CN107504923B - Kelp culture area monitoring method integrating remote sensing image and extension rope information - Google Patents
Kelp culture area monitoring method integrating remote sensing image and extension rope information Download PDFInfo
- Publication number
- CN107504923B CN107504923B CN201710660021.XA CN201710660021A CN107504923B CN 107504923 B CN107504923 B CN 107504923B CN 201710660021 A CN201710660021 A CN 201710660021A CN 107504923 B CN107504923 B CN 107504923B
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- kelp
- area
- culture area
- resolution
- 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
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/28—Measuring arrangements characterised by the use of optical techniques for measuring areas
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
Abstract
The invention discloses a kelp culture area monitoring method integrating remote sensing images and rope extending information, which comprises the following steps of: acquiring a high-resolution remote sensing image of a target area, and preprocessing the acquired remote sensing image; classifying the preprocessed remote sensing images, and identifying the kelp culture area to obtain the longline culture information of the kelp culture area, wherein the longline culture information comprises the length and the width of each longline culture area; obtaining the rope extending interval information of an actual kelp culture area; calculating the number of extension ropes of each extension rope culture area, and obtaining the total length of the kelp culture extension ropes in the area by combining the rope length; dividing the total length of the extension ropes of the kelp culture area by 1000 meters to obtain the actual area of kelp culture; the method has the characteristics of accurate result, convenient operation, economy and high efficiency, provides a brand-new method for the real-time acquisition and large-range dynamic monitoring of the kelp culture area, and is suitable for being applied to relevant management departments, enterprises and public institutions.
Description
Technical Field
The invention relates to the field of ocean remote sensing information, in particular to a method for monitoring the kelp culture area by integrating remote sensing images and elongation rope information.
Background
The seaweed cultivation industry in China starts in the 50 th of the 20 th century, and through the development of more than 60 years, the large-scale seaweed yield in China is the first world at present and accounts for more than half of the total world yield (FAO 2016). Wherein, the yield of the artificially cultured algae accounts for about 98 percent of the total yield of the algae (Chinese fishery statistics yearbook). With the support of government policies, market demands, the change of climate environment, the change of culture structure and the like, the culture area and the yield of the large-sized seaweed are obviously changed, wherein the culture area is increased by more than 7 times, and the yield is also increased by nearly 9 times (year of Chinese fishery statistics). The traditional modes of field investigation, gradual reporting and the like cannot meet the requirement of quickly and accurately acquiring the seaweed cultivation condition. Satellite remote sensing has the advantages of large range, long time, high efficiency, economy and the like, is suitable for large-area long-time monitoring, and is increasingly used in monitoring of coastal zone environments and resources. Therefore, applying high and new technologies such as remote sensing to the large-scale seaweed area monitoring has great significance for understanding the current situation, development trend, global climate change and the like of the seaweed breeding industry.
There are many kinds of large-sized seaweeds, and the common culture categories in China include kelp, sargassum fusiforme, wakame seaweed, laver and the like, which are all health foods rich in nutrition. The cultivated macroalgae have a wide market in east asia and south east asia, and the european and american market is also growing rapidly. In these common cultivated macroalgae, the cultivated area and yield of kelp are nationwide first and are mainly distributed in the northern sea area. The traditional method for acquiring the kelp culture area and yield is that each farmer reports the area and yield step by step from villages, towns and the like and summarizes the area and yield to counties (regions), cities, provinces and the like, and the method has the following defects: 1) a severe lag in time, typically several months after harvest, before relevant data information can be obtained; 2) the unreliability of the data can be influenced by human subjective factors in the process of reporting step by step, and different statistical modes exist in different areas, so that accurate and uniform standard data are difficult to obtain; 3) the technical content is low, and more manpower, material resources and financial resources are needed. Based on this, a new method and technology for obtaining the relevant information of the cultivation area, the yield and the like of the kelp are urgently needed.
The remote sensing information technology can objectively and detailedly acquire the ground spectral information in a short time and in a large range. The large-scale seaweed has spectral information similar to land vegetation, the culture area has specific spatial texture information, and the characteristics can be objectively and clearly reflected in the remote sensing image, so that a foundation is provided for extracting and monitoring the kelp culture area from seawater. The kelp is artificially cultured in a specific mode that kelp seedling seeds are fixed in a extending rope and then float on the sea surface to grow by utilizing a float valve. The area of the kelp cultivation is generally calculated according to the total length of the extension rope. The length information of the extension rope and the density information between the extension ropes are different in different culture areas, so that the remote sensing image and the extension rope information need to be integrated to obtain an accurate kelp culture area.
Disclosure of Invention
The invention aims to provide a kelp culture area monitoring method integrating remote sensing images and elongation information, which has the characteristics of accurate result, convenience in operation, economy, high efficiency and the like, and provides a brand-new method for real-time acquisition and large-range dynamic monitoring of kelp culture area.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows: a method for monitoring the kelp culture area by integrating remote sensing images and elongation rope information comprises the following steps:
(1) acquiring a high-resolution remote sensing image of a target area, and preprocessing the acquired remote sensing image;
(2) classifying the preprocessed remote sensing images, and identifying the kelp culture area to obtain the longline culture information of the kelp culture area, wherein the longline culture information comprises the length and the width of each longline culture area;
(3) obtaining the information of the distance between the extension ropes of the kelp attached to the actual kelp culture area;
(4) dividing the average length of each long rope culture area obtained after classification in the step (2) by the spacing distance of the long ropes in the step (3) to obtain the number of the long ropes of each long rope culture area, and multiplying the width of the long rope culture area obtained in the step (2) by the number of the long ropes to obtain the total length of the long ropes in the long rope culture area; calculating the total length of the extension ropes in each extension rope culture area, thereby obtaining the total length of the extension ropes in the whole kelp culture area;
(5) and (5) dividing the total length of the extension ropes of the whole kelp culture area obtained in the step (4) by 1000 meters to obtain the actual kelp culture area.
Further, in the step (1), the high-resolution remote sensing image may be one of a high-resolution first-order remote sensing image with a resolution of 16 meters, a SPOT5, ALOS, a resource 3 satellite remote sensing image with a resolution of 2.5 meters, a SPOT6 remote sensing image with a resolution of 1.5 meters, an IKONOS and high-resolution second-order remote sensing image with a resolution of 1 meter, and a sub-meter-level QuickBird, GeoEye, WorldView, and other remote sensing images.
Further, the high-resolution remote sensing image is characterized in that the pixel size of the high-resolution remote sensing image is smaller than the distance between two adjacent kelp culture extension ropes according to the actual situation.
The kelp cultivation takes the extension ropes as a unit, the lengths of the extension ropes are different, the specifications of different places are different, namely 8 meters, 10 meters, 50 meters, 60 meters and the like, but the lengths of the extension ropes in the same cultivation area are basically consistent. In order to improve the precision of remote sensing identification and obtain accurate number of extension ropes, the (spatial) resolution of a remote sensing image should be smaller than the distance between the extension ropes. Based on this, the image adopted by the invention is a high-resolution remote sensing image.
Further, in the step (1), the acquisition time of the high-resolution remote sensing image is within the growth period of the kelp, generally between 11 months and 5 months in the next year. In the middle and last ten days of 3-4 months, the kelp tends to grow, and the kelp has obvious spectral reflection characteristics in the period, so that the extraction of a culture area in a remote sensing image is facilitated.
Further, in the step (1), the remote sensing image is first preprocessed by using general remote sensing image processing software, such as enii or ERDAS.
Further, in the step (1), preprocessing is performed on the remote sensing image, and the preprocessing includes geometric correction, radiation correction and atmospheric correction. If the remote sensing image contains a full-color waveband, image fusion can be carried out to improve the spatial resolution of the remote sensing image. If the research area is only a local area in the image, a small-range image can be obtained by processing methods such as image cropping and masking, and the research area can be further locked.
Wherein the geometric correction is based on high-precision digital topographic map or ground geographic data.
And selecting a proper algorithm according to the actual conditions of different images for radiation correction and atmospheric correction.
The image fusion fuses the panchromatic wave band and the multispectral wave band to obtain the multispectral remote sensing image with higher spatial resolution.
The image is cut to obtain a research area, the research range is reduced, the mask utilizes the reflectivity difference of seawater and land in a green wave band and a near infrared wave band to select a normalized water body index (NDWI), the sea and the land are separated, a land area on the shore is masked, and a kelp culture area is an interested area.
Further, in the step (2), a pixel-based supervision classification method is adopted for classifying the preprocessed remote sensing images, and specifically the following steps are adopted:
firstly, the images are visually read, and a general kelp culture area is determined according to priori knowledge and by combining image characteristics. The kelp cultivation area generally shows a rectangle with ink green regularly arranged on the offshore on a true color image.
And selecting samples of the kelp culture area and the seawater area on the image according to the visual interpretation result. And after the initial selection of the sample is completed, calculating the separability and evaluating the sample. If the degree of separability is low, the samples can be adjusted according to actual conditions. The final sample is required to be uniformly distributed on the image, representative and high in separability.
The supervision classifier can be selected from classifiers such as a parallelepiped, a minimum distance, a mahalanobis distance, a maximum likelihood, a support vector machine, a neural network and the like according to actual conditions. If the image quality is high and the difference between the kelp culture area and the seawater is obvious, classifiers based on traditional statistical analysis can be selected, including classifiers such as a parallelepiped, a minimum distance, a mahalanobis distance, a maximum likelihood and the like. Such classifiers are fast to execute. If the image quality is low and the difference between the kelp culture area and the sea water is not obvious, classifiers based on a neural network or pattern recognition can be selected, including classifiers such as a neural network and a support vector machine. Such classifiers have high classification accuracy but are slow to execute.
And (4) introducing the samples into a classifier for classification, and evaluating classification results by using parameters such as classification producer precision, user precision, Kappa coefficient and the like.
In the step (3), the distance between the extension ropes of the culture area can be obtained in two ways: firstly, the measurement is carried out by measuring or inquiring the foster user on the spot, and secondly, the measurement is carried out after the remote sensing image with higher resolution is visually interpreted.
The field measurement is accurate, but time and labor are wasted, so that the method is suitable for the conditions of small research area and easy operation; the method is convenient and easy to implement, but has certain visual interpretation error and measurement error, and is suitable for large range and within the tolerance range of precision.
The invention has the following beneficial effects:
1. the invention integrates high-resolution remote sensing image information and extension rope information, calculates the kelp culture area, and can carry out large-scale, rapid and accurate monitoring on coastal kelp culture in China, thereby realizing macroscopic, dynamic and real-time monitoring on kelp culture distribution and area.
2. The method integrates remote sensing information and on-site kelp culture information, and quickly and accurately acquires the kelp culture area. Kelp seedlings are attached to the rope and grow near the sea surface, the cultivation scale is usually defined by the length of the extension rope, the lengths of the ropes in various cultivation areas are different, such as 6 meters, 8 meters, 50 meters, 60 meters and the like, and the actual lengths of the extension ropes in different cultivation areas can be accurately acquired by a remote sensing classification technology. And because the diameter of the extension rope is centimeter-level, the diameter is limited by the spatial resolution of the remote sensing image, and a single extension rope cannot be directly identified in the remote sensing image, so that the number of the extension ropes is counted. Therefore, the current high-resolution remote sensing image can only obtain more accurate length and width information of the culture area, and the actual number of the extension ropes is calculated by utilizing the distance between two extension ropes. The method combines the remote sensing information with the non-remote sensing information to obtain the accurate kelp culture area. However, with the gradual improvement of the spatial resolution of the remote sensing image, if a sub-meter or decimeter high-resolution image is obtained in time, the step of obtaining the number of the stay ropes by using the breeding distance can be omitted, and the number of the stay ropes can be counted by directly using the classification result, so that the kelp breeding area is calculated.
3. The method has the advantages of accurate result, good universality and simple and convenient operation, is suitable for coastal large-scale kelp culture areas in China, can be applied to departments such as agriculture, oceans and the like, and provides important culture information for farmers, managers and decision makers in time.
Drawings
FIG. 1 is a schematic diagram of the basic process of the present invention;
FIG. 2 is a detailed flow diagram of an embodiment of the present invention;
FIG. 3 is a remote sensing image of a sea tangle cultivation area of Rongcheng city of Weihai city, Shandong province in accordance with the present invention;
FIG. 4 is a graph showing the classification results of the sea tangle cultivation areas of Rongcheng City of Weihai City, Shandong province according to the embodiment of the present invention.
Detailed Description
In order to describe the present invention more specifically, the following detailed description of the embodiments of the present invention is made with reference to the accompanying drawings.
As shown in fig. 1 and 2, the implementation steps of the method for monitoring the area of the kelp culture by integrating the high-resolution remote sensing image and the elongation information provided by the invention are as follows:
(1) and acquiring a clear high-resolution remote sensing image of the target area.
In this embodiment, a cultivation area of Rong-Cheng-Zostera Marina of Weihai city, Shandong province is selected as the area to be monitored. It is known that the honor market is reputed by the reputations of the country of Chinese kelp, the annual kelp yield accounts for about 50 percent of the total national yield, and the kelp occupies the first national yield for many years. The area of a kelp breeding area in the district is up to one hundred thousand mu, one million tons of fresh kelp are produced annually, and the breeding area and the yield are the first nationwide. The annual kelp production accounts for more than eight percent of the total production of the whole province and four percent of the total production of the whole country, and is a product with remarkable geographical advantages.
Because a clear high-resolution image of a research area in a kelp culture period cannot be obtained, the multispectral remote sensing image adopted in the embodiment is a Landsat-8 remote sensing image of 3, month and 8 days in 2017, a panchromatic waveband of 15 m resolution is fused with a multispectral waveband of 30 m resolution to obtain the multispectral image of 15 m resolution, the resolution can meet the requirement of the high-resolution remote sensing image, the fused image comprises seven wavebands such as blue light, green light, red light and near infrared, and the image of the research area is shown in figure 3.
(2) And preprocessing the remote sensing image to obtain a kelp culture sea area, classifying the preprocessed image, and calculating the length and the width of the kelp culture area. Firstly, the digital topographic map of the area is used for carrying out geometric correction on the Landsat-8 image. Then, radiation correction and FLAASH (Fast Line-of-Sight Atmospheric Analysis of spectral Hypercubes) Atmospheric correction are performed, and the image is cropped to distinguish land and sea areas.
1500 kelp pixels and 1000 seawater pixels are randomly selected in the kelp culture sea area respectively as samples, then a support vector machine classifier is selected for classification, kelp in a research area is extracted, and the classification result is shown in figure 4.
And the obtained classification result is exported in a vector format, opened in ArcGIS software, and the length and the width of the kelp culture area are measured to obtain the average length of 1000m and the average width of 90 m.
(3) Acquiring the spacing length of extension ropes of an actual kelp culture area; and measuring the distance between the kelp culture extension ropes in the region in Google Earth, randomly measuring the distance between 20 groups of extension ropes in the research region, and taking the average distance between the obtained extension ropes as 4 m.
(4) Calculating the number of extension ropes of each extension rope culture area, and obtaining the total length of the kelp culture extension ropes in the area by combining the rope length; and (3) dividing the length of the cultivation area by the distance between the extension ropes according to the step (3) of which the distance is 4m to obtain a total of 250 extension ropes in the cultivation area, and finally multiplying the number of the extension ropes by the length of the extension ropes to obtain the total length of 22500m of the extension ropes in the cultivation area, wherein the width of the kelp cultivation area obtained in the step (2) is about 90m, namely the length of the extension ropes is 90 m.
(5) According to literature records, in local fishery statistics, the floating valve type cultured large-scale seaweeds such as kelp are counted by 1000m extension ropes to be one mu of culture area, so that the total length of the extension ropes in a kelp culture area is divided by 1000m to obtain the actual area of the kelp culture area of 22.5 mu.
The above description is only one embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiment, and all technical solutions belonging to the principle of the present invention belong to the protection scope of the present invention. It will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the principles of the invention and these are intended to be within the scope of the invention.
Claims (3)
1. A method for monitoring the kelp culture area by integrating remote sensing images and elongation rope information is characterized by comprising the following steps:
(1) acquiring a high-resolution remote sensing image of a target area, and preprocessing the acquired remote sensing image;
in the step (1), the image source for obtaining the high-resolution remote sensing image is a multispectral remote sensing image with the spatial resolution higher than 20 meters and has infrared band spectrum information;
the pixel size of the high-resolution remote sensing image is smaller than the distance between two adjacent kelp culture extension ropes;
the pretreatment comprises the following treatment modes: geometric correction, radiation correction and atmospheric correction;
(2) classifying the preprocessed remote sensing images, and identifying the kelp culture area to obtain the longline culture information of the kelp culture area, wherein the longline culture information comprises the length and the width of each longline culture area; classifying the remote sensing images by adopting a method combining visual interpretation and supervision classification, and identifying a kelp culture area;
(3) obtaining the information of the distance between the extension ropes of the kelp attached to the actual kelp culture area;
(4) dividing the average length of each long rope culture area obtained after classification in the step (2) by the spacing distance of the long ropes in the step (3) to obtain the number of the long ropes of each long rope culture area, and multiplying the width of the long rope culture area obtained in the step (2) by the number of the long ropes to obtain the total length of the long ropes in each long rope culture area; obtaining the total length of the extension ropes of the whole kelp culture area based on the calculated total length of the extension ropes in each extension rope culture area;
(5) and (5) dividing the total length of the extension ropes of the whole kelp culture area obtained in the step (4) by 1000 meters to obtain the actual kelp culture area.
2. The method for monitoring the kelp culture area by integrating the remote sensing image and the extension rope information according to claim 1, wherein the high-resolution remote sensing image can be one of a 16-meter-resolution high-resolution one-number remote sensing image, a 2.5-meter-resolution SPOT5, a 2.5-meter-resolution ALOS, a 2.5-meter-resolution resource 3-number satellite remote sensing image, a 1.5-meter-resolution SPOT6 remote sensing image, a 1-meter-resolution IKONOOS, a 1-meter-resolution high-resolution two-number remote sensing image, a sub-meter-level QuickBird, a sub-meter-level GeoEye or a sub-meter-level WorldView remote sensing image.
3. The method for monitoring the aquaculture area of the kelp by integrating the remote sensing image and the elongation rope information according to claim 1, wherein in the step (1), the preprocessing further comprises the following processing modes: image fusion, image cropping and masking.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710660021.XA CN107504923B (en) | 2017-08-04 | 2017-08-04 | Kelp culture area monitoring method integrating remote sensing image and extension rope information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710660021.XA CN107504923B (en) | 2017-08-04 | 2017-08-04 | Kelp culture area monitoring method integrating remote sensing image and extension rope information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107504923A CN107504923A (en) | 2017-12-22 |
| CN107504923B true CN107504923B (en) | 2020-03-06 |
Family
ID=60689094
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710660021.XA Active CN107504923B (en) | 2017-08-04 | 2017-08-04 | Kelp culture area monitoring method integrating remote sensing image and extension rope information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107504923B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108875659B (en) * | 2018-06-26 | 2022-04-22 | 上海海事大学 | Sea chart cultivation area identification method based on multispectral remote sensing image |
| CN109029366B (en) * | 2018-07-02 | 2021-01-08 | 中国科学院南京地理与湖泊研究所 | Method for measuring horizontal drift rate of algae spots through aircraft shooting |
| CN109063605A (en) * | 2018-07-16 | 2018-12-21 | 中国水产科学研究院南海水产研究所 | A kind of oyster row's oyster frame cultivation measuring method, system and device for aquaculture |
| CN109359639A (en) * | 2018-12-19 | 2019-02-19 | 美丽国土（北京）生态环境工程技术研究院有限公司 | Strand cultured area investigation method and device |
| CN113538559B (en) * | 2021-07-02 | 2022-02-18 | 宁波大学 | Extraction method of offshore aquaculture raft extraction index based on hyperspectral remote sensing image |
| CN114037902B (en) * | 2021-10-28 | 2023-09-12 | 江苏海洋大学 | Inversion method for extracting and identifying suspended sediment in Porphyra yezoensis cultivation area |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4561972B2 (en) * | 2004-08-06 | 2010-10-13 | 株式会社サタケ | Simple measurement method for damaged area of farmland |
| CN101599120B (en) * | 2009-07-07 | 2012-01-25 | 华中科技大学 | Identification method of remote sensing image building |
| CN102565810B (en) * | 2011-12-30 | 2013-11-06 | 武汉大学 | Method for extracting land utilization landmark boundary outline on remote sensing image |
| CN104374713B (en) * | 2014-12-03 | 2017-04-19 | 中国科学院南京地理与湖泊研究所 | MODIS remote sensing monitoring method for vertical distribution pattern of eutrophic lake water algae |
| CN106123812A (en) * | 2016-08-14 | 2016-11-16 | 覃泽林 | The method and device of relief surface sugarcane acreage is obtained based on remote sensing image |
| CN107527364A (en) * | 2017-07-25 | 2017-12-29 | 浙江大学 | A kind of seaweed growing area monitoring method based on remote sensing images and lace curtaining information |
-
2017
- 2017-08-04 CN CN201710660021.XA patent/CN107504923B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN107504923A (en) | 2017-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107504923B (en) | Kelp culture area monitoring method integrating remote sensing image and extension rope information | |
| Sun et al. | Plant species classification in salt marshes using phenological parameters derived from Sentinel-2 pixel-differential time-series | |
| Lenney et al. | The status of agricultural lands in Egypt: the use of multitemporal NDVI features derived from Landsat TM | |
| CN109086826B (en) | Wheat drought identification method based on image deep learning | |
| CN111598045B (en) | Remote sensing farmland change detection method based on object spectrum and mixed spectrum | |
| CN108195767B (en) | Estuary wetland foreign species monitoring method | |
| CN111738066B (en) | Grid late rice sheath blight disease habitat evaluation method integrating multisource remote sensing information | |
| CN112800973A (en) | Spartina alterniflora extraction method based on vegetation phenological feature decision | |
| CN109977991A (en) | Forest resourceies acquisition method based on high definition satellite remote sensing | |
| Zeng et al. | A phenology-based vegetation index classification (PVC) algorithm for coastal salt marshes using Landsat 8 images | |
| CN115641412A (en) | Hyperspectral data-based three-dimensional semantic map generation method | |
| Chen et al. | 3D model construction and ecological environment investigation on a regional scale using UAV remote sensing | |
| CN113570273A (en) | Spatial method and system for irrigation farmland statistical data | |
| CN114049564A (en) | Pine wood nematode disease grade prediction model construction method based on hyperspectral remote sensing image | |
| CN107437262B (en) | Crop planting area early warning method and system | |
| CN111832480A (en) | Remote sensing identification method for rape planting area based on spectral characteristics | |
| Ormeci et al. | Identification of crop areas Using SPOT–5 data | |
| Xu et al. | Spatiotemporal distribution of cage and raft aquaculture in China's offshore waters using object-oriented random forest classifier | |
| Xie et al. | Object-oriented random forest classification for Enteromorpha prolifera detection with SAR images | |
| CN115527108A (en) | Method for rapidly identifying water and soil loss artificial disturbance plots based on multi-temporal Sentinel-2 | |
| CN114708490A (en) | Rice planting extraction and multiple cropping index monitoring method, system, terminal and storage medium | |
| Zhe et al. | Dynamics of coastal aquaculture ponds in Vietnam from 1990 to 2015 using Landsat data | |
| CN111832486B (en) | Large-scale intertidal vegetation classification method based on synthetic aperture radar | |
| Dehghani | Study of changes in land use and land cover in and around the Chah Nimeh water reservoir in Sistan and Baluchistan Province, Iran | |
| ZHANG et al. | Object-oriented crop classification based on UAV remote sensing imagery |
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 |