CN115063437A - Mangrove canopy visible light image index characteristic analysis method and system - Google Patents
Mangrove canopy visible light image index characteristic analysis method and system Download PDFInfo
- Publication number
- CN115063437A CN115063437A CN202210678055.2A CN202210678055A CN115063437A CN 115063437 A CN115063437 A CN 115063437A CN 202210678055 A CN202210678055 A CN 202210678055A CN 115063437 A CN115063437 A CN 115063437A
- Authority
- CN
- China
- Prior art keywords
- visible light
- image
- light image
- vegetation
- mangrove
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10036—Multispectral image; Hyperspectral image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30188—Vegetation; Agriculture
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Image Processing (AREA)
Abstract
A mangrove canopy visible light image index feature analysis method and system, the method includes the following steps: acquiring a mangrove canopy visible light image dataset, meteorological data and tidal data; analyzing and obtaining the critical tide height of the mangrove forest submerged by the seawater based on the combination of the visible light image data set and the tide data; screening out visible light images below the critical tide height, and carrying out image segmentation on the visible light images to obtain green vegetation area images in the visible light images; and based on the green vegetation region image, performing visible light image index calculation and vegetation change trend simulation to obtain visible light image index characteristics and vegetation change trend. The system comprises: the tidal height calculating system comprises an image collecting module, a tidal height calculating module, an image segmenting module and an index calculating module. The method combines image processing and machine learning technologies, provides a method for automatic and continuous monitoring of mangrove vegetation conditions, and provides technical support for real-time, rapid and accurate estimation of mangrove vegetation growth parameters.
Description
Technical Field
The application relates to the field of image processing, in particular to a mangrove forest canopy visible light image index characteristic analysis method and system.
Background
The mangrove forest ecosystem has the characteristics of high productivity, high return rate, high decomposition rate and strong biomass and carbon storage capacity, can play the roles of preventing wind waves, preventing and treating pollution and beautifying the coast, and has important ecological service function and social and economic values. Quantitative mangrove forest growth status monitoring can provide important data base for deep interpretation of mangrove forest ecosystem function. However, mangrove forest growing on the beach of coastal intertidal zone or river entrance is affected by periodical tide submergence, and the problems of high difficulty, long period, incomplete information and the like exist in the field investigation of growth and development conditions. The rapid development of the remote sensing technology provides a feasible technical means and method for large-scale mangrove forest dynamic monitoring, but the fixed access period of the satellite easily causes key information to be missing or insufficient. Digital camera RGB image shooting has been successfully applied to monitoring comprehensive information such as vegetation growth period, canopy structure, biomass and the like due to advantages of the digital camera RGB image shooting in the aspects of flexibility, low cost, stability and the like.
The image segmentation technology aims to divide an image containing complex ground feature spatial distribution information into different regions with specific semantic labels, and is the basis for developing vegetation monitoring by using near-terrestrial canopy RGB images. Various segmentation methods such as region, histogram thresholding, feature space clustering, edge detection, fuzzy artificial neural network, deep learning and the like have been developed at present. Researchers have constructed various visible vegetation indexes such as NDYI (Normalized Difference yellow index), GLA (Green Leaf Algorithm), VARI (VisibleAtmosphericalagent index), NGRDI (Normalized green-redifference index) and the like based on RGB different color channels for vegetation change monitoring. At present, the RGB image of the unmanned aerial vehicle has an initial effect on mangrove forest vegetation segmentation and canopy structure inversion, but the feasibility of the RGB image obtained from the foundation in mangrove forest growth condition monitoring still needs to be clear, the effectiveness of various segmentation algorithms on mangrove forest vegetation information extraction, and the applicability of various visible light vegetation indexes in mangrove forest growth condition monitoring are all rarely studied.
Disclosure of Invention
The application provides a mangrove canopy visible light image index feature analysis method and system, which are used for obtaining a mangrove canopy visible light image data set, meteorological data and tidal data, carrying out visible light image index calculation and vegetation change trend simulation based on the combination of the visible light image data set and the tidal data, and obtaining visible light image index features and vegetation change trends.
In order to achieve the above object, the present application provides the following solutions:
a mangrove canopy visible light image index feature analysis method comprises the following steps:
s1, acquiring a mangrove canopy visible light image data set and tide data;
s2, obtaining the critical tide height of the mangrove forest submerged by the seawater based on the visible light image data set and the tide data;
s3, screening out a visible light image lower than the critical tide height, and performing image segmentation on the visible light image to obtain a green vegetation area image in the visible light image;
and S4, based on the green vegetation region image, performing visible light image index calculation and vegetation change trend simulation to obtain visible light image index characteristics and vegetation change trend.
Preferably, the analysis method of the critical tidal height is as follows:
based on the visible light image dataset, by comparing the seawater immersed condition on the beach at the bottom of the image, finding out the image with a small amount of accumulated water or completely exposed beach and determining the shooting time;
and determining the critical tide height of the sea water flooding the mangrove forest in a tide table based on the shooting time.
Preferably, the image segmentation method includes:
by utilizing a machine learning segmentation algorithm, firstly generating a training sample by adopting unsupervised clustering, screening the training sample, and then classifying vegetation and background information by adopting a support vector machine to obtain the green vegetation region image.
Preferably, the green vegetation area image is optimized by adopting an NLM algorithm.
Preferably, the visible light index feature calculation method is as follows:
and after R, G, B color channel values of each pixel of the green vegetation area are extracted, averaging all pixels in the area, and then calculating the visible light vegetation index of the mangrove forest.
Preferably, the change trend of the vegetation growth over time is simulated by using a composite sine function to obtain the vegetation change trend, and the calculation formula is as follows:
VI＝a+b sin[2π(t day -c)/365]
wherein a, b and c are empirical coefficients, t day In the order of the days.
The application also provides a mangrove canopy visible light image index feature analysis system, includes: the tidal height calculating system comprises an image collecting module, a tidal height calculating module, an image segmenting module and an index calculating module;
the image collection module is connected with the tide height calculation module and is used for acquiring a mangrove canopy visible light image data set, meteorological data and tide data;
the tide height calculation module is also connected with the image segmentation module and is used for analyzing and obtaining the critical tide height of the mangrove forest submerged by the seawater based on the combination of the visible light image data set and the tide data;
the image segmentation module is also connected with the index calculation module and is used for screening out a visible light image lower than the critical tide height, and performing image segmentation on the visible light image to obtain a green vegetation area image in the visible light image;
the index calculation module is used for performing visible light image index calculation and vegetation change trend simulation based on the green vegetation region image to obtain visible light image index characteristics and vegetation change trend.
Preferably, the image segmentation module is further configured to perform NLM algorithm optimization on the green vegetation region image.
The beneficial effect of this application does:
the method combines image processing and machine learning technologies, provides an effective technical method for automatic and continuous monitoring of mangrove forest vegetation conditions, utilizes a foundation and an unmanned aerial vehicle platform to carry a multispectral camera to obtain multispectral and hyperspectral data, sets a sample prescription in a target area, collects plant physical and chemical property data, and enriches a ground data set; the camera parameters are set, the image correction method is improved, and the variation of the visible light image index can be reduced; a biomass, leaf area index and chlorophyll content prediction model based on the visible light image index is constructed, and technical support can be provided for real-time, rapid and accurate estimation of the mangrove vegetation growth parameters.
Drawings
In order to more clearly illustrate the technical solution of the present application, the drawings needed to be used in the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive exercise.
FIG. 1 is a schematic flow chart of a mangrove forest canopy visible light image index feature analysis method of the present application;
fig. 2 is a schematic structural diagram of a mangrove canopy visible light image index feature analysis system according to the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, the present application is described in further detail with reference to the accompanying drawings and the detailed description.
Example one
In the first embodiment, as shown in fig. 1, a mangrove forest canopy visible light image index feature analysis method selects an ecological meteorological observation test station of mangrove forest in north sea, which is located in the small bay of the national ocean science and technology park in north sea, guangxi. The research area belongs to subtropical monsoon climate, and is warm and moist all year round, the annual average precipitation is 1644mm, and the annual average temperature is 22.6 ℃. The total area of mangrove forest in observation area is about 5.5hm 2 The variety is mainly avicennia marina community and a small amount of Kandelia candel and Kalopanax pictus are mixed; the soil is mainly from gravelly fine sandy soil to coarse sandy soil, and the content of organic matters is low.
The visible light image data set is from a digital camera erected on a flux tower of an ecological weather observation station, the height from the ground is 6m, the model of the camera is ZQZ-TIM, a 1/1.8-inch CMOS sensor is adopted, the total pixels are about 644 ten thousand pixels, the aperture value F is 1.5-4.3, the optical zoom is 30 times, the digital zoom is 16 times, the wide dynamic effect is achieved, the image noise reduction function is added, the day/night image can be well displayed, the horizontal direction is continuously rotated by 360 degrees, the vertical direction is automatically turned by 180 degrees by-20 degrees to 90 degrees, the image is continuously monitored, and no monitoring blind area exists. And after the image acquisition is finished, the image can be uploaded to a cloud platform or imported into a computer for processing. The visible light image acquisition time is 8: 00-17: 00 per day, the interval time is 1h, and the image sequence is from 9/3 in 2018 to 8/31 in 2019. The meteorological data are from automatic meteorological observation equipment of an ecological meteorological observation station, and the observation elements comprise daily average air temperature, daily maximum air temperature, daily minimum air temperature, relative humidity and rainfall. The tide data is from a Chinese tide table (a northern harbor monitoring point) compiled by a national ocean information center, and the observation elements comprise tidal height every hour, tidal time and tidal height.
Through manual visual interpretation, the critical tide height of seawater invasion in the target area is judged by combining tide data, then a visible light image when the critical tide height is lower than the critical tide height is screened out, and finally an image with the maximum daily brightness is selected to represent the image of the day, wherein the brightness value of the visible light image is represented by the sum of R, G, B color channel values. The specific method for determining the critical tide height of mangrove forest flooded by seawater in the target area is as follows: (1) randomly selecting a visible light image data set flooded by seawater for 3 days every month; (2) the seawater invasion situation of the tidal flat at the bottom of the image is visually compared, the image with little accumulated water or completely exposed tidal flat is found out, and the shooting time of the image is determined as the invasion time of flood tide beginning or flood tide ending; (3) and determining the critical tide height of the mangrove forest flooded by the seawater in the tide table according to the time.
Based on a machine learning segmentation algorithm, firstly, a training sample is generated by adopting K-means unsupervised clustering, the sample is screened, and then, a Support Vector Machine (SVM) is adopted to classify vegetation and background information.
The probability of the dislocation part of the vegetation edge part is higher under the influence of factors such as illumination condition difference, imaging quality and the like. In order to reduce the phenomenon of blade edge error segmentation, Non-Local mean filtering (NLM) is introduced to optimize the segmented result. The NLM operator can protect a long and narrow structure similar to a vegetation blade, and the ambiguity of pixel segmentation of the edge part of the vegetation blade is eliminated by mutually enhancing non-adjacent pixels on the same structure in a certain neighborhood range. The principle of the NLM algorithm is as follows:
assuming that a noisy image is v ═ { v (a) | a ∈ a }, the image after denoising is
The weight value for each pixel a can be found by:
in the formula, w (a, b) represents the similarity (Gaussian weighted Euclidean distance) weight between the pixel a and the pixel b, and satisfies that w (a, b) is more than or equal to 0 and less than or equal to 1 and sigma b w (a, b) ═ 1, the expression is as follows:
in the formula (I), the compound is shown in the specification,
and the square of the Gaussian weighted distance between the pixel in the subblock with the pixel a as the center and the pixel in the subblock with the pixel b as the center is expressed for measuring the similarity between two pixel points, wherein a is standard deviation, v (N (a)) expresses a local subblock pixel set around a, and h is a filtering parameter.
And taking the manual on-site labeling result as a reference, and carrying out accuracy evaluation on the classified images obtained before and after filtering by the three segmentation algorithms, wherein an accuracy evaluation index Q seg And S r The calculation formula is as follows:
in the formula, a is a foreground (green vegetation) pixel set (p is 255) or background (information other than green vegetation) pixel set (p is 0) of the segmented image, B is a foreground pixel set (p is 255) or background pixel set (p is 0) obtained by artificially labeling the actual field, m and n are respectively the row number and column number of the image, i and j are respectively corresponding coordinates, the larger the values Qseg and Sr are, the higher the segmentation accuracy is, Qseg represents the consistency of the segmentation result between the background and the foreground, and Sr represents the consistency of the foreground segmentation result only.
After the segmentation of the green vegetation part in the visible light image is completed, R, G, B color channel values of each pixel of the green vegetation area are extracted, all pixels in the area are averaged, and then the mangrove forest visible light vegetation index is calculated, as shown in table 1.
TABLE 1
Note: r, G, B are red, green and blue band values, respectively, and r, g, b are normalized red, green and blue band values.
Vegetation change trend simulation: the change trend of vegetation growth over time is simulated by utilizing a composite sine function, and the calculation and the expression are as follows:
VI＝a+b sin[2π(t day -c)/365]
wherein a, b and c are empirical coefficients, t day In the order of the days.
The 10 visible light image indexes can be divided into two types according to the time sequence change characteristics, the first type is seasonal changes (collectively called seasonal indexes) which are quasi-synchronous with air temperature changes, the seasonal changes comprise ExG, ExGR, GLA, GMRVI, NDYI, RGBHI, VARI and VEG, and the index values are low in winter and spring and high in summer and autumn. The second category is the tendency of seasonal changes to oppose changes in air temperature over time (collectively referred to as anti-seasonal indices), and includes ExR and CIVE, which are low in summer and autumn and high in spring and spring, as opposed to seasonal indices.
The composite sine function can better simulate the annual period change of each visible light image index, and the correlation coefficient of each exponential simulation value and each observation value is between 0.430 and 0.643, wherein the VARI fitting effect is the best (R is 0.643), and the ExG fitting effect is the worst (R is 0.505). The fitting deviation of each exponential complete sequence is between 0.03% and 26.16%, wherein ExR (4.09%), VEG (1.73%) and CIVE (0.03%) fitting values have small deviation from observed values, and other exponential deviations are all larger than 17%.
The deviation difference between the analog value and the observed value of each index in different seasons is obvious, the deviation in spring is 0.02-17.98%, the deviation in summer is 0.04-39.97%, the deviation in autumn is 0.05-59.66%, and the deviation in winter is 0.02-22.05%. In comparison, the deviation between winter and spring is smaller, and the deviation between summer and autumn is larger.
Example two
In the second embodiment, the daily average temperature, the daily maximum air temperature, the daily minimum temperature, the relative humidity and the daily rainfall are selected as main meteorological factors, and the correlation between the meteorological factors and the optical image indexes of the mangrove canopy is analyzed, as shown in table 2. There is a high correlation between the respective visible light image indices, as shown in table 3, but the correlation between different visible light image indices and the respective meteorological factors is significantly different due to the differences in the constituent image bands and parameters. The 8 seasonal visible light image indexes of ExG, ExGR, GLA, GMRVI, NDYI, RGBHI, VARI and VEG are in positive correlation with the average air temperature, the highest air temperature, the lowest air temperature and the precipitation and in negative correlation with the relative humidity, and the correlation between the ExR anti-seasonal visible light image index and each meteorological factor is opposite to the seasonal visible image index. Wherein, the correlation between ExR, VARI, MGRVI and NGRDI and air temperature (average, highest and lowest) and relative humidity reaches a very significant level, while the correlation between NDYI and CIVE and air temperature and relative humidity is not significant. In the aspect of precipitation, the correlations between NDYI, GLA, RGBHI, CIVE and VEG reach a significant level, and the correlations between the indexes of the rest visible light images are not significant.
TABLE 2
Note: ns is that p is more than or equal to 0.05; p < 0.05; p <0.01
TABLE 3
EXAMPLE III
In the third embodiment, as shown in fig. 2, a mangrove canopy visible light image index feature analysis system includes: the tidal height calculating system comprises an image collecting module, a tidal height calculating module, an image segmenting module and an index calculating module; the image collection module is connected with the tide height calculation module and is used for acquiring a mangrove canopy visible light image dataset, meteorological data and tide data; the tide height calculation module is also connected with the image segmentation module and is used for analyzing and obtaining the critical tide height of the mangrove forest submerged by the seawater based on the combination of the visible light image data set and the tide data; the image segmentation module is also connected with the index calculation module and is used for screening out visible light images lower than the critical tide height, carrying out image segmentation on the visible light images to obtain green vegetation area images in the visible light images, and carrying out NLM algorithm optimization on the green vegetation area images to reduce false segmentation of blade edges; the index calculation module is used for performing visible light image index calculation and vegetation change trend simulation based on the green vegetation region image to obtain visible light image index characteristics and vegetation change trend.
The above-described embodiments are merely illustrative of the preferred embodiments of the present application, and do not limit the scope of the present application, and various modifications and improvements made to the technical solutions of the present application by those skilled in the art without departing from the spirit of the present application should fall within the protection scope defined by the claims of the present application.
Claims (8)
1. A mangrove canopy visible light image index feature analysis method is characterized by comprising the following steps:
s1, acquiring a mangrove canopy visible light image data set and tide data;
s2, obtaining the critical tide height of the mangrove forest submerged by the seawater based on the visible light image data set and the tide data;
s3, screening out a visible light image lower than the critical tide height, and performing image segmentation on the visible light image to obtain a green vegetation area image in the visible light image;
and S4, based on the green vegetation region image, performing visible light image index calculation and vegetation change trend simulation to obtain visible light image index characteristics and vegetation change trend.
2. The mangrove forest canopy visible light image index feature analysis method of claim 1, wherein the critical tidal height analysis method is:
based on the visible light image dataset, by comparing the seawater immersed condition on the beach at the bottom of the image, finding out the image with a small amount of accumulated water or completely exposed beach and determining the shooting time;
and determining the critical tide height of the sea water flooding the mangrove forest in a tide table based on the shooting time.
3. The mangrove forest canopy visible light image index feature analysis method of claim 1, wherein the image segmentation method is:
by utilizing a machine learning segmentation algorithm, firstly generating a training sample by adopting unsupervised clustering, screening the training sample, and then classifying vegetation and background information by adopting a support vector machine to obtain the green vegetation region image.
4. The mangrove forest canopy visible light image index feature analysis method of claim 3, wherein the green vegetation area image is optimized by NLM algorithm.
5. The mangrove forest canopy visible light image index feature analysis method according to claim 1, wherein the visible light index feature calculation method is:
and after R, G, B color channel values of each pixel of the green vegetation area are extracted, averaging all pixels in the area, and then calculating the visible light vegetation index of the mangrove forest.
6. The mangrove forest canopy visible light image index feature analysis method of claim 1, characterized in that the vegetation trend of change over time is simulated by using a compound sine function to obtain the vegetation trend, the calculation formula is as follows:
VI＝a+b sin[2π(t day -c)/365]
wherein a, b and c are empirical coefficients, t day In the order of the days.
7. A mangrove canopy visible light image index feature analysis system is characterized by comprising: the system comprises an image collection module, a tide height calculation module, an image segmentation module and an index calculation module;
the image collection module is connected with the tide height calculation module and is used for acquiring a mangrove canopy visible light image dataset, meteorological data and tide data;
the tide height calculation module is also connected with the image segmentation module and is used for analyzing and obtaining the critical tide height of the mangrove forest submerged by the seawater based on the combination of the visible light image data set and the tide data;
the image segmentation module is also connected with the index calculation module and is used for screening out a visible light image lower than the critical tide height, and performing image segmentation on the visible light image to obtain a green vegetation area image in the visible light image;
the index calculation module is used for performing visible light image index calculation and vegetation change trend simulation based on the green vegetation region image to obtain visible light image index characteristics and vegetation change trend.
8. The mangrove forest canopy visible light image index feature analysis system of claim 7, wherein the image segmentation module is further configured to perform NLM algorithm optimization on the green vegetation area image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210678055.2A CN115063437B (en) | 2022-06-16 | 2022-06-16 | Mangrove canopy visible light image index feature analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210678055.2A CN115063437B (en) | 2022-06-16 | 2022-06-16 | Mangrove canopy visible light image index feature analysis method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115063437A true CN115063437A (en) | 2022-09-16 |
| CN115063437B CN115063437B (en) | 2023-04-28 |
Family
ID=83201075
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210678055.2A Active CN115063437B (en) | 2022-06-16 | 2022-06-16 | Mangrove canopy visible light image index feature analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115063437B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116229263A (en) * | 2023-02-24 | 2023-06-06 | 广西壮族自治区气象科学研究所 | Vegetation growth disaster damage verification method based on foundation visible light image |
| CN117607070A (en) * | 2023-11-22 | 2024-02-27 | 广州双木林业有限公司 | Mangrove detection method, system, equipment and medium based on unmanned aerial vehicle |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109034026A (en) * | 2018-07-16 | 2018-12-18 | 中国科学院东北地理与农业生态研究所 | The mangrove extracting method and system in land and water region in a kind of remote sensing image |
| JP2019037198A (en) * | 2017-08-28 | 2019-03-14 | 東京電力ホールディングス株式会社 | Vegetation cover degree determination method and vegetation cover degree determination device |
| CN111275254A (en) * | 2020-01-17 | 2020-06-12 | 河海大学 | Method for predicting development trend of future intertidal zone area based on intertidal zone area change model |
| AU2020100917A4 (en) * | 2020-06-02 | 2020-07-09 | Guizhou Institute Of Pratacultural | A Method For Extracting Vegetation Information From Aerial Photographs Of Synergistic Remote Sensing Images |
| US20200225075A1 (en) * | 2019-01-14 | 2020-07-16 | Wuhan University | Method and system for optical and microwave synergistic retrieval of aboveground biomass |
| CN112765556A (en) * | 2020-12-30 | 2021-05-07 | 中国空间技术研究院 | Method for evaluating tree age of new-born mangrove forest based on intensive time remote sensing data |
| CN112861837A (en) * | 2020-12-30 | 2021-05-28 | 北京大学深圳研究生院 | Unmanned aerial vehicle-based mangrove forest ecological information intelligent extraction method |
| CN112881294A (en) * | 2021-01-13 | 2021-06-01 | 北京大学深圳研究生院 | Unmanned aerial vehicle-based mangrove forest stand health degree evaluation method |
| CN113536937A (en) * | 2021-06-17 | 2021-10-22 | 海南省林业科学研究院(海南省红树林研究院) | Mangrove forest ecological quantitative inversion method based on remote sensing technology |
| CN114266958A (en) * | 2021-11-16 | 2022-04-01 | 中林信达（北京）科技信息有限责任公司 | Cloud platform based mangrove remote sensing rapid and accurate extraction method |
-
2022
- 2022-06-16 CN CN202210678055.2A patent/CN115063437B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2019037198A (en) * | 2017-08-28 | 2019-03-14 | 東京電力ホールディングス株式会社 | Vegetation cover degree determination method and vegetation cover degree determination device |
| CN109034026A (en) * | 2018-07-16 | 2018-12-18 | 中国科学院东北地理与农业生态研究所 | The mangrove extracting method and system in land and water region in a kind of remote sensing image |
| US20200225075A1 (en) * | 2019-01-14 | 2020-07-16 | Wuhan University | Method and system for optical and microwave synergistic retrieval of aboveground biomass |
| CN111275254A (en) * | 2020-01-17 | 2020-06-12 | 河海大学 | Method for predicting development trend of future intertidal zone area based on intertidal zone area change model |
| AU2020100917A4 (en) * | 2020-06-02 | 2020-07-09 | Guizhou Institute Of Pratacultural | A Method For Extracting Vegetation Information From Aerial Photographs Of Synergistic Remote Sensing Images |
| CN112765556A (en) * | 2020-12-30 | 2021-05-07 | 中国空间技术研究院 | Method for evaluating tree age of new-born mangrove forest based on intensive time remote sensing data |
| CN112861837A (en) * | 2020-12-30 | 2021-05-28 | 北京大学深圳研究生院 | Unmanned aerial vehicle-based mangrove forest ecological information intelligent extraction method |
| CN112881294A (en) * | 2021-01-13 | 2021-06-01 | 北京大学深圳研究生院 | Unmanned aerial vehicle-based mangrove forest stand health degree evaluation method |
| CN113536937A (en) * | 2021-06-17 | 2021-10-22 | 海南省林业科学研究院(海南省红树林研究院) | Mangrove forest ecological quantitative inversion method based on remote sensing technology |
| CN114266958A (en) * | 2021-11-16 | 2022-04-01 | 中林信达（北京）科技信息有限责任公司 | Cloud platform based mangrove remote sensing rapid and accurate extraction method |
Non-Patent Citations (6)
| Title |
|---|
| 刘凯等: "基于多源遥感的广东镇海湾红树林演变分析", 《热带地理》 * |
| 周梅等: "红树林空间分布遥感监测精度的影响因素及应对措施", 《南京林业大学学报(自然科学版)》 * |
| 章恒等: "多源遥感影像红树林信息提取方法比较", 《湿地科学》 * |
| 蒙良莉等: "基于Sentinel遥感数据的红树林信息提取研究――以广西茅尾海为例", 《地理与地理信息科学》 * |
| 闻馨等: "基于无人机可见光影像的红树林冠层群落识别", 《森林与环境学报》 * |
| 黎夏等: "珠江口红树林湿地演变的遥感分析", 《地理学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116229263A (en) * | 2023-02-24 | 2023-06-06 | 广西壮族自治区气象科学研究所 | Vegetation growth disaster damage verification method based on foundation visible light image |
| CN117607070A (en) * | 2023-11-22 | 2024-02-27 | 广州双木林业有限公司 | Mangrove detection method, system, equipment and medium based on unmanned aerial vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115063437B (en) | 2023-04-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111666918B (en) | Coastline change identification method based on multiple factors | |
| Liu et al. | Satellite-based monitoring and statistics for raft and cage aquaculture in China’s offshore waters | |
| CN115063437B (en) | Mangrove canopy visible light image index feature analysis method and system | |
| CN111797712B (en) | Remote sensing image cloud and cloud shadow detection method based on multi-scale feature fusion network | |
| CN109063754B (en) | Remote sensing image multi-feature joint classification method based on OpenStreetMap | |
| CN111046613B (en) | Optimal river channel calculation method based on path tracking and river network extraction method based on multi-temporal remote sensing image | |
| Wang et al. | Classification of land-cover types in muddy tidal flat wetlands using remote sensing data | |
| CN111597949A (en) | NPP-VIIRS night light data-based urban built-up area extraction method | |
| CN113221765A (en) | Vegetation phenological period extraction method based on digital camera image effective pixels | |
| CN109657598B (en) | Coastal wetland remote sensing classification method based on layering strategy | |
| CN112418506B (en) | Coastal zone wetland ecological safety pattern optimization method and device based on machine learning | |
| CN115965812B (en) | Evaluation method for classification of unmanned aerial vehicle images on wetland vegetation species and land features | |
| CN112037244B (en) | Landsat-8 image culture pond extraction method combining index and contour indicator SLIC | |
| Chunyang et al. | Sea fog detection using U-Net deep learning model based on MODIS data | |
| CN115452759A (en) | River and lake health index evaluation method and system based on satellite remote sensing data | |
| Yilmaz et al. | The performance analysis of different water indices and algorithms using sentinel-2 and landsat-8 images in determining water surface: Demirkopru dam case study | |
| CN114545528B (en) | Machine learning-based correction method and device after meteorological numerical mode element forecast | |
| CN118279763A (en) | Sea ice monitoring method, system, equipment, storage medium and computer program product | |
| Sun et al. | Mapping China’s coastal aquaculture ponds expansion with sentinel-2 images during 2017–2021 | |
| Nagaraj et al. | Extraction of Surface Water Bodies using Optical Remote Sensing Images: A Review | |
| Chen et al. | Mangrove Growth Monitoring Based on Camera Visible Images—A Case Study on Typical Mangroves in Guangxi | |
| CN116543300A (en) | Cloud-aerosol hierarchical classification method based on semantic segmentation | |
| CN116152655A (en) | Coastal wetland classification method, device, equipment and storage medium | |
| Revollo et al. | Automatic methodology for mapping of coastal zones in video sequences | |
| CN114550005A (en) | Method and system for identifying buildings in natural protection area |
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 |