CN117392500A - Remote sensing image characteristic enhancement method and system for trees and crops - Google Patents
Remote sensing image characteristic enhancement method and system for trees and crops Download PDFInfo
- Publication number
- CN117392500A CN117392500A CN202311697971.1A CN202311697971A CN117392500A CN 117392500 A CN117392500 A CN 117392500A CN 202311697971 A CN202311697971 A CN 202311697971A CN 117392500 A CN117392500 A CN 117392500A
- Authority
- CN
- China
- Prior art keywords
- image
- enhancement
- remote sensing
- trees
- images
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 86
- 230000003595 spectral effect Effects 0.000 claims abstract description 75
- 230000004927 fusion Effects 0.000 claims abstract description 45
- 230000002708 enhancing effect Effects 0.000 claims abstract description 15
- 230000004069 differentiation Effects 0.000 claims abstract description 7
- 238000002310 reflectometry Methods 0.000 claims description 60
- 238000001228 spectrum Methods 0.000 claims description 52
- 238000012937 correction Methods 0.000 claims description 28
- 230000009466 transformation Effects 0.000 claims description 21
- 238000011426 transformation method Methods 0.000 claims description 19
- 230000005540 biological transmission Effects 0.000 claims description 16
- 230000015572 biosynthetic process Effects 0.000 claims description 9
- 238000003786 synthesis reaction Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 7
- 238000012952 Resampling Methods 0.000 claims description 6
- 239000003054 catalyst Substances 0.000 claims description 6
- 238000007499 fusion processing Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000002093 peripheral effect Effects 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 4
- 238000012892 rational function Methods 0.000 claims description 4
- 230000001131 transforming effect Effects 0.000 claims description 4
- 239000003086 colorant Substances 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000005316 response function Methods 0.000 claims description 3
- 238000012550 audit Methods 0.000 description 24
- 238000001914 filtration Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 8
- 241000209140 Triticum Species 0.000 description 6
- 235000021307 Triticum Nutrition 0.000 description 6
- 230000008901 benefit Effects 0.000 description 6
- 238000011160 research Methods 0.000 description 5
- 238000010276 construction Methods 0.000 description 4
- 235000013399 edible fruits Nutrition 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 241000209094 Oryza Species 0.000 description 3
- 235000007164 Oryza sativa Nutrition 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 235000009566 rice Nutrition 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000010521 absorption reaction Methods 0.000 description 2
- 238000009792 diffusion process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007500 overflow downdraw method Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000002689 soil Substances 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 208000003643 Callosities Diseases 0.000 description 1
- 241000371652 Curvularia clavata Species 0.000 description 1
- 206010020649 Hyperkeratosis Diseases 0.000 description 1
- 241000209504 Poaceae Species 0.000 description 1
- 240000008042 Zea mays Species 0.000 description 1
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 1
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 235000005822 corn Nutrition 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
- G06V10/806—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/54—Extraction of image or video features relating to texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
Abstract
The invention provides a remote sensing image characteristic enhancement method and a remote sensing image characteristic enhancement system for trees and crops, which specifically comprise the following steps: s1: constructing a target image; s2: spectral feature enhancement; s3: enhancing texture features; s4: the spectral and textural features enhance fusion. The invention realizes the differentiation of different types of crops or trees.
Description
Technical Field
The invention belongs to the technical field of power transmission and transformation engineering observation, and particularly relates to a remote sensing image characteristic enhancement method and system for trees and crops.
Background
Engineering settlement auditing is an important means for auditing institutions to comprehensively examine the authenticity and legality of engineering settlement. The investment amount of the power transmission and transformation project is large, the construction period is long, and the method has important influence on social folk life and power grid safety, and is always the key point of audit attention. The power transmission and transformation engineering path is long, and the audit objects are numerous along the line. The current engineering settlement audit is a post-audit mode, audit content verification is mainly manually confirmed and reported by means of consulting data, visiting and the like, and audit objects such as crops, trees, house conditions to be removed, actual line length, temporary building and the like before line construction cannot be accurately calculated, so that timeliness and accuracy are lacked. The remote sensing technology has the advantages of large detection range, high data acquisition speed, short period, objectivity and quantification and the like, can timely and effectively acquire audit contents in the power transmission and transformation construction process, and also provides effective data support for post settlement audit to post audit. Meanwhile, the audit content information acquisition not only involves a large range, but also identifies fine content (such as crop types and quantity), and the characteristic enhancement of audit objects based on remote sensing images is helpful for distinguishing audit objects of different types, so that higher requirements are also put forward on the characteristic enhancement technology.
The image enhancement technology mainly adopts a spectral feature enhancement method and a texture feature enhancement method, and aims to improve the visual interpretation performance of remote sensing images, specifically highlight and strengthen the features of different ground features and realize differentiation.
Because the remote sensing data has a large number of spectrum bands, abundant information is provided for solving the ground objects, and meanwhile, redundant information and complexity of data processing are brought, the characteristic optimization of the spectrum image is very critical, and the differential research of the spectrum characteristics of different ground objects is also an important means for identifying and distinguishing different ground objects. Common spectral features include parameters such as spectral slope, spectral absorption index, spectral absorption area, etc., and in order to more highlight the differences of different features between spectral images, processing needs to be performed by using different expression characteristics of the spectral features so as to improve the identifiability of the spectral images, and common algorithms include a spectral derivative and an envelope removal algorithm.
Remote sensing image enhancement methods based on texture features can be basically divided into two types of methods based on a spatial domain and based on a transform domain at present:
1) The remote sensing image enhancement method based on the spatial domain mainly realizes image enhancement by operating the gray level of the pixel point of the original remote sensing image in the spatial domain according to a certain criterion. The method can be mainly divided into gray level conversion, histogram processing, spatial filtering and the like, and concretely comprises gray level stretching, histogram equalization, anti-sharpening masking and the like, wherein the method can improve the contrast of the remote sensing image to a certain extent, but has the phenomenon of noise amplification, and has an unsatisfactory effect of enhancing the detail information of the remote sensing image;
2) The remote sensing image enhancement method based on the transformation domain generally decomposes the remote sensing image through wavelet, curvelet, contourlet, shearlet and other transformation, then utilizes the image enhancement technology based on the spatial domain to respectively enhance the decomposed high and low frequency components, and finally obtains the final enhancement result through inverse transformation. The method can enhance the detail information such as edges and the like, inhibit the interference information such as noise and the like, and improve the interpretability of the remote sensing image; compared with a method based on a spatial domain, the method can effectively enhance the detail information of the remote sensing image, but the subjective visual effect is possibly unsatisfactory, and subjective and objective evaluation is inconsistent.
Feature enhancement studies on remote sensing images currently have different feature enhancement methods by performing feature enhancement on different types of ground objects, such as studies on water bodies, buildings and vegetation, but lack studies on achieving feature enhancement on the fusion texture and spectral features of trees and crops and types thereof.
Disclosure of Invention
Aiming at the technical problems, the invention adopts the following technical scheme:
a method of remote sensing image feature enhancement for trees and crops, the method comprising:
s1: constructing a target image: preprocessing a remote sensing image to obtain a real reflectivity image, and cutting out an area containing trees and crops to obtain target reflectivity images of different trees and crops as target images;
s2: spectral feature enhancement: carrying out spectral feature enhancement on the target image by combining a spectral derivative method and a band operation method to obtain a spectral feature enhancement fusion image;
s3: texture feature enhancement: respectively carrying out texture feature enhancement on different crop types and different tree types of the target image by using two filters to obtain two texture feature enhancement images of different crop types and different tree types;
s4: spectral and texture feature enhancement fusion: and fusing the spectral feature enhanced fused image and the two texture feature enhanced images by using an HSV transformation method to obtain fused feature enhanced images of different tree types and different crop types.
Further, step S1 includes:
s101: fusing the full-color image and the multispectral image in the remote sensing image to obtain a fused remote sensing reflectivity image;
s102: constructing RPC of the fused image according to the rational polynomial coefficient RPC of the full-color image, and carrying out orthographic correction on the fused remote sensing reflectivity image to obtain the fused orthographic image;
s103: atmospheric correction is carried out on the fused orthographic image, and a fused real reflectivity image is obtained;
s104: and superposing a power transmission and transformation engineering line vector in the real reflectivity image, searching a typical target with different trees or different crop types around the peripheral area where the line vector is positioned, and cutting a target area in the real reflectivity image to obtain a target reflectivity image with different trees or crop types.
Further, step S2 includes:
s201: performing spectral characteristic enhancement on the target reflectivity image by utilizing a spectral derivative method to obtain a spectral third-order derivative characteristic enhancement image;
s202: calculating normalized vegetation index NDVI for the band combination of the band 5 and the band 7 of the target reflectivity image to obtain an NDVI band;
s203: and performing RGB color synthesis on the wave band 8 of the spectrum third-order derivative characteristic enhancement image, the NDVI wave band and the wave band 5 of the spectrum third-order derivative characteristic enhancement image to obtain a spectrum characteristic enhancement fusion image.
Further, the two filters are respectively a Sobel filter and a Roberts filter.
Further, step S3 includes:
s301: performing texture feature enhancement on target reflectivity images with different crop types by using a Sobel filter to obtain a Sobel texture feature enhanced image for crops;
s302: and performing texture feature enhancement on the target reflectivity images with different tree types by using a Roberts filter to obtain a Roberts texture feature enhanced image aiming at the tree.
Further, step S4 includes:
s401: the HSV transformation method is used for fusing the spectrum characteristic enhancement fusion image and the Sobel texture characteristic enhancement image which are synthesized by RGB color, so as to obtain characteristic enhancement fusion images aiming at different crop types;
s402: and fusing the spectral feature enhancement fused image and the Roberts texture feature enhancement image which are synthesized by RGB color by utilizing an HSV transformation method to obtain feature enhancement fused images aiming at different tree types.
Further, in step S102, the orthographic correction is performed, including:
establishing a platform relationship among the sensor, the image and the ground by combining a ground control point with a camera or a satellite model, and establishing a correction formula to generate a multi-center projection plane orthographic image;
and carrying out orthographic correction on the fused remote sensing image based on the high-precision digital elevation model DEM data by adopting a remote sensing image orthographic correction tool according to the RPC file and the rational function model of the remote sensing satellite data.
Further, in step S103, atmospheric correction is performed, including:
the apparent reflectivity is converted into the earth surface reflectivity which can reflect the earth surface real information, the spectrum information of the orthographic image is automatically collected from the image by adopting a rapid atmospheric correction tool, and the fused orthographic image is corrected by combining DEM data and a spectrum response function.
Further, in step S201, spectral feature enhancement is performed, including:
and carrying out derivative processing on 8 spectral images of the target reflectivity image, and calculating a third-order derivative of a spectrum, wherein the calculation formula is as follows:
wherein,represent the firstiSpectral reflectance of individual bands, +.>Representation->，/>Represent the firstiEach band.
Further, in step S202:
the formula for normalizing the vegetation index is as follows:
。
further, in step S301:
the Sobel filter extracts texture detail information of the image by using a Sobel differential operator, and superimposes the detail information on the original image to realize image texture feature enhancement, wherein the expression of the Sobel differential operator is as follows
Wherein, in the formula;
wherein, in the above formula, the catalyst,f(x,y) Representing the pixel currently to be processed,xindicating that the pixel is inThe line number in the image is given by the line number,yrepresenting the column number of the picture element in the image,representing the image at @x,y) A convolution template with the position pixels in the horizontal direction,representing the image at @x,y) And a convolution template with position pixels in the vertical direction.
Further, in step S302:
the Roberts filter extracts texture detail information of the image by using a Roberts cross differential operator, and superimposes the detail information on the original image to realize image texture feature enhancement; the Roberts cross differentiation operator expression is as follows:
wherein, in the above formula, the catalyst,f(x,y) Representing the pixel currently to be processed,xfor the row number of the picture element in the image,yis the column number of the picture element in the image.
Further, in step S401, the fusion process using the HSV transformation method is as follows:
s4011: transforming HSV color space aiming at spectrum characteristic enhancement fusion images of different crop types through RGB color synthesis to obtain three bands of color brightness value bands, chromaticity and saturation, and replacing the color brightness value bands with Sobel texture characteristic enhancement images;
s4012: resampling two wave bands of chromaticity and saturation into a Sobel texture feature enhanced image by adopting a cubic convolution interpolation method to obtain a first resampled image;
s4013: and converting the first resampled image back to the RGB color space to obtain the fusion characteristic enhanced image aiming at different crop types.
Further, in step S402, the fusion process using the HSV transformation method is as follows:
s4021: transforming HSV color space by using spectral feature enhancement fusion images synthesized by RGB colors aiming at different tree types to obtain three bands of color brightness value bands, chromaticity and saturation, and replacing the color brightness value bands by using Roberts texture feature enhancement images;
s4022: resampling two wave bands of chromaticity and saturation into the Roberts texture feature enhanced image by adopting a cubic convolution interpolation method to obtain a second resampled image;
s4023: and converting the second resampled image back to the RGB color space to obtain the fusion characteristic enhanced image aiming at different tree types.
The invention also provides a remote sensing image characteristic enhancement system for trees and crops, which comprises:
the target image constructing module is configured to preprocess the remote sensing image to obtain a real reflectivity image, and cut out an area containing trees and crops to obtain target images of different trees and crop types;
the spectral feature enhancement module is configured to perform spectral feature enhancement on the target image by combining a spectral derivative method and a band operation method to obtain a spectral feature enhancement fusion image;
the texture feature enhancement method module is configured to respectively carry out texture feature enhancement on different crop types and different tree types of the target image by utilizing two filters to obtain two texture feature enhancement images of different crop types and different tree types;
the spectrum and texture feature enhancement fusion module is configured to fuse the spectrum feature fusion image and the two texture feature enhancement images by using an HSV transformation method to obtain fusion feature enhancement images of different tree types and different crop types.
Further, the implementation steps of constructing the target image module are as follows:
fusing the full-color image and the multispectral image in the remote sensing image to obtain a fused remote sensing reflectivity image;
constructing RPC of the fused image according to rational polynomial parameters RPC of the full-color image, and carrying out orthographic correction on the fused remote sensing image to obtain the fused orthographic image;
atmospheric correction is carried out on the fused orthographic image, and a fused real reflectivity image is obtained;
and superposing a power transmission and transformation engineering line vector in the real reflectivity image, searching a typical target with different trees or different crop types in the peripheral area of the line vector, and cutting a target area in the real reflectivity image to obtain a target reflectivity image with different trees or crop types.
Compared with the prior art, the remote sensing image characteristic enhancement method and system for the trees and the crops, provided by the invention, realize advantage complementation by combining the texture characteristic enhancement and the spectrum characteristic enhancement, fully utilize the advantages of the texture characteristic enhancement and the spectrum characteristic enhancement for different crops and trees, respectively select the characteristic enhancement method suitable for the crops and the trees, realize the differentiation of different types of crops or trees, highlight the spectrum characteristic difference and the texture characteristic difference of different trees and crops, realize the enhancement of detail information to different degrees aiming at different types, thereby realizing the effect of differentiating different crops and trees and types thereof, effectively enhancing the detail information such as edges, textures and the like, and further improving the interpretability of the remote sensing image.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention may be realized and attained by the structure particularly pointed out in the written description and drawings.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, a brief description will be given below of the drawings required for the embodiments or the prior art descriptions, and it is obvious that the drawings in the following description are some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 shows a flow chart of a remote sensing image feature enhancement method for trees and crops in accordance with an embodiment of the present invention;
FIG. 2 shows a comparison of feature enhanced fusion results for different trees in accordance with an embodiment of the present invention;
FIG. 3 shows a comparison of characteristic enhanced fusion results for different crops in accordance with an embodiment of the present invention;
fig. 4 shows a schematic structural diagram of a remote sensing image feature enhancement system for trees and crops according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Because of the complexity of the power transmission and transformation engineering environment, the audit objects and various ground objects exist in a mixed mode, intelligent identification of the audit objects is difficult, and the characteristic enhancement technology can remarkably improve the quality of interpretation of different audit objects of the remote sensing image. At present, the characteristic enhancement methods such as texture and spectrum are more and mature, but in the aspect of power transmission and transformation engineering application, the characteristic enhancement research for audit objects in the power transmission and transformation engineering is still lacking. Aiming at audit contents such as types and numbers of trees or crops (including corns, wheat and the like) required to be acquired in the audit process of power transmission and transformation engineering, audit settlement standards of different crops or types of trees are different, but visual distinction of different trees or types of crops on satellite images is difficult, so that feature enhancement is required to be carried out on different trees and crops and types thereof on the satellite images so as to distinguish, and meanwhile, the scientificity and the accuracy of tree crop audit are improved.
However, the existing feature enhancement technology performs unified feature enhancement on all objects in the whole image from macroscopic view, lacks pertinence, is less likely to establish a suitable feature enhancement method for specific targets, and particularly lacks attention for trees and crops, and the feature enhancement technology for distinguishing fine features and types of audit objects is not yet related, particularly the related technology for feature enhancement in the aspect of fine scale of distinguishing different tree types and crop types and types thereof is not yet available.
In addition, for the remote sensing image with high spatial resolution (better than 1 meter), because the remote sensing image contains abundant detail information, the spatial heterogeneity of pixels in the image is greatly enhanced, so that a learner considers the characteristic difference among vegetation, water, buildings and other ground features in the image to perform characteristic enhancement processing on the information such as spectrum, shape, texture and the like of the ground features in the image, but the remote sensing image is mostly concentrated in different ground feature types, and less research is conducted in the field of the refined type aiming at different types of the same ground features, such as different types of trees and different types of crops.
Based on the above, the invention provides a remote sensing image feature enhancement method for different trees and crops, provides a corresponding feature enhancement method, and realizes effective differentiation of the trees and crops and different types thereof so as to provide feature enhancement image samples for intelligent recognition of subsequent audit objects, thereby improving remote sensing interpretation capability, and provides a remote sensing image feature enhancement system for different trees and crops so as to realize the remote sensing image feature enhancement method for different trees and crops. The remote sensing image characteristic enhancement method for different trees and crops is described below.
As shown in fig. 1, the present invention provides a method for enhancing the characteristics of remote sensing images of trees and crops, the method comprising:
s1: constructing a target image: preprocessing the remote sensing image to obtain a real reflectivity image, cutting out a research area containing trees and crops, and obtaining target reflectivity images of different trees and crops as target images.
S2: spectral feature enhancement: and carrying out spectral feature enhancement on the target image by combining a spectral derivative method and a band operation method to obtain a spectral feature fusion image.
S3: texture feature enhancement: and respectively carrying out texture feature enhancement on different crop types and different tree types of the target image by using two filters (namely a Sobel filter and a Roberts filter respectively) to obtain two texture feature enhanced images of different crop types and different tree types.
S4: spectral and texture feature enhancement fusion: and fusing the spectral feature enhanced fused image and the two texture feature enhanced images by using an HSV transformation method to obtain fused feature enhanced images of different tree types and different crop types.
Steps S1 to S4 are described in detail below.
In some embodiments of the invention, step S1 comprises:
s101: and fusing the full-color image and the multispectral image in the remote sensing image by utilizing an NNDiffuse (Nearest Neighbor Diffusion, nearest diffusion) fusion method to obtain a fused remote sensing reflectivity image.
S102: constructing RPC of the fused image according to rational polynomial parameters RPC of the full-color image, and carrying out orthographic correction on the fused remote sensing reflectivity image to obtain the fused orthographic image; wherein, the step of orthographic correction comprises the following steps:
establishing 3 platform relations among the sensor, the image and the ground by combining a ground control point with a camera or a satellite model, and establishing a correction formula to generate a multi-center projection plane orthographic image;
and adopting a remote sensing image orthographic correction tool to orthographic correct the fused remote sensing image based on high-precision digital elevation model (Digital Elevation Model, DEM) data according to RPC (Rational polynomial coefficient ) files and rational function models (Rational Function model, RFM) of remote sensing satellite data.
S103: atmospheric correction is carried out on the fused orthographic image, and a fused real reflectivity image is obtained; wherein, carry out the atmospheric correction, include:
the apparent reflectivity is converted into the earth surface reflectivity which can reflect the earth surface real information, the spectrum information of the orthographic image is automatically collected from the image by adopting a rapid atmospheric correction tool (QUick Atmospheric Correction, QUAC), and the fused orthographic image is corrected by combining DEM data and a spectrum response function.
S104: and superposing a power transmission and transformation engineering line vector in the real reflectivity image, searching a typical target with different trees or different crop types in a peripheral area where the line vector is positioned, and cutting a target area in the real reflectivity image to obtain a target reflectivity image with different trees or crop types.
In some embodiments of the invention, step S2 comprises:
s201: spectral derivative method: performing spectral characteristic enhancement on the target reflectivity image by utilizing a spectral derivative method to obtain a spectral third-order derivative characteristic enhancement image; wherein the performing spectral feature enhancement comprises:
the spectral derivative method is based on mathematical differential derivatives, performs derivative processing on 8 spectral images of the target reflectivity image, calculates spectral third-order derivatives, wherein,
the third derivative of the spectrum is calculated as follows:
wherein,represent the firstiSpectral reflectance of individual bands, +.>Representation->，/>Represent the firstiEach band.
S202: algebraic algorithm: calculating a normalized vegetation index (Normalized Difference Vegetation Index, NDVI) of the image: calculating the NDVI of the band combination of the band 5 (red band) and the band 7 (near infrared band) of the target reflectivity image to obtain an NDVI image; the calculation formula of the normalized vegetation index NDVI is as follows:
the crop characteristics in the NDVI images are obviously enhanced, and the coverage of trees can be well distinguished and the growth conditions of different trees can be monitored.
S203: band synthesis RGB image: the three bands of the band 8 (near infrared band, center wavelength 908 nm), the NDVI band and the band 5 (red band, center wavelength 658.8 nm) of the spectrum third-order derivative characteristic enhancement image are subjected to RGB color synthesis to obtain a spectrum characteristic enhancement fusion image after RGB color synthesis, the spectrum characteristic enhancement image can obviously distinguish trees and crops, the spectrum color level is rich, and the characteristics of different tree coverage and the growth level of different crops can be captured.
In some embodiments of the present invention, step S3 includes:
s301: sobel filtering: performing texture feature enhancement on target reflectivity images with different crop types by using a Sobel filter to obtain a Sobel texture feature enhanced image for crops; the Sobel filter utilizes a Sobel differential operator to realize the enhancement of the texture characteristics of the image, the Sobel differential operator adopts the full-direction differential under a 3X 3 template, and the Sobel differential operator expression is as follows
Wherein, in the formula;
wherein, in the above formula, the catalyst,f(x,y) Representing the pixel currently to be processed,xrepresenting the row number of the picture element in the image,yrepresenting the column number of the picture element in the image,representing the image at @x,y) A convolution template with the position pixels in the horizontal direction,representing the image at @x,y) And a convolution template with position pixels in the vertical direction.
S302: roberts filtering: and performing texture feature enhancement on the target reflectivity images with different tree types by using a Roberts filter to obtain a Roberts texture feature enhanced image aiming at the tree. The Roberts filter utilizes a Roberts operator to realize image texture feature enhancement, the Roberts operator is a cross differential operator, and the calculation of sharpening differential is considered from two cross directions, and the calculation formula is as follows:
wherein, in the above formula, the catalyst,f(x,y) Representing the current pixel to be processed, x is the row number of the pixel in the image, and y is the column number of the pixel in the image.
Comparing the texture enhancement effects of Sobel filtering and Robert filtering on different crops and tree types, analyzing and displaying that the local texture feature enhancement of the Sobel filtering result is finer and the detail of the texture feature is richer compared with that of the Roberts filtering result; roberts filtering reduces the edge outline well for different tree types, and the texture feature enhancement result and the degree of distinction are relatively better for different tree types; the Sobel filtering has better texture enhancement effect and differentiation degree on different crop types.
In some embodiments of the invention, step S4 comprises:
s401: characteristic enhancement of different crop types: the HSV transformation method is used for fusing the spectrum characteristic enhanced image and the Sobel texture characteristic enhanced image which are synthesized by RGB color, so as to obtain characteristic enhanced images aiming at different crop types; in this step, the fusion process using HSV transformation is as follows:
s4011: the HSV color space is transformed by the spectrum characteristic enhanced image synthesized by RGB color aiming at different crop types to obtain three wave bands of color brightness value wave bands, chromaticity and saturation, and the color brightness value wave bands are replaced by the Sobel texture characteristic enhanced image.
S4012: resampling two wave bands of chromaticity and saturation into the Sobel texture feature enhanced image by adopting a cubic convolution interpolation method to obtain a first resampled image.
S4013: and converting the first resampled image back to the RGB color space to obtain the fusion characteristic enhanced image aiming at different crop types.
In this step, as shown in fig. 2, in fig. 2: a graph a is a target reflectivity image (the image comprises a fruit tree dense region, a fruit tree sparse region, bare soil, rice and wheat) of different trees, wherein the different tree types are respectively in the fruit tree dense region and the fruit tree sparse region in the graph a of fig. 2; b, the image is a spectrum characteristic enhancement fusion image of the image after spectrum characteristic enhancement and RGB color synthesis; c, the image is a Sobel texture feature enhanced image of the image a after the texture feature enhancement by a Sobel filter; and d, the image b and the image c are fused by an HSV transformation method to form a fusion characteristic enhanced image. As can be seen from fig. 2, the combination of the spectrum and the texture enhancement method has the texture of the tree and also has the spectrum difference of different features. Compared with a single spectral feature enhancement result or a single texture feature enhancement result, the image combined with the texture feature enhancement result can better depict the edges and texture features of different trees, the trees and bare soil can be better distinguished, and the spectral differences of different types of crops are reserved.
S402: feature enhancement for different tree types: the HSV transformation method is used for fusing the spectrum characteristic enhancement fusion image and the Roberts texture characteristic enhancement image which are synthesized by RGB color, so that fusion characteristic enhancement images aiming at different tree types are obtained; in this step, the fusion process using HSV transformation is as follows:
s4021: the HSV color space is transformed by the spectral feature enhancement fusion image synthesized by RGB color aiming at different tree types to obtain three bands of color brightness value bands, chromaticity and saturation, and the color brightness value bands are replaced by the Roberts texture feature enhancement image.
S4022: and resampling the two wave bands of the chromaticity and the saturation into the Roberts texture feature enhanced image by adopting a cubic convolution interpolation method to obtain a second resampled image.
S4023: and converting the second resampled image back to the RGB color space to obtain the fusion characteristic enhanced image aiming at different tree types.
In this step, as shown in fig. 3, in fig. 3: a graph a is a target reflectivity image (the image comprises grasslands, rice and wheat) of different crops, wherein the types of the different crops are respectively rice and wheat in the graph a of fig. 3; b, the image is a spectrum characteristic enhancement fusion image of the image after spectrum characteristic enhancement and RGB color synthesis; c, the picture is a Roberts texture feature enhanced image of the picture a after the texture feature enhancement by a Roberts filter; and d, the image b and the image c are fused by an HSV transformation method to form a fusion characteristic enhanced image. As can be seen from fig. 3, the combination of spectral and textural enhancement results better delineate the edges and textural features of different crops, better distinguish crops from grasses, and preserve the spectral differences of different types of crops, compared to the spectral feature enhancement results alone or the textural feature enhancement results alone. For example, dark black rice has rough texture characteristics, is more convenient to identify, and has enhanced spectrum and texture characteristics; the grasslands with grey white color have clearer edges and more obvious distinction from wheat compared with the independent spectral characteristic enhancement results or the independent texture characteristic enhancement results; the different growth states of the wheat surface correspond to different spectral colors, so that the fused result can be seen to keep different growth conditions of crops.
In another aspect, as shown in fig. 4, the present invention further provides a remote sensing image feature enhancement system for trees and crops, where the system includes:
and the construction target image module is configured to preprocess the remote sensing image to obtain a real reflectivity image, and cut out a research area containing trees and crops to obtain target images of different trees and crop types.
And the spectral characteristic enhancement module is configured to perform spectral characteristic enhancement on the target image by combining a spectral derivative method and a band operation method to obtain a spectral characteristic fusion image.
The texture feature enhancement method module is configured to respectively carry out texture feature enhancement on different crop types and different tree types of the target image by utilizing two filters to obtain two texture feature enhancement images of different crop types and different tree types.
The spectrum and texture feature enhancement fusion module is configured to fuse the spectrum feature fusion image and the two texture feature enhancement images by using an HSV transformation method to obtain feature enhancement images of different tree types and different crop types.
The functions and the implementation manners of the modules in the remote sensing image characteristic enhancement system for trees and crops are corresponding to the other functions and the implementation manners of the steps in the remote sensing image characteristic enhancement method for trees and crops, so that the detailed description is omitted.
In summary, the invention provides a remote sensing image characteristic enhancement method specially aiming at trees and crops in an audit object and provides different characteristic enhancement methods respectively applicable to the trees and the crops aiming at the identification and characteristic enhancement fields of the audit object in power transmission and transformation engineering. The characteristic enhancement method combines the spectrum and texture characteristic enhancement method, and realizes the characteristic enhancement of the textures and spectrums of trees and crops.
The invention also provides a spectral characteristic enhancement fusion method combining a spectral third-order derivative method and a normalized vegetation index method, which constructs RGB color synthesized images, realizes the enhancement of the spectral characteristic of different trees, crops and the types thereof, and can capture the characteristics of different tree coverage and the growth levels of different crops; meanwhile, on the basis of obtaining the spectrum characteristic enhancement image, the spectrum characteristic enhancement image and the corresponding texture characteristic enhancement image are fused by an HSV transformation method, so that the characteristic enhancement image aiming at different crops and tree types is obtained, and the edge and texture characteristics are enhanced while the spectrum characteristics are maintained.
In addition, it is to be understood that the remote sensing image characteristic enhancement method for trees and crops provided by the invention is not only applicable to the characteristic enhancement of trees and crops in the application field of power transmission and transformation engineering, but also applicable to the characteristic enhancement of trees and crops in the application field except the power transmission and transformation engineering.
The present invention is not limited to the above-mentioned embodiments, but is not limited to the above-mentioned embodiments, and any simple modification, equivalent changes and modification made to the above-mentioned embodiments according to the technical matters of the present invention can be made by those skilled in the art without departing from the scope of the present invention.
Claims (16)
1. A method for enhancing the characteristics of remote sensing images of trees and crops, the method comprising:
s1: constructing a target image: preprocessing a remote sensing image to obtain a real reflectivity image, and cutting out an area containing trees and crops to obtain target reflectivity images of different trees and crops as target images;
s2: spectral feature enhancement: carrying out spectral feature enhancement on the target image by combining a spectral derivative method and a band operation method to obtain a spectral feature enhancement fusion image;
s3: texture feature enhancement: respectively carrying out texture feature enhancement on different crop types and different tree types of the target image by using two filters to obtain two texture feature enhancement images of different crop types and different tree types;
s4: spectral and texture feature enhancement fusion: and fusing the spectral feature enhanced fused image and the two texture feature enhanced images by using an HSV transformation method to obtain fused feature enhanced images of different tree types and different crop types.
2. The method for enhancing features of remote sensing images for trees and crops as claimed in claim 1, wherein step S1 comprises:
s101: fusing the full-color image and the multispectral image in the remote sensing image to obtain a fused remote sensing reflectivity image;
s102: constructing RPC of the fused image according to the rational polynomial coefficient RPC of the full-color image, and carrying out orthographic correction on the fused remote sensing reflectivity image to obtain the fused orthographic image;
s103: atmospheric correction is carried out on the fused orthographic image, and a fused real reflectivity image is obtained;
s104: and superposing a power transmission and transformation engineering line vector in the real reflectivity image, searching a typical target with different trees or different crop types around the peripheral area where the line vector is positioned, and cutting a target area in the real reflectivity image to obtain a target reflectivity image with different trees or crop types.
3. The method for enhancing the remote sensing image characteristics of trees and crops according to claim 1 or 2, wherein the step S2 comprises:
s201: performing spectral characteristic enhancement on the target reflectivity image by utilizing a spectral derivative method to obtain a spectral third-order derivative characteristic enhancement image;
s202: calculating normalized vegetation index NDVI for the band combination of the band 5 and the band 7 of the target reflectivity image to obtain an NDVI band;
s203: and performing RGB color synthesis on the wave band 8 of the spectrum third-order derivative characteristic enhancement image, the NDVI wave band and the wave band 5 of the spectrum third-order derivative characteristic enhancement image to obtain a spectrum characteristic enhancement fusion image.
4. The method of claim 1 or 2, wherein the two filters are respectively a Sobel filter and a Roberts filter.
5. The method for enhancing features of remote sensing images for trees and crops as claimed in claim 4, wherein step S3 comprises:
s301: performing texture feature enhancement on target reflectivity images with different crop types by using a Sobel filter to obtain a Sobel texture feature enhanced image for crops;
s302: and performing texture feature enhancement on the target reflectivity images with different tree types by using a Roberts filter to obtain a Roberts texture feature enhanced image aiming at the tree.
6. The method for enhancing features of remote sensing images for trees and crops as claimed in claim 5, wherein step S4 comprises:
s401: the HSV transformation method is used for fusing the spectrum characteristic enhancement fusion image and the Sobel texture characteristic enhancement image which are synthesized by RGB color, so as to obtain characteristic enhancement fusion images aiming at different crop types;
s402: and fusing the spectral feature enhancement fused image and the Roberts texture feature enhancement image which are synthesized by RGB color by utilizing an HSV transformation method to obtain feature enhancement fused images aiming at different tree types.
7. The method of claim 2, wherein in step S102, performing orthographic correction comprises:
establishing a platform relationship among the sensor, the image and the ground by combining a ground control point with a camera or a satellite model, and establishing a correction formula to generate a multi-center projection plane orthographic image;
and carrying out orthographic correction on the fused remote sensing image based on the high-precision digital elevation model DEM data by adopting a remote sensing image orthographic correction tool according to the RPC file and the rational function model of the remote sensing satellite data.
8. The method of claim 2, wherein in step S103, performing atmospheric correction comprises:
the apparent reflectivity is converted into the earth surface reflectivity which can reflect the earth surface real information, the spectrum information of the orthographic image is automatically collected from the image by adopting a rapid atmospheric correction tool, and the fused orthographic image is corrected by combining DEM data and a spectrum response function.
9. A method for enhancing features of remote sensing images for trees and crops according to claim 3, wherein in step S201, spectral feature enhancement is performed, comprising:
and carrying out derivative processing on 8 spectral images of the target reflectivity image, and calculating a third-order derivative of a spectrum, wherein the calculation formula is as follows:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Represent the firstiSpectral reflectance of individual bands, +.>Representation->，/>Represent the firstiEach band.
10. A method for enhancing features of remote sensing images for trees and crops according to claim 3, wherein in step S202:
the formula for normalizing the vegetation index is as follows:
。
11. the method for enhancing features of remote sensing images for trees and crops according to claim 5, wherein in step S301:
the Sobel filter extracts texture detail information of the image by using a Sobel differential operator, and superimposes the detail information on the original image to realize image texture feature enhancement, wherein the expression of the Sobel differential operator is as follows
The method comprises the steps of carrying out a first treatment on the surface of the Wherein, in the formula;
the method comprises the steps of carrying out a first treatment on the surface of the Wherein, in the above formula, the catalyst,f(x,y) Representing the pixel currently to be processed,xrepresenting the row number of the picture element in the image,yrepresenting the column number of the picture element in the image,representing the image at @x,y) Convolution template with position pixels in horizontal direction, +.>Representing the image at @x,y) And a convolution template with position pixels in the vertical direction.
12. The method for enhancing features of remote sensing images for trees and crops according to claim 5, wherein in step S302:
the Roberts filter extracts texture detail information of the image by using a Roberts cross differential operator, and superimposes the detail information on the original image to realize image texture feature enhancement; the Roberts cross differentiation operator expression is as follows:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein, in the above formula, the catalyst,f(x,y) Representing the pixel currently to be processed,xfor the row number of the picture element in the image,yis the column number of the picture element in the image.
13. The method for enhancing features of remote sensing images for trees and crops according to claim 6, wherein in step S401, the fusion process using HSV transformation method is as follows:
s4011: transforming HSV color space aiming at spectrum characteristic enhancement fusion images of different crop types through RGB color synthesis to obtain three bands of color brightness value bands, chromaticity and saturation, and replacing the color brightness value bands with Sobel texture characteristic enhancement images;
s4012: resampling two wave bands of chromaticity and saturation into a Sobel texture feature enhanced image by adopting a cubic convolution interpolation method to obtain a first resampled image;
s4013: and converting the first resampled image back to the RGB color space to obtain the fusion characteristic enhanced image aiming at different crop types.
14. The method for enhancing features of remote sensing images for trees and crops according to claim 6, wherein in step S402, the fusion process using HSV transformation method is as follows:
s4021: transforming HSV color space by using spectral feature enhancement fusion images synthesized by RGB colors aiming at different tree types to obtain three bands of color brightness value bands, chromaticity and saturation, and replacing the color brightness value bands by using Roberts texture feature enhancement images;
s4022: resampling two wave bands of chromaticity and saturation into the Roberts texture feature enhanced image by adopting a cubic convolution interpolation method to obtain a second resampled image;
s4023: and converting the second resampled image back to the RGB color space to obtain the fusion characteristic enhanced image aiming at different tree types.
15. A remote sensing image feature enhancement system for trees and crops, the system comprising:
the target image constructing module is configured to preprocess the remote sensing image to obtain a real reflectivity image, and cut out an area containing trees and crops to obtain target images of different trees and crop types;
the spectral feature enhancement module is configured to perform spectral feature enhancement on the target image by combining a spectral derivative method and a band operation method to obtain a spectral feature enhancement fusion image;
the texture feature enhancement method module is configured to respectively carry out texture feature enhancement on different crop types and different tree types of the target image by utilizing two filters to obtain two texture feature enhancement images of different crop types and different tree types;
the spectrum and texture feature enhancement fusion module is configured to fuse the spectrum feature fusion image and the two texture feature enhancement images by using an HSV transformation method to obtain fusion feature enhancement images of different tree types and different crop types.
16. The remote sensing image feature enhancement system for trees and crops of claim 15, wherein the step of constructing the target image module is performed as follows:
fusing the full-color image and the multispectral image in the remote sensing image to obtain a fused remote sensing reflectivity image;
constructing RPC of the fused image according to rational polynomial parameters RPC of the full-color image, and carrying out orthographic correction on the fused remote sensing image to obtain the fused orthographic image;
atmospheric correction is carried out on the fused orthographic image, and a fused real reflectivity image is obtained;
and superposing a power transmission and transformation engineering line vector in the real reflectivity image, searching a typical target with different trees or different crop types in the peripheral area of the line vector, and cutting a target area in the real reflectivity image to obtain a target reflectivity image with different trees or crop types.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311697971.1A CN117392500B (en) | 2023-12-12 | Remote sensing image characteristic enhancement method and system for trees and crops |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311697971.1A CN117392500B (en) | 2023-12-12 | Remote sensing image characteristic enhancement method and system for trees and crops |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117392500A true CN117392500A (en) | 2024-01-12 |
| CN117392500B CN117392500B (en) | 2024-04-23 |
Family
ID=
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1710445A (en) * | 2005-07-05 | 2005-12-21 | 华东师范大学 | Aeronautical high-spectrum remote-sensing image spectrum zonc noise self-detecting and removing method |
| CN102063710A (en) * | 2009-11-13 | 2011-05-18 | 烟台海岸带可持续发展研究所 | Method for realizing fusion and enhancement of remote sensing image |
| CN109523498A (en) * | 2018-11-06 | 2019-03-26 | 南京农业大学 | A kind of remote sensing image space-time fusion method towards field scale crop growth monitoring |
| CN110309781A (en) * | 2019-07-01 | 2019-10-08 | 中国科学院遥感与数字地球研究所 | Damage remote sensing recognition method in house based on the fusion of multi-scale spectrum texture self-adaption |
| CN112488931A (en) * | 2020-11-04 | 2021-03-12 | 国网浙江省电力有限公司电力科学研究院 | Super-resolution enhancement method and system for power transmission line in satellite remote sensing image |
| CN112800964A (en) * | 2021-01-27 | 2021-05-14 | 中国人民解放军战略支援部队信息工程大学 | Remote sensing image target detection method and system based on multi-module fusion |
| CN113435474A (en) * | 2021-05-25 | 2021-09-24 | 中国地质大学（武汉） | Remote sensing image fusion method based on double-generation antagonistic network |
| CN113706387A (en) * | 2021-09-23 | 2021-11-26 | 重庆市农业科学院 | Method for obtaining remote sensing base map extracted from crops in low hilly areas |
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1710445A (en) * | 2005-07-05 | 2005-12-21 | 华东师范大学 | Aeronautical high-spectrum remote-sensing image spectrum zonc noise self-detecting and removing method |
| CN102063710A (en) * | 2009-11-13 | 2011-05-18 | 烟台海岸带可持续发展研究所 | Method for realizing fusion and enhancement of remote sensing image |
| CN109523498A (en) * | 2018-11-06 | 2019-03-26 | 南京农业大学 | A kind of remote sensing image space-time fusion method towards field scale crop growth monitoring |
| CN110309781A (en) * | 2019-07-01 | 2019-10-08 | 中国科学院遥感与数字地球研究所 | Damage remote sensing recognition method in house based on the fusion of multi-scale spectrum texture self-adaption |
| CN112488931A (en) * | 2020-11-04 | 2021-03-12 | 国网浙江省电力有限公司电力科学研究院 | Super-resolution enhancement method and system for power transmission line in satellite remote sensing image |
| CN112800964A (en) * | 2021-01-27 | 2021-05-14 | 中国人民解放军战略支援部队信息工程大学 | Remote sensing image target detection method and system based on multi-module fusion |
| CN113435474A (en) * | 2021-05-25 | 2021-09-24 | 中国地质大学（武汉） | Remote sensing image fusion method based on double-generation antagonistic network |
| CN113706387A (en) * | 2021-09-23 | 2021-11-26 | 重庆市农业科学院 | Method for obtaining remote sensing base map extracted from crops in low hilly areas |
Non-Patent Citations (4)
| Title |
|---|
| 田晓敏: "中国南方人工林复杂林分机载高光谱树种分类", 《博士电子期刊》, 15 January 2023 (2023-01-15), pages 2 * |
| 胡翔宇等: "数码显微镜硬件与软件的研制", 《光学仪器》, 30 June 2003 (2003-06-30), pages 23 * |
| 金剑;田淑芳;焦润成;高虎;: "基于地物光谱分析的WorldView-2数据岩性识别:以新疆乌鲁克萨依地区为例", 现代地质, no. 02, 15 April 2013 (2013-04-15) * |
| 黄邵东;徐伟恒;吴超;戴杨;寇卫利;: "遥感在茶园监测中的应用研究进展", 西部林业科学, no. 02, 15 April 2020 (2020-04-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10832390B2 (en) | Atmospheric compensation in satellite imagery | |
| Reese et al. | C-correction of optical satellite data over alpine vegetation areas: A comparison of sampling strategies for determining the empirical c-parameter | |
| Goslee | Analyzing remote sensing data in R: the landsat package | |
| Jones et al. | Use of digital terrain data in the interpretation of SPOT-1 HRV multispectral imagery | |
| Leboeuf et al. | A shadow fraction method for mapping biomass of northern boreal black spruce forests using QuickBird imagery | |
| US8712148B2 (en) | Generating agricultural information products using remote sensing | |
| Gonsamo et al. | Improved LAI algorithm implementation to MODIS data by incorporating background, topography, and foliage clumping information | |
| CN108596103A (en) | High resolution ratio satellite remote-sensing image building extracting method based on optimal spectrum Index selection | |
| CN110849814A (en) | Remote sensing image processing method based on multi-source remote sensing satellite | |
| CN112711989B (en) | Corn straw coverage estimation method based on radar remote sensing and optical remote sensing | |
| CN106897707A (en) | Characteristic image time series synthetic method and device based in multi-source points | |
| CN110032963B (en) | Dynamic monitoring method for spartina alterniflora new-born plaques | |
| CN102750701A (en) | Method for detecting spissatus and spissatus shadow based on Landsat thematic mapper (TM) images and Landsat enhanced thematic mapper (ETM) images | |
| CN113436071B (en) | Multi-source satellite remote sensing image mosaic method, system and storage medium | |
| Maynard et al. | Effect of spatial image support in detecting long-term vegetation change from satellite time-series | |
| CN113033279A (en) | Crop fine classification method and system based on multi-source remote sensing image | |
| CN115272860A (en) | Method and system for determining rice planting area, electronic device and storage medium | |
| CN112052757A (en) | Method, device and equipment for extracting information of burned area and storage medium | |
| CN113743303A (en) | Forestry carbon remittance method for forest remote sensing data | |
| CN117392500B (en) | Remote sensing image characteristic enhancement method and system for trees and crops | |
| CN117392500A (en) | Remote sensing image characteristic enhancement method and system for trees and crops | |
| CN116246272A (en) | Cloud and snow distinguishing method for domestic satellite multispectral image quality marks | |
| CN111768101B (en) | Remote sensing cultivated land change detection method and system taking account of physical characteristics | |
| Zheng et al. | Color difference optimization method for multi-source remote sensing image processing | |
| Danoedoro et al. | Combining pan-sharpening and forest cover density transformation methods for vegetation mapping using Landsat-8 Satellite Imagery |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |