CN117541939A - Mountain area fog recognition method, system and computer equipment - Google Patents
Mountain area fog recognition method, system and computer equipment Download PDFInfo
- Publication number
- CN117541939A CN117541939A CN202410029304.4A CN202410029304A CN117541939A CN 117541939 A CN117541939 A CN 117541939A CN 202410029304 A CN202410029304 A CN 202410029304A CN 117541939 A CN117541939 A CN 117541939A
- Authority
- CN
- China
- Prior art keywords
- area
- data
- identification
- fog
- region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000007781 pre-processing Methods 0.000 claims abstract description 11
- 238000002310 reflectometry Methods 0.000 claims description 35
- 239000003595 mist Substances 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000009825 accumulation Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000012986 modification Methods 0.000 claims description 3
- 230000004048 modification Effects 0.000 claims description 3
- 238000003908 quality control method Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 4
- 238000012876 topography Methods 0.000 description 4
- 238000003491 array Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000007670 refining Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000002344 surface layer Substances 0.000 description 1
- 238000009966 trimming Methods 0.000 description 1
- 239000005436 troposphere Substances 0.000 description 1
Abstract
The invention provides a mountain area big fog recognition method, a system and computer equipment, wherein the method comprises the following steps: the method comprises the steps of obtaining multi-source data of a region to be identified, preprocessing, dividing independent identification regions according to topographic data, setting a large fog region threshold according to satellite remote sensing data to obtain a preliminary large fog region, removing a false identification region, obtaining an accurate large fog region, and finishing to obtain a final large fog region. According to the mountain area heavy fog identification method, the multi-source data of the area to be identified are preprocessed into the area image grid data to be identified with multi-dimensional information, the independent identification area is further divided, the heavy fog area threshold value is set, finally the misidentification cloud area is judged and removed through the multi-dimensional data, and then a single lattice point is refined to obtain the finally identified heavy fog area image, so that the accurate identification of the mountain area heavy fog is realized, the problem of misidentification of the cloud area is avoided, and the accuracy of the mountain area heavy fog identification is greatly improved.
Description
Technical Field
The invention relates to the field of image data processing, in particular to a mountain area fog recognition method, a mountain area fog recognition system and computer equipment.
Background
With the development of the three-dimensional traffic network in water, land and air in China, the high-risk weather phenomenon of large fog, which affects aviation and shipping and highway traffic in all directions, is also gradually focused by meteorological departments, and especially in mountain and valley terrains, due to the factors of low topography, water source confluence and the like, three necessary weather factors of generation and maintenance of the large fog, namely the large fog weather is easier to form, and the surrounding traffic lines and living areas are also easier to be affected by the large fog weather, so that the problem of how to accurately identify the large fog in the mountain area and timely send out early warning forecast is urgent to be solved.
At present, a weather department monitors the live condition of big fog mainly by using a weather observation station to observe the visibility so as to judge whether the big fog exists or not and the concentration of the big fog weather, but the weather observation station is limited by regional economic conditions and regional building conditions, so that the weather observation station is still in an insufficient quantity state in a plurality of provincial and urban areas of the country, the observation result of the observation station is greatly influenced by the low visibility caused by non-big fog reasons, the observation data of the observation station is generally used for representing the big fog condition of a county in most areas of China, the problem that the forecasting result is not accurate enough is caused, especially the big fog frequently appears in mountain and river valleys and the observation station has the characteristics of little movement and local generation and elimination, if the distance between the observation stations is far, the monitoring of the large fog is completely missed, so that the meteorological department usually carries out spatial interpolation processing on the visibility data of the observation stations, when the adjacent two stations monitor low visibility, the visibility spatial interpolation is generally processed into a piece of connected fog, but the actual situation is usually two fog areas which are not connected at all, so that the low visibility area obtained by carrying out spatial interpolation on the basis of the sparse observation stations is quite different from the actual fog area distribution, and therefore, the satellite remote sensing monitoring has the advantages of reliable information source, high spatial resolution, wide observation range, continuous monitoring and the like, and is an important research direction for improving the recognition accuracy of the large fog.
However, in the prior art, the requirement of accurately identifying the heavy fog in the mountain area still cannot be met by using satellite remote sensing to monitor the heavy fog, firstly, the identification accuracy of the existing scheme of satellite remote sensing is not high, and meanwhile, when the existing scheme is applied to monitoring the heavy fog in the mountain area, the cloud and the fog are difficult to distinguish, especially the cloud is low, the difference between the cloud and the fog on satellite remote sensing indexes is not large, the occurrence of the false identification condition is further caused, and the problem of low identification accuracy is further caused.
Disclosure of Invention
Based on the above, the invention aims to provide a mountain area heavy fog identification method, a system and computer equipment, which preprocesses multi-source data of an area to be identified into area image grid data with multi-dimensional information to be identified, then divides independent identification areas according to the area image grid data to be identified, sets a heavy fog area threshold value, realizes high-precision heavy fog area primary identification, finally judges and removes a false identification cloud area through multi-dimensional data, and carries out single lattice fine trimming on the area image grid data to be identified so as to obtain a final identified heavy fog area image, thereby realizing accurate identification of mountain area heavy fog, avoiding the problem of false identification of cloud areas and greatly improving the accuracy of mountain area heavy fog identification.
The mountain area fog recognition method provided by the invention comprises the following steps:
the method comprises the steps of obtaining multi-source data of a region to be identified, and preprocessing, wherein the multi-source data comprise ground temperature data, topographic data and satellite remote sensing data;
dividing the region to be identified into independent identification regions according to the terrain data, wherein the independent identification regions comprise mountain regions, middle regions and valley regions;
acquiring the light channel reflectivity value of the mountain area according to the satellite remote sensing data, setting a large fog area threshold according to the light channel reflectivity value of the mountain area to judge whether the light channel reflectivity value of each independent identification area is larger than the large fog area threshold, and judging the independent identification area as a preliminary large fog identification area if the light channel reflectivity value of the independent identification area is larger than the large fog area threshold;
according to the ground temperature data and the satellite remote sensing data, performing false identification region removal on the preliminary identification large fog region to obtain an accurate identification large fog region;
and finishing the precisely identified large fog area to obtain the finally identified large fog area.
In summary, according to the mountain area heavy fog recognition method, the multi-source data of the area to be recognized is preprocessed into the area image grid data to be recognized with multi-dimensional information, then the independent recognition area is divided according to the area image grid data to be recognized, the heavy fog area threshold value is set, the high-precision preliminary recognition of the heavy fog area is realized, finally the misrecognition cloud area is judged and removed through the multi-dimensional data, and the single grid point refinement is carried out on the area image grid data to be recognized, so that the finally recognized heavy fog area image is obtained, the accurate recognition of the mountain area heavy fog is realized, the problem of misrecognition of the cloud area is avoided, and the accuracy of the mountain area heavy fog recognition is greatly improved. Firstly, multi-source data including ground temperature data, topographic data and satellite remote sensing data of a region to be identified are obtained and preprocessed to obtain regional image grid data to be identified with multi-dimensional information, and independent identification areas are divided according to the topographic data to eliminate influences of non-mountain region and valley regions, and then a large fog area threshold value is set according to the satellite remote sensing data to realize preliminary identification of the large fog area, and then the ground temperature data and the satellite remote sensing data are used for comprehensively judging the large fog area and eliminating the large fog area identification influence of the cloud area to be identified by mistake, so that accurate identification of the large fog area is realized, finally, the identification precision is further improved through finishing of single grid points to obtain a final identified large fog area image, and the accuracy of large fog identification of a mountain area is greatly improved.
Further, the step of obtaining and preprocessing multi-source data of the region to be identified, wherein the multi-source data comprises ground temperature data, topographic data and satellite remote sensing data comprises the following steps:
acquiring ground temperature data, topographic data and satellite remote sensing data, wherein the ground temperature data comprises surface temperature and quality control codes, the topographic data comprises drainage basin distribution data and topographic height data, and the satellite remote sensing data comprises visible light channel data and long-wave infrared channel data;
and converting the ground temperature data, the topographic data and the satellite remote sensing data into regional image grid data to be identified with a preset spatial resolution threshold.
Further, the step of dividing the region to be identified into independent identification regions according to the topographic data, wherein the independent identification regions comprise mountain regions, middle regions and valley regions comprises the following steps:
removing a non-mountain area topographic region in a region to be identified according to topographic data, and dividing the region to be identified remaining after removing into a plurality of independent identification regions;
all grid points in the independent identification area are ordered from big to small according to the terrain height value;
dividing the grid points of the preset high-value area into mountain areas, dividing the grid points of the preset low-value area into valley areas, and dividing the rest grid points into middle areas.
Further, the step of obtaining the light channel reflectance value of the mountain area according to the satellite remote sensing data, and setting a large fog area threshold according to the light channel reflectance value of the mountain area to determine whether the light channel reflectance value of each independent identification area is greater than the large fog area threshold, and if the light channel reflectance value of the independent identification area is greater than the large fog area threshold, determining that the independent identification area is a preliminary large fog area comprises:
acquiring the light channel reflectivity values of mountain areas according to satellite remote sensing data, and sequencing the light channel reflectivity values according to the order of magnitude;
obtaining a median value of the light channel reflectivity value of the mountain area, and setting twice of the median value as a large fog area threshold;
acquiring the light channel reflectivity values of all the independent identification areas, judging whether the light channel reflectivity values of the independent identification areas are larger than or equal to the large fog area threshold, and judging that the independent identification areas are primary large fog areas if the light channel reflectivity values of the independent identification areas are larger than or equal to the large fog area threshold.
Further, the step of removing the erroneous recognition area of the preliminary recognized large fog area according to the ground temperature data and the satellite remote sensing data to obtain the accurate recognized large fog area includes:
acquiring long-wave infrared channel data for primarily identifying a large fog area according to satellite remote sensing data;
according to the ground temperature data, converting the long-wave infrared channel data into long-wave infrared channel temperature data consistent with the unit format of the ground temperature data;
acquiring temperature difference data of the preliminary identification large fog region according to the ground temperature data and the long-wave infrared channel temperature data;
acquiring the temperature difference data of the peak area in the preliminary large fog area and sequencing the temperature difference data according to the size sequence;
acquiring a median value of the temperature difference data of the mountain area, and increasing the median value by a preset temperature value to acquire a cloud boundary threshold;
judging whether the temperature difference data of the preliminary identification large fog area is larger than or equal to the cloud boundary threshold value, if the temperature difference data of the preliminary identification large fog area is larger than or equal to the cloud boundary threshold value, judging that the preliminary identification large fog area is a false identification cloud area, and if the temperature difference data of the preliminary identification large fog area is smaller than the cloud boundary threshold value, judging that the preliminary identification large fog area is an accurate identification large fog area.
Further, before the step of refining the precisely identified large fog region to obtain the finally identified large fog region, the method further includes:
and splicing all the independent identification areas back to the area to be identified so as to obtain the area to be refined.
Further, the step of refining the precisely identified heavy fog region to obtain a finally identified heavy fog region includes:
all lattice points for accurately identifying the large fog area are obtained, and adjacent lattice points of each lattice point are summed, wherein the summation formula of the adjacent lattice points is as follows:
，
wherein a represents the original lattice point to be summed, m and n represent grid values of longitude and latitude directions of the original lattice point, a represents the lattice point after summation calculation, i and j represent grid values of longitude and latitude directions of the lattice point after calculation, i1 and i2 are respectively a longitude direction accumulation start website value and a termination website value, j1 and j2 are respectively a latitude direction accumulation start website value and a termination website value, and when i=0: i1 =i, i2=i+1, when 0< i: i1 =i-1, i2=i+1, when i=i: i1 =i-1, i2=i, when j=0: j1 =j, j2=j+1, when 0< j: j1 =j-1, j2=j+1, when j=j: j1 =j-1, j2=j, where I and J are the total grid numbers in the longitudinal and latitudinal directions, respectively;
and counting the adjacent grid points obtained through calculation, judging whether the value of the adjacent grid points is smaller than or equal to a preset isolated noise point threshold value, and if the value of the adjacent grid points is smaller than or equal to the preset isolated noise point threshold value, judging the adjacent grid points as isolated noise points and eliminating the isolated noise points.
The invention provides a mountain area big fog recognition system, which comprises:
the acquisition module is used for acquiring multi-source data of the region to be identified and preprocessing the multi-source data, wherein the multi-source data comprises ground temperature data, topographic data and satellite remote sensing data;
the preliminary identification module is used for dividing the region to be identified into independent identification regions according to the topographic data, wherein the independent identification regions comprise mountain regions, middle regions and valley regions, the light channel reflectivity values of the mountain regions are obtained according to the satellite remote sensing data, the setting of a large fog region threshold value is carried out according to the light channel reflectivity values of the mountain regions, so that whether the light channel reflectivity value of each independent identification region is larger than the large fog region threshold value is judged, and if the light channel reflectivity value of the independent identification region is larger than the large fog region threshold value, the independent identification region is judged to be the preliminary large fog region;
and the accurate identification module is used for removing the false identification area of the preliminary identification large fog area according to the ground temperature data and the satellite remote sensing data so as to obtain an accurate identification large fog area, and carrying out fine modification on the accurate identification large fog area so as to obtain a final identification large fog area.
In another aspect of the present invention, there is also provided a storage medium including the storage medium storing one or more programs which when executed implement the mountain area mist identification method as described above.
Another aspect of the invention also provides a computer device comprising a memory and a processor, wherein:
the memory is used for storing a computer program;
the processor is used for realizing the mountain area fog recognition method when executing the computer program stored in the memory.
Drawings
Fig. 1 is a flowchart of a mountain area mist identification method according to a first embodiment of the present invention;
fig. 2 is a flowchart of a mountain area mist identification method according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a mountain area mist identification system according to a third embodiment of the present invention;
fig. 4 is a diagram of a complete scheme recognition result of a mountain area fog recognition method according to a second embodiment of the present invention;
fig. 5 is a partial scheme recognition result diagram of a mountain area fog recognition method according to a second embodiment of the present invention;
fig. 6 is a diagram of recognition results of a mountain area heavy fog recognition method of a national satellite meteorological center of the national meteorological office.
The invention will be further described in the following detailed description in conjunction with the above-described figures.
Detailed Description
In order that the invention may be readily understood, a more complete description of the invention will be rendered by reference to the appended drawings. Several embodiments of the invention are shown in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
It will be understood that when an element is referred to as being "mounted" on another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. The terms "vertical," "horizontal," "left," "right," and the like are used herein for illustrative purposes only.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
Referring to fig. 1, a flowchart of a mountain area mist identifying method according to a first embodiment of the present invention is shown, and the mountain area mist identifying method includes steps S01 to S05, wherein:
step S01: acquiring multi-source data of a region to be identified and preprocessing;
it should be noted that, the multisource data in this embodiment includes ground temperature data, topographic data and satellite remote sensing data, wherein the ground temperature data includes ground surface temperature observed by an observation station of a national weather department and quality control codes issued by a China weather bureau, the topographic data includes high-precision split-flow area topographic height data issued by the China weather bureau, the satellite remote sensing data includes 0.65um visible light channel data and 10.7um long wave infrared channel data acquired by an FY4a weather satellite issued by the China weather bureau, and the preprocessing in this embodiment is to uniformly process the multisource data into grid data with the same spatial resolution, and the spatial resolution precision is 500 meters.
Step S02: dividing the region to be identified into independent identification regions according to the topographic data;
in this embodiment, according to the high-precision river basin topography data, the 4-level river basin is used as an independent identification area, and the method is a method for identifying the mountain area heavy fog, so that a large-scale basin and a plain downstream of the river are not selected as independent identification areas, the non-mountain area river valley topography areas are removed, all grid points of grid data in each independent identification area are sorted according to the topography height value, the grid point area with 20% of the height value is divided into peak areas, the grid point area with 20% of the height value is divided into valley areas, and the rest grid point areas are divided into middle areas.
Step S03: setting a large fog region threshold according to the satellite remote sensing data so as to judge whether the light channel reflectivity value of each independent identification region is larger than the large fog region threshold or not, thereby primarily identifying the large fog region;
it should be noted that, the large fog area threshold in this embodiment is set according to the 0.65um visible light channel data of the peak area grid point, because the three visible light channels of the FY4a weather satellite data are respectively 0.47um, 0.65um and 0.825um, but in terms of resolution accuracy, the resolution accuracy of the visible light channels of 0.47um and 0.825um is only 1km of grid resolution, while the resolution accuracy of the visible light channels of 0.65um is only 0.5km of grid resolution, and the reflectance difference of the visible light channels of 0.65um is obvious for the fog area and the non-fog area, the boundary of the cloud area can be clearly resolved under the condition of preliminary identification, so as to obtain the identified large fog area image of the peak area with higher identification accuracy and identification accuracy, and the large fog area threshold in this embodiment is set to 2 times the number of the reflection bits of the visible light channels of 0.65um of the peak area grid point.
Step S04: according to the ground temperature data and the satellite remote sensing data, performing false identification region removal on the preliminary identification large fog region to obtain an accurate identification large fog region;
it should be noted that, in the embodiment, the satellite remote sensing data used in step S04 is 10.7um long wave infrared channel data, cloud and fog boundary threshold is set according to the temperature difference data of the ground temperature data and the 10.7um long wave infrared channel data, in the embodiment, the cloud and fog boundary threshold is set to +2deg.C of the median of the temperature difference data of the grid points of the mountain area, and then, based on the rule that the temperature drops by 0.6 ℃ every 100m in the troposphere (under the average 10-12km height in the mid-latitude area), the misidentification cloud area with the near-fog surface layer of 300m or more can be realized.
Step S05: finishing the precisely identified large fog region to obtain a finally identified large fog region;
it should be noted that, in this embodiment, before finishing, all the independent identification areas need to be spliced back to the image of the area to be identified, and then summing statistics is performed on each lattice point and adjacent lattice points, where the sum formula of adjacent points is:
，
wherein a represents the original lattice point to be summed, m and n represent grid values of longitude and latitude directions of the original lattice point, a represents the lattice point after summation calculation, i and j represent grid values of longitude and latitude directions of the lattice point after calculation, i1 and i2 are respectively a longitude direction accumulation start website value and a termination website value, j1 and j2 are respectively a latitude direction accumulation start website value and a termination website value, and when i=0: i1 =i, i2=i+1, when 0< i: i1 =i-1, i2=i+1, when i=i: i1 =i-1, i2=i, when j=0: j1 =j, j2=j+1, when 0< j: j1 =j-1, j2=j+1, when j=j: j1 The method includes the steps of (1) marking grid points identified as fog as 1 and non-fog as 0 to obtain grid point value data with 0 or 1, counting the grid point value data obtained through calculation, judging whether the value of adjacent grid points is smaller than or equal to a preset isolated noise threshold value or not, wherein the preset isolated noise threshold value is 3 in the embodiment, and judging the grid points smaller than or equal to the preset isolated noise threshold value as isolated noise points and eliminating the isolated noise points.
In summary, according to the mountain area heavy fog recognition method, the multi-source data of the area to be recognized is preprocessed into the area image grid data to be recognized with multi-dimensional information, then the independent recognition area is divided according to the area image grid data to be recognized, the heavy fog area threshold value is set, the high-precision preliminary recognition of the heavy fog area is realized, finally the misrecognition cloud area is judged and removed through the multi-dimensional data, and the single grid point refinement is carried out on the area image grid data to be recognized, so that the finally recognized heavy fog area image is obtained, the accurate recognition of the mountain area heavy fog is realized, the problem of misrecognition of the cloud area is avoided, and the accuracy of the mountain area heavy fog recognition is greatly improved. Firstly, multi-source data including ground temperature data, topographic data and satellite remote sensing data of a region to be identified are obtained and preprocessed to obtain regional image grid data to be identified with multi-dimensional information, and independent identification areas are divided according to the topographic data to eliminate influences of non-mountain region and valley regions, and then a large fog area threshold value is set according to the satellite remote sensing data to realize preliminary identification of the large fog area, and then the ground temperature data and the satellite remote sensing data are used for comprehensively judging the large fog area and eliminating the large fog area identification influence of the cloud area to be identified by mistake, so that accurate identification of the large fog area is realized, finally, the identification precision is further improved through finishing of single grid points to obtain a final identified large fog area image, and the accuracy of large fog identification of a mountain area is greatly improved.
Referring to fig. 2, a flowchart of a mountain area mist identifying method according to a second embodiment of the present invention is shown, and the mountain area mist identifying method includes steps S11 to S19, wherein:
step S11: acquiring ground temperature data, topographic data and satellite remote sensing data and converting the data into regional image grid data to be identified of a preset spatial resolution threshold value;
step S12: removing the non-mountain area topographic region in the region to be identified according to the topographic data, and dividing the region to be identified remaining after removing into a plurality of independent identification regions;
step S13: all grid points in the independent identification area are ordered according to the terrain height values from large to small, grid points in a preset high-value area are divided into mountain areas, grid points in a preset low-value area are divided into valley areas, and the rest grid points are divided into middle areas;
step S14: acquiring the light channel reflectivity value of a mountain area according to satellite remote sensing data, sequencing the light channel reflectivity values according to the order of magnitude, acquiring the median value of the light channel reflectivity value of the mountain area, and setting twice of the median value as a large fog area threshold;
step S15: acquiring the light channel reflectivity values of all the independent identification areas, judging whether the light channel reflectivity values of the independent identification areas are larger than or equal to a large fog area threshold value, and judging the independent identification areas as preliminary large fog area identification if the light channel reflectivity values of the independent identification areas are larger than or equal to the large fog area threshold value;
step S16: acquiring long-wave infrared channel data of a preliminary large fog area according to satellite remote sensing data, converting the long-wave infrared channel data into long-wave infrared channel temperature data consistent with a unit format of the ground temperature data according to the ground temperature data, and acquiring temperature difference data of the preliminary large fog area according to the ground temperature data and the long-wave infrared channel temperature data;
step S17: acquiring temperature difference data of a peak area in a preliminary identification large fog area, sequencing the temperature difference data according to a size sequence, acquiring a median value of the temperature difference data of the peak area, and increasing the median value by a preset temperature value to acquire a cloud and fog boundary threshold;
step S18: judging whether the temperature difference data of the preliminary large fog identification area is larger than or equal to a cloud boundary threshold value, if the temperature difference data of the preliminary large fog identification area is larger than or equal to the cloud boundary threshold value, judging the preliminary large fog identification area as a false large fog identification area, and if the temperature difference data of the preliminary large fog identification area is smaller than the cloud boundary threshold value, judging the preliminary large fog identification area as an accurate large fog identification area;
step S19: splicing all the independent identification areas back to the area to be identified so as to obtain the area to be refined, obtaining all the grid points for accurately identifying the large fog area, summing the adjacent grid points of each grid point, counting the adjacent grid points obtained through calculation, judging whether the value of the adjacent grid points is smaller than or equal to a preset isolated noise threshold value, and if the value of the adjacent grid points is smaller than or equal to the preset isolated noise threshold value, judging the adjacent grid points as isolated noise points and eliminating the isolated noise points;
in this embodiment, mountain areas in the river and west range are selected as the identification targets of the areas to be identified, and compared with the mountain area fog identification results of the national satellite meteorological center of the China meteorological office, and the comparison results are shown in the following table 1:
TABLE 1
As can be seen from the table, the accuracy of the complete identification scheme (i.e. the finish identification in the table) is up to 98.3%, compared with the accuracy of the national satellite meteorological center (i.e. the satellite center in the table) of the China meteorological bureau, which is 46.6%, the accuracy is doubled, which is higher than the accuracy by 69.4%, the false alarm rate is only 1.9%, which is far lower than the satellite center, even if the partial scheme of the complete identification scheme is that the preliminary identification in the step is that the unfinished identification in the table is that the current mountain area fog identification scheme is far ahead of the national satellite meteorological center of the China authoritative meteorological unit, referring to FIGS. 4, 5 and 6, the complete scheme and the partial scheme of the complete identification scheme can be intuitively seen compared with the mountain area fog identification area image acquired by the satellite center, which has obvious progress, and the identification accuracy of the mountain area fog area can be greatly improved.
In summary, according to the mountain area heavy fog recognition method, the multi-source data of the area to be recognized is preprocessed into the area image grid data to be recognized with multi-dimensional information, then the independent recognition area is divided according to the area image grid data to be recognized, the heavy fog area threshold value is set, the high-precision preliminary recognition of the heavy fog area is realized, finally the misrecognition cloud area is judged and removed through the multi-dimensional data, and the single grid point refinement is carried out on the area image grid data to be recognized, so that the finally recognized heavy fog area image is obtained, the accurate recognition of the mountain area heavy fog is realized, the problem of misrecognition of the cloud area is avoided, and the accuracy of the mountain area heavy fog recognition is greatly improved. Firstly, multi-source data including ground temperature data, topographic data and satellite remote sensing data of a region to be identified are obtained and preprocessed to obtain regional image grid data to be identified with multi-dimensional information, and independent identification areas are divided according to the topographic data to eliminate influences of non-mountain region and valley regions, and then a large fog area threshold value is set according to the satellite remote sensing data to realize preliminary identification of the large fog area, and then the ground temperature data and the satellite remote sensing data are used for comprehensively judging the large fog area and eliminating the large fog area identification influence of the cloud area to be identified by mistake, so that accurate identification of the large fog area is realized, finally, the identification precision is further improved through finishing of single grid points to obtain a final identified large fog area image, and the accuracy of large fog identification of a mountain area is greatly improved.
Referring to fig. 3, a schematic structural diagram of a mountain area mist identifying system according to a third embodiment of the present invention is shown, the system includes:
the acquisition module 10 is used for acquiring and preprocessing multi-source data of a region to be identified, wherein the multi-source data comprises ground temperature data, topographic data and satellite remote sensing data;
the preliminary identification module 20 is configured to divide the region to be identified according to the topographic data, where the independent identification region includes a peak region, a middle region, and a valley region, obtain, according to the satellite remote sensing data, an optical channel reflectance value of the peak region, and set a large fog region threshold according to the optical channel reflectance value of the peak region, so as to determine whether the optical channel reflectance value of each independent identification region is greater than the large fog region threshold, and if the optical channel reflectance value of the independent identification region is greater than the large fog region threshold, determine that the independent identification region is a preliminary large fog region;
and the precise identification module 30 is configured to perform erroneous identification region removal on the preliminary identification large fog region according to the ground temperature data and the satellite remote sensing data so as to obtain a precise identification large fog region, and perform fine repair on the precise identification large fog region so as to obtain a final identification large fog region.
Further, the acquisition module 10 includes:
the multi-source data acquisition unit 101 is configured to acquire multi-source data of a region to be identified and perform preprocessing, where the multi-source data includes ground temperature data, topographic data and satellite remote sensing data.
Further, the preliminary identification module 20 includes:
an independent identification region dividing unit 201, configured to divide the region to be identified into independent identification regions according to the topographic data, where the independent identification regions include a mountain region, a middle region, and a valley region;
the preliminary large fog region identification unit 202 is configured to obtain the light channel reflectance value of the mountain region according to the satellite remote sensing data, and set a large fog region threshold according to the light channel reflectance value of the mountain region, so as to determine whether the light channel reflectance value of each independent identification region is greater than the large fog region threshold, and if the light channel reflectance value of the independent identification region is greater than the large fog region threshold, determine that the independent identification region is a preliminary large fog region.
Further, the precise recognition module 30 includes:
the precise large fog region identification unit 301 is configured to perform, according to the ground temperature data and the satellite remote sensing data, false identification region removal on the preliminary large fog region identification to obtain a precise large fog region identification;
and the finishing unit 302 is configured to finish the precisely identified heavy fog region to obtain a finally identified heavy fog region.
In another aspect, the present invention also provides a computer storage medium having one or more programs stored thereon, which when executed by a processor, implement the above-described mountain area mist identification method.
The invention also provides computer equipment, which comprises a memory and a processor, wherein the memory is used for storing computer programs, and the processor is used for executing the computer programs stored on the memory so as to realize the mountain area fog recognition method.
Those of skill in the art will appreciate that the logic and/or steps represented in the flow diagrams or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain or store the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing examples illustrate only a few embodiments of the invention and are described in detail herein without thereby limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (10)
1. A mountain area haze recognition method, comprising:
the method comprises the steps of obtaining multi-source data of a region to be identified, and preprocessing, wherein the multi-source data comprise ground temperature data, topographic data and satellite remote sensing data;
dividing the region to be identified into independent identification regions according to the terrain data, wherein the independent identification regions comprise mountain regions, middle regions and valley regions;
acquiring the light channel reflectivity value of the mountain area according to the satellite remote sensing data, setting a large fog area threshold according to the light channel reflectivity value of the mountain area to judge whether the light channel reflectivity value of each independent identification area is larger than the large fog area threshold, and judging the independent identification area as a preliminary large fog identification area if the light channel reflectivity value of the independent identification area is larger than the large fog area threshold;
according to the ground temperature data and the satellite remote sensing data, performing false identification region removal on the preliminary identification large fog region to obtain an accurate identification large fog region;
and finishing the precisely identified large fog area to obtain the finally identified large fog area.
2. The mountain range haze recognition method according to claim 1, wherein the step of acquiring and preprocessing multi-source data of the region to be recognized, the multi-source data including ground temperature data, topographic data, and satellite remote sensing data, comprises:
acquiring ground temperature data, topographic data and satellite remote sensing data, wherein the ground temperature data comprises surface temperature and quality control codes, the topographic data comprises drainage basin distribution data and topographic height data, and the satellite remote sensing data comprises visible light channel data and long-wave infrared channel data;
and converting the ground temperature data, the topographic data and the satellite remote sensing data into regional image grid data to be identified with a preset spatial resolution threshold.
3. The mountain area mist identification method according to claim 1, characterized in that the step of dividing the area to be identified into independent identification areas including a mountain area, a middle area and a valley area according to the topographic data comprises:
removing a non-mountain area topographic region in a region to be identified according to topographic data, and dividing the region to be identified remaining after removing into a plurality of independent identification regions;
all grid points in the independent identification area are ordered from big to small according to the terrain height value;
dividing the grid points of the preset high-value area into mountain areas, dividing the grid points of the preset low-value area into valley areas, and dividing the rest grid points into middle areas.
4. The mountain area heavy fog recognition method according to claim 1, wherein the steps of obtaining the light channel reflectance value of the mountain area according to the satellite remote sensing data, setting a heavy fog area threshold according to the light channel reflectance value of the mountain area, and judging whether the light channel reflectance value of each independent recognition area is greater than the heavy fog area threshold, if the light channel reflectance value of the independent recognition area is greater than the heavy fog area threshold, judging that the independent recognition area is a preliminary recognition heavy fog area comprise:
acquiring the light channel reflectivity values of mountain areas according to satellite remote sensing data, and sequencing the light channel reflectivity values according to the order of magnitude;
obtaining a median value of the light channel reflectivity value of the mountain area, and setting twice of the median value as a large fog area threshold;
acquiring the light channel reflectivity values of all the independent identification areas, judging whether the light channel reflectivity values of the independent identification areas are larger than or equal to the large fog area threshold, and judging that the independent identification areas are primary large fog areas if the light channel reflectivity values of the independent identification areas are larger than or equal to the large fog area threshold.
5. The mountain area mist identification method according to claim 1, wherein the step of performing erroneous identification area removal on the preliminary identification mist area according to the ground temperature data and the satellite remote sensing data to obtain an accurate identification mist area includes:
acquiring long-wave infrared channel data for primarily identifying a large fog area according to satellite remote sensing data;
according to the ground temperature data, converting the long-wave infrared channel data into long-wave infrared channel temperature data consistent with the unit format of the ground temperature data;
acquiring temperature difference data of the preliminary identification large fog region according to the ground temperature data and the long-wave infrared channel temperature data;
acquiring the temperature difference data of the peak area in the preliminary large fog area and sequencing the temperature difference data according to the size sequence;
acquiring a median value of the temperature difference data of the mountain area, and increasing the median value by a preset temperature value to acquire a cloud boundary threshold;
judging whether the temperature difference data of the preliminary identification large fog area is larger than or equal to the cloud boundary threshold value, if the temperature difference data of the preliminary identification large fog area is larger than or equal to the cloud boundary threshold value, judging that the preliminary identification large fog area is a false identification cloud area, and if the temperature difference data of the preliminary identification large fog area is smaller than the cloud boundary threshold value, judging that the preliminary identification large fog area is an accurate identification large fog area.
6. The mountain area mist identification method as set forth in claim 1, wherein the step of finishing the precisely identified mist area to obtain a final identified mist area further includes, prior to:
and splicing all the independent identification areas back to the area to be identified so as to obtain the area to be refined.
7. The mountain range heavy fog recognition method as recited in claim 1, wherein the step of finishing the precisely recognized heavy fog region to obtain a final recognized heavy fog region includes:
all lattice points for accurately identifying the large fog area are obtained, and adjacent lattice points of each lattice point are summed, wherein the summation formula of the adjacent lattice points is as follows:
，
wherein a represents the original lattice point to be summed, m and n represent grid values of longitude and latitude directions of the original lattice point, a represents the lattice point after summation calculation, i and j represent grid values of longitude and latitude directions of the lattice point after calculation, i1 and i2 are respectively a longitude direction accumulation start website value and a termination website value, j1 and j2 are respectively a latitude direction accumulation start website value and a termination website value, and when i=0: i1 =i, i2=i+1, when 0< i: i1 =i-1, i2=i+1, when i=i: i1 =i-1, i2=i, when j=0: j1 =j, j2=j+1, when 0< j: j1 =j-1, j2=j+1, when j=j: j1 =j-1, j2=j, where I and J are the total grid numbers in the longitudinal and latitudinal directions, respectively;
and counting the adjacent grid points obtained through calculation, judging whether the value of the adjacent grid points is smaller than or equal to a preset isolated noise point threshold value, and if the value of the adjacent grid points is smaller than or equal to the preset isolated noise point threshold value, judging the adjacent grid points as isolated noise points and eliminating the isolated noise points.
8. A mountain area mist identification system, comprising:
the acquisition module is used for acquiring multi-source data of the region to be identified and preprocessing the multi-source data, wherein the multi-source data comprises ground temperature data, topographic data and satellite remote sensing data;
the preliminary identification module is used for dividing the region to be identified into independent identification regions according to the topographic data, wherein the independent identification regions comprise mountain regions, middle regions and valley regions, the light channel reflectivity values of the mountain regions are obtained according to the satellite remote sensing data, the setting of a large fog region threshold value is carried out according to the light channel reflectivity values of the mountain regions, so that whether the light channel reflectivity value of each independent identification region is larger than the large fog region threshold value is judged, and if the light channel reflectivity value of the independent identification region is larger than the large fog region threshold value, the independent identification region is judged to be the preliminary large fog region;
and the accurate identification module is used for removing the false identification area of the preliminary identification large fog area according to the ground temperature data and the satellite remote sensing data so as to obtain an accurate identification large fog area, and carrying out fine modification on the accurate identification large fog area so as to obtain a final identification large fog area.
9. A storage medium, comprising: the storage medium stores one or more programs which, when executed by a processor, implement the mountain area mist identification method as set forth in any one of claims 1-7.
10. A computer device comprising a memory and a processor, wherein:
the memory is used for storing a computer program;
the processor is configured to implement the mountain area mist identification method of any one of claims 1 to 7 when executing the computer program stored in the memory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410029304.4A CN117541939B (en) | 2024-01-09 | Mountain area fog recognition method, system and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410029304.4A CN117541939B (en) | 2024-01-09 | Mountain area fog recognition method, system and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117541939A true CN117541939A (en) | 2024-02-09 |
| CN117541939B CN117541939B (en) | 2024-04-26 |
Family
ID=
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103293084A (en) * | 2013-05-08 | 2013-09-11 | 南京大学 | Sea fog all-time all-weather inversion method based on multispectral weather satellite information |
| US20170248969A1 (en) * | 2016-02-29 | 2017-08-31 | Thinkware Corporation | Method and system for providing route of unmanned air vehicle |
| CN107272007A (en) * | 2012-09-20 | 2017-10-20 | 伟摩有限责任公司 | Detect the method and system of highway weather conditions |
| CN112287881A (en) * | 2020-11-19 | 2021-01-29 | 国网湖南省电力有限公司 | Satellite remote sensing image smoke scene detection method and system and computer storage medium |
| CN114758253A (en) * | 2022-04-15 | 2022-07-15 | 国家卫星气象中心(国家空间天气监测预警中心) | Haze identification method combining satellite remote sensing multispectral information and geographic information |
| CN116482644A (en) * | 2023-06-25 | 2023-07-25 | 成都远望科技有限责任公司 | Sea fog identification method |
| CN116609859A (en) * | 2023-05-30 | 2023-08-18 | 航天宏图信息技术股份有限公司 | Weather disaster high-resolution regional mode forecasting system and method |
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107272007A (en) * | 2012-09-20 | 2017-10-20 | 伟摩有限责任公司 | Detect the method and system of highway weather conditions |
| CN103293084A (en) * | 2013-05-08 | 2013-09-11 | 南京大学 | Sea fog all-time all-weather inversion method based on multispectral weather satellite information |
| US20170248969A1 (en) * | 2016-02-29 | 2017-08-31 | Thinkware Corporation | Method and system for providing route of unmanned air vehicle |
| CN112287881A (en) * | 2020-11-19 | 2021-01-29 | 国网湖南省电力有限公司 | Satellite remote sensing image smoke scene detection method and system and computer storage medium |
| CN114758253A (en) * | 2022-04-15 | 2022-07-15 | 国家卫星气象中心(国家空间天气监测预警中心) | Haze identification method combining satellite remote sensing multispectral information and geographic information |
| CN116609859A (en) * | 2023-05-30 | 2023-08-18 | 航天宏图信息技术股份有限公司 | Weather disaster high-resolution regional mode forecasting system and method |
| CN116482644A (en) * | 2023-06-25 | 2023-07-25 | 成都远望科技有限责任公司 | Sea fog identification method |
Non-Patent Citations (1)
| Title |
|---|
| 周红妹;汤绪;葛伟强;刘冬;柏桦;杨引明;: "城市和沿海大雾遥感自动检测和云、雾分离技术研究", 高原气象, no. 03, 15 June 2011 (2011-06-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109738970B (en) | Method, device and storage medium for realizing lightning early warning based on lightning data mining | |
| CN104899437B (en) | Heavy rainfall type landslide disaster method for early warning | |
| CN112070286B (en) | Precipitation forecast and early warning system for complex terrain river basin | |
| Kim et al. | 3D classification of power-line scene from airborne laser scanning data using random forests | |
| KR101258668B1 (en) | Korea local radar processing system | |
| Lakshmanan et al. | Data mining storm attributes from spatial grids | |
| CN111623722A (en) | Multi-sensor-based slope deformation three-dimensional monitoring system and method | |
| CN111062368B (en) | City update region monitoring method based on Landsat time sequence remote sensing image | |
| CN109407177B (en) | Machine learning and conventional meteorological observation-based fog identification system and application method | |
| CN107657618B (en) | Automatic extraction method of regional scale erosion gully based on remote sensing image and topographic data | |
| CN108562885B (en) | High-voltage transmission line airborne LiDAR point cloud extraction method | |
| CN115331190B (en) | Road hidden danger identification method and device based on radar vision fusion | |
| CN107958312B (en) | Electric transmission line galloping prediction method and system based on inversion algorithm and storage medium | |
| CN115423272B (en) | Flood risk assessment method and system integrating historical flooding strength | |
| Luo et al. | Terrace extraction based on remote sensing images and digital elevation model in the loess plateau, China | |
| KR101221793B1 (en) | Method for tracking reflectivity cells associated with severe weather | |
| CN114518612A (en) | Thunderstorm risk early warning method and system and electronic equipment | |
| CN115792918A (en) | Method for identifying aviation convection risk area based on multi-source data fusion batching method | |
| KR101221755B1 (en) | Method for identifying reflectivity cells associated with severe weather | |
| CN105701856B (en) | A kind of vegetation extracting method and system | |
| CN117541939B (en) | Mountain area fog recognition method, system and computer equipment | |
| CN117541939A (en) | Mountain area fog recognition method, system and computer equipment | |
| Keller et al. | CEH-GEAR: 1 km resolution daily and monthly areal rainfall estimates for the UK for hydrological use | |
| CN115358507A (en) | Production and construction project disturbance pattern spot water and soil loss risk identification and evaluation method | |
| CN113850822B (en) | Automatic slope unit dividing method based on confluence division |
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 |