WO2018137103A1 - 一种基于多源遥感数据的流域污染检测方法及系统 - Google Patents

一种基于多源遥感数据的流域污染检测方法及系统 Download PDF

Info

Publication number
WO2018137103A1
WO2018137103A1 PCT/CN2017/072374 CN2017072374W WO2018137103A1 WO 2018137103 A1 WO2018137103 A1 WO 2018137103A1 CN 2017072374 W CN2017072374 W CN 2017072374W WO 2018137103 A1 WO2018137103 A1 WO 2018137103A1
Authority
WO
WIPO (PCT)
Prior art keywords
remote sensing
pollution
sensing data
source remote
source
Prior art date
Application number
PCT/CN2017/072374
Other languages
English (en)
French (fr)
Inventor
熊益冲
Original Assignee
深圳企管加企业服务有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 深圳企管加企业服务有限公司 filed Critical 深圳企管加企业服务有限公司
Priority to PCT/CN2017/072374 priority Critical patent/WO2018137103A1/zh
Publication of WO2018137103A1 publication Critical patent/WO2018137103A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition

Definitions

  • the invention relates to the field of multi-source remote sensing technology, in particular to a watershed pollution detection method and system based on multi-source remote sensing data.
  • a basin is the entire area through which the main stream and tributaries of a water system flow.
  • the pollution caused by harmful substances entering the watershed environment will damage biological resources, endanger human health, hinder fishing and other human activities in the basin, and damage the water quality and environmental quality of the river basin, causing damage to the ecosystem.
  • environmental and pollution problems become more serious, investment in watershed pollution monitoring is increasing year by year.
  • Conventional monitoring methods for watersheds are point-to-face, large in manpower, high in cost, and subjective. Remote sensing has the advantage of large-area, fast, dynamic and low-cost access to regional information.
  • the embodiment of the invention provides a watershed pollution detection method and system based on multi-source remote sensing data, and forms an overall solution on full-link integration of remote sensing data acquisition, analysis, management and display.
  • a first aspect of the embodiments of the present invention discloses a watershed pollution detection method based on multi-source remote sensing data, including:
  • the smoke fluctuation analysis is performed on the detection area where the pollution accident occurs, and a pollution accident material diffusion model is generated;
  • the location of the source of the accident is obtained based on the pollution accident material diffusion model.
  • the acquiring the multi-source remote sensing data of the detection area in the watershed environment includes:
  • multi-source remote sensing data of the detection area Acquiring, by the environmental pollution detecting device of the detection area, multi-source remote sensing data of the detection area from various earth observation satellites, wherein the multi-source remote sensing data comprises a multi-source remote sensing satellite image;
  • the preprocessing the multi-source remote sensing data includes:
  • Radiation correction, geometric correction and remote sensing image fusion processing are performed on the multi-source remote sensing image in the multi-source remote sensing data.
  • the determining whether the value of the extracted pollution information exceeds a preset pollutant determination threshold specifically includes:
  • the pollution information includes a plurality of pollutant information, and correspondingly includes a plurality of pollutant determination thresholds;
  • a second aspect of the embodiments of the present invention discloses a watershed pollution detection system based on multi-source remote sensing data, including:
  • An obtaining unit configured to acquire multi-source remote sensing data of a detection area in a watershed environment
  • An extracting unit configured to perform pollution information extraction on the multi-source remote sensing data
  • a determining unit configured to determine whether the value of the extracted pollution information exceeds a preset pollutant determination threshold
  • the determining unit is configured to determine that a pollution accident occurs in the detection area if the determination threshold is exceeded.
  • system further includes:
  • An analysis unit is configured to perform smoke turbulence analysis on the detection area where the pollution accident has occurred, and generate a pollution accident material diffusion model
  • a position determining unit configured to obtain a location of the accident source according to the pollution accident material diffusion model.
  • the acquiring unit is specifically configured to acquire, by using an environmental pollution detecting device of the detection area, multi-source remote sensing data of the detection area from various earth observation satellites, the multi-source remote sensing The data includes multi-source remote sensing satellite images;
  • the system further includes: a pre-processing unit, configured to perform pre-processing on the multi-source remote sensing data;
  • the storage unit is configured to store the pre-processed multi-source remote sensing data.
  • the pre-processing unit is specifically configured to perform radiation correction, geometric correction, and remote sensing image fusion processing on the multi-source remote sensing image in the multi-source remote sensing data.
  • system further includes:
  • a setting unit configured to pre-set each pollutant determination threshold corresponding to each area in the database
  • the determining unit is configured to compare the extracted pollution information with the corresponding pollutant determination threshold, where the pollution information includes a plurality of pollutant information, and the plurality of pollutant determination thresholds are correspondingly included;
  • the determining unit is further configured to determine whether the pollution value of any one of the extracted pollutants is greater than a stored threshold of the pollutant, and if yes, determine that the value of the extracted pollution information has exceeded a predetermined pollution The object determines the threshold.
  • the multi-source remote sensing data of the detection area in the watershed environment is acquired; the pollution information is extracted from the multi-source remote sensing data; and whether the value of the extracted pollution information exceeds a preset pollutant determination threshold; If the determination threshold is exceeded, it is determined that a pollution accident has occurred in the detection area. It can be seen that the implementation of the embodiments of the present invention can collect, analyze, and manage remote sensing data, and can judge the location of pollution accidents and accident sources, and improve the treatment and response speed of watershed pollution.
  • FIG. 1 is a schematic flow chart of a method for detecting a watershed pollution based on multi-source remote sensing data according to a first embodiment of the present invention
  • FIG. 2 is a schematic structural diagram of a watershed pollution detection system based on multi-source remote sensing data according to a second embodiment of the present invention.
  • the embodiment of the invention provides a multi-point thermometer reporting method based on the Internet of Things, which can report the temperature to the monitoring center or record the historical temperature curve, and view the temperature condition anytime and anywhere through the mobile device.
  • FIG. 1 is a schematic flowchart diagram of a watershed pollution detection method based on multi-source remote sensing data according to a first embodiment of the present invention.
  • the watershed pollution detection method based on the multi-source remote sensing data shown in FIG. 1 may include the following steps:
  • the multi-source remote sensing data of the detection area is acquired from various earth observation satellites by the environmental pollution detecting device of the detection area, and the multi-source remote sensing data includes a multi-source remote sensing satellite image;
  • the multi-source remote sensing data is preprocessed, and specifically comprises performing radiation correction, geometric correction and remote sensing image fusion processing on the multi-source remote sensing image in the multi-source remote sensing data.
  • the preprocessed multi-source remote sensing data is stored.
  • Remote Sensing Image Radiation Correction Due to the response characteristics of the sensor and the absorption, scattering and other random factors of the atmosphere, the image is blurred and the resolution and contrast of the image are relatively reduced. These need to be restored by radiation correction to eliminate the attachment of remote sensing image data. The process of various distortions in radiance is radiation corrected.
  • Remote Sensing Image Geometric Correction There are two kinds of geometric corrections for remote sensing digital images. One is to calculate the position of each satellite on the basis of the satellite's position, attitude, orbit, shape of the earth's surface and scanning characteristics as a function of time. Coordinates, this correction often results in a small error in the corrected image due to the low accuracy of the position and attitude measurement of the remote sensing sensor. Therefore, it is also called coarse geometric correction.
  • the coarse correction is generally carried out by remote sensing data producers, such as satellite remote sensing ground stations or remote sensing companies.
  • fine geometric correction is performed on coarse geometrically corrected images, which requires ground control points. Performed with calibration models such as polynomials.
  • Geometric correction is performed by using control points. It uses a mathematical model to approximate the geometric distortion process of remote sensing images, and uses this geometry of some corresponding points (ie, control points) between the distorted remote sensing image and the standard map. Distortion model, then using the submodel Correction of geometric distortion, which does not take into account the specific cause of the distortion, but only considers how to use the distortion model to correct the image.
  • Image Fusion Technology is an information fusion of images as research objects. It uses multiple images obtained by different sensors for the same target or scene, or different images obtained by different sensors or different imaging times. The image is fused into an image in which the information of multiple original images can be reflected to achieve a comprehensive description of the target and the ground object.
  • Multi-source remote sensing data refers to remote sensing images of the same area obtained by multiple sensors or remote sensing image data of the same area obtained by the same sensor at different times.
  • Multi-source information fusion can enrich the complementary information of different data sources in the same area, reduce data inaccuracy, reduce data ambiguity, and make classification more accurate and reliable, so as to form a complete and consistent information description of the target area.
  • the pollution information includes a plurality of pollutant information, and correspondingly includes a plurality of pollutant determination thresholds;
  • the accident source identification unit performs smoke fluttering analysis on a plurality of multi-source remote sensing images in the multi-source remote sensing data of the detection area where the pollution accident has occurred, and generates a pollution accident material diffusion vector diagram.
  • the accidental material diffusion vector diagram and the actual conditions of the location scene of the detection area where the pollution accident occurred are used to establish the pollution accident material diffusion model, and the neural network combination optimization algorithm is used to dynamically adjust the input conditions of the pollution accident material diffusion model to make the input conditions and
  • the above-mentioned pollution accident material diffusion vector diagrams are consistent or approximately consistent, and the optimization of the pollution accident material diffusion model is completed.
  • the process of generating the pollution vector of pollution accidents is mainly to use the remote sensing images of different time to generate the diffusion of pollution accident materials, and then use the buffer technology of GIS technology to describe the pollution diffusion vector.
  • Air pollution model The purpose of studying the law of atmospheric pollutant diffusion under different meteorological conditions is to: (1) provide scientific basis for industrial planning and layout according to local meteorological conditions, and prevent possible air pollution; 2 according to local atmospheric diffusion capacity and environmental sanitation standards , propose emission standards (emissions and emission heights); 3 conduct air pollution forecasting in order to take emergency measures in a planned manner to prevent deterioration of environmental quality (long-term) and prevent possible pollution accidents (short-term).
  • Diffusion theory has two ways to study the process of air pollution diffusion: one is the experimental method, which is to determine the concentration distribution of pollutants for a given source, and to find out the relationship between concentration, space and meteorological conditions. Explore its laws. This method can also be implemented in the laboratory by wind tunnel simulation. The other is the theoretical method, which uses the theory of turbulent exchange to establish a model describing the diffusion and dilution process of atmospheric pollution (see air pollution mode), and to find out the relationship between concentration distribution and meteorological parameters.
  • the location of the accident source of the pollution accident is determined according to the solution result.
  • the multi-source remote sensing data of the detection area in the watershed environment is acquired; the pollution information is extracted from the multi-source remote sensing data; and whether the value of the extracted pollution information exceeds a preset pollutant determination threshold; If the determination threshold is exceeded, it is determined that a pollution accident has occurred in the detection area. It can be seen that the embodiments of the present invention can implement remote sensing data collection, analysis, management, and pollution The location of accidents and accident sources has improved the treatment and response speed of watershed pollution.
  • the system embodiment of the present invention is used to implement the method for implementing the first embodiment of the method of the present invention.
  • FIG. 2 is a structural diagram of a watershed pollution detection system based on multi-source remote sensing data according to a second embodiment of the present invention.
  • the system can include:
  • the obtaining unit 201 is configured to acquire multi-source remote sensing data of the detection area in the watershed environment.
  • the multi-source remote sensing data of the detection area is acquired from various earth observation satellites by the environmental pollution detecting device of the detection area, and the multi-source remote sensing data includes multi-source remote sensing. Satellite image; then preprocessing the multi-source remote sensing data, specifically comprising performing radiation correction, geometric correction and remote sensing image fusion processing on the multi-source remote sensing image in the multi-source remote sensing data. Finally, the preprocessed multi-source remote sensing data is stored.
  • Multi-source remote sensing data refers to remote sensing images of the same area obtained by multiple sensors or remote sensing image data of the same area obtained by the same sensor at different times.
  • Multi-source information fusion can enrich the complementary information of different data sources in the same area, reduce data inaccuracy, reduce data ambiguity, and make classification more accurate and reliable, so as to form a complete and consistent information description of the target area.
  • the extracting unit 202 is configured to perform pollution information extraction on the multi-source remote sensing data.
  • the determining unit 203 is configured to determine whether the value of the extracted pollution information exceeds a preset pollutant determination threshold.
  • each pollutant determination threshold corresponding to each region is preset in a database, and the extracted pollution information and the corresponding pollutant determination threshold are compared, and the pollution information is compared.
  • the method includes a plurality of pollutant information, corresponding to the plurality of pollutant determination thresholds, determining whether the pollution value of any one of the extracted pollutants is greater than a stored threshold of the pollutants, and if yes, determining the extracted pollution information. The value has exceeded the preset contaminant determination threshold.
  • the determining unit 204 is configured to determine that a pollution accident occurs in the detection area if the determination threshold is exceeded.
  • the pollution information includes a plurality of pollutant information, and correspondingly includes a plurality of pollutant determination thresholds;
  • the analyzing unit 205 is configured to perform smoke turbulence analysis on the detection area where the pollution accident has occurred, and generate a pollution accident material diffusion model;
  • the location determining unit 206 is configured to obtain a location of the source of the accident according to the pollution accident material diffusion model.
  • the accident source identification unit performs smoke fluttering analysis on a plurality of multi-source remote sensing images in the multi-source remote sensing data of the detection area where the pollution accident has occurred, and generates a pollution accident material diffusion vector diagram.
  • the accidental material diffusion vector diagram and the actual conditions of the location scene of the detection area where the pollution accident occurred are used to establish the pollution accident material diffusion model, and the neural network combination optimization algorithm is used to dynamically adjust the input conditions of the pollution accident material diffusion model to make the input conditions and
  • the above-mentioned pollution accident material diffusion vector diagrams are consistent or approximately consistent, and the optimization of the pollution accident material diffusion model is completed.
  • the process of generating the pollution vector of pollution accidents is mainly to use the remote sensing images of different time to generate the diffusion of pollution accident materials, and then use the buffer technology of GIS technology to describe the pollution diffusion vector.
  • Air pollution model The purpose of studying the law of atmospheric pollutant diffusion under different meteorological conditions is to: (1) provide scientific basis for industrial planning and layout according to local meteorological conditions, and prevent possible air pollution; 2 according to local atmospheric diffusion capacity and environmental sanitation standards , propose emission standards (emissions and emission heights); 3 conduct air pollution forecasting in order to take emergency measures in a planned manner to prevent deterioration of environmental quality (long-term) and prevent possible pollution accidents (short-term).
  • Diffusion theory has two ways to study the process of air pollution diffusion: one is the experimental method, which is to determine the concentration distribution of pollutants for a given source, and to find out the relationship between concentration, space and meteorological conditions. Explore its laws. This method can also be implemented in the laboratory by wind tunnel simulation. The other is the theoretical method, which uses the theory of turbulent exchange to establish a model describing the diffusion and dilution process of atmospheric pollution (see air pollution mode), and to find out the relationship between concentration distribution and meteorological parameters.
  • the location of the accident source of the pollution accident is determined according to the solution result.
  • the pre-processing unit 207 is configured to perform pre-processing on the multi-source remote sensing data.
  • the preprocessing specifically includes performing radiation correction, geometric correction, and remote sensing image fusion processing on the multi-source remote sensing image in the multi-source remote sensing data.
  • Remote Sensing Image Radiation Correction Due to the response characteristics of the sensor and the absorption, scattering and other random factors of the atmosphere, the image is blurred and the resolution and contrast of the image are relatively reduced. These need to be restored by radiation correction to eliminate the attachment of remote sensing image data. The process of various distortions in radiance is radiation corrected.
  • Remote Sensing Image Geometric Correction There are two kinds of geometric corrections for remote sensing digital images. One is to calculate the position of each satellite on the basis of the satellite's position, attitude, orbit, shape of the earth's surface and scanning characteristics as a function of time. Coordinates, this correction often results in a small error in the corrected image due to the low accuracy of the position and attitude measurement of the remote sensing sensor. Therefore, it is also called coarse geometric correction.
  • the coarse correction is generally carried out by remote sensing data producers, such as satellite remote sensing ground stations or remote sensing companies.
  • fine geometric correction is performed on coarse geometrically corrected images, which requires ground control points. Performed with calibration models such as polynomials.
  • Geometric correction is performed by using control points. It uses a mathematical model to approximate the geometric distortion process of remote sensing images, and uses this geometry of some corresponding points (ie, control points) between the distorted remote sensing image and the standard map. The distortion model is then corrected for the geometric distortion using the sub-model. This correction does not take into account the specific cause of the distortion, but only considers how to use the distortion model to correct the image.
  • Image Fusion Technology is an information fusion of images as research objects. It uses multiple images obtained by different sensors for the same target or scene, or different images obtained by different sensors or different imaging times. The image is fused into an image in which the information of multiple original images can be reflected to achieve a comprehensive description of the target and the ground object.
  • the storage unit 208 is configured to store the pre-processed multi-source remote sensing data.
  • the setting unit 209 is configured to pre-set each pollutant determination threshold corresponding to each region in the database
  • the multi-source remote sensing data of the detection area in the watershed environment is acquired; the pollution information is extracted from the multi-source remote sensing data; and whether the value of the extracted pollution information exceeds a preset pollutant determination threshold; If the determination threshold is exceeded, it is determined that a pollution accident has occurred in the detection area. It can be seen that the implementation of the embodiments of the present invention can collect, analyze, and manage remote sensing data, and can judge the location of pollution accidents and accident sources, and improve the treatment and response speed of watershed pollution.
  • the embodiment of the present invention further provides a computer storage medium, wherein the computer storage medium can store a program, and the program includes a part or all steps of a monitoring method of any one of the service processes in the method embodiment.
  • the insufficiency of the method of the embodiment of the present invention may be adjusted, merged, or deleted according to actual needs.
  • the unit of the terminal in the embodiment of the present invention may be integrated, further divided or deleted according to actual needs.
  • the disclosed system may be implemented in other manners, for example, the system embodiments described above are illustrative, such as the unit Dividing, for a logical function division, may be further divided in actual implementation, for example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an inductive or communication connection through some interface, device or unit, and may be electrical or otherwise.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. . Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • each unit included is only divided according to functional logic, but is not limited to the above division, as long as the corresponding The functions of the functional units are only for the purpose of facilitating mutual differentiation and are not intended to limit the scope of the present invention.
  • ROM Read-Only Memory
  • RAM Random Access Memory
  • PROM Programmable Read-Only Memory
  • Erasable Programmable Read Only Memory Erasable Programmable Read Only Memory
  • EPROM One-time Programmable Read-Only Memory
  • OTPROM One-time Programmable Read-Only Memory
  • EEPROM Electronically-Erasable Programmable Read-Only Memory
  • CD-ROM Compact Disc Read-Only Memory

Abstract

一种基于多源遥感数据的流域污染检测方法及系统,其中方法包括:获取流域环境中的检测区域的多源遥感数据(101);对所述多源遥感数据进行污染信息提取(102);判断提取出的污染信息的数值是否超过预先设定的污染物判断阈值(103);若超过判断阈值,则确定所述检测区域发生了污染事故(104)。由此可见,该方法可对遥感数据采集、分析、管理,并可对污染事故和事故源位置判断,提高了对流域污染的处理及应对速度。

Description

一种基于多源遥感数据的流域污染检测方法及系统 技术领域
本发明涉及多源遥感技术领域,尤其涉及一种基于多源遥感数据的流域污染检测方法及系统。
背景技术
近几十年,随着世界工业的发展,流域的污染也日趋加重。流域是指一个水系的干流和支流所流过的整个地区。有害物质进入流域环境而造成的污染,会损害生物资源,危害人类健康,妨碍捕鱼和人类在流域的其他活动,损坏流域水质和环境质量等,使生态系统遭到破坏。随着环境与污染问题日趋加重,对流域污染监测的投资在逐年增加。常规对于流域的监测手段以点代面、人力投入大、成本高、主观性强。遥感具有大面积、快速、动态、低成本获取区域信息的优势,由于流域污染物的复杂性,如何从大量的遥感图像中识别并跟踪污染物目标已成为一个亟需解决的科学前沿问题。然而,真正实现“多源”遥感数据采集与应用的系统尚不成熟。在流域遥感监测应用方面基本空白,仍停留在采样水质分析阶段。而并没有在遥感数据采集、分析、管理、展示等全链路集成上形成整体解决方案。
发明内容
本发明实施例提供了一种基于多源遥感数据的流域污染检测方法及系统,在遥感数据采集、分析、管理、展示等全链路集成上形成整体解决方案。
本发明实施例第一方面公开了一种基于多源遥感数据的流域污染检测方法,包括:
获取流域环境中的检测区域的多源遥感数据;
对所述多源遥感数据进行污染信息提取;
判断提取出的污染信息的数值是否超过预先设定的污染物判断阈值;
若超过判断阈值,则确定所述检测区域发生了污染事故。
作为一种可选的实施方式,对所述发生了污染事故的检测区域进行烟雾飘动性分析,生成污染事故物质扩散模型;
根据所述污染事故物质扩散模型得到事故源的位置。
作为一种可选的实施方式,所述获取流域环境中的检测区域的多源遥感数据,具体包括:
通过所述检测区域的环境污染检测装置从各种对地观测卫星获取所述检测区域的多源遥感数据,所述多源遥感数据包括多源遥感卫星图像;
对所述多源遥感数据进行预处理;
存储预处理后的多源遥感数据。
作为一种可选的实施方式,所述对所述多源遥感数据进行预处理,具体包括:
对所述多源遥感数据中的多源遥感图像进行辐射校正、几何校正和遥感图像融合处理。
作为一种可选的实施方式,所述判断提取出的污染信息的数值是否超过预先设定的污染物判断阈值,具体包括:
在数据库中预先设置各区域对应的各个污染物判断阈值;
将所述提取出的污染信息和所述对应的污染物判断阈值进行比较,所述污染信息包括多个污染物信息,对应包括多个污染物判断阈值;
判断是否提取出的任何一个污染物的污染值大于存储的该污染物的判断阈值,如果是,则确定所述提取出的污染信息的数值已超过预先设定的污染物判断阈值。
本发明实施例第二方面公开了一种基于多源遥感数据的流域污染检测系统,包括:
获取单元,用于获取流域环境中的检测区域的多源遥感数据;
提取单元,用于对所述多源遥感数据进行污染信息提取;
判断单元,用于判断提取出的污染信息的数值是否超过预先设定的污染物判断阈值,
确定单元,用于若超过判断阈值时,则确定所述检测区域发生了污染事故。
作为一种可选的实施方式,所述系统还包括:
分析单元,用于对所述发生了污染事故的检测区域进行烟雾飘动性分析,生成污染事故物质扩散模型;
位置确定单元,用于根据所述污染事故物质扩散模型得到事故源的位置。
作为一种可选的实施方式,所述获取单元,具体用于通过所述检测区域的环境污染检测装置从各种对地观测卫星获取所述检测区域的多源遥感数据,所述多源遥感数据包括多源遥感卫星图像;
所述系统还包括:预处理单元,用于对所述多源遥感数据进行预处理;
存储单元,用于存储预处理后的多源遥感数据。
作为一种可选的实施方式,所述预处理单元,具体用于对所述多源遥感数据中的多源遥感图像进行辐射校正、几何校正和遥感图像融合处理。
作为一种可选的实施方式,所述系统还包括:
设置单元,用于在数据库中预先设置各区域对应的各个污染物判断阈值;
所述判断单元,具体用于将所述提取出的污染信息和所述对应的污染物判断阈值进行比较,所述污染信息包括多个污染物信息,对应包括多个污染物判断阈值;
所述判断单元还用于判断是否提取出的任何一个污染物的污染值大于存储的该污染物的判断阈值,如果是,则确定所述提取出的污染信息的数值已超过预先设定的污染物判断阈值。
从以上技术方案可以看出,本发明实施例具有以下优点:
本发明实施例中,获取流域环境中的检测区域的多源遥感数据;对所述多源遥感数据进行污染信息提取;判断提取出的污染信息的数值是否超过预先设定的污染物判断阈值;若超过判断阈值,则确定所述检测区域发生了污染事故。由此可见,实施本发明实施例,可对遥感数据采集、分析、管理,并可对污染事故和事故源位置判断,提高了对流域污染的处理及应对速度。
附图说明
为了更清楚地说明本发明实施例中的技术方案,下面将对实施例描述中所 需要使用的附图作简要介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域的普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1为本发明第一实施例公开的一种基于多源遥感数据的流域污染检测方法的流程示意图;
图2为本发明第二实施例公开的一种一种基于多源遥感数据的流域污染检测系统的结构示意图。
具体实施方式
为了使本发明的目的、技术方案和优点更加清楚,下面将结合附图对本发明作进一步地详细描述,显然,所描述的实施例仅仅是本发明一部份实施例,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它实施例,都属于本发明保护的范围。
本发明的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别不同的对象,而不是用于描述特定顺序。此外,术语“包括”和“具有”以及它们任何变形,意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元,而是可选地还包括没有列出的步骤或单元,或可选地还包括对于这些过程、方法或设备固有的其他步骤或单元。
在本文中提及实施例意味着,结合实施例描述的特定特征、结构或特性可以包含在本发明的至少一个实施例中。在说明书的各个位置出现该短语并不一定均是指相同的实施例,也不是与其他实施例互斥的独立的或备选的实施例。本领域技术人员显式地和隐式地理解的是,本文所描述的实施例可以与其他实施例相结合。
本发明实施例提供了一种基于物联网的多点测温仪上报方法,可以将温度上报监控中心,也可以记录历史温度曲线,通过移动设备随时随地查看温度状况。
请参阅图1,图1是本发明第一实施例公开的一种基于多源遥感数据的流域污染检测方法的流程示意图。其中,图1所示的基于多源遥感数据的流域污染检测方法可以包括以下步骤:
101、获取流域环境中的检测区域的多源遥感数据。
本发明实施例中,通过所述检测区域的环境污染检测装置从各种对地观测卫星获取所述检测区域的多源遥感数据,所述多源遥感数据包括多源遥感卫星图像;接着对所述多源遥感数据进行预处理,具体包括对所述多源遥感数据中的多源遥感图像进行辐射校正、几何校正和遥感图像融合处理。最后存储预处理后的多源遥感数据。
遥感图像辐射校正:由于传感器响应特性和大气的吸收、散射以及其他随机因素影响,导致图像模糊失真,造成图像的分辨率和对比度相对下降,这些都需要通过辐射校正复原,消除遥感图像数据中依附在辐射亮度中的各种失真的过程为辐射校正。
遥感图像几何校正:遥感数字图像的几何校正有两种:一是根据卫星轨道公式将卫星的位置,姿态,轨道,大地曲面形状及扫描特征作为时间的函数来计算每条扫描线上像元的坐标,这种校正往往因为对遥感传感器的位置及姿态测量精度不高而使得校正后图像仍有不小的误差。所以又称其为粗几何校正,粗校正一般由遥感数据生产者,如卫星遥感地面站或遥感公司负责进行;二是对经过粗几何校正影像进行精几何校正,该校正需要借助地面控制点,和多项式等校正模型进行。一般来说,遥感卫星使用较准确的定位技术,姿态保持相当稳定,由卫星姿态变化引起的几何误差较小,但是成像过程中大气扰动引起的几何误差较大;而航空遥感飞机,特别是航模飞机,其姿态变化引起的几何误差不能忽略,有时还相当大。几何校正是利用控制点进行的,它是用一种数学模型来近似描述遥感图像的几何畸变过程,并利用畸变的遥感图像与标准地图之间的一些对应点(即控制点)球的这个几何畸变模型,然后利用次模型进行 几何畸变的校正,这种校正不考虑畸变的具体原因,而只考虑如何利用畸变模型来校正图像。
遥感图像融合:图像融合技术是以图像为研究对象的信息融合,它把对同一目标或场景用不同传感器获得的多种图像,或用同种传感器以不同成像方式或在不同成像时间获得的不同图像,融合为一幅图像,在这一幅融合图像中能反映多重原始图像的信息,以达到对目标和地物的综合描述。
多源遥感数据是指多个传感器获得的同一区域的遥感图像或同一传感器在不同时刻获得的同一区域的遥感图像数据。多源信息融合能富集同一区域的不同数据源的互补信息,降低数据的不精确性,减少数据的模糊度,使分类更加精确和可靠,以形成对目标区域的完整一致的信息描述。
102、对所述多源遥感数据进行污染信息提取。
103、判断提取出的污染信息的数值是否超过预先设定的污染物判断阈值。
在数据库中预先设置各区域对应的各个污染物判断阈值;
将所述提取出的污染信息和所述对应的污染物判断阈值进行比较,所述污染信息包括多个污染物信息,对应包括多个污染物判断阈值;
判断是否提取出的任何一个污染物的污染值大于存储的该污染物的判断阈值,如果是,则确定所述提取出的污染信息的数值已超过预先设定的污染物判断阈值。
104、若超过判断阈值,则确定所述检测区域发生了污染事故。
105、对所述发生了污染事故的检测区域进行烟雾飘动性分析,生成污染事故物质扩散模型;
106、根据所述污染事故物质扩散模型得到事故源的位置。
当判断出检测区域发生了污染事故后,需要对检测区域的污染事故的事故源进行辨识。
事故源辨识单元对发生了污染事故的检测区域的多源遥感数据中的多个多源遥感图像进行烟雾飘动性分析,生成污染事故物质扩散矢量图。再利用该事故物质扩散矢量图和发生了污染事故的检测区域的位置场景的实际条件建立污染事故物质扩散模型,结合神经网络组合优化算法动态调整污染事故物质扩散模型的输入条件,使输入条件与上述污染事故物质扩散矢量图达到一致或近似一致,完成对污染事故物质扩散模型的优化处理。生成污染事故物质扩散矢量图的过程主要是利用不同时间的遥感图像对比生成污染事故物质扩散,然后利用地理信息系统技术的缓冲区技术进行污染扩散矢量图的描绘。
大气污染模型:研究不同气象条件下大气污染物扩散规律的目的在于:①根据当地气象条件,对工业规划布局提供科学依据,预防可能造成的大气污染;②根据当地的大气扩散能力和环境卫生标准,提出排放标准(排放量和排放高度);③进行大气污染预报,以便有计划地采取应急措施,预防环境质量的恶化(长期的)和防止可能发生的污染事故(短期的)。扩散理论对大气污染扩散过程的研究有两种途径:一种是实验方法,就是针对给定的排放源,测定污染物的浓度分布,并找出浓度分布同时间、空间和气象条件变化的关系,探索其规律。这种方法也可以在实验室内用风洞模拟的方法实施。另一种是理论方法,即运用湍流交换的理论建立描写大气污染扩散稀释过程的模式(见大气污染模式),找出浓度分布与气象参数的关系。
湍流扩散的主要理论体系有两种:①梯度-输送理论:从平均场入手,利用湍流半经验理论(即通量和梯度之间呈线性关系)可推出湍流扩散方程,在一定的起始条件和边界条件下可获得方程的解。但是理论推导的结果和实际结果往往有很大出入。②统计理论:从研究个别流体微粒运动入手,并据此以确定表示扩散的特征量。用湍流场的统计特征量来描写扩散参数,并用可测的气象参数来表达这些统计特征量,进而找出扩散参数和可测气象条件的直接联系。
然后,利用数值方对优化后的污染事故物质扩散模型进行求解反问题,根据求解结果确定上述污染事故的事故源的位置。
本发明实施例中,获取流域环境中的检测区域的多源遥感数据;对所述多源遥感数据进行污染信息提取;判断提取出的污染信息的数值是否超过预先设定的污染物判断阈值;若超过判断阈值,则确定所述检测区域发生了污染事故。由此可见,实施本发明实施例,可对遥感数据采集、分析、管理,并可对污染 事故和事故源位置判断,提高了对流域污染的处理及应对速度。
下面为本发明系统实施例,本发明系统实施例用于执行本发明方法实施例一实现的方法。
请参阅图2,图2是本发明第二实施例公开的一种基于多源遥感数据的流域污染检测系统的结构图。如图2所示,该系统可以包括:
获取单元201,用于获取流域环境中的检测区域的多源遥感数据。
本发明实施例中,本发明实施例中,通过所述检测区域的环境污染检测装置从各种对地观测卫星获取所述检测区域的多源遥感数据,所述多源遥感数据包括多源遥感卫星图像;接着对所述多源遥感数据进行预处理,具体包括对所述多源遥感数据中的多源遥感图像进行辐射校正、几何校正和遥感图像融合处理。最后存储预处理后的多源遥感数据。
多源遥感数据是指多个传感器获得的同一区域的遥感图像或同一传感器在不同时刻获得的同一区域的遥感图像数据。多源信息融合能富集同一区域的不同数据源的互补信息,降低数据的不精确性,减少数据的模糊度,使分类更加精确和可靠,以形成对目标区域的完整一致的信息描述。
提取单元202,用于对所述多源遥感数据进行污染信息提取。
判断单元203,用于判断提取出的污染信息的数值是否超过预先设定的污染物判断阈值。
本发明实施例中,在本发明实施例中,在数据库中预先设置各区域对应的各个污染物判断阈值,将所述提取出的污染信息和所述对应的污染物判断阈值进行比较,污染信息包括多个污染物信息,对应包括多个污染物判断阈值,判断是否提取出的任何一个污染物的污染值大于存储的该污染物的判断阈值,如果是,则确定所述提取出的污染信息的数值已超过预先设定的污染物判断阈值。
确定单元204,用于若超过判断阈值时,则确定所述检测区域发生了污染事故。
在数据库中预先设置各区域对应的各个污染物判断阈值;
将所述提取出的污染信息和所述对应的污染物判断阈值进行比较,所述污染信息包括多个污染物信息,对应包括多个污染物判断阈值;
判断是否提取出的任何一个污染物的污染值大于存储的该污染物的判断阈值,如果是,则确定所述提取出的污染信息的数值已超过预先设定的污染物判断阈值。
分析单元205,用于对所述发生了污染事故的检测区域进行烟雾飘动性分析,生成污染事故物质扩散模型;
位置确定单元206,用于根据所述污染事故物质扩散模型得到事故源的位置。
当判断出检测区域发生了污染事故后,需要对检测区域的污染事故的事故源进行辨识。
事故源辨识单元对发生了污染事故的检测区域的多源遥感数据中的多个多源遥感图像进行烟雾飘动性分析,生成污染事故物质扩散矢量图。再利用该事故物质扩散矢量图和发生了污染事故的检测区域的位置场景的实际条件建立污染事故物质扩散模型,结合神经网络组合优化算法动态调整污染事故物质扩散模型的输入条件,使输入条件与上述污染事故物质扩散矢量图达到一致或近似一致,完成对污染事故物质扩散模型的优化处理。生成污染事故物质扩散矢量图的过程主要是利用不同时间的遥感图像对比生成污染事故物质扩散,然后利用地理信息系统技术的缓冲区技术进行污染扩散矢量图的描绘。
大气污染模型:研究不同气象条件下大气污染物扩散规律的目的在于:①根据当地气象条件,对工业规划布局提供科学依据,预防可能造成的大气污染;②根据当地的大气扩散能力和环境卫生标准,提出排放标准(排放量和排放高度);③进行大气污染预报,以便有计划地采取应急措施,预防环境质量的恶化(长期的)和防止可能发生的污染事故(短期的)。扩散理论对大气污染扩散过程的研究有两种途径:一种是实验方法,就是针对给定的排放源,测定污染物的浓度分布,并找出浓度分布同时间、空间和气象条件变化的关系,探索其规律。这种方法也可以在实验室内用风洞模拟的方法实施。另一种是理论方法,即运用湍流交换的理论建立描写大气污染扩散稀释过程的模式(见大气污染模式),找出浓度分布与气象参数的关系。
湍流扩散的主要理论体系有两种:①梯度-输送理论:从平均场入手,利用湍流半经验理论(即通量和梯度之间呈线性关系)可推出湍流扩散方程,在一定的起始条件和边界条件下可获得方程的解。但是理论推导的结果和实际结果往往有很大出入。②统计理论:从研究个别流体微粒运动入手,并据此以确定表示扩散的特征量。用湍流场的统计特征量来描写扩散参数,并用可测的气象参数来表达这些统计特征量,进而找出扩散参数和可测气象条件的直接联系。
然后,利用数值方对优化后的污染事故物质扩散模型进行求解反问题,根据求解结果确定上述污染事故的事故源的位置。
预处理单元207,用于对所述多源遥感数据进行预处理。
预处理具体包括对所述多源遥感数据中的多源遥感图像进行辐射校正、几何校正和遥感图像融合处理。
遥感图像辐射校正:由于传感器响应特性和大气的吸收、散射以及其他随机因素影响,导致图像模糊失真,造成图像的分辨率和对比度相对下降,这些都需要通过辐射校正复原,消除遥感图像数据中依附在辐射亮度中的各种失真的过程为辐射校正。
遥感图像几何校正:遥感数字图像的几何校正有两种:一是根据卫星轨道公式将卫星的位置,姿态,轨道,大地曲面形状及扫描特征作为时间的函数来计算每条扫描线上像元的坐标,这种校正往往因为对遥感传感器的位置及姿态测量精度不高而使得校正后图像仍有不小的误差。所以又称其为粗几何校正,粗校正一般由遥感数据生产者,如卫星遥感地面站或遥感公司负责进行;二是对经过粗几何校正影像进行精几何校正,该校正需要借助地面控制点,和多项式等校正模型进行。一般来说,遥感卫星使用较准确的定位技术,姿态保持相当稳定,由卫星姿态变化引起的几何误差较小,但是成像过程中大气扰动引起的几何误差较大;而航空遥感飞机,特别是航模飞机,其姿态变化引起的几何误差不能忽略,有时还相当大。几何校正是利用控制点进行的,它是用一种数学模型来近似描述遥感图像的几何畸变过程,并利用畸变的遥感图像与标准地图之间的一些对应点(即控制点)球的这个几何畸变模型,然后利用次模型进行几何畸变的校正,这种校正不考虑畸变的具体原因,而只考虑如何利用畸变模型来校正图像。
遥感图像融合:图像融合技术是以图像为研究对象的信息融合,它把对同一目标或场景用不同传感器获得的多种图像,或用同种传感器以不同成像方式或在不同成像时间获得的不同图像,融合为一幅图像,在这一幅融合图像中能反映多重原始图像的信息,以达到对目标和地物的综合描述。
存储单元208,用于存储预处理后的多源遥感数据。
设置单元209,用于在数据库中预先设置各区域对应的各个污染物判断阈值
本发明实施例中,获取流域环境中的检测区域的多源遥感数据;对所述多源遥感数据进行污染信息提取;判断提取出的污染信息的数值是否超过预先设定的污染物判断阈值;若超过判断阈值,则确定所述检测区域发生了污染事故。由此可见,实施本发明实施例,可对遥感数据采集、分析、管理,并可对污染事故和事故源位置判断,提高了对流域污染的处理及应对速度。
本发明实施例还提供一种计算机存储介质,其中,该计算机存储介质可存储有程序,该程序执行时包括上述方法实施例中机智的任何一种服务进程的监控方法的部分或全步骤。
需要说明的是,对于前述的各方法实施例,为了简单描述,故将其都表述为一系列的动作组合,但是本领域技术人员应该知悉,本发明并不受所描述的动作顺序的限制,因为依据本发明,某些步骤可以采用其他顺序或者同时进行。其次,本领域技术人员也应该知悉,说明书中国所描述的实施例均属于优选实施例,所涉及的动作和单元并不一定是本发明所必须的。
本发明实施例的方法的不足顺序可以根据实际需要进行调整、合并或删减。本发明实施例的终端的单元可以根据实际需要进行整合、进一步划分或删减。
在上述实施例中,对各个实施例的描述都各有侧重,某个实施例中没有详述的部分,可以参加其他实施例的相关描述。
在本申请所提供的几个实施例中,应该理解到,所揭露的系统,可通过其他的方式实现,例如,以上所描述的系统实施例是示意性的,例如所述单元的 划分,为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口,装置或单元的简介耦合或通信连接,可以是电性或其他的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以是不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外,在本发明各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用软件功能单元的形式实现。
值得注意的是,上述基于物联网的多点测温仪上报系统和终端设备实施例中,所包括的各个单元只是按照功能逻辑进行划分的,但并不局限于上述的划分,只要能够实现相应的功能即可;另外,各功能单元的具体名称也只是为了便于相互区分,并不用于限制本发明的保护范围。
另外,本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成,该程序可以存储于一计算机可读存储介质中,存储介质包括只读存储器(Read-Only Memory,ROM)、随机存储器(RandomAccess Memory,RAM)、可编程只读存储器(Programmable Read-only Memory,PROM)、可擦除可编程只读存储器(Erasable Programmable Read Only Memory,EPROM)、一次可编程只读存储器(One-time Programmable Read-Only Memory,OTPROM)、电子抹除式可复写只读存储器(Electrically-Erasable Programmable Read-Only Memory,EEPROM)、只读光盘(Compact Disc Read-Only Memory,CD-ROM)或其他光盘存储器、磁盘存储器、磁带存储器、或者能够用于携带或存储数据的计算机可读的任何其他介质。
以上仅为本发明较佳的具体实施方式,但本发明的保护范围并不局限于此,任何熟悉本技术领域的技术人员在本发明实施例揭露的技术范围内,可轻 易想到的变化或替换,都应涵盖在本发明的保护范围之内。因此,本发明的保护范围应该以权利要求的保护范围为准。

Claims (10)

  1. 一种基于多源遥感数据的流域污染检测方法,其特征在于,包括:
    获取流域环境中的检测区域的多源遥感数据;
    对所述多源遥感数据进行污染信息提取;
    判断提取出的污染信息的数值是否超过预先设定的污染物判断阈值;
    若超过判断阈值,则确定所述检测区域发生了污染事故。
  2. 根据权利要求1所述方法,其特征在于,所述方法还包括:
    对所述发生了污染事故的检测区域进行烟雾飘动性分析,生成污染事故物质扩散模型;
    根据所述污染事故物质扩散模型得到事故源的位置。
  3. 根据权利要求1所述方法,其特征在于,所述获取流域环境中的检测区域的多源遥感数据,具体包括:
    通过所述检测区域的环境污染检测装置从各种对地观测卫星获取所述检测区域的多源遥感数据,所述多源遥感数据包括多源遥感卫星图像;
    对所述多源遥感数据进行预处理;
    存储预处理后的多源遥感数据。
  4. 根据权利要求1中所述方法,其特征在于,所述对所述多源遥感数据进行预处理,具体包括:
    对所述多源遥感数据中的多源遥感图像进行辐射校正、几何校正和遥感图像融合处理。
  5. 根据权利要求1~3中任意一项所述方法,其特征在于,所述判断提取出的污染信息的数值是否超过预先设定的污染物判断阈值,具体包括:
    在数据库中预先设置各区域对应的各个污染物判断阈值;
    将所述提取出的污染信息和所述对应的污染物判断阈值进行比较,所述污 染信息包括多个污染物信息,对应包括多个污染物判断阈值;
    判断是否提取出的任何一个污染物的污染值大于存储的该污染物的判断阈值,如果是,则确定所述提取出的污染信息的数值已超过预先设定的污染物判断阈值。
  6. 一种基于多源遥感数据的流域污染检测系统,其特征在于,包括:
    获取单元,用于获取流域环境中的检测区域的多源遥感数据;
    提取单元,用于对所述多源遥感数据进行污染信息提取;
    判断单元,用于判断提取出的污染信息的数值是否超过预先设定的污染物判断阈值;
    确定单元,用于若超过判断阈值时,则确定所述检测区域发生了污染事故。
  7. 根据权利要求6所述的系统,其特征在于,所述系统还包括:
    分析单元,用于对所述发生了污染事故的检测区域进行烟雾飘动性分析,生成污染事故物质扩散模型;
    位置确定单元,用于根据所述污染事故物质扩散模型得到事故源的位置。
  8. 根据权利要求6所述的系统,其特征在于,
    所述获取单元,具体用于通过所述检测区域的环境污染检测装置从各种对地观测卫星获取所述检测区域的多源遥感数据,所述多源遥感数据包括多源遥感卫星图像;
    所述系统还包括:
    预处理单元,用于对所述多源遥感数据进行预处理;
    存储单元,用于存储预处理后的多源遥感数据。
  9. 根据权利要求6中所述的系统,其特征在于,
    所述预处理单元,具体用于对所述多源遥感数据中的多源遥感图像进行辐射校正、几何校正和遥感图像融合处理。
  10. 根据权利要求6~8中任意一项所述的系统,其特征在于,所述系统还包括:
    设置单元,用于在数据库中预先设置各区域对应的各个污染物判断阈值;
    所述判断单元,具体用于将所述提取出的污染信息和所述对应的污染物判断阈值进行比较,所述污染信息包括多个污染物信息,对应包括多个污染物判断阈值;
    所述判断单元还用于判断是否提取出的任何一个污染物的污染值大于存储的该污染物的判断阈值,如果是,则确定所述提取出的污染信息的数值已超过预先设定的污染物判断阈值。
PCT/CN2017/072374 2017-01-24 2017-01-24 一种基于多源遥感数据的流域污染检测方法及系统 WO2018137103A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2017/072374 WO2018137103A1 (zh) 2017-01-24 2017-01-24 一种基于多源遥感数据的流域污染检测方法及系统

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2017/072374 WO2018137103A1 (zh) 2017-01-24 2017-01-24 一种基于多源遥感数据的流域污染检测方法及系统

Publications (1)

Publication Number Publication Date
WO2018137103A1 true WO2018137103A1 (zh) 2018-08-02

Family

ID=62977819

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/072374 WO2018137103A1 (zh) 2017-01-24 2017-01-24 一种基于多源遥感数据的流域污染检测方法及系统

Country Status (1)

Country Link
WO (1) WO2018137103A1 (zh)

Cited By (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109190572A (zh) * 2018-09-12 2019-01-11 北京英视睿达科技有限公司 基于卫星遥感数据的渗坑识别方法
CN109472504A (zh) * 2018-11-19 2019-03-15 北京英视睿达科技有限公司 基于卫星遥感数据确定水环境热点网格的方法及装置
CN110111022A (zh) * 2019-05-17 2019-08-09 中科三清科技有限公司 水污染源的评价方法及装置
CN111553942A (zh) * 2020-04-30 2020-08-18 王一帆 一种遥感水文站监测河流径流的系统及其方法
CN111581308A (zh) * 2020-03-26 2020-08-25 中国农业科学院农业信息研究所 一种农业遥感监测数据多维融合方法及系统
CN112069999A (zh) * 2020-09-07 2020-12-11 广东生太修复科技有限公司 智能黑臭水处理方法及相关装置
CN112132450A (zh) * 2020-09-22 2020-12-25 南京创蓝科技有限公司 一种气态污染物的定位方法
CN112585610A (zh) * 2018-08-31 2021-03-30 三菱电机株式会社 设置环境推测装置以及程序
CN113203691A (zh) * 2021-05-06 2021-08-03 福建省水利水电科学研究院 一种基于小波分析的水质污染物溯源方法
CN113610358A (zh) * 2021-07-16 2021-11-05 南昌工程学院 基于云平台的远程水质风险预警系统
CN114119444A (zh) * 2021-11-29 2022-03-01 武汉大学 一种基于深度神经网络的多源遥感图像融合方法
CN114324074A (zh) * 2021-12-22 2022-04-12 陕西智星空间科技有限公司 一种基于后向轨迹模型与遥感影像的大气监测走航方法
CN114742812A (zh) * 2022-04-27 2022-07-12 中交基础设施养护集团有限公司 基于低空星座的多源遥感物探数据一体化探测方法及系统
CN115684516A (zh) * 2022-08-29 2023-02-03 邯郸市亿润工程咨询有限公司 一种水利工程污水处理检测方法、装置、电子设备及介质
CN115936543A (zh) * 2023-03-15 2023-04-07 湖北君邦环境技术有限责任公司 一种突发水污染事故污染溯源方法、系统、设备及介质
CN116546431A (zh) * 2023-07-04 2023-08-04 北京江云智能科技有限公司 一种基于北斗全网通多网融合数据采集通信系统及方法
CN116630825A (zh) * 2023-06-09 2023-08-22 北京佳格天地科技有限公司 一种卫星遥感数据与监控视频融合方法及系统
CN116699072A (zh) * 2023-06-08 2023-09-05 东莞市华复实业有限公司 基于侦测巡航的环境预警方法
CN117274884A (zh) * 2023-11-21 2023-12-22 赣江新区慧工科技有限公司 一种基于图像识别的施工扬尘污染事件检测方法及系统
CN117292331A (zh) * 2023-11-27 2023-12-26 四川发展环境科学技术研究院有限公司 基于深度学习的复杂异物检测系统及方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103984310A (zh) * 2014-05-12 2014-08-13 华迪计算机集团有限公司 基于多源遥感数据的化工园区环境污染检测方法和装置
CN104361418A (zh) * 2014-12-05 2015-02-18 北京师范大学 一种流域水生态安全监控预警平台及其预警方法
WO2016125941A1 (ko) * 2015-02-05 2016-08-11 (주)유엔이 환경 오염 예측 시스템 및 방법
CN105912790A (zh) * 2016-04-15 2016-08-31 重庆大学 基于深度回归模型的遥感水质监测方法
CN106815606A (zh) * 2017-01-24 2017-06-09 深圳企管加企业服务有限公司 一种基于多源遥感数据的流域污染检测方法及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103984310A (zh) * 2014-05-12 2014-08-13 华迪计算机集团有限公司 基于多源遥感数据的化工园区环境污染检测方法和装置
CN104361418A (zh) * 2014-12-05 2015-02-18 北京师范大学 一种流域水生态安全监控预警平台及其预警方法
WO2016125941A1 (ko) * 2015-02-05 2016-08-11 (주)유엔이 환경 오염 예측 시스템 및 방법
CN105912790A (zh) * 2016-04-15 2016-08-31 重庆大学 基于深度回归模型的遥感水质监测方法
CN106815606A (zh) * 2017-01-24 2017-06-09 深圳企管加企业服务有限公司 一种基于多源遥感数据的流域污染检测方法及系统

Cited By (30)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112585610A (zh) * 2018-08-31 2021-03-30 三菱电机株式会社 设置环境推测装置以及程序
CN109190572A (zh) * 2018-09-12 2019-01-11 北京英视睿达科技有限公司 基于卫星遥感数据的渗坑识别方法
CN109472504A (zh) * 2018-11-19 2019-03-15 北京英视睿达科技有限公司 基于卫星遥感数据确定水环境热点网格的方法及装置
CN110111022A (zh) * 2019-05-17 2019-08-09 中科三清科技有限公司 水污染源的评价方法及装置
CN111581308A (zh) * 2020-03-26 2020-08-25 中国农业科学院农业信息研究所 一种农业遥感监测数据多维融合方法及系统
CN111581308B (zh) * 2020-03-26 2023-06-06 中国农业科学院农业信息研究所 一种农业遥感监测数据多维融合方法及系统
CN111553942B (zh) * 2020-04-30 2023-10-13 王一帆 一种遥感水文站监测河流径流的系统及其方法
CN111553942A (zh) * 2020-04-30 2020-08-18 王一帆 一种遥感水文站监测河流径流的系统及其方法
CN112069999A (zh) * 2020-09-07 2020-12-11 广东生太修复科技有限公司 智能黑臭水处理方法及相关装置
CN112132450A (zh) * 2020-09-22 2020-12-25 南京创蓝科技有限公司 一种气态污染物的定位方法
CN113203691A (zh) * 2021-05-06 2021-08-03 福建省水利水电科学研究院 一种基于小波分析的水质污染物溯源方法
CN113610358A (zh) * 2021-07-16 2021-11-05 南昌工程学院 基于云平台的远程水质风险预警系统
CN114119444A (zh) * 2021-11-29 2022-03-01 武汉大学 一种基于深度神经网络的多源遥感图像融合方法
CN114119444B (zh) * 2021-11-29 2024-04-16 武汉大学 一种基于深度神经网络的多源遥感图像融合方法
CN114324074A (zh) * 2021-12-22 2022-04-12 陕西智星空间科技有限公司 一种基于后向轨迹模型与遥感影像的大气监测走航方法
CN114742812A (zh) * 2022-04-27 2022-07-12 中交基础设施养护集团有限公司 基于低空星座的多源遥感物探数据一体化探测方法及系统
CN114742812B (zh) * 2022-04-27 2024-03-29 中交基础设施养护集团有限公司 基于低空星座的多源遥感物探数据一体化探测方法及系统
CN115684516A (zh) * 2022-08-29 2023-02-03 邯郸市亿润工程咨询有限公司 一种水利工程污水处理检测方法、装置、电子设备及介质
CN115684516B (zh) * 2022-08-29 2024-03-26 邯郸市亿润工程咨询有限公司 一种水利工程污水处理检测方法、装置、电子设备及介质
CN115936543A (zh) * 2023-03-15 2023-04-07 湖北君邦环境技术有限责任公司 一种突发水污染事故污染溯源方法、系统、设备及介质
CN115936543B (zh) * 2023-03-15 2023-06-06 湖北君邦环境技术有限责任公司 一种突发水污染事故污染溯源方法、系统、设备及介质
CN116699072A (zh) * 2023-06-08 2023-09-05 东莞市华复实业有限公司 基于侦测巡航的环境预警方法
CN116699072B (zh) * 2023-06-08 2024-01-26 东莞市华复实业有限公司 基于侦测巡航的环境预警方法
CN116630825A (zh) * 2023-06-09 2023-08-22 北京佳格天地科技有限公司 一种卫星遥感数据与监控视频融合方法及系统
CN116546431A (zh) * 2023-07-04 2023-08-04 北京江云智能科技有限公司 一种基于北斗全网通多网融合数据采集通信系统及方法
CN116546431B (zh) * 2023-07-04 2023-09-19 北京江云智能科技有限公司 一种基于北斗全网通多网融合数据采集通信系统及方法
CN117274884B (zh) * 2023-11-21 2024-02-20 赣江新区慧工科技有限公司 一种基于图像识别的施工扬尘污染事件检测方法及系统
CN117274884A (zh) * 2023-11-21 2023-12-22 赣江新区慧工科技有限公司 一种基于图像识别的施工扬尘污染事件检测方法及系统
CN117292331B (zh) * 2023-11-27 2024-02-02 四川发展环境科学技术研究院有限公司 基于深度学习的复杂异物检测系统及方法
CN117292331A (zh) * 2023-11-27 2023-12-26 四川发展环境科学技术研究院有限公司 基于深度学习的复杂异物检测系统及方法

Similar Documents

Publication Publication Date Title
WO2018137103A1 (zh) 一种基于多源遥感数据的流域污染检测方法及系统
US11069133B2 (en) Method and device for generating three-dimensional scene map
EP3848509A1 (en) Crack analysis device, crack analysis method, and crack analysis program
CN110826549A (zh) 基于计算机视觉的巡检机器人仪表图像识别方法及系统
CN104240264B (zh) 一种运动物体的高度检测方法和装置
WO2015157643A1 (en) Solar energy forecasting
CN111598098B (zh) 一种基于全卷积神经网络的水尺水位线检测及有效性识别方法
CN108195736B (zh) 一种三维激光点云提取植被冠层间隙率的方法
CN103679167A (zh) 一种ccd图像处理的方法
KR102136106B1 (ko) 태양광 발전량 예측 장치
CN110969610A (zh) 基于深度学习的电力设备红外热图的识别方法及系统
CN113780270A (zh) 目标检测方法和装置
CN115439753A (zh) 一种基于dem的陡峭河岸识别方法及系统
CN114858226A (zh) 一种无人机山洪流量测量方法、装置及设备
Varjo et al. Image based visibility estimation during day and night
Jing et al. Efficient point cloud corrections for mobile monitoring applications using road/rail-side infrastructure
CN106815606A (zh) 一种基于多源遥感数据的流域污染检测方法及系统
CN110298302A (zh) 一种人体目标检测方法及相关设备
Li et al. Hybrid cloud detection algorithm based on intelligent scene recognition
CN116340863B (zh) 空气污染物预测方法、装置、电子设备及可读存储介质
KR102317207B1 (ko) 미세먼지 농도 추정 시스템, 방법 및 컴퓨터 프로그램
CN112581301A (zh) 一种基于深度学习的农田残膜残留量的检测预警方法及系统
CN116503727A (zh) 一种基于泊松分布和点云聚类的植被聚集度指数估算方法
CN113096129B (zh) 高光谱卫星影像中的云量检测方法和装置
KR102317206B1 (ko) 미세먼지 농도 추정 시스템, 방법 및 컴퓨터 프로그램

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17894596

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17894596

Country of ref document: EP

Kind code of ref document: A1