CN106204596B - Panchromatic waveband remote sensing image cloud detection method based on Gaussian fitting function and fuzzy mixed estimation - Google Patents
Panchromatic waveband remote sensing image cloud detection method based on Gaussian fitting function and fuzzy mixed estimation Download PDFInfo
- Publication number
- CN106204596B CN106204596B CN201610550554.8A CN201610550554A CN106204596B CN 106204596 B CN106204596 B CN 106204596B CN 201610550554 A CN201610550554 A CN 201610550554A CN 106204596 B CN106204596 B CN 106204596B
- Authority
- CN
- China
- Prior art keywords
- gaussian
- fuzzy
- estimation
- data set
- binary
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 30
- 230000011218 segmentation Effects 0.000 claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 20
- 238000004422 calculation algorithm Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000009826 distribution Methods 0.000 claims description 6
- 238000007476 Maximum Likelihood Methods 0.000 claims description 4
- 230000007797 corrosion Effects 0.000 claims description 4
- 238000005260 corrosion Methods 0.000 claims description 4
- 238000005315 distribution function Methods 0.000 claims description 3
- 238000011430 maximum method Methods 0.000 claims description 2
- 241001270131 Agaricus moelleri Species 0.000 abstract 1
- 238000001914 filtration Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 239000000126 substance Substances 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 239000003550 marker Substances 0.000 description 3
- 238000001308 synthesis method Methods 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000002156 mixing Methods 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 230000010339 dilation Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a panchromatic waveband remote sensing image cloud detection method based on Gaussian fitting function and fuzzy mixed estimation. The method has the advantages that the method can continuously iteratively converge the gray scales of two types of high-brightness patches with long distance to a consistent state by self-adaptive segmentation classification of the gray scale of the panchromatic waveband image and combining a Gaussian fitting function and a fuzzy mixed estimation method, thereby calculating and estimating a cloud detection threshold with more accurate estimation and obviously improving the accuracy, the breadth and the depth of detection.
Description
Technical Field
The invention belongs to the fields of surveying and mapping science and technology, and relates to a panchromatic waveband remote sensing image cloud detection method based on Gaussian fitting function and fuzzy mixed estimation, which is mainly applied to the fields of optical satellite remote sensing data processing and application and the like.
Background
For a long time, the land resource optical satellite image is limited by the influence of cloud, and the wide-range earth observation has a bottleneck. The existence of the cloud area not only covers the ground feature information, but also causes a plurality of influences on the processing of image registration, fusion and the like. Currently, the commonly used cloud detection algorithms mainly include a texture analysis method, a homomorphic filtering method, a multispectral synthesis method and the like. Texture analysis extracts spatial characteristics of cloud regions and non-cloud regions based on a statistical method, large lamellar clouds can be effectively identified, but small rolling clouds with strong textures are difficult to identify. Homomorphic filtering methods are effective in processing a wide range of thin clouds but are not suitable for thick cloud images, and algorithms involve the selection of filters and cut-off frequencies, which can lose some useful information during the filtering process. The multispectral synthesis method utilizes the difference of object reflectivity to distinguish cloud from clear sky, but requires a sensor to be provided with a plurality of thermal infrared bands, detection wavelength needs to cover the absorption band of water or carbon dioxide, is mainly used for medium-resolution imaging instruments, high-level very-high-resolution radiometers and the like, and is not completely suitable for land resource optical satellite images.
The satellite images usually have small volume clouds with rich textures and large-range thick clouds, mainstream high-resolution land resource satellites have fewer wave bands but rich color levels, and a full-color camera and a multi-spectrum camera comprising 4 blue, green, red and near infrared bands are carried on the satellite images generally and are subjected to radiation quantization by adopting 10-12 bits. The panchromatic band image data is high in resolution and is a main data source for satellite remote sensing application, and therefore, the method has important significance in exploring an automatic cloud detection algorithm suitable for a terrestrial resource optical satellite panchromatic band image.
Disclosure of Invention
The invention aims to provide a panchromatic waveband remote sensing image cloud detection method based on a Gaussian fitting function and fuzzy mixed estimation, which can overcome the defects of the existing cloud detection method technology and meet the requirement of efficient and automatic cloud area detection on single panchromatic waveband image data.
The technical scheme of the invention is a panchromatic waveband remote sensing image cloud detection method based on Gaussian fitting function and fuzzy mixed estimation, which comprises the following steps,
step 1, self-adaptive initial binary marking, utilizing an Otsu algorithm to perform self-adaptive binary segmentation threshold calculation on a panchromatic waveband remote sensing image, and dividing the image into a high-brightness data set and a low-dark data set according to gray scale according to binary segmentation;
step 2, fuzzy statistics of Gaussian fitting functions are carried out, fuzzy estimation is carried out on the two types of data sets by the Gaussian fitting functions according to the statistical results of the histograms, and binary segmentation threshold values of the two types of data sets are respectively determined;
step 3, solving a new binary marking threshold value of the whole image, solving a weighted binary marking threshold value of the whole data set according to the two binary division threshold values, and marking and dividing the two data sets again;
step 4, an iteration process is carried out, the step 2 and the step 3 are repeatedly carried out until the difference between the thresholds of the two types of data sets obtained by the fuzzy estimation of the Gaussian fitting function is smaller than a limited difference, and the iteration is finished;
step 5, determining a final cloud detection threshold, and finishing final binary segmentation marking of the image on any one of the two types of data set thresholds obtained in the step 4 to obtain a final high-brightness data set and a final low-dark data set;
and 6, performing regional arrangement, namely sequentially performing mathematical morphology operations of expansion and corrosion on the highlight data set marks obtained in the step 5, so as to obtain a final cloud detection result.
Regarding a large-scale satellite image containing multiple ground objects, the histogram distribution of the satellite image is regarded as a multimodal form formed by mixing a plurality of simple distributions, and the grey scale statistic function in step 2h(x)Can use a Gaussian fitting modelg(x)To approximate the following equation,
wherein the content of the first and second substances,Mis the number of gaussian waves in the mixed model;
is as followsmA Gaussian distribution function corresponding to each waveform (m = 1,2,……M)；
Its corresponding weight. Let the total number of pixels of the image beNThen, then
Satisfies the following formula:
fuzzy estimation of the gaussian fit model can be performed using the expectation-maximization algorithm. The expectation-maximization algorithm is an iterative method that finds the maximum likelihood estimate or the maximum a posteriori estimate of the parameters in a probabilistic model that relies on latent variables that cannot be observed. The invention firstly determines the number of categories according to the automatic detection of the imageMAnd each class weight
Mean value of
Standard deviation of
At an initial value of (1), wherein
. Then a certain number of random samples are added, parameters of the maximum likelihood function are adjusted through iterative calculation, and the optimal solution in the maximum likelihood meaning is obtained through convergence.
In step 3, it is assumed that the binary segmentation thresholds of the two fuzzy estimates are finally close to be consistent, so according to the distance principle of the euclidean geometry, the weighting mode can be an average weighting mode, that is, the arithmetic mean of the two numbers is taken as the binary segmentation threshold of the data set in the next step.
In step 6, the judged highlight data set is an initial result of cloud detection, but as small patches exist in the result and the edges are too fragmented, the small patches need to be removed by a corrosion algorithm, and then the fragmented edges need to be merged by a dilation algorithm.
Aiming at the satellite images of panchromatic wave bands, the method makes up the defects of the traditional texture analysis method, the homomorphic filtering method and the multispectral synthesis method from different angles, and can be used for automatic cloud detection of mass remote sensing images without prior knowledge. The method has the main advantages of high detection precision, less misjudgment, no need of manual intervention and higher calculation speed.
Drawings
Fig. 1 is a flow chart of a panchromatic band remote sensing image cloud detection technology based on gaussian fitting function and fuzzy hybrid estimation in an embodiment of the invention.
Detailed Description
The technical scheme of the invention is explained in detail in the following by combining the drawings and the embodiment.
Referring to fig. 1, the method for detecting a full-color band remote sensing image cloud provided by the invention realizes initial marking of two types of pixel data of high gray and low dark after image self-adaptive binary judgment, then calculates new gaussian fitting function parameters in the two types of marked pixels by using a fuzzy estimation method to perform gray binary segmentation threshold estimation, calculates two types of binary segmentation thresholds in a weighted manner to obtain an iterative binary marker of the whole image, performs fuzzy estimation of the gaussian fitting function on the iterative marker again to enable the two types of data set binary segmentation thresholds to gradually converge to be similar, and finally meets threshold limit difference to obtain a final high-brightness image spot gray segmentation threshold, thereby realizing full-color band remote sensing image cloud detection
The specific implementation method of the embodiment comprises the following steps:
step 1, self-adaptive initial binary marking: and performing self-adaptive binary segmentation threshold calculation on the panchromatic waveband remote sensing image by using an Otsu algorithm, and dividing the image into a high-brightness data set and a low-dark data set according to the gray level according to binary segmentation.
According to the embodiment, binarization of an image is carried out on a full-color waveband satellite remote sensing image by utilizing an Otsu algorithm under the condition of no prior knowledge, such as cloud pictures and other data assistance, pixel positions on the image are divided into two categories and marked according to gray features, wherein one category is a high-brightness data set, and the other category is a low-dark data set.
Step 2, fuzzy estimation of a Gaussian fitting function: and performing fuzzy estimation on the two data sets by using a Gaussian fitting function according to the statistical result of the histogram, and respectively determining the binary segmentation threshold values of the two data sets.
The embodiment respectively carries out gray histogram fitting on the two types of data sets by utilizing a Gaussian fitting function, and carries out fuzzy estimation on function model parameters by adopting an expectation-maximization algorithm to obtain two binary segmentation threshold values obtained by calculating the fitting function. Wherein the histogram distribution of the data set is regarded as a multi-peak morphology formed by mixing a plurality of simple distributions, a grey scale statistical functionh(x)Can use a Gaussian fitting modelg(x)To approximate the following equation,
wherein the content of the first and second substances,Mis the number of gaussian waves in the mixed model;
is as followsmA Gaussian distribution function corresponding to each waveform (m = 1,2,……M)；
Its corresponding weight. Let the total number of pixels of the image beNThen, then
Satisfies the following formula:
initial value of Gaussian fitting function in example
Detecting according to histogram distribution, namely setting a local window with a certain size, acquiring a plurality of histogram peak points by using a local maximum method, removing undersize peak points, and taking the number of the remaining larger peak points as the number of Gaussian wavesMThen, between adjacent peaks, a valley point is obtained using a local minimum method.
At this time, noteP m Is as followsmThe abscissa of the peak point of each gaussian waveform,V m 、V m+1 are respectively the firstmThe horizontal coordinates of the left and right valley points of each waveform. The initial parameters, and, respectively, may be expressed as:
then, based on the initial value and the posterior probability
Carrying out fuzzy estimation to obtain new model parameter values
Wherein the content of the first and second substances,x n is a samplenThe value of the observed value of (c),Nand (4) for the number of samples, the iterative computation enables the parameters of the function model to be gradually converged, the Gaussian fitting function estimation results of the two types of data sets are obtained, and a binary segmentation threshold value is selected.
Step 3, solving a new binary marker threshold value of the whole image: and solving a weighted integral data set binary segmentation threshold according to the two binary segmentation thresholds, and marking and dividing the two data sets again.
The embodiment takes the arithmetic mean of the two binary division thresholds as the new binary mark threshold of the whole image.
Step 4, setting a limit difference, and performing an iteration process: and (5) repeating the step (2) and the step (3) until the difference between the thresholds of the two types of data sets obtained by the fuzzy estimation of the Gaussian fitting function is smaller than the limited difference, and ending the iteration.
In the embodiment, the limit difference between the thresholds is 3, which is taken as an experience limit difference, and is used as a termination condition of the iterative processing in the steps 2 and 3, so that the final calculation result of the cloud detection threshold is controlled.
Step 5, finally determining a cloud detection threshold: and (4) selecting one of the two types of data set threshold values obtained in the step (4) to finish the final binary segmentation mark of the image.
Embodiments select a segmentation threshold for the highlight dataset as the final cloud detection threshold.
Step 6, regional arrangement: and (5) performing mathematical morphology operation of expansion and corrosion on the highlight data set marks obtained in the step (5) in sequence, thereby obtaining a final cloud detection result.
The specific embodiments described herein are merely illustrative of the spirit of the invention. Various modifications or additions may be made to the described embodiments or alternatives may be employed by those skilled in the art without departing from the spirit or ambit of the invention as defined in the appended claims.
Claims (3)
1. A panchromatic band remote sensing image cloud detection method based on Gaussian fitting function and fuzzy mixed estimation is characterized in that: comprises the following steps of (a) carrying out,
step 1, self-adaptive initial binary marking, utilizing an Otsu algorithm to perform self-adaptive binary segmentation threshold calculation on a panchromatic waveband remote sensing image, and dividing the image into a high-brightness data set and a low-dark data set according to the calculated binary segmentation threshold;
step 2, fuzzy statistics of Gaussian fitting functions are carried out, fuzzy estimation is carried out on the two types of data sets by the Gaussian fitting functions according to the statistical results of the histograms, and binary segmentation threshold values of the two types of data sets are respectively determined;
step 3, solving a new binary marking threshold value of the whole image, solving a weighted binary marking threshold value of the whole data set according to the two binary division threshold values, and marking and dividing the two data sets again;
step 4, an iteration process is carried out, the step 2 and the step 3 are repeatedly carried out until the difference between the thresholds of the two types of data sets obtained by the fuzzy estimation of the Gaussian fitting function is smaller than a limited difference, and the iteration is finished;
step 5, determining a final cloud detection threshold, and finishing final binary segmentation marking of the image on any one of the two types of data set thresholds obtained in the step 4 to obtain a final high-brightness data set and a final low-dark data set;
and 6, performing regional arrangement, namely sequentially performing mathematical morphology operations of expansion and corrosion on the highlight data set marks obtained in the step 5, so as to obtain a final cloud detection result.
2. The panchromatic band remote sensing image cloud detection method based on the Gaussian fitting function and the fuzzy mixed estimation is characterized in that: the gray scale statistic function h (x) in step 2 is approximated by a Gaussian fit model g (x) as follows,
wherein M is the number of Gaussian waves in the mixed model; g (y | theta)m) A gaussian distribution function corresponding to the mth waveform (M ═ 1, 2, … … M); tau ismIts corresponding weight; let the total pixel number of the image be N, then taumSatisfies the following formula:
fuzzy estimation of a Gaussian fit model using an expectation-maximization algorithm, i.e. an iterative method of finding a maximum likelihood estimate or a maximum a posteriori estimate of a parameter in a probabilistic model, wherein the probabilistic model depends on unobservable latent variables, initial values of a Gaussian fit function
And
detecting according to histogram distribution, namely setting a local window with a certain size, acquiring a plurality of histogram peak points by using a local maximum method, removing undersize peak points, obtaining the number of residual larger peak points as the number M of Gaussian waves, then acquiring valley points between adjacent peak values by using a local minimum method,
at this time, note PmIs the abscissa, V, of the peak point of the mth Gaussian waveformm、Vm+1The horizontal coordinates of the left and right valley points of the mth waveform respectively are obtained, and the initial parameter tau is obtainedm、μmAnd σmCan be respectively expressed as:
Then, based on the initial value and the posterior probability
Fuzzy estimation is carried out to obtain a new model parameter value,
wherein x isnAnd (3) for the observed value of the sample N, wherein N is the number of samples, iterative calculation is carried out to enable the parameters of the function model to gradually converge, the Gaussian fitting function estimation results of the two types of data sets are obtained, and a binary segmentation threshold value is selected.
3. The panchromatic band remote sensing image cloud detection method based on the Gaussian fitting function and the fuzzy mixed estimation is characterized in that: in step 3, it is assumed that the binary segmentation thresholds of the two fuzzy estimates are finally close to be consistent, so according to the distance principle of the euclidean geometry, the weighting mode selects the average value weighting, that is, the arithmetic mean of the two numbers is taken as the binary segmentation threshold of the data set in the next step.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610550554.8A CN106204596B (en) | 2016-07-14 | 2016-07-14 | Panchromatic waveband remote sensing image cloud detection method based on Gaussian fitting function and fuzzy mixed estimation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610550554.8A CN106204596B (en) | 2016-07-14 | 2016-07-14 | Panchromatic waveband remote sensing image cloud detection method based on Gaussian fitting function and fuzzy mixed estimation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106204596A CN106204596A (en) | 2016-12-07 |
| CN106204596B true CN106204596B (en) | 2020-12-29 |
Family
ID=57477971
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610550554.8A Active CN106204596B (en) | 2016-07-14 | 2016-07-14 | Panchromatic waveband remote sensing image cloud detection method based on Gaussian fitting function and fuzzy mixed estimation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106204596B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107103295B (en) * | 2017-04-20 | 2021-01-08 | 苏州中科天启遥感科技有限公司 | Optical remote sensing image cloud detection method |
| CN110046646B (en) * | 2019-03-07 | 2023-06-30 | 深圳先进技术研究院 | Image processing method, system, computing device and storage medium |
| CN115424131B (en) * | 2022-07-19 | 2023-04-21 | 南京航空航天大学 | Cloud detection optimal threshold selection method, cloud detection method and cloud detection system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101520896A (en) * | 2009-03-30 | 2009-09-02 | 中国电子科技集团公司第十研究所 | Method for automatically detecting cloud interfering naval vessel target by optical remote sensing image |
| US20130079626A1 (en) * | 2011-09-26 | 2013-03-28 | Andriy Shmatukha | Systems and methods for automated dynamic contrast enhancement imaging |
| CN105160306A (en) * | 2015-08-11 | 2015-12-16 | 北京天诚盛业科技有限公司 | Iris image blurring determination method and device |
| CN105354865A (en) * | 2015-10-27 | 2016-02-24 | 武汉大学 | Automatic cloud detection method and system for multi-spectral remote sensing satellite image |
| CN105574502A (en) * | 2015-12-15 | 2016-05-11 | 中海网络科技股份有限公司 | Automatic detection method for violation behaviors of self-service card sender |
-
2016
- 2016-07-14 CN CN201610550554.8A patent/CN106204596B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101520896A (en) * | 2009-03-30 | 2009-09-02 | 中国电子科技集团公司第十研究所 | Method for automatically detecting cloud interfering naval vessel target by optical remote sensing image |
| US20130079626A1 (en) * | 2011-09-26 | 2013-03-28 | Andriy Shmatukha | Systems and methods for automated dynamic contrast enhancement imaging |
| CN105160306A (en) * | 2015-08-11 | 2015-12-16 | 北京天诚盛业科技有限公司 | Iris image blurring determination method and device |
| CN105354865A (en) * | 2015-10-27 | 2016-02-24 | 武汉大学 | Automatic cloud detection method and system for multi-spectral remote sensing satellite image |
| CN105574502A (en) * | 2015-12-15 | 2016-05-11 | 中海网络科技股份有限公司 | Automatic detection method for violation behaviors of self-service card sender |
Non-Patent Citations (3)
| Title |
|---|
| Texture-Based Remote-Sensing Image Segmentation;Dihua Guo等;《2005 IEEE International Conference on Multimedia and Expo》;20051024;第1-4页 * |
| 国产高分辨率遥感卫星影像自动云检测;谭凯等;《测绘学报》;20160531;第45卷(第5期);第581-591页 * |
| 基于光学遥感图像的舰船目标自动检测技术;施鹏;《中国优秀硕士学位论文全文数据库 信息科技辑》;20110115(第1期);I140-686 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106204596A (en) | 2016-12-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107301661B (en) | High-resolution remote sensing image registration method based on edge point features | |
| Zhang et al. | Object-oriented shadow detection and removal from urban high-resolution remote sensing images | |
| CN110287898B (en) | Optical satellite remote sensing image cloud detection method | |
| CN109460764B (en) | Satellite video ship monitoring method combining brightness characteristics and improved interframe difference method | |
| CN108051371B (en) | A kind of shadow extraction method of ecology-oriented environment parameter remote-sensing inversion | |
| CN111027446B (en) | Coastline automatic extraction method of high-resolution image | |
| CN105139396B (en) | Full-automatic remote sensing image cloud and fog detection method | |
| CN111008664B (en) | Hyperspectral sea ice detection method based on space-spectrum combined characteristics | |
| CN113077486B (en) | Method and system for monitoring vegetation coverage rate in mountainous area | |
| CN109978848A (en) | Method based on hard exudate in multiple light courcess color constancy model inspection eye fundus image | |
| JP2019537151A (en) | Image processing apparatus, image processing method, and image processing program | |
| CN113076802A (en) | Transformer substation switch on-off state image identification method based on lack of disconnected image sample | |
| CN106204596B (en) | Panchromatic waveband remote sensing image cloud detection method based on Gaussian fitting function and fuzzy mixed estimation | |
| CN112767267B (en) | Image defogging method based on simulation polarization fog-carrying scene data set | |
| CN107346549B (en) | Multi-class change dynamic threshold detection method utilizing multiple features of remote sensing image | |
| Zeng et al. | Detecting and measuring fine roots in minirhizotron images using matched filtering and local entropy thresholding | |
| CN114565653B (en) | Heterologous remote sensing image matching method with rotation change and scale difference | |
| CN107704864A (en) | Well-marked target detection method based on image object Semantic detection | |
| CN110136128B (en) | SAR image change detection method based on Rao detection | |
| CN115147613A (en) | Infrared small target detection method based on multidirectional fusion | |
| CN109740468B (en) | Self-adaptive Gaussian low-pass filtering method for extracting black soil organic matter information | |
| CN104573692B (en) | License plate binarization method based on fuzzy degradation model | |
| CN111340779B (en) | Comprehensive detection method for quasi-circular vegetation patches | |
| CN116342417B (en) | Radiation correction method and system for aerial remote sensing image | |
| Afreen et al. | A method of shadow detection and shadow removal for high resolution remote sensing images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |