Plastic solid waste remote sensing automatic extraction method and device

Abstract

The invention discloses a plastic solid waste remote sensing automatic extraction method and device, and belongs to the technical field of satellite remote sensing. Based on high-resolution multispectral optical image data, the method comprises the following steps: firstly, carrying out preprocessing, then, in combination with different ground feature ground spectrum curve characteristics, firstly, extracting an impervious surface area, removing ground features such as vegetation, and then, carrying out road masking and water body masking, and removing a road and a water body. And then a plastic solid waste index is constructed, and the plastic garbage is separated from the impermeable surface. According to the invention, accurate identification and extraction of the plastic solid waste are realized, and the false alarm rate and the missing report rate are reduced; by utilizing the advantages of the remote sensing technology, rapid monitoring of a large-range area is realized, technical support is provided for solid waste environment supervision, and environmental protection and sustainable development are promoted. The automatic process of data processing and extraction is realized, the defects of manual monitoring are overcome, the working efficiency is improved, and the labor cost is reduced.

Description

Technical Field

[0001] The present invention relates to the field of satellite remote sensing technology, and in particular to a remote sensing automatic extraction method and device for plastic solid waste. Background Art

[0002] With the widespread use of plastic products, plastic pollution has become a global environmental problem, especially the increasingly serious problem of marine plastic pollution. Traditional manual monitoring methods are not only inefficient, but also difficult to cover wide areas. Remote sensing technology has shown great potential in environmental monitoring with its ability to obtain surface information over a large range and quickly. However, existing remote sensing technology still has problems such as insufficient accuracy and susceptibility to interference in the extraction of plastic solid waste, especially for the difficulty in identifying small, translucent plastic fragments or plastic fragments that are close to the environmental background. Summary of the invention

[0003] In order to solve the above technical problems, the present invention provides a remote sensing automatic extraction method and device for plastic solid waste, which realizes large-scale accurate identification and extraction of plastic solid waste and reduces the false alarm rate and missed alarm rate.

[0004] The present invention provides the following technical solutions:

[0005] A remote sensing automatic extraction method for plastic solid waste, the method comprising:

[0006] S1: Acquire a remote sensing image covering the area to be studied, wherein the remote sensing image includes a blue band, a green band, a red band and a near infrared band;

[0007] S2: preprocessing the remote sensing image;

[0008] S3: Extract impervious surface area based on preprocessed remote sensing images;

[0009] S4: Eliminate the road area and the water area in the impermeable surface area to obtain a target area;

[0010] S5: constructing a plastic solid waste index according to the target area;

[0011]

[0012] Wherein, PLI is the plastic solid waste index of any pixel in the target area, ρ B , G , R are the surface reflectance of the blue band, green band and red band of the pixel respectively;

[0013] S6: Extract plastic solid waste according to the plastic solid waste index of each pixel in the target area and the set plastic solid waste threshold to obtain a plastic solid waste area.

[0014] Further, the S3 includes:

[0015] S31: using the normalized vegetation index to remove vegetation areas from the pre-processed remote sensing image;

[0016] S32: Extract the impervious surface area from the remote sensing image after removing the vegetation area using the impervious surface index.

[0017] Further, the S31 includes:

[0018] S311: Calculate the Normalized Difference Vegetation Index NDVI of each pixel of the preprocessed remote sensing image;

[0019]

[0020] ρ NIR is the surface reflectance of the near-infrared band of the pixel of the remote sensing image;

[0021] S312: comparing the normalized vegetation index of each pixel with the set vegetation index threshold, and classifying the pixels whose normalized vegetation index is greater than the vegetation index threshold as vegetation areas;

[0022] S313: Eliminate vegetation areas from the pre-processed remote sensing image.

[0023] Further, the S32 includes:

[0024] S321: Calculate the impervious surface index VNISI of each pixel of the remote sensing image after removing the vegetation area;

[0025]

[0026] S322: Compare the impervious surface index of each pixel with the set impervious surface threshold range, and classify the pixels whose impervious surface index falls within the impervious surface threshold range as impervious surface areas.

[0027] Further, the S4 includes:

[0028] S41: Masking the roads in the impermeable surface area based on the road network data to remove the road area;

[0029] S42: Performing a water body mask on the area after the road is removed by using a normalized water body index, removing the water body area, and obtaining a target area.

[0030] Furthermore, the remote sensing image is a high-resolution optical remote sensing image, and S2 includes:

[0031] The remote sensing image is subjected to radiation calibration, atmospheric correction, orthorectification and image enhancement.

[0032] Further, the S6 includes:

[0033] The plastic solid waste index of each pixel is compared with the plastic solid waste threshold, and the pixels whose plastic solid waste index is greater than the plastic solid waste threshold are classified as plastic solid waste areas.

[0034] A remote sensing automatic extraction device for plastic solid waste, the device comprising:

[0035] A data preparation module is used to obtain remote sensing images covering the area to be studied, wherein the remote sensing images include a blue band, a green band, a red band, and a near-infrared band;

[0036] A preprocessing module, used for preprocessing the remote sensing image;

[0037] An impervious surface extraction module is used to extract the impervious surface area based on the preprocessed remote sensing image;

[0038] A mask module is used to remove the road area and the water area in the impermeable surface area to obtain a target area;

[0039] A plastic solid waste index calculation module, used to construct a plastic solid waste index according to the target area;

[0040]

[0041] Wherein, PLI is the plastic solid waste index of any pixel in the target area, ρ B , G , R are the surface reflectance of the blue band, green band and red band of the pixel respectively;

[0042] The plastic solid waste extraction module is used to extract plastic solid waste according to the plastic solid waste index of each pixel in the target area and the set plastic solid waste threshold to obtain a plastic solid waste area.

[0043] Furthermore, the impermeable surface extraction module includes:

[0044] The vegetation removal unit is used to remove vegetation areas from the pre-processed remote sensing image using the normalized vegetation index;

[0045] The impervious surface area extraction unit is used to extract the impervious surface area from the remote sensing image after the vegetation area is removed by using the impervious surface index.

[0046] Furthermore, the vegetation removal unit includes:

[0047] The normalized vegetation index calculation subunit is used to calculate the normalized vegetation index NDVI of each pixel of the preprocessed remote sensing image;

[0048]

[0049] ρ NIR is the surface reflectance of the near-infrared band of the pixel of the remote sensing image;

[0050] The vegetation area classification subunit is used to compare the normalized vegetation index of each pixel with the set vegetation index threshold, and classify the pixels whose normalized vegetation index is greater than the vegetation index threshold as vegetation areas;

[0051] The vegetation area removal unit is used to remove the vegetation area from the preprocessed remote sensing image.

[0052] Furthermore, the impermeable surface area extraction unit includes:

[0053] The impervious surface index calculation subunit is used to calculate the impervious surface index VNISI of each pixel of the remote sensing image after removing the vegetation area;

[0054]

[0055] The impervious surface area extraction subunit is used to compare the impervious surface index of each pixel with the set impervious surface threshold range, and classify the pixels whose impervious surface index falls within the impervious surface threshold range as impervious surface areas.

[0056] Furthermore, the mask module includes:

[0057] A road masking unit, used for masking the roads in the impermeable surface area based on the road network data to remove the road area;

[0058] The water body masking unit is used to perform water body masking on the area after the road is removed by normalizing the water body index, remove the water body area, and obtain the target area.

[0059] Furthermore, the remote sensing image is a high-resolution optical remote sensing image, and the preprocessing module includes:

[0060] The remote sensing image is subjected to radiation calibration, atmospheric correction, orthorectification and image enhancement.

[0061] Furthermore, the plastic solid waste extraction module includes:

[0062] The plastic solid waste index of each pixel is compared with the plastic solid waste threshold, and the pixels whose plastic solid waste index is greater than the plastic solid waste threshold are classified as plastic solid waste areas.

[0063] The present invention has the following beneficial effects:

[0064] The present invention realizes accurate identification and extraction of plastic solid waste, reduces false alarm rate and missed alarm rate; takes advantage of remote sensing technology to realize rapid monitoring of large areas, provides technical support for solid waste environmental supervision, and promotes environmental protection and sustainable development. It realizes the automated process of data processing and extraction, makes up for the shortcomings of manual monitoring, improves work efficiency, and reduces labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 This is a flow chart of the remote sensing automatic extraction method for plastic solid waste of the present invention;

[0066] Figure 2 Schematic diagram of the acquired remote sensing image;

[0067] Figure 3 for Figure 2 Schematic diagram of impervious surface area calculated from remote sensing images;

[0068] Figure 4 for Figure 2 Schematic diagram of plastic solid waste areas extracted from remote sensing images;

[0069] Figure 5 It is a schematic diagram of the surface reflectivity curve of typical landforms;

[0070] Figure 6 It is a schematic diagram of the remote sensing automatic extraction device for plastic solid waste of the present invention. DETAILED DESCRIPTION

[0071] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0072] Embodiment 1:

[0073] The embodiment of the present invention provides a remote sensing automatic extraction method for plastic solid waste, such as Figure 1-5 As shown, the method includes:

[0074] S1: Obtain a remote sensing image covering the area to be studied. The remote sensing image is a high-resolution optical remote sensing image, such as commonly used high-resolution optical images such as GF-1, GF-2, GF-6, etc., which include a blue band, a green band, a red band, and a near-infrared band.

[0075] S2: Preprocess the remote sensing image.

[0076] Preprocessing can include radiometric calibration, atmospheric correction, orthorectification and image enhancement.

[0077] S3: Extract impervious surface areas based on the preprocessed remote sensing images.

[0078] Impervious surfaces refer to surfaces that cannot be penetrated by water, usually hard surfaces such as buildings, roads, squares, parking lots, as well as land covered with artificial materials and urban construction areas. Plastic solid waste areas belong to a category of impervious surfaces, so it is necessary to extract the impervious surface area.

[0079] The present invention does not limit the method of extracting the impermeable surface area. In one example, the method includes the following steps:

[0080] S31: Use the normalized vegetation index to remove vegetation areas from the preprocessed remote sensing image.

[0081] The present invention utilizes the Normalized Difference Vegetation Index (NDVI) to exclude the vegetation-covered area from the study area, thereby extracting the land not covered by vegetation.

[0082] The specific vegetation extraction steps include:

[0083] S311: Calculate the Normalized Difference Vegetation Index NDVI of each pixel of the preprocessed remote sensing image.

[0084]

[0085] ρ NIR , R It is the surface reflectance of the near-infrared band and the red band of the pixels of the remote sensing image.

[0086] S312: Compare the normalized vegetation index of each pixel with the set vegetation index threshold, and classify the pixels whose normalized vegetation index is greater than the vegetation index threshold as vegetation areas.

[0087] S313: Eliminate vegetation areas from the pre-processed remote sensing image.

[0088] S32: Extract the impervious surface area from the remote sensing image after removing the vegetation area using the impervious surface index.

[0089] The present invention extracts the impervious surface area based on a specially constructed impervious surface index, and the specific method is as follows:

[0090] S321: Calculate the impervious surface index VNISI of each pixel of the remote sensing image after removing the vegetation area.

[0091]

[0092] S322: Compare the impervious surface index of each pixel with the set impervious surface threshold range, and classify the pixels whose impervious surface index falls within the impervious surface threshold range as impervious surface areas.

[0093] The remote sensing image before extracting the impervious surface area is as follows Figure 2 As shown, Figure 2 The area enclosed by the red border in the figure is the known plastic solid waste area. Figure 2 The extracted impervious surface area is as follows Figure 3 As shown, Figure 3 The area outside the white area is the impervious surface area.

[0094] S4: Eliminate the road area and water area in the impervious surface area to obtain the target area.

[0095] Specifically, the steps include:

[0096] S41: Masking the roads in the impervious surface area based on the road network data to remove the road area.

[0097] Road network data can be obtained from a geographic information system. After obtaining the road network data, the road network data is imported and the roads in the image are masked.

[0098] S42: Performing a water body mask on the area after the road is removed by using a normalized water body index, removing the water body area, and obtaining a target area.

[0099] Since water bodies may be confused with shadows of buildings in the city during classification, water bodies are masked and removed. The present invention removes water body areas by normalizing the water body index and the vegetation index. The specific implementation method is as follows:

[0100] S421: Calculate the normalized difference water index NDWI of each pixel of the remote sensing image.

[0101]

[0102] S422: Compare the normalized water index of each pixel with the set water index threshold, and classify the pixels whose normalized water index is greater than the water index threshold as water areas.

[0103] S5: Construct a plastic solid waste index based on target areas.

[0104] The spectral reflectance characteristics of each object in the extracted target area are as follows: Figure 5 As shown, it can be seen that the slope of the green-red band of bare land and red-roofed buildings is opposite to that of other landforms. Therefore, the red-roofed buildings and bare land can be eliminated by the slopes between different bands. Further analysis shows that the blue-red band slope of plastic solid waste is smaller than that of blue-roofed buildings and larger than that of roads. Therefore, the target landforms can be extracted by the difference in the blue-red band slopes. That is:

[0105]

[0106] Among them, ρ Rbarren , Gbarren are the reflectivity of bare ground in the red and green bands, ρ Bbuild , Rbuild are the reflectivity of the building in the blue band and the red band, ρ Broad , Rroad are the reflectivity of the road in the blue band and the red band, ρ Bplastic , Gplastic , Rplastic They are the reflectivity of plastic solid waste in the blue band, green band and red band respectively.

[0107] The plastic leakage extraction index is constructed from this. .

[0108] Among them, PLI is the plastic solid waste index of any pixel in the target area, ρ B , G , R The surface reflectance of the blue band, green band and red band of the pixel respectively. Multiply the formula by 10 4 The constant is used to expand the distinction between different objects after calculation.

[0109] S6: Extract plastic solid waste according to the plastic solid waste index of each pixel in the target area and the set plastic solid waste threshold to obtain the plastic solid waste area.

[0110] Specifically, the plastic solid waste index of each pixel is compared with the plastic solid waste threshold, and the pixels with a plastic solid waste index greater than the plastic solid waste threshold are classified as plastic solid waste areas. For example, the plastic solid waste threshold can be taken as 16000. Figure 2 The extracted plastic solid waste areas are as follows Figure 4 As shown, Figure 4 The middle blue area is the plastic solid waste area.

[0111] The present invention is based on high-resolution multispectral optical image data. It first performs preprocessing, then combines the ground spectral curve characteristics of different objects, first extracts the impermeable surface area, removes vegetation and other objects, and then performs road masking and water masking to remove roads and water bodies. Then, it constructs a plastic solid waste index to separate plastic waste from impermeable surfaces.

[0112] The present invention realizes accurate identification and extraction of plastic solid waste, reduces false alarm rate and missed alarm rate; takes advantage of remote sensing technology to realize rapid monitoring of large areas, provides technical support for solid waste environmental supervision, and promotes environmental protection and sustainable development. It realizes the automated process of data processing and extraction, makes up for the shortcomings of manual monitoring, improves work efficiency, and reduces labor costs.

[0113] Embodiment 2:

[0114] The embodiment of the present invention provides a remote sensing automatic extraction device for plastic solid waste, such as Figure 6 As shown, the device comprises:

[0115] The data preparation module 1 is used to obtain remote sensing images covering the area to be studied, and the remote sensing images include a blue band, a green band, a red band and a near-infrared band.

[0116] The preprocessing module 2 is used to preprocess the remote sensing image.

[0117] The impervious surface extraction module 3 is used to extract the impervious surface area according to the pre-processed remote sensing image.

[0118] The mask module 4 is used to remove the road area and the water area in the impermeable surface area to obtain the target area.

[0119] The plastic solid waste index calculation module 5 is used to construct a plastic solid waste index according to the target area.

[0120]

[0121] Among them, PLI is the plastic solid waste index of any pixel in the target area, ρ B , G , R They are the surface reflectance of the blue band, green band, and red band of the pixel respectively.

[0122] The plastic solid waste extraction module 6 is used to extract plastic solid waste according to the plastic solid waste index of each pixel in the target area and the set plastic solid waste threshold to obtain the plastic solid waste area.

[0123] The present invention realizes accurate identification and extraction of plastic solid waste, reduces false alarm rate and missed alarm rate; takes advantage of remote sensing technology to realize rapid monitoring of large areas, provides technical support for solid waste environmental supervision, and promotes environmental protection and sustainable development. It realizes the automated process of data processing and extraction, makes up for the shortcomings of manual monitoring, improves work efficiency, and reduces labor costs.

[0124] As an improvement of the embodiment of the present invention, the aforementioned impervious surface extraction module includes:

[0125] The vegetation removal unit is used to remove vegetation areas from the pre-processed remote sensing image using the normalized vegetation index.

[0126] The impervious surface area extraction unit is used to extract the impervious surface area from the remote sensing image after the vegetation area is removed by using the impervious surface index.

[0127] Specifically, the vegetation removal unit includes:

[0128] The normalized difference vegetation index calculation subunit is used to calculate the normalized difference vegetation index NDVI of each pixel of the preprocessed remote sensing image.

[0129]

[0130] ρ NIR It is the surface reflectance of the near-infrared band of the pixels of the remote sensing image.

[0131] The vegetation area classification subunit is used to compare the normalized vegetation index of each pixel with the set vegetation index threshold, and classify the pixels whose normalized vegetation index is greater than the vegetation index threshold as vegetation areas.

[0132] The vegetation area removal unit is used to remove the vegetation area from the preprocessed remote sensing image.

[0133] Accordingly, the impervious surface area extraction unit includes:

[0134] The impervious surface index calculation subunit is used to calculate the impervious surface index VNISI of each pixel of the remote sensing image after the vegetation area is removed.

[0135]

[0136] The impervious surface area extraction subunit is used to compare the impervious surface index of each pixel with the set impervious surface threshold range, and classify the pixels whose impervious surface index falls within the impervious surface threshold range as impervious surface areas.

[0137] As another improvement of the embodiment of the present invention, the mask module includes:

[0138] The road mask unit is used to mask the roads in the impervious surface area based on the road network data to remove the road area.

[0139] The water body masking unit is used to perform water body masking on the area after the road is removed by normalizing the water body index, remove the water body area, and obtain the target area.

[0140] The remote sensing image in the present invention is a high-resolution optical remote sensing image, and the corresponding preprocessing module includes:

[0141] Perform radiation calibration, atmospheric correction, orthorectification and image enhancement on remote sensing images.

[0142] As an example, the plastic solid waste extraction module includes:

[0143] The plastic solid waste index of each pixel is compared with the plastic solid waste threshold, and the pixels whose plastic solid waste index is greater than the plastic solid waste threshold are classified as plastic solid waste areas.

[0144] The device provided in the embodiment of the present invention has the same implementation principle and technical effects as the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment 1. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the aforementioned devices and units can all refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here.

[0145] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present invention, which are used to illustrate the technical solutions of the present invention rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the aforementioned embodiments, those of ordinary skill in the art should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the aforementioned embodiments within the technical scope disclosed by the present invention, or can easily conceive of changes, or make equivalent replacements for some of the technical features therein. Such modifications, changes or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the protection scope of the present invention.

Claims

1. A remote sensing automatic extraction method for plastic solid waste, characterized in that: The method comprises: S1: Acquire a remote sensing image covering the area to be studied, wherein the remote sensing image includes a blue band, a green band, a red band and a near infrared band; S2: preprocessing the remote sensing image; S3: Extract impervious surface area based on preprocessed remote sensing images; S4: Eliminate the road area and the water area in the impermeable surface area to obtain a target area; S5: constructing a plastic solid waste index according to the target area; Wherein, PLI is the plastic solid waste index of any pixel in the target area, ρ B , G , R are the surface reflectance of the blue band, green band and red band of the pixel respectively; S6: Extract plastic solid waste according to the plastic solid waste index of each pixel in the target area and the set plastic solid waste threshold to obtain a plastic solid waste area.

2. The method for automatic remote sensing extraction of plastic solid waste according to claim 1, characterized in that: The S3 includes: S31: using the normalized vegetation index to remove vegetation areas from the pre-processed remote sensing image; S32: Extract the impervious surface area from the remote sensing image after removing the vegetation area using the impervious surface index.

3. The method for automatic remote sensing extraction of plastic solid waste according to claim 2, characterized in that: The S31 includes: S311: Calculate the Normalized Difference Vegetation Index NDVI of each pixel of the preprocessed remote sensing image; ρ NIR is the surface reflectance of the near-infrared band of the pixel of the remote sensing image; S312: comparing the normalized vegetation index of each pixel with the set vegetation index threshold, and classifying the pixels whose normalized vegetation index is greater than the vegetation index threshold as vegetation areas; S313: Eliminate vegetation areas from the pre-processed remote sensing image.

4. The method for automatic remote sensing extraction of plastic solid waste according to claim 3 is characterized in that: The S32 includes: S321: Calculate the impervious surface index VNISI of each pixel of the remote sensing image after removing the vegetation area; S322: Compare the impervious surface index of each pixel with the set impervious surface threshold range, and classify the pixels whose impervious surface index falls within the impervious surface threshold range as impervious surface areas.

5. The method for automatic remote sensing extraction of plastic solid waste according to any one of claims 1 to 4, characterized in that: The S4 includes: S41: Masking the roads in the impermeable surface area based on the road network data to remove the road area; S42: Performing a water body mask on the area after the road is removed by using a normalized water body index, removing the water body area, and obtaining a target area.

6. The method for automatic remote sensing extraction of plastic solid waste according to claim 5, characterized in that: The remote sensing image is a high-resolution optical remote sensing image, and S2 includes: The remote sensing image is subjected to radiation calibration, atmospheric correction, orthorectification and image enhancement.

7. The method for automatic remote sensing extraction of plastic solid waste according to claim 6, characterized in that: The S6 includes: The plastic solid waste index of each pixel is compared with the plastic solid waste threshold, and the pixels whose plastic solid waste index is greater than the plastic solid waste threshold are classified as plastic solid waste areas.

8. A remote sensing automatic extraction device for plastic solid waste, characterized in that: The device comprises: A data preparation module is used to obtain remote sensing images covering the area to be studied, wherein the remote sensing images include a blue band, a green band, a red band, and a near-infrared band; A preprocessing module, used for preprocessing the remote sensing image; An impervious surface extraction module is used to extract the impervious surface area based on the preprocessed remote sensing image; A mask module is used to remove the road area and the water area in the impermeable surface area to obtain a target area; A plastic solid waste index calculation module, used to construct a plastic solid waste index according to the target area; Wherein, PLI is the plastic solid waste index of any pixel in the target area, ρ B , G , R are the surface reflectance of the blue band, green band and red band of the pixel respectively; The plastic solid waste extraction module is used to extract plastic solid waste according to the plastic solid waste index of each pixel in the target area and the set plastic solid waste threshold to obtain a plastic solid waste area.

9. The remote sensing automatic extraction device for plastic solid waste according to claim 8 is characterized in that: The impervious surface extraction module comprises: The vegetation removal unit is used to remove vegetation areas from the pre-processed remote sensing image using the normalized vegetation index; The impervious surface area extraction unit is used to extract the impervious surface area from the remote sensing image after the vegetation area is removed by using the impervious surface index.

10. The automatic remote sensing extraction device for plastic solid waste according to claim 8 or 9, characterized in that: The mask module comprises: A road masking unit, used for masking the roads in the impermeable surface area based on the road network data to remove the road area; The water body masking unit is used to perform water body masking on the area after the road is removed by normalizing the water body index, remove the water body area, and obtain the target area.

Images