CN113240026B - Vector-grid combined inland water surface floater batch identification and extraction method - Google Patents
Vector-grid combined inland water surface floater batch identification and extraction method Download PDFInfo
- Publication number
- CN113240026B CN113240026B CN202110563234.7A CN202110563234A CN113240026B CN 113240026 B CN113240026 B CN 113240026B CN 202110563234 A CN202110563234 A CN 202110563234A CN 113240026 B CN113240026 B CN 113240026B
- Authority
- CN
- China
- Prior art keywords
- water surface
- floater
- suspected
- vector
- remote sensing
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
Abstract
The invention discloses a vector grid combined inland water surface floater batch identification and extraction method, which comprises the following steps: obtaining a remote sensing image in a water surface range; classifying the remote sensing images in the water surface range, screening out and exporting the pattern spots of the suspected water surface floaters, and obtaining a planar pattern layer of the suspected water surface floaters; calculating the area of each suspected water surface floater pattern spot in the suspected water surface floater planar pattern layer to obtain a suspected water surface floater dot pattern layer; calculating the characteristic value of the non-water surface floater of each point in the suspected water surface floater point-like graph layer; and eliminating misjudgment pattern spots according to the characteristic values of the non-water surface floaters, and extracting a water surface floaters identification result. The remarkable effects are as follows: the vector data space analysis technology and the remote sensing grid data are fully utilized, the fast and accurate automatic identification of the terrestrial water surface floater in a large scale range is realized, the defect that foreign matters are in the same spectrum in the floater identification method only by utilizing the remote sensing image is overcome, and the identification accuracy is higher.
Description
Technical Field
The invention relates to the technical field of geographic information, in particular to a vector-grid combined inland water surface floater batch identification and extraction method.
Background
While the social economy of China is rapidly developed, the water pollution is aggravated, and a large amount of floating objects appear on the water surfaces of inland lakes, reservoirs, rivers and the like. The existence of the floating objects not only pollutes the water environment and threatens the health of human beings, but also has adverse effects on the development of regional economy.
The existing identification method for the floaters on the water surface mainly comprises a background subtraction method and an image segmentation method, for example, the background segmentation technology is utilized to identify the floaters on the sea surface by comprehensively considering the water surface color information characteristics and the floaters motion state; according to the characteristic of low saturation of the ocean surface, carrying out embossment processing and edge detection on the extracted water surface area image to obtain the position of the target floating object; and (4) segmenting the water surface target by using a Mean-shift algorithm and an OSTU method, and then identifying the water surface target by using an SVM (support vector machine). The existing method is basically based on image algorithm identification, and the phenomenon of misjudgment of 'foreign body and spectrum' is difficult to avoid.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide a vector grid combined inland water surface floater batch identification and extraction method, which can be used for identifying the water surface floater space distribution method in batches by utilizing the respective advantages of vector data and grid data, can realize large-scale, batch and automatic extraction of water surface floater vector pattern spots, master the space distribution condition of the water surface floater vector pattern spots, and can be used for cleaning floaters in water areas such as reservoirs, lakes and the like and protecting the water area environment and the like.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
the method for identifying and extracting inland water surface floaters in batches by combining vector grids is characterized by comprising the following steps of:
step 1, obtaining a remote sensing image in a water surface range;
step 2, carrying out ground object classification on the remote sensing image in the water surface range, screening out suspected water surface floater figure spots and exporting the suspected water surface floater figure spots to obtain a suspected water surface floater surface-shaped figure layer;
step 3, calculating the area of each suspected water surface floater pattern spot in the suspected water surface floater planar pattern layer, and performing surface turning point processing on the calculation result to obtain a suspected water surface floater point pattern layer;
step 4, according to the formula
Calculating characteristic values Pzs of non-water surface floating objects at each point in the suspected water surface floating object point graph layer, wherein r is the search radius and W is the distance between the search radius and the pointiIs the area of the spot of the suspected water surface float where point i is located, DiIs the distance between point i and any point (x, y) within the search radius, WmaxSearching the maximum area of the suspected water surface floater pattern spot within the radius range;
and 5, removing misjudgment pattern spots according to the characteristic values Pzs of the non-water surface floats of each point in the suspected water surface float point-like pattern layer, and extracting a water surface float identification result.
Further, the process of acquiring the remote sensing image in the water surface range in the step 1 is as follows:
and (3) processing the high-resolution remote sensing image with the spatial resolution of 0.2 meter by using the water surface range vector layer as a mask, and extracting the remote sensing image in the required water surface range.
Further, the obtaining process of the planar image layer of the suspected floating object on the water surface in the step 2 is specifically as follows:
step 2.1, establishing a remote sensing image interpretation identifier;
2.2, carrying out classification calculation on the remote sensing image in the water surface range according to the remote sensing image interpretation identification to obtain a ground feature classification result of the remote sensing image in the water surface range;
step 2.3, carrying out grid vector transformation processing on the ground feature classification result of the remote sensing image in the water surface range by adopting a double boundary search algorithm, and keeping the ground feature classification attribute;
and 2.4, screening out the pattern spots of the suspected water surface floaters according to the ground object classification attributes, and exporting the pattern spots as a new vector layer to obtain the planar pattern layer of the suspected water surface floaters.
Further, the calculation formula for performing classification calculation on the remote sensing image in the water surface range in the step 2.2 is as follows:
wherein F (x) is an objective function; x is a vector in n-dimensional space; k is a covariance matrix between the n-dimensional eigenvectors; w is aiIs a vector consisting of the mean of the features of each dimension.
Further, the remote sensing image interpretation identification comprises ships, bare island reefs, bridges, wires and cables and water surface floating objects.
Further, the calculation formula of the area of the pattern spot of the water surface floating object in the step 3 is as follows:
wherein, P is the area of the pattern spot; a is an ellipsoid long semi-axis; b is an ellipsoid short semi-axis; t is the longitude difference of the east-west outlines of the map; b is1、B2Respectively, the latitude of the north and south outlines of the map, (B)2-B1) The latitude difference of the north-south figure of the map is shown; b ism＝(B1+B2)/2；
e2＝(a2-b2)/a2。
Further, the specific process of extracting the identification result of the water surface floater in the step 5 is as follows:
step 5.1, carrying out fracture grading on the characteristic value Pzs of the non-water surface floater of each point in the suspected water surface floater point-like graph layer by adopting a natural fracture method, and extracting data not less than a preset threshold value;
step 5.2, carrying out grid-to-vector conversion processing on the extracted data to obtain a vector range pattern spot;
and 5.3, deleting misjudged suspected water surface floater image spots in the vector range image spots, and obtaining a water surface floater identification result.
Further, the value of the preset threshold is 366.54.
The invention has the following remarkable effects: on the basis of traditional image algorithm identification, a vector grid combination method is utilized, and the vector data space analysis technology and remote sensing grid data are fully utilized to perform secondary calculation, analysis and extraction on misjudgment data of foreign matter homoplasms, so that the quick and accurate automatic identification of the terrestrial water surface floaters in a large scale range is realized, the defect that foreign matter homoplasms are only utilized in a floaters identification method by remote sensing images is overcome, and the identification accuracy is higher;
by utilizing the advantages of the vector data and the grid data, the spatial distribution of the water surface floaters can be identified in batches, the vector pattern spots of the water surface floaters can be extracted in a large-scale, batch and automatic mode, the spatial distribution condition of the water surface floaters can be mastered, and the method can be used for cleaning floaters in water areas such as reservoirs and lakes, protecting the water area environment and the like.
Drawings
FIG. 1 is a flow chart of a method of the present invention;
fig. 2 is a schematic diagram of the identification and extraction result of the water surface floating object.
Detailed Description
The following provides a more detailed description of the embodiments and the operation of the present invention with reference to the accompanying drawings.
As shown in fig. 1, a vector grid combined inland water surface floater batch identification and extraction method specifically comprises the following steps:
step 1, obtaining a remote sensing image in a water surface range:
preparing data materials: the data information used for obtaining the remote sensing image in the water surface range comprises a high-resolution remote sensing image (the spatial resolution is 0.2 m) and a water surface range vector layer (derived from a land utilization survey result). The data space reference information is unified into a 2000 national geodetic coordinate system and a 1985 national elevation standard.
Remote sensing image cutting: in order to reduce the interference of other ground objects outside the water surface in the remote sensing image, an Extract by mask tool in an Arcgis platform is used, the remote sensing image is processed by taking the water surface range vector layer as a mask, the remote sensing image in the water surface range is extracted, and the remote sensing image layer is exported to be a new remote sensing image layer.
Step 2, carrying out ground object classification on the remote sensing image in the water surface range, screening out suspected water surface floater pattern spots and exporting the suspected water surface floater pattern spots to obtain a suspected water surface floater surface-shaped pattern layer, wherein the specific process is as follows:
step 2.1, establishing a remote sensing image interpretation identifier;
2.2, carrying out classification calculation on the remote sensing images in the water surface range according to the remote sensing image interpretation identification to obtain a ground feature classification result (raster data) of the remote sensing images in the water surface range;
the calculation formula of the classification calculation is as follows:
wherein F (x) is an objective function; x is a vector in n-dimensional space; k is a covariance matrix between the n-dimensional eigenvectors; w is aiIs a vector consisting of the mean of the features of each dimension.
Step 2.3, carrying out grid vector transformation processing on the ground feature classification result of the remote sensing image in the water surface range by adopting a double boundary search algorithm, and keeping the ground feature classification attribute;
and 2.4, screening out the pattern spots of the ground objects classified as the water surface floaters according to the ground object classification attributes, and exporting the pattern spots as a new vector image layer, namely obtaining the planar image layer of the suspected water surface floaters.
Further, the remote sensing image interpretation identification comprises ships, bare island reefs, bridges, wires and cables and water surface floating objects.
By analyzing the classification result, the phenomenon of 'same spectrum of foreign matters' exists (the same spectrum of the foreign matters means that two different ground objects possibly present the same spectral line characteristics in a certain spectral band), and the phenomenon of 'same spectrum of the foreign matters' mainly causes two main situations of misjudgment, wherein one situation is that the area of the phenomenon is larger than that of a real floating object, such as a partial ship body, a bridge, an exposed island reef and the like; the other is that the area is similar to that of the real floating objects, and the part has the characteristics of more dense concentration and more regular arrangement and is generally distributed around the misjudgment pattern spot with larger area. In order to solve the defect of erroneous judgment, the image spots which are wrongly classified as the water surface floating objects are effectively removed, and the image spots which are wrongly classified are screened through the following steps 3 and 4.
Step 3, calculating the area of each suspected water surface floater pattern spot in the suspected water surface floater planar pattern layer, and performing surface turning point processing on the calculation result to obtain a suspected water surface floater point pattern layer, which is specifically:
firstly, adding attribute fields to the suspected water surface floater planar image layer to calculate the geometric area of each water surface floater graphic spot, wherein the type of the added fields is double-precision, and the area of the graphic spot is calculated by using the following formula, and the unit is square meter.
Wherein, P is the area of the pattern spot; a is an ellipsoid long semi-axis (unit: meter); b is the minor semi-axis of the ellipsoid (unit: meter), e2＝(a2-b2)/a2(ii) a T is the longitude difference (unit: point) of the east-west outlines of the map; b is1、B2Respectively, the latitude of the north and south outlines of the map, (B)2-B1) The latitude difference of the north-south map of the map sheet (unit: radian); b ism＝(B1+B2)/2；
e2＝(a2-b2)/a2。
And then, performing surface-to-point processing on the calculation result by using a Feature to point tool in the Arcgis platform, and simultaneously keeping the area attribute of the pattern spots on the calculation result to obtain the point pattern layer of the suspected water surface floater.
Step 4, based on the area of each suspected water surface floater pattern spot calculated in the step 3, according to a formula
Calculating the characteristic value P of the non-water surface floater of each point in the suspected water surface floater point graph layerzs. Wherein r is a search radius, and the effect is best when the search radius r is determined to be 100 meters through experimental comparison and analysis according to the sizes of the ground objects such as inland water body hulls, bridges, bare island reefs and the like; i is the input point, WiThe area of the pattern spot of the water surface floater where the point i is located is larger, the weight of the pattern spot is larger, the calculation result value is larger, and the pattern spot area serving as the weight is the key for screening out a ship body, a bridge and a water surface island reef; diIs the distance between point i and any point (x, y) within the search radius, WmaxTo search for the maximum area of the water surface float pattern spot within the radius,
the larger the value of the figure spot is, the closer the figure spot area is, otherwise, the larger the figure spot area difference is;
generally, the larger the area of the suspected water surface floater body or the nearby graph is, the more densely the suspected water surface floater body is gathered, the larger the Pzs value is, otherwise, the smaller the area is, therefore, through the calculation of the area of the suspected water surface floater figure spots in the step 3 and the calculation of the non-water surface floater characteristic value Pzs based on the area of the figure spots in the step 4, the misjudged suspected water surface floater figure spots can be screened out according to the Pzs value, and further, the purpose of screening the misjudged figure spots in batches is achieved.
Step 5, according to the characteristic value Pzs of the non-water surface floater of each point in the suspected water surface floater point-like graph layer, rejecting misjudgment graph spots and extracting a water surface floater identification result, wherein the specific process is as follows:
step 5.1, performing fracture classification on the non-water surface floater characteristic values Pzs of each point in the suspected water surface floater dot-shaped layer by adopting a natural fracture method, and extracting non-water surface floater characteristic value data not less than a preset threshold value (in the embodiment, the value of the preset threshold value is 366.54);
step 5.2, carrying out grid-to-vector conversion processing on the extracted characteristic value data of the non-water surface floater to obtain a vector range pattern spot;
and 5.3, deleting misjudged suspected water surface floater image spots in the vector range image spots, and obtaining a water surface floater identification result.
And 5, carrying out fracture classification on the characteristic value Pzs of the non-water surface floater of each point by a natural fracture method, and deleting the pattern spots which are larger than or equal to a preset threshold value in the suspected water surface floater pattern spots, so that the aims of batch deletion and batch deletion of misjudgment pattern spots are fulfilled.
And (3) performing precision verification on the water surface floater pattern spot extraction result: selecting a water surface remote sensing image of about 20 square kilometers, carrying out water surface floater pattern spot identification and extraction by adopting the method, carrying out total identification and extraction on 74028 water surface floater pattern spots, and carrying out manual one-by-one inspection as shown in figure 2, wherein 855 pattern spots are extracted in a missing or wrong way, and the accuracy rate of water surface floater identification and extraction is 98.85 percent.
The technical solution provided by the present invention is described in detail above. The principles and embodiments of the present invention are explained herein using specific examples, which are presented only to assist in understanding the method and its core concepts. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.
Claims (8)
1. A vector grid combined inland water surface floater batch identification and extraction method is characterized by comprising the following steps:
step 1, obtaining a remote sensing image in a water surface range;
step 2, carrying out ground object classification on the remote sensing image in the water surface range, screening out suspected water surface floater figure spots and exporting the suspected water surface floater figure spots to obtain a suspected water surface floater surface-shaped figure layer;
step 3, calculating the area of each suspected water surface floater pattern spot in the suspected water surface floater planar pattern layer, and performing surface turning point processing on the calculation result to obtain a suspected water surface floater point pattern layer;
step 4, according to the formula
Calculating characteristic values Pzs of non-water surface floating objects at each point in the suspected water surface floating object point graph layer, wherein r is the search radius and W is the distance between the search radius and the pointiIs the area of the spot of the suspected water surface float where point i is located, DiIs the distance between point i and any point (x, y) within the search radius, WmaxSearching the maximum area of the suspected water surface floater pattern spot within the radius range;
and 5, removing misjudgment pattern spots according to the characteristic values Pzs of the non-water surface floats of each point in the suspected water surface float point-like pattern layer, and extracting a water surface float identification result.
2. The vector grid combined inland water surface floater batch identification and extraction method as claimed in claim 1, characterized in that: the process of acquiring the remote sensing image in the water surface range in the step 1 is as follows:
and (3) processing the high-resolution remote sensing image with the spatial resolution of 0.2 meter by using the water surface range vector layer as a mask, and extracting the remote sensing image in the required water surface range.
3. The vector grid combined inland water surface floater batch identification and extraction method as claimed in claim 1, characterized in that: the process for obtaining the planar image layer of the suspected floating object on the water surface in the step 2 is as follows:
step 2.1, establishing a remote sensing image interpretation identifier;
2.2, carrying out classification calculation on the remote sensing image in the water surface range according to the remote sensing image interpretation identification to obtain a ground feature classification result of the remote sensing image in the water surface range;
step 2.3, carrying out grid vector transformation processing on the ground feature classification result of the remote sensing image in the water surface range by adopting a double boundary search algorithm, and keeping the ground feature classification attribute;
and 2.4, screening out the pattern spots of the suspected water surface floaters according to the ground object classification attributes, and exporting the pattern spots as a new vector layer to obtain the planar pattern layer of the suspected water surface floaters.
4. The vector grid combined inland water surface floater batch identification and extraction method according to claim 3, characterized in that: in step 2.2, the calculation formula for carrying out classification calculation on the remote sensing image in the water surface range is as follows:
wherein F (x) is an objective function; x is a vector in n-dimensional space; k is a covariance matrix between the n-dimensional eigenvectors; w is aiIs a vector consisting of the mean of the features of each dimension.
5. The vector grid combined inland water surface floater batch identification and extraction method according to claim 3 or 4, characterized in that: the remote sensing image interpretation identification comprises a ship, a bare island, a bridge, a wire cable and a water surface floater.
6. The vector grid combined inland water surface floater batch identification and extraction method as claimed in claim 1, characterized in that: the calculation formula of the area of the suspected water surface floater pattern spot in the step 3 is as follows:
wherein, P is the area of the pattern spot; a is an ellipsoid long semi-axis; b is an ellipsoid short semi-axis; t is the longitude difference of the east-west outlines of the map; b is1、B2Respectively, the latitude of the north and south outlines of the map, (B)2-B1) The latitude difference of the north-south figure of the map is shown; b ism＝(B1+B2)/2；
e2＝(a2-b2)/a2。
7. The vector grid combined inland water surface floater batch identification and extraction method as claimed in claim 1, characterized in that: the specific process of extracting the identification result of the water surface floater in the step 5 is as follows:
step 5.1, carrying out fracture grading on the characteristic value Pzs of the non-water surface floater of each point in the suspected water surface floater point-like graph layer by adopting a natural fracture method, and extracting data not less than a preset threshold value;
step 5.2, carrying out grid-to-vector conversion processing on the extracted data to obtain a vector range pattern spot;
and 5.3, deleting misjudged suspected water surface floater image spots in the vector range image spots, and obtaining a water surface floater identification result.
8. The vector grid combined inland water surface floater batch identification and extraction method according to claim 7, characterized in that: the value of the preset threshold is 366.54.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110563234.7A CN113240026B (en) | 2021-05-24 | 2021-05-24 | Vector-grid combined inland water surface floater batch identification and extraction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110563234.7A CN113240026B (en) | 2021-05-24 | 2021-05-24 | Vector-grid combined inland water surface floater batch identification and extraction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113240026A CN113240026A (en) | 2021-08-10 |
| CN113240026B true CN113240026B (en) | 2022-03-25 |
Family
ID=77138383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110563234.7A Active CN113240026B (en) | 2021-05-24 | 2021-05-24 | Vector-grid combined inland water surface floater batch identification and extraction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113240026B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1854757A (en) * | 2005-04-28 | 2006-11-01 | 中国科学院遥感应用研究所 | Remote-sensing imaging set interpretation system method |
| CN102004922A (en) * | 2010-12-01 | 2011-04-06 | 南京大学 | High-resolution remote sensing image plane extraction method based on skeleton characteristic |
| CN104992140A (en) * | 2015-05-27 | 2015-10-21 | 上海海事大学 | Sea surface abnormal floating object detecting method based on remote sensing image |
| CN108388916A (en) * | 2018-02-26 | 2018-08-10 | 武汉大学 | A kind of water body floating material automatic identifying method and system based on artificial intelligence |
| US10055648B1 (en) * | 2015-04-16 | 2018-08-21 | Bae Systems Information And Electronic Systems Integration Inc. | Detection, classification, and tracking of surface contacts for maritime assets |
| CN108846402A (en) * | 2018-05-25 | 2018-11-20 | 南京师范大学 | The terraced fields raised path through fields based on multi-source data automates extracting method |
| CN109214270A (en) * | 2018-07-13 | 2019-01-15 | 中国地质调查局南京地质调查中心 | Doubtful illegal land used information rapid extracting method based on unmanned plane image |
| CN109636758A (en) * | 2018-12-15 | 2019-04-16 | 四创科技有限公司 | A kind of floating on water object detecting method based on space-time dynamic operator |
| CN110147779A (en) * | 2019-05-27 | 2019-08-20 | 宁夏云图勘测规划有限公司 | A kind of method of remote sensing image City Building function classification |
| CN110188632A (en) * | 2019-05-14 | 2019-08-30 | 苏州嘉奕晟中小企业科技咨询有限公司 | A kind of land used information census data processing system |
| CN110414334A (en) * | 2019-06-20 | 2019-11-05 | 浙江大学 | A kind of smart water quality recognition methods maked an inspection tour based on unmanned plane |
| CN110473205A (en) * | 2019-07-10 | 2019-11-19 | 北京吉威数源信息技术有限公司 | Remote sensing image information extracting method and system based on arrow bar phantom |
| CN110956101A (en) * | 2019-11-19 | 2020-04-03 | 广东省城乡规划设计研究院 | Remote sensing image yellow river ice detection method based on random forest algorithm |
| CN111079724A (en) * | 2020-03-25 | 2020-04-28 | 速度时空信息科技股份有限公司 | Unmanned aerial vehicle-based sea floating garbage identification method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7916933B2 (en) * | 2007-01-18 | 2011-03-29 | Northrop Grumman Systems Corporation | Automatic target recognition system for detection and classification of objects in water |
-
2021
- 2021-05-24 CN CN202110563234.7A patent/CN113240026B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1854757A (en) * | 2005-04-28 | 2006-11-01 | 中国科学院遥感应用研究所 | Remote-sensing imaging set interpretation system method |
| CN102004922A (en) * | 2010-12-01 | 2011-04-06 | 南京大学 | High-resolution remote sensing image plane extraction method based on skeleton characteristic |
| US10055648B1 (en) * | 2015-04-16 | 2018-08-21 | Bae Systems Information And Electronic Systems Integration Inc. | Detection, classification, and tracking of surface contacts for maritime assets |
| CN104992140A (en) * | 2015-05-27 | 2015-10-21 | 上海海事大学 | Sea surface abnormal floating object detecting method based on remote sensing image |
| CN108388916A (en) * | 2018-02-26 | 2018-08-10 | 武汉大学 | A kind of water body floating material automatic identifying method and system based on artificial intelligence |
| CN108846402A (en) * | 2018-05-25 | 2018-11-20 | 南京师范大学 | The terraced fields raised path through fields based on multi-source data automates extracting method |
| CN109214270A (en) * | 2018-07-13 | 2019-01-15 | 中国地质调查局南京地质调查中心 | Doubtful illegal land used information rapid extracting method based on unmanned plane image |
| CN109636758A (en) * | 2018-12-15 | 2019-04-16 | 四创科技有限公司 | A kind of floating on water object detecting method based on space-time dynamic operator |
| CN110188632A (en) * | 2019-05-14 | 2019-08-30 | 苏州嘉奕晟中小企业科技咨询有限公司 | A kind of land used information census data processing system |
| CN110147779A (en) * | 2019-05-27 | 2019-08-20 | 宁夏云图勘测规划有限公司 | A kind of method of remote sensing image City Building function classification |
| CN110414334A (en) * | 2019-06-20 | 2019-11-05 | 浙江大学 | A kind of smart water quality recognition methods maked an inspection tour based on unmanned plane |
| CN110473205A (en) * | 2019-07-10 | 2019-11-19 | 北京吉威数源信息技术有限公司 | Remote sensing image information extracting method and system based on arrow bar phantom |
| CN110956101A (en) * | 2019-11-19 | 2020-04-03 | 广东省城乡规划设计研究院 | Remote sensing image yellow river ice detection method based on random forest algorithm |
| CN111079724A (en) * | 2020-03-25 | 2020-04-28 | 速度时空信息科技股份有限公司 | Unmanned aerial vehicle-based sea floating garbage identification method |
Non-Patent Citations (2)
| Title |
|---|
| 一种改进SLIC分割的多尺度面向对象CVA遥感影像变化检测方法;李语旻 等;《甘肃科学学报》;20200819(第04期);第3-10页 * |
| 基于SSD深度网络的河道漂浮物检测技术研究;唐小敏等;《计算机技术与发展》;20200910(第09期);第160-164页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113240026A (en) | 2021-08-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109583369B (en) | Target identification method and device based on target area segmentation network | |
| WO2021243743A1 (en) | Deep convolutional neural network-based submerged oil sonar detection image recognition method | |
| CN111476120B (en) | Unmanned aerial vehicle intelligent ship water gauge identification method and device | |
| WO2023039959A1 (en) | Remote sensing image marine and non-marine area segmentation method based on pyramid mechanism | |
| CN104992172B (en) | Port remote sensing image shore ship detection method based on coastal outburst and different area scanning | |
| CN110287837A (en) | Sea obstacle detection method based on prior estimate network and space constraint mixed model | |
| CN112508079B (en) | Fine identification method, system, equipment, terminal and application of ocean frontal surface | |
| CN109284663A (en) | A kind of sea obstacle detection method based on normal state and uniform Mixture Distribution Model | |
| CN113538559A (en) | Extraction method of offshore aquaculture raft extraction index based on hyperspectral remote sensing image | |
| CN112734729A (en) | Water gauge water level line image detection method and device suitable for night light supplement condition and storage medium | |
| CN110569733B (en) | Lake long time sequence continuous water area change reconstruction method based on remote sensing big data platform | |
| CN113469097B (en) | Multi-camera real-time detection method for water surface floaters based on SSD network | |
| Ren et al. | Detection of SST fronts from a high-resolution model and its preliminary results in the south China sea | |
| CN113344148A (en) | Marine ship target identification method based on deep learning | |
| CN113240026B (en) | Vector-grid combined inland water surface floater batch identification and extraction method | |
| Zou et al. | Maritime target detection of intelligent ship based on faster R-CNN | |
| CN110751077B (en) | Optical remote sensing picture ship detection method based on component matching and distance constraint | |
| CN112966558A (en) | Port automatic identification method and system based on optimized SSD target detection model | |
| CN112101250A (en) | Method for detecting offshore ship target based on context semantic perception | |
| CN111860534A (en) | SAR image oil spill detection method based on image significance analysis | |
| Zhang et al. | FRS-Net: An efficient ship detection network for thin-cloud and FOG-covered high-resolution optical satellite imagery | |
| CN113780117B (en) | Method for rapidly identifying and extracting relevant parameters of estuary plume outline | |
| CN115797792A (en) | Distance vertex angle rule-based Huang Hailu tidal distribution area and drift prediction initial field manufacturing method thereof | |
| Liu et al. | Water extraction on the hyperspectral images of gaofen-5 satellite using spectral indices | |
| CN111639623B (en) | Multi-scale ship-enterprise scene recognition and extraction method combined with space distance constraint |
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 |