CN109146779B - Digital camouflage pattern splicing method based on texture synthesis and optimal suture line - Google Patents
Digital camouflage pattern splicing method based on texture synthesis and optimal suture line Download PDFInfo
- Publication number
- CN109146779B CN109146779B CN201810798188.7A CN201810798188A CN109146779B CN 109146779 B CN109146779 B CN 109146779B CN 201810798188 A CN201810798188 A CN 201810798188A CN 109146779 B CN109146779 B CN 109146779B
- Authority
- CN
- China
- Prior art keywords
- camouflage pattern
- camouflage
- pattern
- splicing
- digital
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 23
- 230000015572 biosynthetic process Effects 0.000 title claims abstract description 21
- 238000003786 synthesis reaction Methods 0.000 title claims abstract description 21
- 238000005516 engineering process Methods 0.000 claims abstract description 14
- 238000011156 evaluation Methods 0.000 claims description 9
- 230000007704 transition Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 7
- 230000004927 fusion Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000009958 sewing Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004826 seaming Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4038—Scaling the whole image or part thereof for image mosaicing, i.e. plane images composed of plane sub-images
-
- G06T5/77—
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Abstract
The invention provides a digital camouflage pattern splicing method based on texture synthesis and an optimal suture line, which can generate large-size patterns with consistent textures and natural transition by applying a texture synthesis technology; the artificially created overlap region is taken from the pattern generated by the texture synthesis technology, so that the original linear seam is directly replaced by the overlap region, and the linear seam is eliminated. Meanwhile, the optimal suture tries to find a path which enables the difference between two sides of the gap to be minimum, and the splicing pattern can be smoothly transited on two sides of the suture as far as possible. The algorithm can better eliminate the splicing gaps, does not change the size of the splicing patterns, and has stronger universality.
Description
Technical Field
The invention belongs to the cross technical field of computer technology and military engineering camouflage technology, and particularly relates to a digital camouflage pattern splicing method based on texture synthesis and an optimal suture line.
Background
The digital camouflage is a camouflage pattern which is developed rapidly in recent years and is widely applied in the military camouflage field. The digital camouflage utilizes the spatial color mixing principle and the plaque characteristic, so that the boundary between the camouflage target and the background is broken and blurred, and the camouflage effect is better than that of the traditional camouflage pattern. Generally, a digital camouflage pattern generated according to a natural background of a camouflage target is a two-dimensional image with a fixed size, and when the digital camouflage pattern is applied to an actual camouflage target, obvious splicing marks appear at the edges of each plane, so that a new target exposure feature is formed, the significance of the target is increased, and the camouflage effect is greatly reduced.
Currently, the mainstream image stitching algorithm is based on feature point stitching. The method mainly comprises the steps of calculating the overlapping area of two images according to the result of feature point matching, then obtaining the optimal suture line of the overlapping area, and finally completing splicing by using an image fusion technology.
Feature point-based image registration may result in rotation of the images to be stitched, and the stitched image size is difficult to determine. The digital camouflage patterns are sensitive to rotation, the splicing size is fixed, registration of the characteristic points is not facilitated, and meanwhile the digital camouflage is single in color and not beneficial to image fusion. This makes it difficult to directly apply the conventional stitching algorithm to digital camouflage stitching.
Aiming at the splicing and seaming problems of digital camouflage, a digital camouflage splicing scheme based on a cylinder is proposed in the document [1] a digital camouflage splicing algorithm (Jun, zhang Qiang, cheng Zhong Wei, et al. Optical technology, 2017,43 (4): 339-342.). According to the method, two digital camouflage patterns can be smoothly transited at the splicing position by adding multiple rows of transitional camouflage patterns. However, the method can cause the size of the splicing diagram to be enlarged, and the application range is small; because the transitional camouflage color is determined according to the patch configuration at the two sides of the seam, if the single color area at one side of the seam is larger, the seam is obvious, and meanwhile, the color blocks with large area can generate larger influence on the transitional camouflage color array, so that the generated transitional camouflage color array is difficult to eliminate the seam.
Disclosure of Invention
The invention aims to provide a digital camouflage pattern splicing method based on texture synthesis and an optimal suture line, which solves the problem of obvious seams in the existing digital camouflage pattern splicing so as to improve the camouflage performance of a digital camouflage target.
In order to achieve the purpose, the technical scheme of the invention is as follows:
the digital camouflage pattern splicing method based on texture synthesis and an optimal suture line comprises the following steps:
step 1, selecting a typical background area, shooting and acquiring an original background image of the area, and designing a digital camouflage pattern A according to the original background image and a digital camouflage generation algorithm;
step 2, generating a large-size camouflage pattern B by using a texture synthesis technology according to the digital camouflage pattern A;
step 3, randomly intercepting two camouflage patterns C with the same size in the digital camouflage pattern B 1 And camouflage pattern C 2 And assume camouflage pattern C 1 Pieced together in camouflage pattern C 2 Left of (d);
step 4, applying texture synthesis technology to obtain the camouflage pattern C 1 Spread to the right side to generate a camouflage pattern D 1 Pattern C of camouflage 2 Expanding to the left side to obtain a camouflage pattern D 2 (ii) a Camouflage pattern C 1 Zhonghe camouflage pattern D 2 Overlapped part and camouflage pattern D 2 Together forming a pseudo overlap region omega 1 Camouflage pattern C 2 Zhonghe camouflage pattern D 1 Overlapped part and camouflage pattern D 1 Together forming a pseudo overlap region omega 2 ；
Step 5, calculating the pseudo-overlapping areas omega by using a suture algorithm respectively 1 And a pseudo overlap region omega 2 Suture line L of 1 And L 2 Are respectively aligned with L 1 And L 2 Adding the evaluation values of the points, selecting L 1 Or L 2 The suture with smaller addition value E is evaluated as the optimal suture for final splicing;
step 6, aiming at the camouflage pattern C in the step 5 1 And camouflage pattern C 2 Optimal suture stitching is performed.
Further, in step 6, the camouflage pattern C is treated 1 And camouflage pattern C 2 The optimal suture line splicing is carried out, and the specific method comprises the following steps: will be a pseudo-overlap regionTwo camouflage patterns in the domain (one of the camouflage patterns to be spliced is expanded) are cut along the suture line, the part close to one side of the splicing is discarded, and the rest parts are spliced together along the suture line, so that the whole splicing process is completed.
The invention has the beneficial effects that:
the digital camouflage pattern splicing method provided by the invention can generate large-size patterns with consistent textures and natural transition by using a texture synthesis technology; the artificially created overlap area is taken from the pattern generated by the texture synthesis technology, so that the original straight seam is directly replaced by the overlap area, and the straight seam is eliminated. Meanwhile, the optimal suture tries to find a path which enables the difference between two sides of the gap to be minimum, and the splicing pattern can be smoothly transited on two sides of the suture as far as possible. The algorithm can better eliminate the splicing gaps, does not change the size of the splicing patterns, and has stronger universality.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a region division diagram of a mosaic pattern, wherein FIG. 2 (a) is a camouflage pattern D 1 FIG. 2 (b) is a schematic view of a camouflage pattern D 2 FIG. 2 (c) is a schematic view showing a pseudo overlap region Ω 1 FIG. 2 (d) is a schematic view showing a pseudo overlap region Ω 2 A schematic diagram;
FIG. 3 (a) is a photograph of an original background of an aerial photograph of an embodiment, and FIG. 3 (b) is a schematic diagram of a digital camouflage pattern A generated by a design of an embodiment;
FIG. 4 is a schematic view of an embodiment of a digital camouflage pattern B;
FIG. 5 shows an embodiment of the camouflage pattern C 1 And camouflage pattern C 2 Schematic in camouflage pattern B;
FIG. 6 (a) is a camouflage pattern C of the embodiment 1 FIG. 6 (b) is a schematic view of a camouflage pattern D in the embodiment 1 FIG. 6 (c) is a schematic view of a camouflage pattern D in the embodiment 2 FIG. 6 (d) is a schematic view of a camouflage pattern C in the embodiment 2 FIG. 6 (e) is a schematic view showing a pseudo overlap region Ω in the embodiment 1 FIG. 6 (f) is a diagram showing a pseudo overlap region Ω in the example 1 Optimal suture line L 1 FIG. 6 (g) is a schematic view showing a pseudo overlap region Ω in the embodiment 2 FIG. 6 (h) is a diagram of the pseudo overlap region Ω in the example 2 Optimal suture line L 2 A schematic view;
FIG. 7 is a diagram illustrating the splicing effect of the embodiment.
Detailed Description
The present invention will be described in further detail with reference to the following detailed description and accompanying drawings. Wherein like elements in different embodiments are numbered with like associated elements. In the following description, numerous details are set forth in order to provide a better understanding of the present application. However, those skilled in the art will readily recognize that some of the features may be omitted or replaced with other elements, materials, methods in different instances. In some instances, certain operations related to the present application have not been shown or described in this specification in order not to obscure the core of the present application with unnecessary detail, and it is not necessary for those skilled in the art to describe these operations in detail, so that they may be fully understood from the description in the specification and the general knowledge in the art.
As shown in fig. 1, the digital camouflage pattern splicing method based on texture synthesis and optimal suture line of the invention is characterized by comprising the following steps:
step 1, selecting a typical background area, shooting and obtaining an original background image of the area, and designing a digital camouflage pattern A according to the original background image and a digital camouflage generation algorithm (research on digital camouflage generation algorithms (Jun, swordsman, caliper and persevere, etc.; photoelectric engineering 2010,37 (11): 110-114.)));
step 2, generating a large-size camouflage pattern B by using a texture synthesis technology according to the digital camouflage pattern A;
step 3, randomly intercepting two camouflage patterns C with the same size in the digital camouflage pattern B 1 、C 2 And assume camouflage pattern C 1 Is spliced at C 2 Left of (d);
step 4, applying texture synthesis technologySurgery, make the camouflage pattern C 1 Expand to the right side to generate a camouflage pattern D 1 As shown in FIG. 2 (a); make the camouflage pattern C 2 Expanding to the left side to obtain a camouflage pattern D 2 As shown in FIG. 2 (b); camouflage pattern C 1 Zhonghe camouflage pattern D 2 Overlapped part and camouflage pattern D 2 Together forming a pseudo overlap region omega 1 The shaded portion in FIG. 2 (c) represents Ω 1 Camouflage pattern C 2 Zhonghe camouflage pattern D 1 Overlapped part and camouflage pattern D 1 Together forming a pseudo overlap region omega 2 The shaded portion in FIG. 2 (d) represents Ω 2 (ii) a The curves inside the overlapping areas of fig. 2 (c), 2 (d) are sutures; (obtaining camouflage pattern D in the figure 1 And camouflage pattern D 2 Is a camouflage pattern C 1 Or camouflage pattern C 2 One-half of the width);
step 5, respectively calculating the pseudo overlapping areas omega 1 And a pseudo overlap region omega 2 Is optimum suture line L 1 And L 2 Selecting a suture line with a smaller sum E of the evaluation values as an optimal suture line for final splicing;
and 6, splicing the camouflage pattern C1 and the camouflage pattern C2 which are obtained in the step 5 by using a suture line.
The invention is described in detail below with reference to a specific example:
example (b):
step 1, using a Xinntom 4 unmanned aerial vehicle in Xin Jiang to take an ocean background photo in field, wherein the height and distance of aerial photo are about 0-100 m, the incidence complementary angle is not more than 45 degrees, the aerial photo direction is within 30 degrees from the left and right of the illumination direction, the solar altitude angle is more than 30 degrees, the atmospheric visibility is more than 10 kilometers, and no exposure and noise appear on pictures; based on the principles of research on digital camouflage generation algorithms (well-known, swordsman, museup et al. Photoelectric engineering, 2010,37 (11): 110-114.), a digital camouflage pattern a (resolution 286 × 184) was generated using Matlab software and original background photograph design, with the aerial background photograph shown in fig. 3 (a) and the generated digital camouflage pattern shown in fig. 3 (b).
Step 2, using texture synthesis technology and Matlab software in Tile size adaptive Tile texture synthesis algorithm (sun sharp, liu shun, computer engineering and application, 2016,52 (11): 164-168.), a digital camouflage pattern a is used as a sample to generate a digital camouflage pattern B with a resolution of 1280 × 900, as shown in fig. 4.
Step 3, randomly searching the camouflage pattern C with the resolution of 240 multiplied by 270 in the digital camouflage pattern B 1 And camouflage pattern C 2 As a mosaic pattern, and assume a camouflage pattern C 1 Pieced together in the camouflage pattern C 2 Left side of (camouflage pattern C) 1 And camouflage pattern C 2 Of the same size) as shown in fig. 5, wherein the area selected by the box is the camouflage pattern C 1 And camouflage pattern C 2 ；
Step 4, respectively aligning the camouflage patterns C 1 And camouflage pattern C 2 Expanding in the splicing direction to obtain a pattern camouflage pattern D with the resolution of 120 multiplied by 270 1 And camouflage pattern D 2 See fig. 6 (b) and 6 (c), for the purpose of artificially creating the pseudo-overlap region Ω 1 And a pseudo overlap region omega 2 。
Step 5, respectively calculating the pseudo-overlap region omega by using a method in image stitching combined with optimal suture line and multi-resolution fusion (valley rain, zhouyang, ninggang, and the like, chinese graphic newspaper, 2017,22 (6): 842-851.) 1 And a pseudo overlap region omega 2 The optimal suture line is searched in the energy evaluation graph, and the method for searching the optimal suture line specifically adopts a greedy strategy to select the optimal suture line from a large number of suture lines; FIG. 6 (a), FIG. 6 (b), FIG. 6 (C), FIG. 6 (d) are the camouflage pattern C 1 Camouflage pattern D 1 Camouflage pattern D 2 Camouflage pattern C 2 Fig. 6 (e) and 6 (g) show the pseudo overlap region Ω, respectively 1 And a pseudo overlap region omega 2 Fig. 6 (f) and 6 (h) are the pseudo overlap region Ω, respectively 1 And a pseudo overlap region omega 2 Is optimum for the suture line L 1 、L 2 。
Step 6, in the document "image stitching combining optimal stitching line and multi-resolution fusion" (valley rain, zhouyang, ninggang, etc., china graphic newspaper, 2017,22 (6): 842-851.), the sum E of the evaluation values is determined by the stitching lineThe evaluation values of all points are added, and the evaluation values are evaluation indexes used for determining the optimal suture line in the suture line algorithm. The sum of the evaluation values indicates the difference between the images on both sides of the sewing line, and the larger the value, the larger the difference between the images on both sides of the sewing line, and vice versa. In order to make the transition at the splice smoother, a smaller value of E is selected, and the optimal suture line L is calculated respectively 1 And L 2 Sum of the evaluated values of
And
to obtain
Thus selecting the suture L with smaller E 2 Splicing is carried out, and the specific implementation method comprises the following steps: the pseudo overlap region omega 2 Along the seam L 2 Cutting, and cutting 1 In the suture line L 2 Right part and C 2 In the suture line L 2 The left parts are pieced together to form a camouflage pattern S, and then C 2 And (4) directly splicing the two parts on the right side of the S, thereby completing the whole splicing process. The splicing results are shown in fig. 7.
The present invention has been described in terms of specific examples, which are provided to aid understanding of the invention and are not intended to be limiting. For a person skilled in the art to which the invention pertains, several simple deductions, modifications or substitutions may be made according to the idea of the invention.
Claims (2)
1. The digital camouflage pattern splicing method based on texture synthesis and an optimal suture line is characterized by comprising the following steps of:
step 1, selecting a typical background area, shooting and acquiring an original background image of the area, and designing a digital camouflage pattern A according to the original background image and a digital camouflage generation algorithm;
step 2, generating a large-size camouflage pattern B by using a texture synthesis technology according to the digital camouflage pattern A;
step 3, randomly intercepting two camouflage patterns C with the same size in the digital camouflage pattern B 1 And camouflage pattern C 2 And assume camouflage pattern C 1 Pieced together in the camouflage pattern C 2 The left side of (c);
step 4, applying texture synthesis technology to obtain the camouflage pattern C 1 Expand to the right side to generate a camouflage pattern D 1 Pattern C of camouflage 2 Expanding to the left side to obtain a camouflage pattern D 2 (ii) a Camouflage pattern C 1 Zhonghe camouflage pattern D 2 Overlapped part and camouflage pattern D 2 Together forming a pseudo overlap region omega 1 Camouflage pattern C 2 Zhonghe camouflage pattern D 1 Overlapped part and camouflage pattern D 1 Together forming a pseudo overlap region omega 2 ；
Step 5, respectively calculating the pseudo-overlapping areas omega by using a suture line algorithm 1 And a pseudo overlap region omega 2 Of (2) a suture L 1 And L 2 Respectively to L 1 And L 2 Adding the evaluation values of the points, selecting L 1 Or L 2 Evaluating the suture with smaller addition value E as the optimal suture for final splicing;
step 6, aiming at the camouflage pattern C in the step 5 1 And camouflage pattern C 2 Optimal suture stitching is performed.
2. The method for splicing a digital camouflage pattern based on texture synthesis and optimal suture line according to claim 1, wherein in step 6, the camouflage pattern C is subjected to 1 And camouflage pattern C 2 The optimal suture splicing is carried out, and the specific method comprises the following steps: and cutting the two camouflage patterns in the pseudo-overlapping area along the optimal suture line, discarding the part close to one side of the splicing, and splicing the rest parts together along the optimal suture line, thereby completing the whole splicing process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810798188.7A CN109146779B (en) | 2018-07-19 | 2018-07-19 | Digital camouflage pattern splicing method based on texture synthesis and optimal suture line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810798188.7A CN109146779B (en) | 2018-07-19 | 2018-07-19 | Digital camouflage pattern splicing method based on texture synthesis and optimal suture line |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109146779A CN109146779A (en) | 2019-01-04 |
| CN109146779B true CN109146779B (en) | 2022-11-08 |
Family
ID=64801069
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810798188.7A Active CN109146779B (en) | 2018-07-19 | 2018-07-19 | Digital camouflage pattern splicing method based on texture synthesis and optimal suture line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109146779B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112800499B (en) * | 2020-12-02 | 2023-12-26 | 杭州群核信息技术有限公司 | Diatom ooze pattern high-order design method based on image processing and real-time material generation capability |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103473798A (en) * | 2013-09-16 | 2013-12-25 | 云南大学 | Improved line-based texture synthesis accelerating method |
| CN104680501A (en) * | 2013-12-03 | 2015-06-03 | 华为技术有限公司 | Image splicing method and device |
| CN107146213A (en) * | 2017-05-08 | 2017-09-08 | 西安电子科技大学 | Unmanned plane image split-joint method based on suture |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9940695B2 (en) * | 2016-08-26 | 2018-04-10 | Multimedia Image Solution Limited | Method for ensuring perfect stitching of a subject's images in a real-site image stitching operation |
-
2018
- 2018-07-19 CN CN201810798188.7A patent/CN109146779B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103473798A (en) * | 2013-09-16 | 2013-12-25 | 云南大学 | Improved line-based texture synthesis accelerating method |
| CN104680501A (en) * | 2013-12-03 | 2015-06-03 | 华为技术有限公司 | Image splicing method and device |
| CN107146213A (en) * | 2017-05-08 | 2017-09-08 | 西安电子科技大学 | Unmanned plane image split-joint method based on suture |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109146779A (en) | 2019-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105245841B (en) | A kind of panoramic video monitoring system based on CUDA | |
| CN104680501B (en) | The method and device of image mosaic | |
| CN104732482B (en) | A kind of multi-resolution image joining method based on control point | |
| Fang et al. | Textureshop: texture synthesis as a photograph editing tool | |
| EP2057585B1 (en) | Mosaic oblique images and methods of making and using same | |
| CN109242954B (en) | Multi-view three-dimensional human body reconstruction method based on template deformation | |
| US7365744B2 (en) | Methods and systems for image modification | |
| CN111968129A (en) | Instant positioning and map construction system and method with semantic perception | |
| Pandey et al. | Image mosaicing: A deeper insight | |
| CN105957007A (en) | Image stitching method based on characteristic point plane similarity | |
| CN110390640A (en) | Graph cut image split-joint method, system, equipment and medium based on template | |
| CN104408689A (en) | Holographic-image-based streetscape image fragment optimization method | |
| CN1853195A (en) | Program for correcting image distortion, apparatus for correcting image distortion, method for correcting image distortion, and recording medium storing program for correcting image distortion | |
| CN103871072B (en) | Orthography based on project digital elevation model inlays line extraction method | |
| CN109146779B (en) | Digital camouflage pattern splicing method based on texture synthesis and optimal suture line | |
| CN107862674A (en) | Depth image fusion method and system | |
| Tsoi et al. | Multi-view document rectification using boundary | |
| Zhao et al. | RFVTM: a recovery and filtering vertex trichotomy matching for remote sensing image registration | |
| Wang et al. | Research on key techniques of multi-resolution coastline image fusion based on optimal seam-line | |
| Guislain et al. | Detecting and correcting shadows in urban point clouds and image collections | |
| CN112396555A (en) | Interactive multi-scene image processing, information extraction and synthesis method | |
| CN116228521A (en) | Heterologous image registration and fusion method | |
| CN114565717A (en) | Three-dimensional image splicing method based on three-dimensional scene reconstruction | |
| Yang et al. | An error-activation-guided blind metric for stitched panoramic image quality assessment | |
| Frohlich et al. | Region based fusion of 3D and 2D visual data for Cultural Heritage objects |
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 |