CN113392788A - Construction waste identification method and device - Google Patents
Construction waste identification method and device Download PDFInfo
- Publication number
- CN113392788A CN113392788A CN202110698568.5A CN202110698568A CN113392788A CN 113392788 A CN113392788 A CN 113392788A CN 202110698568 A CN202110698568 A CN 202110698568A CN 113392788 A CN113392788 A CN 113392788A
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- construction waste
- sensing image
- multispectral remote
- historical
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
The application provides a construction waste identification method and device, and relates to the technical field of remote sensing monitoring. The method comprises the following steps: acquiring a target multispectral remote sensing image of a target area; and identifying the distribution information of the construction waste in the target multispectral remote sensing image according to the sensitive wave band of the construction waste by using a pre-trained classifier so as to determine the position of the construction waste in the target area. According to the embodiment of the application, the problem of low efficiency in determining the distribution situation of the whole urban construction waste in the related technology can be solved.
Description
Technical Field
The application relates to the technical field of remote sensing monitoring, in particular to a method and a device for identifying construction waste.
Background
Along with the acceleration of the urbanization process of China, the orderly development of old city reconstruction and new city development work, various construction sites are distributed in the urban area by adopting the star chess, and a large amount of construction waste is generated at the same time, and is the largest source of urban solid waste at present. A large amount of dust generated in the construction process of a construction site, the transportation process of construction waste and the stacking process can even reach 60 percent of the total amount of the dust, and the urban environment is seriously damaged.
At present, in order to avoid serious environmental pollution, construction waste in cities needs to be monitored manually at variable time, manual monitoring needs workers to arrive at places such as construction sites and the like, the distribution area of the construction waste is measured manually, and then the distribution situation of the construction waste in the whole cities is obtained.
Disclosure of Invention
The embodiment of the application provides a construction waste identification method, a construction waste identification device, computer equipment and a computer storage medium, and can solve the problem of low efficiency of determining the distribution situation of the construction waste of a whole city in the related art.
In a first aspect, an embodiment of the present application provides a method for identifying construction waste, where the method includes:
acquiring a target multispectral remote sensing image of a target area;
and identifying the distribution information of the construction waste in the target multispectral remote sensing image according to the sensitive wave band of the construction waste by using a pre-trained classifier.
In one realizable mode, the construction waste comprises covered construction waste and uncovered construction waste, and the sensitive wave band of the construction waste comprises a sensitive wave band corresponding to the covering color of the covered construction waste and a sensitive wave band of the uncovered construction waste; the method comprises the following steps of identifying distribution information of the construction waste in a target multispectral remote sensing image according to sensitive wave bands of the construction waste by using a pre-trained classifier, wherein the distribution information comprises the following steps:
and identifying the distribution information of the construction waste with different cover colors in the target multispectral remote sensing image by using a classifier according to the sensitive wave band corresponding to the cover color, the sensitive wave band of the construction waste without the cover, the sensitive wave band corresponding to the preset temporary building, the preset normalized vegetation index and the preset normalized water body index.
In one implementation, prior to acquiring the multi-spectral remote sensing image of the target region, the method further comprises:
acquiring a stored historical multispectral remote sensing image, wherein the historical multispectral remote sensing image carries label information, and the label information comprises distribution information of building rubbish in the historical multispectral remote sensing image;
and according to the distribution information of the construction waste in the historical multispectral remote sensing image, performing spectral feature analysis on the construction waste in the historical multispectral remote sensing image to obtain a sensitive wave band corresponding to the construction waste in the historical multispectral remote sensing image.
In an implementation manner, the label information further includes a covering color corresponding to the construction waste in the historical multispectral remote sensing image; according to the distribution information of the construction waste in the historical multispectral remote sensing image, performing spectral feature analysis on the construction waste in the historical multispectral remote sensing image to obtain a sensitive wave band corresponding to the construction waste in the historical multispectral remote sensing image, and the method comprises the following steps:
and performing spectral feature analysis on the historical multispectral remote sensing image according to the distribution information of the building rubbish in the historical multispectral remote sensing image and the color of the covering corresponding to the building rubbish, and determining the sensitive wave band of each covering color.
In an implementation manner, the tag information further includes distribution information of an adjacent building in the historical multispectral remote sensing image, and spectral feature analysis is performed on the historical multispectral remote sensing image according to the distribution information of the building waste in the historical multispectral remote sensing image and the color of a covering corresponding to the building waste to obtain a sensitive band of each covering color, including:
according to the distribution information of the building rubbish in the historical multispectral remote sensing image, the corresponding covering color of the building rubbish and the distribution information of the temporary building, performing spectral feature analysis on the building rubbish and the temporary building in the historical multispectral remote sensing image to obtain a preset spectral feature curve;
carrying out statistical analysis on pixels in the historical multispectral remote sensing image to obtain a wave band with the largest standard deviation in the historical multispectral remote sensing image;
and determining the sensitive wave band of each covering color according to the wave band with the maximum standard deviation and a preset spectral characteristic curve.
In one implementation, the classifier is a maximum likelihood classifier.
In one implementation, before identifying distribution information of the construction waste in the target multispectral remote sensing image according to the sensitive wave band of the construction waste by using a pre-trained classifier, the method further comprises:
performing spectral characteristic analysis on each pixel in the target multispectral remote sensing image to obtain a spectral characteristic curve of each pixel;
calculating the similarity between the spectral characteristic curve of each pixel and a preset spectral characteristic curve;
determining a target pixel with the similarity larger than a similarity threshold value from the pixels;
identifying distribution information of the construction waste in the target multispectral remote sensing image according to the sensitive wave band of the construction waste by using a pre-trained classifier to determine the position of the construction waste in the target area, wherein the method comprises the following steps:
identifying the refractive index of each target pixel in the target multispectral remote sensing image to the sensitive wave band of the construction waste;
determining a pixel corresponding to the construction waste according to the refractive index, the preset normalized vegetation index and the preset normalized water body index;
and determining the distribution information of the construction waste in the multispectral remote sensing image according to the target pixel corresponding to the construction waste.
In a second aspect, an embodiment of the present application provides an identification apparatus for construction waste, the apparatus including:
the acquisition module is used for acquiring a target multispectral remote sensing image of a target area;
and the identification module is used for identifying the distribution information of the construction waste in the target multispectral remote sensing image according to the sensitive wave band of the construction waste by using a pre-trained classifier.
In one realizable mode, the construction waste comprises covered construction waste and uncovered construction waste, and the sensitive wave band of the construction waste comprises a sensitive wave band corresponding to the covering color of the covered construction waste and a sensitive wave band of the uncovered construction waste; and the identification module is used for identifying the distribution information of the building rubbish with different cover colors in the target multispectral remote sensing image according to the sensitive wave band corresponding to the cover color, the sensitive wave band of the building rubbish without the cover, the sensitive wave band corresponding to the preset temporary building, the preset normalized vegetation index and the preset normalized water body index by using the classifier.
In one implementable manner, the apparatus further comprises:
the acquisition module is used for acquiring a stored historical multispectral remote sensing image, wherein the historical multispectral remote sensing image carries label information, and the label information comprises distribution information of building rubbish in the historical multispectral remote sensing image;
and the analysis module is used for carrying out spectral feature analysis on the building rubbish in the historical multi-spectral remote sensing image according to the distribution information of the building rubbish in the historical multi-spectral remote sensing image to obtain a sensitive wave band corresponding to the building rubbish in the historical multi-spectral remote sensing image.
In an implementation manner, the label information further includes a covering color corresponding to the construction waste in the historical multispectral remote sensing image; and the analysis module is used for carrying out spectral feature analysis on the historical multispectral remote sensing image according to the distribution information of the building rubbish in the historical multispectral remote sensing image and the colors of the coverings corresponding to the building rubbish, and determining the sensitive wave band of each covering color.
In an implementation manner, the tag information further includes distribution information of the temporary building in the historical multispectral remote sensing image, and the analysis module is configured to:
according to the distribution information of the building rubbish in the historical multispectral remote sensing image, the corresponding covering color of the building rubbish and the distribution information of the temporary building, performing spectral feature analysis on the building rubbish and the temporary building in the historical multispectral remote sensing image to obtain a preset spectral feature curve;
carrying out statistical analysis on pixels in the historical multispectral remote sensing image to obtain a wave band with the largest standard deviation in the historical multispectral remote sensing image;
and determining the sensitive wave band of each covering color according to the wave band with the maximum standard deviation and a preset spectral characteristic curve.
In one implementation, the classifier is a maximum likelihood classifier.
In one implementable manner, the apparatus further comprises:
the analysis module is used for carrying out spectral characteristic analysis on each pixel in the target multispectral remote sensing image to obtain a spectral characteristic curve of each pixel;
the calculating module is used for calculating the similarity between the spectral characteristic curve of each pixel and a preset spectral characteristic curve;
the determining module is used for determining a target pixel with the similarity larger than a similarity threshold value from the pixels;
an identification module to:
identifying the refractive index of each target pixel in the target multispectral remote sensing image to the sensitive wave band of the construction waste;
determining a pixel corresponding to the construction waste according to the refractive index, the preset normalized vegetation index and the preset normalized water body index;
and determining the distribution information of the construction waste in the multispectral remote sensing image according to the target pixel corresponding to the construction waste.
In a third aspect, an embodiment of the present application provides a computer device, including a processor, a memory, and a computer program stored on the memory and executable on the processor, where the computer program, when executed by the processor, implements the method as provided in the first aspect or any one of the possible implementation manners of the first aspect.
In a fourth aspect, an embodiment of the present application provides a computer storage medium, where instructions are stored, and when the instructions are executed on a computer, the instructions cause the computer to perform the method provided in the first aspect or any one of the possible implementation manners of the first aspect.
According to the method and the device for identifying the building rubbish, the target multispectral remote sensing image of the target area is obtained, the pre-trained classifier is used, the target multispectral remote sensing image is identified according to the sensitive wave band of the building rubbish, the distribution information of the building rubbish in the target multispectral remote sensing image is determined, and therefore the position of the building rubbish in the target area is determined. Therefore, the distribution condition of the building rubbish in the city is determined without manually investigating each distribution on the spot, and the efficiency of determining the distribution condition of the building rubbish in the whole city is improved.
Drawings
Fig. 1 shows a schematic structural diagram of a closed-loop system in a computer device according to an embodiment of the present application;
fig. 2 is a schematic flow chart illustrating a method for identifying construction waste according to an embodiment of the present application;
fig. 3 is a schematic flow chart illustrating another method for identifying construction waste according to an embodiment of the present application;
fig. 4 is a schematic structural diagram illustrating an identification apparatus for construction waste according to an embodiment of the present application;
fig. 5 shows a schematic structural diagram of a computer device provided in an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the embodiments of the present application will be described below with reference to the accompanying drawings.
In the description of the embodiments of the present application, the words "exemplary," "for example," or "for instance" are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary," "e.g.," or "e.g.," is not to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the words "exemplary," "e.g.," or "exemplary" is intended to present relevant concepts in a concrete fashion.
In the description of the embodiments of the present application, the term "and/or" is only one kind of association relationship describing an associated object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, B exists alone, and A and B exist at the same time. In addition, the term "plurality" means two or more unless otherwise specified. For example, the plurality of systems refers to two or more systems, and the plurality of screen terminals refers to two or more screen terminals.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicit indication of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and variations thereof mean "including, but not limited to," unless expressly specified otherwise.
The embodiment of the application provides a building rubbish identification system, and as shown in fig. 1, the building rubbish identification system provided by the embodiment of the application comprises a remote sensing satellite 11 and a computer device 12. The remote sensing satellite 11 can rapidly acquire large-area ground surface information on the earth, the remote sensing satellite 11 can communicate with the computer device 12, and the computer device 12 can execute the method for identifying the construction waste provided by the embodiment of the application after receiving the remote sensing image.
In some embodiments, in order to accurately identify the construction waste from the remote sensing image, the remote sensing satellite 11 may be a multispectral remote sensing satellite, such as Sentinel 2 (Sentinel-2), where Sentinel 2 covers 13 spectral bands with different spatial resolutions from visible light and near infrared to short wave infrared, 10m, 20m and 60m respectively, and the resolutions of red, green, blue and near infrared bands are 10m, so as to accurately identify the construction waste from the remote sensing image.
The computer device 12 in the embodiment of the present application can execute the method for identifying construction waste provided in the embodiment of the present application, and the method for identifying construction waste provided in the embodiment of the present application is described in detail below.
Fig. 2 is a schematic flow diagram of a method for identifying construction waste provided in an embodiment of the present application, and as shown in fig. 2, the method for identifying construction waste provided in the embodiment of the present application may include S201 and S202.
S201: and acquiring a target multispectral remote sensing image of the target area.
The computer equipment is communicated with the multispectral remote sensing satellite, so that a target multispectral remote sensing image of a target area captured by the multispectral remote sensing satellite can be received.
After the target multispectral remote sensing image is acquired, preprocessing can be performed on the target multispectral remote sensing image, such as radiometric calibration, atmospheric correction, geometric correction, orthometric correction, resampling and the like. For example, sentinel number 2 can cover 13 spectral bands with different spatial resolutions ranging from visible and near infrared to short wave infrared, 10m, 20m and 60m respectively, with red, green, blue, near infrared bands having a resolution of 10 m. 10m resampling is carried out on the wave Band with the spatial resolution of 20m, and 10 wave bands with the resolution of 10m are obtained, namely, Band 2-Band 8, Band8A and Band 11-Band 12.
S202: and identifying the distribution information of the construction waste in the target multispectral remote sensing image according to the sensitive wave band of the construction waste by using a pre-trained classifier so as to determine the position of the construction waste in the target area.
The construction waste corresponds to a sensitive waveband, wherein the sensitive waveband refers to a waveband corresponding to the earth surface spectral response value of the earth surface object when the earth surface spectral response value is maximum. The wavelength bands are different due to the fact that the surface spectral response values of different surface objects are the largest. Based on a pre-trained classifier, identifying the distribution information of the construction waste in the target multispectral remote sensing image according to the sensitive wave band of the construction waste, thereby determining the position of the construction waste in the target area.
In some embodiments, the construction waste in the city may or may not be covered by the mulch, and the color of the covering may be similar to the color of some other surface feature. For example, the covering color of the construction waste comprises green and blue, while the color of the plants in the ground is green and the color of the building is blue. Construction waste can include covered construction waste and uncovered construction waste. In order to eliminate the interference of vegetation and water bodies on the classification of the construction waste, increase the distinguishing degree of a dustproof film and other land features and more accurately identify the construction waste, in S202, the distribution information of the construction waste in the target multispectral remote sensing image can be identified based on a pre-trained classifier, a sensitive wave band corresponding to each cover color of the construction waste, a sensitive wave band of the construction waste without a cover, a sensitive wave band corresponding to a building adjacent to the building, a preset normalized vegetation index and a preset normalized water body index, and the cover color of the construction waste and whether the cover exists can be identified, so that the construction waste without a cover in the target area is determined, the construction waste without a cover is covered, wind, sand and dust are avoided, and the environment is protected.
Here, the sensitive band corresponding to the covering color of the building rubbish and the sensitive band of the building rubbish without the covering are determined according to the historical multispectral remote sensing image. Before S201, firstly, obtaining a stored historical multispectral remote sensing image, wherein the historical multispectral remote sensing image carries label information, and the label information comprises distribution information of construction waste in the historical multispectral remote sensing image; and then, according to the distribution information of the construction waste in the historical multispectral remote sensing image, performing spectral feature analysis on the construction waste in the historical multispectral remote sensing image to obtain a sensitive wave band corresponding to the construction waste in the historical multispectral remote sensing image.
The historical multispectral remote sensing image is obtained through a multispectral remote sensing satellite. In order to determine the distribution information of the construction waste in the historical multispectral remote sensing image, a worker can conduct field investigation on a city or an area corresponding to the historical multispectral remote sensing image, so that the position of the construction waste in the city or the area is determined, the historical multispectral remote sensing image is marked, and therefore the label information of the historical multispectral remote sensing image is obtained.
After the historical multispectral remote sensing image is received, preprocessing such as radiometric calibration, atmospheric correction, geometric correction, orthometric correction, resampling and the like is required to be carried out on the historical multispectral remote sensing image. For example, sentinel number 2 can cover 13 spectral bands with different spatial resolutions ranging from visible and near infrared to short wave infrared, 10m, 20m and 60m respectively, with red, green, blue, near infrared bands having a resolution of 10 m. 10m resampling is carried out on the wave Band with the spatial resolution of 20m, and 10 wave bands with the resolution of 10m are obtained, namely, Band 2-Band 8, Band8A and Band 11-Band 12.
In order to determine sensitive wave bands corresponding to different covering colors of the building waste, after a historical multispectral remote sensing image is obtained, the sensitive wave bands are displayed through a display device of a computer device, then workers label the covering colors of the building waste distributed in each distribution based on a field investigation result, it is required to be stated that the building waste without the covering is labeled as bare soil, and therefore the computer device obtains label information of the historical multispectral remote sensing image, wherein the label information further comprises the covering colors of the building waste in the historical multispectral remote sensing image. And then, according to the distribution information of the building rubbish in the historical multispectral remote sensing image and the color of the covering corresponding to the building rubbish, performing spectral feature analysis on the historical multispectral remote sensing image to determine the sensitive wave band of each covering color.
In some embodiments, in order to ensure the accuracy of analyzing the spectral characteristics of the colors of the covering materials of the construction waste, the staff further needs to label the distribution information of the buildings to be built in the historical multispectral remote sensing image, so that the label information obtained by the computer device includes the distribution information of the buildings to be built in the historical multispectral remote sensing image. Secondly, performing spectral feature analysis on the building rubbish and the building temporary in the historical multispectral remote sensing image according to the distribution information of the building rubbish, the corresponding covering color of the building rubbish and the distribution information of the building temporary in the historical multispectral remote sensing image to obtain a preset spectral feature curve; then, carrying out statistical analysis on pixels in the historical multispectral remote sensing image to obtain a wave band with the maximum standard deviation in the historical multispectral remote sensing image; and finally, determining the sensitive wave band of each covering color according to the wave band with the maximum standard deviation and a preset spectral characteristic curve.
Marking a plurality of ground objects on the historical multispectral remote sensing image acquired by the sentinel No. 2, and then performing spectral feature analysis on the construction waste and the temporary building, wherein the construction waste can be covered with a covering material or not covered with the covering material, namely, bare soil, and the covering material of the construction waste comprises a blue covering film and a green covering film. As shown in fig. 3, the change curves of the spectral response values of different wavelength bands of different color covering garbage and blue building house.
Data redundancy among wave bands can affect the extraction precision, so that wave band compression is needed during ground feature identification, and sensitive wave bands of different ground features are determined. Since the information amount is proportional to the standard deviation, statistical analysis needs to be performed on the pixels in the historical multispectral remote sensing image to determine the band with the largest standard deviation in the historical multispectral remote sensing image, for example, the band with the largest standard deviation in the historical multispectral remote sensing image obtained by sentinel 2 is the band 12. Meanwhile, the preset spectral characteristic curve is analyzed, and the sensitive wave band of the construction waste is determined by combining the wave band with the maximum standard deviation.
For example, as shown in fig. 3, with a preset spectral characteristic curve, the construction waste with the blue cover film and the green cover film has similar trend in the rest wave bands except that the blue cover film has a descending trend and the green cover film has a different ascending trend in the 2 wave bands, and only the spectral response value of the blue cover film at the 6 wave bands has a larger difference from that of the green cover film, so that the construction waste is easy to distinguish; the spectral response value of the bare soil is in an ascending trend on 2-7 wave bands, the spectral response value is increased from the lowest value of the 2 wave bands to the highest value of the 7 wave bands, the difference between the spectral response value and the spectral response values of other three types of ground objects at the 6 wave band is the largest, the separability is good, and the spectral response values are similar to spectral characteristic curves of other coating type ground objects and are difficult to distinguish; the spectral characteristic curve of the temporary building is the most different from other types, reaches the peak value in the wave band12 and has the best separability. Therefore, in the historical multispectral remote sensing image acquired by the sentinel 2, the sensitive wave bands of the construction waste are the wave band2, the wave band 6 and the wave band 12.
In some embodiments, the classifier may be a maximum likelihood classifier. In the training process, the ground objects in the training sample image of the maximum likelihood classifier are uniformly distributed, and the number of the ground objects is larger than a preset threshold value. In order to improve the identification accuracy of the construction waste, the maximum likelihood classifier needs to set a minimum similarity threshold. For example, when the threshold value is around 0.005, the classification accuracy is the largest with the threshold value, and when the threshold value is reduced to 0.001, the accuracy tends to be gentle with the threshold value, and therefore, the minimum similarity threshold value may be set to 0.001.
In some embodiments, the trained maximum likelihood classifier is used for identifying the distribution information of the construction waste in the target multispectral remote sensing image, and spectral feature analysis can be performed on each pixel in the target multispectral remote sensing image. Specifically, after S201 and before S202, firstly, performing spectral feature analysis on each pixel in the target multispectral remote sensing image to obtain a spectral feature curve of each pixel; then, calculating the similarity between the spectral characteristic curve of each pixel and a preset spectral characteristic curve; and finally, determining the target image element with the similarity larger than the similarity threshold value from the image elements.
After the target pixels are determined, the refractive index of each target pixel in the target multispectral remote sensing image to the sensitive wave band of the construction waste can be identified, and then the pixels corresponding to the construction waste are determined according to the refractive index, the preset normalized vegetation index and the preset normalized water body index; and finally, determining the distribution information of the construction waste in the multispectral remote sensing image according to the target pixel corresponding to the construction waste.
According to the method for identifying the building rubbish, the target multispectral remote sensing image of the target area is obtained, the pre-trained classifier is used, the target multispectral remote sensing image is identified according to the sensitive wave band of the building rubbish, distribution information of the building rubbish in the target multispectral remote sensing image is determined, and therefore the position of the building rubbish in the target area is determined. Therefore, the distribution situation of the construction waste in the city is determined without manually investigating each region on the spot, and the efficiency of determining the distribution situation of the construction waste in the whole city is improved.
Based on the identification method of the construction waste in the embodiment, the embodiment of the application further provides an identification device of the construction waste. Fig. 4 is a schematic structural diagram of a construction waste recognition apparatus 400 according to an embodiment of the present application, and as shown in fig. 4, the construction waste recognition apparatus 400 may include an obtaining module 401 and a recognition module 402.
The acquisition module is used for acquiring a target multispectral remote sensing image of a target area;
and the identification module is used for identifying the distribution information of the construction waste in the target multispectral remote sensing image according to the sensitive wave band of the construction waste by using a pre-trained classifier so as to determine the position of the construction waste in the target area.
In some embodiments of the present application, the construction waste includes covered construction waste and uncovered construction waste, and the sensitive waveband of the construction waste includes a sensitive waveband corresponding to a cover color of the covered construction waste and a sensitive waveband of the uncovered construction waste; and the identification module is used for identifying the distribution information of the building rubbish with different cover colors in the target multispectral remote sensing image according to the sensitive wave band corresponding to the cover color, the sensitive wave band of the building rubbish without the cover, the sensitive wave band corresponding to the preset temporary building, the preset normalized vegetation index and the preset normalized water body index by using the classifier.
In some embodiments of the present application, the apparatus further comprises:
the acquisition module 401 is configured to acquire a stored historical multi-spectral remote sensing image, where the historical multi-spectral remote sensing image carries tag information, and the tag information includes distribution information of building waste in the historical multi-spectral remote sensing image;
and the analysis module is used for carrying out spectral feature analysis on the building rubbish in the historical multi-spectral remote sensing image according to the distribution information of the building rubbish in the historical multi-spectral remote sensing image to obtain a sensitive wave band corresponding to the building rubbish in the historical multi-spectral remote sensing image.
In some embodiments of the present application, the label information further includes a color of a covering corresponding to the construction waste in the historical multispectral remote sensing image; and the analysis module is used for carrying out spectral feature analysis on the historical multi-spectral remote sensing image according to the distribution information of the building rubbish in the historical multi-spectral remote sensing image and the colors of the coverings corresponding to the building rubbish, and determining the sensitive wave band of each covering color.
In some embodiments of the present application, the tag information further includes distribution information of a building in the historical multispectral remote sensing image, and the analysis module is configured to:
according to the distribution information of the building rubbish in the historical multispectral remote sensing image, the corresponding covering color of the building rubbish and the distribution information of the temporary building, performing spectral feature analysis on the building rubbish and the temporary building in the historical multispectral remote sensing image to obtain a preset spectral feature curve;
carrying out statistical analysis on pixels in the historical multispectral remote sensing image to obtain a wave band with the largest standard deviation in the historical multispectral remote sensing image;
and determining the sensitive wave band of each covering color according to the wave band with the maximum standard deviation and a preset spectral characteristic curve.
In some embodiments of the present application, the classifier is a maximum likelihood classifier.
In some embodiments of the present application, the apparatus further comprises:
the analysis module is used for carrying out spectral characteristic analysis on each pixel in the target multispectral remote sensing image to obtain a spectral characteristic curve of each pixel;
the calculating module is used for calculating the similarity between the spectral characteristic curve of each pixel and a preset spectral characteristic curve;
the determining module is used for determining a target pixel with the similarity larger than a similarity threshold value from the pixels;
an identification module 402 for:
identifying the refractive index of each target pixel in the target multispectral remote sensing image to the sensitive wave band of the construction waste;
determining a pixel corresponding to the construction waste according to the refractive index, the preset normalized vegetation index and the preset normalized water body index;
and determining the distribution information of the construction waste in the multispectral remote sensing image according to the target pixel corresponding to the construction waste.
According to the identification device for the construction waste, the target multispectral remote sensing image of the target area is obtained, the pre-trained classifier is used, the target multispectral remote sensing image is identified according to the sensitive wave band of the construction waste, distribution information of the construction waste in the target multispectral remote sensing image is determined, and therefore the position of the construction waste in the target area is determined. Therefore, the distribution situation of the construction waste in the city is determined without manually investigating each region on the spot, and the efficiency of determining the distribution situation of the construction waste in the whole city is improved.
A computer device provided in an embodiment of the present application is described below.
Fig. 5 is a schematic structural diagram of a computer device according to an embodiment of the present application. As shown in fig. 5, the computer device provided in the embodiment of the present application may be used to implement the method for identifying construction waste described in the foregoing method embodiment.
The computer device may comprise a processor 501 and a memory 502 in which computer program instructions are stored.
Specifically, the processor 501 may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured to implement one or more Integrated circuits of the embodiments of the present Application.
The memory may include Read Only Memory (ROM), Random Access Memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical/tangible memory storage devices. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software comprising computer-executable instructions and when the software is executed (e.g., by one or more processors), it is operable to perform operations described with reference to methods in accordance with the present application.
The processor 501 reads and executes the computer program instructions stored in the memory 502 to implement any one of the construction waste identification methods in the above embodiments.
In one example, the computer device can also include a communication interface 505 and a bus 510. As shown in fig. 5, the processor 501, the memory 502, and the communication interface 505 are connected via a bus 510 to complete communication therebetween.
The communication interface 505 is mainly used for implementing communication between modules, apparatuses, units and/or devices in the embodiments of the present application.
In addition, in combination with the above embodiments, the embodiments of the present application may be implemented by providing a computer storage medium. The computer storage medium having computer program instructions stored thereon; the computer program instructions, when executed by the processor, implement any one of the above-described embodiments of the method for identifying construction waste.
The functional blocks shown in the above-described structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the present application are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of a machine-readable medium include electronic circuits, semiconductor memory devices, ROM, flash memory, Erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.
It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.
Aspects of the present application are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions/acts specified in the flowchart and/or block diagram block or blocks. Such a processor may be, but is not limited to, a general purpose processor, a special purpose processor, an application specific processor, or a field programmable logic circuit. It will also be understood that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware for performing the specified functions or acts, or combinations of special purpose hardware and computer instructions.
As described above, only the specific embodiments of the present application are provided, and it can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the module and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present application, and these modifications or substitutions should be covered within the scope of the present application.
Claims (8)
1. A method for identifying construction waste, the method comprising:
acquiring a target multispectral remote sensing image of a target area;
and identifying the distribution information of the construction waste in the target multispectral remote sensing image according to the sensitive wave band of the construction waste by using a pre-trained classifier.
2. The method of claim 1, wherein the construction waste comprises covered construction waste and uncovered construction waste, and the sensitive waveband of the construction waste comprises a sensitive waveband corresponding to a covering color of the covered construction waste and a sensitive waveband of the uncovered construction waste; the method for identifying the distribution information of the construction waste in the target multispectral remote sensing image according to the sensitive wave band of the construction waste by using the pre-trained classifier comprises the following steps:
and identifying the distribution information of the construction waste with different cover colors in the target multispectral remote sensing image according to the sensitive wave band corresponding to the cover color, the sensitive wave band of the construction waste without the cover, the sensitive wave band corresponding to the preset temporary building, the preset normalized vegetation index and the preset normalized water body index by using the classifier.
3. The method according to claim 1, wherein prior to acquiring the multi-spectral remote sensing image of the target region, the method further comprises:
acquiring a stored historical multispectral remote sensing image, wherein the historical multispectral remote sensing image carries label information, and the label information comprises distribution information of construction waste in the historical multispectral remote sensing image;
and according to the distribution information of the construction waste in the historical multispectral remote sensing image, performing spectral feature analysis on the construction waste in the historical multispectral remote sensing image to obtain a sensitive wave band corresponding to the construction waste in the historical multispectral remote sensing image.
4. The method according to claim 3, wherein the label information further comprises a covering color corresponding to construction waste in the historical multispectral remote sensing image; the spectral feature analysis is carried out on the building rubbish in the historical multispectral remote sensing image according to the distribution information of the building rubbish in the historical multispectral remote sensing image to obtain the sensitive wave band corresponding to the building rubbish in the historical multispectral remote sensing image, and the method comprises the following steps:
and according to the distribution information of the building rubbish in the historical multispectral remote sensing image and the color of the covering corresponding to the building rubbish, performing spectral feature analysis on the historical multispectral remote sensing image, and determining the sensitive wave band of each covering color.
5. The method according to claim 4, wherein the label information further includes distribution information of buildings to be built in the historical multispectral remote sensing image, and the spectral feature analysis is performed on the historical multispectral remote sensing image according to the distribution information of the building waste in the historical multispectral remote sensing image and the covering color corresponding to the building waste to obtain a sensitive band of each covering color, including:
according to the distribution information of the building rubbish in the historical multispectral remote sensing image, the color of a covering object corresponding to the building rubbish and the distribution information of the temporary building, performing spectral feature analysis on the building rubbish and the temporary building in the historical multispectral remote sensing image to obtain a preset spectral feature curve;
carrying out statistical analysis on pixels in the historical multispectral remote sensing image to obtain a wave band with the largest standard deviation in the historical multispectral remote sensing image;
and determining the sensitive wave band of each covering color according to the wave band with the maximum standard deviation and the preset spectral characteristic curve.
6. The method of claim 1, wherein the classifier is a maximum likelihood classifier.
7. The method according to claim 6, wherein prior to said identifying distribution information of construction waste in the target multispectral remote sensing image from sensitive bands of construction waste using a pre-trained classifier, the method further comprises:
performing spectral characteristic analysis on each pixel in the target multispectral remote sensing image to obtain a spectral characteristic curve of each pixel;
calculating the similarity between the spectral characteristic curve of each pixel and a preset spectral characteristic curve;
determining a target pixel with the similarity larger than a similarity threshold value from the pixels;
the identifying, by using a pre-trained classifier, distribution information of the construction waste in the target multispectral remote sensing image according to a sensitive band of the construction waste to determine a position of the construction waste in the target area includes:
identifying the refractive index of each target pixel in the target multispectral remote sensing image to the sensitive wave band of the construction waste;
determining a pixel corresponding to the construction waste according to the refractive index, the preset normalized vegetation index and the preset normalized water body index;
and determining the distribution information of the construction waste in the multispectral remote sensing image according to the target pixel corresponding to the construction waste.
8. An apparatus for identifying construction waste, the apparatus comprising:
the acquisition module is used for acquiring a target multispectral remote sensing image of a target area;
and the identification module is used for identifying the distribution information of the construction waste in the target multispectral remote sensing image according to the sensitive wave band of the construction waste by using a pre-trained classifier.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110698568.5A CN113392788B (en) | 2021-06-23 | 2021-06-23 | Construction waste identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110698568.5A CN113392788B (en) | 2021-06-23 | 2021-06-23 | Construction waste identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113392788A true CN113392788A (en) | 2021-09-14 |
| CN113392788B CN113392788B (en) | 2022-11-01 |
Family
ID=77623546
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110698568.5A Active CN113392788B (en) | 2021-06-23 | 2021-06-23 | Construction waste identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113392788B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7075557B1 (en) | 2021-08-18 | 2022-05-26 | 中国科学院西北生態環境資源研究院 | Rural non-regular waste classification and risk identification methods based on multi-source data |
| CN114598728A (en) * | 2022-03-01 | 2022-06-07 | 南京精筑智慧科技有限公司 | Building rubbish supervision system based on Internet of things and application method thereof |
| CN117830856A (en) * | 2024-01-24 | 2024-04-05 | 青岛华正信息技术股份有限公司 | Intelligent optimization method and device for park environment monitoring image |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108288059A (en) * | 2017-12-29 | 2018-07-17 | 中国电子科技集团公司第二十七研究所 | A kind of building waste monitoring method based on high-definition remote sensing technology |
| CN109389161A (en) * | 2018-09-28 | 2019-02-26 | 广州大学 | Rubbish identification evolutionary learning method, apparatus, system and medium based on deep learning |
| CN110598784A (en) * | 2019-09-11 | 2019-12-20 | 北京建筑大学 | Machine learning-based construction waste classification method and device |
| CN112597936A (en) * | 2020-12-29 | 2021-04-02 | 北京建筑大学 | Building rubbish separation method based on object-oriented hierarchical segmentation and related products |
-
2021
- 2021-06-23 CN CN202110698568.5A patent/CN113392788B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108288059A (en) * | 2017-12-29 | 2018-07-17 | 中国电子科技集团公司第二十七研究所 | A kind of building waste monitoring method based on high-definition remote sensing technology |
| CN109389161A (en) * | 2018-09-28 | 2019-02-26 | 广州大学 | Rubbish identification evolutionary learning method, apparatus, system and medium based on deep learning |
| CN110598784A (en) * | 2019-09-11 | 2019-12-20 | 北京建筑大学 | Machine learning-based construction waste classification method and device |
| CN112597936A (en) * | 2020-12-29 | 2021-04-02 | 北京建筑大学 | Building rubbish separation method based on object-oriented hierarchical segmentation and related products |
Non-Patent Citations (1)
| Title |
|---|
| 张兴琼: "面向对象的成都市武侯区建筑垃圾遥感信息提取", 《中国优秀博硕士学位论文全文数据库(硕士) 工程科技Ⅰ辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7075557B1 (en) | 2021-08-18 | 2022-05-26 | 中国科学院西北生態環境資源研究院 | Rural non-regular waste classification and risk identification methods based on multi-source data |
| JP2023029184A (en) * | 2021-08-18 | 2023-03-03 | 中国科学院西北生態環境資源研究院 | Rural non-regular garbage separation and risk identification method based on multi-source data |
| CN114598728A (en) * | 2022-03-01 | 2022-06-07 | 南京精筑智慧科技有限公司 | Building rubbish supervision system based on Internet of things and application method thereof |
| CN117830856A (en) * | 2024-01-24 | 2024-04-05 | 青岛华正信息技术股份有限公司 | Intelligent optimization method and device for park environment monitoring image |
| CN117830856B (en) * | 2024-01-24 | 2024-06-04 | 青岛华正信息技术股份有限公司 | Intelligent optimization method and device for park environment monitoring image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113392788B (en) | 2022-11-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113392788B (en) | Construction waste identification method and device | |
| US9805261B1 (en) | Systems and methods for surface and subsurface damage assessments, patch scans, and visualization | |
| CN110796001B (en) | Satellite image film-covering farmland identification and extraction method and system | |
| US20200250424A1 (en) | Automated management of potentially hazardous objects near power lines | |
| Ngoc et al. | Coastal and inland water pixels extraction algorithm (WiPE) from spectral shape analysis and HSV transformation applied to Landsat 8 OLI and Sentinel-2 MSI | |
| CN111489352B (en) | Tunnel gap detection and measurement method and device based on digital image processing | |
| CN113325868A (en) | Crop real-time identification system and method based on unmanned aerial vehicle | |
| CN107991243B (en) | High-altitude area water body extraction method based on aviation hyperspectral remote sensing data | |
| CN110703244A (en) | Method and device for identifying urban water body based on remote sensing data | |
| CN103927759A (en) | Automatic cloud detection method of aerial images | |
| CN112179294A (en) | Land proofreading method, device and system | |
| CN111060455B (en) | Northeast cold-cool area oriented remote sensing image crop marking method and device | |
| Hidayati et al. | A comparative study of various indices for extraction urban impervious surface of Landsat 8 OLI | |
| CN113469127B (en) | River sensibility grading method, device, equipment and storage medium | |
| KR101294347B1 (en) | Mehtod for brick path recognition using image shape pattern and texture feature | |
| CN112613437B (en) | Method for identifying illegal buildings | |
| CN113378754A (en) | Construction site bare soil monitoring method | |
| CN112329853A (en) | Traffic accident detection method, device, equipment and medium based on image fusion | |
| CN114445498A (en) | Depth camera calibration method, system, device and medium | |
| CN110929739A (en) | Automatic impervious surface range remote sensing iterative extraction method | |
| CN114445326A (en) | Photovoltaic panel abnormity detection method, detection device and computer readable storage device | |
| CN115375774A (en) | Method, apparatus, device and storage medium for determining external parameters of a camera | |
| US20030156186A1 (en) | Registration correction method in image processing, and vegetation state display method using the registration correction method | |
| Maurya et al. | Building extraction from very high resolution multispectral images using NDVI based segmentation and morphological operators | |
| CN111583336A (en) | Robot and inspection method and device thereof |
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 |