CN114821287A - Oil field polluted water body identification method and device based on time sequence remote sensing image - Google Patents
Oil field polluted water body identification method and device based on time sequence remote sensing image Download PDFInfo
- Publication number
- CN114821287A CN114821287A CN202110079947.6A CN202110079947A CN114821287A CN 114821287 A CN114821287 A CN 114821287A CN 202110079947 A CN202110079947 A CN 202110079947A CN 114821287 A CN114821287 A CN 114821287A
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- sensing image
- water body
- time sequence
- image data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 289
- 238000000034 method Methods 0.000 title claims abstract description 70
- 238000012545 processing Methods 0.000 claims abstract description 66
- 238000004519 manufacturing process Methods 0.000 claims abstract description 59
- 238000002310 reflectometry Methods 0.000 claims abstract description 47
- 239000007788 liquid Substances 0.000 claims abstract description 45
- 239000002699 waste material Substances 0.000 claims abstract description 45
- 230000002776 aggregation Effects 0.000 claims abstract description 29
- 238000004220 aggregation Methods 0.000 claims abstract description 29
- 238000012937 correction Methods 0.000 claims abstract description 29
- 235000006506 Brasenia schreberi Nutrition 0.000 claims abstract description 26
- 238000011160 research Methods 0.000 claims abstract description 18
- 238000003860 storage Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 18
- 210000000746 body region Anatomy 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 6
- 230000000873 masking effect Effects 0.000 abstract description 6
- 238000001514 detection method Methods 0.000 description 26
- 239000004215 Carbon black (E152) Substances 0.000 description 18
- 238000010586 diagram Methods 0.000 description 13
- 230000033558 biomineral tissue development Effects 0.000 description 12
- 229930195733 hydrocarbon Natural products 0.000 description 11
- 150000002430 hydrocarbons Chemical class 0.000 description 11
- 230000003595 spectral effect Effects 0.000 description 10
- 238000006116 polymerization reaction Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000007781 pre-processing Methods 0.000 description 5
- 238000010521 absorption reaction Methods 0.000 description 4
- 238000002329 infrared spectrum Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000004931 aggregating effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000379 polymerizing effect Effects 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 238000010183 spectrum analysis Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 239000002351 wastewater Substances 0.000 description 2
- 241001420622 Meris Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 239000003653 coastal water Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000011031 large-scale manufacturing process Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 239000002332 oil field water Substances 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 239000010913 used oil Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
An oil field polluted water body identification method and device based on a time sequence remote sensing image are disclosed, the method comprises the following steps: carrying out radiometric calibration, atmospheric correction, orthorectification and image registration according to each original satellite remote sensing image data in the time sequence remote sensing image data set of the research area to obtain reflectivity values corresponding to each waveband data; determining a water body index of the corresponding time sequence remote sensing image to extract a water body target area in the corresponding time sequence remote sensing image; masking the non-water body area; obtaining a time sequence aggregation remote sensing image data set according to the time sequence remote sensing image data set after mask processing; acquiring production waste liquid indexes of all pixel points in a water target area in all the aggregated remote sensing data; acquiring a corresponding threshold value based on a preset threshold value-frequency corresponding relation according to the occurrence frequency of the water body target in the time sequence remote sensing image set; and identifying whether the water target is a production polluted water body or not according to the production waste liquid index of each pixel point in the water target area and the corresponding threshold value, so that the identification precision and efficiency are improved.
Description
Technical Field
The invention relates to the technical field of oil and gas production, in particular to a method and a device for identifying polluted water in an oil field based on a time sequence remote sensing image.
Background
The discharge of large-scale production waste liquid is accompanied in the oil and gas production process, and the high-salinity water body and the high-hydrocarbon-content polluted water body are two main production discharge polluted waste liquid and are usually stored in special storage points, such as a high-salinity water body treatment pool or a legal oily waste liquid pool in a treatment plant station, and are subjected to treatment and then are discharged in a compliance manner. By using the remote sensing technology, the polluted water body information of the oil field is quickly identified, and the remote sensing technology has practical significance for reducing the manual investigation cost and improving the unified supervision efficiency.
At present, the remote sensing inversion of the mineralization degree of inland water bodies mainly aims at inland salt lake water bodies with large scale, such as: the method is characterized in that MERIS, TM and MODIS remote sensing images based on medium and low resolution such as Liu Ying, field Shufang and Jianghong are used for inverting the mineralization degree of the water body of the salt lake, the SPOT high-resolution remote sensing images are used for estimating the mineralization degree of the gaaskuler salt lake by Wangjunhu and the like, and the research is mainly aimed at the aspects of the change trend of the mineralization degree of the water body of the inland salt lake and the like. Remote sensing detection of inland oil polluted water mainly aims at researching spectral characteristics of inland rivers, lakes and coastal water, and remotely sensing and inverting the relation between the content of petroleum in the water and the spectral characteristics, such as: liu Yang and the like extract an abnormal distribution area in an oil and gas production area by utilizing thermal abnormality and multispectral information aiming at large-scale high-hydrocarbon-content polluted waste liquid based on middle-resolution LANDSAT satellite data. The two types of polluted water bodies need to be respectively extracted by different methods.
The detection of the oil field high-salinity polluted water body and the high-hydrocarbon-content polluted water body mainly aims at the water body target with smaller scale, the accurate identification of the polluted water body is emphasized, the concentration analysis is not, and the high-resolution remote sensing image has larger identification difficulty and low precision due to limited spectral information.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides an oil and gas production working area polluted water body identification method and device for simultaneously extracting a mineralization degree water body and an oil-containing polluted water body based on time sequence remote sensing, an electronic device and a computer readable storage medium, and the problems in the prior art can be at least partially solved.
In order to achieve the purpose, the invention adopts the following technical scheme:
in a first aspect, an oil field polluted water body identification method based on a time sequence remote sensing image is extracted, and comprises the following steps:
establishing a time sequence remote sensing image data set according to original satellite remote sensing image data of a plurality of time phases in a research area;
carrying out radiometric calibration, atmospheric correction, orthorectification and image registration on each original satellite remote sensing image data in the time sequence remote sensing image data set to obtain reflectivity values corresponding to each waveband data;
determining a water body index of the corresponding time sequence remote sensing image according to the reflectivity value corresponding to each wave band data in each time sequence remote sensing image;
extracting a water body target area in a corresponding time sequence remote sensing image based on the water body index;
performing mask processing on a non-water body region in the corresponding time sequence remote sensing image according to the water body target region;
obtaining a time sequence aggregation remote sensing image data set according to the time sequence remote sensing image data set after mask processing;
acquiring production waste liquid indexes of all pixel points in a water target area in all aggregated remote sensing data in the time sequence aggregated remote sensing image data set;
acquiring a corresponding threshold value based on a preset threshold value-frequency corresponding relation according to the occurrence frequency of the water body target in the time sequence remote sensing image set;
and identifying whether the water body target is a production polluted water body or not according to the production waste liquid index of each pixel point in the water body target area and the corresponding threshold value.
Further, the performing of the orthorectification, radiometric calibration, atmospheric correction and image registration on each original satellite remote sensing image data in the time series remote sensing image data set includes:
obtaining calibration parameters and correction parameters according to header file information of original satellite remote sensing data of a plurality of time phases;
carrying out radiometric calibration, atmospheric correction and orthorectification on each original satellite remote sensing image data in the time sequence remote sensing image data set according to the calibration parameters and the correction parameters;
and performing geographic registration on the corrected images.
Further, determining the water body index corresponding to each region in the time sequence remote sensing image according to the following formula:
NDWI＝((p(Green)-p(NIR))/((p(Green)+p(NIR))
wherein p (green) and p (nir) represent reflectance values corresponding to green and near infrared band data, respectively.
Further, the oil field polluted water body identification method based on the time sequence remote sensing image further comprises the following steps:
setting a threshold-frequency corresponding relation.
Further, the setting of the threshold-time correspondence includes:
carrying out time phase superposition processing on the time sequence remote sensing image data set after the mask processing to obtain a superposed remote sensing image data set;
obtaining an average value of production waste liquid indexes of a typical water target area in each superposed remote sensing image and corresponding occurrence times;
and fitting the production waste liquid index average value of the typical water body target area in each superposed remote sensing image and the corresponding occurrence frequency to obtain a threshold value-frequency corresponding relation.
Further, the obtaining of the time series aggregation remote sensing image data set according to the time series remote sensing image data set after the mask processing includes:
and superposing the time sequence remote sensing images after the mask processing to obtain the polymerized remote sensing image.
Further, determining the index of the production waste liquid of each pixel point in the water target area according to the following formula:
PWI＝(p(Green)-p(Red))/p(NIR)
wherein p (green) represents reflectance values corresponding to green band data, p (red) represents reflectance values corresponding to red band data, and p (nir) represents reflectance values corresponding to near infrared band data.
In a second aspect, an oil field polluted water body identification device based on a time sequence remote sensing image is provided, which comprises:
the time sequence remote sensing image data set establishing module is used for establishing a time sequence remote sensing image data set according to original satellite remote sensing image data of a plurality of time phases in a research area;
the image processing module is used for carrying out radiometric calibration, atmospheric correction, orthorectification and image registration on each original satellite remote sensing image data in the time sequence remote sensing image data set to obtain reflectivity values corresponding to each waveband data;
the water body index calculation module is used for determining the water body index of the corresponding time sequence remote sensing image according to the reflectivity value corresponding to each wave band data in each time sequence remote sensing image;
the water body target area extraction module is used for extracting a water body target area in the corresponding time sequence remote sensing image based on the water body index;
the mask processing module is used for performing mask processing on a non-water body region in the corresponding time sequence remote sensing image according to the water body target region;
the image aggregation module is used for obtaining a time sequence aggregation remote sensing image data set according to the time sequence remote sensing image data set after mask processing;
the production waste liquid index calculation module is used for acquiring the production waste liquid index of each pixel point in the water target area in each aggregated remote sensing data in the time sequence aggregated remote sensing image data set;
the threshold value acquisition module is used for acquiring a corresponding threshold value based on a preset threshold value-frequency corresponding relation according to the occurrence frequency of a water body target in the time sequence remote sensing image set;
and the polluted water body identification module is used for identifying whether the water body target is a production polluted water body or not according to the production waste liquid index of each pixel point in the water body target area and the corresponding threshold value.
In a third aspect, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the program, the steps of the method for identifying the polluted water in the oil field based on the time-series remote sensing image are implemented.
In a fourth aspect, a computer readable storage medium is provided, on which a computer program is stored, which when executed by a processor, implements the steps of the method for identifying a contaminated water body in an oil field based on a time series remote sensing image.
The invention provides an oil field polluted water body identification method and device based on a time sequence remote sensing image, wherein the method comprises the following steps: establishing a time sequence remote sensing image data set according to original satellite remote sensing image data of a plurality of time phases in a research area; carrying out radiometric calibration, atmospheric correction, orthorectification and image registration on each original satellite remote sensing image data in the time sequence remote sensing image data set to obtain reflectivity values corresponding to each waveband data; determining a water body index of the corresponding time sequence remote sensing image according to the reflectivity value corresponding to each wave band data in each time sequence remote sensing image; extracting a water body target area in a corresponding time sequence remote sensing image based on the water body index; performing mask processing on a non-water body region in the corresponding time sequence remote sensing image according to the water body target region; obtaining a time sequence aggregation remote sensing image data set according to the time sequence remote sensing image data set after mask processing; acquiring production waste liquid indexes of all pixel points in a water target area in all aggregated remote sensing data in the time sequence aggregated remote sensing image data set; acquiring a corresponding threshold value based on a preset threshold value-frequency corresponding relation according to the occurrence frequency of the water body target in the time sequence remote sensing image set; and identifying whether the water body target is a production polluted water body or not according to the production waste liquid index of each pixel point in the water body target area and the corresponding threshold, wherein the polluted water body is identified based on the production waste liquid pollution index and the corresponding threshold by establishing a time sequence remote sensing image set, so that the identification difficulty is reduced, and the identification precision and efficiency are improved.
On the other hand, when the threshold-frequency corresponding relation is set, the weak spectral information difference characteristics of the polluted water body and the clean water body can be enhanced through time phase superposition and fitting technology, and the purpose of simultaneously separating the high-salinity polluted water body and the high-hydrocarbon-content polluted water body from the water body target is achieved.
In order to make the aforementioned and other objects, features and advantages of the invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts. In the drawings:
FIG. 1 is a schematic diagram of an architecture between a server S1 and a client device B1 according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of an oil field polluted water body identification method based on a time sequence remote sensing image in the embodiment of the invention;
FIG. 3 is an exemplary flow chart of a method for identifying a polluted water body in an oil field based on a time-series remote sensing image according to an embodiment of the present invention;
fig. 4 shows the specific steps of step S100 in fig. 3;
FIG. 5 is a block diagram of the structure of an oil field polluted water body identification device based on a time sequence remote sensing image in the embodiment of the invention;
fig. 6 is a block diagram of an electronic device according to an embodiment of the invention.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
It should be noted that the terms "comprises" and "comprising," and any variations thereof, in the description and claims of this application and the above-described drawings, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
The detection of the oil field high-salinity polluted water body and the high-hydrocarbon-content polluted water body mainly aims at the water body target with smaller scale, the accurate identification of the polluted water body is emphasized, the concentration analysis is not, and the high-resolution remote sensing image has larger identification difficulty and low precision due to limited spectral information.
In order to at least partially solve the technical problems in the prior art, embodiments of the present invention provide a method for identifying an oil field polluted water body based on a time sequence remote sensing image, wherein a time sequence remote sensing image set is established, and a hypersalinity water body and a high hydrocarbon-containing polluted water body are identified based on a production waste liquid pollution index and a corresponding threshold value, so that the identification accuracy and efficiency are improved.
In view of the above, the present application provides an apparatus for identifying an oil field polluted water body based on time series remote sensing images, which may be a server S1, see fig. 1, where the server S1 may be in communication connection with at least one client device B1, the client device B1 may transmit raw satellite remote sensing image data of multiple time phases of a research area to the server S1, and the server S1 may receive raw satellite remote sensing image data of multiple time phases of the research area on line. The server S1 can carry out online or offline preprocessing on the acquired original satellite remote sensing image data of a plurality of time phases of the research area, and establishes a time sequence remote sensing image data set according to the original satellite remote sensing image data of the plurality of time phases of the research area; carrying out radiometric calibration, atmospheric correction, orthorectification and image registration on each original satellite remote sensing image data in the time sequence remote sensing image data set to obtain reflectivity values corresponding to each waveband data; determining a water body index of the corresponding time sequence remote sensing image according to the reflectivity value corresponding to each wave band data in each time sequence remote sensing image; extracting a water body target area in a corresponding time sequence remote sensing image based on the water body index; performing mask processing on a non-water body region in the corresponding time sequence remote sensing image according to the water body target region; obtaining a time sequence aggregation remote sensing image data set according to the time sequence remote sensing image data set after mask processing; acquiring production waste liquid indexes of all pixel points in a water target area in all aggregated remote sensing data in the time sequence aggregated remote sensing image data set; acquiring a corresponding threshold value based on a preset threshold value-frequency corresponding relation according to the occurrence frequency of the water body target in the time sequence remote sensing image set; and identifying whether the water body target is a production polluted water body or not according to the production waste liquid index of each pixel point in the water body target area and the corresponding threshold value. Then, the server S1 may send the oilfield polluted water body identification result to the client device B1 on line. The client device B1 may receive the oilfield contaminated water body identification results online.
It is understood that the client device B1 may include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a Personal Digital Assistant (PDA), a vehicle-mounted device, a smart wearable device, etc. Wherein, intelligence wearing equipment can include intelligent glasses, intelligent wrist-watch, intelligent bracelet etc..
In practical applications, the identification of the polluted water in the oil field based on the time-series remote sensing image may be performed on the side of the server S1 as described above, that is, as the architecture shown in fig. 1, all operations may be completed in the client device B1, and the client device B1 may be directly in communication connection with the database server S2. Specifically, the selection may be performed according to the processing capability of the client device B1, the limitation of the user usage scenario, and the like. This is not a limitation of the present application. If all the operations are completed in the client device B1, the client device B1 may further include a processor for performing specific processing of oil field polluted water body identification based on the time-series remote sensing image.
The server and the client device may communicate using any suitable network protocol, including network protocols not yet developed at the filing date of this application. The network protocol may include, for example, a TCP/IP protocol, a UDP/IP protocol, an HTTP protocol, an HTTPS protocol, or the like. Of course, the network Protocol may also include, for example, an RPC Protocol (Remote Procedure Call Protocol), a REST Protocol (Representational State Transfer Protocol), and the like used above the above Protocol.
The applicant finds that the average reflectivity in the target region represents the reflectivity of the target through a large number of tests and researches, the remote sensing reflectivity value of a typical water body target is obtained, the single-time phase and double-time phase reflectivity of three types of targets are respectively subjected to statistical analysis by taking a single-time phase and a double-time phase as examples, and the researches show that the clean water body presents stronger absorption characteristics in a near infrared band and the high hydrocarbon-containing water body presents weak absorption characteristics in a visible light region.
FIG. 2 is a schematic flow chart of an oil field polluted water body identification method based on a time sequence remote sensing image in the embodiment of the invention; as shown in fig. 2, the method for identifying the polluted water body in the oil field based on the time-series remote sensing image may include:
step S1000: establishing a time sequence remote sensing image data set according to original satellite remote sensing image data of a plurality of time phases in a research area;
the images in the time sequence remote sensing image data set are arranged according to the imaging time sequence. The remote sensing data comprises visible light red, green, blue and near infrared spectrum bands.
Step S2000: carrying out radiometric calibration, atmospheric correction, orthorectification and image registration on each original satellite remote sensing image data in the time sequence remote sensing image data set to obtain reflectivity values corresponding to each waveband data;
and obtaining calibration parameters and correction parameters for correction according to header file information of the original satellite remote sensing data of a plurality of time phases.
Step S3000: determining a water body index of the corresponding time sequence remote sensing image according to the reflectivity value corresponding to each wave band data in each time sequence remote sensing image;
specifically, the water body index corresponding to each region in the time sequence remote sensing image is determined according to the following formula:
NDWI＝((p(Green)-p(NIR))/((p(Green)+p(NIR))
wherein p (green) and p (nir) represent reflectance values corresponding to green and near infrared band data, respectively.
Step S4000: extracting a water body target area in a corresponding time sequence remote sensing image based on the water body index;
calculating a water body index NDWI for each reflectivity image, extracting a water body area from the detection area based on the water body index, and determining the existence period of different water body targets, namely determining the time phase times of each target detected by remote sensing;
step S5000: performing mask processing on a non-water body region in the corresponding time sequence remote sensing image according to the water body target region;
specifically, masking is carried out on a non-target area, remote sensing data of the masked area does not participate in aggregation operation, and only target area data which do not pass through the mask participate in aggregation processing;
step S6000: obtaining a time sequence aggregation remote sensing image data set according to the time sequence remote sensing image data set after mask processing;
aggregating the remote sensing data in the processed time sequence remote sensing data set to obtain an aggregated remote sensing data set { DNnew over n different time phases 1 ，DNnew 2 ，。。。。。。DNnew n And (c) the step of (c) in which,
step S7000: acquiring production waste liquid indexes of all pixel points in a water target area in all aggregated remote sensing data in the time sequence aggregated remote sensing image data set;
specifically, the index of the production waste liquid of each pixel point in the water target area is determined according to the following formula:
PWI＝(p(Green)-p(Red))/p(NIR)
wherein p (green) represents reflectance values corresponding to green band data, p (red) represents reflectance values corresponding to red band data, and p (nir) represents reflectance values corresponding to near infrared band data.
Step S8000: acquiring a corresponding threshold value based on a preset threshold value-frequency corresponding relation according to the occurrence frequency of the water body target in the time sequence remote sensing image set;
the method comprises the steps of utilizing threshold setting of structural characteristic indexes (PWI) to identify high-salinity water bodies and high-hydrocarbon-containing polluted water bodies from water body targets, and enabling the high-salinity water bodies and the high-hydrocarbon-containing polluted water bodies to pass through two threshold PWIs oil And PWI salinity To identify two types of targets. Considering the inconsistency of the existing time periods of the detection targets, different thresholds need to be adopted for detection of the targets with different existing periods, so that the method is based on the aggregated remote sensing data set { DNnew 1 ，DNnew 2 ，。。。。。。DNnew n Get different threshold PWI oil And PWI salinity And the target detection device is used for detecting targets with different existence periods.
Step S9000: and identifying whether the water body target is a production polluted water body or not according to the production waste liquid index of each pixel point in the water body target area and the corresponding threshold value.
By adopting the technical scheme, the polluted water body is identified based on the pollution index of the production waste liquid and the corresponding threshold value by establishing the time sequence remote sensing image set, so that the identification difficulty is reduced, and the identification precision and efficiency are improved.
In an alternative embodiment, the step S2000 may include:
obtaining calibration parameters and correction parameters according to header file information of original satellite remote sensing data of a plurality of time phases;
carrying out radiometric calibration, atmospheric correction and orthorectification on each original satellite remote sensing image data in the time sequence remote sensing image data set according to the calibration parameters and the correction parameters;
and carrying out geographic registration on the corrected images.
In an optional embodiment, the method for identifying the polluted water body in the oil field based on the time series remote sensing image further comprises the following steps:
setting a threshold-frequency corresponding relation.
Specifically, firstly, carrying out time phase superposition processing on the time sequence remote sensing image data set after mask processing to obtain a superposed remote sensing image data set; then obtaining the average value of the production waste liquid indexes of the typical water body target area in each superposed remote sensing image and the corresponding occurrence times; and finally, fitting the production waste liquid index average value of the typical water target area in each superposed remote sensing image and the corresponding occurrence frequency to obtain a threshold value-frequency corresponding relation.
In an alternative embodiment, the step S6000 may include: and superposing the time sequence remote sensing images after the mask processing to obtain the polymerized remote sensing image.
FIG. 3 is an exemplary flow chart of a method for identifying a polluted water body in an oil field based on a time-series remote sensing image according to an embodiment of the present invention; as shown in fig. 3, the method for identifying the polluted water body in the oil field based on the time-series remote sensing image may include the following steps:
step S100: establishing a time sequence remote sensing image set according to an original remote sensing image set of a research area;
acquiring original remote sensing image data of n time phases of a preset target area, wherein the original satellite remote sensing data comprises visible light and near infrared spectrum data, the current high-resolution remote sensing data comprises the waveband spectrum data, specifically, the original remote sensing image set can be a plurality of GF-2 domestic high-resolution remote sensing images within a period of time, arranging the multi-time-phase remote sensing image data according to a time sequence, preprocessing the original remote sensing data in the data set, obtaining the reflectivity value of the corresponding waveband in each time-phase original remote sensing image through orthorectification, radiometric calibration and atmospheric correction, and carrying out image registration on the remote sensing data of different time phases to obtain a preprocessed time sequence remote sensing image data set { DN } based on the reflectivity value 1 ，DN 2 ，。。。。。。DN n }；
Step S200: extracting a water body target area in each time sequence remote sensing image according to the water body index;
specifically, the preprocessed time sequence remote sensing image data set is used, based on the reflectance value of each time phase remote sensing image, a water body index (NDWI) of the corresponding time phase remote sensing image is calculated, a water body target area of the corresponding time phase remote sensing image is extracted by setting a threshold, and the water body index is calculated as formula 1:
NDWI ═ ((p (green) -p (nir))/((p (green)) + p (nir)) (equation 1)
The time sequence remote sensing data set comprises a time sequence remote sensing data set, a time sequence remote sensing data set and a time sequence remote sensing data set, wherein p (Green) and p (NIR) respectively represent reflectance values at a green wave band and a near infrared wave band, and the times of time phases of different water targets in the time sequence remote sensing data set are determined based on the extracted water body information, so that target identification can be conveniently carried out by utilizing different threshold settings in the later period;
step S300: mask processing of non-water body target area in each time phase remote sensing image
Specifically, a binary data mask layer of a water target in each time phase remote sensing image is generated by using the extracted water body boundary of each time phase remote sensing image, only the reflectivity value in the water body area in each time phase remote sensing image is reserved through mask processing, the reflectivity value outside the water body area is set as an invalid value, subsequent processing is not involved, and a time sequence remote sensing data set after mask processing is obtained;
step S400: obtaining a polymerization remote sensing image according to the time sequence remote sensing image set after the mask processing, and establishing a time sequence polymerization remote sensing image data set;
specifically, data in the time sequence remote sensing image set after mask processing are subjected to superposition processing, namely, images in the time sequence remote sensing image set are arranged according to a time sequence, and are sequentially accumulated by taking a first time phase as a reference to obtain a time sequence aggregation remote sensing image data set { DNnew 1 ，DNnew 2 ，。。。。。。DNnew n And calculating the aggregated remote sensing image as formula 2:
wherein DN i The reflectivity image of the ith time phase in the time sequence remote sensing data set after the masking processing is carried out, n is the number of the time phases in the time sequence remote sensing data set, DNnew n The aggregation remote sensing data is obtained by adding the remote sensing data of n time phases;
step S500: acquiring a production waste liquid pollution index of each pixel point in a water target area in the aggregated remote sensing image data set;
according to the spectral analysis result, a characteristic Index, namely a production waste liquid pollution Index (PWI) is constructed by utilizing visible light red and green wave bands and near infrared wave bands, the PWI of each pixel point in a water body target area in each aggregate remote sensing image is obtained based on the time sequence aggregate remote sensing image data set, and the formula (3) is calculated:
PWI ═ (p (green) -p (red))/p (nir) (equation 3)
Wherein p (green) represents reflectance values of green band, p (red) represents reflectance values of red band, and p (nir) represents reflectance values of near infrared band.
Step S600: according to the occurrence frequency of the water body target in the time sequence remote sensing image set and the threshold-frequency corresponding relation of the preset index
And acquiring a corresponding threshold value.
Step S700: and identifying whether the water body target is a polluted water body or not according to the production waste liquid pollution index of each pixel point in the water body target area and the corresponding threshold value.
And identifying the high-salinity water body and the high-hydrocarbon-containing polluted water body from the water body target by using the constructed production waste liquid pollution index and the corresponding threshold value.
According to the method for identifying the polluted water body of the oil field based on the time sequence remote sensing image, the time sequence remote sensing image set is established, the polluted water body is identified based on the pollution index of the production waste liquid and the corresponding threshold value, the identification difficulty is reduced, and the identification precision and efficiency are improved.
In an optional embodiment, the method for identifying the polluted water body in the oil field based on the time-series remote sensing image may further include: setting a threshold-frequency corresponding relation.
Specifically, referring to fig. 4, the step of setting the threshold-number correspondence may include the following:
step 1: respectively extracting a water body target area of each time sequence remote sensing image by using a water body index NDWI, extracting a water body vector boundary, acquiring the frequency of the water body target appearing from the time sequence remote sensing data set, performing mask processing on each time sequence remote sensing image, generating a binary image layer by using the extracted water body boundary, performing mask processing operation on the corresponding remote sensing image, and only keeping a reflectivity value in the water body target area;
time phase superposition is carried out on the time sequence remote sensing data set after mask processing to obtain a time sequence polymerization remote sensing image data set, images in the time sequence remote sensing data set are arranged according to a time sequence, a first time phase is taken as a reference, sequential accumulation is carried out, and single time phase image data DN are respectively obtained 1 Double time phase image data DN 2 Up to the data DN resulting from the addition of n phases n (referred to as n-phase data) is calculated by equation 1.
Step 2: acquiring the average value of the index of the produced mineralization wastewater of each pixel in the water target area in each superposed image and the corresponding occurrence frequency;
the method comprises the steps of obtaining a production waste liquid pollution index PWI of each polymerization remote sensing image, selecting a typical water body target area comprising a clean water body, a high-salinity water body and a high hydrocarbon-containing polluted water body, obtaining an average PWI value of pixels in the typical target water body area, and obtaining the occurrence frequency of the corresponding water body target in time sequence remote sensing image data set based on the typical water body target.
And step 3: and obtaining a threshold-frequency corresponding relation according to the average value of the indexes of the production mineralization wastewater in the typical water target area in the aggregate remote sensing image data set and the corresponding occurrence frequency.
The method can be realized by unary linear regression.
According to the polymerization remote sensing images of different time phases, aiming at a typical water body target, threshold value setting for identifying a high-salinity water body and a high-hydrocarbon-containing polluted water body from the water body target is obtained, and two threshold values PWI are used oil And PWI salinity To identify two types of targets. Considering the inconsistency of the existing time periods of the detection targets, different thresholds need to be adopted for detection of the targets with different existing periods, so that the method is based on the aggregated remote sensing data set { DNnew 1 ，DNnew 2 ，。。。。。。DNnew n And aiming at the detection target with the existence period of i time phases, obtaining i different threshold settings to obtain { PWI } oil 1 ，PWI oil 2 ，。。。。。。，PWI oil i And { PWI } salinity 1 ，PWI salinity 2 ，。。。。。。，PWI salinity i And f, wherein i is less than or equal to n, when the detection target exists in the whole period of the time sequence remote sensing data set all the time, i is equal to n, and corresponding threshold values are adopted for setting the detection targets with different existence periods.
For a long-term detection target, the threshold PWI can be set based on the acquired i oil And PWI salinity Separately fitting the PWI oill And PWI salinity And (3) obtaining corresponding threshold setting according to the fitted threshold-frequency corresponding relation without establishing a new time sequence remote sensing data set, wherein the PWI threshold setting corresponding to the frequency is calculated as a formula (3):
PWI n k n + b (formula 4)
Where n is the number of time phases in which the target appears, PWI n And k and b are coefficients obtained by fitting based on the reflectivity threshold of the water body target after the n time phases are superposed.
The method for identifying the oil field polluted water body based on the time sequence remote sensing image, provided by the embodiment of the invention, is characterized in that on the basis of remote sensing interpretation of the high-resolution remote sensing image, a multi-temporal high-resolution remote sensing image is utilized for interpreting a target, typical clean water body, high-salinity water body and high-hydrocarbon-content polluted water body samples are collected, spectral characteristics at a multispectral wave band are analyzed, the oil field polluted water body is identified by constructing a characteristic identification index (PWI), on the basis of the typical target, the relation between the PWI and the number of the multi-temporal superposition is obtained, different threshold values are set for targets with different continuous existence times, the background value is effectively inhibited by setting the threshold values, and the target ground object is highlighted, so that the remote and quick identification of the oil field polluted water body can be realized.
In an alternative embodiment, referring to fig. 4, this step S100 may include the following:
step S110: obtaining a calibration parameter and a correction parameter according to the header file information of the original remote sensing image set;
step S120: and performing radiation correction, atmospheric correction and orthorectification on each original remote sensing image according to the calibration parameters and the correction parameters.
Obtaining a time sequence remote sensing image data set based on a reflectivity value after preprocessing through the processing;
specifically, performing orthorectification, radiometric rectification and atmospheric rectification on each original remote sensing image according to the calibration parameters to obtain a reflectivity image.
Step S130: and carrying out geographic registration on the corrected remote sensing image set, and shooting each time sequence remote sensing image according to the event sequence to obtain the time sequence remote sensing image set.
In an optional embodiment, the method for identifying the polluted water body in the oil field based on the time series remote sensing image further comprises the following steps: and performing mask processing on the corresponding time-sequence remote sensing image according to the water body target area.
Specifically, a binary data mask layer of the water body target is generated by using the extracted water body target boundary vector, after the image is masked, the reflectivity value in the water body boundary is reserved, and the reflectivity outside the water body boundary is set as an invalid value.
In summary, the oilfield polluted water body identification technology based on the time sequence remote sensing image provided by the embodiment of the invention utilizes multi-temporal GF-2 domestic high-resolution remote sensing images to construct a time sequence remote sensing image set, and enhances the weak spectral information difference characteristics of the polluted water body and the clean water body through multi-temporal aggregation analysis, thereby achieving the purpose of simultaneously separating the high-salinity polluted water body and the high-hydrocarbon-containing polluted water body from the water body target.
Aiming at the characteristics that a large number of high-salinity polluted water bodies and high-hydrocarbon-containing polluted water bodies simultaneously exist in the polluted water bodies of the oil fields at present and the problems of high supervision difficulty and high environmental risk are faced, the characteristics that the high-salinity water bodies, the high-hydrocarbon-containing water bodies and the clean water bodies have weak wave spectrum difference characteristics in a visible light and near infrared spectrum interval are utilized, the weak information characteristics are enhanced through the aggregation analysis of time sequence high-resolution remote sensing images, the automatic identification of the two types of oil field polluted water bodies is realized, and the blank of the identification of the type of polluted water bodies is filled. The PWI can be used for simultaneously dividing the oil field high-salinity water body and the high hydrocarbon-containing polluted water body; based on a time sequence remote sensing image set formed by aggregation and superposition of different phase quantities obtained by multi-time phase superposition, fitting to obtain a fitting relation between a target PWI and the quantity of the superposed time phases, and adopting different threshold settings for targets with different existing times to identify the targets. It is worth explaining that in the embodiment of the invention, the identification of the polluted water body in the oil field is based on the target of remote sensing interpretation, and is not based on the whole high-resolution remote sensing image; in addition, targets with different continuous existence times are set and identified by adopting different thresholds of PWI, and the identification precision of the ground object is influenced by the fitting relation between PSI and the number of superposed time phases; the aggregation processing of the multi-temporal remote sensing images is based on the multi-temporal remote sensing images, and the registration precision after the orthorectification influences the target identification.
In order to make the application better understood by those skilled in the art, the following examples illustrate the implementation of the application:
(1) establishing a high-resolution time sequence remote sensing data set of a target area
Obtaining original satellite remote sensing data of a plurality of time phases of a detection area, and establishing a high-resolution time sequence remote sensing data set { DN (numerical control) of a target area 1 ，DN 2 ，。。。。。。DN n Arranging data in the data set according to an imaging time sequence, wherein the remote sensing data comprises visible light red, green, blue and near infrared spectrum wave bands, carrying out radiometric calibration and atmospheric correction processing on each original satellite remote sensing data in the data set to obtain reflectivity remote sensing data, and then carrying out orthorectification on the reflectivity remote sensing data to obtain a remote sensing data set based on reflectivity after geographic registration;
(2) water body target extraction
Calculating a water body index NDWI for each reflectivity image in the remote sensing data set processed in the step 1, extracting a water body area from the detection area based on the water body index, and determining the existence period of different water body targets, namely determining the time phase times of each target detected by remote sensing;
(3) masking treatment of water and non-water regions
Masking the non-target area, wherein the remote sensing data of the masked area does not participate in the aggregation operation, and only the data of the target area which does not pass through the mask participates in the aggregation processing;
(4) aggregated remote sensing dataset acquisition
Aggregating the remote sensing data in the time sequence remote sensing data set processed in the step 3 to obtain an aggregated remote sensing data set { DNnew) obtained by overlapping n different time phases 1 ，DNnew 2 ，。。。。。。DNnew n And (c) the step of (c) in which,
(5) performing spectral feature analysis based on the typical target;
(6) constructing a characteristic index PWI (production Watership index);
(7) PWI calculation based on aggregated remote sensing data set
Based on the aggregate remote sensing data set of the step 4, each aggregate remote sensing data DNnew n All calculate to obtain the structural index PWI n Wherein, PWI n Is based on remote sensing data DNnew obtained by polymerizing n time phases n (ii) calculated PWI data;
(8) threshold setting based on aggregated remote sensing data set
The method comprises the steps of utilizing threshold setting of structural characteristic indexes (PWI) to identify water with high mineralization and water with high hydrocarbon pollution from water targets, and enabling the water targets to pass through two threshold PWIs oil And PWI salinity To identify two types of targets. Considering the inconsistency of the existing time periods of the detection targets, different thresholds need to be adopted for detection of the targets with different existing periods, so that the method is based on the aggregated remote sensing data set { DNnew 1 ，DNnew 2 ，。。。。。。DNnew n Get different threshold PWI oil And PWI salinity And the target detection device is used for detecting targets with different existence periods.
(9) Linear relation fitting of characteristic index threshold setting and multi-temporal superposition number
Based on n obtained threshold PWI oil And PWI salinity Separately fitting the PWI oill And PWI salinity Linear relation with the aggregation time phase quantity is used for estimating target detection threshold values of different existence periods;
(10) identification of contaminated water
Aiming at the targets with different existence periods, different thresholds are utilized to realize the identification of the water body with high mineralization and the water body polluted by high hydrocarbon.
The invention is based on the remote sensing interpretation of high-resolution remote sensing data, utilizes multi-temporal high-resolution remote sensing data to acquire typical clean water, high-salinity water and high-hydrocarbon-content polluted water samples aiming at an interpreted target, analyzes the spectral characteristics at a multispectral wave band, identifies the polluted water in an oil field by constructing a characteristic identification index (PWI), acquires the relation between the PWI and the number of the multi-temporal superposition based on the typical target, sets different threshold values aiming at targets with different continuous existence times, effectively inhibits a background value by setting the threshold values, highlights target ground objects, and thus can realize the remote and rapid identification of the polluted water in the oil field.
In order to verify the effect of the invention, a certain research area is selected, and classified extraction is carried out by taking GF-2 remote sensing data as an example, and the specific technical scheme adopted is as follows:
(1) high-resolution time sequence remote sensing data set establishment and preprocessing
Obtaining GF-2 multi-temporal original remote sensing data of a preset target area, forming a remote sensing data set consisting of n multi-temporal remote sensing data, arranging the multi-temporal remote sensing data according to a time sequence, establishing a time sequence remote sensing data set, preprocessing the original remote sensing data in the data set, checking head file information of the original data, performing radiation correction on the multispectral data according to a calibration parameter, performing atmospheric correction to obtain reflectivity data of the multispectral data, performing orthorectification on the reflectivity data, performing geographic registration on the time sequence remote sensing data to obtain a preprocessed time sequence remote sensing data set { DN 1 ，DN 2 ，。。。。。。DN n }。
(2) Remote sensing extraction of water body information
Extracting the reflectivity data in the remote sensing data set after the pretreatment of the step 1 through setting a threshold value based on a water body index (NDWI), wherein the formula is as follows:
NDWI ═ ((p (green) -p (nir))/((p (green)) + p (nir)) (equation 1)
Wherein, p (green) and p (nir) respectively represent reflectance values at a green band and a near-infrared band, and based on the extracted water body information, the existence period of different water body targets in the time sequence remote sensing data image integration period is determined, that is, the number of times of a time phase of each target detected by the remote sensing data set is determined, so as to perform target identification by using different threshold settings in the later period.
(3) Masking treatment of water target area
Extracting a water body target boundary, generating a binary data mask layer of the water body target, performing mask processing on the multispectral data, keeping a reflectivity value in the water body boundary, and setting the reflectivity outside the water body boundary as an invalid value to obtain a masked remote sensing data set.
(4) Aggregate processing of time series remote sensing data (aggregate remote sensing data set acquisition)
Aggregating the data in the time sequence remote sensing data set after the step 3, sequentially accumulating the data with the first time phase as the reference (the data in the time sequence data set are arranged according to the time sequence), and respectively obtaining single-time phase data DNnew 1 Double time phase polymerization data DNnew 2 Up to n time phase polymerization data DNnew obtained by adding n time phases n And finally, obtaining an aggregate remote sensing data set { DNnew 1 ，DNnew 2 ，。。。。。。DNnew n As formula 2:
wherein DN i The reflectivity data of the ith time phase in the time sequence remote sensing data set after the mask processing is carried out, n is the number of the time phases in the time sequence remote sensing data set, DNnew n The aggregated remote sensing data is obtained by adding the remote sensing data of n time phases.
(5) Spectral feature analysis
Based on a time sequence remote sensing data set after polymerization treatment, typical clean water body, high salinity water body and high hydrocarbon-containing polluted water body targets are selected, the average reflectivity in a target region represents the reflectivity of the targets, the remote sensing reflectivity value of the typical water body targets is obtained, the single-time phase and double-time phase reflectivity of the three types of targets are respectively subjected to statistical analysis by taking a single-time phase and a double-time phase as examples, and research shows that the clean water body presents stronger absorption characteristics in a near infrared band and the high hydrocarbon-containing water body presents weak absorption characteristics in a visible light region.
(6) Feature index construction
According to the spectral analysis result, a characteristic index PWI (production Water index) is constructed by using the visible light red, green and near infrared bands, as shown in formula 3:
PWI ═ (p (green) -p (red))/p (nir) (equation 3)
Wherein p (green) represents reflectance values of green band, p (red) represents reflectance values of red band, and p (nir) represents reflectance values of near infrared band.
(7) PWI calculation of aggregated remote sensing data sets
Based on the aggregate remote sensing data set in the step 4, DNnew is carried out on each aggregate remote sensing data n Computing to obtain PWI n Data, wherein, PWI n Is based on remote sensing data DNnew obtained by polymerizing n time phases n Calculated PWI data.
(8) Threshold setting based on aggregated remote sensing data set
The method comprises the steps of utilizing threshold setting of structural characteristic indexes (PWI) to identify water with high mineralization and water with high hydrocarbon pollution from water targets, and enabling the water targets to pass through two threshold PWIs oil And PWI salinity To identify two types of targets. Considering the inconsistency of the existing time periods of the detection targets, different thresholds need to be adopted for detection of the targets with different existing periods, so that the method is based on the aggregated remote sensing data set { DNnew 1 ，DNnew 2 ，。。。。。。DNnew n Obtaining i different threshold settings for the detection target with i time phases in the existing periodTo obtain { PWI oil 1 ，PWI oil 2 ，。。。。。。，PWI oil i And { PWI } salinity 1 ，PWI salinity 2 ，。。。。。。，PWI salinity i And f, wherein i is less than or equal to n, when the detection target exists in the whole period of the time sequence remote sensing data set all the time, i is equal to n, and corresponding threshold values are adopted for setting the detection targets with different existence periods.
(9) Relation fitting of characteristic index threshold setting and multi-temporal superposition quantity
Based on the obtained i pair threshold PWI oil And PWI salinity Separately fitting the PWI oill And PWI salinity And the number of aggregation phases, for calculating a detection threshold of the target whose number of detection target existence phases is greater than i phases, as shown in formula 4:
PWI ═ k · n + b equation 3
Wherein n is the number of superimposed time phases, PSWI n K and b are coefficients obtained by fitting, and are values calculated based on the reflectance data after the n time phases are superimposed.
Based on the linear relation between the threshold value setting of least square fitting structural characteristic indexes and the number of superposed time phases, the DNnew of the aggregated remote sensing data based on superposition of different time phases can be calculated according to the linear relation n The target identification threshold of (a);
(10) identification of oil field polluted water
And setting a threshold value through data statistics by using the constructed index, and identifying the water body with high mineralization degree and the water body with high hydrocarbon pollution from the water body target. The threshold value can be set according to the quantity of collected multi-temporal remote sensing data in the target existence interval and the relationship between the PSWI in the 7 th time and the data time phase number n.
In conclusion, the invention constructs a characteristic index (PWI), and the characteristic index can be used for simultaneously dividing the oil field water body with high mineralization and the water body with high hydrocarbon pollution; based on a time sequence remote sensing data set formed by aggregation and superposition of different phase quantities obtained by multi-time phase superposition, fitting to obtain a fitting relation between a target PWI and the quantity of the superposed time phases, and adopting different threshold settings for targets with different existing times to identify the targets.
The method mainly comprises the following steps: firstly, the identification of the polluted water body in the oil field is based on the target of remote sensing interpretation, and is not based on the whole high-resolution remote sensing data; secondly, targets with different continuous existence times are identified by adopting different threshold settings of PWI, and the fitting relation between the PWI and the number of superposed time phases influences the identification precision of the ground objects; and thirdly, the aggregation processing of the multi-temporal remote sensing data is based on the multi-temporal remote sensing data, and the registration precision after the orthorectification influences the target identification.
Based on the same inventive concept, the embodiment of the application also provides an oil field polluted water body identification device based on the time sequence remote sensing image, which can be used for realizing the method described in the embodiment, as described in the following embodiment. Because the principle of solving the problems of the oil field polluted water body recognition device based on the time sequence remote sensing image is similar to that of the method, the implementation of the oil field polluted water body recognition device based on the time sequence remote sensing image can refer to the implementation of the method, and repeated parts are not repeated. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware or a combination of software and hardware is also possible and contemplated.
Fig. 5 is a structural block diagram of an oil field polluted water body identification device based on a time sequence remote sensing image in the embodiment of the invention. As shown in fig. 5, the oil field polluted water body identification device based on the time series remote sensing image comprises: the system comprises a time sequence remote sensing image data set establishing module 10, an image processing module 20, a water body index calculating module 30, a water body target region extracting module 40, a mask processing module 50, an image aggregation module 60, a production waste liquid index calculating module 70, a threshold value obtaining module 80 and a polluted water body identification module 90.
The time sequence remote sensing image data set establishing module 10 establishes a time sequence remote sensing image data set according to original satellite remote sensing image data of a plurality of time phases of a research area;
the image processing module 20 performs radiometric calibration, atmospheric correction, orthorectification and image registration on each original satellite remote sensing image data in the time sequence remote sensing image data set to obtain reflectivity values corresponding to each waveband data;
the water body index calculation module 30 determines the water body index of the corresponding time sequence remote sensing image according to the reflectivity value corresponding to each wave band data in each time sequence remote sensing image;
the water body target area extraction module 40 extracts a water body target area in the corresponding time sequence remote sensing image based on the water body index;
the mask processing module 50 performs mask processing on the non-water body region in the corresponding time sequence remote sensing image according to the water body target region;
the image aggregation module 60 obtains a time series aggregation remote sensing image data set according to the time series remote sensing image data set after mask processing;
the production waste liquid index calculation module 70 obtains the production waste liquid index of each pixel point in the water target area in each aggregated remote sensing data in the time sequence aggregated remote sensing image data set;
the threshold value obtaining module 80 obtains a corresponding threshold value based on a preset threshold value-frequency corresponding relation according to the occurrence frequency of the water body target in the time sequence remote sensing image set;
the polluted water body identification module 90 identifies whether the water body target is a production polluted water body according to the production waste liquid index of each pixel point in the water body target area and the corresponding threshold value.
By adopting the technical scheme, the polluted water body is identified based on the pollution index of the production waste liquid and the corresponding threshold value by establishing the time sequence remote sensing image set, so that the identification difficulty is reduced, and the identification precision and efficiency are improved.
The apparatuses, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or implemented by a product with certain functions. A typical implementation device is an electronic device, which may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
In a typical example, the electronic device specifically includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the program to implement the steps of the method for identifying the contaminated water body in the oil field based on the time-series remote sensing image.
Referring now to FIG. 6, shown is a schematic diagram of an electronic device 600 suitable for use in implementing embodiments of the present application.
As shown in fig. 6, the electronic apparatus 600 includes a Central Processing Unit (CPU)601 that can perform various appropriate works and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM)) 603. In the RAM603, various programs and data necessary for the operation of the system 600 are also stored. The CPU601, ROM602, and RAM603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted as necessary on the storage section 608.
In particular, according to an embodiment of the present invention, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, an embodiment of the present invention includes a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the method for identifying an oilfield polluted water based on a time series remote sensing image.
In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
For convenience of description, the above devices are described as being divided into various units by function, respectively. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.
The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
All the embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. An oil field polluted water body identification method based on a time sequence remote sensing image is characterized by comprising the following steps:
establishing a time sequence remote sensing image data set according to original satellite remote sensing image data of a plurality of time phases in a research area;
carrying out radiometric calibration, atmospheric correction, orthorectification and image registration on each original satellite remote sensing image data in the time sequence remote sensing image data set to obtain reflectivity values corresponding to each waveband data;
determining a water body index of the corresponding time sequence remote sensing image according to the reflectivity value corresponding to each wave band data in each time sequence remote sensing image;
extracting a water body target area in a corresponding time sequence remote sensing image based on the water body index;
performing mask processing on a non-water body region in the corresponding time sequence remote sensing image according to the water body target region;
obtaining a time sequence aggregation remote sensing image data set according to the time sequence remote sensing image data set after mask processing;
acquiring production waste liquid indexes of all pixel points in a water target area in all aggregated remote sensing data in the time sequence aggregated remote sensing image data set;
acquiring a corresponding threshold value based on a preset threshold value-frequency corresponding relation according to the occurrence frequency of the water body target in the time sequence remote sensing image set;
and identifying whether the water body target is a production polluted water body or not according to the production waste liquid index of each pixel point in the water body target area and the corresponding threshold value.
2. The method for identifying the polluted water body in the oil field based on the time sequence remote sensing image according to claim 1, wherein the steps of performing orthorectification, radiometric calibration, atmospheric rectification and image registration on each original satellite remote sensing image data in the time sequence remote sensing image data set comprise:
obtaining calibration parameters and correction parameters according to header file information of original satellite remote sensing data of a plurality of time phases;
carrying out radiometric calibration, atmospheric correction and orthorectification on each original satellite remote sensing image data in the time sequence remote sensing image data set according to the calibration parameters and the correction parameters;
and performing geographic registration on the corrected images.
3. The method for identifying the polluted water body in the oil field based on the time sequence remote sensing image according to claim 1, wherein the water body index corresponding to each area in the time sequence remote sensing image is determined according to the following formula:
NDWI＝((p(Green)-p(NIR))/((p(Green)+p(NIR))
wherein p (green) and p (nir) represent reflectance values corresponding to green and near infrared band data, respectively.
4. The method for identifying the polluted water body in the oil field based on the time sequence remote sensing image according to claim 1, further comprising the following steps of:
setting a threshold-frequency corresponding relation.
5. The method for identifying the polluted water body in the oil field based on the time sequence remote sensing image according to claim 4, wherein the setting of the threshold-frequency corresponding relation comprises the following steps:
carrying out time phase superposition processing on the time sequence remote sensing image data set after the mask processing to obtain a superposed remote sensing image data set;
obtaining an average value of production waste liquid indexes of a typical water target area in each superposed remote sensing image and corresponding occurrence times;
and fitting the production waste liquid index average value of the typical water body target area in each superposed remote sensing image and the corresponding occurrence frequency to obtain a threshold value-frequency corresponding relation.
6. The method for identifying the polluted water body in the oil field based on the time sequence remote sensing image according to claim 1, wherein the step of obtaining the time sequence aggregation remote sensing image data set according to the time sequence remote sensing image data set after the mask processing comprises the following steps:
and superposing the time sequence remote sensing images after the mask processing to obtain the polymerized remote sensing image.
7. The method for identifying the oil field polluted water body based on the time sequence remote sensing image according to any one of claims 1 to 6, wherein the index of the production waste liquid of each pixel point in the water body target area is determined according to the following formula:
PWI＝(p(Green)-p(Red))/p(NIR)
wherein p (green) represents reflectance values corresponding to green band data, p (red) represents reflectance values corresponding to red band data, and p (nir) represents reflectance values corresponding to near infrared band data.
8. The utility model provides an oil field pollutes water recognition device based on chronogenesis remote sensing image which characterized in that includes:
the time sequence remote sensing image data set establishing module is used for establishing a time sequence remote sensing image data set according to original satellite remote sensing image data of a plurality of time phases in a research area;
the image processing module is used for carrying out radiometric calibration, atmospheric correction, orthorectification and image registration on each original satellite remote sensing image data in the time sequence remote sensing image data set to obtain reflectivity values corresponding to each waveband data;
the water body index calculation module is used for determining the water body index of the corresponding time sequence remote sensing image according to the reflectivity value corresponding to each wave band data in each time sequence remote sensing image;
the water body target area extraction module is used for extracting a water body target area in the corresponding time sequence remote sensing image based on the water body index;
the mask processing module is used for performing mask processing on a non-water body region in the corresponding time sequence remote sensing image according to the water body target region;
the image aggregation module is used for obtaining a time sequence aggregation remote sensing image data set according to the time sequence remote sensing image data set after mask processing;
the production waste liquid index calculation module is used for acquiring the production waste liquid index of each pixel point in the water target area in each aggregated remote sensing data in the time sequence aggregated remote sensing image data set;
the threshold value acquisition module is used for acquiring a corresponding threshold value based on a preset threshold value-frequency corresponding relation according to the occurrence frequency of a water body target in the time sequence remote sensing image set;
and the polluted water body identification module is used for identifying whether the water body target is a production polluted water body or not according to the production waste liquid index of each pixel point in the water body target area and the corresponding threshold value.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method for identifying contaminated water in an oil field based on time series remote sensing images according to any one of claims 1 to 7 when executing the program.
10. A computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps of the method for identifying a contaminated water body in an oil field based on time series remote sensing images according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110079947.6A CN114821287A (en) | 2021-01-21 | 2021-01-21 | Oil field polluted water body identification method and device based on time sequence remote sensing image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110079947.6A CN114821287A (en) | 2021-01-21 | 2021-01-21 | Oil field polluted water body identification method and device based on time sequence remote sensing image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114821287A true CN114821287A (en) | 2022-07-29 |
Family
ID=82524380
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110079947.6A Pending CN114821287A (en) | 2021-01-21 | 2021-01-21 | Oil field polluted water body identification method and device based on time sequence remote sensing image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114821287A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115424143A (en) * | 2022-08-29 | 2022-12-02 | 南方海洋科学与工程广东省实验室(广州) | Water source pollution tracing method and device, storage medium and computer equipment |
| CN117557584A (en) * | 2024-01-10 | 2024-02-13 | 北京观微科技有限公司 | Water body extraction method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107944368A (en) * | 2017-11-16 | 2018-04-20 | 中国科学院遥感与数字地球研究所 | A kind of Clean water withdraw method based on sequential remote sensing images |
| CN108169142A (en) * | 2017-12-20 | 2018-06-15 | 环境保护部卫星环境应用中心 | Water colour exception method for rapidly positioning and device based on remote sensing image |
| CN110849814A (en) * | 2019-11-20 | 2020-02-28 | 平衡机器科技(深圳)有限公司 | Remote sensing image processing method based on multi-source remote sensing satellite |
| AU2020101095A4 (en) * | 2020-06-23 | 2020-07-23 | Tarim University | A Satellite Remote Sensing Monitoring Method for the Content of Chlorophyll A in the Canopy of Jujube Trees |
-
2021
- 2021-01-21 CN CN202110079947.6A patent/CN114821287A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107944368A (en) * | 2017-11-16 | 2018-04-20 | 中国科学院遥感与数字地球研究所 | A kind of Clean water withdraw method based on sequential remote sensing images |
| CN108169142A (en) * | 2017-12-20 | 2018-06-15 | 环境保护部卫星环境应用中心 | Water colour exception method for rapidly positioning and device based on remote sensing image |
| CN110849814A (en) * | 2019-11-20 | 2020-02-28 | 平衡机器科技(深圳)有限公司 | Remote sensing image processing method based on multi-source remote sensing satellite |
| AU2020101095A4 (en) * | 2020-06-23 | 2020-07-23 | Tarim University | A Satellite Remote Sensing Monitoring Method for the Content of Chlorophyll A in the Canopy of Jujube Trees |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115424143A (en) * | 2022-08-29 | 2022-12-02 | 南方海洋科学与工程广东省实验室(广州) | Water source pollution tracing method and device, storage medium and computer equipment |
| CN117557584A (en) * | 2024-01-10 | 2024-02-13 | 北京观微科技有限公司 | Water body extraction method and device, electronic equipment and storage medium |
| CN117557584B (en) * | 2024-01-10 | 2024-04-09 | 北京观微科技有限公司 | Water body extraction method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhao et al. | A robust adaptive spatial and temporal image fusion model for complex land surface changes | |
| Gašparović et al. | Automatic cost-effective method for land cover classification (ALCC) | |
| CN105243367B (en) | A kind of water body range monitoring method and device based on satellite remote sensing date | |
| Deng et al. | A spatially adaptive spectral mixture analysis for mapping subpixel urban impervious surface distribution | |
| CN102436652B (en) | Automatic registering method of multisource remote sensing images | |
| CN114821287A (en) | Oil field polluted water body identification method and device based on time sequence remote sensing image | |
| Ye et al. | FusionCNN: a remote sensing image fusion algorithm based on deep convolutional neural networks | |
| CN106650812B (en) | A kind of urban water-body extracting method of satellite remote-sensing image | |
| Rahmati et al. | Quantitative remote sensing of soil electrical conductivity using ETM+ and ground measured data | |
| CN109374537A (en) | The smelly identifying water boy method and device of urban black | |
| CN107145891B (en) | Water body extraction method and system based on remote sensing image | |
| CN107292258B (en) | High-spectral image low-rank representation clustering method based on bilateral weighted modulation and filtering | |
| CN103871058A (en) | Compressed sampling matrix decomposition-based infrared small target detection method | |
| Kageyama et al. | Analysis of water quality in Miharu dam reservoir, Japan, using UAV data | |
| CN109859231A (en) | A kind of leaf area index extraction threshold segmentation method based on optical imagery | |
| CN113433075B (en) | Simple remote sensing rapid monitoring method for black and odorous water body | |
| Fu et al. | Fusion of hyperspectral and multispectral images accounting for localized inter-image changes | |
| Ma et al. | A spectral grouping-based deep learning model for haze removal of hyperspectral images | |
| Li et al. | A pseudo-siamese deep convolutional neural network for spatiotemporal satellite image fusion | |
| CN108827880B (en) | Earth surface coverage change detection method based on multispectral image and NDVI time sequence | |
| JP6958743B2 (en) | Image processing device, image processing method and image processing program | |
| Wang et al. | Smoothing filter-based panchromatic spectral decomposition for multispectral and hyperspectral image pansharpening | |
| Rao et al. | Fast spatiotemporal data fusion: merging LISS III with AWiFS sensor data | |
| Stankevich et al. | Knowledge-based multispectral remote sensing imagery superresolution | |
| CN112861824B (en) | Coastline extraction method and device, terminal device and readable storage medium |
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 |