CN117312973B - Inland water body optical classification method and system - Google Patents
Inland water body optical classification method and system Download PDFInfo
- Publication number
- CN117312973B CN117312973B CN202311253664.4A CN202311253664A CN117312973B CN 117312973 B CN117312973 B CN 117312973B CN 202311253664 A CN202311253664 A CN 202311253664A CN 117312973 B CN117312973 B CN 117312973B
- Authority
- CN
- China
- Prior art keywords
- water
- water bodies
- bodies
- spectrum
- categories
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 284
- 230000003287 optical effect Effects 0.000 title claims abstract description 76
- 238000000034 method Methods 0.000 title claims abstract description 58
- 230000003595 spectral effect Effects 0.000 claims abstract description 56
- 238000001228 spectrum Methods 0.000 claims abstract description 46
- 238000000985 reflectance spectrum Methods 0.000 claims abstract description 21
- 238000002310 reflectometry Methods 0.000 claims description 31
- 238000012545 processing Methods 0.000 claims description 23
- 239000013598 vector Substances 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 12
- 241000192710 Microcystis aeruginosa Species 0.000 claims description 9
- 238000010606 normalization Methods 0.000 claims description 4
- XLYOFNOQVPJJNP-ZSJDYOACSA-N Heavy water Chemical compound [2H]O[2H] XLYOFNOQVPJJNP-ZSJDYOACSA-N 0.000 claims 4
- 238000005259 measurement Methods 0.000 claims 2
- 238000004458 analytical method Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 20
- 230000008859 change Effects 0.000 description 10
- 230000007423 decrease Effects 0.000 description 8
- 239000005422 algal bloom Substances 0.000 description 7
- 230000000694 effects Effects 0.000 description 7
- 238000011160 research Methods 0.000 description 6
- 101100012902 Saccharomyces cerevisiae (strain ATCC 204508 / S288c) FIG2 gene Proteins 0.000 description 5
- 101001121408 Homo sapiens L-amino-acid oxidase Proteins 0.000 description 3
- 102100026388 L-amino-acid oxidase Human genes 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000012804 iterative process Methods 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 101000827703 Homo sapiens Polyphosphoinositide phosphatase Proteins 0.000 description 1
- 102100023591 Polyphosphoinositide phosphatase Human genes 0.000 description 1
- 101100233916 Saccharomyces cerevisiae (strain ATCC 204508 / S288c) KAR5 gene Proteins 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 239000003643 water by type Substances 0.000 description 1
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
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
本发明提出一种内陆水体光学分类方法和系统。其中，方法包括：基于K‑means方法，以光谱角度距离为度量，将所有水体归一化遥感反射率光谱粗分为20类水体；计算所述20类水体的类内距离，并采用K‑means方法将类内距离大于预设值的类拆分，拆分后变成25类水体；计算25类水体的平均光谱，将平均光谱进行逐步迭代的K‑means分类，从25类水体逐步减少到10类水体，并分别计算每一次迭代后的光谱角度距离；根据分析所述25类水体到所述10类水体的光谱角度距离，将水体分为13类。本发明提出的方案能够建立了完备的内陆水体光学分类体系，并提供了建立该体系的方法，填补了水环境遥感领域的内陆水体光学分类体系空白。
The present invention proposes an inland water optical classification method and system. The method includes: based on the K-means method, taking the spectral angle distance as a measure, roughly dividing the normalized remote sensing reflectance spectra of all water bodies into 20 categories of water bodies; calculating the intra-class distance of the 20 categories of water bodies, and using the K-means method to split the classes with intra-class distances greater than a preset value, and the splitting becomes 25 categories of water bodies; calculating the average spectrum of the 25 categories of water bodies, and performing step-by-step iterative K-means classification on the average spectrum, gradually reducing it from 25 categories of water bodies to 10 categories of water bodies, and calculating the spectral angle distance after each iteration; dividing the water bodies into 13 categories based on the analysis of the spectral angle distance from the 25 categories of water bodies to the 10 categories of water bodies. The scheme proposed by the present invention can establish a complete inland water optical classification system, and provides a method for establishing the system, filling the gap in the inland water optical classification system in the field of water environment remote sensing.
Description
技术领域Technical Field
本发明属于水体光学分类领域，尤其涉及一种内陆水体光学分类方法和系统。The invention belongs to the field of water body optical classification, and in particular relates to an inland water body optical classification method and system.
背景技术Background technique
湖泊、河流、水库等内陆水体是人类赖以生存和发展的自然生态系统重要组成部分。水色遥感参数反演是监测、评价与预测预警水环境与水生态的重要技术手段，而水体光学类型是宏观认识水环境现状和变化趋势的重要参量，是提高常用水色遥感参数反演精度的基础。对水体进行分类有助于识别光学复杂水域，分析水体环境变化。近年来的研究已经证明了水体光学分类的重要性，但水体分类研究仍存在一些问题：现有二类水体分类研究缺少针对中国内陆水体建立完备的水体光学分类体系。为了解决这一问题，本专利发明了一种内陆水体光学分类体系，深入研究了不同类型内陆水体光谱反射率特征，为各种类型内陆水体水质参数反演提供理论基础以及技术支撑。Inland water bodies such as lakes, rivers, and reservoirs are important components of the natural ecosystem on which human beings depend for survival and development. The inversion of water color remote sensing parameters is an important technical means to monitor, evaluate, predict and warn of water environment and water ecology, and the optical type of water bodies is an important parameter for macroscopic understanding of the current status and changing trends of water environment, and is the basis for improving the accuracy of inversion of commonly used water color remote sensing parameters. Classifying water bodies helps to identify optically complex waters and analyze changes in water environment. Research in recent years has proved the importance of water body optical classification, but there are still some problems in water body classification research: the existing second-class water body classification research lacks a complete water body optical classification system for China's inland water bodies. In order to solve this problem, this patent invents an inland water body optical classification system, and deeply studies the spectral reflectance characteristics of different types of inland water bodies, providing a theoretical basis and technical support for the inversion of water quality parameters of various types of inland water bodies.
目前国内外学者在水体分类研究上做了大量的工作，水体光学分类研究对象多为大洋水体、近岸与内陆结合水体、单一湖泊、多个典型湖泊等，缺少专门针对内陆水体的水体光学类型框架和体系；关于使用的聚类方法中的聚类数量的确定无法保持其客观性，现有研究所选用的数据集以及假定的聚类数量区间不尽相同，缺少普遍接受的水体类型划分标准。At present, scholars at home and abroad have done a lot of work on water body classification research. The objects of water optical classification research are mostly ocean water bodies, combined nearshore and inland water bodies, single lakes, multiple typical lakes, etc. There is a lack of a water body optical type framework and system specifically for inland water bodies; the determination of the number of clusters in the clustering method used cannot maintain its objectivity, the data sets selected by existing research and the assumed range of cluster numbers are not the same, and there is a lack of generally accepted standards for water body type classification.
发明内容Summary of the invention
为解决上述技术问题，本发明提出一种内陆水体光学分类方法的技术方案，以解决上述技术问题。In order to solve the above technical problems, the present invention proposes a technical solution for an inland water optical classification method to solve the above technical problems.
本发明第一方面公开了一种内陆水体光学分类方法，所述方法包括：The first aspect of the present invention discloses an optical classification method for inland water bodies, the method comprising:
步骤S1、选取400～900nm波段的内陆水体的遥感反射率光谱，并对遥感反射率光谱进行归一化处理；Step S1, selecting a remote sensing reflectance spectrum of an inland water body in a band of 400 to 900 nm, and normalizing the remote sensing reflectance spectrum;
步骤S2、基于K-means方法，以光谱角度距离为度量，将所有水体归一化遥感反射率光谱粗分为20类水体；Step S2: Based on the K-means method, all water body normalized remote sensing reflectance spectra are roughly divided into 20 types of water bodies using spectral angle distance as a metric;
步骤S3、计算所述20类水体的类内距离，并采用K-means方法将类内距离大于预设值的类拆分，拆分后变成25类水体；Step S3, calculating the intra-class distances of the 20 types of water bodies, and using the K-means method to split the classes whose intra-class distances are greater than a preset value, into 25 types of water bodies after splitting;
步骤S4、计算25类水体的平均光谱，将平均光谱进行逐步迭代的K-means分类，从25类水体逐步减少到10类水体，并分别计算每一次迭代后的光谱角度距离；Step S4, calculating the average spectrum of 25 types of water bodies, performing K-means classification on the average spectrum in a step-by-step iterative manner, gradually reducing the number of water bodies from 25 types to 10 types, and calculating the spectral angle distance after each iteration;
步骤S5、根据分析所述25类水体到所述10类水体的光谱角度距离，将水体分为13类。Step S5: Classify the water bodies into 13 categories based on analyzing the spectral angle distances from the 25 categories of water bodies to the 10 categories of water bodies.
根据本发明第一方面的方法，在所述步骤S1中，所述对遥感反射率进行归一化处理的方法包括：According to the method of the first aspect of the present invention, in step S1, the method of normalizing the remote sensing reflectivity includes:
其中，NRrs(λ)表示在400nm和900nm之间积分得到的归一化光谱，Rrs(λ)表示遥感反射率光谱。Wherein, NR rs (λ) represents the normalized spectrum integrated between 400 nm and 900 nm, and R rs (λ) represents the remote sensing reflectance spectrum.
根据本发明第一方面的方法，在所述步骤S2中，所述光谱角距离的计算公式为：According to the method of the first aspect of the present invention, in step S2, the calculation formula of the spectral angular distance is:
其中，SAD为光谱角距离，xs和xt为两个光谱反射率向量，和/>为xs和xt的转置向量。Where SAD is the spectral angular distance, xs and xt are two spectral reflectance vectors, and/> is the transposed vector of xs and xt .
根据本发明第一方面的方法，在所述步骤S3中，所述类内距离的计算公式为：According to the method of the first aspect of the present invention, in step S3, the calculation formula of the intra-class distance is:
其中，D为类内距离，Ni为第i类水体的样本数，为第i类水体的第k条光谱反射率向量，Xi为第i类的平均光谱，/>为光谱角距离的计算结果的平方。Among them, D is the intra-class distance, Ni is the number of samples of the i-th water body, is the kth spectral reflectance vector of the i-th water body, Xi is the average spectrum of the i-th class, /> is the square of the calculated spectral angular distance.
根据本发明第一方面的方法，在所述步骤S3中，所述预设值为0.08。According to the method of the first aspect of the present invention, in step S3, the preset value is 0.08.
根据本发明第一方面的方法，在所述步骤S5中，所述根据分析所述25类水体到所述10类水体的光谱角度距离，将水体分为13类的方法包括：所述根据分析所述25类水体到所述10类水体的光谱角度距离，在分为13类和15类时，光谱角度距离有较大变化，适合作为最终的分类数目。根据对比最终合并效果，分为13类水体更具有实际物理意义，因此，将所有水体最终分为13类。具体，分析从25类到10类的光谱角度距离变化可知，在分为13类和15类时，光谱角度值有较大变化，适合作为最终的分类数目。根据对比最终合并效果，发现分为13类水体更具有实际物理意义，因此，将所有水体最终分为13类。According to the method of the first aspect of the present invention, in the step S5, the method of dividing the water bodies into 13 categories based on the analysis of the spectral angle distances from the 25 categories of water bodies to the 10 categories of water bodies includes: the spectral angle distances from the 25 categories of water bodies to the 10 categories of water bodies have a large change when they are divided into 13 categories and 15 categories, which is suitable as the final number of classifications. According to the comparison of the final merging effect, it is more practical to divide the water bodies into 13 categories, and therefore, all water bodies are finally divided into 13 categories. Specifically, the analysis of the change in spectral angle distance from 25 categories to 10 categories shows that when they are divided into 13 categories and 15 categories, the spectral angle value has a large change, which is suitable as the final number of classifications. According to the comparison of the final merging effect, it is found that it is more practical to divide the water bodies into 13 categories, and therefore, all water bodies are finally divided into 13 categories.
根据本发明第一方面的方法，在所述步骤S5中，所述13类水体的水体类型为：According to the method of the first aspect of the present invention, in step S5, the water body types of the 13 types of water bodies are:
高度清洁水体、清洁水体、一般清洁水体、轻度浑浊水体、中度浑浊水体、高度浑浊水体、轻度富营养化水体、中度富营养化水体、重度富营养化水体、浑浊富营养化水体、黑臭水体、轻度水华和重度水华。Highly clean water bodies, clean water bodies, generally clean water bodies, slightly turbid water bodies, moderately turbid water bodies, highly turbid water bodies, slightly eutrophic water bodies, moderately eutrophic water bodies, severely eutrophic water bodies, turbid and eutrophic water bodies, black and smelly water bodies, slight algal bloom and severe algal bloom.
本发明第二方面公开了一种内陆水体光学分类系统，所述系统包括：A second aspect of the present invention discloses an inland water optical classification system, the system comprising:
第一处理模块，被配置为，选取400～900nm波段的内陆水体的遥感反射率光谱，并对遥感反射率光谱进行归一化处理；The first processing module is configured to select a remote sensing reflectance spectrum of an inland water body in a 400-900 nm band and perform normalization processing on the remote sensing reflectance spectrum;
第二处理模块，被配置为，基于K-means方法，以光谱角度距离为度量，将所有水体归一化遥感反射率光谱粗分为20类水体；The second processing module is configured to roughly classify all water body normalized remote sensing reflectance spectra into 20 types of water bodies based on the K-means method and using the spectral angle distance as a metric;
第三处理模块，被配置为，计算所述20类水体的类内距离，并采用K-means方法将类内距离大于预设值的类拆分，拆分后变成25类水体；The third processing module is configured to calculate the intra-class distances of the 20 types of water bodies, and use the K-means method to split the classes whose intra-class distances are greater than a preset value, into 25 types of water bodies after splitting;
第四处理模块，被配置为，计算25类水体的平均光谱，将平均光谱进行逐步迭代的K-means分类，从25类水体逐步减少到10类水体，并分别计算每一次迭代后的光谱角度距离；The fourth processing module is configured to calculate the average spectrum of 25 types of water bodies, perform K-means classification on the average spectrum in a step-by-step iterative manner, gradually reduce the average spectrum from 25 types of water bodies to 10 types of water bodies, and calculate the spectral angle distance after each iteration;
第五处理模块，被配置为，根据分析所述25类水体到所述10类水体的光谱角度距离，将水体分为13类。The fifth processing module is configured to classify the water bodies into 13 categories based on analyzing the spectral angle distances from the 25 categories of water bodies to the 10 categories of water bodies.
本发明第三方面公开了一种电子设备。电子设备包括存储器和处理器，存储器存储有计算机程序，处理器执行计算机程序时，实现本公开第一方面中任一项的一种内陆水体光学分类方法中的步骤。The third aspect of the present invention discloses an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any one of the inland water optical classification methods in the first aspect of the present disclosure are implemented.
本发明第四方面公开了一种计算机可读存储介质。计算机可读存储介质上存储有计算机程序，计算机程序被处理器执行时，实现本公开第一方面中任一项的一种内陆水体光学分类方法中的步骤。The fourth aspect of the present invention discloses a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any one of the inland water optical classification methods in the first aspect of the present disclosure are implemented.
综上，本发明提出的方案能够建立了完备的内陆水体光学分类体系，并提供了建立该体系的方法，填补了水环境遥感领域的内陆水体光学分类体系空白，为宏观认知全球、全国大范围内陆水体状况提供了新的指标，为全球和全国大范围水质参数遥感分类反演提供了理论和技术支撑。In summary, the scheme proposed in the present invention can establish a complete optical classification system for inland water bodies and provide a method for establishing the system, filling the gap in the optical classification system for inland water bodies in the field of water environment remote sensing, providing new indicators for macro-cognition of the status of inland water bodies in a global and national scale, and providing theoretical and technical support for the remote sensing classification and inversion of water quality parameters in a global and national scale.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
为了更清楚地说明本发明具体实施方式或现有技术中的技术方案，下面将对具体实施方式或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图是本发明的一些实施方式，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
图1为根据本发明实施例的一种内陆水体光学分类方法的流程图；FIG1 is a flow chart of an inland water optical classification method according to an embodiment of the present invention;
图2为根据本发明实施例的K-means聚类的20类和25类水体类型的类内距离示意图；FIG2 is a schematic diagram of intra-class distances of 20 and 25 water body types according to K-means clustering according to an embodiment of the present invention;
图3为根据本发明实施例的平均SAD与聚类数的关系示意图；FIG3 is a schematic diagram showing the relationship between the average SAD and the number of clusters according to an embodiment of the present invention;
图4为根据本发明实施例的内陆水体光学分类体系平均光谱；FIG4 is an average spectrum of an inland water optical classification system according to an embodiment of the present invention;
图5为根据本发明实施例的高度清洁水体光学特征图；FIG5 is an optical characteristic diagram of highly clean water according to an embodiment of the present invention;
图6为根据本发明实施例的清洁水体光学特征图；FIG6 is an optical characteristic diagram of clean water according to an embodiment of the present invention;
图7为根据本发明实施例的一般清洁水体光学特征图；FIG7 is a diagram showing optical characteristics of a general clean water body according to an embodiment of the present invention;
图8为根据本发明实施例的轻度浑浊水体光学特征图；FIG8 is an optical characteristic diagram of slightly turbid water according to an embodiment of the present invention;
图9为根据本发明实施例的中度浑浊水体光学特征图；FIG9 is an optical characteristic diagram of moderately turbid water according to an embodiment of the present invention;
图10为根据本发明实施例的高度浑浊水体光学特征图；FIG10 is an optical characteristic diagram of highly turbid water according to an embodiment of the present invention;
图11为根据本发明实施例的轻度富营养化水体光学特征图；FIG11 is an optical characteristic diagram of a slightly eutrophic water body according to an embodiment of the present invention;
图12为根据本发明实施例的中度富营养化水体光学特征图；FIG12 is an optical characteristic diagram of a moderately eutrophic water body according to an embodiment of the present invention;
图13为根据本发明实施例的重度富营养化水体光学特征图；FIG13 is an optical characteristic diagram of a severely eutrophic water body according to an embodiment of the present invention;
图14为根据本发明实施例的浑浊富营养化水体光学特征图；FIG14 is an optical characteristic diagram of turbid eutrophic water according to an embodiment of the present invention;
图15为根据本发明实施例的黑臭水体光学特征图；FIG15 is an optical characteristic diagram of black and odorous water according to an embodiment of the present invention;
图16为根据本发明实施例的轻度水华光学特征图；FIG16 is a diagram showing optical characteristics of mild water bloom according to an embodiment of the present invention;
图17为根据本发明实施例的重度水华光学特征图；FIG17 is an optical characteristic diagram of severe water bloom according to an embodiment of the present invention;
图18为根据本发明实施例的一种内陆水体光学分类系统的结构图；FIG18 is a structural diagram of an inland water optical classification system according to an embodiment of the present invention;
图19为根据本发明实施例的一种电子设备的结构图。FIG. 19 is a structural diagram of an electronic device according to an embodiment of the present invention.
具体实施方式Detailed ways
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例只是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.
本发明第一方面公开了一种内陆水体光学分类方法。图1为根据本发明实施例的一种内陆水体光学分类方法的流程图，如图1所示，所述方法包括：The first aspect of the present invention discloses an inland water optical classification method. FIG1 is a flow chart of an inland water optical classification method according to an embodiment of the present invention. As shown in FIG1 , the method comprises:
步骤S1、选取400～900nm波段的内陆水体的遥感反射率光谱，并对遥感反射率光谱进行归一化处理；Step S1, selecting a remote sensing reflectance spectrum of an inland water body in a band of 400 to 900 nm, and normalizing the remote sensing reflectance spectrum;
步骤S2、基于K-means方法，以光谱角度距离为度量，将所有水体归一化遥感反射率光谱粗分为20类水体；Step S2: Based on the K-means method, all water body normalized remote sensing reflectance spectra are roughly divided into 20 types of water bodies using spectral angle distance as a metric;
步骤S3、计算所述20类水体的类内距离，并采用K-means方法将类内距离大于预设值的类拆分，拆分后变成25类水体；Step S3, calculating the intra-class distances of the 20 types of water bodies, and using the K-means method to split the classes whose intra-class distances are greater than a preset value, into 25 types of water bodies after splitting;
步骤S4、计算25类水体的平均光谱，将平均光谱进行逐步迭代的K-means分类，从25类水体逐步减少到10类水体，并分别计算每一次迭代后的光谱角度距离；Step S4, calculating the average spectrum of 25 types of water bodies, performing K-means classification on the average spectrum in a step-by-step iterative manner, gradually reducing the number of water bodies from 25 types to 10 types, and calculating the spectral angle distance after each iteration;
步骤S5、根据分析所述25类水体到所述10类水体的光谱角度距离，将水体分为13类。Step S5: Classify the water bodies into 13 categories based on analyzing the spectral angle distances from the 25 categories of water bodies to the 10 categories of water bodies.
在步骤S1，选取400～900nm波段的内陆水体的遥感反射率光谱，并对遥感反射率光谱进行归一化处理。In step S1, a remote sensing reflectance spectrum of an inland water body in a band of 400-900 nm is selected, and the remote sensing reflectance spectrum is normalized.
在一些实施例中，在所述步骤S1中，所述对遥感反射率进行归一化处理的方法包括：In some embodiments, in step S1, the method for normalizing the remote sensing reflectivity includes:
其中，NRrs(λ)表示在400nm和900nm之间积分得到的归一化光谱，Rrs(λ)表示遥感反射率光谱。Wherein, NR rs (λ) represents the normalized spectrum integrated between 400 nm and 900 nm, and R rs (λ) represents the remote sensing reflectance spectrum.
在步骤S2，基于K-means方法，以光谱角度距离为度量，将所有水体归一化遥感反射率光谱粗分为20类水体。In step S2, based on the K-means method and taking the spectral angle distance as the metric, all water body normalized remote sensing reflectance spectra are roughly divided into 20 types of water bodies.
在一些实施例中，在所述步骤S2中，所述光谱角距离的计算公式为：In some embodiments, in step S2, the calculation formula of the spectral angular distance is:
其中，SAD为光谱角距离，xs和xt为两个光谱反射率向量，和/>为xs和xt的转置向量。SAD越小，两光谱的相似度越高。Where SAD is the spectral angular distance, xs and xt are two spectral reflectance vectors, and/> is the transposed vector of xs and xt . The smaller the SAD is, the higher the similarity between the two spectra is.
在步骤S3，计算所述20类水体的类内距离，并采用K-means方法将类内距离大于预设值的类拆分，拆分后变成25类水体。In step S3, the intra-class distances of the 20 types of water bodies are calculated, and the K-means method is used to split the classes whose intra-class distances are greater than a preset value, and the classes become 25 types of water bodies after splitting.
在一些实施例中，在所述步骤S3中，类内距离即同一类各模式样本点间的均方根距离，所述类内距离的计算公式为：In some embodiments, in step S3, the intra-class distance is the root mean square distance between the pattern sample points of the same class, and the calculation formula of the intra-class distance is:
其中，D为类内距离，Ni为第i类水体的样本数，为第i类水体的第k条光谱反射率向量，Xi为第i类的平均光谱，/>为光谱角距离的计算结果的平方。Among them, D is the intra-class distance, Ni is the number of samples of the i-th water body, is the kth spectral reflectance vector of the i-th water body, Xi is the average spectrum of the i-th class, /> is the square of the calculated spectral angular distance.
所述预设值为0.08。The preset value is 0.08.
具体地，通过对得到的20个类别的光谱进行观察和分析，发现存在一些错误分类的情况。为了解决这个问题，本实施例计算了20个类别的类内距离，如图2所示，并发现那些存在错误分类的类别的类内距离均大于0.08。因此本实施例将拆分的阈值设定为0.08，最后得到25个类别，且这些类别的类内距离均小于0.08，如图2所示。Specifically, by observing and analyzing the spectra of the 20 categories obtained, it is found that there are some cases of misclassification. In order to solve this problem, the present embodiment calculates the intra-class distances of the 20 categories, as shown in FIG2 , and finds that the intra-class distances of those categories with misclassification are all greater than 0.08. Therefore, the present embodiment sets the threshold value of splitting to 0.08, and finally obtains 25 categories, and the intra-class distances of these categories are all less than 0.08, as shown in FIG2 .
在步骤S5，根据分析所述25类水体到所述10类水体的光谱角度距离，将水体分为13类。In step S5, the water bodies are divided into 13 categories based on analyzing the spectral angle distances from the 25 categories of water bodies to the 10 categories of water bodies.
在一些实施例中，在所述步骤S5中，所述根据分析所述25类水体到所述10类水体的光谱角度距离，将水体分为13类的方法包括：所述根据分析所述25类水体到所述10类水体的光谱角度距离，在分为13类和15类时，光谱角度距离有较大变化，适合作为最终的分类数目。根据对比最终合并效果，分为13类水体更具有实际物理意义，因此，将所有水体最终分为13类。。In some embodiments, in step S5, the method of classifying the water bodies into 13 categories according to the analysis of the spectral angle distances from the 25 categories of water bodies to the 10 categories of water bodies includes: when the spectral angle distances from the 25 categories of water bodies to the 10 categories of water bodies are divided into 13 categories and 15 categories, the spectral angle distances have a large change, which is suitable as the final classification number. According to the comparison of the final merging effect, the classification into 13 categories of water bodies has more practical physical significance, so all water bodies are finally divided into 13 categories. .
具体地，分析从25类到10类的光谱角度距离变化可知，在分为13类和15类时，光谱角度值有较大变化，适合作为最终的分类数目。根据对比最终合并效果，发现分为13类水体更具有实际物理意义，因此，将所有水体最终分为13类。Specifically, the change in spectral angle distance from 25 to 10 shows that the spectral angle value changes greatly when it is divided into 13 and 15 categories, which is suitable as the final number of categories. According to the comparison of the final merging effect, it is found that the classification into 13 categories of water bodies has more practical physical significance, so all water bodies are finally divided into 13 categories.
所述13类水体的水体类型为：The water types of the 13 types of water bodies are:
高度清洁水体、清洁水体、一般清洁水体、轻度浑浊水体、中度浑浊水体、高度浑浊水体、轻度富营养化水体、中度富营养化水体、重度富营养化水体、浑浊富营养化水体、黑臭水体、轻度水华和重度水华。Highly clean water bodies, clean water bodies, generally clean water bodies, slightly turbid water bodies, moderately turbid water bodies, highly turbid water bodies, slightly eutrophic water bodies, moderately eutrophic water bodies, severely eutrophic water bodies, turbid and eutrophic water bodies, black and smelly water bodies, slight algal bloom and severe algal bloom.
具体地，计算25个类别的平均光谱，利用逐步迭代K-means对25条平均光谱进行合并，图3为采用逐步迭代K-means从25到10类的迭代过程，从图中可以看出，从15-25类类间距变化不大，没有明显特征，分为13类和15类较为典型，类间距在这两类都有较大变化，可以作为最终分类数目。根据对比最终合并效果，发现13类水体更具有实际物理意义，因此，本研究将所有遥感反射率数据分为13类。内陆水体光学分类体系如图4所示。Specifically, the average spectra of 25 categories are calculated, and the 25 average spectra are merged using stepwise iterative K-means. Figure 3 shows the iterative process from 25 to 10 categories using stepwise iterative K-means. It can be seen from the figure that the class spacing from 15 to 25 categories does not change much, and there is no obvious feature. It is more typical to divide it into 13 and 15 categories. The class spacing has a large change in these two categories, which can be used as the final classification number. According to the comparison of the final merging effect, it is found that the 13-category water body has more practical physical significance. Therefore, this study divides all remote sensing reflectance data into 13 categories. The optical classification system of inland water bodies is shown in Figure 4.
如图5所示，高度清洁水体的光学特征为：蓝波段反射率较高，红和近红外很低；As shown in Figure 5, the optical characteristics of highly clean water are: high reflectivity in the blue band, and very low reflectivity in the red and near-infrared bands;
如图6所示，清洁水体的光学特征为：深蓝波段反射率下降，但反射率峰值仍然在蓝波段；As shown in Figure 6, the optical characteristics of clean water are: the reflectivity of the deep blue band decreases, but the reflectivity peak is still in the blue band;
如图7所示，一般清洁水体的光学特征为：蓝波段反射率降低，绿波段形成反射峰；As shown in Figure 7, the optical characteristics of a general clean water body are: the reflectivity of the blue band decreases, and a reflection peak is formed in the green band;
如图8所示，轻度浑浊水体的光学特征为：绿波段到红波段反射率呈下降趋势，近红外波段开始升高；As shown in Figure 8 , the optical characteristics of slightly turbid water bodies are as follows: the reflectivity decreases from the green band to the red band and begins to increase in the near-infrared band;
如图9所示，中度浑浊水体的光学特征为：红和近红外波段反射率升高明显；As shown in Figure 9, the optical characteristics of moderately turbid water bodies are: the reflectance in the red and near-infrared bands increases significantly;
如图10所示，高度浑浊水体的光学特征为：红和近红外波段反射率升高明显，红波段反射率和绿波段相当或高于绿波段；As shown in Figure 10, the optical characteristics of highly turbid water bodies are: the reflectance in the red and near-infrared bands increases significantly, and the reflectance in the red band is equivalent to or higher than that in the green band;
如图11所示，轻度富营养化水体的光学特征为：绿波段反射峰明显，红边波段反射峰较低；As shown in Figure 11, the optical characteristics of slightly eutrophic water bodies are: the green band reflection peak is obvious, and the red edge band reflection peak is low;
如图12所示，中度富营养化水体的光学特征为：绿波段反射峰明显，红边波段反射峰升高；As shown in Figure 12, the optical characteristics of moderately eutrophic water bodies are: the green band reflection peak is obvious, and the red edge band reflection peak is increased;
如图13所示，重度富营养化水体的光学特征为：红边波段反射峰较高，高度和绿波段相当；As shown in Figure 13, the optical characteristics of severely eutrophic water bodies are: the red edge band reflection peak is relatively high, and its height is comparable to that of the green band;
如图14所示，浑浊富营养化水体的光学特征为：红和近红外波段反射率较高，且红边波段反射峰明显；As shown in Figure 14, the optical characteristics of turbid eutrophic water bodies are: high reflectivity in the red and near-infrared bands, and an obvious reflection peak in the red edge band;
如图15所示，黑臭水体的光学特征为：反射率比一般水体低且曲线平坦，无明显的峰谷特征；As shown in Figure 15, the optical characteristics of black and odorous water bodies are: the reflectivity is lower than that of ordinary water bodies and the curve is flat, without obvious peak and valley characteristics;
如图16所示，轻度水华的光学特征为：红边波段反射率最高，近红外波段有所降低，但高于红波段；As shown in Figure 16, the optical characteristics of mild water bloom are as follows: the reflectivity is highest in the red edge band, which decreases slightly in the near infrared band but is higher than the red band;
如图17所示，重度水华的光学特征为：红边和近红外波段反射率很高且曲线平坦，近红外波段降低趋势不明显。As shown in Figure 17, the optical characteristics of severe algal bloom are: the reflectivity in the red edge and near-infrared bands is very high and the curve is flat, and there is no obvious decreasing trend in the near-infrared band.
综上，本发明提出的方案能够建立了完备的内陆水体光学分类体系，并提供了建立该体系的方法，填补了水环境遥感领域的内陆水体光学分类体系空白，为宏观认知全球、全国大范围内陆水体状况提供了新的指标，为全球和全国大范围水质参数遥感分类反演提供了理论和技术支撑。In summary, the scheme proposed in the present invention can establish a complete optical classification system for inland water bodies and provide a method for establishing the system, filling the gap in the optical classification system for inland water bodies in the field of water environment remote sensing, providing new indicators for macro-cognition of the status of inland water bodies in a global and national scale, and providing theoretical and technical support for the remote sensing classification and inversion of water quality parameters in a global and national scale.
本发明第二方面公开了一种内陆水体光学分类系统。图18为根据本发明实施例的一种内陆水体光学分类系统的结构图；如图18所示，所述系统100包括：The second aspect of the present invention discloses an inland water optical classification system. FIG18 is a structural diagram of an inland water optical classification system according to an embodiment of the present invention; as shown in FIG18 , the system 100 includes:
第一处理模块101，被配置为，选取400～900nm波段的内陆水体的遥感反射率光谱，并对遥感反射率光谱进行归一化处理；The first processing module 101 is configured to select a remote sensing reflectance spectrum of an inland water body in a 400-900 nm band and perform normalization processing on the remote sensing reflectance spectrum;
第二处理模块102，被配置为，基于K-means方法，以光谱角度距离为度量，将所有水体归一化遥感反射率光谱粗分为20类水体；The second processing module 102 is configured to roughly classify all water body normalized remote sensing reflectance spectra into 20 types of water bodies based on the K-means method and using the spectral angle distance as a metric;
第三处理模块103，被配置为，计算所述20类水体的类内距离，并采用K-means方法将类内距离大于预设值的类拆分，拆分后变成25类水体；The third processing module 103 is configured to calculate the intra-class distances of the 20 types of water bodies, and use the K-means method to split the classes whose intra-class distances are greater than a preset value, into 25 types of water bodies after splitting;
第四处理模块104，被配置为，计算25类水体的平均光谱，将平均光谱进行逐步迭代的K-means分类，从25类水体逐步减少到10类水体，并分别计算每一次迭代后的光谱角度距离；The fourth processing module 104 is configured to calculate the average spectrum of 25 types of water bodies, perform K-means classification on the average spectrum in a step-by-step iterative manner, gradually reduce the 25 types of water bodies to 10 types of water bodies, and calculate the spectral angle distance after each iteration;
第五处理模块105，被配置为，根据分析所述25类水体到所述10类水体的光谱角度距离，将水体分为13类。The fifth processing module 105 is configured to classify the water bodies into 13 categories based on analyzing the spectral angle distances from the 25 categories of water bodies to the 10 categories of water bodies.
根据本发明第二方面的系统，所述第一处理模块101具体被配置为，所述对遥感反射率进行归一化处理的方法包括：According to the system of the second aspect of the present invention, the first processing module 101 is specifically configured as follows: the method for normalizing the remote sensing reflectivity includes:
其中，NRrs(λ)表示在400nm和900nm之间积分得到的归一化光谱，Rrs(λ)表示遥感反射率光谱。Wherein, NR rs (λ) represents the normalized spectrum integrated between 400 nm and 900 nm, and R rs (λ) represents the remote sensing reflectance spectrum.
根据本发明第二方面的系统，所述第二处理模块102具体被配置为，所述光谱角距离的计算公式为：According to the system of the second aspect of the present invention, the second processing module 102 is specifically configured as follows: the calculation formula of the spectral angular distance is:
其中，SAD为光谱角距离，xs和xt为两个光谱反射率向量，和/>为xs和xt的转置向量。SAD越小，两光谱的相似度越高。Where SAD is the spectral angular distance, xs and xt are two spectral reflectance vectors, and/> is the transposed vector of xs and xt . The smaller the SAD is, the higher the similarity between the two spectra is.
根据本发明第二方面的系统，所述第三处理模块103具体被配置为，类内距离即同一类各模式样本点间的均方根距离，所述类内距离的计算公式为：According to the system of the second aspect of the present invention, the third processing module 103 is specifically configured as follows: the intra-class distance is the root mean square distance between the pattern sample points of the same class, and the calculation formula of the intra-class distance is:
其中，D为类内距离，Ni为第i类水体的样本数，为第i类水体的第k条光谱反射率向量，Xi为第i类的平均光谱，/>为光谱角距离的计算结果的平方。Among them, D is the intra-class distance, Ni is the number of samples of the i-th water body, is the kth spectral reflectance vector of the i-th water body, Xi is the average spectrum of the i-th class, /> is the square of the calculated spectral angular distance.
所述预设值为0.08。The preset value is 0.08.
具体地，通过对得到的20个类别的光谱进行观察和分析，发现存在一些错误分类的情况。为了解决这个问题，本实施例计算了20个类别的类内距离，如图2所示，并发现那些存在错误分类的类别的类内距离均大于0.08。因此本实施例将拆分的阈值设定为0.08，最后得到25个类别，且这些类别的类内距离均小于0.08，如图2所示。Specifically, by observing and analyzing the spectra of the 20 categories obtained, it is found that there are some cases of misclassification. In order to solve this problem, the present embodiment calculates the intra-class distances of the 20 categories, as shown in FIG2 , and finds that the intra-class distances of those categories with misclassification are all greater than 0.08. Therefore, the present embodiment sets the threshold value of splitting to 0.08, and finally obtains 25 categories, and the intra-class distances of these categories are all less than 0.08, as shown in FIG2 .
根据本发明第二方面的系统，所述第五处理模块105具体被配置为，所述根据分析所述25类水体到所述10类水体的光谱角度距离，将水体分为13类的方法包括：所述根据分析所述25类水体到所述10类水体的光谱角度距离，在分为13类和15类时，光谱角度距离有较大变化，适合作为最终的分类数目。根据对比最终合并效果，分为13类水体更具有实际物理意义，因此，将所有水体最终分为13类。According to the system of the second aspect of the present invention, the fifth processing module 105 is specifically configured as follows: the method of dividing the water body into 13 categories based on analyzing the spectral angle distance from the 25 categories of water bodies to the 10 categories of water bodies includes: the spectral angle distance from the 25 categories of water bodies to the 10 categories of water bodies has a large change when divided into 13 categories and 15 categories, which is suitable as the final classification number. According to the comparison of the final merging effect, the classification into 13 categories of water bodies has more practical physical significance, so all water bodies are finally divided into 13 categories.
所述13类水体的水体类型为：The water types of the 13 types of water bodies are:
高度清洁水体、清洁水体、一般清洁水体、轻度浑浊水体、中度浑浊水体、高度浑浊水体、轻度富营养化水体、中度富营养化水体、重度富营养化水体、浑浊富营养化水体、黑臭水体、轻度水华和重度水华。Highly clean water bodies, clean water bodies, generally clean water bodies, slightly turbid water bodies, moderately turbid water bodies, highly turbid water bodies, slightly eutrophic water bodies, moderately eutrophic water bodies, severely eutrophic water bodies, turbid and eutrophic water bodies, black and smelly water bodies, slight algal bloom and severe algal bloom.
具体地，计算25个类别的平均光谱，利用逐步迭代K-means对25条平均光谱进行合并，图3为采用逐步迭代K-means从25到10类的迭代过程，从图中可以看出，从15-25类类间距变化不大，没有明显特征，分为13类和15类较为典型，类间距在这两类都有较大变化，可以作为最终分类数目。根据对比最终合并效果，发现13类水体更具有实际物理意义，因此，本研究将所有遥感反射率数据分为13类。内陆水体光学分类体系如图4所示。Specifically, the average spectra of 25 categories are calculated, and the 25 average spectra are merged using stepwise iterative K-means. Figure 3 shows the iterative process from 25 to 10 categories using stepwise iterative K-means. It can be seen from the figure that the class spacing from 15 to 25 categories does not change much, and there is no obvious feature. It is more typical to divide it into 13 and 15 categories. The class spacing has a large change in these two categories, which can be used as the final classification number. According to the comparison of the final merging effect, it is found that the 13-category water body has more practical physical significance. Therefore, this study divides all remote sensing reflectance data into 13 categories. The optical classification system of inland water bodies is shown in Figure 4.
如图5所示，高度清洁水体的光学特征为：蓝波段反射率较高，红和近红外很低；As shown in Figure 5, the optical characteristics of highly clean water are: high reflectivity in the blue band, and very low reflectivity in the red and near-infrared bands;
如图6所示，清洁水体的光学特征为：深蓝波段反射率下降，但反射率峰值仍然在蓝波段；As shown in Figure 6, the optical characteristics of clean water are: the reflectivity of the deep blue band decreases, but the reflectivity peak is still in the blue band;
如图7所示，一般清洁水体的光学特征为：蓝波段反射率降低，绿波段形成反射峰；As shown in Figure 7, the optical characteristics of a general clean water body are: the reflectivity of the blue band decreases, and a reflection peak is formed in the green band;
如图8所示，轻度浑浊水体的光学特征为：绿波段到红波段反射率呈下降趋势，近红外波段开始升高；As shown in Figure 8 , the optical characteristics of slightly turbid water bodies are as follows: the reflectivity decreases from the green band to the red band and begins to increase in the near-infrared band;
如图9所示，中度浑浊水体的光学特征为：红和近红外波段反射率升高明显；As shown in Figure 9, the optical characteristics of moderately turbid water bodies are: the reflectance in the red and near-infrared bands increases significantly;
如图10所示，高度浑浊水体的光学特征为：红和近红外波段反射率升高明显，红波段反射率和绿波段相当或高于绿波段；As shown in Figure 10, the optical characteristics of highly turbid water bodies are: the reflectance in the red and near-infrared bands increases significantly, and the reflectance in the red band is equivalent to or higher than that in the green band;
如图11所示，轻度富营养化水体的光学特征为：绿波段反射峰明显，红边波段反射峰较低；As shown in Figure 11, the optical characteristics of slightly eutrophic water bodies are: the green band reflection peak is obvious, and the red edge band reflection peak is low;
如图12所示，中度富营养化水体的光学特征为：绿波段反射峰明显，红边波段反射峰升高；As shown in Figure 12, the optical characteristics of moderately eutrophic water bodies are: the green band reflection peak is obvious, and the red edge band reflection peak is increased;
如图13所示，重度富营养化水体的光学特征为：红边波段反射峰较高，高度和绿波段相当；As shown in Figure 13, the optical characteristics of severely eutrophic water bodies are: the red edge band reflection peak is relatively high, and its height is comparable to that of the green band;
如图14所示，浑浊富营养化水体的光学特征为：红和近红外波段反射率较高，且红边波段反射峰明显；As shown in Figure 14, the optical characteristics of turbid eutrophic water bodies are: high reflectivity in the red and near-infrared bands, and an obvious reflection peak in the red edge band;
如图15所示，黑臭水体的光学特征为：反射率比一般水体低且曲线平坦，无明显的峰谷特征；As shown in Figure 15, the optical characteristics of black and odorous water bodies are: the reflectivity is lower than that of ordinary water bodies and the curve is flat, without obvious peak and valley characteristics;
如图16所示，轻度水华的光学特征为：红边波段反射率最高，近红外波段有所降低，但高于红波段；As shown in Figure 16, the optical characteristics of mild water bloom are as follows: the reflectivity is highest in the red edge band, which decreases slightly in the near infrared band but is higher than the red band;
如图17所示，重度水华的光学特征为：红边和近红外波段反射率很高且曲线平坦，近红外波段降低趋势不明显。本发明第三方面公开了一种电子设备。电子设备包括存储器和处理器，存储器存储有计算机程序，处理器执行计算机程序时，实现本发明公开第一方面中任一项的一种内陆水体光学分类方法中的步骤。As shown in FIG17 , the optical characteristics of severe water bloom are: the reflectivity in the red edge and near-infrared bands is very high and the curve is flat, and the near-infrared band has no obvious decreasing trend. The third aspect of the present invention discloses an electronic device. The electronic device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the steps of any one of the inland water optical classification methods disclosed in the first aspect of the present invention are implemented.
图19为根据本发明实施例的一种电子设备的结构图，如图19所示，电子设备包括通过系统总线连接的处理器、存储器、通信接口、显示屏和输入装置。其中，该电子设备的处理器用于提供计算和控制能力。该电子设备的存储器包括非易失性存储介质、内存储器。该非易失性存储介质存储有操作系统和计算机程序。该内存储器为非易失性存储介质中的操作系统和计算机程序的运行提供环境。该电子设备的通信接口用于与外部的终端进行有线或无线方式的通信，无线方式可通过WIFI、运营商网络、近场通信(NFC)或其他技术实现。该电子设备的显示屏可以是液晶显示屏或者电子墨水显示屏，该电子设备的输入装置可以是显示屏上覆盖的触摸层，也可以是电子设备外壳上设置的按键、轨迹球或触控板，还可以是外接的键盘、触控板或鼠标等。FIG19 is a block diagram of an electronic device according to an embodiment of the present invention. As shown in FIG19 , the electronic device includes a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the electronic device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, an operator network, near field communication (NFC) or other technologies. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covered on the display screen, or a button, a trackball or a touchpad provided on the housing of the electronic device, or an external keyboard, touchpad or mouse, etc.
本领域技术人员可以理解，图19中示出的结构，仅仅是与本公开的技术方案相关的部分的结构图，并不构成对本申请方案所应用于其上的电子设备的限定，具体的电子设备可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。Those skilled in the art will understand that the structure shown in FIG. 19 is merely a structural diagram of the portion related to the technical solution of the present disclosure, and does not constitute a limitation on the electronic device to which the technical solution of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.
本发明第四方面公开了一种计算机可读存储介质。计算机可读存储介质上存储有计算机程序，计算机程序被处理器执行时，实现本发明公开第一方面中任一项的一种内陆水体光学分类方法中的步骤。The fourth aspect of the present invention discloses a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any one of the inland water optical classification methods disclosed in the first aspect of the present invention are implemented.
请注意，以上实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。以上实施例仅表达了本申请的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对发明专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本申请构思的前提下，还可以做出若干变形和改进，这些都属于本申请的保护范围。因此，本申请专利的保护范围应以所附权利要求为准。Please note that the technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification. The above embodiments only express several implementation methods of the present application, and their descriptions are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that for ordinary technicians in this field, without departing from the concept of the present application, several variations and improvements can be made, which all belong to the scope of protection of the present application. Therefore, the scope of protection of the patent in this application shall be based on the attached claims.
Claims (5)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311253664.4A CN117312973B (en) | 2023-09-26 | 2023-09-26 | Inland water body optical classification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311253664.4A CN117312973B (en) | 2023-09-26 | 2023-09-26 | Inland water body optical classification method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117312973A CN117312973A (en) | 2023-12-29 |
| CN117312973B true CN117312973B (en) | 2024-05-03 |
Family
ID=89286044
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311253664.4A Active CN117312973B (en) | 2023-09-26 | 2023-09-26 | Inland water body optical classification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117312973B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106650810A (en) * | 2016-12-26 | 2017-05-10 | 河海大学 | Spectrum attribute information and space information based reservoir water body classification method and device |
| CN107330875A (en) * | 2017-05-31 | 2017-11-07 | 河海大学 | Based on the forward and reverse heterogeneous water body surrounding enviroment change detecting method of remote sensing images |
| CN111179218A (en) * | 2019-12-06 | 2020-05-19 | 深圳市派科斯科技有限公司 | Conveyor belt material detection method and device, storage medium and terminal equipment |
| CN113159167A (en) * | 2021-04-19 | 2021-07-23 | 福州大学 | Inland-based chlorophyll a inversion method for different types of water bodies |
| CN113406015A (en) * | 2021-05-31 | 2021-09-17 | 内蒙古师范大学 | Transparency calculation method and system for water bodies of near-shore and inland waters |
| WO2023000160A1 (en) * | 2021-07-20 | 2023-01-26 | 海南长光卫星信息技术有限公司 | Hyperspectral remote sensing image semi-supervised classification method, apparatus, and device, and storage medium |
| WO2023134626A1 (en) * | 2022-01-11 | 2023-07-20 | 北华航天工业学院 | Malodorous black water body extraction method based on cart classification model |
-
2023
- 2023-09-26 CN CN202311253664.4A patent/CN117312973B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106650810A (en) * | 2016-12-26 | 2017-05-10 | 河海大学 | Spectrum attribute information and space information based reservoir water body classification method and device |
| CN107330875A (en) * | 2017-05-31 | 2017-11-07 | 河海大学 | Based on the forward and reverse heterogeneous water body surrounding enviroment change detecting method of remote sensing images |
| CN111179218A (en) * | 2019-12-06 | 2020-05-19 | 深圳市派科斯科技有限公司 | Conveyor belt material detection method and device, storage medium and terminal equipment |
| CN113159167A (en) * | 2021-04-19 | 2021-07-23 | 福州大学 | Inland-based chlorophyll a inversion method for different types of water bodies |
| CN113406015A (en) * | 2021-05-31 | 2021-09-17 | 内蒙古师范大学 | Transparency calculation method and system for water bodies of near-shore and inland waters |
| WO2023000160A1 (en) * | 2021-07-20 | 2023-01-26 | 海南长光卫星信息技术有限公司 | Hyperspectral remote sensing image semi-supervised classification method, apparatus, and device, and storage medium |
| WO2023134626A1 (en) * | 2022-01-11 | 2023-07-20 | 北华航天工业学院 | Malodorous black water body extraction method based on cart classification model |
Non-Patent Citations (3)
| Title |
|---|
| SHUN BI 等.Optical classification of inland waters based on an improved Fuzzy C-Means method.《Optics Express》.2019,第27卷(第24期),1-19. * |
| 张方方 等.高分一号卫星浑浊水体水质参数软分类反演.《遥感学报》.2023,第27卷(第3期),第3.1、3.3节. * |
| 王相海等.一种基于2D-PLDA和小波子带的虹膜识别算法.《中国图象图形学报》.2011,第16卷(第1期),第2节. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117312973A (en) | 2023-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111723876B (en) | Load curve integrated spectrum clustering method considering double-scale similarity | |
| Nayak et al. | Classification of tumor histopathology via sparse feature learning | |
| CN110717368A (en) | Qualitative classification method for textiles | |
| CN107220764A (en) | A kind of electricity sales amount Forecasting Methodology compensated based on preamble analysis and factor and device | |
| David et al. | Hierarchical data organization, clustering and denoising via localized diffusion folders | |
| CN108764138A (en) | A kind of highlands cloud snow sorting technique cascading forest based on the more granularities of multidimensional | |
| CN107037001A (en) | A kind of corn monoploid seed discrimination method based on near-infrared spectrum technique | |
| CN113298058A (en) | Water quality prediction inversion method and system based on hyperspectral image of unmanned aerial vehicle | |
| CN114463637A (en) | Winter wheat remote sensing identification analysis method and system based on deep learning | |
| CN105279524A (en) | High-dimensional data clustering method based on unweighted hypergraph segmentation | |
| CN117312973B (en) | Inland water body optical classification method and system | |
| CN117437633A (en) | Chromosome image quality assessment method, device, computer equipment and storage medium | |
| CN109271874B (en) | Hyperspectral image feature extraction method fusing spatial and spectral information | |
| Marchetti | Convergence rate in terms of the continuous SSIM (cSSIM) index in RBF interpolation | |
| Istepanian et al. | Comparative analysis of genomic signal processing for microarray data clustering | |
| CN118706680A (en) | Jet fuel multi-index detection method, system, medium and electronic device | |
| US20240255284A2 (en) | Devices, systems and method for analysis and characterization of surface topography | |
| Zhang et al. | Hyperspectral image unsupervised classification using improved connection center evolution | |
| CN111637849A (en) | Method, device and equipment for measuring morphology parameters | |
| CN106530238A (en) | Feature-preserving filtering method of scattered point cloud | |
| Yao et al. | Covariate information matrix for sufficient dimension reduction | |
| CN116343032A (en) | A Classification Method Combining Gaussian Regression Mixture Model and MRF Hyperspectral Function Data | |
| CN115985415A (en) | Prediction method of common physical and chemical properties of organic molecules based on multiple learning models | |
| Zhang et al. | DSL: discriminative subgraph learning via sparse self-representation | |
| CN115129503A (en) | A method and system for cleaning equipment fault data |
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 |