CN115631119A - Image fusion method for improving target significance - Google Patents
Image fusion method for improving target significance Download PDFInfo
- Publication number
- CN115631119A CN115631119A CN202211094340.6A CN202211094340A CN115631119A CN 115631119 A CN115631119 A CN 115631119A CN 202211094340 A CN202211094340 A CN 202211094340A CN 115631119 A CN115631119 A CN 115631119A
- Authority
- CN
- China
- Prior art keywords
- image
- target
- fusion
- improving
- saliency
- 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
- 238000007500 overflow downdraw method Methods 0.000 title claims abstract description 12
- 230000004927 fusion Effects 0.000 claims abstract description 28
- 238000000034 method Methods 0.000 claims abstract description 11
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 7
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 239000003086 colorant Substances 0.000 claims abstract description 4
- 230000003313 weakening effect Effects 0.000 claims abstract description 4
- 239000011159 matrix material Substances 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002203 pretreatment 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
- 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
- G06T5/90—Dynamic range modification of images or parts thereof
-
- 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
- G06T2207/10048—Infrared 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
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of image fusion systems, in particular to an image fusion method for improving target saliency, which comprises the following steps of 1: processing the whole infrared image through a formula, selecting a parameter less than 1, and weakening background contents except the target; step 2: performing image fusion in a multi-scale mode to obtain a gray level fusion image, performing multi-scale decomposition on the infrared and low-light level images, and adopting different fusion strategies on different layers to highlight details of a target and a background; and step 3: the contrast of the colors of the image is improved, again improving the saliency of the target, by means of an improved method of local color transfer. The method comprises the steps of firstly preprocessing an infrared video image with stronger target characteristics to weaken the image contents except for a target; then, a multi-scale fusion algorithm with enhanced local detail is adopted; and finally, when the fusion image is rendered, a local color transfer method is adopted, so that the layering sense of the whole image color is enhanced, and the target is more highlighted.
Description
Technical Field
The invention relates to the technical field of image fusion systems, in particular to an image fusion method for improving target significance.
Background
Object saliency is a measure of how conspicuous an object is relative to the surrounding background, and generally the stronger the saliency of an object in the observed image of the system, the easier it is to search for and detect, especially under special viewing conditions, such as at night, in rainy, snowy, foggy days, and the like. Since the ultimate user of the image fusion system is the observer, the main algorithms for fusion at present are multi-scale fusion and global color delivery. The processing is focused on the aspects of image integrity, such as transparency, naturalness, contrast and the like, and the target area is not processed in a targeted manner, so that the following conditions occur: 1. the image is overall clear, and the target significance is not strong; 2. the overall image feels natural, and the target significance is reduced; 3. only the target edge is enhanced; 4. the target is enhanced and the overall image is unnatural.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an image fusion method for improving the target significance, which comprises the steps of firstly preprocessing an infrared video image with stronger target characteristics to weaken the image contents except for a target; then, a multi-scale fusion algorithm with enhanced local detail is adopted; and finally, when the fusion image is rendered, a local color transfer method is adopted, so that the layering sense of the whole image color is enhanced, and the target is more highlighted.
The invention is realized by the following technical scheme:
an image fusion method for improving the significance of a target comprises the following steps:
step 1: processing the whole infrared image through a formula, selecting a parameter less than 1, and weakening background contents except the target;
namely the formula is:
wherein the content of the first and second substances,
p (i, j) represents a pixel value with the coordinate (i, j) in the original infrared image;
p' (i, j) represents a pixel value with coordinates (i, j) after infrared image preprocessing;
c is a parameter;
and 2, step: performing image fusion in a multi-scale mode to obtain a gray level fusion image, performing multi-scale decomposition on the infrared and low-light level images, and adopting different fusion strategies on different layers to highlight details of a target and a background;
and 3, step 3: the contrast of the colors of the image is improved, again improving the saliency of the target, by means of an improved method of local color transfer.
Preferably, in the step 1, the parameter c is 0.2.
Preferably, in the step 2, laplacian (laplacian) 3 layer decomposition and fusion are adopted.
Preferably, the step 3 specifically includes the following steps:
step a): calculating the local mean value of the reference image and the target image according to the image data fused in the step 2
Sum variance
Step b): calculating a matching error of a pixel corresponding to the reference image in the target image;
Err(i，j)＝min(Err)；
m 1 、m 2 representing an error coefficient;
step c): determining a value T, performing normal color transfer when Err (i, j) < T, otherwise not performing color transfer, only keeping a pixel brightness value, and taking U and V as unknown chromaticity spaces;
step d): carrying out extended filling on an unknown color space; sequentially calculating the local color space mean value u of a pixel 3 multiplied by 3 neighborhood in the whole image color space after the step c), wherein when the mean value is not 0, the chroma value of the pixel is the neighborhood mean value.
Preferably, in the step c), the value T is half of the mean value of the error matrix.
The invention has the following beneficial effects:
1. the invention can more effectively highlight the characteristic that the background imaging characteristics of the micro-light channel are closer to nature;
2. the method can avoid the interference of imaging data of the infrared channel background on the fusion image;
3. the invention can more highlight the infrared characteristics of the target, and effectively improve the identification degree of the target during long-distance observation;
4. the invention can well keep and even improve the definition and color gradation of the background while improving the target significance.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a schematic flow chart diagram of an embodiment of the present invention.
FIG. 2 is a diagram illustrating the effect of pre-treatment according to an embodiment of the present invention; wherein (a) is an original infrared image; and (b) a target highlight effect image.
FIG. 3 is a graph comparing the effects of embodiments of the present invention with a current process; wherein (a) is a visible light image; (b) is an infrared image; (c) is a linear weighting algorithm image; (d) multi-scale fusion + color transfer images; and (e) obtaining an effect image of the method.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. 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.
Referring to fig. 1, the present invention provides an image fusion method for improving target saliency, including the following steps:
step 1: processing the whole infrared image through a formula, selecting a parameter less than 1, and weakening background contents except the target;
namely the formula is:
wherein the content of the first and second substances,
p (i, j) represents a pixel value with the coordinate (i, j) in the original infrared image;
p' (i, j) represents a pixel value with coordinates (i, j) after infrared image preprocessing;
c is a parameter, and the parameter c is 0.2;
step 2: performing image fusion in a multi-scale mode to obtain a gray level fusion image, performing multi-scale decomposition on the infrared and low-light level images, and adopting different fusion strategies on different layers to highlight details of a target and a background; adopting Laplacian (Lapacian) 3-layer decomposition and fusion;
and step 3: the contrast of the colors of the image is improved, again improving the saliency of the target, by means of an improved method of local color transfer.
In this embodiment, the step 3 specifically includes the following steps:
step a): calculating the local mean value of the reference image and the target image according to the image data fused in the step 2
Sum variance
Step b): calculating the matching error of the pixel corresponding to the reference image in the target image;
Err(i，j)＝min(Err)；
m 1 、m 2 representing an error coefficient;
step c): determining a T value which is half of the mean value of the error matrix; when Err (i, j) < T, carrying out normal color transfer, otherwise, not carrying out color transfer, only keeping the brightness value of the pixel, and U and V are unknown chromaticity spaces;
step d): carrying out expansion filling on an unknown color space; sequentially calculating the local color space mean value u of a pixel 3 multiplied by 3 neighborhood in the whole image color space after the step c), and when the mean value is not 0, the chroma value of the pixel is the neighborhood mean value.
In summary, the invention first preprocesses the infrared video image with strong target characteristics to weaken the image contents except the target; then, a multi-scale fusion algorithm with local detail enhancement is adopted; and finally, when the fusion image is rendered, a local color transfer method is adopted, so that the layering sense of the whole image color is enhanced, and the target is more highlighted.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (5)
1. An image fusion method for improving the significance of a target is characterized by comprising the following steps:
step 1: processing the whole infrared image through a formula, selecting a parameter less than 1, and weakening background contents except the target;
namely the formula is:
wherein the content of the first and second substances,
p (i, j) represents a pixel value with the coordinate (i, j) in the original infrared image;
p' (i, j) represents a pixel value with coordinates (i, j) after infrared image preprocessing;
c is a parameter;
step 2: performing image fusion in a multi-scale mode to obtain a gray level fusion image, performing multi-scale decomposition on the infrared and low-light level images, and adopting different fusion strategies on different layers to highlight details of a target and a background;
and 3, step 3: the contrast of the colors of the image is improved, again improving the saliency of the target, by means of an improved method of local color transfer.
2. The image fusion method for improving the saliency of the target according to claim 1, characterized in that in step 1, the parameter c is 0.2.
3. The image fusion method for improving the saliency of the target of claim 2, characterized in that in said step 2, laplace 3 layer decomposition and fusion is used.
4. The image fusion method for improving the saliency of an object according to claim 3, characterized in that said step 3 specifically includes the following steps:
step a): calculating the local mean value of the reference image and the target image according to the image data fused in the step 2
Sum variance
Step b): calculating the matching error of the pixel corresponding to the reference image in the target image;
Err(i，j)＝min(Err)；
m 1 、m 2 representing an error coefficient;
step c): determining a value T, and when Err (i, j) < T, carrying out normal color transfer, otherwise, not carrying out color transfer, only keeping the brightness value of a pixel, wherein U and V are unknown chromaticity spaces;
step d): carrying out extended filling on an unknown color space; sequentially calculating the local color space mean value u of a pixel 3 multiplied by 3 neighborhood in the whole image color space after the step c), and when the mean value is not 0, the chroma value of the pixel is the neighborhood mean value.
5. The image fusion method for improving the saliency of the target according to claim 4, wherein in said step c), the value of T is half of the mean value of the error matrix.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211094340.6A CN115631119A (en) | 2022-09-08 | 2022-09-08 | Image fusion method for improving target significance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211094340.6A CN115631119A (en) | 2022-09-08 | 2022-09-08 | Image fusion method for improving target significance |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115631119A true CN115631119A (en) | 2023-01-20 |
Family
ID=84902520
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211094340.6A Pending CN115631119A (en) | 2022-09-08 | 2022-09-08 | Image fusion method for improving target significance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115631119A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118154443A (en) * | 2024-05-09 | 2024-06-07 | 江苏北方湖光光电有限公司 | Method for improving fusion sight distance of fusion night vision device in real time |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106780470A (en) * | 2016-12-23 | 2017-05-31 | 浙江大学 | CT image nipple automated detection methods |
| CN107705268A (en) * | 2017-10-20 | 2018-02-16 | 天津工业大学 | One kind is based on improved Retinex and the enhancing of Welsh near-infrared images and colorization algorithm |
| CN108389158A (en) * | 2018-02-12 | 2018-08-10 | 河北大学 | A kind of infrared and visible light image interfusion method |
| CN110751660A (en) * | 2019-10-18 | 2020-02-04 | 南京林业大学 | Color image segmentation method |
| CN111723670A (en) * | 2020-05-21 | 2020-09-29 | 河海大学 | Remote sensing target detection algorithm based on improved FastMBD |
| CN113935984A (en) * | 2021-11-01 | 2022-01-14 | 中国电子科技集团公司第三十八研究所 | Multi-feature fusion method and system for detecting infrared dim small target in complex background |
| CN113962900A (en) * | 2021-11-15 | 2022-01-21 | 北京环境特性研究所 | Method, device, equipment and medium for detecting infrared dim target under complex background |
| CN114612359A (en) * | 2022-03-09 | 2022-06-10 | 南京理工大学 | Visible light and infrared image fusion method based on feature extraction |
-
2022
- 2022-09-08 CN CN202211094340.6A patent/CN115631119A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106780470A (en) * | 2016-12-23 | 2017-05-31 | 浙江大学 | CT image nipple automated detection methods |
| CN107705268A (en) * | 2017-10-20 | 2018-02-16 | 天津工业大学 | One kind is based on improved Retinex and the enhancing of Welsh near-infrared images and colorization algorithm |
| CN108389158A (en) * | 2018-02-12 | 2018-08-10 | 河北大学 | A kind of infrared and visible light image interfusion method |
| CN110751660A (en) * | 2019-10-18 | 2020-02-04 | 南京林业大学 | Color image segmentation method |
| CN111723670A (en) * | 2020-05-21 | 2020-09-29 | 河海大学 | Remote sensing target detection algorithm based on improved FastMBD |
| CN113935984A (en) * | 2021-11-01 | 2022-01-14 | 中国电子科技集团公司第三十八研究所 | Multi-feature fusion method and system for detecting infrared dim small target in complex background |
| CN113962900A (en) * | 2021-11-15 | 2022-01-21 | 北京环境特性研究所 | Method, device, equipment and medium for detecting infrared dim target under complex background |
| CN114612359A (en) * | 2022-03-09 | 2022-06-10 | 南京理工大学 | Visible light and infrared image fusion method based on feature extraction |
Non-Patent Citations (5)
| Title |
|---|
| 何永强 等: "基于融合和色彩传递的灰度图像彩色化技术", 《红外技术》, vol. 34, no. 5, 31 May 2012 (2012-05-31), pages 276 - 279 * |
| 张骢 等: "红外成像探测技术与应用", 31 August 2022, 北京理工大学出版社, pages: 42 - 44 * |
| 朱黎博;孙韶媛;王冬;: "基于图像分割和色彩扩展的灰度图像彩色化方法", 微型电脑应用, no. 05, 20 May 2009 (2009-05-20) * |
| 朱黎博;孙韶媛;谷小婧;夏如镜;叶茂锹;: "基于色彩传递与扩展的图像着色算法", 中国图象图形学报, no. 02, 15 February 2010 (2010-02-15) * |
| 谯涵丹 等: "红外与微光融合图像的 多尺度色彩传递算法", 《红外技术》, vol. 38, no. 2, 28 February 2016 (2016-02-28), pages 157 - 162 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118154443A (en) * | 2024-05-09 | 2024-06-07 | 江苏北方湖光光电有限公司 | Method for improving fusion sight distance of fusion night vision device in real time |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Singh et al. | A comprehensive review of computational dehazing techniques | |
| CN108596849B (en) | Single image defogging method based on sky region segmentation | |
| Li et al. | Nighttime haze removal with glow and multiple light colors | |
| CN111968054B (en) | Underwater image color enhancement method based on potential low-rank representation and image fusion | |
| CN109064426B (en) | Method and device for suppressing glare in low-illumination image and enhancing image | |
| Gao et al. | Sand-dust image restoration based on reversing the blue channel prior | |
| Li et al. | A multi-scale fusion scheme based on haze-relevant features for single image dehazing | |
| Park et al. | Single image haze removal with WLS-based edge-preserving smoothing filter | |
| Yang et al. | Coarse-to-fine luminance estimation for low-light image enhancement in maritime video surveillance | |
| CN112837233A (en) | Polarization image defogging method for acquiring transmissivity based on differential polarization | |
| CN112700363B (en) | Self-adaptive visual watermark embedding method and device based on region selection | |
| Mi et al. | Multi-purpose oriented real-world underwater image enhancement | |
| CN111598814B (en) | Single image defogging method based on extreme scattering channel | |
| WO2019128459A1 (en) | Method and device for image shadow elimination | |
| CN112465708A (en) | Improved image defogging method based on dark channel | |
| CN110866889A (en) | Multi-camera data fusion method in monitoring system | |
| CN115631119A (en) | Image fusion method for improving target significance | |
| CN109410160B (en) | Infrared polarization image fusion method based on multi-feature and feature difference driving | |
| Wei et al. | An image fusion dehazing algorithm based on dark channel prior and retinex | |
| CN111311503A (en) | Night low-brightness image enhancement system | |
| CN108898561B (en) | Defogging method, server and system for foggy image containing sky area | |
| CN112184608B (en) | Infrared and visible light image fusion method based on feature transfer | |
| CN107301625B (en) | Image defogging method based on brightness fusion network | |
| Lai et al. | Single image dehazing with optimal transmission map | |
| Hong et al. | Single image dehazing based on pixel-wise transmission estimation with estimated radiance patches |
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 |