CN118334525B - Modern marine pasture site selection reliability assessment method based on decision tree model - Google Patents
Modern marine pasture site selection reliability assessment method based on decision tree model Download PDFInfo
- Publication number
- CN118334525B CN118334525B CN202410725837.6A CN202410725837A CN118334525B CN 118334525 B CN118334525 B CN 118334525B CN 202410725837 A CN202410725837 A CN 202410725837A CN 118334525 B CN118334525 B CN 118334525B
- Authority
- CN
- China
- Prior art keywords
- sub
- boundary
- decision tree
- image
- water color
- 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
- 238000003066 decision tree Methods 0.000 title claims abstract description 96
- 238000000034 method Methods 0.000 title claims abstract description 48
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 126
- 238000012549 training Methods 0.000 claims abstract description 47
- 238000009304 pastoral farming Methods 0.000 claims abstract description 33
- 238000012937 correction Methods 0.000 claims abstract description 23
- 238000007781 pre-processing Methods 0.000 claims abstract description 13
- ATNHDLDRLWWWCB-AENOIHSZSA-M chlorophyll a Chemical compound C1([C@@H](C(=O)OC)C(=O)C2=C3C)=C2N2C3=CC(C(CC)=C3C)=[N+]4C3=CC3=C(C=C)C(C)=C5N3[Mg-2]42[N+]2=C1[C@@H](CCC(=O)OC\C=C(/C)CCC[C@H](C)CCC[C@H](C)CCCC(C)C)[C@H](C)C2=C5 ATNHDLDRLWWWCB-AENOIHSZSA-M 0.000 claims description 65
- 229930002875 chlorophyll Natural products 0.000 claims description 61
- 235000019804 chlorophyll Nutrition 0.000 claims description 61
- 238000012795 verification Methods 0.000 claims description 17
- 238000012216 screening Methods 0.000 claims description 8
- 238000003708 edge detection Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 3
- 238000010200 validation analysis Methods 0.000 claims 1
- 238000012545 processing Methods 0.000 abstract description 4
- 238000004590 computer program Methods 0.000 description 7
- 241000195493 Cryptophyta Species 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 206010013496 Disturbance in attention Diseases 0.000 description 3
- 241001420622 Meris Species 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 229930002868 chlorophyll a Natural products 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000009792 diffusion process Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 241000238557 Decapoda Species 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000009313 farming Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 235000013311 vegetables Nutrition 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/182—Network patterns, e.g. roads or rivers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/248—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/147—Details of sensors, e.g. sensor lenses
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/36—Applying a local operator, i.e. means to operate on image points situated in the vicinity of a given point; Non-linear local filtering operations, e.g. median filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Computing Systems (AREA)
- Tourism & Hospitality (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mining & Mineral Resources (AREA)
- Evolutionary Computation (AREA)
- Strategic Management (AREA)
- Marine Sciences & Fisheries (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Animal Husbandry (AREA)
- Nonlinear Science (AREA)
- Vascular Medicine (AREA)
- Agronomy & Crop Science (AREA)
- Remote Sensing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a decision tree model-based modern marine ranching site selection reliability assessment method, which comprises the steps of obtaining a water color remote sensing image of a sea area to be assessed in a historical time period; marking a plurality of regions of interest in the water color remote sensing image and preprocessing to extract sub-images of the regions of interest; carrying out boundary correction operation on each sub-image to obtain a boundary correction sub-image; training the decision tree model through the corrected boundary sub-images in all the water color remote sensing images to obtain a pre-trained decision tree model; and identifying whether the marine ranching site selection area in the sea area to be evaluated is a marine ranching site selection area with high reliability by utilizing a pre-trained decision tree model. The remote sensing image boundary is corrected, so that the boundary of the marine pasture avoids the potential risks, the recognition accuracy, rationality and reliability of the subsequent decision tree model on the marine pasture position are improved, and the method is applied to the technical field of geographic information data processing.
Description
Technical Field
The invention relates to the technical field of geographic information data processing, in particular to a modern marine pasture site selection reliability assessment method based on a decision tree model.
Background
The ocean pasture is generally constructed by adopting artificial reefs made of concrete or artificial reefs and algal farms constructed by utilizing natural conditions such as reefs and reefs in deep open sea, and the existing site selection method is applied to the ocean pasture with low reliability because the site selection position of the ocean pasture is influenced by biological environments such as weather, hydrology, geography, dark current, algae, aquatic organisms and the like in the deep open sea greatly different from the land because the site selection position of the ocean pasture is directly influenced by the biological environments and the production efficiency is directly influenced by the site selection position because of the large environmental difference between the deep open sea and the land.
Disclosure of Invention
The invention aims to provide a modern marine ranching site selection reliability assessment method based on a decision tree model, so as to solve one or more technical problems in the prior art and at least provide a beneficial selection or creation condition.
To achieve the above object, according to an aspect of the present invention, there is provided a modern marine ranch site selection reliability assessment method based on a decision tree model, the method comprising the steps of:
s100, acquiring a water color remote sensing image of a sea area to be evaluated in a historical time period;
s200, marking a plurality of regions of interest in the water color remote sensing image and preprocessing to extract sub-images of the regions of interest;
s300, carrying out boundary correction operation on each sub-image to obtain a boundary correction sub-image;
S400, training the decision tree model through corrected boundary sub-images in all the water color remote sensing images to obtain a pre-trained decision tree model;
S500, identifying whether the marine ranching site selection area in the sea area to be evaluated is a marine ranching site selection area with high reliability by utilizing a pre-trained decision tree model.
Further, the method further comprises the following steps: and S600, outputting the site selection place of the corresponding position of the marine pasture site selection area with high reliability to a corresponding GIS map to be displayed on a client or to be stored in a database.
Further, in S100, the history period is a selected history period of 5 to 40 days.
Wherein, the remote sensing image of water color is used for selecting the chlorophyll a concentration in the water color dataThe remote sensing image product is used as a water color remote sensing image.
Wherein the water color remote sensing image passes through a MERIS water color sensor, a medium resolution imaging spectrometer and/or a MODIS medium resolution imaging spectrometerAnd (5) image acquisition.
Further, in S200, the method for marking a plurality of regions of interest in a water color remote sensing image and preprocessing to extract sub-images of the regions of interest includes the steps of: marking a plurality of regions of interest in a water-color remote sensing image in the water-color remote sensing image; performing bottom hat transformation on each region of interest, and extracting an image of the region of interest by threshold segmentation to obtain sub-images;
and inverting the water color remote sensing image to obtain chlorophyll content distribution of the water color remote sensing image.
Even though the transformation of the water color (chlorophyll a concentration) of the water color remote sensing image between the boundaries of each sub-image in the marine pasture is influenced by concentration differences of algae and water living things, the large differences of factors such as dark current, wave height, ocean current and the like among the sub-images can cause the final site selection of the marine pasture to be unreliable, so that the yield after the marine pasture is selected at the corresponding position can quickly change due to the chlorophyll concentration loss passage formed at the edge position by the factors, and finally the yield of the marine pasture is lower than expected.
Further, in S300, the method for obtaining the corrected boundary sub-image by performing the corrected boundary operation on each sub-image includes the following steps:
graying is carried out on each sub-image to obtain a gray sub-image;
Calculating the water color channel degree of each gray sub-image;
Screening gray sub-images with the water color channel degree smaller than the average water color channel degree of all gray sub-images as boundary sub-images to be corrected;
And carrying out boundary correction operation on the boundary sub-image to be corrected to obtain a corrected boundary sub-image.
Whether the chlorophyll forms a concentration loss channel in a local range on the boundary of the sub-image can be accurately reflected by calculating the degree of the water color channel, whether the whole sub-image affects the balance of the chlorophyll in the ocean site selection area is judged by the change of the size of the concentration loss channel, if the degree of the water color channel is larger, the boundary expansion or reduction is further needed, so that the area with obvious concentration flow direction of the chlorophyll on the boundary is reduced, the boundary position is redetermined, and the reliability and the accuracy on the boundary of the ocean site selection are ensured.
Further, the method for calculating the water color channel degree of each gray sub-image comprises the following steps:
Let the set of gray sub-images be areas= { Areas i }, regard i as the serial number of gray sub-images, i e [1, N ], N is the number of gray sub-images; area i is the ith gray scale sub-image; edge detection is carried out on the Areas i, and the Areas i are divided into a plurality of water color flow direction Areas by all edge lines obtained through detection;
The local limit chlorophyll PEAKGREEN i is the average chlorophyll content value with the largest average chlorophyll content value in each of the water color flow Areas of Areas i, and the average value of the average chlorophyll content values in all of the water color flow Areas of Areas i is QMEANGREEN i;
All water color flow direction areas with average chlorophyll content greater than or equal to PEAKGREEN i in the respective water color flow direction areas in all gray level sub-images form a set all i, and the average value of the average chlorophyll content values in all water color flow direction areas in the set all i is HMEANGREEN i;
The water color channel degree Tunnel i of the gray sub-image Areas i is calculated as follows:
Tunneli=PeakGreeni/(QMeanGreeni+HMeanGreeni)。
The calculated water color channel degree is a trend intensity value of a water color flow direction region which possibly forms a chlorophyll diffusion channel towards the periphery in the chlorophyll content, and is an index of whether the boundary of a gray sub-image in the whole water color remote sensing image is balanced or not.
Further, the method for obtaining the corrected boundary sub-image by carrying out the boundary correction operation on the boundary sub-image to be corrected comprises the following steps:
Forming a set EdgeStre = { EdgeStre j},EdgeStrej of the boundary sub-images to be corrected with the serial number j in EdgeStre according to the size sequence of the water color channel degree of the boundary sub-images to be corrected; performing edge detection on EdgeStre j, and dividing EdgeStre j into a plurality of water color flow direction areas by using each detected edge line;
Starting from j=2, sequentially carrying out boundary correction operation on EdgeStre j in the value range of j, wherein the specific method comprises the following steps:
recording CycMaxP as the center of inscribed circle of the water color flow direction region with the largest chlorophyll content in each water color flow direction region in EdgeStre j; the inscribed circle center of the water color flow direction area with the minimum chlorophyll content in each water color flow direction area in EdgeStre j is CycMinP; the water color flow direction is the direction from CycMaxP to CycMinP;
EdgeMaxP j is the point on the boundary line of EdgeStre j where the chlorophyll content is the greatest; edgeMinP j is the point on the boundary line of EdgeStre j where the chlorophyll content is minimum; the boundary to be corrected is marked by a curve between the water color flow directions from EdgeMaxP j to EdgeMinP j on the boundary line of EdgeStre j;
Searching all to-be-corrected boundary sub-images with the serial numbers smaller than j, and marking the to-be-corrected boundary sub-image with the minimum difference between the chlorophyll content of the point with the largest chlorophyll content on the boundary line and the chlorophyll content of the point with the largest chlorophyll content on the boundary line of EdgeStre j as a stable boundary sub-image EdgeStable;
StabMaxP is the point on the boundary line of EdgeStable where the chlorophyll content is the greatest; stabMinP is the point on the boundary line of EdgeStable where the chlorophyll content is minimum; the corrected boundary curve FixLine is marked by the curve between the water color flow directions from StabMaxP to StabMinP on the boundary line of EdgeStable;
Deleting the boundary to be corrected on the boundary line EdgeStre j, marking the point EdgeMaxP j on the boundary line EdgeStre j as an end point A, marking the point EdgeMinP j on the boundary line EdgeStre j as an end point B,
The StabMaxP point of the copied corrected boundary curve FixLine is marked as the C endpoint, and the StabMinP point of the copied corrected boundary curve is marked as the D endpoint;
scaling curve FixLine equally to the distance between the C and D endpoints and the distance between the a and B endpoints is noted as curve UpFixLine;
moving the curve UpFixLine as a whole to reconstruct the modified boundary EdgeStre j with the C-endpoint coincident with the a-endpoint and the D-endpoint coincident with the B-endpoint;
And taking the boundary sub-image to be corrected of the corrected boundary EdgeStre j as a corrected boundary sub-image.
The beneficial effects are as follows: the boundary to be corrected is the region boundary with the most abnormal chlorophyll flow rate, if the boundary to be corrected exists on the site selection boundary of the marine pasture, the problem that the water color flow direction is abnormal due to factors such as weather, heat flow, algae, aquatic organisms, dark current, wave height, ocean current and the like possibly exists on the boundary, the abnormal chlorophyll flow direction directly means that the abnormal factors exist in the sea area, unstable factors can appear on the marine pasture, and the fish and shrimp farming industry in the marine pasture, the agricultural products such as algae, marine vegetables and the like reduce the yield or run off, so that the site selection of the marine pasture is directly unreliable; by correcting the boundary, the boundary of the marine pasture avoids the potential risks, so that the recognition accuracy and reliability of the subsequent decision tree model are improved.
Further, in S400, the decision tree model is XGBoost model.
The method for training the decision tree model through the corrected boundary sub-images in all the water color remote sensing images to obtain the pre-trained decision tree model comprises the following steps: dividing each sub-image in all the water color remote sensing images into a training set and a verification set, wherein the training set and the verification set are specifically as follows: marking the corrected boundary sub-image as a positive sample as 1, screening out gray sub-images with the water color channel degree larger than the average water color channel degree of all gray sub-images, and marking the gray sub-images as a negative sample as 0, thereby completing marking of the sample; the marked positive sample and negative sample form a training sample set; dividing the training sample set into a training set and a verification set according to the ratio of 4:1, wherein the training set is used for training the decision tree model, and the verification set is used for verifying the prediction performance of the trained decision tree model.
Training the decision tree model by using the training set and the verification set to obtain a pre-trained decision tree model.
The method for training the decision tree model by using the training set and the verification set comprises the following steps:
extracting features of the training set, inputting the features into a decision tree model, optimizing the super parameters in the decision tree model by adopting a grid search method, retraining the decision tree model according to the optimized super parameters, and obtaining a trained pre-trained decision tree model.
Further, in S500, the method for identifying whether the marine ranch site selection area in the sea area to be evaluated is a marine ranch site selection area with high reliability by using the pre-trained decision tree model specifically includes:
By MERIS water color sensor, medium resolution imaging spectrometer and/or MODIS medium resolution imaging spectrometer The method comprises the steps of obtaining a water color remote sensing image of a marine pasture site selection area in a sea area to be evaluated through an image;
inverting the water color remote sensing image to obtain chlorophyll content distribution of the water color remote sensing image;
marking a plurality of regions of interest on the water color remote sensing image, preprocessing and extracting sub-images of the regions of interest, and graying;
And screening the positive sample area in the gray sub-image by using a pre-trained decision tree model, and judging that the marine ranching site selection area in the sea area to be evaluated is a marine ranching site selection area with high reliability if the positive sample area can be screened.
The invention also provides a decision tree model-based modern marine ranching site selection reliability evaluation system, which comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the computer program to run in units of the following system:
the remote sensing image acquisition unit is used for acquiring a water color remote sensing image of the sea area to be evaluated in a historical time period;
the preprocessing unit is used for marking a plurality of regions of interest in the water color remote sensing image and preprocessing to extract sub-images of the regions of interest;
the boundary correction unit is used for carrying out boundary correction operation on each sub-image to obtain a corrected boundary sub-image;
the decision tree training unit is used for training the decision tree model through the corrected boundary sub-images in all the water color remote sensing images to obtain a pre-trained decision tree model;
The decision tree identification unit is used for identifying whether the marine ranching site selection area in the sea area to be evaluated is a marine ranching site selection area with high reliability by utilizing a pre-trained decision tree model.
The beneficial effects of the invention are as follows: the invention provides a modern ocean pasture site selection reliability assessment method based on a decision tree model, which corrects the boundary of a remote sensing image, so that the boundary of the ocean pasture avoids the potential risks, thereby improving the recognition accuracy, rationality and reliability of the subsequent decision tree model on the ocean pasture position.
Drawings
The above and other features of the present invention will become more apparent from the detailed description of the embodiments thereof given in conjunction with the accompanying drawings, in which like reference characters designate like or similar elements, and it is apparent that the drawings in the following description are merely some examples of the present invention, and other drawings may be obtained from these drawings without inventive effort to those of ordinary skill in the art, in which:
FIG. 1 is a flow chart of a method for evaluating reliability of a modern marine ranch site selection based on a decision tree model;
FIG. 2 is a block diagram of a modern marine ranch site selection reliability assessment system based on a decision tree model.
Detailed Description
The conception, specific structure, and technical effects produced by the present application will be clearly and completely described below with reference to the embodiments and the drawings to fully understand the objects, aspects, and effects of the present application. It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other.
A flow chart of a method for evaluating the reliability of a modern marine ranch site selection based on a decision tree model according to the invention is shown in fig. 1, and a method for evaluating the reliability of a modern marine ranch site selection based on a decision tree model according to an embodiment of the invention is described below with reference to fig. 1.
The embodiment of the invention provides a modern marine ranching site selection reliability assessment method based on a decision tree model, which specifically comprises the following steps:
s100, acquiring a water color remote sensing image of a sea area to be evaluated in a historical time period;
s200, marking a plurality of regions of interest in the water color remote sensing image and preprocessing to extract sub-images of the regions of interest;
s300, carrying out boundary correction operation on each sub-image to obtain a boundary correction sub-image;
S400, training the decision tree model through corrected boundary sub-images in all the water color remote sensing images to obtain a pre-trained decision tree model;
S500, identifying whether the marine ranching site selection area in the sea area to be evaluated is a marine ranching site selection area with high reliability by utilizing a pre-trained decision tree model.
Further, the method further comprises the following steps: and S600, outputting the site selection place of the corresponding position of the marine pasture site selection area with high reliability to a corresponding GIS map to be displayed on a client.
Further, in S100, the history period is a selected history period of 40 days.
Wherein, the remote sensing image of water color is used for selecting the chlorophyll a concentration in the water color dataThe remote sensing image product is used as a water color remote sensing image.
Further, in S200, the method for marking a plurality of regions of interest in a water color remote sensing image and preprocessing to extract sub-images of the regions of interest includes the steps of: marking a plurality of regions of interest in a water-color remote sensing image in the water-color remote sensing image; performing bottom hat transformation on each region of interest, and extracting an image of the region of interest by threshold segmentation to obtain sub-images;
and inverting the water color remote sensing image to obtain chlorophyll content distribution of the water color remote sensing image.
Further, in S300, the method for obtaining the corrected boundary sub-image by performing the corrected boundary operation on each sub-image includes the following steps:
graying is carried out on each sub-image to obtain a gray sub-image;
Calculating the water color channel degree of each gray sub-image;
Screening gray sub-images with the water color channel degree smaller than the average water color channel degree of all gray sub-images as boundary sub-images to be corrected;
And carrying out boundary correction operation on the boundary sub-image to be corrected to obtain a corrected boundary sub-image.
Further, the method for calculating the water color channel degree of each gray sub-image comprises the following steps:
Let the set of gray sub-images be areas= { Areas i }, regard i as the serial number of gray sub-images, i e [1, N ], N is the number of gray sub-images; area i is the ith gray scale sub-image; edge detection is carried out on the Areas i, and the Areas i are divided into a plurality of water color flow direction Areas by all edge lines obtained through detection;
The local limit chlorophyll PEAKGREEN i is the average chlorophyll content value with the largest average chlorophyll content value in each of the water color flow Areas of Areas i, and the average value of the average chlorophyll content values in all of the water color flow Areas of Areas i is QMEANGREEN i;
All water color flow direction areas with average chlorophyll content greater than or equal to PEAKGREEN i in the respective water color flow direction areas in all gray level sub-images form a set all i, and the average value of the average chlorophyll content values in all water color flow direction areas in the set all i is HMEANGREEN i;
The water color channel degree Tunnel i of the gray sub-image Areas i is calculated as follows:
Tunneli=PeakGreeni/(QMeanGreeni+HMeanGreeni)。
The calculated water color channel degree is a trend intensity value of a water color flow direction region which possibly forms a chlorophyll diffusion channel towards the periphery in the chlorophyll content, and is an index of whether the boundary of a gray sub-image in the whole water color remote sensing image is balanced or not.
Further, the method for obtaining the corrected boundary sub-image by carrying out the boundary correction operation on the boundary sub-image to be corrected comprises the following steps:
Forming a set EdgeStre = { EdgeStre j},EdgeStrej of the boundary sub-images to be corrected with the serial number j in EdgeStre according to the size sequence of the water color channel degree of the boundary sub-images to be corrected; performing edge detection on EdgeStre j, and dividing EdgeStre j into a plurality of water color flow direction areas by using each detected edge line;
Starting from j=2, sequentially carrying out boundary correction operation on EdgeStre j in the value range of j, wherein the specific method comprises the following steps:
recording CycMaxP as the center of inscribed circle of the water color flow direction region with the largest chlorophyll content in each water color flow direction region in EdgeStre j; the inscribed circle center of the water color flow direction area with the minimum chlorophyll content in each water color flow direction area in EdgeStre j is CycMinP; the water color flow direction is the direction from CycMaxP to CycMinP;
EdgeMaxP j is the point on the boundary line of EdgeStre j where the chlorophyll content is the greatest; edgeMinP j is the point on the boundary line of EdgeStre j where the chlorophyll content is minimum; the boundary to be corrected is marked by a curve between the water color flow directions from EdgeMaxP j to EdgeMinP j on the boundary line of EdgeStre j;
Searching all to-be-corrected boundary sub-images with the serial numbers smaller than j, and marking the to-be-corrected boundary sub-image with the minimum difference between the chlorophyll content of the point with the largest chlorophyll content on the boundary line and the chlorophyll content of the point with the largest chlorophyll content on the boundary line of EdgeStre j as a stable boundary sub-image EdgeStable;
StabMaxP is the point on the boundary line of EdgeStable where the chlorophyll content is the greatest; stabMinP is the point on the boundary line of EdgeStable where the chlorophyll content is minimum; the corrected boundary curve FixLine is marked by the curve between the water color flow directions from StabMaxP to StabMinP on the boundary line of EdgeStable;
Deleting the boundary to be corrected on the boundary line EdgeStre j, marking the point EdgeMaxP j on the boundary line EdgeStre j as an end point A, marking the point EdgeMinP j on the boundary line EdgeStre j as an end point B,
The StabMaxP point of the copied corrected boundary curve FixLine is marked as the C endpoint, and the StabMinP point of the copied corrected boundary curve is marked as the D endpoint;
scaling curve FixLine equally to the distance between the C and D endpoints and the distance between the a and B endpoints is noted as curve UpFixLine;
moving the curve UpFixLine as a whole to reconstruct the modified boundary EdgeStre j with the C-endpoint coincident with the a-endpoint and the D-endpoint coincident with the B-endpoint;
And taking the boundary sub-image to be corrected of the corrected boundary EdgeStre j as a corrected boundary sub-image.
Further, in S400, the decision tree model is XGBoost model.
The method for training the decision tree model through the corrected boundary sub-images in all the water color remote sensing images to obtain the pre-trained decision tree model comprises the following steps: dividing each sub-image in all the water color remote sensing images into a training set and a verification set, wherein the training set and the verification set are specifically as follows: marking the corrected boundary sub-image as a positive sample as 1, screening out gray sub-images with the water color channel degree larger than the average water color channel degree of all gray sub-images, and marking the gray sub-images as a negative sample as 0, thereby completing marking of the sample; the marked positive sample and negative sample form a training sample set; dividing the training sample set into a training set and a verification set according to the ratio of 4:1, wherein the training set is used for training the decision tree model, and the verification set is used for verifying the prediction performance of the trained decision tree model.
Training the decision tree model by using the training set and the verification set to obtain a pre-trained decision tree model.
The method for training the decision tree model by using the training set and the verification set comprises the following steps:
extracting features of the training set, inputting the features into a decision tree model, optimizing the super parameters in the decision tree model by adopting a grid search method, retraining the decision tree model according to the optimized super parameters, and obtaining a trained pre-trained decision tree model.
Further, in S500, the method for identifying whether the marine ranch site selection area in the sea area to be evaluated is a marine ranch site selection area with high reliability by using the pre-trained decision tree model specifically includes:
acquiring a water color remote sensing image of a marine pasture site selection area in the sea area to be evaluated through a MERIS water color sensor;
inverting the water color remote sensing image to obtain chlorophyll content distribution of the water color remote sensing image;
marking a plurality of regions of interest on the water color remote sensing image, preprocessing and extracting sub-images of the regions of interest, and graying;
And screening the positive sample area in the gray sub-image by using a pre-trained decision tree model, and judging that the marine ranching site selection area in the sea area to be evaluated is a marine ranching site selection area with high reliability if the positive sample area can be screened.
The system for evaluating the site selection reliability of the modern marine ranching based on the decision tree model provided by the embodiment of the invention is shown in fig. 2, which is a structural diagram of the system for evaluating the site selection reliability of the modern marine ranching based on the decision tree model, and the system for evaluating the site selection reliability of the modern marine ranching based on the decision tree model comprises the following components: a processor, a memory and a computer program stored in the memory and executable on the processor, which when executed implements the steps in the above described embodiments of a modern marine ranch site selection reliability assessment system based on a decision tree model.
The system comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the computer program to run in units of the following system:
the remote sensing image acquisition unit is used for acquiring a water color remote sensing image of the sea area to be evaluated in a historical time period;
the preprocessing unit is used for marking a plurality of regions of interest in the water color remote sensing image and preprocessing to extract sub-images of the regions of interest;
the boundary correction unit is used for carrying out boundary correction operation on each sub-image to obtain a corrected boundary sub-image;
the decision tree training unit is used for training the decision tree model through the corrected boundary sub-images in all the water color remote sensing images to obtain a pre-trained decision tree model;
The decision tree identification unit is used for identifying whether the marine ranching site selection area in the sea area to be evaluated is a marine ranching site selection area with high reliability by utilizing a pre-trained decision tree model.
The modern marine ranching site selection reliability evaluation system based on the decision tree model can be operated in computing equipment such as a desktop computer, a notebook computer, a palm computer, a cloud server and the like. The decision tree model-based modern marine ranching site selection reliability assessment system may include, but is not limited to, a processor, a memory. It will be appreciated by those skilled in the art that the examples are merely examples of a decision tree model based modern marine ranching reliability assessment system and do not constitute a limitation of the decision tree model based modern marine ranching reliability assessment system, and may include more or fewer components than examples, or may combine certain components, or different components, e.g., the decision tree model based modern marine ranching reliability assessment system may also include input and output devices, network access devices, buses, etc.
The Processor may be a central processing unit (Central Processing Unit, CPU), other general purpose Processor, digital signal Processor (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. The general processor can be a microprocessor or any conventional processor, etc., and the processor is a control center of the system for operating the modern marine ranch site selection reliability evaluation system based on the decision tree model, and various interfaces and lines are used for connecting various parts of the system for operating the whole modern marine ranch site selection reliability evaluation system based on the decision tree model.
The memory may be used to store the computer program and/or module, and the processor may implement the various functions of the decision tree model-based modern marine ranch site selection reliability assessment system by running or executing the computer program and/or module stored in the memory and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data, phonebook, etc.) created according to the use of the handset, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart memory card (SMART MEDIA CARD, SMC), secure Digital (SD) card, flash memory card (FLASH CARD), at least one disk storage device, flash memory device, or other volatile solid-state storage device.
Although the present invention has been described in considerable detail and with particularity with respect to several described embodiments, it is not intended to be limited to any such detail or embodiment or any particular embodiment so as to effectively cover the intended scope of the invention. Furthermore, the foregoing description of the invention has been presented in its embodiments contemplated by the inventors for the purpose of providing a useful description, and for the purposes of providing a non-essential modification of the invention that may not be presently contemplated, may represent an equivalent modification of the invention.
Claims (6)
1. The modern marine ranching site selection reliability assessment method based on the decision tree model is characterized by comprising the following steps of:
s100, acquiring a water color remote sensing image of a sea area to be evaluated in a historical time period;
s200, marking a plurality of regions of interest in the water color remote sensing image and preprocessing to extract sub-images of the regions of interest;
s300, carrying out boundary correction operation on each sub-image to obtain a boundary correction sub-image;
S400, training the decision tree model through corrected boundary sub-images in all the water color remote sensing images to obtain a pre-trained decision tree model;
s500, identifying whether the marine ranching site selection area in the sea area to be evaluated is a marine ranching site selection area with high reliability by utilizing a pre-trained decision tree model;
In S300, the method specifically includes the following steps:
graying is carried out on each sub-image to obtain a gray sub-image;
Calculating the water color channel degree of each gray sub-image;
Screening gray sub-images with the water color channel degree smaller than the average water color channel degree of all gray sub-images as boundary sub-images to be corrected;
carrying out boundary correction operation on the boundary sub-image to be corrected to obtain a corrected boundary sub-image;
the method for calculating the water color channel degree of each gray sub-image comprises the following steps:
Let the set of gray sub-images be areas= { Areas i }, regard i as the serial number of gray sub-images, i e [1, N ], N is the number of gray sub-images; area i is the ith gray scale sub-image; edge detection is carried out on the Areas i, and the Areas i are divided into a plurality of water color flow direction Areas by all edge lines obtained through detection;
The local limit chlorophyll PEAKGREEN i is the average chlorophyll content value with the largest average chlorophyll content value in each of the water color flow Areas of Areas i, and the average value of the average chlorophyll content values in all of the water color flow Areas of Areas i is QMEANGREEN i; all water color flow direction areas with average chlorophyll content greater than or equal to PEAKGREEN i in the respective water color flow direction areas in all gray level sub-images form a set all i, and the average value of the average chlorophyll content values in all water color flow direction areas in the set all i is HMEANGREEN i;
The water color channel degree Tunnel i of the gray sub-image Areas i is calculated as follows:
Tunneli=PeakGreeni/(QMeanGreeni+HMeanGreeni)；
the method for obtaining the corrected boundary sub-image by carrying out the boundary correction operation on the boundary sub-image to be corrected comprises the following steps:
Forming a set EdgeStre = { EdgeStre j},EdgeStrej of the boundary sub-images to be corrected with the serial number j in EdgeStre according to the size sequence of the water color channel degree of the boundary sub-images to be corrected; performing edge detection on EdgeStre j, and dividing EdgeStre j into a plurality of water color flow direction areas by using each detected edge line;
Starting from j=2, sequentially carrying out boundary correction operation on EdgeStre j in the value range of j, wherein the specific method comprises the following steps:
recording CycMaxP as the center of inscribed circle of the water color flow direction region with the largest chlorophyll content in each water color flow direction region in EdgeStre j; the inscribed circle center of the water color flow direction area with the minimum chlorophyll content in each water color flow direction area in EdgeStre j is CycMinP; the water color flow direction is the direction from CycMaxP to CycMinP;
EdgeMaxP j is the point on the boundary line of EdgeStre j where the chlorophyll content is the greatest; edgeMinP j is the point on the boundary line of EdgeStre j where the chlorophyll content is minimum; the boundary to be corrected is marked by a curve between the water color flow directions from EdgeMaxP j to EdgeMinP j on the boundary line of EdgeStre j;
Searching all to-be-corrected boundary sub-images with the serial numbers smaller than j, and marking the to-be-corrected boundary sub-image with the minimum difference between the chlorophyll content of the point with the largest chlorophyll content on the boundary line and the chlorophyll content of the point with the largest chlorophyll content on the boundary line of EdgeStre j as a stable boundary sub-image EdgeStable;
StabMaxP is the point on the boundary line of EdgeStable where the chlorophyll content is the greatest; stabMinP is the point on the boundary line of EdgeStable where the chlorophyll content is minimum; the corrected boundary curve FixLine is marked by the curve between the water color flow directions from StabMaxP to StabMinP on the boundary line of EdgeStable;
Deleting the boundary to be corrected on the boundary line EdgeStre j, marking the point EdgeMaxP j on the boundary line EdgeStre j as an end point A, marking the point EdgeMinP j on the boundary line EdgeStre j as an end point B,
The StabMaxP point of the copied corrected boundary curve FixLine is marked as the C endpoint, and the StabMinP point of the copied corrected boundary curve is marked as the D endpoint;
scaling curve FixLine equally to the distance between the C and D endpoints and the distance between the a and B endpoints is noted as curve UpFixLine;
moving the curve UpFixLine as a whole to a modified boundary that is reconstructed EdgeStre j by overlapping the C-endpoint with the a-endpoint and the D-endpoint with the B-endpoint;
And taking the boundary sub-image EdgeStre j to be corrected after the boundary correction as a boundary correction sub-image.
2. The decision tree model-based modern marine ranching site selection reliability assessment method of claim 1, further comprising: and S600, outputting the site selection place of the corresponding position of the marine pasture site selection area with high reliability to a corresponding GIS map to be displayed on a client or to be stored in a database.
3. A modern marine ranching site selection reliability assessment method based on a decision tree model according to claim 1, characterized in that in S200 the method of marking a plurality of regions of interest in a water-color remote sensing image and preprocessing to extract sub-images of the regions of interest comprises the steps of: marking a plurality of regions of interest in a water-color remote sensing image in the water-color remote sensing image; the bottom hat transformation is performed on each region of interest and the image of the region of interest is extracted as a sub-image with thresholding.
4. The method for evaluating the site selection reliability of a modern marine ranch based on a decision tree model according to claim 1, characterized in that in S400 the decision tree model is XGBoost model.
5. The decision tree model-based modern marine ranching site selection reliability assessment method according to claim 1, wherein the method for training the decision tree model through the corrected boundary sub-images in all water color remote sensing images to obtain a pre-trained decision tree model is as follows: dividing each sub-image in all the water color remote sensing images into a training set and a verification set, wherein the training set and the verification set are specifically as follows: marking the corrected boundary sub-image as a positive sample as 1, screening out gray sub-images with the water color channel degree larger than the average water color channel degree of all gray sub-images, and marking the gray sub-images as a negative sample as 0, thereby completing marking of the sample; the marked positive sample and negative sample form a training sample set; dividing the training sample set into a training set and a verification set according to the ratio of 4:1, wherein the training set is used for training the decision tree model, and the verification set is used for verifying the prediction performance of the trained decision tree model;
training the decision tree model by using the training set and the verification set to obtain a pre-trained decision tree model.
6. The decision tree model-based modern marine ranching site selection reliability assessment method of claim 5, wherein the method of training the decision tree model using a training set and a validation set is: extracting features of the training set, inputting the features into a decision tree model, optimizing the super parameters in the decision tree model by adopting a grid search method, retraining the decision tree model according to the optimized super parameters, and obtaining a trained pre-trained decision tree model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410725837.6A CN118334525B (en) | 2024-06-06 | 2024-06-06 | Modern marine pasture site selection reliability assessment method based on decision tree model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410725837.6A CN118334525B (en) | 2024-06-06 | 2024-06-06 | Modern marine pasture site selection reliability assessment method based on decision tree model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118334525A CN118334525A (en) | 2024-07-12 |
| CN118334525B true CN118334525B (en) | 2024-08-16 |
Family
ID=91777242
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410725837.6A Active CN118334525B (en) | 2024-06-06 | 2024-06-06 | Modern marine pasture site selection reliability assessment method based on decision tree model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118334525B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112001641A (en) * | 2020-08-27 | 2020-11-27 | 中国海洋大学 | Scallop culture area suitability remote sensing evaluation system |
| CN116313145A (en) * | 2023-05-10 | 2023-06-23 | 江西省农业科学院畜牧兽医研究所 | Intelligent epidemiological investigation system for animals |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10628756B1 (en) * | 2019-09-12 | 2020-04-21 | Performance Livestock Analytics, Inc. | Livestock and feedlot data collection and processing using UHF-band interrogation of radio frequency identification tags |
| CN116502903A (en) * | 2023-03-22 | 2023-07-28 | 中国科学院海洋研究所 | Method for evaluating suitability of bottom-sowing scallop breeding area site selection based on analytic hierarchy process |
| CN116739817B (en) * | 2023-08-08 | 2024-01-19 | 广州桓乐生态环境科技有限公司 | Marine organism diversity monitoring system and data processing method |
| CN118134678A (en) * | 2024-03-20 | 2024-06-04 | 广东海洋大学 | Modern marine ranching site selection method |
-
2024
- 2024-06-06 CN CN202410725837.6A patent/CN118334525B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112001641A (en) * | 2020-08-27 | 2020-11-27 | 中国海洋大学 | Scallop culture area suitability remote sensing evaluation system |
| CN116313145A (en) * | 2023-05-10 | 2023-06-23 | 江西省农业科学院畜牧兽医研究所 | Intelligent epidemiological investigation system for animals |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118334525A (en) | 2024-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xiong et al. | Identification of cash crop diseases using automatic image segmentation algorithm and deep learning with expanded dataset | |
| Paravolidakis et al. | Automatic coastline extraction using edge detection and optimization procedures | |
| Ji et al. | Seabed sediment classification using multibeam backscatter data based on the selecting optimal random forest model | |
| CN116994140A (en) | Cultivated land extraction method, device, equipment and medium based on remote sensing image | |
| CN111986099A (en) | Tillage monitoring method and system based on convolutional neural network with residual error correction fused | |
| CN113450328B (en) | Medical image key point detection method and system based on improved neural network | |
| CN113269257A (en) | Image classification method and device, terminal equipment and storage medium | |
| CN112017192B (en) | Glandular cell image segmentation method and glandular cell image segmentation system based on improved U-Net network | |
| CN111784721A (en) | Ultrasonic endoscopic image intelligent segmentation and quantification method and system based on deep learning | |
| Zhang et al. | MFCIS: an automatic leaf-based identification pipeline for plant cultivars using deep learning and persistent homology | |
| CN115439654B (en) | Method and system for finely dividing weakly supervised farmland plots under dynamic constraint | |
| Wunderlich et al. | Comprehensively evaluating the performance of species distribution models across clades and resolutions: choosing the right tool for the job | |
| Kamani et al. | Shape matching using skeleton context for automated bow echo detection | |
| KR101821770B1 (en) | Techniques for feature extraction | |
| CN118334525B (en) | Modern marine pasture site selection reliability assessment method based on decision tree model | |
| Ruiz‐Munoz et al. | Super resolution for root imaging | |
| CN118230166A (en) | Corn canopy organ identification method and canopy phenotype detection method based on improved Mask2YOLO network | |
| CN116433596A (en) | Slope vegetation coverage measuring method and device and related components | |
| Abishek et al. | Soil Texture Prediction Using Machine Learning Approach for Sustainable Soil Health Management | |
| Takayama et al. | Optimal segmentation of classification and prediction maps for monitoring forest condition with spectral and spatial information from hyperspectral data | |
| Lansbergen et al. | Sonar 2021-2022 field experiment method development: a case-study of seaweed cultivation and biomass estimation using different sonar techniques and image recognizing networks | |
| Osadebey et al. | Plant leaves region segmentation in cluttered and occluded images using perceptual color space and k-means-derived threshold with set theory | |
| Awad | A New Winter Wheat Crop Segmentation Method Based on a New Fast-UNet Model and Multi-Temporal Sentinel-2 Images. | |
| CN118115889B (en) | Terrace automatic extraction method and terrace automatic extraction system based on deep learning semantic segmentation model | |
| CN117409329B (en) | Method and system for reducing false alarm rate of underground cavity detection by three-dimensional ground penetrating radar |
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 |