CN112033914B - Color steel tile factory building extraction method based on remote sensing image - Google Patents
Color steel tile factory building extraction method based on remote sensing image Download PDFInfo
- Publication number
- CN112033914B CN112033914B CN202010902866.7A CN202010902866A CN112033914B CN 112033914 B CN112033914 B CN 112033914B CN 202010902866 A CN202010902866 A CN 202010902866A CN 112033914 B CN112033914 B CN 112033914B
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- color steel
- steel tile
- sensing image
- nir
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N2021/1765—Method using an image detector and processing of image signal
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N2021/1793—Remote sensing
- G01N2021/1797—Remote sensing in landscape, e.g. crops
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/194—Terrestrial scenes using hyperspectral data, i.e. more or other wavelengths than RGB
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a remote sensing image-based color steel tile factory building extraction method which comprises the steps of obtaining a remote sensing image, preprocessing the remote sensing image to obtain a spectral reflectivity image, wherein the remote sensing image at least comprises blue, green, red and near infrared wave bands. Respectively carrying out wave band operation R on the remote sensing imagesB×(RB‑RR) And 1-mean (R)B+RG+RNIR) (ii) a Then combining the two parts; or respectively carrying out wave band operation (R) on the remote sensing imagesB×(RB‑RG)×|RG‑RR|)1/3And mean (R)NIR+RR)‑mean(RB+RG+RR) (ii) a Then combining the two parts; two kinds of extraction formulas for the color steel tile can be obtained. The invention also discloses a corresponding extraction system. Because the spectral reflectivity of the ground objects in blue, green, red and near infrared bands has difference, the core idea of the invention is to enhance the difference through band operation and extract the target ground object through the optimal threshold value, and the target ground object of the invention is the color steel tile so as to realize the extraction of the color steel tile factory building.
Description
Technical Field
The invention belongs to the technical field of remote sensing image processing, relates to extraction of color steel tiles (plant ceiling materials), and particularly relates to a remote sensing image-based color steel tile plant extraction method.
Background
The rapid growth of construction land is the most intuitive expression of the urbanization process in China in space. Research has shown that in the last thirty years, the area of newly-added construction land in China is as large as 8 ten thousand square kilometers, and nearly one fourth of the newly-added construction land is used for industrial land to meet the increasing industrialization demand. The Dioscorea shields are also becoming increasingly sharp in the process of urbanization in China: on one hand, more than half of the newly added construction land comes from the occupation of the cultivated land around the city; on the other hand, the demand for urban expansion and industrial land still shows a strong growth trend, but faces the situation of land shortage and index shortage. Therefore, the spatial distribution information of the industrial land can be timely, accurately and efficiently acquired, and scientific reference can be provided for urban space planning. The color steel tiles are the most widely used materials for building roofs in industrial fields, and the distribution of the color steel tiles is identified.
The prior art has high requirements on the wave band of the remote sensing image, the processing steps are complicated, and the extraction efficiency and the extraction precision of the color steel tile factory building are limited to a certain degree.
Disclosure of Invention
The invention aims to provide a color steel tile factory building extraction method based on remote sensing images based on spectral characteristics of color steel tiles so as to realize factory building extraction.
In order to achieve the aim, the invention provides the technical scheme that:
a color steel tile factory building extraction method based on remote sensing images is characterized by comprising the following steps:
acquiring a remote sensing image, wherein the remote sensing image at least comprises blue, green, red and near-infrared wave bands; preprocessing the remote sensing image to obtain a spectral reflectivity image If(x, y), wherein f belongs to { B, G, R, NIR }, wherein x and y represent the coordinates of the pixel in the image, and B, G, R and NIR represent a blue light wave band, a green light wave band, a red light wave band and a near infrared wave band respectively;
step two, enhancing the remote sensing image of the color steel tile: respectively performing band operation RB×(RB-RR) Sum band operation 1-mean (R)B+RG+RNIR) (ii) a Finally, combining the two parts to form the following color steel tile extractionThe formula:
equation 1:
wherein R isB，RG，RRAnd RNIRRespectively representing the reflectivity of a single pixel in the remote sensing image in four wave bands of blue, green, red and near infrared;
and step three, setting a reasonable threshold value and extracting a color steel tile area.
Furthermore, the reflectivity of the color steel tile in a blue light wave band is high, and the reflectivity in the blue light wave band is higher than that in a red light wave band, so that a first-step wave band operation R is performed on the remote sensing imageB×(RB-RR) Highlighting the characteristics of the color steel tile; because the interior of the same ground object has great difference, the same object different spectrum characteristics can also cause great interference to the identification precision, and the second step of band operation 1-mean (R)B+RG+RNIR) Further highlighting the overall spectral characteristics of the color steel tile and achieving the purpose of reducing the spectral characteristic difference inside other ground objects.
Further, the threshold value in the third step is set to be about 0.01, namely the image element brightness in the image which is calculated and generated through the formula 1 and is greater than 0.01 is the coverage area of the color steel tile factory building.
A color steel tile factory building extraction method based on remote sensing images comprises the following steps:
acquiring a remote sensing image, wherein the remote sensing image at least comprises blue, green, red and near-infrared wave bands; preprocessing the remote sensing image to obtain a spectral reflectivity image If(x, y), wherein f belongs to { B, G, R, NIR }, wherein x and y represent the coordinates of the pixel in the image, and B, G, R and NIR represent a blue light wave band, a green light wave band, a red light wave band and a near infrared wave band respectively;
step two, enhancing the remote sensing image of the color steel tile: respectively performing band operation (R)B×(RB-RG)×|RG-RR|)1/3Sum band operation mean (R)NIR+RR)-mean(RB+RG+RR) (ii) a Finally, two are putAnd combining the parts to form the following color steel tile extraction formula:
equation 2:
wherein R isB，RG，RRAnd RNIRRespectively representing the reflectivity of a single pixel in the remote sensing image in four wave bands of blue, green, red and near infrared.
Further, said (R)B×(RB-RG)＝|RG-RR|)1/3The spectral characteristics of the water body and the ground objects which are not removed are restrained, and the spectral characteristics of the color steel tile are highlighted; the mean (R)NIR+RR)-mean(RB+RG+RR) Has higher stability.
A color steel tile factory building extraction system based on remote sensing images comprises the following components:
an image preprocessing module: the remote sensing image acquisition device is used for acquiring a remote sensing image, and the remote sensing image at least comprises blue, green, red and near infrared wave bands; the remote sensing image preprocessing module is used for preprocessing the remote sensing image to obtain a spectral reflectivity image;
color steel tile reinforcing module: and respectively carrying out band operation on the remote sensing image, and combining the two band operation results as a numerator and a denominator respectively into a color steel tile extraction formula.
Further, the color steel tile reinforcing module: respectively carrying out wave band operation R on the remote sensing imagesB×(RB-RR) Sum band operation 1-mean (R)B+RG+RNIR) And finally combining the two to form the following color steel tile extraction formula:
equation 1:
wherein R isB，RG，RRAnd RNIRRespectively representing the reflectivity of a single pixel in the remote sensing image in four wave bands of blue, green, red and near infrared;
the system also comprises a threshold extraction module, and the threshold extraction module is used for setting a threshold and extracting the color steel tile area.
Or, the color steel tile reinforcing module: respectively performing band operation (R) on the remote sensing imagesB×(RB-RG)×|RG-RR|)1/3Sum band operation mean (R)NIR+RR)-mean(RB+RG+RR) And then combining the two parts to form the following color steel tile extraction formula:
equation 2:
wherein R isB，RG，RRAnd RNIRRespectively representing the reflectivity of a single pixel in the remote sensing image in four wave bands of blue, green, red and near infrared.
An electronic device comprising a memory and a processor, the memory configured to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method for rehouse extraction as claimed in any one of the preceding claims.
A computer readable storage medium storing a computer program for causing a computer to execute a method for implementing a color steel tile factory building extraction method as claimed in any one of the preceding claims.
The spectral reflectivity of the ground object in four wave bands of blue, green, red and near infrared are different, the core idea of the invention is to enhance the difference through wave band operation and extract the target ground object through an optimal threshold value, and the target ground object is a color steel tile factory building.
After the calculation of the formula 1, the pixel value of the color steel tile is obviously higher than that of other ground objects, and a detailed graph of the color steel tile can be effectively highlighted. And then the color steel tile can be extracted by setting a brightness threshold value. The method has the advantages that: the speed is high, the efficiency is high, and the method is suitable for extracting large-area color steel tiles; the disadvantages are that: the accuracy is relatively low and the selection of the threshold is subjective.
The advantages of comparing method one (equation 1) and method two (equation 2) are: the effect of extracting the color steel tile is better, and the precision is higher. Through multiple experiments, the color steel tile is extracted by the second method, a breaking point, namely an optimal threshold value, is bound to appear, and the extraction result is more objective; the disadvantages are that: the operation is relatively complicated and the efficiency is reduced.
In conclusion, the method for extracting the color steel tile factory building can be selected according to the self requirements (such as high precision or high efficiency required by the requirement) by utilizing the design of the invention, the applicability is strong, the method is greatly helpful for obtaining the spatial distribution information of the industrial land, and scientific reference can be provided for urban space planning.
Drawings
FIG. 1 shows spectral reflectance characteristics of a ground object in a remote sensing image in red, green, blue and near infrared bands: wherein (a) is vegetation; (b) bare land; (c) artificial earth surface; (d) a body of water;
fig. 2 is an image of a color steel tile enhanced by formula 1: (a) a sample region overall effect map; (b) detail drawing of the color steel tile;
FIG. 3 is a pixel brightness distribution curve of the color steel tile image enhanced by formula 2;
FIG. 4 is a comparison graph of the color steel tile results extracted by equation 2: (a) an original remote sensing image map; (b) and (5) extracting color steel tile plants in the corresponding areas.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Example 1
In this embodiment, the identification and extraction process of the coverage area of the color steel tile is shown by taking the data of a domestic satellite high-score second (GF-2) satellite as an example. The GF-2 satellite is the first civil optical remote sensing satellite with spatial resolution better than 1 meter which is independently developed in China, and is provided with two high-resolution 1-meter panchromatic 4-meter multispectral cameras.
In the embodiment, a multispectral image with a high score of two is adopted, remote sensing image preprocessing such as radiometric calibration, atmospheric correction, geometric correction and the like is carried out on the image to obtain a reflectivity data image, the radiometric calibration is carried out according to a coefficient published by satellite data with the high score of two, and FLAASH atmospheric correction is adopted for atmospheric correction.
From the perspective of automatic classification of remote sensing images, the types of ground surface coverage of cities and the surrounding cities can be generally classified into four major categories, namely vegetation, bare land, artificial ground surface and water body. Each major category can be divided into several sub-categories, for example, vegetation can be divided into several categories according to density, bare land can be divided into several categories according to water content, water body can be divided into several categories according to silt content and water grass content, and artificial ground surface can be divided into roof, road, cement land and the like according to different materials. In the embodiment, five types of samples are uniformly selected for each category according to the characteristics of the categories to analyze the reflectivity difference of different earth surfaces covering four wave bands of blue, green, red and near infrared (shown in figure 1). Wherein, the vegetation has a small reflection peak in the green light wave band, and the reflectivity in the near infrared wave band is obviously higher than the reflectivity in the other three wave bands; the reflectivity of the bare ground in blue, green, red and near infrared four wave bands is in a trend of increasing at a constant speed; the reflectivity of the water body in four wave bands tends to decrease firstly and then increase, and a small reflection peak also appears occasionally in a green wave band due to the aquatic weeds. The reflection curve of the artificial ground surface is most complex due to the variety of materials, but the reflectivity curves of the color steel tile in four bands of blue, green, red and near infrared are obviously different from those of other ground objects due to the particularity of the materials, and the sample 4 in fig. 1(c) is the spectral reflection curve of the color steel tile.
As can be seen from fig. 1, the reflectivity characteristics and differences of the color steel tile (sample 4 of fig. 1 (c)) and the rest of the ground features in the four bands of blue, green, red and near infrared are embodied as:
1) the reflectivity of the color steel tile in a blue light wave band is about 0.25, which is obviously higher than other ground objects. The reflectivity of the rest artificial earth surfaces in the blue light wave band is lower than or slightly higher than 0.2, and the reflectivity of bare land and water in the blue light wave band is lower than 0.2;
2) the reflectivity of the color steel tile in a blue light wave band is far higher than that in a red light wave band, the difference value of the reflectivities is about 0.1, and the reflectivities of a bare ground and other artificial earth surfaces in the blue light wave band are lower than those in the red light wave band; although the reflectivity of the water body in the blue light wave band is higher than that in the red light wave band, the difference is only between 0.02 and 0.03 and is far smaller than that of the color steel tile;
3) the average reflectivity of the color steel tile in blue light, green light and near infrared bands is the highest and is about 0.25, the average reflectivity of vegetation in the three bands is lower than or slightly higher than 0.2, the average reflectivity of bare land in the three bands is less than 0.25, and the average reflectivity of water in the three bands is not higher than 0.18.
In summary, according to the above features and differences, it can be known that the reflectivity of the color steel tile in the blue light band is abnormally high, and the reflectivity in the blue light band is significantly higher than that in the red light band.
Therefore, the remote sensing image is subjected to the first step of waveband calculation RB×(RB-RR) This step can effectively highlight the features of the color steel tile. Because the interior of the same ground object has great difference and the characteristics of the same object and different spectrums can cause great interference to the identification precision, the embodiment performs the second step of waveband calculation 1-mean (R) on the remote sensing imageB+RG+RNIR) The step can further highlight the whole spectral characteristics of the color steel tile, and further achieve the purpose of reducing the spectral characteristic difference inside other ground objects. And finally, combining the two parts to form the following color steel tile extraction formula:
equation 1:
in the formula, RB，RG，RRAnd RNIRRespectively representing the reflectivity of a single pixel in the remote sensing image in four wave bands of blue, green, red and near infrared.
After the calculation of the formula 1, the pixel value of the color steel tile is significantly higher than that of the rest ground objects, and the result image shows bright white (fig. 2), the image on the left side of fig. 2 is a sample area overall effect image, and the image on the right side is a detail image of the color steel tile. And then, the color steel tiles can be extracted by setting a brightness threshold (for example, about 0.01, namely the area covered by the color steel tile factory where the pixel brightness in the image calculated and generated by the formula 1 is greater than 0.01). The method has the advantages that: the speed is high, the efficiency is high, and the method is suitable for extracting large-area color steel tiles; the disadvantages are that: the accuracy is relatively low and the selection of the threshold is subjective.
Example 2
On the basis of embodiment 1, this embodiment is further modified.
Based on the reflectivity characteristics and differences of the color steel tile and other ground features in four bands of red, green, blue and near infrared, the difference between the color steel tile and other ground features is further enhanced by improving the formula 1.
First, as can be seen from the spectral reflectance curve (fig. 1c, sample 4) of the color steel tile, the reflectance of the color steel tile in the blue light band is greater than that in the green light band, i.e., RB-RG>0. Most of vegetation, bare land and artificial land except color steel tiles can be effectively removed by the condition, because the reflectivity of the vegetation, the bare land and the artificial land except the color steel tiles in a blue light wave band is generally smaller than that in a green light wave band, namely RB-RG<0。
Then separating the color steel tiles from the water body and a small amount of ground objects which are not removed. The reflectivity of the color steel tile in the blue light wave band is far higher than that of the water body in the blue light wave band; the difference value of the reflectivity of the color steel tile in a green light wave band and a red light wave band is between 0.04 and 0.05, the difference value of the reflectivity of the water body in the green light wave band and the red light wave band is between 0.02 and 0.03, and the former is higher than the latter. In order to avoid the influence of a small amount of uneliminated ground objects, the embodiment is used for RG-RRUsing absolute values, i.e. | RG-RRL. Based on the above three characteristics, the first step of this embodiment adopts the formula RB×(RB-RR)×|RG-RR|）1/3The spectral characteristics of the water body and the ground objects which are not removed are restrained, and the spectral characteristics of the color steel tile are highlighted. The second step uses mean (R)NIR+RR)-mean(RB+RG+RR) Instead ofGeneration 1-mean (R)B+RG+RNIR) Becomes the denominator because mean (R)NIR-RR)-mean(RB+RG+RR) Has higher stability, and can obtain a more fixed optimal threshold (the stability is high, namely the difference between the color steel tile factory building and other ground objects can be enlarged, so that the difference between the color steel tile factory building and other ground objects forms a breaking point, namely the optimal threshold of figure 3). And finally, combining the two parts to form the following improved color steel tile extraction formula:
equation 2:
in the formula, RB，RG，RRAnd RNIRRespectively representing the reflectivity of a single pixel in the remote sensing image in four wave bands of blue, green, red and near infrared.
After the above formula operation, the image pixel brightness distribution curve has an obvious breaking point, the breaking point is an optimal threshold, the left side of the breaking point is a water body and a small amount of uneliminated other ground objects, the right side is a color steel tile, and the optimal threshold in the example is 0.255 (fig. 3). The finally extracted color steel tile also has higher precision and more complete outline. The left side of fig. 4 is the original remote sensing image map, and the right side of fig. 4 is the color steel tile extracted from the corresponding area.
The advantage of (equation 2) of this example over (equation 1) of example 1 is: the effect of extracting the color steel tile is better, and the precision is higher. Through multiple experiments, the formula 2 is adopted to extract the color steel tile, a breaking point, namely an optimal threshold value, is bound to appear, and the extraction result has objectivity; the disadvantages are that: the operation is relatively complicated and the efficiency is reduced.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (7)
1. A color steel tile factory building extraction method based on remote sensing images is characterized by comprising the following steps:
acquiring a remote sensing image, wherein the remote sensing image at least comprises blue, green, red and near-infrared wave bands; preprocessing the remote sensing image to obtain a spectral reflectivity image If(x, y), wherein f belongs to { B, G, R, NIR }, wherein x and y represent the coordinates of the pixel in the image, and B, G, R and NIR represent a blue light wave band, a green light wave band, a red light wave band and a near infrared wave band respectively;
step two, enhancing the remote sensing image of the color steel tile: respectively performing band operation RB×(RB-RR) Sum band operation 1-mean (R)B+RG+RNIR) (ii) a And finally, combining the two parts to form the following color steel tile extraction formula:
equation 1:
wherein R isB，RG，RRAnd RNIRRespectively representing the reflectivity of a single pixel in the remote sensing image in four wave bands of blue, green, red and near infrared;
setting a reasonable threshold value and extracting a color steel tile area; the reflectivity of the color steel tile in a blue light wave band is high, and the reflectivity in the blue light wave band is higher than that in a red light wave band, so that a first-step wave band operation R is performed on a remote sensing imageB×(RB-RR) Highlighting the characteristics of the color steel tile;
because the interior of the same ground object has great difference, the same object different spectrum characteristics can also cause great interference to the identification precision, and the second step of band operation 1-mean (R)B+RG+RNIR) Further highlighting the overall spectral characteristics of the color steel tile and achieving the purpose of reducing the spectral characteristic difference inside other ground objects.
2. The remote sensing image-based color steel tile factory building extraction method according to claim 1, wherein the threshold value in the third step is set to 0.01.
3. A color steel tile factory building extraction method based on remote sensing images is characterized by comprising the following steps:
acquiring a remote sensing image, wherein the remote sensing image at least comprises blue, green, red and near-infrared wave bands; preprocessing the remote sensing image to obtain a spectral reflectivity image If(x, y), wherein f belongs to { B, G, R, NIR }, wherein x and y represent the coordinates of the pixel in the image, and B, G, R and NIR represent a blue light wave band, a green light wave band, a red light wave band and a near infrared wave band respectively;
step two, enhancing the remote sensing image of the color steel tile: respectively performing band operation (R)B×(RB-RG)×|RG-RR|)1/3Sum band operation mean (R)NIR+RR)-mean(RB+RG+RR) (ii) a And finally, combining the two parts to form the following color steel tile extraction formula:
equation 2:
wherein R isB，RG，RRAnd RNIRRespectively representing the reflectivity of a single pixel in the remote sensing image in four wave bands of blue, green, red and near infrared;
after the calculation of the formula, the image pixel brightness distribution curve has obvious breaking points, the breaking points are optimal threshold values, the left sides of the breaking points are water bodies and a small amount of other ground objects which are not removed, and the right sides of the breaking points are color steel tiles.
4. The method for extracting color steel tile factory building based on remote sensing image according to claim 3, wherein said (R)B×(RB-RG)×|RG-RR|)1/3The spectral characteristics of the water body and the ground objects which are not removed are restrained, and the spectral characteristics of the color steel tile are highlighted; the mean (R)NIR+RR)-mean(RB+RG+RR) Has higher stability.
5. The utility model provides a various steel tile factory building extraction system based on remote sensing image which characterized in that, the system includes:
an image preprocessing module: the remote sensing image acquisition device is used for acquiring a remote sensing image, wherein the remote sensing image at least comprises blue, green, red and near infrared wave bands; the remote sensing image preprocessing module is used for preprocessing the remote sensing image to obtain a spectral reflectivity image;
color steel tile reinforcing module: respectively carrying out band operation on the remote sensing image, and combining two band operation results respectively serving as a numerator and a denominator into a color steel tile extraction formula;
the color steel tile reinforcing module: respectively carrying out wave band operation R on the remote sensing imagesB×(RB-RR) Sum band operation 1-mean (R)B+RG+RNIR) And finally combining the two to form the following color steel tile extraction formula:
equation 1:
wherein R isB，RG，RRAnd RNIRRespectively representing the reflectivity of a single pixel in the remote sensing image in four wave bands of blue, green, red and near infrared;
the system also comprises a threshold extraction module, wherein the threshold extraction module is used for setting a threshold and extracting the color steel tile area;
or, the color steel tile reinforcing module: respectively performing band operation (R) on the remote sensing imagesB×(RB-RG)×|RG-RR|)1/3Sum band operation mean (R)NIR+RR)-mean(RB+RG+RR) And then combining the two parts to form the following color steel tile extraction formula:
equation 2:
wherein R isB，RG，RRAnd RNIRRespectively representing the reflectivity of a single pixel in the remote sensing image in four wave bands of blue, green, red and near infrared.
6. An electronic device, comprising a memory and a processor, wherein the memory is configured to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method for color steel tile factory extraction according to any one of claims 1-4.
7. A computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute a method for implementing the extraction method of color steel tile factory building according to any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010902866.7A CN112033914B (en) | 2020-09-01 | 2020-09-01 | Color steel tile factory building extraction method based on remote sensing image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010902866.7A CN112033914B (en) | 2020-09-01 | 2020-09-01 | Color steel tile factory building extraction method based on remote sensing image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112033914A CN112033914A (en) | 2020-12-04 |
| CN112033914B true CN112033914B (en) | 2021-04-20 |
Family
ID=73590444
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010902866.7A Active CN112033914B (en) | 2020-09-01 | 2020-09-01 | Color steel tile factory building extraction method based on remote sensing image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112033914B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112800993A (en) * | 2021-02-03 | 2021-05-14 | 北华航天工业学院 | Regional scale industrial factory building information enhancement method based on discrete wavelet transform |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1959703A (en) * | 2006-11-24 | 2007-05-09 | 中国科学院上海技术物理研究所 | Realization method for automatic identifying residential areas in different type in city by using remote sensing images |
| CN106778629A (en) * | 2016-12-21 | 2017-05-31 | 中国科学院深圳先进技术研究院 | Greenhouse recognition methods and device |
| CN106934405A (en) * | 2017-03-21 | 2017-07-07 | 北京师范大学 | A kind of method of vinyl house extraction and cover degree inverting in intermediate-resolution remote sensing image |
| CN109087316A (en) * | 2018-09-07 | 2018-12-25 | 南京大学 | A kind of greenhouse extracting method and device based on remote sensing images |
| CN110390276A (en) * | 2019-07-04 | 2019-10-29 | 中科卫星应用德清研究院 | Green house recognition methods and system based on remote sensing big data |
| CN110852207A (en) * | 2019-10-29 | 2020-02-28 | 北京科技大学 | Blue roof building extraction method based on object-oriented image classification technology |
| CN111539318A (en) * | 2020-04-22 | 2020-08-14 | 洛阳师范学院 | Red ground object extraction method, device, storage medium and system |
| CN111539403A (en) * | 2020-07-13 | 2020-08-14 | 航天宏图信息技术股份有限公司 | Agricultural greenhouse identification method and device and electronic equipment |
-
2020
- 2020-09-01 CN CN202010902866.7A patent/CN112033914B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1959703A (en) * | 2006-11-24 | 2007-05-09 | 中国科学院上海技术物理研究所 | Realization method for automatic identifying residential areas in different type in city by using remote sensing images |
| CN106778629A (en) * | 2016-12-21 | 2017-05-31 | 中国科学院深圳先进技术研究院 | Greenhouse recognition methods and device |
| CN106934405A (en) * | 2017-03-21 | 2017-07-07 | 北京师范大学 | A kind of method of vinyl house extraction and cover degree inverting in intermediate-resolution remote sensing image |
| CN109087316A (en) * | 2018-09-07 | 2018-12-25 | 南京大学 | A kind of greenhouse extracting method and device based on remote sensing images |
| CN110390276A (en) * | 2019-07-04 | 2019-10-29 | 中科卫星应用德清研究院 | Green house recognition methods and system based on remote sensing big data |
| CN110852207A (en) * | 2019-10-29 | 2020-02-28 | 北京科技大学 | Blue roof building extraction method based on object-oriented image classification technology |
| CN111539318A (en) * | 2020-04-22 | 2020-08-14 | 洛阳师范学院 | Red ground object extraction method, device, storage medium and system |
| CN111539403A (en) * | 2020-07-13 | 2020-08-14 | 航天宏图信息技术股份有限公司 | Agricultural greenhouse identification method and device and electronic equipment |
Non-Patent Citations (2)
| Title |
|---|
| 基于GF－2遥感影像的塑料大棚提取方法对比;高梦婕 等;《中国农业大学学报》;20181231;第23卷(第8期);第125-134页 * |
| 基于高分辨率遥感影像的城区彩钢棚提取研究;李鹏元 等;《地理空间信息》;20170930;第15卷(第9期);摘要，第13-15、18页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112033914A (en) | 2020-12-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110390267B (en) | Mountain landscape building extraction method and device based on high-resolution remote sensing image | |
| CN108596103B (en) | High-resolution remote sensing image building extraction method based on optimal spectral index selection | |
| CN112381013B (en) | Urban vegetation inversion method and system based on high-resolution remote sensing image | |
| CN106023133B (en) | A kind of high-resolution remote sensing image Clean water withdraw method based on multiple features combining processing | |
| CN104504603B (en) | A kind of city trees and shrubs digitization system and site selecting method | |
| CN110849814A (en) | Remote sensing image processing method based on multi-source remote sensing satellite | |
| CN109767409B (en) | Landslide change detection method based on remote sensing image, storage medium and electronic equipment | |
| CN112183247B (en) | Laser point cloud data classification method based on multispectral image | |
| AU2021100848A4 (en) | A Regional Extraction Method of Ecological Restoration Project in the Grassland Based on the High-resolution Remote Sensing Images | |
| CN107688777A (en) | A kind of urban green space extracting method for cooperateing with multi-source Remote Sensing Images | |
| CN112033914B (en) | Color steel tile factory building extraction method based on remote sensing image | |
| CN112669459A (en) | Satellite image optimal mosaic line generation method based on feature library intelligent decision | |
| CN114049566B (en) | Method and device for detecting cloud and cloud shadow of land satellite image in step-by-step refinement manner | |
| CN108007880B (en) | Method for establishing tree species spectral curve polygon area index | |
| CN113705523A (en) | Layered city impervious surface extraction method based on optical and dual-polarization SAR fusion | |
| CN112329790A (en) | Rapid extraction method for urban impervious surface information | |
| CN110929739B (en) | Automatic impervious surface range remote sensing iterative extraction method | |
| CN115100609B (en) | Extra-high voltage construction disturbance range extraction method and system | |
| CN109801304B (en) | Building index construction and building area rapid extraction method for inhibiting bare land | |
| CN111914896A (en) | Urban local climate zone classification method based on multi-source data | |
| CN116129278A (en) | Land utilization classification and identification system based on remote sensing images | |
| CN115203624B (en) | Comprehensive evaluation method for surface environment at any moment based on time sequence remote sensing | |
| CN113902759B (en) | Space-spectrum information combined satellite-borne hyperspectral image segmentation and clustering method | |
| CN115018859A (en) | Urban built-up area remote sensing extraction method and system based on multi-scale space nesting | |
| CN115457325A (en) | Object and spectrum rule oriented multi-spectral remote sensing image unsupervised classification method |
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 | ||
| GR01 | Patent grant |