CN112270375B - Method, device, equipment and storage medium for determining trace - Google Patents
Method, device, equipment and storage medium for determining trace Download PDFInfo
- Publication number
- CN112270375B CN112270375B CN202011246109.5A CN202011246109A CN112270375B CN 112270375 B CN112270375 B CN 112270375B CN 202011246109 A CN202011246109 A CN 202011246109A CN 112270375 B CN112270375 B CN 112270375B
- Authority
- CN
- China
- Prior art keywords
- companion
- track
- determining
- target
- passable area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 29
- 238000007637 random forest analysis Methods 0.000 claims abstract description 27
- 238000012937 correction Methods 0.000 claims description 17
- 238000007781 pre-processing Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 abstract description 27
- 238000012545 processing Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 9
- 238000012876 topography Methods 0.000 description 7
- 230000005855 radiation Effects 0.000 description 5
- 238000002310 reflectometry Methods 0.000 description 5
- 239000002689 soil Substances 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000012952 Resampling Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000003628 erosive effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 239000000443 aerosol Substances 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/55—Specular reflectivity
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N2021/1793—Remote sensing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The method, the device, the equipment and the storage medium for determining the trace track provided by the application, wherein the method comprises the following steps: and acquiring a plurality of historical companion tracks of each road section in the long-distance pipeline, wherein each historical companion track comprises position information of a plurality of track points, acquiring at least one alternative companion track from the plurality of historical companion tracks by adopting a random forest algorithm, and determining a target companion track of each road section from the at least one alternative companion track. Therefore, the automatic identification of the accompanying track is realized, and the inspection quality and the inspection efficiency are improved.
Description
Technical Field
The present invention relates to the field of computer processing technologies, and in particular, to a method, an apparatus, a device, and a storage medium for determining a trace.
Background
Long-distance pipeline refers to a pipeline for conveying commodity media, and the long-distance pipeline usually spans a large number of mileage and important protection facilities of residents, roads and rivers along the line, and once the pipeline leaks, serious safety accidents can be easily caused, so that setting pipeline inspection posts is extremely important for pipeline safety.
In the prior art, the tracing track is a patrol track, which refers to a walking path of a pipeline patrol personnel when the pipeline is patrol, and the patrol track is usually determined in a buffer area of 50 meters, 100 meters and 200 meters at two sides of a long-distance pipeline.
However, some inspection areas cannot pass due to topography or meteorological factors, so that pipeline inspection staff cannot inspect long-distance pipelines in the areas, and inspection quality and inspection efficiency are low.
Disclosure of Invention
The invention aims to provide a method, a device, equipment and a storage medium for determining a tracing track, aiming at the defects in the prior art, so as to solve the problems of low inspection quality and low inspection efficiency in the prior art.
In order to achieve the above purpose, the technical solution adopted in the embodiment of the present application is as follows:
in a first aspect, an embodiment of the present application provides a method for determining a trace, where the method includes:
acquiring a plurality of history companion tracks of each road section in a long-distance pipeline, wherein each history companion track comprises position information of a plurality of track points;
acquiring at least one alternative companion track from the plurality of historical companion tracks by adopting a random forest algorithm;
and determining the target companion track of each road section from the at least one candidate companion track.
In an alternative embodiment, the determining the target companion track of each road segment from the at least one candidate companion track includes:
extracting vegetation indexes and texture information from remote sensing images of areas on two sides of the long-distance pipeline, wherein the vegetation indexes are used for indicating the reflection degree of vegetation on light, and the texture information is used for indicating the type of ground objects;
determining whether at least one passable area exists in the remote sensing image according to the vegetation index and the texture information;
if yes, determining the target companion track from the at least one alternative companion track according to the at least one passable area.
In an optional embodiment, the determining the target companion track from the at least one candidate companion track according to the at least one passable area includes:
acquiring a target passable area from the at least one passable area by adopting a random forest algorithm;
and determining the target companion track positioned in the target passable area from the at least one alternative companion track.
In an alternative embodiment, the determining whether at least one passable area exists in the remote sensing image according to the vegetation index and the texture information includes:
obtaining a terrain factor according to a terrain digital elevation model of the area on both sides of the long-distance pipeline, wherein the terrain factor is used for indicating the terrain characteristics of the area on both sides of the long-distance pipeline;
and determining whether the at least one passable area exists in the remote sensing image according to the vegetation index, the texture information and the terrain factor.
In an alternative embodiment, the determining whether the at least one passable area exists in the remote sensing image according to the vegetation index, the texture information and the terrain factor includes:
acquiring real-time weather disaster data of an area where the long-distance pipeline is located;
and determining whether the at least one passable area exists in the remote sensing image according to the vegetation index, the texture information, the terrain factors and the real-time meteorological disaster data.
In an alternative embodiment, the determining whether the at least one passable area exists in the remote sensing image according to the vegetation index, the texture information, the terrain factor and the real-time weather disaster data includes:
acquiring weather factors according to the real-time weather disaster data, wherein the weather factors are used for indicating weather disaster grades of areas where the long-distance pipeline is located;
and determining whether the at least one passable area exists in the remote sensing image according to the vegetation index, the texture information, the terrain factor and the meteorological factor.
In an optional embodiment, before extracting the vegetation index and the texture information from the remote sensing image of the area where the two sides of the long-distance pipeline are located, the method further includes:
performing image preprocessing on the remote sensing image, wherein the image preprocessing comprises at least one of the following processes: radiometric calibration, atmospheric correction, orthographic correction and image cropping.
In a second aspect, another embodiment of the present application provides a device for determining a trace, where the device includes:
the acquisition module is used for acquiring a plurality of historical companion tracks of each road section in the long-distance pipeline, each historical companion track comprises position information of a plurality of track points, and at least one alternative companion track is acquired from the plurality of historical companion tracks by adopting a random forest algorithm;
and the determining module is used for determining the target companion track of each road section from the at least one candidate companion track.
In an alternative embodiment, the determining module is specifically configured to:
extracting vegetation indexes and texture information from remote sensing images of areas on two sides of the long-distance pipeline, wherein the vegetation indexes are used for indicating the reflection degree of vegetation on light, and the texture information is used for indicating the type of ground objects;
determining whether at least one passable area exists in the remote sensing image according to the vegetation index and the texture information;
if yes, determining the target companion track from the at least one alternative companion track according to the at least one passable area.
In an alternative embodiment, the determining module is specifically configured to:
acquiring a target passable area from the at least one passable area by adopting a random forest algorithm;
and determining the target companion track positioned in the target passable area from the at least one alternative companion track.
In an alternative embodiment, the determining module is specifically configured to:
obtaining a terrain factor according to a terrain digital elevation model of the area on both sides of the long-distance pipeline, wherein the terrain factor is used for indicating the terrain characteristics of the area on both sides of the long-distance pipeline;
and determining whether the at least one passable area exists in the remote sensing image according to the vegetation index, the texture information and the terrain factor.
In an alternative embodiment, the determining module is specifically configured to:
acquiring real-time weather disaster data of an area where the long-distance pipeline is located;
and determining whether the at least one passable area exists in the remote sensing image according to the vegetation index, the texture information, the terrain factors and the real-time meteorological disaster data.
In an alternative embodiment, the determining module is specifically configured to:
acquiring weather factors according to the real-time weather disaster data, wherein the weather factors are used for indicating weather disaster grades of areas where the long-distance pipeline is located;
and determining whether the at least one passable area exists in the remote sensing image according to the vegetation index, the texture information, the terrain factor and the meteorological factor.
In an alternative embodiment, the method further comprises:
the processing module is used for carrying out image preprocessing on the remote sensing image, and the image preprocessing comprises at least one of the following processes: radiometric calibration, atmospheric correction, orthographic correction and image cropping.
In a third aspect, another embodiment of the present application provides a computer device, comprising: a processor, a storage medium storing machine-readable instructions executable by the processor, the processor and the storage medium communicating over a bus when the computer device is running, the processor executing the machine-readable instructions to perform a method as in any of the first aspects above.
In a fourth aspect, another embodiment of the present application provides a storage medium having stored thereon a computer program which, when executed by a processor, performs any of the above-described aspects.
The method, the device, the equipment and the storage medium for determining the trace track provided by the application, wherein the method comprises the following steps: and acquiring a plurality of historical companion tracks of each road section in the long-distance pipeline, wherein each historical companion track comprises position information of a plurality of track points, acquiring at least one alternative companion track from the plurality of historical companion tracks by adopting a random forest algorithm, and determining a target companion track of each road section from the at least one alternative companion track. Therefore, the automatic identification of the accompanying track is realized, and the inspection quality and the inspection efficiency are improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered limiting the scope, and that other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a method for determining a companion track according to an embodiment of the present application;
FIG. 2 shows a schematic diagram of a model of a random forest algorithm provided by an embodiment of the present application;
fig. 3 shows a second flowchart of a method for determining a trace track according to an embodiment of the present application;
fig. 4 shows a flowchart of a method for determining a companion track according to an embodiment of the present application;
fig. 5 shows a flowchart of a method for determining a companion track according to an embodiment of the present application;
fig. 6 shows a fifth flowchart of a method for determining a trace track according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of a determination device for a trace track according to an embodiment of the present application;
fig. 8 shows a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it should be understood that the accompanying drawings in the present application are only for the purpose of illustration and description, and are not intended to limit the protection scope of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. A flowchart, as used in this application, illustrates operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be implemented out of order and that steps without logical context may be performed in reverse order or concurrently. Moreover, one or more other operations may be added to the flow diagrams and one or more operations may be removed from the flow diagrams as directed by those skilled in the art.
In addition, the described embodiments are only some, but not all, of the embodiments of the present application. The components of the embodiments of the present application, which are generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, as provided in the accompanying drawings, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, are intended to be within the scope of the present application.
It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the presence of the features stated hereinafter, but not to exclude the addition of other features.
The main responsibility of the pipeline inspection staff is to monitor and inspect the environment around the pipeline body and the pipeline, report and inspect hidden dangers around the pipeline in advance, prevent major accidents and guarantee the pipeline safety.
The tracing track is a patrol track, which refers to a walking path of a pipeline patrol personnel when the pipeline patrol personnel patrol the pipeline, is a strip-shaped area, the patrol track is usually determined in a buffer area of 50 meters, 100 meters and 200 meters at the two sides of a long-distance pipeline at present, the pipeline patrol personnel need to patrol the tracing track in the buffer area of the pipeline in the patrol process, otherwise, the patrol quality is judged to be lower level or not pass due to the fact that the overtime is checked, but the method has no practical value and flexibility, and because the long-distance pipeline spans the mileage, the topography and the ground at the two sides of the pipeline have great influence on the patrol, and meanwhile, the pipeline patrol personnel cannot patrol the pipeline in a short distance due to factors such as weather disasters, the patrol quality and the patrol efficiency are influenced, and the patrol quality is low if the patrol is still carried out according to the tracing track in the fixed buffer area, so that the patrol quality is not beneficial to the check.
Based on the above problems, the current determination mode of the patrol tracing track can not meet the current actual demand, so the application provides a determination method of the tracing track, and the target tracing track of each road section is determined from the plurality of historical tracing tracks by combining the plurality of historical tracing tracks of each road section in a long-distance pipeline and adopting a random forest algorithm.
The following describes the method for determining the trace track provided in the present application in detail with reference to the following several specific embodiments.
Fig. 1 shows a first flowchart of a method for determining a trace provided in an embodiment of the present application, where an execution body of the embodiment may be a computer device, for example, may be a server, a mobile phone, a computer, etc., and as shown in fig. 1, the method may include:
s100, acquiring a plurality of historical accompanying tracks of each road section in the long-distance pipeline, wherein each historical accompanying track comprises position information of a plurality of track points.
S200, acquiring at least one alternative companion track from a plurality of historical companion tracks by adopting a random forest algorithm.
The long-distance pipeline is divided into a plurality of road sections, each road section can be provided with a corresponding pipeline inspection person for inspecting the road section, so that each road section in the long-distance pipeline can be provided with a plurality of historical tracing tracks, the plurality of historical tracing tracks can be tracing tracks obtained by the pipeline inspection person corresponding to each road section inspecting the road section in a historical period, and it is to be noted that the historical inspection condition and the travelling path habit of the pipeline inspection person can be different, and the historical period can be within half a year or within one year.
Each history trace includes position information of a plurality of trace points, that is, the history trace is composed of a plurality of trace points that have been inspected by a pipe inspection person.
And acquiring a plurality of historical companion tracks of each road section in the long-distance pipeline, performing big data analysis by adopting a random forest algorithm, and acquiring at least one alternative companion track from the plurality of historical companion tracks, namely, selecting the alternative companion track of each road section based on the plurality of historical companion tracks of each road section.
It should be noted that, the basic idea of the random forest algorithm is to select a plurality of independent subsamples from the original data set by using a bootstrap resampling method, and construct decision tree models one by one, and vote to obtain the final output classification result after each decision tree model is separately classified.
The random forest algorithm relies on the Python big data processing framework, python is a cross-platform object oriented open source scripting language. The Python big data processing frame contains a plurality of class libraries which need to be used for big data analysis, and the availability, the high availability and the like of random forest big data analysis can be realized based on the Python big data processing frame.
Referring to fig. 2 for explaining a random forest algorithm, fig. 2 shows a schematic diagram of a model of the random forest algorithm provided in the embodiment of the present application, and as shown in fig. 2, a history trace 1 to a history trace n are used as inputs of the model, and after classification is completed by the classifier through a decision tree model, that is, the classifier 1 to the classifier n, n are positive integers greater than or equal to 2, at least one candidate trace is obtained by voting, and it should be noted that, in the model processing process, a classification result may be represented by a score value, and then a trace with a score value greater than a preset score value may be used as the candidate trace.
S300, determining target companion tracks of all road sections from at least one candidate companion track.
The target companion track of each road section is determined from at least one alternative companion track, and is the optimal companion track of each road section selected currently, so that the complexity of companion track selection based on irrational and on-site acquisition of a pipeline generation buffer zone can be reduced to the minimum, and the target companion track of each road section can be generated for different road sections, and the method has great flexibility.
The method has the advantages that the target companion track of each road section determined by the method is professional in design, the server can be stable, the functional design is humanized, the operation is simple and convenient, and the user can automatically calculate and generate the optimal companion track of different pipeline inspection personnel by inputting a plurality of historical companion tracks of each road section in a long-distance pipeline in the system.
In addition, the determined target trace can be displayed on a map and applied to modules of over-distance alarm, inspection quality check and the like of an inspection system, so that the management and control efficiency is improved, meanwhile, historical trace data is saved, comparison check can be performed, the trace management level is improved, and powerful support and technical support are provided for the inspection management of long-distance pipelines.
According to the method for determining the companion track, a plurality of historical companion tracks of all road sections in a long-distance pipeline are obtained, each historical companion track comprises position information of a plurality of track points, at least one alternative companion track is obtained from the plurality of historical companion tracks by adopting a random forest algorithm, and a target companion track of each road section is determined from the at least one alternative companion track. Therefore, the automatic identification of the accompanying track is realized, and the inspection quality and the inspection efficiency are improved.
One possible implementation of determining the target companion trajectory for each road segment is described below in connection with the example of fig. 3. Fig. 3 shows a second flowchart of a method for determining a companion track according to an embodiment of the present application, as shown in fig. 3, step S300 may include:
s310, extracting vegetation index and texture information from remote sensing images of areas on two sides of the long-distance pipeline.
S320, determining whether at least one passable area exists in the remote sensing image according to the vegetation index and the texture information.
The vegetation index is used for indicating the reflection degree of the vegetation to light, the light reflection of different vegetation to the wave band is different, which areas in the remote sensing image have vegetation through the vegetation index, and which type of vegetation is.
Texture information is used to indicate the type of ground object, which refers to various physical objects and intangibles on the ground, the physical objects may include mountains, forests, buildings, etc., and the intangibles may include province and county.
The areas on both sides of the long-distance pipeline may be areas with preset distances from the left and right sides of the long-distance pipeline, where the preset distances may be, for example, 500 meters, 600 meters, etc., which is not limited in this embodiment.
Remote sensing images of the areas on two sides of the long-distance pipeline can be downloaded from a network, a preset image processing algorithm is adopted, vegetation index and texture information can be extracted from the remote sensing images, and whether at least one passable area exists in the remote sensing images or not is determined according to the vegetation index and the texture information.
It should be noted that, the preset image processing algorithm may be implemented based on an open source grid geographic data format library GDAL, which may perform reading, writing, processing, etc. of various grid data, and may extract vegetation index and texture information by performing image processing and calculation on the remote sensing image.
For example, if the vegetation index meets the preset vegetation index requirement and the texture information is mountain, it is indicated that the corresponding area has high coverage rate vegetation and mountain, and the area can be indicated as the non-passable area; similarly, if the vegetation index is less than the preset vegetation index and the texture information is a county boundary, then the area may be indicated as a passable area. That is, at least one passable area satisfies a vegetation index satisfying a preset vegetation index requirement, and the texture information satisfies a preset texture requirement, which may be, for example, an intangible object.
It should be noted that the vegetation index may include at least one of the following indexes:
normalized vegetation index, ratio vegetation index, difference vegetation index, enhanced vegetation index, red index.
The normalized vegetation index is the quotient of the difference between the reflection values of the near-red wave band and the red wave band, and can detect the vegetation generation state and the vegetation coverage.
The ratio vegetation index refers to the ratio of the reflectivity of the red light wave band to the near infrared wave band, and is suitable for vegetation monitoring with vigorous vegetation generation and high coverage.
The difference vegetation index refers to the difference of reflectivity of a red light wave band and a near-red light wave band, is sensitive to soil background change, and is suitable for detecting vegetation in early and middle stages or in low and middle coverage of vegetation development.
The enhanced vegetation index refers to supplementing the effect of aerosols on red light channels by the difference in blue and red light channel values to reduce the effect of atmospheric and soil noise.
The red index refers to a correction factor of the soil color affecting the vegetation index, which can correct detection of low vegetation coverage due to soil color changes.
And S330, if so, determining a target companion track from at least one alternative companion track according to the at least one passable area.
If it is determined that at least one passable region exists in the remote sensing image, a target companion track may be determined from at least one candidate companion track according to the at least one passable region, that is, a companion track located in the passable region is determined from the at least one candidate companion track as the target companion track. Therefore, the determined target companion track considers the trafficability and improves the rationality of the target companion track.
According to the method for determining the companion track, the vegetation index and the texture information are extracted from the remote sensing images of the areas on the two sides of the long-distance pipeline, whether at least one passable area exists in the remote sensing images is determined according to the vegetation index and the texture information, and if yes, the target companion track is determined from at least one alternative companion track according to the at least one passable area. And determining a passable area by combining the remote sensing image, and determining a target tracing track by combining the passable area, so that the rationality of the target tracing track is improved.
In an alternative embodiment, before extracting the vegetation index and the texture information from the remote sensing image of the area where the two sides of the long-distance pipeline are located, the method further includes:
image preprocessing is carried out on the remote sensing image, and the image preprocessing comprises at least one of the following processes: radiometric calibration, atmospheric correction, orthographic correction and image cropping.
In order to improve accuracy and rationality of the remote sensing image, the remote sensing image may be further subjected to image preprocessing before extracting vegetation index and texture information from the remote sensing image of the area where two sides of the long-distance pipeline are located, where the preprocessing includes at least one of the following processes: radiometric calibration, atmospheric correction, orthographic correction and image cropping.
The radiation calibration refers to converting the brightness gray value of an image into absolute radiation brightness when a user needs to calculate the spectral reflectivity or the spectral radiation brightness of a ground feature or when images acquired by different sensors at different times need to be compared.
Atmospheric correction refers to the process of inverting the true surface reflectivity of the surface features by eliminating radiation errors caused by atmospheric effects, because the total radiance of the surface target measured by the sensor is not a reflection of the true surface reflectivity, including radiation errors caused by atmospheric absorption, especially scattering.
The orthographic correction refers to resampling an image into an orthographic image by selecting a plurality of ground control points on the image and simultaneously carrying out inclination correction and projection difference correction on the image by utilizing digital elevation model data in the range of the image which is acquired originally.
Image cropping refers to cropping an image into one or more new image files based on the extent of the area actually worked or studied.
One implementation of determining a target companion trajectory from at least one alternative companion trajectory based on at least one passable region is described below in connection with the example of fig. 4. Fig. 4 shows a third flowchart of a method for determining a companion track according to an embodiment of the present application, as shown in fig. 4, step S330 may include:
s331, acquiring a target passable area from at least one passable area by adopting a random forest algorithm.
S332, determining the target companion track in the target passable area from at least one candidate companion track.
The method comprises the steps of classifying and voting at least one passable area by adopting a random forest algorithm, acquiring a target passable area from the at least one passable area, and determining a target tracing track positioned in the target passable area from at least one alternative tracing track, namely, referring to fig. 2, taking the at least one passable area as input of a model, respectively passing through classifiers, and voting to obtain the target passable area after classification, wherein the classification result of the at least one passable area can be expressed by a score value, and then taking the passable area with the score value larger than a preset score value as the target passable area.
It should be noted that at least one of the passable areas may have different passability, for example, the passable area 1 is covered with vegetation, the passable area 2 is not covered with vegetation, and the passable area 1 and the passable area 2 are different although they are passable areas, and the passable area 2 is more passable, and the score value of the passable area 2 may be higher than the score value of the passable area 1 when the random forest algorithm processing is performed.
According to the method for determining the companion track, a random forest algorithm is adopted, a target passable area is obtained from at least one passable area, and a target companion track located in the target passable area is determined from at least one alternative companion track. And a random forest algorithm is adopted to identify the passable target area, and the tracing track of the target is determined according to the passable target area, so that the rationality of the tracing track of the target is improved.
An embodiment of determining whether at least one passable area exists in the remote sensing image according to the vegetation index and the texture information is described below with reference to the embodiment of fig. 5. Fig. 5 shows a flowchart of a method for determining a companion track according to an embodiment of the present application. As shown in fig. 5, step S320 may include:
s321, obtaining a terrain factor according to a terrain digital elevation model of the area where the two sides of the long-distance pipeline are located.
S322, determining whether at least one passable area exists in the remote sensing image according to the vegetation index, the texture information and the terrain factor.
The terrain digital elevation models (Digital Elevation Model, DEM) of the areas on the two sides of the long-distance pipeline can be downloaded from a network, and a preset acquisition algorithm is adopted, so that terrain factors can be acquired according to the terrain digital elevation models, and the terrain factors are used for indicating the terrain characteristics of the areas on the two sides of the long-distance pipeline.
The topographical features may include, for example, a grade of the terrain, a rate of change of the grade of the terrain, and a elevation of the terrain.
According to the vegetation index, the texture information and the terrain factor, whether at least one passable area exists in the remote sensing image can be determined, namely, whether at least one passable area exists in the remote sensing image can be comprehensively judged by taking the vegetation index, the texture information and the terrain factor as consideration factors. For example, if the vegetation index meets the preset vegetation index requirement, the texture information is mountain and the gradient is greater than the preset gradient, it may be indicated that the corresponding area has high coverage of vegetation and mountain, and the gradient of mountain is greater, it may be indicated that the area is an unvented area. That is, at least one passable area satisfies a vegetation index satisfying a preset vegetation index requirement, the texture information satisfies a preset texture requirement, the preset texture requirement may be, for example, an intangible object, and the terrain factor satisfies a preset terrain factor, which may include, for example, a gradient less than a preset gradient.
In the embodiment, the passable area is further filtered by combining with the terrain factors, so that the rationality and the flexibility of the passable area are improved.
An implementation manner of determining whether at least one passable area exists in the remote sensing image according to the vegetation index, the texture information and the topography factor is described below with reference to the embodiment of fig. 6, fig. 6 shows a fifth flowchart of a method for determining a companion track provided in the embodiment of the present application, and as shown in fig. 6, step S322 may include:
s3221, acquiring real-time weather disaster data of an area where the long-distance pipeline is located.
S3222, determining whether the at least one passable area exists in the remote sensing image according to the vegetation index, the texture information, the terrain factors and the real-time meteorological disaster data.
The real-time weather disaster data of the area where the long-distance pipeline is located can be obtained from an weather table, and the real-time weather disaster data can comprise, for example, large rainfall, serious heavy erosion such as slump and landslide caused by debris flow, large flood and the like.
Determining whether at least one passable area exists in the remote sensing image according to the vegetation index, the texture information, the topography factor and the real-time weather disaster data, namely, the at least one passable area meets the vegetation index to meet the preset vegetation index requirement, the texture information meets the preset texture requirement, the topography factor meets the preset topography factor, and the real-time weather disaster data meets the preset weather requirement, wherein the preset weather requirement can be that the rainfall is smaller than the preset rainfall, for example.
In an alternative embodiment, step S3222 may include:
and acquiring weather factors according to the real-time weather disaster data.
And determining whether at least one passable area exists in the remote sensing image according to the vegetation index, the texture information, the terrain factor and the meteorological factor.
The weather factors are used for indicating weather disaster grades of areas where long-distance pipelines are located, that is, the weather disaster grades can be determined according to real-time weather disaster data, for example, the real-time weather disaster data comprise serious gravity erosion such as slump and landslide caused by debris flow, the corresponding weather factors can be the dangerous level of the debris flow, the real-time weather disaster data comprise large rainfall, and the corresponding weather factors can be the dangerous level of rainfall.
According to the vegetation index, the texture information, the topography factors and the meteorological factors, whether at least one passable area exists in the remote sensing image is determined, so that the meteorological factors are taken as consideration factors, the passable area is further filtered, the current meteorological conditions can be clearly represented by the meteorological factors, the passable area is not determined easily due to the fact that the data size of real-time meteorological data is large, and the meteorological factors are taken as filtering conditions of the passable area, so that the determination efficiency of the passable area can be improved.
In the embodiment, real-time weather disaster data are combined, the passable area is filtered when weather disasters occur, flexibility and rationality of companion track selection are realized, powerful support is provided for inspection management and assessment, automatic recognition of companion tracks is performed according to the real-time weather disaster data, and local conditions of companion track selection are realized; in addition, the generation of the accompanying tracks combines with the meteorological disaster data, the meteorological disaster data in different time periods has significance for the generation of the accompanying tracks of the pipeline inspection workers, and different accompanying tracks are automatically generated under different meteorological disaster conditions, so that the influence on inspection examination and inspection work is minimized.
It should be noted that, a plurality of historical trace tracks and target trace tracks of each road section in the long-distance pipeline can be backed up regularly, the backup mechanism can be established to backup the data in the database regularly, the backup medium can be an optical disk or a magnetic tape, the backup medium should be kept properly, and if necessary, the long-distance storage can be realized. An access authorization mechanism can be established, the database limits the rights of the user through rights management of different security levels so as to ensure the security of data stored in the database, and different roles can be set for convenience of rights management, and rights granting and recycling can be flexibly managed through the role management.
Fig. 7 shows a schematic structural diagram of a trace-track determining apparatus provided in an embodiment of the present application, and the trace-track determining apparatus 400 may be integrated in a computer device. As shown in fig. 7, the trace-track determining apparatus 400 may include:
an obtaining module 410, configured to obtain a plurality of historical companion tracks of each road section in the long-distance pipeline, where each historical companion track includes position information of a plurality of track points, and obtain at least one candidate companion track from the plurality of historical companion tracks by adopting a random forest algorithm;
a determining module 420, configured to determine a target companion track of each road segment from the at least one candidate companion track.
In an alternative embodiment, the determining module 420 is specifically configured to:
extracting vegetation indexes and texture information from remote sensing images of areas on two sides of the long-distance pipeline, wherein the vegetation indexes are used for indicating the reflection degree of vegetation on light, and the texture information is used for indicating the type of ground objects;
determining whether at least one passable area exists in the remote sensing image according to the vegetation index and the texture information;
if yes, determining the target companion track from the at least one alternative companion track according to the at least one passable area.
In an alternative embodiment, the determining module 420 is specifically configured to:
acquiring a target passable area from the at least one passable area by adopting a random forest algorithm;
and determining the target companion track positioned in the target passable area from the at least one alternative companion track.
In an alternative embodiment, the determining module 420 is specifically configured to:
obtaining a terrain factor according to a terrain digital elevation model of the area on both sides of the long-distance pipeline, wherein the terrain factor is used for indicating the terrain characteristics of the area on both sides of the long-distance pipeline;
and determining whether the at least one passable area exists in the remote sensing image according to the vegetation index, the texture information and the terrain factor.
In an alternative embodiment, the determining module 420 is specifically configured to:
acquiring real-time weather disaster data of an area where the long-distance pipeline is located;
and determining whether the at least one passable area exists in the remote sensing image according to the vegetation index, the texture information, the terrain factors and the real-time meteorological disaster data.
In an alternative embodiment, the determining module 420 is specifically configured to:
acquiring weather factors according to the real-time weather disaster data, wherein the weather factors are used for indicating weather disaster grades of areas where the long-distance pipeline is located;
and determining whether the at least one passable area exists in the remote sensing image according to the vegetation index, the texture information, the terrain factor and the meteorological factor.
In an alternative embodiment, the method further comprises:
the processing module 430 is configured to perform image preprocessing on the remote sensing image, where the image preprocessing includes at least one of the following processing: radiometric calibration, atmospheric correction, orthographic correction and image cropping.
The process flow of each module in the apparatus and the interaction flow between the modules may be described with reference to the related descriptions in the above method embodiments, which are not described in detail herein.
Fig. 8 shows a schematic structural diagram of a computer device provided in an embodiment of the present application, and as shown in fig. 8, a computer device 500 may include:
a processor 510, a memory 520 and a bus 530, the memory 520 storing machine readable instructions executable by the processor 510, the processor 510 and the memory 520 communicating over the bus 530 when the computer device 500 is running, the processor executing the machine readable instructions to perform the method embodiments described above.
The present application also provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the above-described method embodiments.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described system and apparatus may refer to corresponding procedures in the method embodiments, which are not described in detail in this application. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. The above-described apparatus embodiments are merely illustrative, and the division of the modules is merely a logical function division, and there may be additional divisions when actually implemented, and for example, multiple modules or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, indirect coupling or communication connection of devices or modules, electrical, mechanical, or other form.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes or substitutions are covered in the protection scope of the present application.
Claims (8)
1. A method of determining a companion trajectory, comprising:
acquiring a plurality of history companion tracks of each road section in a long-distance pipeline, wherein each history companion track comprises position information of a plurality of track points;
acquiring at least one alternative companion track from the plurality of historical companion tracks by adopting a random forest algorithm;
determining a target companion track of each road section from the at least one candidate companion track;
the determining the target companion track of each road section from the at least one candidate companion track comprises the following steps:
extracting vegetation indexes and texture information from remote sensing images of areas on two sides of the long-distance pipeline, wherein the vegetation indexes are used for indicating the reflection degree of vegetation on light, and the texture information is used for indicating the type of ground objects;
determining whether at least one passable area exists in the remote sensing image according to the vegetation index and the texture information;
if yes, determining the target companion track from the at least one alternative companion track according to the at least one passable area;
the determining the target companion track from the at least one alternative companion track according to the at least one passable area comprises:
acquiring a target passable area from the at least one passable area by adopting a random forest algorithm;
and determining the target companion track positioned in the target passable area from the at least one alternative companion track.
2. The method of claim 1, wherein the determining whether at least one passable area exists in the remote sensing image based on the vegetation index and the texture information comprises:
obtaining a terrain factor according to a terrain digital elevation model of the area on both sides of the long-distance pipeline, wherein the terrain factor is used for indicating the terrain characteristics of the area on both sides of the long-distance pipeline;
and determining whether the at least one passable area exists in the remote sensing image according to the vegetation index, the texture information and the terrain factor.
3. The method of claim 2, wherein the determining whether the at least one passable region exists in the remote sensing image based on the vegetation index, the texture information, and the terrain factor comprises:
acquiring real-time weather disaster data of an area where the long-distance pipeline is located;
and determining whether the at least one passable area exists in the remote sensing image according to the vegetation index, the texture information, the terrain factors and the real-time meteorological disaster data.
4. The method of claim 3, wherein the determining whether the at least one passable area exists in the remote sensing image based on the vegetation index, the texture information, the terrain factor, and the real-time weather hazard data comprises:
acquiring weather factors according to the real-time weather disaster data, wherein the weather factors are used for indicating weather disaster grades of areas where the long-distance pipeline is located;
and determining whether the at least one passable area exists in the remote sensing image according to the vegetation index, the texture information, the terrain factor and the meteorological factor.
5. The method of claim 1, further comprising, prior to extracting the vegetation index and the texture information from the remote sensing image of the area on both sides of the long-distance pipeline:
performing image preprocessing on the remote sensing image, wherein the image preprocessing comprises at least one of the following processes: radiometric calibration, atmospheric correction, orthographic correction and image cropping.
6. A trace-track determining apparatus, comprising:
the acquisition module is used for acquiring a plurality of historical companion tracks of each road section in the long-distance pipeline, each historical companion track comprises position information of a plurality of track points, and at least one alternative companion track is acquired from the plurality of historical companion tracks by adopting a random forest algorithm;
the determining module is used for determining the target companion track of each road section from the at least one candidate companion track;
the determining module is specifically configured to:
extracting vegetation indexes and texture information from remote sensing images of areas on two sides of the long-distance pipeline, wherein the vegetation indexes are used for indicating the reflection degree of vegetation on light, and the texture information is used for indicating the type of ground objects;
determining whether at least one passable area exists in the remote sensing image according to the vegetation index and the texture information;
if yes, determining the target companion track from the at least one alternative companion track according to the at least one passable area;
the determining module is specifically configured to:
acquiring a target passable area from the at least one passable area by adopting a random forest algorithm;
and determining the target companion track positioned in the target passable area from the at least one alternative companion track.
7. A computer device, comprising: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory in communication over the bus when the computer device is running, the processor executing the machine-readable instructions to perform the method of any of claims 1-5.
8. A storage medium having stored thereon a computer program which, when executed by a processor, performs the method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011246109.5A CN112270375B (en) | 2020-11-10 | 2020-11-10 | Method, device, equipment and storage medium for determining trace |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011246109.5A CN112270375B (en) | 2020-11-10 | 2020-11-10 | Method, device, equipment and storage medium for determining trace |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112270375A CN112270375A (en) | 2021-01-26 |
| CN112270375B true CN112270375B (en) | 2024-02-02 |
Family
ID=74339773
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011246109.5A Active CN112270375B (en) | 2020-11-10 | 2020-11-10 | Method, device, equipment and storage medium for determining trace |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112270375B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114333098B (en) * | 2021-12-27 | 2024-03-08 | 中国建设银行股份有限公司 | Night patrol method, night patrol device, electronic equipment and computer readable medium |
| CN114387367B (en) * | 2022-03-22 | 2022-06-10 | 南京天朗防务科技有限公司 | Radar track display method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109496288A (en) * | 2017-07-13 | 2019-03-19 | 北京嘀嘀无限科技发展有限公司 | System and method for determining track |
| CN109945877A (en) * | 2017-12-20 | 2019-06-28 | 北京中盈安信技术服务股份有限公司 | A kind of patrolled and examined track generation method and device |
| CN110414359A (en) * | 2019-07-01 | 2019-11-05 | 中国石化销售有限公司华南分公司 | The analysis of long distance pipeline unmanned plane inspection data and management method and system |
| CN111292327A (en) * | 2020-05-08 | 2020-06-16 | 成都派沃特科技股份有限公司 | Machine room inspection method, device, equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018141368A1 (en) * | 2017-01-31 | 2018-08-09 | Verizon Connect Ireland Limited | System and method for detecting and classifying recurrent stops of a vehicle fleet |
-
2020
- 2020-11-10 CN CN202011246109.5A patent/CN112270375B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109496288A (en) * | 2017-07-13 | 2019-03-19 | 北京嘀嘀无限科技发展有限公司 | System and method for determining track |
| CN109945877A (en) * | 2017-12-20 | 2019-06-28 | 北京中盈安信技术服务股份有限公司 | A kind of patrolled and examined track generation method and device |
| CN110414359A (en) * | 2019-07-01 | 2019-11-05 | 中国石化销售有限公司华南分公司 | The analysis of long distance pipeline unmanned plane inspection data and management method and system |
| CN111292327A (en) * | 2020-05-08 | 2020-06-16 | 成都派沃特科技股份有限公司 | Machine room inspection method, device, equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| AIS data driven general vessel destination prediction：A random forest based approach;Chengkai Zhang 等;《Transportation Research Part C》;1-19 * |
| 基于随机森林的车辆驾驶行为分析方法研究;陈东攀;;《电脑知识与技术》;第15卷(第35期);204-206 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112270375A (en) | 2021-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hao et al. | Constructing a complete landslide inventory dataset for the 2018 monsoon disaster in Kerala, India, for land use change analysis | |
| EP3327198B1 (en) | Crack analyzer, crack analysis method, and crack analysis program | |
| Hölbling et al. | An object-based approach for semi-automated landslide change detection and attribution of changes to landslide classes in northern Taiwan | |
| Ioannidis et al. | Towards a strategy for control of suburban informal buildings through automatic change detection | |
| CN112270375B (en) | Method, device, equipment and storage medium for determining trace | |
| JP6646527B2 (en) | Object detection evaluation system and object detection evaluation method | |
| US20200250424A1 (en) | Automated management of potentially hazardous objects near power lines | |
| Zhang | Detection of urban housing development by fusing multisensor satellite data and performing spatial feature post-classification | |
| US11170217B2 (en) | Method and system for prediction and mitigation of spontaneous combustion in coal stock piles | |
| Lubin et al. | Remote sensing-based mapping of the destruction to Aleppo during the Syrian Civil War between 2011 and 2017 | |
| Al-Ruzouq et al. | Infrastructure growth assessment of urban areas based on multi-temporal satellite images and linear features | |
| Yin et al. | Automation for sewer pipe assessment: CCTV video interpretation algorithm and sewer pipe video assessment (SPVA) system development | |
| CN116645616A (en) | Method for evaluating damage degree of building in natural disasters by using remote sensing images | |
| CN116363524A (en) | Monitoring and early warning method and device for highway geological disaster high-risk area | |
| Zhao et al. | Combining ICESat-2 photons and Google Earth Satellite images for building height extraction | |
| Adu-Gyamfi et al. | Functional evaluation of pavement condition using a complete vision system | |
| Schweizer et al. | Automating near real-time, post-hazard detection of crack damage to critical infrastructure | |
| Lemma et al. | Forest cover change detection in relation to climate variability and LULC changes using GIS and RS techniques. A case of the Kafa zone, southwest Ethiopia | |
| Elstohy et al. | A flash flood detected area using classification-based image processing for sentinel-2 satellites data: A case study of Zafaraana Road at Red Sea | |
| Cunningham et al. | A Platform for Proactive Risk-Based Slope Asset Management-Phase II | |
| Lopes Amaral Loures et al. | Condition assessment of unpaved roads using low-cost computer vision–based solutions | |
| Joao | Road Construction Assessment Model (RC-AM) to Prevent Contract Overbilling in Angola | |
| Chan et al. | Combined spatial point pattern analysis and remote sensing for assessing landmine affected areas | |
| CN113673632B (en) | Slope video monitoring method and device | |
| Saputra et al. | Enhanced mine road monitoring using unmanned aerial vehicles and deep-learning approach |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |