CN113516633A - Cloud detection identification filling method for satellite image - Google Patents
Cloud detection identification filling method for satellite image Download PDFInfo
- Publication number
- CN113516633A CN113516633A CN202110593217.8A CN202110593217A CN113516633A CN 113516633 A CN113516633 A CN 113516633A CN 202110593217 A CN202110593217 A CN 202110593217A CN 113516633 A CN113516633 A CN 113516633A
- Authority
- CN
- China
- Prior art keywords
- cloud
- satellite
- cloud detection
- image
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/40—Filling a planar surface by adding surface attributes, e.g. colour or texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
- G06T7/45—Analysis of texture based on statistical description of texture using co-occurrence matrix computation
-
- 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
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30192—Weather; Meteorology
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Image Processing (AREA)
Abstract
A cloud detection identification filling method for satellite images belongs to the technical field of image data processing of electronic and communication systems. The invention utilizes the auxiliary data area of the satellite image to fill the detection result into the reserved position of the auxiliary data area in real time, and the method has the following advantages: firstly, other data areas do not need to be occupied, and the data transmission bandwidth is saved; secondly, when satellite image data are received on the ground, real-time extraction and analysis are facilitated; finally, the cloud identification content is 'FFFF' or '0000', so that the accuracy of the judgment of the cloud detection algorithm can be conveniently observed subjectively, and the interference of channel error codes can be effectively prevented.
Description
Technical Field
The invention relates to a cloud detection identification filling method for satellite images, and belongs to the technical field of image data processing of electronic and communication systems.
Background
For an optical remote sensing satellite, cloud is a serious obstacle to light propagation, and the quality of remote sensing information acquisition is greatly influenced. Many satellite remote sensing images have blind areas shielded by cloud layers, local ground object information is lost, analysis and understanding of the images are not facilitated, and the utilization rate of data is reduced. According to the global cloud data statistics provided by international satellite cloud climate program ISCCP from month 7 to month 6 in 1983, the global average cloud content is 66.38%. The cloud detection is effectively carried out in real time, the data volume of cloud area images is reduced, on one hand, the pressure of remote sensing satellite mass data on a transmission channel can be relieved, the utilization rate of satellite remote sensing images is improved, on the other hand, the saved data volume can be provided for non-cloud area images, and the non-cloud area images can obtain better compressed image quality.
The development track of the cloud detection technology mainly follows two routes, wherein one route is the construction of a cloud characteristic space, namely a cloud description space is established through radiation, spectrum, texture, spectrum and time-frequency analysis; the other is classifier design based on cloud feature space, and mainly non-linear classifier design. Most of the researches do not consider the problems of algorithm operation resources and realization speed.
Due to the restriction of resource limitation and real-time requirement, the satellite cloud detection technology has the advantage that the operation complexity becomes an important evaluation index of the realizability under the condition that the algorithm detection accuracy is guaranteed. In 2003, an NASA geoscience and technology research laboratory and an Earth scientific and technical laboratory in Massachusetts are developed in a cooperative way, and an on-satellite real-time cloud detection algorithm is successfully tested on an EO-1(Earth observation-1) satellite, the algorithm adopts a cloud spectrum data structure model based on PCA (principal component analysis), a ground feature spectrum threshold detection strategy based on ground feature information prior knowledge is fused, cloud pixel and cloud coverage area detection of remote sensing images is carried out, characteristic analysis is carried out on multispectral images of 6 wave bands, various Earth surface types such as cloud, snow, ice, sand and the like can be distinguished, and the error rate reported is only 1% -2%. The united states Landsat7 satellite uses an automatic cloud cover assessment algorithm (ACCA) to score the cloud cover in each acquired image, and the scoring results are used as the basis for the satellite flight mission formulator to rearrange the receiving plan and delete the multiple cloud covers from the user query database.
The space flight Qinghua I micro satellite emitted in 2000 in China has three wave bands of green (0.52-0.6 um), red (0.63-0.69 um) and near infrared (0.76-0.94 um), a gray threshold method cloud detection technology is adopted for a red wave band image, a ground object image polluted by cloud is removed, a simple compression technology a-MPBTC is adopted for compressing the image, the transmission pressure is reduced, and a satisfactory image is obtained at the same time. The cloud detection technology is adopted for remote sensing series satellites in China and the like, and real-time cloud detection is carried out by using methods such as classification texture characteristic values and the like, and detection results are downloaded or used as remote control signals or real-time guidance compression and the like.
At present, the detection result of the satellite cloud is necessarily downloaded along with the image. There are several downloading methods: firstly, the cloud detection identification is printed on telemetering data for downloading, as telemetering information is read on time by a whole satellite sending instruction, and the cloud detection processing of the data transmission subsystem is related to an image receiving frame, the cloud detection result and the telemetering reading cannot be synchronous, and the reading and analysis are not direct enough; secondly, the cloud detection identifier is added to the image data area for downloading, and after cloud detection is performed on the image, operations such as data compression, AOS coding and the like are required, and subsequent compression coding, the content of the image data changes, and the data volume, the compression packet format and the data transmission packet format change significantly, so a series of unpacking operations must be performed before the cloud detection result of the corresponding image is analyzed on the ground.
Disclosure of Invention
The technical problem solved by the invention is as follows: the cloud detection identification filling method of the satellite image is characterized in that a cloud detection result is filled in an image auxiliary data area, and the image auxiliary data does not participate in cloud detection and data compression, is only synchronized with current image data in real time and is downloaded, so that ground analysis is simple and clear, other data areas are not occupied, and data transmission bandwidth is saved; secondly, when satellite image data are received on the ground, real-time extraction and analysis are facilitated; finally, the cloud identification content is 'FFFF' or '0000', so that the accuracy of the judgment of the cloud detection algorithm can be conveniently observed subjectively, and the interference of channel error codes can be effectively prevented.
The technical solution of the invention is as follows: a cloud detection identification filling method for satellite images comprises the following steps:
step A: acquiring satellite image data in a preset frame format; the satellite image data in the preset frame format comprises auxiliary data and image data;
and B: carrying out cloud detection on the satellite image data;
and C: and generating a corresponding cloud detection identifier according to the cloud detection result, and filling the cloud detection identifier into the auxiliary data area.
Furthermore, the length of the auxiliary data is 32, the auxiliary data is used for recording satellite shooting time, line number and ground position information, and information bits are reserved for subsequent filling; the length of the image data is set according to the satellite camera.
Further, the cloud detection of the satellite image data comprises the following steps:
partitioning the image according to the cloud image resolution and the satellite orbit HEIGHT, wherein the size of the block is HEIGHT WIDTH, and the length L2 of the image data is an integral multiple of WIDTH;
counting the number NUM of high-gray pixels in the block, if the number NUM is larger than 3/4 of the number of pixels in the whole block, determining the block as a cloud, otherwise, calculating the mean value, the variance and the root mean square of the image block, and calculating the value of a parameter M1;
generating an image block gray level co-occurrence matrix and calculating an eigenvalue ASM;
and performing parameter weighting calculation to obtain a cloud detection judgment value M, wherein if the cloud detection judgment value M is larger than 0, the current image block is cloud, and otherwise, the current image block is non-cloud.
Further, if the cloud is a cloud, the cloud detection flag is "FFFF", and if the cloud is a non-cloud, the cloud detection flag is "0000".
A cloud detection logo populating system of satellite images, comprising:
the clock processing module is used for carrying out DCM frequency multiplication on an FPGA input clock to respectively generate clocks of 100MHz, 120MHz and clk _200MHz for other modules to use;
the 2711 input module is used for converting the data of the 2711 clock domain into an FPGA clock domain through asynchronous FIFO cache;
2711 output module, which is used to convert the data of FPAG clock domain into 2711 clock domain through asynchronous FIFO buffer;
the FIFO cache module is used for caching 120M discontinuous DDR output data into 100M continuous data output by lines;
the DDR user interface module is used for carrying out time sequence and bit width processing on data so as to meet the data exchange between each module and an external DDR;
the cloud detection module is used for carrying out cloud detection on the satellite image data and generating a cloud detection identifier;
and the cloud detection identifier filling module is used for filling the cloud detection identifier into an auxiliary data area of the satellite image data in the preset frame format.
Furthermore, the length of the auxiliary data is 32, the auxiliary data is used for recording satellite shooting time, line number and ground position information, and information bits are reserved for subsequent filling; the length of the image data is set according to the satellite camera.
Further, the cloud detection of the satellite image data comprises the following steps:
partitioning the image according to the cloud image resolution and the satellite orbit HEIGHT, wherein the size of the block is HEIGHT WIDTH, and the length L2 of the image data is an integral multiple of WIDTH;
counting the number NUM of high-gray pixels in the block, if the number NUM is larger than 3/4 of the number of pixels in the whole block, determining the block as a cloud, otherwise, calculating the mean value, the variance and the root mean square of the image block, and calculating the value of a parameter M1;
generating an image block gray level co-occurrence matrix and calculating an eigenvalue ASM;
and (3) calculating the cloud detection judgment value M value by parameter weighting, wherein if the cloud detection judgment value M value is larger than 0, the current image block is cloud, and otherwise, the current image block is non-cloud.
Further, if the cloud is a cloud, the cloud detection flag is "FFFF", and if the cloud is a non-cloud, the cloud detection flag is "0000".
A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method for cloud detection identity filling of satellite images.
A cloud detection identification filling device for satellite images comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor realizes the steps of the cloud detection identification filling method for satellite images when executing the computer program.
The invention provides a cloud detection identification filling method of a satellite image, which utilizes an auxiliary data area of the satellite image to fill a detection result into a reserved position of the auxiliary data area in real time, and has the following advantages:
firstly, other data areas do not need to be occupied, and the data transmission bandwidth is saved;
secondly, when satellite image data are received on the ground, real-time extraction and analysis are facilitated;
thirdly, since the cloud identifies content or is "FFFF", or is "0000", this filling manner can effectively combat channel errors. And if the channel has a certain error rate, keeping the interpretation of the correct cloud judgment result through the approximate probability numbers of '1' and '0'.
Finally, since the cloud identifies content or is "FFFF", or is "0000", the content facilitates subjective observation of the correctness of the cloud detection algorithm decision. When the image is displayed, if the image is a cloud, the image auxiliary data area is displayed as a bright point, and if the image is not a cloud, the image auxiliary data area is displayed as a black point; as shown in fig. 5, the cloud decision result of the right image block is obviously displayed, and the accuracy of the cloud decision can be artificially and subjectively seen.
The cloud detection identification filling method is suitable for the remote sensing satellite data transmission platform, and has good application prospect and competitiveness in the remote sensing satellite data platform due to the fact that the cloud detection identification filling method is simple, effective and code-free, and accuracy of cloud detection can be observed subjectively conveniently.
Drawings
Fig. 1 is a schematic diagram of a satellite image data frame format.
Fig. 2 is a flow chart of a cloud detection algorithm.
Fig. 3 is a schematic block diagram of a cloud detection implemented by an FPGA.
FIG. 4 is a cloud detection identity population diagram.
Fig. 5 shows the result of cloud decision in the auxiliary data for the original image enlargement effect.
Fig. 6 shows a result of cloud determination in the original viewing assistance data.
Detailed Description
In order to better understand the technical solutions, the technical solutions of the present application are described in detail below with reference to the drawings and specific embodiments, and it should be understood that the specific features in the embodiments and examples of the present application are detailed descriptions of the technical solutions of the present application, and are not limitations of the technical solutions of the present application, and the technical features in the embodiments and examples of the present application may be combined with each other without conflict.
The cloud detection identifier filling method for the satellite image provided by the embodiment of the present application is further described in detail below with reference to the drawings of the specification, and specific implementation manners may include (as shown in fig. 1 to 6):
step A: the satellite image data frame format consists of two parts, namely auxiliary data and image data;
the satellite image data is transmitted to the data transmission subsystem according to frames, wherein the former frame is transmitted and then the latter frame is transmitted; each frame of data includes auxiliary data and image data, the auxiliary data length is denoted as L1, the image data length is denoted as L2, and as shown in fig. 1, the auxiliary data and the image data length may be different for different satellites.
And B: the cloud detection function is carried out on the satellite image data, and an algorithm flow chart is shown in detail in an attached figure 2;
(1) partitioning the image according to the cloud image resolution, the satellite orbit HEIGHT and the like, wherein the size of the blocks is HEIGHT WIDTH, and the image line length L2 is integral multiple of WIDTH;
(2) counting the number NUM of high-gray pixels in the block, if the number is greater than 3/4 of the number of pixels in the whole block, determining the block as a cloud, otherwise, calculating other values;
(3) calculating the mean of image blocks
Variance (variance)
Equal value of wherein
xi,jIs the image gray value of the ith row and the jth column,
sign () is a sign value for the average gray value of the image block.
(4) Generating image block gray level co-occurrence matrix and calculating characteristic value
Wherein glcm is a gray level co-occurrence matrix of one image.
(5) Obtaining M-M1 + ASM-0.2 by parameter weighted calculation, wherein if M is larger than 0, the cloud is obtained, otherwise, the cloud is obtained; wherein, ASM is the characteristic value of the gray level co-occurrence matrix.
A specific functional block diagram of the cloud detection algorithm implemented by the FPGA is shown in fig. 3, and mainly includes seven modules, namely a 2711 receiving module, a clock processing module, a DDR user interface module, a cloud detection identifier filling module, an output FIFO buffer module, and a 2711 output module.
(1) A clock processing module: and performing DCM frequency multiplication on an FPGA input clock to respectively generate clocks of 100MHz, 120MHz and clk _200MHz for other modules to use.
(2)2711 input module: the data of 2711 clock domain is converted into FPGA clock domain through asynchronous FIFO buffer; the 2711 output module has the function of converting data of the FPAG clock domain into a 2711 clock domain through asynchronous FIFO buffer.
(3) FIFO buffer module: 120M of non-contiguous DDR output data is buffered into 100M of contiguous data output by row.
(4) DDR user interface module: and carrying out time sequence and bit width processing on the data so as to meet the data exchange between the FPGA and the DDR.
(5) The cloud detection module: completing the cloud detection algorithm shown in the figure 2 and generating a cloud detection identifier;
(6) cloud detection identifier filling module: filling the cloud detection identification (cloud or non-cloud) into the fixed auxiliary data area, wherein the specific filling method is shown in step C;
(7) a parameter weighting determination module: certain algorithm calculation is carried out on each parameter to obtain the most accurate cloud judgment result.
And C: the cloud detection flag is populated into the auxiliary data area as detailed in figure 4.
(1) When image data is input, the front end of each frame of data is provided with auxiliary data with a fixed length L1, the bit width of the auxiliary data is 16 bits, and a certain reserved area is provided;
(2) partitioning an image, wherein each frame of image data comprises an integral multiple of the number of blocks;
(3) if the image block is judged to be a cloud, the cloud is identified as 'FFFF'; if the image block is judged to be non-cloud, the cloud identification is 0000.
(4) Cloud detection identifier filling: sequentially filling cloud marks in a reserved area at the tail part of the first frame of auxiliary data of the image block according to the number of the image blocks; specifically, as shown in fig. 4, the "1" position is filled with the first cloud identifier, the "2" position is filled with the second cloud identifier, and so on, and the last position is filled with the last cloud identifier.
The present invention will be described in further detail with reference to the following embodiments of image data with a frame length of 32+2048 and an image block size of 512 × 512. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not to be construed as limiting the invention, and will be described in detail in conjunction with fig. 1-6.
Step A: the satellite image data frame format consists of two parts, namely auxiliary data and image data, and auxiliary data
The auxiliary data length is 32, and the image data length is 2048.
And B: the cloud detection function is carried out on the satellite image data, and an algorithm flow chart is shown in detail in an attached figure 2;
(1) partitioning the image, wherein the block size is 512 x 512, and the length of each frame of image is divided into 4 image blocks, namely a block 1, a block 2, a block 3 and a block 4;
(2) counting the number NUM of high-gray pixels in the block, if the number is greater than 3/4 of the number of pixels in the whole block, determining the block as a cloud, otherwise, calculating other values;
(3) calculating the values of the mean, variance, root mean square, etc. of the image block, wherein,
(4) generating an image block gray level co-occurrence matrix and calculating an eigenvalue ASM;
(5) and performing parameter weighting calculation to obtain M, wherein if M is larger than 0, the M is cloud, and otherwise, the M is non-cloud.
And C: the cloud detection flag is populated into the auxiliary data area as detailed in figure 4.
(1) The front end of each frame of image data is provided with auxiliary data with the fixed length of 32 bits, the bit width of the auxiliary data is 16 bits, and the tail part of the auxiliary data is provided with a reserved area with 4 positions;
(2) partitioning the image into blocks, namely a block 1, a block 2, a block 3 and a block 4;
(3) if the image block is judged to be a cloud, the cloud is identified as 'FFFF'; if the image block is judged to be non-cloud, the cloud identification is 0000.
(4) Cloud detection identifier filling: in a reserved area at the tail of the first frame of auxiliary data of the image block, the cloud identification of the image block 1 is filled in the fourth last position, the cloud identification of the image block 2 is filled in the third last position, the cloud identification of the image block 3 is filled in the second last position, and the cloud identification of the image block 4 is filled in the last position.
A computer-readable storage medium having stored thereon computer instructions which, when executed on a computer, cause the computer to perform the method of fig. 1.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Those skilled in the art will appreciate that those matters not described in detail in the present specification are well known in the art.
Claims (10)
1. A cloud detection identification filling method for satellite images is characterized by comprising the following steps:
step A: acquiring satellite image data in a preset frame format; the satellite image data in the preset frame format comprises auxiliary data and image data;
and B: carrying out cloud detection on the satellite image data;
and C: and generating a corresponding cloud detection identifier according to the cloud detection result, and filling the cloud detection identifier into the auxiliary data area.
2. The method for filling the cloud detection identifier of the satellite image according to claim 1, wherein: the length of the auxiliary data is 32, the auxiliary data is used for recording satellite shooting time, line number and ground position information, and information bits are reserved for subsequent filling; the length of the image data is set according to the satellite camera.
3. The method according to claim 1, wherein the cloud detection of the satellite image data comprises the following steps:
partitioning the image according to the cloud image resolution and the satellite orbit HEIGHT, wherein the size of the block is HEIGHT WIDTH, and the length L2 of the image data is an integral multiple of WIDTH;
counting the number NUM of high-gray pixels in the block, if the number NUM is larger than 3/4 of the number of pixels in the whole block, determining the block as a cloud, otherwise, calculating the mean value, the variance and the root mean square of the image block, and calculating the value of a parameter M1;
generating an image block gray level co-occurrence matrix and calculating an eigenvalue ASM;
and performing parameter weighting calculation to obtain a cloud detection judgment value M, wherein if the cloud detection judgment value M is larger than 0, the current image block is cloud, and otherwise, the current image block is non-cloud.
4. The method as claimed in claim 1, wherein the cloud detection flag is "FFFF" if the satellite image is a cloud, and is "0000" if the satellite image is a non-cloud.
5. A cloud detection logo populating system for satellite images, comprising:
the clock processing module is used for carrying out DCM frequency multiplication on an FPGA input clock to respectively generate clocks of 100MHz, 120MHz and clk _200MHz for other modules to use;
the 2711 input module is used for converting the data of the 2711 clock domain into an FPGA clock domain through asynchronous FIFO cache;
2711 output module, which is used to convert the data of FPAG clock domain into 2711 clock domain through asynchronous FIFO buffer;
the FIFO cache module is used for caching 120M discontinuous DDR output data into 100M continuous data output by lines;
the DDR user interface module is used for carrying out time sequence and bit width processing on data so as to meet the data exchange between each module and an external DDR;
the cloud detection module is used for carrying out cloud detection on the satellite image data and generating a cloud detection identifier;
and the cloud detection identifier filling module is used for filling the cloud detection identifier into an auxiliary data area of the satellite image data in the preset frame format.
6. The cloud detection identity population system for satellite images as claimed in claim 5, wherein: the length of the auxiliary data is 32, the auxiliary data is used for recording satellite shooting time, line number and ground position information, and information bits are reserved for subsequent filling; the length of the image data is set according to the satellite camera.
7. The system of claim 5, wherein the cloud detection of the satellite image data comprises the following steps:
partitioning the image according to the cloud image resolution and the satellite orbit HEIGHT, wherein the size of the block is HEIGHT WIDTH, and the length L2 of the image data is an integral multiple of WIDTH;
counting the number NUM of high-gray pixels in the block, if the number NUM is larger than 3/4 of the number of pixels in the whole block, determining the block as a cloud, otherwise, calculating the mean value, the variance and the root mean square of the image block, and calculating the value of a parameter M1;
generating an image block gray level co-occurrence matrix and calculating an eigenvalue ASM;
and (3) calculating the cloud detection judgment value M value by parameter weighting, wherein if the cloud detection judgment value M value is larger than 0, the current image block is cloud, and otherwise, the current image block is non-cloud.
8. The cloud detection identity population system for satellite images as claimed in claim 5, wherein: if the cloud is cloud, the cloud detection flag is "FFFF", and if the cloud is non-cloud, the cloud detection flag is "0000".
9. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 4.
10. A cloud detection marker filling apparatus for satellite images, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: the processor, when executing the computer program, performs the steps of the method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110593217.8A CN113516633A (en) | 2021-05-28 | 2021-05-28 | Cloud detection identification filling method for satellite image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110593217.8A CN113516633A (en) | 2021-05-28 | 2021-05-28 | Cloud detection identification filling method for satellite image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113516633A true CN113516633A (en) | 2021-10-19 |
Family
ID=78065148
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110593217.8A Pending CN113516633A (en) | 2021-05-28 | 2021-05-28 | Cloud detection identification filling method for satellite image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113516633A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116486277A (en) * | 2023-03-28 | 2023-07-25 | 武汉卓目科技有限公司 | Remote sensing load image interpretation method and remote sensing load quick-looking system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101799921A (en) * | 2009-02-10 | 2010-08-11 | 中国科学院计算技术研究所 | Cloud detection method of optic remote sensing image |
| CN105426903A (en) * | 2015-10-27 | 2016-03-23 | 航天恒星科技有限公司 | Cloud determination method and system for remote sensing satellite images |
| CN107124185A (en) * | 2017-04-10 | 2017-09-01 | 中山大学 | A kind of data buffer storage and playback system of time-interleaved A/D conversion system |
| CN110913226A (en) * | 2019-09-25 | 2020-03-24 | 西安空间无线电技术研究所 | Image data processing system and method based on cloud detection |
| US20200125844A1 (en) * | 2018-10-19 | 2020-04-23 | The Climate Corporation | Machine learning techniques for identifying clouds and cloud shadows in satellite imagery |
-
2021
- 2021-05-28 CN CN202110593217.8A patent/CN113516633A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101799921A (en) * | 2009-02-10 | 2010-08-11 | 中国科学院计算技术研究所 | Cloud detection method of optic remote sensing image |
| CN105426903A (en) * | 2015-10-27 | 2016-03-23 | 航天恒星科技有限公司 | Cloud determination method and system for remote sensing satellite images |
| CN107124185A (en) * | 2017-04-10 | 2017-09-01 | 中山大学 | A kind of data buffer storage and playback system of time-interleaved A/D conversion system |
| US20200125844A1 (en) * | 2018-10-19 | 2020-04-23 | The Climate Corporation | Machine learning techniques for identifying clouds and cloud shadows in satellite imagery |
| CN110913226A (en) * | 2019-09-25 | 2020-03-24 | 西安空间无线电技术研究所 | Image data processing system and method based on cloud detection |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116486277A (en) * | 2023-03-28 | 2023-07-25 | 武汉卓目科技有限公司 | Remote sensing load image interpretation method and remote sensing load quick-looking system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112132119B (en) | Passenger flow statistical method and device, electronic equipment and storage medium | |
| CN103034858B (en) | A kind of secondary cluster segmentation method of satellite cloud picture | |
| CN112380921A (en) | Road detection method based on Internet of vehicles | |
| CN110781756A (en) | Urban road extraction method and device based on remote sensing image | |
| CN112149547A (en) | Remote sensing image water body identification based on image pyramid guidance and pixel pair matching | |
| CN110443862B (en) | Lithologic map filling method and system based on unmanned aerial vehicle and electronic equipment | |
| CN112232371B (en) | American license plate recognition method based on YOLOv3 and text recognition | |
| CN111541511B (en) | Communication interference signal identification method based on target detection in complex electromagnetic environment | |
| CN113052868B (en) | Method and device for training matting model and image matting | |
| CN112580512B (en) | Lightweight unmanned aerial vehicle target detection method based on channel cutting | |
| CN109949242A (en) | The generation method of image defogging model, device and image defogging method, device | |
| CN103593853A (en) | Remote-sensing image multi-scale object-oriented classification method based on joint sparsity representation | |
| CN112446342A (en) | Key frame recognition model training method, recognition method and device | |
| CN114998757A (en) | Target detection method for unmanned aerial vehicle aerial image analysis | |
| CN112001293A (en) | Remote sensing image ground object classification method combining multi-scale information and coding and decoding network | |
| CN113516633A (en) | Cloud detection identification filling method for satellite image | |
| CN108073865B (en) | Aircraft trail cloud identification method based on satellite data | |
| CN106529472A (en) | Target detection method and apparatus based on large-scale high-resolution and high-spectral image | |
| CN112308087A (en) | Integrated imaging identification system and method based on dynamic vision sensor | |
| CN104463962A (en) | Three-dimensional scene reconstruction method based on GPS information video | |
| CN114549959A (en) | Infrared dim target real-time detection method and system based on target detection model | |
| CN112911171A (en) | Intelligent photoelectric information processing system and method based on accelerated processing | |
| CN115035406A (en) | Method and system for labeling remote sensing scene data set, storage medium and electronic equipment | |
| CN113902044A (en) | Image target extraction method based on lightweight YOLOV3 | |
| CN113657287A (en) | Target detection method based on deep learning improved YOLOv3 |
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 |