Method and apparatus for extracting buildings and demolition waste from remote sensing images

Abstract

The application discloses a kind of based on remote sensing image's building and demolition waste extraction method and device, belong to remote sensing monitoring technical field.It includes: obtaining the remote sensing image covering the region to be studied, the remote sensing image includes blue band, green band, red band and near infrared band;Remote sensing image is pretreated;Using normalized vegetation index, normalized water index, normalized red roof index and normalized blue roof index to remove vegetation area, water area, red roof and blue roof from the remote sensing image after pretreatment, obtain initial extraction image;Building and demolition waste index is constructed, and according to the building and demolition waste index, building and demolition waste extraction is carried out to initial extraction image, to obtain building and demolition waste area.The application realizes the automatic identification and fine extraction of building and demolition waste in a wide range of area, improves the accuracy, automation degree and practical application effect of identification and extraction.

Description

Technical Field

[0001] This invention relates to the field of remote sensing monitoring technology, specifically to a method and apparatus for extracting construction and demolition waste based on remote sensing images. Background Technology

[0002] In recent years, with the continuous advancement of urban renewal, old city renovation, infrastructure construction, and demolition work, the amount of construction and demolition waste (hereinafter referred to as construction and demolition waste) has continued to increase. If this solid waste is not disposed of in a timely, standardized, and effective manner, it can easily lead to a series of ecological and environmental risks such as land resource occupation, dust pollution, and water pollution. Therefore, carrying out rapid identification and dynamic monitoring of construction and demolition waste is of great significance for improving the level of solid waste pollution source supervision and supporting the refined governance of cities.

[0003] Existing methods for monitoring construction and demolition waste mainly include manual inspections, on-site verification, and localized drone surveys. While these methods are applicable to small areas and localized regions, they suffer from limitations such as limited coverage, high reliance on manual labor, high monitoring costs, and long update cycles, making them unsuitable for large-scale, routine, and dynamic regulatory requirements. High-resolution multispectral remote sensing imagery offers advantages such as wide coverage, high acquisition efficiency, and rapid temporal updates, providing a feasible approach for regional-scale identification of construction and demolition waste.

[0004] However, because the spectral characteristics of buildings and demolition waste in remote sensing images are quite similar to those of bare soil, roads, and buildings, there is a clear phenomenon of "foreign objects with similar spectra," which can easily lead to confusion in identification. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a method and apparatus for extracting construction and demolition waste based on remote sensing imagery. This method enables automatic identification and precise extraction of construction and demolition waste over a large area, improving the accuracy, automation level, and practical application effectiveness of identification and extraction.

[0006] The technical solution provided by this invention is as follows:

[0007] A method for extracting construction and demolition waste based on remote sensing imagery, the method comprising:

[0008] S1: Acquire remote sensing images covering the area to be studied, the remote sensing images including blue band, green band, red band and near-infrared band;

[0009] S2: Preprocess the remote sensing image;

[0010] S3: Using the normalized vegetation index, normalized water index, normalized red roof index, and normalized blue roof index, vegetation areas, water areas, red roofs, and blue roofs are removed from the preprocessed remote sensing image to obtain the initial extracted image.

[0011] S4: Construct a building and demolition waste index, and extract building and demolition waste from the initial extracted image based on the building and demolition waste index to obtain the building and demolition waste area.

[0012] Furthermore, the formula for calculating the construction and demolition waste index is as follows:

[0013]

[0014] or,

[0015]

[0016] in, The building and demolition waste index for any pixel in the initially extracted image. These represent the reflectance of the pixel in the near-infrared, red, green, and blue bands, respectively.

[0017] Furthermore, the calculation formulas for the normalized vegetation index, normalized water index, normalized red roof index, and normalized blue roof index are as follows:

[0018]

[0019]

[0020]

[0021]

[0022] in, These are the Normalized Difference Vegetation Index, Normalized Water Index, Normalized Red Roof Index, and Normalized Blue Roof Index, respectively.

[0023] Furthermore, vegetation areas, water areas, red roofs, and blue roofs are excluded in the following ways:

[0024] The normalized vegetation index, normalized water index, normalized red roof index, and normalized blue roof index of each pixel in the preprocessed remote sensing image are compared with the set threshold values ​​for vegetation index, water index, red roof index, and blue roof index, respectively.

[0025] Pixels with a normalized vegetation index greater than the vegetation index threshold are removed; pixels with a normalized water index greater than the water index threshold are removed; pixels with a normalized red roof index greater than the red roof index threshold are removed; pixels with a normalized blue roof index greater than the blue roof index threshold are removed.

[0026] Furthermore, construction and demolition waste is extracted in the following ways:

[0027] The building and demolition waste index of each pixel in the initial extracted image is compared with the set waste index threshold, and pixels with building and demolition waste indices greater than the waste index threshold are classified as building and demolition waste areas.

[0028] Furthermore, the preprocessing includes radiometric calibration, atmospheric correction, orthorectification, and image fusion.

[0029] A device for extracting construction and demolition waste based on remote sensing imagery, the device comprising:

[0030] The data acquisition module is used to acquire remote sensing images covering the area to be studied, including blue band, green band, red band and near-infrared band;

[0031] The preprocessing module is used to preprocess the remote sensing images;

[0032] The removal module is used to remove vegetation areas, water areas, red roofs and blue roofs from the preprocessed remote sensing image using the normalized vegetation index, normalized water index, normalized red roof index and normalized blue roof index to obtain the initial extracted image.

[0033] The extraction module is used to construct a construction and demolition waste index and extract construction and demolition waste from the initial extracted image based on the construction and demolition waste index to obtain the construction and demolition waste area.

[0034] Furthermore, the formula for calculating the construction and demolition waste index is as follows:

[0035]

[0036] or,

[0037]

[0038] in, The building and demolition waste index for any pixel in the initially extracted image. These represent the reflectance of the pixel in the near-infrared, red, green, and blue bands, respectively.

[0039] Furthermore, the calculation formulas for the normalized vegetation index, normalized water index, normalized red roof index, and normalized blue roof index are as follows:

[0040]

[0041]

[0042]

[0043]

[0044] in, These are the Normalized Difference Vegetation Index, Normalized Water Index, Normalized Red Roof Index, and Normalized Blue Roof Index, respectively.

[0045] Furthermore, vegetation areas, water areas, red roofs, and blue roofs are excluded in the following ways:

[0046] The normalized vegetation index, normalized water index, normalized red roof index, and normalized blue roof index of each pixel in the preprocessed remote sensing image are compared with the set threshold values ​​for vegetation index, water index, red roof index, and blue roof index, respectively.

[0047] Pixels with a normalized vegetation index greater than the vegetation index threshold are removed; pixels with a normalized water index greater than the water index threshold are removed; pixels with a normalized red roof index greater than the red roof index threshold are removed; pixels with a normalized blue roof index greater than the blue roof index threshold are removed.

[0048] Furthermore, construction and demolition waste is extracted in the following ways:

[0049] The building and demolition waste index of each pixel in the initial extracted image is compared with the set waste index threshold, and pixels with building and demolition waste indices greater than the waste index threshold are classified as building and demolition waste areas.

[0050] Furthermore, the preprocessing includes radiometric calibration, atmospheric correction, orthorectification, and image fusion.

[0051] The present invention has the following beneficial effects:

[0052] This invention compares the spectral curves of buildings and demolition waste with various typical land features. Based on the comparison results, a two-step strategy is adopted: first, easily distinguishable vegetation, water bodies, red roofs, and blue roofs are removed; then, difficult-to-distinguish urban high-rises, roads, and bare soil are removed. Through a hierarchical extraction strategy from easy to difficult, various land feature information is gradually removed, effectively reducing the interference of complex background conditions on the identification results of buildings and demolition waste.

[0053] To address the problems of confusion, low extraction accuracy, and insufficient automation in existing remote sensing identification technologies, which often involve "similar spectra of dissimilar objects" such as construction and demolition waste and bare soil, roads, and buildings, this invention, after detailed analysis of the spectral characteristics of easily confused objects like roads, urban buildings, and bare soil, constructs a construction and demolition waste index. This index amplifies the differences between roads, urban buildings, bare soil, and construction and demolition waste, thereby highlighting their representation in images. This maximizes the suppression of confused objects, effectively reducing confusion between construction and demolition waste and similar objects like bare soil and roads, and improving the accuracy and automation of remote sensing extraction.

[0054] This invention comprehensively employs remote sensing image preprocessing, spectral analysis, threshold segmentation, and other technical means. It is applicable to high-resolution multispectral optical remote sensing images such as Gaofen-2, and can achieve automatic identification and precise extraction of irregular dumping areas of construction and demolition waste over a large area. This improves the accuracy, automation, and practical application effect of identification and extraction, and provides reliable technical support for solid waste environmental supervision, illegal dumping inspection, dynamic monitoring of disposal sites, and refined urban governance. It has good prospects for business applications. Attached Figure Description

[0055] Figure 1 This is a flowchart of the method for extracting construction and demolition waste based on remote sensing images according to the present invention;

[0056] Figure 2 Here is an example image of the preprocessed remote sensing image;

[0057] Figure 3 A comparative map of the spectral characteristics of building and demolition waste and other major land features;

[0058] Figure 4 for Figure 2 A schematic diagram of the extracted construction and demolition waste area;

[0059] Figure 5 This is a schematic diagram of the construction and demolition waste extraction device based on remote sensing images according to the present invention. Detailed Implementation

[0060] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0061] This invention provides a method for extracting construction and demolition waste based on remote sensing images, which overcomes the shortcomings of existing construction and demolition waste monitoring methods that mainly rely on manual inspections, on-site verification, and local drone surveys, such as limited coverage, low monitoring efficiency, poor timeliness, difficulty in meeting the needs of large-scale dynamic supervision, and confusion caused by "foreign objects with similar spectra".

[0062] like Figure 1 As shown, the method includes:

[0063] S1: Acquire remote sensing images covering the area to be studied. The remote sensing images include blue band, green band, red band, and near-infrared band.

[0064] The remote sensing imagery described in this invention is high-resolution multispectral imagery, such as imagery from the Gaofen-2 satellite. This data source is stable, acquisition costs are relatively low, and it is easy to promote and apply. To study the spectral characteristics of construction and demolition waste, this invention can also obtain sample data of construction and demolition waste, as well as auxiliary geographic information data.

[0065] S2: Preprocess the remote sensing images.

[0066] For example, preprocessing includes sequentially performing radiometric calibration, atmospheric correction, orthorectification, and image fusion on the remote sensing image to improve its geometric positioning accuracy and spectral reliability. The ultimate goal is to obtain high-resolution surface reflectance data, providing high-quality foundational data for the identification of construction and demolition waste. An example of a preprocessed remote sensing image is shown below. Figure 2 As shown.

[0067] To accurately discover the spectral characteristics of construction and demolition waste, this invention compares the spectral curves of construction and demolition waste with typical land features such as vegetation, water bodies, buildings (including urban high-rises, red roofs, and blue roofs), roads, and bare soil, and analyzes the differences in the blue, green, red, and near-infrared bands to establish a typical spectral feature expression system for the identification of construction and demolition waste.

[0068] Comparison of spectral curves of various land features, such as Figure 3 As shown, comparison revealed that the spectral curves of vegetation, water bodies, red roofs, and blue roofs differed significantly from those of buildings and demolition waste, while the spectral curves of urban high-rises, roads, and bare soil showed spectral similarity to those of buildings and demolition waste.

[0069] Based on this, the present invention determines a two-step overall strategy for extracting building and demolition waste: first removing vegetation, water bodies, red roofs, and blue roofs, and then removing urban high-rise buildings, roads, and bare soil.

[0070] S3: Using the normalized vegetation index, normalized water index, normalized red roof index, and normalized blue roof index, vegetation areas, water areas, red roofs, and blue roofs are removed from the preprocessed remote sensing image to obtain the initial extracted image.

[0071] This invention utilizes the characteristic that vegetation has high reflectivity in the near-infrared band and low reflectivity in the red band. (Normalized Difference Vegetation Index) Vegetation was removed; based on the characteristic that water bodies have high reflectance in the green band and low reflectance in the near-infrared band, [the following was used]... (Normalized Difference Water Index) excluding water bodies; based on the characteristic that red roofs have high reflectivity in the red band and low reflectivity in the green band, a [data structure / indices] is constructed. (Normalized Red Roof Index) Red roofs were removed; based on the characteristic that blue roofs have high reflectivity in the blue band and low reflectivity in the green band, a normalized red roof index was constructed. (Normalized Blue Roof Index) Remove blue roofs.

[0072] The formulas for calculating each index are as follows:

[0073]

[0074]

[0075]

[0076]

[0077] in, These represent the reflectance of the pixel in the near-infrared, red, green, and blue bands, respectively.

[0078] When removing vegetation areas, water areas, red roofs, and blue roofs, a threshold segmentation method can be used, as follows:

[0079] The normalized vegetation index, normalized water index, normalized red roof index, and normalized blue roof index of each pixel in the preprocessed remote sensing image are compared with the set threshold values ​​for vegetation index, water index, red roof index, and blue roof index, respectively.

[0080] Pixels with a normalized vegetation index greater than the vegetation index threshold, pixels with a normalized water index greater than the water index threshold, pixels with a normalized red roof index greater than the red roof index threshold, and pixels with a normalized blue roof index greater than the blue roof index threshold are removed.

[0081] Regarding red and blue roofs, the following characteristics are observed:

[0082] (1) Blue and red roofs are numerous and quite common.

[0083] (2) Blue roofs, red roofs and building and demolition wastes have significant spectral differences and can be effectively identified by a simple normalization index.

[0084] Therefore, blue and red roofs are excluded beforehand. Other roofs are generally categorized as subsequent urban high-rises (similar to urban high-rises in terms of material, such as concrete), and are distinguished by the construction and demolition waste index.

[0085] S4: Construct a building and demolition waste index, and extract building and demolition waste from the initial image based on the building and demolition waste index to obtain the building and demolition waste area.

[0086] The spectral characteristics of urban high-rise buildings, roads, and bare soil are quite similar to those of construction and demolition waste, but careful analysis reveals the following subtle differences in their spectral curves:

[0087] 1. The reflectivity of building and demolition waste and bare soil differs more significantly in the near-infrared and red bands, and in the red and green bands than that of urban high-rise buildings and roads, thus allowing for effective differentiation between the two.

[0088] 2. Further comparison of building and demolition waste and bare soil revealed that the reflectivity of bare soil in the green and blue bands was significantly greater than that of building and demolition waste. This characteristic can be used to effectively distinguish between the two.

[0089] Based on the above differences, in order to amplify the differences among these four types of land features, a square function and an exponential function are introduced to construct a building and demolition waste index. This index effectively eliminates interference from bare soil, roads, and urban high-rise buildings, thus highlighting construction and demolition waste. Its formula is as follows:

[0090]

[0091] or,

[0092]

[0093] Based on the constructed construction and demolition waste index described above, a threshold segmentation method can be used to automatically identify and extract construction and demolition waste within the study area. The specific implementation process is as follows:

[0094] The building and demolition waste index of each pixel in the initial image is compared with the set waste index threshold. Pixels with a building and demolition waste index greater than the waste index threshold are classified as building and demolition waste areas.

[0095] This invention utilizes a threshold segmentation method to gradually eliminate various land cover information, thereby automatically extracting building and demolition waste within the study area and obtaining its spatial distribution. Experimental verification shows that when NDVI < 0.2 (vegetation index threshold), the influence of vegetation can be eliminated; when NDWI < 0 (water index threshold), the influence of water bodies can be eliminated; when NBRI < 0 (blue roof index threshold), the influence of blue roofs can be eliminated; when NRRI < 0.1 (red roof index threshold), the influence of red roofs can be eliminated; and when CDDI is greater than the waste index threshold (when the calculation formula is (1), the waste index threshold is 10; when the calculation formula is (2), the waste index threshold is 3), the influence of bare soil, urban high-rise buildings, and roads can be eliminated, thus obtaining the area of ​​building and demolition waste. Figure 2 The extracted building and demolition waste areas, such as Figure 4 As shown.

[0096] After obtaining the aforementioned building and demolition waste areas, post-processing of the results can be carried out, specifically including:

[0097] The study involved patch screening, boundary optimization, hole filling, and vectorization of the building and demolition waste areas. The identified attributes (latitude, longitude, area, location, etc.) were also edited. Ultimately, the spatial distribution of building and demolition waste in the study area, along with corresponding area and location attribute information, was obtained.

[0098] This invention compares the spectral curves of buildings and demolition waste with various typical land features. Based on the comparison results, a two-step strategy is adopted: first, easily distinguishable vegetation, water bodies, red roofs, and blue roofs are removed; then, difficult-to-distinguish urban high-rises, roads, and bare soil are removed. Through a hierarchical extraction strategy from easy to difficult, various land feature information is gradually removed, effectively reducing the interference of complex background conditions on the identification results of buildings and demolition waste.

[0099] To address the problems of confusion, low extraction accuracy, and insufficient automation in existing remote sensing identification technologies, which often involve "similar spectra of dissimilar objects" such as construction and demolition waste and bare soil, roads, and buildings, this invention, after detailed analysis of the spectral characteristics of easily confused objects like roads, urban buildings, and bare soil, constructs a construction and demolition waste index. This index amplifies the differences between roads, urban buildings, bare soil, and construction and demolition waste, thereby highlighting their representation in images. This maximizes the suppression of confused objects, effectively reducing confusion between construction and demolition waste and similar objects like bare soil and roads, and improving the accuracy and automation of remote sensing extraction.

[0100] This invention comprehensively employs remote sensing image preprocessing, spectral analysis, threshold segmentation, and other technical means. It is applicable to high-resolution multispectral optical remote sensing images such as Gaofen-2, and can achieve automatic identification and precise extraction of irregular dumping areas of construction and demolition waste over a large area. This improves the accuracy, automation, and practical application effect of identification and extraction, and provides reliable technical support for solid waste environmental supervision, illegal dumping inspection, dynamic monitoring of disposal sites, and refined urban governance. It has good prospects for business applications.

[0101] This invention also provides a device for extracting construction and demolition waste based on remote sensing imagery, such as... Figure 5 As shown, the device includes:

[0102] Data acquisition module 1 is used to acquire remote sensing images covering the area to be studied. The remote sensing images include blue band, green band, red band and near-infrared band.

[0103] Preprocessing module 2 is used to preprocess remote sensing images. The preprocessing includes radiometric calibration, atmospheric correction, orthorectification, and image fusion.

[0104] The removal module 3 is used to remove vegetation areas, water areas, red roofs, and blue roofs from the preprocessed remote sensing image using the normalized vegetation index, normalized water index, normalized red roof index, and normalized blue roof index, to obtain the initial extracted image.

[0105] Extraction module 4 is used to construct the construction and demolition waste index and extract construction and demolition waste from the initial extracted image based on the construction and demolition waste index to obtain the construction and demolition waste area.

[0106]

[0107] or,

[0108]

[0109] in, The building and demolition waste index for any pixel in the initially extracted image. These represent the reflectance of the pixel in the near-infrared, red, green, and blue bands, respectively.

[0110] Specifically, the calculation formulas for the Normalized Difference Vegetation Index (NDVI), Normalized Water Index (NDI), Normalized Red Roof Index (NRDI), and Normalized Blue Roof Index (NRDI) are as follows:

[0111]

[0112]

[0113]

[0114]

[0115] in, These are the Normalized Difference Vegetation Index, Normalized Water Index, Normalized Red Roof Index, and Normalized Blue Roof Index, respectively.

[0116] Accordingly, vegetated areas, water areas, red roofs, and blue roofs can be removed in the following ways:

[0117] The normalized vegetation index, normalized water index, normalized red roof index, and normalized blue roof index of each pixel in the preprocessed remote sensing image are compared with the set threshold values ​​for vegetation index, water index, red roof index, and blue roof index, respectively.

[0118] Pixels with a normalized vegetation index greater than the vegetation index threshold, pixels with a normalized water index greater than the water index threshold, pixels with a normalized red roof index greater than the red roof index threshold, and pixels with a normalized blue roof index greater than the blue roof index threshold are removed.

[0119] Furthermore, construction and demolition waste is extracted in the following manner:

[0120] The building and demolition waste index of each pixel in the initial image is compared with the set waste index threshold. Pixels with a building and demolition waste index greater than the waste index threshold are classified as building and demolition waste areas.

[0121] The apparatus provided in this embodiment of the invention operates on the same principle and produces the same technical effects as the aforementioned method embodiments. For the sake of brevity, any parts not mentioned in the apparatus embodiments can be referred to the corresponding content in the aforementioned method embodiments. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the apparatus and units described above can all be referred to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0122] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit them. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the scope of the technology disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention.

Claims

1. A method for extracting construction and demolition waste based on remote sensing imagery, characterized in that, The method includes: S1: Acquire remote sensing images covering the area to be studied, the remote sensing images including blue band, green band, red band and near-infrared band; S2: Preprocess the remote sensing image; S3: Using the normalized vegetation index, normalized water index, normalized red roof index, and normalized blue roof index, vegetation areas, water areas, red roofs, and blue roofs are removed from the preprocessed remote sensing image to obtain the initial extracted image. S4: Construct a building and demolition waste index, and extract building and demolition waste from the initial extracted image based on the building and demolition waste index to obtain the building and demolition waste area.

2. The method for extracting construction and demolition waste based on remote sensing imagery according to claim 1, characterized in that, The formula for calculating the construction and demolition waste index is as follows: in, The building and demolition waste index for any pixel in the initially extracted image. These represent the reflectance of the pixel in the near-infrared, red, green, and blue bands, respectively.

3. The method for extracting construction and demolition waste based on remote sensing imagery according to claim 1, characterized in that, The formula for calculating the construction and demolition waste index is as follows: in, The building and demolition waste index for any pixel in the initially extracted image. These represent the reflectance of the pixel in the near-infrared, red, green, and blue bands, respectively.

4. The method for extracting construction and demolition waste based on remote sensing imagery according to any one of claims 1-3, characterized in that, The formulas for calculating the Normalized Difference Vegetation Index, Normalized Water Index, Normalized Red Roof Index, and Normalized Blue Roof Index are as follows: in, These are the Normalized Difference Vegetation Index, Normalized Water Index, Normalized Red Roof Index, and Normalized Blue Roof Index, respectively.

5. The method for extracting construction and demolition waste based on remote sensing imagery according to claim 4, characterized in that, Vegetated areas, water areas, red roofs, and blue roofs were removed using the following methods: The normalized vegetation index, normalized water index, normalized red roof index, and normalized blue roof index of each pixel in the preprocessed remote sensing image are compared with the set threshold values ​​for vegetation index, water index, red roof index, and blue roof index, respectively. Pixels with a normalized vegetation index greater than the vegetation index threshold are removed; pixels with a normalized water index greater than the water index threshold are removed; pixels with a normalized red roof index greater than the red roof index threshold are removed; pixels with a normalized blue roof index greater than the blue roof index threshold are removed.

6. The method for extracting construction and demolition waste based on remote sensing imagery according to claim 5, characterized in that, Construction and demolition waste shall be extracted in the following manner: The building and demolition waste index of each pixel in the initial extracted image is compared with the set waste index threshold, and pixels with building and demolition waste indices greater than the waste index threshold are classified as building and demolition waste areas.

7. The method for extracting construction and demolition waste based on remote sensing imagery according to claim 6, characterized in that, The preprocessing includes radiometric calibration, atmospheric correction, orthorectification, and image fusion.

8. A device for extracting construction and demolition waste based on remote sensing imagery, characterized in that, The device includes: The data acquisition module is used to acquire remote sensing images covering the area to be studied, including blue band, green band, red band and near-infrared band; The preprocessing module is used to preprocess the remote sensing images; The removal module is used to remove vegetation areas, water areas, red roofs and blue roofs from the preprocessed remote sensing image using the normalized vegetation index, normalized water index, normalized red roof index and normalized blue roof index to obtain the initial extracted image. The extraction module is used to construct a construction and demolition waste index and extract construction and demolition waste from the initial extracted image based on the construction and demolition waste index to obtain the construction and demolition waste area.

9. The construction and demolition waste extraction device based on remote sensing imagery according to claim 8, characterized in that, The formula for calculating the construction and demolition waste index is as follows: in, The building and demolition waste index for any pixel in the initially extracted image. These represent the reflectance of the pixel in the near-infrared, red, green, and blue bands, respectively.

10. The construction and demolition waste extraction device based on remote sensing imagery according to claim 8, characterized in that, The formula for calculating the construction and demolition waste index is as follows: in, The building and demolition waste index for any pixel in the initially extracted image. These represent the reflectance of the pixel in the near-infrared, red, green, and blue bands, respectively.

Images