Overlay fusion method, system, device and storage medium based on generalized vegetation cover

Abstract

The present invention discloses a superposition fusion method, system, device and storage medium based on generalized vegetation cover, the method comprising: obtaining a satellite remote sensing image having a near-infrared band, a red band, a green band and a blue band; performing inter-spectral fusion of the near-infrared band with one or more of the red band, the green band and the blue band, calculating a characteristic ratio index using the fused band combination as a numerator and the corresponding band combination before fusion as a denominator; constructing a linear transformation function based on the characteristic ratio index; setting a virtual minimum value v of the characteristic ratio index as min =kx min A power function based on generalized vegetation cover is constructed based on the linear transformation function and the virtual minimum. The characteristic power of the power function based on generalized vegetation cover is determined by the power function value corresponding to the characteristic threshold of the characteristic ratio index being equal to ε. According to the principle of superposition enhancement, the power function based on generalized vegetation cover with the determined characteristic power is used to enhance the red and green bands, respectively. This invention improves the standardization of the enhancement process and the consistency of the processing results.

Description

Technical Field

[0001] The present invention relates to the field of remote sensing image fusion technology, and in particular to a superposition fusion method, system, computer equipment and computer-readable storage medium based on generalized vegetation cover. Background Art

[0002] With the development of multi-platform, multi-sensor, multi-weather, multi-temporal, and multi-resolution remote sensing technology, imagery with varying spatial, temporal, and spectral resolutions is becoming increasingly abundant. Over the past two decades, spatiotemporal fusion of remote sensing images has emerged as a new direction in remote sensing image processing, with various fusion techniques rapidly developing and achieving a series of new results. However, research on interspectral fusion of multispectral images is limited, primarily focusing on true color image simulation or vegetation enhancement.

[0003] With the widespread application of remote sensing in various industries, visible light multispectral satellite remote sensing true color imagery, with its advantageous "what you see is what you get" feature, has become one of the most widely used remote sensing image types. However, inherent flaws, such as unnatural and unrealistic vegetation colors, have limited its effectiveness. Effectively enhancing vegetation features in visible light satellite remote sensing true color imagery is a key and challenging aspect of visible light satellite remote sensing true color image processing. Researchers have conducted fruitful research on this topic, laying the theoretical and technical foundation for further addressing related issues. Based on primary satellite remote sensing products, Chen Chun et al. applied Rayleigh scattering correction to remote sensing data, resulting in color signal images that approximate those of ground-based true color images (Chen Chun et al., "Extraction and Reproduction of Color Signals from Remote Sensing Sources," Science of Surveying and Mapping, January 2006, Vol. 31, No. 1; Han Xiuzhen et al., "Research and Application of Synthesis Methods for Fengyun-3D True Color Images," Journal of Marine Meteorology, May 2019, Vol. 39, No. 2). You Jing et al. used white balancing and colorimetry-based color correction to improve vegetation features in true color images, resulting in more realistic true color images (You Jing et al., "A White Balance Method for Processing Color Multispectral Images," Journal of Atmospheric and Environmental Optics, Vol. 7, No. 4, July 2012; Huang Honglian et al., "True Color Synthesis of Multispectral Remote Sensing Images Based on Artificial Targets," Infrared and Laser Engineering, Vol. 45, No. 11, November 2016). Fan Xuyan et al., based on secondary processing of remote sensing images, obtained relatively good true color images by enhancing the green band. In the early days, the green band and the near-infrared band were mainly used to obtain a new green band by using an overall weighted combination operation scheme (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 Applicability of Gaofen-2 Satellite Remote Sensing Imagery for 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 perform weighted classification processing on 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).

[0004] The evaluation technology of vegetation enhancement effect of true color image includes visual evaluation and quantitative evaluation. (1) Visual evaluation: As we all know, although the original remote sensing true color image is consistent with the ground objects in the water body, exposed land and other land features, the color is dim and the layers are unclear in the vegetation area. Generally, true color image needs to enhance the vegetation to obtain true color image that is consistent with the ground color in the above-mentioned land features. That is, vegetation is based on green, and vegetation of different types and different coverages presents various shades of green; water bodies are based on blue, except for the green, yellow, black, etc. due to different components such as water surface vegetation coverage, 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, showing gray, black, white, red, orange, yellow, green, cyan, blue, purple and other colors. By visually selecting typical land features such as water, 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. (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 the true color image, and also to ensure the richness and clarity of the layers, details, etc. of the enhanced true color image. In general, the reconstructed image can be quantitatively evaluated from two aspects: one 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 CIELab, it is generally believed that the RGB three-primary color model is suitable for computer screen displays, and printing models such as CMYK are suitable for color image printouts. The color description of color space models such as IHS and CIELab conforms to the human eye's visual perception mode. Based on this understanding, the commonly used method for quantitatively evaluating the quality of true-color imagery is to convert remote sensing images described in the RGB color space into images described in the IHS or CIELab color space. The hue, saturation, and intensity of vegetation features before and after enhancement in these color spaces are then analyzed to analyze their changing trends and characteristics. Secondly, the quality indicators of the enhanced true-color images are statistically analyzed and compared. Generally speaking, the quality of image processing can be evaluated from three perspectives: first, the information richness of the enhanced image as a whole and in the vegetation region, which can be measured using entropy and joint entropy. Second, the color richness and brightness of the enhanced image as a whole and in the vegetation region can be measured using band statistics—maximum, minimum, mean, variance, and inter-band correlation indicators—correlation coefficient and covariance. Third, the level of hierarchy (edges), detail (texture), and clarity of the enhanced image as a whole and in the vegetation region can be measured using gradients and average gradients. By comparing the differences in these indicators before and after enhancement, the overall image and in the vegetation region can be analyzed to determine the direction of change in spectral (grayscale, hue), edge (level, difference), and texture (detail) information.

[0005] To address the shortcomings of satellite remote sensing true-color imagery, such as the dimness and unnatural colors of vegetation and other features, multi-index, multi-transform, multi-mode, and multi-parameter methods for enhancing vegetation features in natural-color images have been developed. These methods effectively improve the quality of true-color images and enhance both visual resolution and computer resolution. This diverse set of enhancement methods provides diverse image processing technicians with a wide range of options for personalized processing of specific images. However, in large-scale applications of true-color remote sensing image enhancement, high consistency of processing results is often required to facilitate their application in mapping and classification. Clearly, there is a significant conflict between personalized processing and the requirements of standardization and consistency. Summary of the Invention

[0006] The present invention provides a superposition fusion method, system, computer device and computer-readable storage medium based on generalized vegetation cover, aiming to resolve the contradiction between the personalized processing of single images and the standardization and consistency processing requirements of large-scale images in true color image enhancement.

[0007] The first object of the present invention is to provide a superposition and fusion method based on generalized vegetation cover.

[0008] The second object of the present invention is to provide a superposition and fusion system based on generalized vegetation cover.

[0009] A third object of the present invention is to provide a computer device.

[0010] A fourth object of the present invention is to provide a computer-readable storage medium.

[0011] The first object of the present invention can be achieved by adopting the following technical solutions:

[0012] A superposition fusion method based on generalized vegetation cover, the method comprising:

[0013] Acquire satellite remote sensing images with near-infrared, red, green and blue bands;

[0014] Perform spectrum fusion on the near-infrared band with one or more of the red band, green band, and blue band, use the fused band combination as the numerator and the corresponding band combination before fusion as the denominator to calculate the characteristic ratio index;

[0015] According to the characteristic ratio index, a linear transformation function is constructed;

[0016] Let the virtual minimum value v of the characteristic ratio index be min =kx min; Construct a power function based on the generalized vegetation coverage according to the linear transformation function and the virtual minimum value; where, k ∈ [0, 1] is a given value, and x min is the minimum value of the characteristic ratio index x;

[0017] Determine the characteristic power of the power function based on the generalized vegetation coverage by making the value of the power function based on the generalized vegetation coverage corresponding to the characteristic threshold of the characteristic ratio index equal to ε; where, ε is a given value greater than 0 and much less than 1;

[0018] According to the principle of superposition enhancement, use the power function based on the generalized vegetation coverage that determines the characteristic power to enhance the red band and the green band respectively; Synthesize the enhanced red band and green band with the blue band to obtain the true color image after vegetation enhancement;

[0019] Among them, the linear transformation function satisfies the conditions: h(c) = 1, and: when x > c, h(x) > 1; when x < c, h(x) < 1; c is the characteristic threshold of the characteristic ratio index x, and s and t are both constants.

[0020] Furthermore, s = 1, t = 1 - c; or, s = c, t = 0; or, s = 1, t = 0.

[0021] Furthermore, the constructing of the power function based on the generalized vegetation coverage according to the linear transformation function and the virtual minimum value includes:

[0022] Construct the generalized vegetation coverage based on h(x) according to the linear transformation function and the virtual minimum value as:

[0023]

[0024] Obtain the power function based on the generalized vegetation coverage as:

[0025]

[0026] Among them, x max is the maximum value of the characteristic ratio index x; n is the characteristic power to be determined, and n > 0.

[0027] Furthermore, the constructing of the power function based on the generalized vegetation coverage according to the linear transformation function and the virtual minimum value includes:

[0028] The normalized index NdhI corresponding to the linear transformation function h(x) is:

[0029]

[0030] Construct the generalized vegetation coverage based on NdhI according to the normalized index NdhI and the virtual minimum value as:

[0031]

[0032] According to the generalized vegetation cover based on NdhI, the power function based on the generalized vegetation cover is obtained as follows:

[0033]

[0034] Among them, x max is the maximum value of the characteristic ratio exponent x; n is the characteristic power to be determined, n>0.

[0035] Furthermore, the power function based on the generalized vegetation cover is constructed according to the linear transformation function and the virtual minimum, including:

[0036] According to the linear transformation function and the virtual minimum, the generalized vegetation cover based on h(x) is constructed as follows:

[0037]

[0038] The normalized index NdhI corresponding to the linear transformation function h(x) is:

[0039]

[0040] According to the normalized index NdhI and the virtual minimum value, the generalized vegetation cover based on NdhI is constructed as follows:

[0041]

[0042] According to the generalized vegetation cover based on h(x) and the generalized vegetation cover based on NdhI, the power function based on the average value of the two generalized vegetation covers is obtained as follows:

[0043]

[0044] Among them, x max is the maximum value of the characteristic ratio index x; n is the characteristic power to be determined, n>0;

[0045] M(x) is a power function constructed based on generalized vegetation cover.

[0046] Furthermore, the power function based on the generalized vegetation cover is constructed according to the linear transformation function and the virtual minimum, including:

[0047] According to the linear transformation function and the virtual minimum, the generalized vegetation cover based on h(x) is constructed as follows:

[0048]

[0049] The normalized index NdhI corresponding to the linear transformation function h(x) is:

[0050]

[0051] According to the normalized index NdhI and the virtual minimum value, the generalized vegetation cover based on NdhI is constructed as follows:

[0052]

[0053] According to the generalized vegetation cover based on h(x) and the generalized vegetation cover based on NdhI, the power function based on the product of the two generalized vegetation covers is:

[0054]

[0055] Among them, x max is the maximum value of the characteristic ratio index x; n is the characteristic power to be determined, n>0;

[0056] P(x) is a power function constructed based on generalized vegetation cover.

[0057] Furthermore, according to the principle of superposition enhancement, the red band and the green band are enhanced respectively using a power function based on generalized vegetation cover with a determined characteristic power, including:

[0058] R′=[mZ ε (x)+1]R

[0059] G′=[mZ ε (x)+1]G

[0060] Among them, R′ and G′ are the enhanced red band and green band respectively, m>0 is the greenness adjustment coefficient, and Z ε (x) is the power function based on generalized vegetation cover to determine the characteristic power, R and G are the red band and green band respectively.

[0061] Furthermore, the feature threshold c∈[x min ,x max ] or feature threshold c∈[x w ,x v ]; where x max is the maximum value of the characteristic ratio index x, x w 、x v These are the thresholds for pure water bodies and pure vegetation determined by human-computer interaction, respectively.

[0062] The second object of the present invention can be achieved by adopting the following technical solutions:

[0063] A superposition and fusion system based on generalized vegetation cover, comprising:

[0064] An acquisition module, configured to acquire satellite remote sensing images having near-infrared bands, red bands, green bands, and blue bands;

[0065] A calculation module, configured to perform spectral fusion on the near-infrared band with one or more of the red band, green band, and blue band, use the fused band combination as the numerator, and use the corresponding band combination before fusion as the denominator to calculate a characteristic ratio index;

[0066] A first construction module, configured to construct a linear transformation function according to the characteristic ratio index;

[0067] A second construction module, configured to set a virtual minimum value v of the characteristic ratio index min = kx min ; construct a power function based on the generalized vegetation coverage according to the linear transformation function and the virtual minimum value; where k ∈ [0, 1] is a given value, and x min is the minimum value of the characteristic ratio index x;

[0068] A determination module, configured to determine the characteristic power of the power function based on the generalized vegetation coverage by making the value of the power function based on the generalized vegetation coverage corresponding to the characteristic threshold of the characteristic ratio index equal to ε; where ε is a given value greater than 0 and much less than 1;

[0069] A fusion module, configured to enhance the red band and the green band respectively by using the power function based on the generalized vegetation coverage for determining the characteristic power according to the principle of superposition enhancement; synthesize the enhanced red band and green band with the blue band to obtain a true color image with enhanced vegetation;

[0070] where the linear transformation function satisfies the conditions: h(c) = 1, and: when x > c, h(x) > 1; when x < c, h(x) < 1; c is the characteristic threshold of the characteristic ratio index x, and s and t are both constants.

[0071] The third object of the present invention can be achieved by adopting the following technical solution:

[0072] A computer device, including a processor and a memory for storing programs executable by the processor. When the processor executes the programs stored in the memory, the above-mentioned superposition fusion method based on the generalized vegetation coverage is implemented.

[0073] The fourth object of the present invention can be achieved by adopting the following technical solution:

[0074] A computer-readable storage medium stores a program. When the program is executed by a processor, the above-mentioned superposition fusion method based on the generalized vegetation coverage is implemented.

[0075] The present invention has the following beneficial effects compared to the prior art:

[0076] The present invention sets the virtual minimum value v of the characteristic ratio index min is less than or equal to the minimum value of the characteristic ratio index, ε is greater than 0 and much less than 1, and the power function value based on the generalized vegetation cover corresponding to the characteristic threshold of the characteristic ratio index is equal to ε, thereby determining a characteristic curve of the generalized vegetation cover power function space for true color image enhancement (a power function based on the generalized vegetation cover with a determined characteristic power), realizing automatic calculation of the characteristic power, reducing human dependence, improving the standardization of the enhancement process and the consistency of the processing results, effectively improving the vegetation chromaticity and layer characteristics on the original true color composite image, and greatly improving the overall effect of the true color image. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying any creative work.

[0078] Figure 1 This is a simplified flowchart of the superposition and fusion method based on generalized vegetation cover according to Example 1 of the present invention;

[0079] Figure 2 This is a detailed flow chart of the superposition and fusion method based on generalized vegetation cover according to Example 1 of the present invention;

[0080] Figure 3 The true color combined color image before vegetation feature enhancement according to Example 1 of the present invention;

[0081] Figure 4 This is a characteristic ratio index image diagram of Example 1 of the present invention;

[0082] Figure 5 This is the enhanced image of vegetation coverage based on h(x) in Example 1 of the present invention;

[0083] Figure 6 The enhanced image of vegetation coverage based on NDhI according to Example 1 of the present invention (untransformed);

[0084] Figure 7 The enhanced image based on the product of two vegetation coverages according to Example 1 of the present invention (untransformed);

[0085] Figure 8 The enhanced image based on the average values ​​of the two vegetation coverages according to Example 1 of the present invention (untransformed);

[0086] Figure 9 The enhanced image of vegetation cover based on NDhI (exponential shift transformation) according to Example 1 of the present invention is shown in FIG.

[0087] Figure 10 The enhanced image (exponential shift transformation) based on the product of two vegetation coverages according to embodiment 1 of the present invention is shown;

[0088] Figure 11 This is the enhanced image (exponential shift transformation) based on the average values ​​of two vegetation coverages according to Example 1 of the present invention;

[0089] Figure 12 This is the enhanced image of vegetation cover based on NDhI (exponential scaling transformation) according to Example 1 of the present invention;

[0090] Figure 13 The enhanced image based on the product of two vegetation coverages (exponential scaling transformation) of Example 1 of the present invention;

[0091] Figure 14 This is the enhanced image (exponential scaling transformation) based on the average values ​​of two vegetation coverages according to Example 1 of the present invention;

[0092] Figure 15 This is a structural block diagram of a superposition and fusion system based on generalized vegetation coverage according to Example 2 of the present invention;

[0093] Figure 16 This is a structural block diagram of a computer device according to embodiment 3 of the present invention. DETAILED DESCRIPTION

[0094] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention. It should be understood that the specific embodiments described are only used to explain this application and are not used to limit this application.

[0095] Example 1:

[0096] like Figure 1 、 2 As shown, this embodiment provides a superposition fusion method based on generalized vegetation cover, including the following steps:

[0097] S101. Input satellite remote sensing images.

[0098] Input satellite remote sensing images with near-infrared (NIR), red (R), green (G), and blue (B) bands.

[0099] S102. Calculate a characteristic ratio index based on satellite remote sensing images.

[0100] Assume b i is one of the true color bands, and the bands involved in the fusion are NIR and m true color bands. The number of band results after fusion is m, and the fusion result is recorded as b i ′.

[0101] (1) For quasi-Brovey fusion, the fusion result is recorded as:

[0102]

[0103] Where m = 1, 2, 3, i = 1, ..., m, b i 、b j is the true color band involved in the fusion.

[0104] (2) For Schmidt-Gram, PCA fusion or Wavelet fusion, the fusion result is recorded as:

[0105] b i ′=Fusion(NIR,b1,…,b m )

[0106] Where m = 1, 2, 3, i = 1, ..., m, b 1, ,…,b m The true color bands involved in the fusion. Fusion is the GS (Gram-Schmidt), PCA fusion, or WL (Wavelet) fusion method.

[0107] The characteristic ratio index is:

[0108]

[0109] Where n=1,…,m.

[0110] S103: Determine the feature threshold and construct a linear transformation function based on the feature ratio index.

[0111] Furthermore, step S103 includes:

[0112] (1) Determine the characteristic threshold of the characteristic ratio index.

[0113] Calculate the minimum, maximum and average values ​​of the characteristic ratio index x, denoted as x min 、x max 、x m , then the characteristic threshold value c∈[xmin ,x max ]; or human-computer interaction to determine the threshold value x of pure water w , the threshold value x of pure exposed ground objects b , the threshold value of pure vegetation x v , then the feature threshold c∈[x w ,x v ]; c=x by default m , or other values ​​can be taken according to the actual characteristics of the image or user enhancement needs, such as x w 、x b or x v Or other values.

[0114] (2) Construct a linear transformation function based on the feature ratio index and feature threshold.

[0115] Assuming s and t to be constants, a linear transformation of the characteristic ratio index can be obtained:

[0116]

[0117] h(x) has similar mathematical properties and physical functions to x. Like x, it can also be used as a basic parameter for vegetation feature enhancement.

[0118] If h(x) is multiplied with the original image, if the position greater than the threshold c is required to be enhanced and the position less than the threshold c is required to remain unchanged, and the image is required to remain continuous, the following conditions must be met: h(c) = 1, and x>c, h(x)>1; x <c,h(x)<1。

[0119] Two typical linear transformations that meet the above conditions are:

[0120] (2-1) During translation transformation, s = 1, t = 1-c;

[0121] (2-2) During scaling transformation, s=c, t=0 (st=0, st-s=-c, st+s=c).

[0122] In particular, when s=1, t=0, there is no transformation.

[0123] Then the normalized index corresponding to h(x) is:

[0124]

[0125] In translation transformation, st-s=-c, st+s=2-c;

[0126] During scaling transformation, st-s=-c, st+s=c;

[0127] In particular, when there is no transformation, st-s=-1, st+s=1.

[0128] NDhI has similar mathematical properties and physical functions to h(x). Like h(x), it can also be used as a basic parameter for vegetation feature enhancement.

[0129] S104. Construct the generalized vegetation cover and its power function space based on the linear transformation function.

[0130] Furthermore, step S104 includes:

[0131] (1) Assume that the characteristic ratio index x has a virtual minimum value v min ∈[0,x min ], linear transformation function h(x) based on characteristic ratio index and virtual minimum v min The generalized vegetation cover is constructed as:

[0132]

[0133] Its power function space is:

[0134]

[0135] H(v min )=0

[0136] H(x max )=1

[0137] Where n>0.

[0138] It can be seen that no matter it is a scaling transformation or a translation transformation, the power function of vegetation cover has the same mathematical properties as when there is no transformation.

[0139] Similarly:

[0140] (2) The generalized vegetation cover based on NDhI is:

[0141]

[0142] Its power function space is:

[0143]

[0144] N(v min )=0

[0145] N(x max )=1

[0146] Where n>0.

[0147] (3) The power function space based on the product of two generalized vegetation covers is:

[0148]

[0149] P(v min )=H(v min )N(v min )=0

[0150] P(x max )=H(x max )N(x max )=1

[0151] Where n>0.

[0152] (4) The power function space based on the average values ​​of the two generalized vegetation coverages is:

[0153]

[0154] We can get:

[0155]

[0156]

[0157] Where n>0.

[0158] H(x), N(x), P(x), and M(x) have excellent properties. min , x max ] is an increasing function, at the virtual minimum x=v min The function value is 0 at the maximum value of the characteristic ratio index x = x max The function value at the feature threshold is 1, and the function value at the feature threshold depends on an independent parameter - the power n. When it is used as a vegetation feature enhancement function, it can be used as an incremental coefficient factor for superposition fusion.

[0159] S105. Determine the characteristic power in the power function space based on the generalized vegetation cover and its corresponding superposition enhancement scheme.

[0160] Furthermore, step S105 includes:

[0161] Assume that the red, green, and blue bands of a true color image are R, G, and B respectively.

[0162] The general expression of superposition enhancement is:

[0163] R′=[mZ(x)+1]R

[0164] G′=[mZ(x)+1]G

[0165] B′=B

[0166] Among them, Z(x) is the power function space based on generalized vegetation cover.

[0167] (1) Overlay enhancement scheme of generalized vegetation cover based on h(x).

[0168] Let v min =kx min , k∈[0,1], ε>0 and much less than 1, H(c)=ε, then:

[0169]

[0170] Then the characteristic power is:

[0171]

[0172] Then the characteristic curve is:

[0173]

[0174] Feature scheme of superposition enhancement:

[0175] R′=[mH ε (x)+1]R

[0176] G′=[mH ε (x)+1]G

[0177] B′=B

[0178] Among them, m>0 is the greenness adjustment coefficient, which is 1 by default.

[0179] (2) Overlay enhancement scheme of generalized vegetation cover based on NDhI.

[0180] Let v min =kx min , k∈[0,1], ε>0 and much less than 1, N(c)=ε, then:

[0181]

[0182] Then the characteristic power is:

[0183]

[0184] Then the characteristic curve is:

[0185]

[0186] Feature scheme of superposition enhancement:

[0187] R′=[mN ε (x)+1]R

[0188] G′=[mN ε (x)+1]G

[0189] B′=B

[0190] Among them, m>0 is the greenness adjustment coefficient, which is 1 by default.

[0191] (3) A superposition enhancement scheme based on the product of two broad vegetation coverages.

[0192] Let v min =kx min , k∈[0,1], ε>0 and much less than 1, P(c)=ε, then:

[0193]

[0194] Then the characteristic power is:

[0195]

[0196] Then the characteristic curve is:

[0197]

[0198] Feature scheme of superposition enhancement:

[0199] R′=[mP ε (x)+1]R

[0200] G′=[mP ε (x)+1]G

[0201] B′=B

[0202] Among them, m>0 is the greenness adjustment coefficient, which is 1 by default.

[0203] (4) Superposition enhancement scheme based on the average values ​​of two generalized vegetation coverages.

[0204] Let v min =kx min , k∈[0,1], ε>0 and much less than 1, M(c)=ε, then:

[0205]

[0206] Then the characteristic power is:

[0207]

[0208] Then the characteristic curve is:

[0209]

[0210] Feature scheme of superposition enhancement:

[0211] R′=[mM ε (x)+1]R

[0212] G′=[mM ε (x)+1]G

[0213] B′=B

[0214] Among them, m>0 is the greenness adjustment coefficient, which is 1 by default.

[0215] S106: synthesize and store the vegetation-enhanced true color image.

[0216] The color image is synthesized using the three bands R′, G′, and B corresponding to the red, green, and blue channels of the color image, and the enhanced true color image is stored.

[0217] In general, the enhancement algorithm provided in this embodiment is based on the inherent characteristics of satellite image data and has strong data adaptability. The characteristic ratio index, characteristic threshold, generalized vegetation cover, generalized vegetation cover power function space and its characteristic curve have clear physical meanings. The parameters of feature enhancement are determined by calculation, which reduces human dependence, has clear processing objectives, reliable quality, and is easy to use. It has the following advantages:

[0218] (1) The given superposition factor has the function of enhancing vegetation characteristics and maintaining non-vegetation characteristics.

[0219] The superposition factor (based on the power function space of generalized vegetation cover) has excellent characteristics - it is 0 at the virtual minimum of the characteristic ratio exponent, a small value in a neighborhood of 0 at the threshold, and an incremental coefficient of 1 at the maximum value. It ensures that the enhanced image is smooth at the threshold and maintains non-vegetation features while enhancing vegetation features.

[0220] (2) The characteristic power of generalized vegetation cover is given to effectively improve the vegetation chromaticity and layer differences, and the greenness adjustment coefficient makes the enhancement effect adjustable and controllable.

[0221] The characteristic power of generalized vegetation cover enhances the hierarchical differences between different vegetation types, effectively highlighting their differences. As the greenness adjustment coefficient changes from small to large, the hue of the vegetation in the enhanced image changes from dark green to yellow-green. The adjustment direction and enhancement effect are predictable and controllable.

[0222] This embodiment will illustrate the above method with reference to specific application examples:

[0223] In order to achieve the purpose of enhancing vegetation features in satellite remote sensing true color images, this embodiment mainly uses ENVI remote sensing image processing software to achieve this.

[0224] Step 1: Input remote sensing image.

[0225] Open a multispectral remote sensing image with near infrared band (NIR), red band (R), green band (G), and blue band (B). Figure 3 This is the true color composite color image before vegetation feature enhancement (the effect image is stretched by 0.1% according to the default setting of envi).

[0226] Step 2: Calculate the feature ratio index and determine its threshold.

[0227] Take the characteristic ratio index obtained by quasi-GS fusion as an example.

[0228]

[0229] GSR, GSG, and GSB are the results of the fusion of NIR with R, G, and B. The calculation results are as follows Figure 4 (The effect of 0.1% stretching according to the default setting of envi).

[0230] Step 3: Determine the overlay fusion plan.

[0231] Table 1 shows the statistical characteristic results of the characteristic ratio index, and Tables 2 to 4 show the calculation results.

[0232] Table 1 Statistical characteristics of characteristic ratio index x

[0233] Characteristic ratio index Min Max Mean Stdev x 0.410289 2.594493 1.022385 0.290669

[0234] Taking the vegetation characteristic threshold c = 1.022385 of the characteristic ratio index x, the linear transformation function of the characteristic ratio is:

[0235]

[0236] (1) When no transformation occurs, s = 1, t = 0 (st = 0, st + s = 1)

[0237] (2) During translation transformation, s = 1, t = 1-c = -0.022385 (st = -0.022385, st + s = 0.977615)

[0238] (3) When scaling, s = c = 1.022385, t = 0 (st = 0, st + s = 1.022385) Table 2 Calculation results (no transformation)

[0239]

[0240] Table 3 Calculation results (exponential translation transformation)

[0241]

[0242] Table 4 Calculation results (exponential scaling transformation)

[0243]

[0244] Among them, m=1, b1 is the characteristic ratio index x, and b2 is the red band R or the green band G.

[0245] Step 4: Integrate the results and their effects.

[0246] From Tables 2 to 4, we can see that 3 linear transformations correspond to 12 calculation schemes, among which the superposition enhancement effect of vegetation coverage based on h(x) corresponding to the 3 linear transformations is the same. The results calculated using ENVI can be referred to Figures 5 to 14 .

[0247] From a visual perspective, the enhancement results achieved by the above schemes are similar, effectively enhancing vegetation information while preserving the characteristics of non-vegetation information. This is illustrated by taking the power function of the product of two generalized vegetation coverages corresponding to the characteristic ratio exponential translation transform (the generalized vegetation coverage corresponding to the ratio index and the generalized vegetation coverage corresponding to the normalized index) as the enhancement results, as shown in Statistical Tables 5-8.

[0248] Table 5 Comparative analysis of RGB mode statistical features of enhanced true color images and original true color images

[0249]

[0250] Table 6 Comparative analysis of vegetation regional statistical characteristics between enhanced true color images and original true color images in RGB mode

[0251]

[0252] Table 7 Comparative analysis of statistical characteristics of non-vegetation areas in enhanced true color images and original true color images in RGB mode

[0253]

[0254] Table 8 Comparative analysis of HLS classification statistical characteristics of enhanced true color images and original true color images

[0255]

[0256] According to Tables 5 to 8, the following conclusions can be drawn:

[0257] (1) The green vegetation features of true color images are effectively enhanced, which improves the visual separability and computer parsing capabilities of vegetation.

[0258] The method provided in this embodiment comprehensively improves the color, texture, and layering of vegetation by enhancing the vegetation pixels of the true color composite image point by point, effectively improving the visual resolution and computer parsing capabilities of the true color image vegetation information, and improving the vegetation analysis capabilities and effects of the true color image mode.

[0259] (2) The overall characteristics of true color images have been greatly improved, expanding their application scope and potential.

[0260] The method provided in this embodiment enhances the vegetation features in true color images while maintaining the features of exposed objects such as water bodies, soil, rocks, and buildings in true color images, greatly improving the overall visual features and effects of true color images. At the same time, the correlation between the various bands of true color images is reduced, and the image colors, textures, and layers are richer.

[0261] Those skilled in the art will appreciate that all or part of the steps in the method for implementing the above embodiments may be completed by instructing related hardware through a program, and the corresponding program may be stored in a computer-readable storage medium.

[0262] It should be noted that although the method operations of the above embodiments are described in a particular order in the accompanying drawings, this does not require or imply that the operations must be performed in this particular order, or that all of the illustrated operations must be performed to achieve the desired results. Rather, the depicted steps may be performed in a different order. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into a single step, and / or a single step may be broken down into multiple steps.

[0263] Example 2:

[0264] like Figure 15 As shown, this embodiment provides a superposition and fusion system based on generalized vegetation cover, which includes an acquisition module 1501, a calculation module 1502, a first construction module 1503, a second construction module 1504, a determination module 1505, and a fusion module 1506, wherein:

[0265] The acquisition module 1501 is used to acquire satellite remote sensing images with near infrared band, red band, green band and blue band;

[0266] A calculation module 1502 is configured to perform spectrum fusion between the near-infrared band and one or more of the red band, the green band, and the blue band, and calculate a characteristic ratio index using the fused band combination as a numerator and the corresponding band combination before fusion as a denominator;

[0267] A first construction module 1503 is configured to construct a linear transformation function according to a characteristic ratio index;

[0268] A second construction module 1504 for setting a virtual minimum value v of the characteristic ratio index min = kx min ; construct a power function based on the generalized vegetation coverage according to the linear transformation function and the virtual minimum value; where k ∈ [0, 1] is a given value, and x min is the minimum value of the characteristic ratio index x;

[0269] A determination module 1505 for determining the characteristic power of the power function based on the generalized vegetation coverage by making the value of the power function based on the generalized vegetation coverage corresponding to the characteristic threshold of the characteristic ratio index equal to ε; where ε is a given value greater than 0 and much less than 1;

[0270] A fusion module 1506 for enhancing the red band and the green band respectively by using the power function based on the generalized vegetation coverage for determining the characteristic power according to the principle of superposition enhancement; synthesizing the enhanced red band and green band with the blue band to obtain a true color image after vegetation enhancement;

[0271] Among them, the linear transformation function satisfies the conditions: h(c) = 1, and: if x > c, then h(x) > 1, if x < c, then h(x) < 1; c is the characteristic threshold of the characteristic ratio index x, and s and t are both constants.

[0272] For the specific implementation of each module in this embodiment, reference can be made to Embodiment 1 above, which will not be elaborated here one by one; it should be noted that the system provided in this embodiment is only illustrated by the above division of each functional module. In actual applications, the above functions can be allocated to different functional modules as needed, that is, the internal structure is divided into different functional modules to complete all or part of the functions described above.

[0273] Embodiment 3:

[0274] This embodiment provides a computer device, which can be a computer. As Figure 16 shown, it includes a processor 1602, a memory, an input device 1603, a display 1604, and a network interface 1605 connected by a system bus 1601. The processor is used to provide computing and control capabilities. The memory includes a non-volatile storage medium 1606 and an internal memory 1607. The non-volatile storage medium 1606 stores an operating system, a computer program, and a database. The internal memory 1607 provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. When the processor 1602 executes the computer program stored in the memory, it implements the superposition fusion method based on the generalized vegetation coverage in Embodiment 1 above.

[0275] Embodiment 4:

[0276] This embodiment provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the overlay fusion method based on generalized vegetation cover of the above-mentioned embodiment 1 is implemented.

[0277] It should be noted that the computer-readable storage medium of the present embodiment may be a computer-readable signal medium or a computer-readable storage medium or any combination thereof. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0278] In summary, the present invention mainly targets the inherent defects of vegetation features in satellite remote sensing images with near-infrared, red, green, and blue bands. Based on the intrinsic relationship of remote sensing band data, an enhancement formula based on the power function of vegetation cover characteristics is constructed, which effectively improves the vegetation chromaticity and layer characteristics on the original true color composite image, and greatly improves the overall effect of the true color image. The method has a clear physical meaning and a wide range of applications. The enhanced image has bright colors, rich information, and is easy to visually and automatically classify. Especially in the current context of rapid development of high-resolution satellite remote sensing, it has a huge promoting effect on promoting the promotion and application of domestic high-resolution images in various industries at home and abroad.

[0279] In the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include at least one of such features. In the description of the present invention, "plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0280] The above is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes based on the technical solution and inventive concept of the present invention within the scope disclosed by the present invention, which falls within the scope of protection of the present invention.

Claims

1. A superposition fusion method based on generalized vegetation cover, characterized in that: The method comprises: Acquire satellite remote sensing images with near-infrared, red, green and blue bands; Perform spectrum fusion on the near-infrared band with one or more of the red band, green band, and blue band, use the fused band combination as the numerator and the corresponding band combination before fusion as the denominator to calculate the characteristic ratio index; According to the characteristic ratio index, a linear transformation function is constructed; Let the virtual minimum value v of the characteristic ratio index be min =kx min ; According to the linear transformation function and the virtual minimum, a power function based on generalized vegetation cover is constructed; where k∈[0,1] is a given value, x min is the minimum value of the characteristic ratio index x; The power function value based on the generalized vegetation cover corresponding to the characteristic threshold of the characteristic ratio index is equal to ε, thereby determining the characteristic power of the power function based on the generalized vegetation cover; wherein ε is a given value greater than 0 and much less than 1; According to the principle of superposition enhancement, the red and green bands are enhanced separately using a power function based on generalized vegetation cover with a determined characteristic power. The enhanced red and green bands are synthesized with the blue band to obtain a true color image after vegetation enhancement. Among them, the linear transformation function satisfies the conditions: h(c) = 1, and: if x > c, then h(x) > 1; if x < c, then h(x) < 1; c is the characteristic threshold of the characteristic ratio index x, and both s and t are constants.

2. The superposition fusion method according to claim 1, characterized in that: s=1, t=1-c; or, s=c, t=0; or, s=1, t=0.

3. The superposition fusion method according to any one of claims 1 and 2, characterized in that: The power function based on the generalized vegetation cover is constructed according to the linear transformation function and the virtual minimum, including: According to the linear transformation function and the virtual minimum, the generalized vegetation cover based on h(x) is constructed as follows: According to the generalized vegetation cover based on h(x), the power function based on the generalized vegetation cover is obtained as follows: Among them, x max is the maximum value of the characteristic ratio exponent x; n is the characteristic power to be determined, n>0.

4. The superposition fusion method according to any one of claims 1 and 2, characterized in that: The power function based on the generalized vegetation cover is constructed according to the linear transformation function and the virtual minimum, including: The normalized index NdhI corresponding to the linear transformation function h(x) is: According to the normalized index NdhI and the virtual minimum value, the generalized vegetation cover based on NdhI is constructed as follows: According to the generalized vegetation cover based on NdhI, the power function based on the generalized vegetation cover is obtained as follows: Among them, x max is the maximum value of the characteristic ratio exponent x; n is the characteristic power to be determined, n>0.

5. The superposition fusion method according to any one of claims 1 and 2, characterized in that: The power function based on the generalized vegetation cover is constructed according to the linear transformation function and the virtual minimum, including: According to the linear transformation function and the virtual minimum, the generalized vegetation cover based on h(x) is constructed as follows: The normalized index NdhI corresponding to the linear transformation function h(x) is: According to the normalized index NdhI and the virtual minimum value, the generalized vegetation cover based on NdhI is constructed as follows: According to the generalized vegetation cover based on h(x) and the generalized vegetation cover based on NdhI, the power function based on the average value of the two generalized vegetation covers is obtained as follows: Among them, x max is the maximum value of the characteristic ratio index x; n is the characteristic power to be determined, n>0; M(x) is a power function constructed based on generalized vegetation cover.

6. The superposition fusion method according to any one of claims 1 and 2, characterized in that: The power function based on the generalized vegetation cover is constructed according to the linear transformation function and the virtual minimum, including: According to the linear transformation function and the virtual minimum, the generalized vegetation cover based on h(x) is constructed as follows: The normalized index NdhI corresponding to the linear transformation function h(x) is: According to the normalized index NdhI and the virtual minimum value, the generalized vegetation cover based on NdhI is constructed as follows: According to the generalized vegetation cover based on h(x) and the generalized vegetation cover based on NdhI, the power function based on the product of the two generalized vegetation covers is: Among them, x max is the maximum value of the characteristic ratio index x; n is the characteristic power to be determined, n>0; P(x) is a power function constructed based on generalized vegetation cover.

7. The superposition fusion method according to any one of claims 1 and 2, characterized in that: According to the principle of superposition enhancement, the red band and the green band are enhanced respectively by using a power function based on generalized vegetation cover with a determined characteristic power, including: R′=[mZ ε (x)+1]R G′=[mZ ε (x)+1]G Among them, R′ and G′ are the enhanced red band and green band respectively, m>0 is the greenness adjustment coefficient, and Z ε (x) is the power function based on generalized vegetation cover to determine the characteristic power, R and G are the red band and green band respectively.

8. The superposition fusion method according to any one of claims 1 and 2, characterized in that: The feature threshold c∈[x mim ,x max ] or feature threshold c∈[x w ,x v ]; where x max is the maximum value of the characteristic ratio index x, x w 、x v These are the thresholds for pure water bodies and pure vegetation determined by human-computer interaction, respectively.

9. A superposition fusion system based on generalized vegetation cover, characterized in that: The system comprises: An acquisition module is used to acquire satellite remote sensing images with near-infrared band, red band, green band and blue band; A calculation module is used to perform spectral fusion of the near-infrared band with one or more bands of the red band, the green band, and the blue band, and calculate a characteristic ratio index using the fused band combination as a numerator and the corresponding band combination before fusion as a denominator; A first construction module is used to construct a linear transformation function according to the characteristic ratio index; The second building block is used to set the virtual minimum value v of the characteristic ratio index min =kx min ; According to the linear transformation function and the virtual minimum, a power function based on generalized vegetation cover is constructed; where k∈[0,1] is a given value, x min is the minimum value of the characteristic ratio index x; A determination module is configured to determine a characteristic power of the power function based on the generalized vegetation cover when the power function value based on the generalized vegetation cover corresponding to the characteristic threshold of the characteristic ratio index is equal to ε; wherein ε is a given value greater than 0 and much less than 1; The fusion module is used to enhance the red and green bands separately according to the principle of superposition enhancement using a power function based on generalized vegetation cover with a determined characteristic power; the enhanced red and green bands are synthesized with the blue band to obtain a true color image after vegetation enhancement; Among them, the linear transformation function satisfies the conditions: h(c) = 1, and: if x > c, then h(x) > 1; if x < c, then h(x) < 1; c is the characteristic threshold of the characteristic ratio index x, and both s and t are constants.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the superposition and fusion method according to any one of claims 1 to 8 is implemented.

Images