CN113850734A - Poisson equation fused remote sensing image automatic color homogenizing method - Google Patents
Poisson equation fused remote sensing image automatic color homogenizing method Download PDFInfo
- Publication number
- CN113850734A CN113850734A CN202111041316.1A CN202111041316A CN113850734A CN 113850734 A CN113850734 A CN 113850734A CN 202111041316 A CN202111041316 A CN 202111041316A CN 113850734 A CN113850734 A CN 113850734A
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- sensing image
- image
- color
- boundary
- 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 title claims abstract description 43
- 230000005855 radiation Effects 0.000 claims abstract description 11
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 238000000265 homogenisation Methods 0.000 claims abstract description 5
- 238000012937 correction Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 2
- 238000010606 normalization Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 230000004927 fusion Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000012805 post-processing Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000002310 reflectometry Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- 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
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- 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
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- 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
-
- 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
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10036—Multispectral image; Hyperspectral image
-
- 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
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10041—Panchromatic image
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Facsimile Image Signal Circuits (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an automatic color homogenizing method for remote sensing images fused with Poisson's equation, which comprises the following steps: acquiring a remote sensing image, and preprocessing the remote sensing image; automatically selecting a first remote sensing image and a second remote sensing image from the preprocessed remote sensing images, wherein the first remote sensing image and the second remote sensing image are intersected to form an overlapping area, and the overlapping area comprises a plurality of intersection points; and according to the overlapping area and the plurality of intersection points, performing color homogenization on the first remote sensing image and the second remote sensing image through a Poisson equation. Compared with the traditional color homogenizing method and the mosaic line eliminating method, the method can be suitable for mosaic lines with any shapes and topologies, and can realize true seamless low distortion on the basis of ensuring the normalization precision of relative radiation.
Description
Technical Field
The invention belongs to the field of remote sensing image processing, and particularly relates to an automatic color homogenizing method for a remote sensing image fused with a Poisson equation.
Background
With the rapid development of remote sensing technology, large-scale and high-precision regional monitoring based on remote sensing satellite images is widely applied to various industry fields. Due to the limitation of imaging width, mechanism and cloud coverage, a single remote sensing image cannot cover the whole monitoring area, and multiple remote sensing images need to be spliced.
Remote sensing image splicing, also called remote sensing image mosaic, is a technical process of splicing two or more images with a certain overlapping degree together to form an integral image. Due to the influences of factors such as imaging time, an imaging sensor, an illumination effect, atmospheric attenuation and the like, the radiation levels of remote sensing images are different, so that the radiation distortion of the same object is caused, and the tone difference of ground objects among the images is large. Relative radiation normalization among a plurality of remote sensing images can realize hue difference among the images, and is important work for remote sensing image splicing.
The relative radiation normalization method of the remote sensing image can improve the hue difference between images, but on the mosaic line, post-processing is still needed to realize smooth transition at the mosaic line. Meanwhile, in a complex scene with a large number of remote sensing images, the images have different cross modes or extreme topological relations (cross areas are small), and the removal of the mosaic lines by using the method is more difficult. It can be said that the elimination of the mosaic lines directly affects the image stitching effect, and the manual post-processing of the mosaic lines consumes a lot of manpower and time costs.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention provides an automatic color homogenizing method for remote sensing images fused with a Poisson equation, which can solve the problems in the prior art.
In order to achieve the technical purpose, the technical scheme adopted by the invention is as follows:
the invention provides an automatic color homogenizing method for remote sensing images fused with Poisson's equation, which comprises the following steps:
s1: acquiring a remote sensing image, and preprocessing the remote sensing image;
s2: automatically selecting a first remote sensing image and a second remote sensing image from the preprocessed remote sensing images, wherein the first remote sensing image and the second remote sensing image are intersected to form an overlapping area, and the overlapping area comprises a plurality of intersection points;
s3: and according to the overlapping area and the plurality of intersection points, performing color homogenization on the first remote sensing image and the second remote sensing image through a Poisson equation.
Further, the S3 includes:
s31: generating mosaic lines according to the intersection points and the overlapping regions, and obtaining mosaic line regions after the overlapping regions are optimized based on the mosaic lines;
s32: constructing a target space omega according to the mosaic line, the color distribution of the first remote sensing image in the mosaic line region and the color distribution of the second remote sensing image in the mosaic line region, wherein the target space omega is composed of a boundary space delta omega and a boundary space omega0Composition of the space omega in the boundary0Composed of one or more pixels, the space omega in the boundary0The gradient field v in the color matching is an optimized gradient field obtained by a first color homogenizing method;
s33: fitting the space in the boundary Ω by Poisson's equation0The pixel value of (2) is calculated to obtain an optimized pixel value, and the optimized pixel value is taken as the space omega in the boundary0The remote sensing image is automatically homogenized by the pixel value of the image sensor.
Further, the poisson equation is as follows:
Δf=divυoverΩwith f|δΩ=f*|δΩ
in the formula, f is a pixel value in the target space omega, f is a pixel value outside the target space omega, and v is an optimized gradient field obtained by the first color homogenizing method.
Further, the first color homogenizing method includes a histogram matching method and a Wallis filtering method.
Further, the boundary space δ Ω is composed of a mosaic line and a boundary line of the color distribution of the second remote sensing image in the mosaic line region.
Further, the preprocessing comprises orthorectification, geometric rectification and radiation rectification.
Further, the pre-processing also includes atmospheric correction.
Further, the step of automatically selecting the first remote sensing image and the second remote sensing image from the preprocessed remote sensing images comprises:
selecting the neighborhood gray level average value of the preprocessed remote sensing image as a spatial characteristic quantity of gray level distribution, and forming a characteristic binary group by the spatial characteristic quantity and the pixel gray level of the preprocessed remote sensing image;
calculating the two-dimensional entropy of the preprocessed discrete image of the remote sensing image by a discrete image two-dimensional entropy method;
the formula of the discrete image two-dimensional entropy is as follows:
in the formula, H is a two-dimensional entropy of the discrete image, and i is a spatial characteristic quantity of gray distribution; j is the pixel gray scale of the remote sensing image, f (i, j) is the frequency of appearance of the characteristic binary group (i, j), and N is the scale of the remote sensing image;
and selecting the remote sensing image with large two-dimensional entropy of the discrete image as a first remote sensing image, and selecting the remote sensing image with small two-dimensional entropy of the discrete image as a second remote sensing image.
The invention also comprises the step of carrying out automatic color matching on the uniform color image obtained in the step S3 and the reference color image to obtain a uniform color image result meeting the corresponding color requirement.
The invention has the beneficial effects that: the invention discloses an automatic color homogenizing method for fusing a Poisson equation in remote sensing image splicing, which comprises the steps of obtaining a remote sensing image and preprocessing the remote sensing image; automatically selecting a first remote sensing image and a second remote sensing image from the preprocessed remote sensing images, wherein the first remote sensing image and the second remote sensing image are intersected to form an overlapping area, and the overlapping area comprises a plurality of intersection points; and according to the overlapping area and the plurality of intersection points, performing color homogenization on the first remote sensing image and the second remote sensing image through a Poisson equation. Compared with the traditional color homogenizing method and the mosaic line eliminating method, the method can be suitable for mosaic lines with any shapes and topologies, can realize real seamless low distortion on the basis of ensuring the normalization precision of relative radiation, is fully automatic, and saves a large amount of labor and time cost.
Drawings
FIG. 1 is a schematic flow chart of a first embodiment of the method for automatically homogenizing colors of remote sensing images by fusing Poisson's equation;
fig. 2(a) is a schematic diagram of a first remote sensing image region;
fig. 2(b) is a schematic diagram of a second remote sensing image region;
FIG. 2(c) is a schematic view of the overlap region;
FIG. 3 is a schematic view of the composition of the target space;
FIG. 4(a) is a schematic diagram of a remote sensing image before automatic color equalization according to an embodiment of the present invention;
FIG. 4(b) is a schematic diagram of a remote sensing image after automatic color equalization according to an embodiment of the present invention;
FIG. 5(a) is a partial schematic view of a remote sensing image before automatic color equalization according to an embodiment of the present invention;
fig. 5(b) is a schematic partial view of a remote sensing image after automatic color equalization according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a flowchart of an automated color-homogenizing method for fusion poisson fusion in remote sensing image stitching, which includes steps S1-S3.
Step S1 is to obtain remote sensing image and to preprocess the remote sensing image.
The remote sensing image preprocessing comprises orthorectification, geometric rectification, radiometric calibration and atmospheric rectification, wherein the image is a panchromatic image or a multispectral image:
(1) orthorectification and geometric correction guarantee the correctness of the spatial position of the remote sensing image to be spliced;
(2) the radiometric calibration converts DN value into apparent reflectivity, converts the brightness gray value of the remote sensing image into absolute radiance, and has the formula as follows:
Lλ=k*DN+c (1)
wherein L isλIs the radiance value of the band λ, dn (digital number) records the gray value of the feature, k and c are the gain and offset, respectively.
The atmosphere correction is to convert the absolute radiance information into the earth surface reflectivity and eliminate the errors caused by atmosphere scattering, absorption and reflection. The atmospheric correction adopts a 6S atmospheric radiation transmission model. The atmospheric radiation transmission model 6S adopts a most similar and continuous scattering SOS (successful Order of Scattering) method to solve a radiation transmission equation.
Step S2, automatically selecting a first remote sensing image and a second remote sensing image from the preprocessed remote sensing images, wherein the first remote sensing image and the second remote sensing image are intersected to form an overlapping area, and the overlapping area comprises a plurality of intersection points.
Screening the first remote sensing image and the second remote sensing image by using a discrete image two-dimensional entropy method, wherein the discrete image two-dimensional entropy is larger than that of the first remote sensing image and is used as a reference image; and the discrete image with small two-dimensional entropy is a second remote sensing image which is used as an image to be homogenized. As a result, as shown in fig. 2, fig. 2(a) shows a first remote sensing image region, i.e., a reference image; fig. 2(b) is a second remote sensing image, i.e. an image area to be homogenized; fig. 2(c) is a schematic view of the overlapping region.
The specific process of selecting the first remote sensing image and the second remote sensing image is as follows:
(1) selecting the neighborhood gray level average value of the preprocessed remote sensing image as a spatial characteristic quantity of gray level distribution, and forming a characteristic binary group by the spatial characteristic quantity and the pixel gray level of the preprocessed remote sensing image;
(2) calculating the probability of a certain gray level appearing in the remote sensing image according to the spatial characteristic quantity of the gray level distribution and the pixel gray level of the remote sensing image:
wherein Pij is the probability of a certain gray level appearing in the remote sensing image, and i is the spatial characteristic quantity of gray level distribution; j is the pixel gray scale of the remote sensing image, f (i, j) is the frequency of the appearance of the characteristic binary group (i, j), and N is the scale of the remote sensing image.
(3) Constructing a discrete image two-dimensional entropy according to the probability of a certain gray level appearing in the remote sensing image:
wherein H is the two-dimensional entropy of the discrete image.
(4) And selecting the first remote sensing image with the large two-dimensional entropy of the discrete image and the second remote sensing image with the small two-dimensional entropy of the discrete image.
And step S3, according to the overlapping area and the plurality of intersection points, homogenizing the first remote sensing image and the second remote sensing image through a Poisson equation.
S31: and generating mosaic lines according to the intersection points and the overlapping regions, wherein the overlapping regions are optimized based on the mosaic lines to obtain mosaic line regions.
(1) Acquiring an intersection set I ═ I where the overlapping region and the reference image intersect1,I2,...,In};
(2) Obtaining the connection sequence C of each intersection point In the intersection point set I according to the sequence of the intersection points In on the intersection line of the overlapping region and the reference image1,C2,...,Cn-1};
(3) Establishing a buffer area B ═ B on the overlapping area according to the connection sequence C1,B2,...,Bn-1In which BtIs CtA corresponding cache region, t ∈ (1, 2.. n-1);
(4) in each buffer BtAccording to BtAnd constructing a loss function according to the color difference of each pixel of the upper reference image and the image to be color-homogenized, and solving the optimal mosaic line path according to the loss function. The constructed chromatic aberration construction loss function is as follows:
wherein the content of the first and second substances,the loss values of the pixels (x, y) on the reference image and the image to be homogenized,is defined as:
wherein k is the number of bands of the image,is the color value at the reference image (x, y),to be color-homogenizedColor values at the image (x, y).
S32: constructing a target space omega according to the mosaic line, the color distribution of the first remote sensing image in the mosaic line region and the color distribution of the second remote sensing image in the mosaic line region, wherein the target space omega is composed of a boundary space delta omega and a boundary space omega0Composition of the space omega in the boundary0Composed of one or more pixels, the space omega in the boundary0The gradient field v in (1) is the gradient field optimized by the first color homogenizing method.
The target space omega is composed of a boundary space delta omega and a boundary space omega00 composition, see fig. 3, boundary space δ Ω or boundary 31, and boundary space Ω00 is 32. Space omega in the boundary0An optimization space is obtained after optimization by a histogram and other methods. Optimized boundary inner space omega0The noise immunity to water, cloud and change abnormal response can be improved, and simultaneously the gradient field value can be changed to the maximum extent, and the color homogenizing effect is improved.
S33: fitting the space in the boundary Ω by Poisson's equation0The pixel value of (2) is calculated to obtain an optimized pixel value, and the optimized pixel value is taken as omega0The remote sensing image is automatically homogenized by the pixel value of the image sensor.
The poisson equation is as follows:
Δf=divυoverΩwith f|δΩ=f*|δΩ (6)
wherein f is a pixel value in the target space omega, f is a pixel value outside the target space omega, and v is an optimized gradient field obtained by the first color homogenizing method.
Fig. 4(a) is a schematic diagram of a remote sensing image before automatic color homogenization according to an embodiment of the present invention, and fig. 5(a) is a schematic diagram of a partial enlargement of fig. 4 (a). Fig. 4(b) is a schematic diagram of a remote sensing image after automatic color homogenizing according to an embodiment of the present invention, and fig. 5(b) is a schematic diagram of a partial enlargement of fig. 4 (b).
Claims (8)
1. A remote sensing image automatic color homogenizing method fused with a Poisson equation is characterized by comprising the following steps:
s1: acquiring a remote sensing image, and preprocessing the remote sensing image;
s2: automatically selecting a first remote sensing image and a second remote sensing image from the preprocessed remote sensing images, wherein the first remote sensing image and the second remote sensing image are intersected to form an overlapping area, and the overlapping area comprises a plurality of intersection points;
s3: and according to the overlapping area and the plurality of intersection points, performing color homogenization on the first remote sensing image and the second remote sensing image through a Poisson equation.
2. The method for automatically homogenizing remote sensing images fused with Poisson' S equation according to claim 1, wherein the S3 includes:
s31: generating mosaic lines according to the intersection points and the overlapping regions, and obtaining mosaic line regions after the overlapping regions are optimized based on the mosaic lines;
s32: constructing a target space omega according to the mosaic line, the color distribution of the first remote sensing image in the mosaic line region and the color distribution of the second remote sensing image in the mosaic line region, wherein the target space omega is composed of a boundary space delta omega and a boundary space omega0Composition of the space omega in the boundary0Composed of one or more pixels, the space omega in the boundary0The gradient field v in the color matching is an optimized gradient field obtained by a first color homogenizing method;
s33: fitting the space in the boundary Ω by Poisson's equation0The pixel value of (2) is calculated to obtain an optimized pixel value, and the optimized pixel value is taken as the space omega in the boundary0The remote sensing image is automatically homogenized by the pixel value of the image sensor.
3. The automatic color-homogenizing method for the remote sensing image fused with the poisson equation, as claimed in claim 1, wherein the poisson equation is as follows:
Δf=div v overΩwithf|δΩ=f*|δΩ
in the formula, f is a pixel value in the target space omega, f is a pixel value outside the target space omega, and v is an optimized gradient field obtained by the first color homogenizing method.
4. The automatic color-homogenizing method for the remote sensing image fused with the Poisson equation, as recited in claim 1, wherein the first color-homogenizing method comprises a histogram matching method and a Wallis filtering method.
5. The automatic color-homogenizing method for the remote sensing image fused with the Poisson equation as claimed in claim 1, wherein the boundary space δ Ω is composed of a mosaic line and a boundary line of the color distribution of the second remote sensing image in the mosaic line region.
6. The method for automatically homogenizing the remote sensing images fused with the Poisson equation, according to claim 1, wherein the preprocessing comprises orthorectification, geometric rectification and radiation rectification.
7. The method for automatically homogenizing remote sensing images fused with Poisson's equation according to claim 6, wherein the preprocessing further comprises atmospheric correction.
8. The automatic color homogenizing method for fusing the Poisson equation in the remote sensing image splicing according to any one of claims 1 to 7, wherein the step of automatically selecting the first remote sensing image and the second remote sensing image from the preprocessed remote sensing images comprises the following steps:
selecting the neighborhood gray level average value of the preprocessed remote sensing image as a spatial characteristic quantity of gray level distribution, and forming a characteristic binary group by the spatial characteristic quantity and the pixel gray level of the preprocessed remote sensing image;
calculating the two-dimensional entropy of the preprocessed discrete image of the remote sensing image by a discrete image two-dimensional entropy method;
the formula of the discrete image two-dimensional entropy is as follows:
in the formula, H is a two-dimensional entropy of the discrete image, and i is a spatial characteristic quantity of gray distribution; j is the pixel gray scale of the remote sensing image, f (i, j) is the frequency of appearance of the characteristic binary group (i, j), and N is the scale of the remote sensing image;
and selecting the remote sensing image with large two-dimensional entropy of the discrete image as a first remote sensing image, and selecting the remote sensing image with small two-dimensional entropy of the discrete image as a second remote sensing image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111041316.1A CN113850734A (en) | 2021-09-06 | 2021-09-06 | Poisson equation fused remote sensing image automatic color homogenizing method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111041316.1A CN113850734A (en) | 2021-09-06 | 2021-09-06 | Poisson equation fused remote sensing image automatic color homogenizing method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113850734A true CN113850734A (en) | 2021-12-28 |
Family
ID=78973214
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111041316.1A Pending CN113850734A (en) | 2021-09-06 | 2021-09-06 | Poisson equation fused remote sensing image automatic color homogenizing method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113850734A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118135149A (en) * | 2024-05-10 | 2024-06-04 | 北京数慧时空信息技术有限公司 | Method for generating remote sensing orthographic image embedded line |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2013244189A (en) * | 2012-05-25 | 2013-12-09 | Asahi Roentgen Kogyo Kk | Poisson noise removal device, poisson noise removal method, and x-ray imaging apparatus |
CN108230376A (en) * | 2016-12-30 | 2018-06-29 | 北京市商汤科技开发有限公司 | Remote sensing image processing method, device and electronic equipment |
CN112634169A (en) * | 2020-12-30 | 2021-04-09 | 成都星时代宇航科技有限公司 | Color homogenizing method and device for remote sensing image |
-
2021
- 2021-09-06 CN CN202111041316.1A patent/CN113850734A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2013244189A (en) * | 2012-05-25 | 2013-12-09 | Asahi Roentgen Kogyo Kk | Poisson noise removal device, poisson noise removal method, and x-ray imaging apparatus |
CN108230376A (en) * | 2016-12-30 | 2018-06-29 | 北京市商汤科技开发有限公司 | Remote sensing image processing method, device and electronic equipment |
CN112634169A (en) * | 2020-12-30 | 2021-04-09 | 成都星时代宇航科技有限公司 | Color homogenizing method and device for remote sensing image |
Non-Patent Citations (1)
Title |
---|
丁先华等: "基于泊松插值的正射影像镶嵌线羽化方法", 测绘与空间地理信息, vol. 38, no. 11, 25 November 2015 (2015-11-25) * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118135149A (en) * | 2024-05-10 | 2024-06-04 | 北京数慧时空信息技术有限公司 | Method for generating remote sensing orthographic image embedded line |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111080724A (en) | Infrared and visible light fusion method | |
CN104182949B (en) | Image inking and fusing method and system based on histogram feature point registration | |
CN108269244B (en) | Image defogging system based on deep learning and prior constraint | |
CN102577355B (en) | The method of the defect of predicted picture acquisition system and related system thereof | |
US8340423B1 (en) | Enhancing digital image mosaics using region-statistics | |
CN105528797A (en) | Optical image color consistency self-adaption processing and quick mosaic method | |
CN107680140B (en) | Depth image high-resolution reconstruction method based on Kinect camera | |
CN112307901B (en) | SAR and optical image fusion method and system for landslide detection | |
Xie et al. | Guided color consistency optimization for image mosaicking | |
CN114005042A (en) | Remote sensing image urban building extraction method based on shadow compensation and U-net | |
CN108416784A (en) | Completed region of the city boundary rapid extracting method, device and terminal device | |
CN110110131B (en) | Airplane cable support identification and parameter acquisition method based on deep learning and binocular stereo vision | |
CN106101588A (en) | The compensation method of panoramic picture gradual halation phenomena | |
CN113436071B (en) | Multi-source satellite remote sensing image mosaic method, system and storage medium | |
CN106611410B (en) | Pansharpen based on pyramid model merges optimization method | |
CN114067197A (en) | Pipeline defect identification and positioning method based on target detection and binocular vision | |
CN111340895A (en) | Image color uniformizing method based on pyramid multi-scale fusion | |
CN115330653A (en) | Multi-source image fusion method based on side window filtering | |
CN116152068A (en) | Splicing method for solar panel images | |
CN113850734A (en) | Poisson equation fused remote sensing image automatic color homogenizing method | |
CN108830921A (en) | Laser point cloud reflected intensity correcting method based on incident angle | |
CN108109118B (en) | Aerial image geometric correction method without control points | |
CN114331835A (en) | Panoramic image splicing method and device based on optimal mapping matrix | |
CN100428280C (en) | DMC color composition image radiation re-handling method | |
KR20210096925A (en) | Flexible Color Correction Method for Massive Aerial Orthoimages |
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 |