A remote sensing image fusion method, system and storage medium based on vegetation cover

By calculating the characteristic ratio index of remote sensing true color images and constructing the vegetation cover function, the problem of unnatural color in the vegetation area of ​​remote sensing true color images is solved, and the vegetation characteristics enhancement in the red and green bands is achieved, which significantly improves the sense of hierarchy of the images and computer resolution.

CN118334531BActive Publication Date: 2024-11-01PEARL RIVER HYDRAULIC RES INST OF PEARL RIVER WATER RESOURCES COMMISSION
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410496394.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-04-24
Publication Date
2024-11-01
Estimated Expiration
2044-04-24

AI Technical Summary

Technical Problem

The existing remote sensing true color images have unnatural and unreal colors in vegetation areas, making it difficult to effectively enhance vegetation characteristics, limiting their application results.

Method used

By calculating the characteristic ratio index of remote sensing true color images, vegetation cover and normalized cover functions are constructed, vegetation characteristic thresholds are determined, vegetation characteristic enhancement step function and incremental coefficient function are designed, and vegetation characteristics are realized for red and green bands. Enhanced, synthesize enhanced true color images.

Benefits of technology

It significantly improves the hierarchy and clarity of vegetation characteristics of satellite remote sensing images, improves the visual resolution and computer resolution of true color images, and enhances the separability and analysis capabilities of vegetation information.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118334531B_ABST
    Figure CN118334531B_ABST
Patent Text Reader

Abstract

The present invention provides a remote sensing image fusion method, system and storage medium based on vegetation coverage. In the remote sensing true color image vegetation feature enhancement, by constructing the vegetation coverage, normalized vegetation coverage and sum function and product function space of the remote sensing image, the direct correspondence between the remote sensing image vegetation coverage and the vegetation features is utilized, and the satellite remote sensing image vegetation feature enhancement amount is designed accordingly to achieve directional enhancement of the image vegetation information features. According to the principle of superposition enhancement, the red and green bands of the remote sensing true color image are enhanced based on the above-mentioned function space, and the enhanced remote sensing true color image is synthesized together with the original blue band. The present invention gives full play to the advantage of the direct correlation between vegetation coverage and image vegetation features, greatly improves the vegetation feature layering and clarity of satellite remote sensing images, and improves the visual resolution and computer resolution of remote sensing true color images.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of remote sensing image feature enhancement, and more specifically, to a remote sensing image fusion method, system and storage medium based on vegetation coverage. Background Art

[0002] With the development of multi-platform, multi-sensor, multi-weather, multi-temporal, and multi-resolution remote sensing technology, images with different spatial resolutions, temporal resolutions, and spectral resolutions are becoming increasingly abundant. In the past two decades, remote sensing image spatiotemporal fusion has become a new direction in remote sensing image processing, and various fusion technologies have developed rapidly, achieving a series of new results. However, there are few studies on the fusion of multispectral images, which are mainly concentrated in true color image simulation or vegetation enhancement processing.

[0003] There are currently several ways to evaluate the effect of adding vegetation to true color images:

[0004] (1) Visual evaluation: As is known to all, although the original remote sensing true color images are consistent with the ground objects in the water bodies, exposed land and other landforms, the colors are dim and the layers are unclear in the vegetation areas. Generally, true color images need to be enhanced to obtain true color images that are consistent with the ground colors in the above-mentioned landforms. That is, vegetation is based on green, and vegetation of different types and coverage presents various shades of green; water bodies are based on blue, except for the green, yellow, black, etc. due to different components such as vegetation coverage on the water surface, high concentration of sand, and high pollution, the main body is various shades of blue; other exposed land such as rocks, exposed soil, roads, and residential areas are consistent with the rich colors of the ground, presenting gray, black, white, red, orange, yellow, green, cyan, blue, purple and other colors. By visually selecting typical land features such as water areas, exposed land, and vegetation, and qualitatively comparing the color changes between the original true color image and the enhanced true color image, the effect of vegetation enhancement in the true color image can be visually evaluated.

[0005] (2) Quantitative evaluation: Quantitative evaluation is, to a certain extent, the quantification of visual evaluation indicators. For the enhancement of vegetation features in true color images, it is necessary to improve the color of vegetation in true color images and to ensure the richness and clarity of the layers, details, etc. of the enhanced true color images. In general, the reconstructed images can be quantitatively evaluated from two aspects:

[0006] The first is the quantitative description and comparison of the vegetation color enhancement effect. Among the models that describe color space, such as RGB, CMYK, IHS, and CIE Lab, it is generally believed that the RGB three-primary color model is suitable for computer screen displays, and the CMYK and other printing models are suitable for color image printouts, while the color description of the IHS, CIE Lab and other color space models conforms to the human eye visual perception mode. Based on this understanding, the method generally used to quantitatively evaluate the effect of true color images is: convert the remote sensing image described in the RGB three-primary color space into an image described in the IHS or CIE Lab color space, read the chromaticity, saturation, intensity, etc. of the vegetation objects in these color spaces before and after enhancement, and analyze their changing trends and characteristics.

[0007] Second, the quality index statistics and comparison of enhanced true color images. Generally speaking, the quality of image processing can be evaluated from three aspects: first, the information richness of the overall image and vegetation area after enhancement can be measured by entropy and joint entropy; second, the color richness and brightness of the overall image and vegetation area after enhancement can be measured by band statistical characteristics - maximum value, minimum value, mean, variance and correlation indexes between bands - correlation coefficient, covariance, etc.; third, the level (edge), details (texture) and clarity of the overall image and vegetation area after enhancement can be measured by gradient, average gradient, etc. By comparing the differences in various indicators of the overall image and vegetation area before and after enhancement, the change direction of spectral (grayscale, hue) information, edge (level, difference) information, and texture (detail) information can be analyzed.

[0008] With the popularization of remote sensing applications in all walks of life, visible light multispectral satellite remote sensing true color images have the excellent characteristic of what you see is what you get, and have become one of the most widely used remote sensing image types. However, there are inherent defects such as unnatural and unrealistic vegetation colors, which restricts its application effectiveness. How to effectively enhance the vegetation characteristics of visible light satellite remote sensing true color images is the focus and difficulty of visible light satellite remote sensing true color image processing. Relevant researchers have made fruitful explorations for this purpose, laying a theoretical and technical foundation for further solving related problems.

[0009] Based on the primary products of satellite remote sensing, Chen Chun et al. corrected the remote sensing data for Rayleigh scattering, making the color signal image close to the ground true color image (Chen Chun et al., Extraction and Reproduction of Color Signals of Remote Sensing Sources, Surveying and Mapping Science, January 2006, Vol. 31, No. 1; Han Xiuzhen et al., Research and Application of Fengyun-3D True Color Image Synthesis Method, Journal of Marine Meteorology, May 2019, Vol. 39, No. 2). You Jing et al. used the white balance method and color correction based on colorimetry to improve the vegetation characteristics of true color images and obtained more realistic true color images (You Jing et al., A White Balance Method for Processing Color Multispectral Images, Journal of Atmospheric and Environmental Optics, July 2012, Vol. 7, No. 4; Huang Honglian et al., True Color Synthesis of Multispectral Remote Sensing Images Based on Artificial Targets, November 2016, Vol. 45, No. 11).

[0010] Based on the secondary processed products of remote sensing images, Fan Xuyan and others obtained relatively good true color images through green band enhancement processing. In the early days, the overall weighted combination operation scheme of green band and near infrared band was mainly used to obtain new green bands (Fan Xuyan et al., Remote Sensing Image Simulation True Color Fusion Method Based on Principal Component Analysis, Journal of Surveying and Mapping Science and Technology, August 2006, Vol. 23, No. 4; Wang Haiyan et al., Discussion on ALOS Natural Color Image Transformation and Fusion Method, Surveying and Mapping Technology and Equipment, Vol. 14, No. 1, 2012; Shi Yuanli et al., Analysis on the Suitability of GF-2 Satellite Remote Sensing Image Mapping, Bulletin of Surveying and Mapping, No. 12, 2017); Later, it gradually developed into The normalized vegetation index is used as the classification function to classify and weight the vegetation pixels in the image to obtain a new green band (Zhang Wei et al., True color synthesis method of multispectral images based on vegetation index, Surveying and Spatial Geographic Information, Vol. 33, No. 6, December 2010); the recent development is to use the normalized vegetation index segmentation to perform Contourlet fusion on the green band and the near-infrared band to obtain a new green band image (Ding Huimei, Research on improving the color naturalness of multispectral remote sensing images using near-infrared, Master's thesis, 2016). Summary of the invention

[0011] In view of the above problems, the object of the present invention is to provide a remote sensing image fusion method, system and storage medium based on vegetation cover.

[0012] A first aspect of the present invention provides a remote sensing image fusion method based on vegetation coverage, the method comprising:

[0013] Input remote sensing true color images with near infrared band, red band, green band and blue band;

[0014] Calculate the characteristic ratio index of remote sensing true color images;

[0015] According to the characteristic ratio index of remote sensing true color images, the vegetation coverage and coverage power function, the vegetation normalized coverage and normalized coverage power function are constructed;

[0016] Determine vegetation feature thresholds;

[0017] A vegetation feature enhancement step function is constructed according to the vegetation feature threshold;

[0018] Constructing the incremental coefficient function for vegetation feature enhancement;

[0019] According to the vegetation feature enhancement step function and the vegetation feature enhancement increment coefficient function, a vegetation feature enhancement coefficient function is constructed;

[0020] The remote sensing image fusion and enhancement are performed on the vegetation features of the red and green bands of the remote sensing true color image; and the true color image after vegetation enhancement is synthesized.

[0021] Preferably, the calculating of the characteristic ratio index of the remote sensing image specifically includes:

[0022] Assume b i is a band of remote sensing true color image, the remote sensing true color image bands involved in the fusion are near infrared band and m true color bands; the number of bands of the fused image result is m, and the fused result is recorded as b' i ;

[0023] (1) For quasi-Brovey fusion, the fusion result is recorded as:

[0024]

[0025] Where m = 1, 2, 3, i = 1, ..., m, b i , b j is the true color band involved in fusion;

[0026] (2) For Schmidt-Gram, PCA fusion or Wavelet fusion, the fusion result is recorded as:

[0027] b′ i =Fusion(NIR,b1,…,b m )

[0028] where m = 1, 2, 3, i = 1, ..., m, b1, ..., b m It is the true color band involved in fusion; Fusion is a fusion method such as GS (Gram-Schmidt) or WL (Wavelet).

[0029] The characteristic ratio index is:

[0030]

[0031] Where n=1,…,m.

[0032] Preferably, the steps of constructing vegetation coverage and coverage power function, and constructing vegetation normalized coverage and normalized coverage power function are specifically as follows:

[0033] The vegetation coverage is constructed using the characteristic ratio index x, and the formula is:

[0034]

[0035] In the formula, x is the characteristic ratio index, x min is the minimum value of the characteristic index, x max is the maximum value of the characteristic index;

[0036] The vegetation coverage is constructed by the normalized index of the characteristic ratio index x, and the formula is:

[0037]

[0038] in,

[0039]

[0040] Where NDxI is the normalized index of the characteristic ratio index, NDxI min is the minimum value of the normalized index, NDxI max is the maximum value of the normalized index;

[0041] Construct the power function h(x) of vegetation cover:

[0042]

[0043] The power function t(x) of constructing normalized index vegetation cover is:

[0044]

[0045] In the formula, n>0, h(x) and t(x) have the same monotonically increasing property and the same characteristic points (0,0) and (1,1) as x. h(x) and t(x) can be used as basic parameters for vegetation feature enhancement.

[0046] Preferably, the vegetation feature threshold c∈[x w , x v ], by default c=x m ;

[0047] Among them, x w The threshold value of the characteristic ratio index is x, and the threshold value of the characteristic ratio index of pure vegetation is x v , c is the vegetation feature threshold, x mis the average value of the characteristic ratio index x.

[0048] Preferably, the vegetation feature enhancement step function is:

[0049]

[0050] Preferably, the expression of the vegetation feature increment coefficient function is:

[0051]

[0052] k is the greenness adjustment coefficient, k>0, and k=1 by default; g(x) is the composite function of the smooth constraint basis function, g(x max ) is the maximum value of the smooth constrained composite function.

[0053] The specific construction method of the vegetation characteristic increment coefficient function is as follows:

[0054] Construct the smooth constrained basis function u(h(x)) of vegetation cover and the smooth constrained basis function u(t(x)) of normalized exponential vegetation cover:

[0055]

[0056]

[0057] u(h(x)) is the smooth constrained basis function of vegetation cover; u(t(x)) is the smooth constrained basis function of normalized exponential vegetation cover.

[0058] A series of incremental coefficient functions f(x) are constructed based on two types of smooth constraint basis functions, and their typical forms include but are not limited to the following:

[0059] (1) Smooth constraint function based on vegetation coverage:

[0060]

[0061] (2) Smooth constraint function based on normalized index vegetation cover:

[0062]

[0063] (3) Smooth constraint function based on the product of vegetation coverage and normalized index vegetation coverage:

[0064]

[0065] (4) Smooth constraint function based on the linear combination of vegetation cover and normalized index vegetation cover:

[0066]

[0067] Where k1 and k2 are weight coefficients, k1∈[0,1], k2=1-k1.

[0068] Preferably, the expression of the vegetation feature enhancement coefficient function is:

[0069] F(x)=δ(x)f(x)+1.

[0070] Preferably, the vegetation feature enhancement scheme for the red and green bands of the remote sensing true color image is as follows:

[0071] R′=[δ(x)f(x)+1]×R

[0072] G′=[δ(x)f(x)+1]×G

[0073] Among them, R' is the enhanced green band, R is the green band, G' is the enhanced red band, and G is the red band.

[0074] A second aspect of the present invention provides a remote sensing image fusion system based on vegetation coverage, comprising a memory and a processor, wherein the memory comprises a remote sensing image fusion method program based on vegetation coverage, and when the remote sensing image fusion method program based on vegetation coverage is executed by the processor, the steps of a remote sensing image fusion method based on vegetation coverage are implemented.

[0075] The third aspect of the present invention provides a computer-readable storage medium, which includes a remote sensing image fusion method program based on vegetation coverage. When the remote sensing image fusion method program based on vegetation coverage is executed by a processor, the steps of a remote sensing image fusion method based on vegetation coverage are implemented.

[0076] Compared with the prior art, the technical solution of the present invention has the following beneficial effects:

[0077] The present invention provides a remote sensing image fusion method, system and storage medium based on vegetation coverage. In the remote sensing true color image vegetation feature enhancement, by constructing the vegetation coverage of the remote sensing image, the normalized vegetation coverage and the sum function and product function space thereof, the direct correspondence between the vegetation coverage of the remote sensing image and the vegetation features is utilized, and accordingly, the satellite remote sensing image vegetation feature enhancement amount is designed to achieve directional enhancement of the image vegetation information features. According to the principle of superposition enhancement, the red and green bands of the remote sensing true color image are enhanced based on the above-mentioned function space, and the enhanced true color image is synthesized together with the original blue band. The present invention directly utilizes the vegetation coverage of the satellite remote sensing image to directional enhance the vegetation features of the true color image, giving full play to the advantage of the direct correlation between the vegetation coverage and the image vegetation features, greatly improving the layering and clarity of the vegetation features of the satellite remote sensing image, and improving the visual resolution and computer resolution of the true color image. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] Figure 1 This is a flow chart of a remote sensing image fusion method based on vegetation coverage described in Example 1.

[0079] Figure 2 This is a true color composite color image before vegetation feature enhancement.

[0080] Figure 3 It is a true color composite color image vegetation cover map.

[0081] Figure 4 The enhanced true color image is synthesized by combining the enhanced red band, green band and the original blue band according to the red, green and blue channels.

[0082] Figure 5 The enhanced true color image is synthesized by combining the enhanced red band, green band and the original blue band according to the red, green and blue channels.

[0083] Figure 6 The enhanced true color image is synthesized by combining the enhanced red band, green band and the original blue band according to the red, green and blue channels.

[0084] Figure 7 The enhanced true color image is synthesized by combining the enhanced red band, green band and the original blue band according to the red, green and blue channels. DETAILED DESCRIPTION

[0085] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0086] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0087] Example 1

[0088] like Figure 1 As shown, this embodiment discloses a remote sensing image fusion method based on vegetation coverage, the method comprising:

[0089] S1: Input remote sensing true color image with near infrared band, red band, green band and blue band.

[0090] S2: Calculate the characteristic ratio index of remote sensing true color images.

[0091] Assume b i is a band of remote sensing true color image, the remote sensing true color image bands involved in the fusion are near infrared band and m true color bands; the number of bands of the fused image result is m, and the fused result is recorded as b' i ;

[0092] (1) For quasi-Brovey fusion, the fusion result is recorded as:

[0093]

[0094] Where m = 1, 2, 3, i = 1, ..., m, b i , b j is the true color band involved in fusion;

[0095] (2) For Schmidt-Gram, PCA fusion or Wavelet fusion, the fusion result is recorded as:

[0096] b′ i =Fusion(NIR,b1,…,b m )

[0097] where m = 1, 2, 3, i = 1, ..., m, b1, ..., b m It is the true color band involved in fusion; Fusion is a fusion method such as GS (Gram-Schmidt) or WL (Wavelet).

[0098] The characteristic ratio index of remote sensing true color image is:

[0099]

[0100] Where n=1,…,m.

[0101] S3: Based on the characteristic ratio index of remote sensing true color images, construct vegetation cover and cover power function, construct vegetation normalized cover and normalized cover power function.

[0102] The vegetation coverage is constructed directly using the characteristic ratio index x, and the formula is:

[0103]

[0104] In the formula, x is the characteristic ratio index, x min is the minimum value of the characteristic index, x max is the maximum value of the characteristic index;

[0105] The vegetation coverage is constructed by the normalized index of the characteristic ratio index x, and the formula is:

[0106]

[0107] Among them,

[0108]

[0109] In the formula, NDxI is the normalized index of the characteristic ratio index, and NDxI min is the minimum value of the normalized index, and NDxI max is the maximum value of the normalized index;

[0110] Construct the power function h(x) of vegetation coverage:

[0111]

[0112] Construct the power function t(x) of the normalized index vegetation coverage as:

[0113]

[0114] In the formula, n>0, and h(x) and t(x) have the same monotonically increasing property as x and the same characteristic points (0,0) and (1,1). h(x) and t(x) can be used as the basic parameters for vegetation feature enhancement.

[0115] It should be noted that in this embodiment, the vegetation coverage is used to enhance the vegetation features of true-color images, effectively improving the vegetation feature enhancement ability and effect. The vegetation coverage constructed in this embodiment has the advantage of being directly corresponding to the vegetation feature information of remote sensing images, with excellent characteristics, and the value of the vegetation coverage is between 0 and 1, the value threshold range is clear, and the vegetation information enhancement effect is highly predictable. Using the vegetation coverage to construct a series of feature enhancement functions and their combinations effectively expands the function space of feature enhancement, and the remote sensing image enhancement effect is excellent. Especially for images with unclear vegetation features and unremarkable vegetation differences in winter, the vegetation feature enhancement effect is more direct and significant.

[0116] It should be noted that the power of the vegetation coverage and the chromaticity adjustment coefficient in this embodiment have the function of jointly adjusting the vegetation chromaticity and hierarchy, with clear processing objectives and controllable effects.

[0117] For the power n of the vegetation coverage in this embodiment, when 0 < n < 1, the smaller the n value, the better the enhancement effect on weak vegetation information. When n > 1, the larger the n value, the better the enhancement effect on high-coverage vegetation; when the greenness adjustment coefficient k changes from small to large, the vegetation hue of the enhanced image changes from dark green to yellow-green. There is a good correspondence between the changes in the magnitudes of the two adjustment coefficients and the direction of vegetation color change.

[0118] S4: Determine the vegetation feature threshold.

[0119] From the perspective of classification enhancement only, the vegetation feature threshold can be the minimum feature ratio index x min and the maximum value x max Any value between . Assume that the threshold of the characteristic ratio index of pure vegetation is x v , the average value of the characteristic ratio index is x m , the threshold value x of pure bare ground b , the threshold value of pure water is x w . Take x w or x b As a feature threshold, the vegetation features of all pixels in the image can be enhanced while maintaining the features of pure water bodies and pure exposed objects on land. Generally speaking, the value range of the vegetation feature threshold is:

[0120] c∈[x w ,x v ]

[0121] Generally take x m It is the default value, and other values ​​can be taken according to the actual characteristics of the image or user enhancement needs.

[0122] If there is no vegetation in the remote sensing image, but only exposed objects such as water bodies, deserts, soil, rocks, buildings, etc., such true color images do not actually need to be enhanced, and the value of feature thresholds is not involved.

[0123] S5: constructing vegetation feature enhancement step function according to vegetation feature threshold;

[0124] Generally, if h(x) or t(x) is a continuous function, b'=h(x)×b, b'=t(x)×b, c is the vegetation feature threshold, and the value of image b' is taken where x>c, and the value of b is taken where x≤c, a new fused image B can be obtained. Suppose x has a step function when the vegetation feature threshold is c:

[0125]

[0126] According to the above permutation and fusion operation rules, we have:

[0127] B={δ(x)×f(x)+1}×b

[0128] Obviously, the step function δ(x) is discontinuous at the threshold c. To make the image B maintain a smooth transition, f(x) must be a continuous function. That is, f(c)=0.

[0129] S6: Construct the incremental coefficient function for vegetation feature enhancement.

[0130] Based on the vegetation cover power function h(x) or t(x), the image vegetation features greater than the threshold c are enhanced. According to the principle of superposition and fusion, it can be written as a general expression:

[0131] b′=[δ(x)×f(x)+1]×b

[0132] Since the step function δ(x) is a discontinuous function at the threshold c, it is easy to cause the fused image to have jagged and speckled noise, making the color transition between the objects on the image uneven and not smooth. The necessary and sufficient condition for the enhanced image b' to remain smooth is that δ(x)f(h(x)) or δ(x)f(t(x)) is a continuous function. That is:

[0133]

[0134] The above condition is equivalent to:

[0135]

[0136] f(h(x)) or f(t(x)) that satisfies the above constraints is called a smooth constraint function with h(x) or t(x) as a parameter.

[0137] Obviously, there are infinitely many such functions, two of which are concise smooth constraint functions:

[0138]

[0139]

[0140] u(h(x)) is the smooth constrained basis function of vegetation cover; u(t(x)) is the smooth constrained basis function of normalized exponential vegetation cover.

[0141] Let n, n1, n2>0, c1∈[0,c], then:

[0142] h(x)∈[0,1], t(x)∈[0,1],

[0143] h(x max )=1,t(x max )=1

[0144]

[0145]

[0146]

[0147]

[0148] A series of incremental coefficient functions can be constructed based on two types of smooth constraint basis functions. Several typical incremental coefficient functions f(x) are as follows:

[0149] (1) Smooth constraint function based on vegetation coverage:

[0150]

[0151] (2) Smooth constraint function based on normalized index vegetation cover:

[0152]

[0153] (3) Smooth constraint function based on the product of vegetation coverage and normalized index vegetation coverage:

[0154] When the smooth constraint function is constructed by multiplying vegetation coverage with normalized index vegetation coverage, only one of the indexes needs to satisfy the smooth constraint condition, that is:

[0155]

[0156] (4) Smooth constraint function based on the linear combination of vegetation cover and normalized index vegetation cover:

[0157] When the linear organization of vegetation coverage and normalized index vegetation coverage is used to construct a smooth constraint function, the smooth constraint functions of vegetation coverage index and normalized index vegetation coverage are required to be 0, that is:

[0158]

[0159] Where k1 and k2 are weight coefficients, k1∈[0,1], k2=1-k1.

[0160] The above smooth constraint function can be uniformly expressed as:

[0161]

[0162] where g(x) is a composite function of the smooth constraint basis function, g(x max ) is the maximum value of the smooth constraint composite function. k is a constant coefficient that has the function of adjusting the greenness of vegetation, and is called the greenness adjustment coefficient. When k changes from small to large, the greenness of vegetation changes from the blue-gray to cyan to yellow-green of the original true color image. The default value is k = 1.

[0163] It should be noted that the present embodiment sets a smooth constraint function for feature classification enhancement to avoid the situation where noise is generated during the processing of remote sensing images. The smooth constraint function for feature classification enhancement described in the present embodiment is flexibly constructed with the increment coefficient at the threshold being 0 as a constraint condition, ensuring that the enhanced image is smoothed over at the threshold, effectively avoiding the noise phenomenon that often occurs in classification enhancement with non-zero constraints.

[0164] S7: According to the vegetation feature enhancement step function and the vegetation feature enhancement incremental coefficient function, a vegetation feature enhancement coefficient function and a fusion expression are constructed.

[0165] Assuming that the red, green, and blue bands of the remote sensing true color image are R, G, and B respectively, according to the principle of superposition fusion, the vegetation feature enhancement coefficient can be obtained from the step function and the incremental coefficient function as follows:

[0166] F(x)=δ(x)f(x)+1

[0167] S8: Perform remote sensing image fusion enhancement on the vegetation features of the red and green bands of the remote sensing true color image; synthesize the true color image after vegetation enhancement.

[0168] The red and green bands are enhanced using the vegetation feature enhancement coefficient function, and the image fusion expression for vegetation feature enhancement is as follows:

[0169] R′=[δ(x)f(x)+1]×R

[0170] G′=[δ(x)f(x)+1]×G

[0171] According to the image fusion expression for vegetation feature enhancement, the remote sensing image fusion enhancement is performed on the vegetation features of the red and green bands of the remote sensing true color image; and the true color image after vegetation enhancement is synthesized.

[0172] As a specific embodiment, the present application is described below with reference to a specific example:

[0173] In order to achieve the purpose of enhancing the vegetation features of satellite remote sensing true color images, this embodiment mainly uses ENVI remote sensing image processing software to achieve it, and is further described by a remote sensing image with a near infrared band (NIR), a red light band (R), a green light band (G), and a blue light band (B).

[0174] 1. Input remote sensing image.

[0175] Open a multispectral remote sensing image with near infrared band (NIR), red band (R), green band (G), and blue band (B). Figure 2 This is a true color composite color image before vegetation feature enhancement (the effect of 2% stretching according to the default setting of envi, the same below).

[0176] 2. Calculate the characteristic ratio index

[0177] The characteristic ratio index is calculated using the image obtained by GS fusion. The calculation results are as follows: Figure 3 shown.

[0178] Use ENVI statistical tools to find the average value x of the characteristic ratio index x m =1.047966, minimum value x min =0.590689, maximum value x max =3.025816.

[0179] 3. Determine feature threshold and translation transformation index

[0180] Determine the vegetation feature threshold c, that is, c = x m =1.047966.

[0181] Let n, n1, n2>0, c1∈[0,c], then: h(x)∈[0,1], t(x)∈[0,1], h(x max )=1,t(x max )=1

[0182]

[0183]

[0184]

[0185]

[0186] 4. Enhanced calculation of vegetation features in red and green bands and true color synthesis.

[0187] (1) Enhanced scheme 1: smooth constraint function based on vegetation cover.

[0188] Take n = 0.5, k = 1, and we get:

[0189]

[0190] R′=[δ(x)f(x)+1]×R

[0191] G′=[δ(x)f(x)+1]×G

[0192] According to the above formula, input the calculation expression: uint(((b1 gt1.047966)*1*(((b1-0.590689) / (2.435127))^0.5-(0.187784)^0.5) / (1-(0.187784)^0.5)+1)*b2+0.5), where b1 is the characteristic ratio index x, and b2 is the red band or green band of the true color image. The enhanced red band, green band and original blue band are combined into a color image according to the red, green and blue channels to form an enhanced true color image. Figure 4 As shown in the figure, the reconstructed image file is stored.

[0193] The comparative analysis tables of the statistical features of the color image after vegetation feature enhancement in this embodiment and the full image and enhanced area in the RGB color mode of the original true color image are shown in Tables 1 and 2.

[0194] Table 1 Comparative analysis of RGB mode statistical features of true color images after vegetation feature enhancement and original true color images

[0195]

[0196] Table 2 Comparative analysis of vegetation regional statistical characteristics of true color images after vegetation feature enhancement and original true color images in RGB mode

[0197]

[0198]

[0199] (2) Enhanced scheme 2: Smooth constraint function based on normalized index vegetation cover.

[0200] Take n = 0.5, k = 1, and we get:

[0201]

[0202] R′=[δ(x)f(x)+1]×R

[0203] G′=[δ(x)f(x)+1]×G

[0204] According to the above formula, enter the calculation expression in ENVI: uint(((b1 gt1.047966)*1*((1.653226*(b1-0.590689) / (b1+1))^0.5-0.369138^0.5) / (1-0.369138^0.5)+1)*b2+0.5), where b1 is the characteristic ratio index and b2 is the red band or green band of the image. The enhanced red band, green band and original blue band are combined into a color image according to the red, green and blue channels to form an enhanced true color image. Figure 5 As shown in the figure, the reconstructed image file is stored.

[0205] The comparative analysis tables of the statistical features of the color image after vegetation feature enhancement in this embodiment and the full image and enhanced area in the RGB color mode of the original true color image are shown in Tables 3 and 4.

[0206] Table 3 Comparative analysis of RGB mode statistical features of true color images after vegetation feature enhancement and original true color images

[0207]

[0208]

[0209] Table 4 Comparative analysis of vegetation regional statistical characteristics between true color images after vegetation feature enhancement and original true color images in RGB mode

[0210]

[0211] (3) Enhanced scheme 3: Smooth constraint function based on the product of vegetation cover and normalized index vegetation cover.

[0212] Take n = 0.5, k = 2, c1 = c, and we get:

[0213]

[0214] R′=[δ(x)f(x)+1]×R

[0215] G′=[δ(x)f(x)+1]×G

[0216] According to the above formula, enter the calculation expression: uint(((b1 gt1.047966)*2*(((b1-0.590689) / (2.435127))^0.5-((1.047966-0.590689) / 2.435127)^0.5) / (1-((1.047966-0.590689) / 2.435127)^0.5)*((1.653226*(b1-0.590689) / (b1+1))^0.5-0.369138^0.5) / (1-0.369138^0.5)+1)*b2+0.5), where b1 is the characteristic ratio index and b2 is the red band or green band of the image. The enhanced red band, green band and original blue band are combined into a color image synthesized according to the red, green and blue channels to obtain an enhanced true color image. Figure 6 As shown in the figure, the reconstructed image file is stored.

[0217] The comparative analysis tables of the statistical features of the color image after vegetation feature enhancement in this embodiment and the full image and enhanced area in the RGB color mode of the original true color image are shown in Tables 5 and 6.

[0218] Table 5 Comparative analysis of RGB mode statistical features of true color images after vegetation feature enhancement and original true color images

[0219]

[0220]

[0221] Table 6 Comparative analysis of vegetation regional statistical characteristics between the true color image after vegetation feature enhancement and the original true color image RGB mode

[0222]

[0223] (4) Enhanced scheme 4: a smooth constraint function based on the linear combination of vegetation cover and its normalized index.

[0224] Take n1=n2=0.5,k=1,k1=k2=0.5, we get:

[0225]

[0226] R′=[δ(x)f(x)+1]×R

[0227] G′=[δ(x)f(x)+1]×G

[0228] According to the above formula, input the calculation expression: uint(((b1 gt1.047966)*1*((0.5*(((b1-0.590689) / (2.435127))^0.5-(0.187784)^0.5) / (1-(0.187784)^0.5))+(0.5*((1.653226*(b1-0.590689) / (b1+1))^0.5-0.369138^0.5) / (1-0.369138^0.5)))+1)*b2+0.5), where b1 is the characteristic ratio index, and b2 is the red or green band of the image. The enhanced red and green bands are synthesized with the original blue band according to the red, green and blue channels to form a color image to obtain the enhanced true color image. Figure 7 The reconstructed image file is stored as the result.

[0229] The comparative analysis tables of the statistical features of the color image after vegetation feature enhancement in this embodiment and the full image and enhanced area in the RGB color mode of the original true color image are shown in Tables 7 and 8.

[0230] Table 7 Comparative analysis of RGB mode statistical features of true color images after vegetation feature enhancement and original true color images

[0231]

[0232] Table 8 Comparative analysis of vegetation regional statistical characteristics of true color images after vegetation feature enhancement and original true color images in RGB mode

[0233]

[0234]

[0235] The remote sensing true color image vegetation feature enhancement technology described in this embodiment is mainly aimed at the inherent defects of vegetation features in remote sensing images with near infrared, red, green and blue bands. According to the intrinsic relationship of remote sensing band data, a multi-parameter and multi-mode enhancement formula is constructed based on the vegetation coverage of satellite remote sensing images, which effectively improves the vegetation features on the original true color synthetic image and greatly improves the overall effect of the true color image. Specifically, it includes:

[0236] 1. The green vegetation features of true color images are effectively enhanced, improving the visual separability and computer analysis capabilities of vegetation.

[0237] The method described in this embodiment enhances the vegetation pixels of the true color composite image point by point, and the color, texture and layering of the vegetation are comprehensively improved, especially for the vegetation area with weak information, the enhancement effect is better, the image enhancement has stronger predictability, and the visual resolution and computer analysis capabilities of the true color image vegetation information are effectively improved, and the vegetation analysis capability and effect of the true color image mode are improved.

[0238] 2. The overall characteristics of true color images have been greatly improved, expanding their application scope and potential

[0239] The method described in this embodiment maintains the characteristics of exposed objects such as water bodies, soil, rocks, and buildings in true color images while enhancing the characteristics of vegetation in true color images, greatly improving the overall visual characteristics and effects of true color images. At the same time, the colors, textures, and layers of the features of the objects in the true color images are richer, effectively improving the visual resolution and computer analysis capabilities of the true color images.

[0240] Example 2

[0241] The present embodiment discloses a remote sensing image fusion system based on vegetation coverage, including a memory and a processor. The memory includes a remote sensing image fusion method program based on vegetation coverage. When the remote sensing image fusion method program based on vegetation coverage is executed by the processor, the steps of a remote sensing image fusion method based on vegetation coverage described in Example 1 are implemented.

[0242] Example 3

[0243] The present embodiment discloses a computer-readable storage medium, which includes a remote sensing image fusion method program based on vegetation coverage. When the remote sensing image fusion method program based on vegetation coverage is executed by a processor, the steps of a remote sensing image fusion method based on vegetation coverage described in Example 1 are implemented.

[0244] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0245] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0246] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0247] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.

[0248] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

Claims

1. A remote sensing image fusion method based on vegetation cover, It is characterized in that The method comprises: Input remote sensing true color images with near infrared band, red band, green band and blue band; Calculate the characteristic ratio index of remote sensing true color images; According to the characteristic ratio index of remote sensing true color images, the vegetation coverage and coverage power function, the vegetation normalized coverage and normalized coverage power function are constructed; Determine vegetation feature thresholds; A vegetation feature enhancement step function is constructed according to the vegetation feature threshold; Constructing the incremental coefficient function for vegetation feature enhancement; According to the vegetation feature enhancement step function and the vegetation feature enhancement increment coefficient function, a vegetation feature enhancement coefficient function is constructed; Perform remote sensing image fusion enhancement on the vegetation features of the red and green bands of remote sensing true color images; synthesize true color images after vegetation enhancement; The calculating of the characteristic ratio index of the remote sensing image specifically includes: Assume b i is a band of remote sensing true color image, the remote sensing true color image bands involved in the fusion are near infrared band and m true color bands; the number of bands of the fused image result is m, and the fused result is recorded as b' i ; The characteristic ratio index is: Where n = 1, ..., m; The steps of constructing vegetation coverage and coverage power function, and constructing vegetation normalized coverage and normalized coverage power function are specifically as follows: The vegetation coverage is constructed using the characteristic ratio index x, and the formula is: In the formula, x is the characteristic ratio index, x min is the minimum value of the characteristic index, x max is the maximum value of the characteristic index; The vegetation coverage is constructed by the normalized index of the characteristic ratio index x, and the formula is: in, Where NDxI is the normalized index of the characteristic ratio index, NDxI min is the minimum value of the normalized index, NDxI max is the maximum value of the normalized index; Construct the power function h(x) of vegetation cover: The power function t(x) of constructing normalized index vegetation cover is: Where n>0, h(x) and t(x) have the same monotonically increasing property and the same characteristic points (0,0) and (1,1) as x; The vegetation feature threshold c∈[x w , x v ], by default c=x m ; where x w The threshold value of the characteristic ratio index is x, and the threshold value of the characteristic ratio index of pure vegetation is x v , c is the vegetation feature threshold, x m is the average value of the characteristic ratio index x; The vegetation feature enhancement step function is:

2. According to the remote sensing image fusion method based on vegetation coverage described in claim 1, It is characterized in that The expression of the vegetation characteristic increment coefficient function is: k is the greenness adjustment coefficient, k>0, and k=1 by default; g(x) is the composite function of the smooth constraint basis function, g(x max ) is the maximum value of the smooth constraint composite function; The specific construction method of the vegetation characteristic increment coefficient function is as follows: Construct the smooth constrained basis function u(h(x)) of vegetation cover and the smooth constrained basis function u(t(x)) of normalized exponential vegetation cover: u(h(x)) is the smooth constrained basis function of vegetation cover; u(t(x)) is the smooth constrained basis function of normalized exponential vegetation cover; A series of incremental coefficient functions f(x) are constructed based on the smooth constraint basis function of vegetation cover and the smooth constraint basis function of normalized exponential vegetation cover, including at least the following: (1) Smooth constraint function based on vegetation coverage: (2) Smooth constraint function based on normalized index vegetation cover: (3) Smooth constraint function based on the product of vegetation coverage and normalized index vegetation coverage: (4) Smooth constraint function based on the linear combination of vegetation cover and normalized index vegetation cover: In the formula, k 1 and k 2 is the weight coefficient, k 1 ∈[0,1], k 2 =1-k 1 .

3. According to the remote sensing image fusion method based on vegetation coverage described in claim 2, It is characterized in that The expression of the vegetation feature enhancement coefficient function is: F(x)=δ(x)f(x)+1.

4. According to claim 3, a remote sensing image fusion method based on vegetation coverage, It is characterized in that The red and green band vegetation feature enhancement scheme of the remote sensing true color image is as follows: R'=[δ(x)f(x)+1]×R G'=R[6(x)f(x)+1]×G Among them, R' is the enhanced green band, R is the green band, G' is the enhanced red band, and G is the red band.

5. A remote sensing image fusion system based on vegetation cover, It is characterized in that It comprises a memory and a processor, wherein the memory comprises a remote sensing image fusion method program based on vegetation coverage, and when the remote sensing image fusion method program based on vegetation coverage is executed by the processor, the steps of a remote sensing image fusion method based on vegetation coverage as described in any one of claims 1 to 4 are implemented.

6. A computer-readable storage medium, It is characterized in that The computer-readable storage medium includes a remote sensing image fusion method program based on vegetation coverage. When the remote sensing image fusion method program based on vegetation coverage is executed by a processor, the steps of a remote sensing image fusion method based on vegetation coverage as described in any one of claims 1 to 4 are implemented.