise；
Step S6, the mean value and standard deviation of calculating difference image, according to the size relation threshold value of mean value and standard deviation；
Step S7, error image is divided into according to threshold value by binary map；
Step S8, breadth first algorithm is utilized in binary map, finds optimal path, and optimal path is to inlay line.
2. the rapid generation that remote sensing image according to claim 1 inlays line, it is characterised in that: the step S4
In, when calculating the error image of overlapping region, take two width image geographical coordinate absolute value of the difference of same position as error image.
3. the rapid generation that remote sensing image according to claim 1 or 2 inlays line, it is characterised in that: the step
In S5, median filtering uses multithreads computing to improve calculating speed.
4. the rapid generation that remote sensing image according to claim 1-3 inlays line, it is characterised in that: described
In step S6, according to the concrete mode of mean value and the size relation threshold value of standard deviation are as follows: if mean value is less than standard deviation, show
Two width images are not much different, and take mean value as threshold value；If mean value is greater than standard deviation, show that two width images difference is larger, threshold value takes
Sum of the two.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810735088.XA CN108986030A (en) | 2018-07-06 | 2018-07-06 | A kind of remote sensing image inlays the rapid generation of line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810735088.XA CN108986030A (en) | 2018-07-06 | 2018-07-06 | A kind of remote sensing image inlays the rapid generation of line |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108986030A true CN108986030A (en) | 2018-12-11 |
Family
ID=64536280
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810735088.XA Withdrawn CN108986030A (en) | 2018-07-06 | 2018-07-06 | A kind of remote sensing image inlays the rapid generation of line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108986030A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112669459A (en) * | 2020-12-25 | 2021-04-16 | 北京市遥感信息研究所 | Satellite image optimal mosaic line generation method based on feature library intelligent decision |
-
2018
- 2018-07-06 CN CN201810735088.XA patent/CN108986030A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112669459A (en) * | 2020-12-25 | 2021-04-16 | 北京市遥感信息研究所 | Satellite image optimal mosaic line generation method based on feature library intelligent decision |
| CN112669459B (en) * | 2020-12-25 | 2023-05-05 | 北京市遥感信息研究所 | Satellite image optimal mosaic line generation method based on feature library intelligent decision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | Learning signed distance field for multi-view surface reconstruction | |
| CN109145922B (en) | Automatic cutout system | |
| CN110853026B (en) | Remote sensing image change detection method integrating deep learning and region segmentation | |
| CN105761308B (en) | A kind of occlusion area building facade method for reconstructing of ground LiDAR and image data fusion | |
| Wei et al. | BuildMapper: A fully learnable framework for vectorized building contour extraction | |
| CN111583097A (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
| CN103871072B (en) | Orthography based on project digital elevation model inlays line extraction method | |
| WO2022037170A1 (en) | Instance segmentation method and system for enhanced image, and device and medium | |
| Jarząbek-Rychard et al. | 3D building reconstruction from ALS data using unambiguous decomposition into elementary structures | |
| Pang et al. | SGM-based seamline determination for urban orthophoto mosaicking | |
| CN109685145A (en) | A kind of small articles detection method based on deep learning and image procossing | |
| CN102663716A (en) | Seam line network generating method suitable for convex polygonal image effective ranges | |
| CN111160291A (en) | Human eye detection method based on depth information and CNN | |
| Zeng et al. | Interactive shape from shading | |
| CN116630352A (en) | Rock core measurement method and device based on bidirectional cascade pixel differential network | |
| CN108986030A (en) | A kind of remote sensing image inlays the rapid generation of line | |
| Deng et al. | UMiT-Net: a U-shaped mix-transformer network for extracting precise roads using remote sensing images | |
| CN110472640A (en) | A kind of target detection model prediction frame processing method and processing device | |
| Quan et al. | ORSI Salient Object Detection via Progressive Semantic Flow and Uncertainty-aware Refinement | |
| CN112258561B (en) | Matching point acquisition method for image stitching | |
| Nguyen et al. | High-definition texture reconstruction for 3D image-based modeling | |
| JP2005165969A (en) | Image processor and method | |
| CN107369150B (en) | Method for detecting rectangular target and rectangular target detection device | |
| Trunz et al. | Inverse procedural modeling of knitwear | |
| CN105205826B (en) | A kind of SAR image azimuth of target method of estimation screened based on direction straight line |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 101399 No. 2 East Airport Road, Shunyi Airport Economic Core Area, Beijing (1st, 5th and 7th floors of Industrial Park 1A-4) Applicant after: Zhongke Star Map Co., Ltd. Address before: 101399 No. 2 East Airport Road, Shunyi Airport Economic Core Area, Beijing (1st, 5th and 7th floors of Industrial Park 1A-4) Applicant before: Space Star Technology (Beijing) Co., Ltd. |
|
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20181211 |