CN117848979A - A remote sensing monitoring system and method for intelligent device environment - Google Patents
A remote sensing monitoring system and method for intelligent device environment Download PDFInfo
- Publication number
- CN117848979A CN117848979A CN202310439367.2A CN202310439367A CN117848979A CN 117848979 A CN117848979 A CN 117848979A CN 202310439367 A CN202310439367 A CN 202310439367A CN 117848979 A CN117848979 A CN 117848979A
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- data
- fusion
- module
- sensing data
- 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.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 10
- 230000004927 fusion Effects 0.000 claims abstract description 117
- 238000007781 pre-processing Methods 0.000 claims abstract description 48
- 230000007613 environmental effect Effects 0.000 claims abstract description 10
- 238000001514 detection method Methods 0.000 claims description 36
- 238000000605 extraction Methods 0.000 claims description 19
- 238000004458 analytical method Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 9
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 9
- 238000001228 spectrum Methods 0.000 claims description 4
- 238000002360 preparation method Methods 0.000 claims description 3
- 230000001133 acceleration Effects 0.000 claims 4
- 238000011156 evaluation Methods 0.000 claims 3
- 230000008447 perception Effects 0.000 abstract description 16
- 238000005516 engineering process Methods 0.000 abstract description 13
- 230000004044 response Effects 0.000 abstract description 13
- 238000011161 development Methods 0.000 abstract description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 230000003595 spectral effect Effects 0.000 description 11
- 230000018109 developmental process Effects 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 101001121408 Homo sapiens L-amino-acid oxidase Proteins 0.000 description 1
- 101000827703 Homo sapiens Polyphosphoinositide phosphatase Proteins 0.000 description 1
- 102100026388 L-amino-acid oxidase Human genes 0.000 description 1
- 102100023591 Polyphosphoinositide phosphatase Human genes 0.000 description 1
- 101100012902 Saccharomyces cerevisiae (strain ATCC 204508 / S288c) FIG2 gene Proteins 0.000 description 1
- 101100233916 Saccharomyces cerevisiae (strain ATCC 204508 / S288c) KAR5 gene Proteins 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000023004 detection of visible light Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Alarm Systems (AREA)
Abstract
本发明公开了一种智能设备环境遥感监测系统及方法，具体涉及环境监测技术领域，包括多源遥感数据预处理系统，所述多源遥感数据预处理系统的终端设有多源遥感数据融合与协同感知系统，所述多源遥感数据融合与协同感知系统的终端设有多源遥感数据融合灾害应急系统，本发明，本系统可以整合不同平台、不同载荷的商业对地观测卫星数据，完善地面资源，解决遥感观测卫星数据源各为所有，相互独立问题；并通过与其他观测手段结合，形成全天候、全覆盖的对地观测能力；结合大数据与人工智能等相关技术，突破遥感大数据融合共性关键技术；同时，开展遥感大数据融合在灾害应急中的应用，旨在维护区域战略安全和发展利益。
The present invention discloses an intelligent equipment environment remote sensing monitoring system and method, which specifically relates to the field of environmental monitoring technology, including a multi-source remote sensing data preprocessing system, wherein a terminal of the multi-source remote sensing data preprocessing system is provided with a multi-source remote sensing data fusion and collaborative perception system, and a terminal of the multi-source remote sensing data fusion and collaborative perception system is provided with a multi-source remote sensing data fusion disaster emergency response system. According to the present invention, the system can integrate commercial earth observation satellite data of different platforms and different payloads, improve ground resources, and solve the problem that the data sources of remote sensing observation satellites are owned by each other and are independent of each other; and through combination with other observation means, an all-weather and full-coverage earth observation capability is formed; and by combining with relevant technologies such as big data and artificial intelligence, a breakthrough is made in the common key technologies of remote sensing big data fusion; at the same time, the application of remote sensing big data fusion in disaster emergency response is carried out, aiming to safeguard regional strategic security and development interests.
Description
技术领域Technical Field
本发明涉及环境监测技术领域，具体为一种智能设备环境遥感监测系统及方法。The present invention relates to the technical field of environmental monitoring, and in particular to a system and method for remotely sensing an environment of an intelligent device.
背景技术Background technique
随着进几十年的发展，我国已经初步形成遥感卫星对地观测体系，但多源遥感数据融合及协同感知研究尚处于初级阶段，尤其是多源数据协同在各行业中的应用，于不同类型数据成像方式不同、特点不同，造成业务运行、快速应急服务的能力明显不够，另外，由于缺乏自主知识产权、性价比较高的遥感数据处理软件，加之遥感数据产品的生产和分发滞后，妨碍很多用户使用的同时，也影响我国空基和天基信息产业的规模效应；With the development of the past few decades, my country has initially formed a remote sensing satellite earth observation system, but the research on multi-source remote sensing data fusion and collaborative perception is still in its infancy, especially the application of multi-source data collaboration in various industries. Due to the different imaging methods and characteristics of different types of data, the ability of business operation and rapid emergency service is obviously insufficient. In addition, due to the lack of independent intellectual property rights and cost-effective remote sensing data processing software, coupled with the lagging production and distribution of remote sensing data products, many users are hindered from using them, and the scale effect of my country's air-based and space-based information industries is also affected;
针对以上问题，本申请充分结合各类多源遥感数据的优势，研究突破多源遥感数据融合与协同感知关键技术为相关应用提供更高质量的数据需求；结合灾害应急领域的需求,开展多源遥感数据协同感知的灾害应急应用示范系统开发与集成，解决单一来源遥感数据实际应用中的不足。In response to the above problems, this application fully combines the advantages of various types of multi-source remote sensing data, studies and breaks through the key technologies of multi-source remote sensing data fusion and collaborative perception to provide higher quality data requirements for related applications; combined with the needs of the disaster emergency field, develop and integrate disaster emergency application demonstration systems with collaborative perception of multi-source remote sensing data to solve the shortcomings in the practical application of single-source remote sensing data.
发明内容Summary of the invention
本发明的目的在于提供一种智能设备环境遥感监测系统及方法，以解决上述背景技术中提出的问题。The purpose of the present invention is to provide a system and method for remote sensing monitoring of an intelligent device environment to solve the problems raised in the above-mentioned background technology.
为实现上述目的，本发明提供如下技术方案：一种智能设备环境遥感监测系统，包括多源遥感数据预处理系统，所述多源遥感数据预处理系统的终端设有多源遥感数据融合与协同感知系统，所述多源遥感数据融合与协同感知系统的终端设有多源遥感数据融合灾害应急系统。To achieve the above-mentioned objectives, the present invention provides the following technical solutions: an intelligent device environment remote sensing monitoring system, comprising a multi-source remote sensing data preprocessing system, wherein the terminal of the multi-source remote sensing data preprocessing system is provided with a multi-source remote sensing data fusion and collaborative perception system, and the terminal of the multi-source remote sensing data fusion and collaborative perception system is provided with a multi-source remote sensing data fusion disaster emergency response system.
作为本发明的一种优选技术方案，所述多源遥感数据预处理系统包括可见光数据预处理模块、SAR遥感数据预处理模块、多时相数据预处理模块、高分辨率遥感数据预处理模块、高分辨率遥感数据预处理模块和其他遥感数据预处理模块。As a preferred technical solution of the present invention, the multi-source remote sensing data preprocessing system includes a visible light data preprocessing module, a SAR remote sensing data preprocessing module, a multi-phase data preprocessing module, a high-resolution remote sensing data preprocessing module, a high-resolution remote sensing data preprocessing module and other remote sensing data preprocessing modules.
作为本发明的一种优选技术方案，所述多源遥感数据融合与协同感知系统包括多光谱数据与全色数据融合模组、SAR数据与可见光数据融合模组、多源时空数据融合模组。As a preferred technical solution of the present invention, the multi-source remote sensing data fusion and collaborative perception system includes a multi-spectral data and panchromatic data fusion module, a SAR data and visible light data fusion module, and a multi-source spatiotemporal data fusion module.
作为本发明的一种优选技术方案，所述多源遥感数据融合与协同感知系统还包括多源遥感数据变化检测模组、多源遥感数据协同检测模组。As a preferred technical solution of the present invention, the multi-source remote sensing data fusion and collaborative perception system also includes a multi-source remote sensing data change detection module and a multi-source remote sensing data collaborative detection module.
作为本发明的一种优选技术方案，所述多光谱数据与全色数据融合模组得出多光谱与全色融合数据。As a preferred technical solution of the present invention, the multispectral data and panchromatic data fusion module obtains multispectral and panchromatic fusion data.
作为本发明的一种优选技术方案，所述SAR数据与可见光数据融合模组得出SAR与可见光融合数据。As a preferred technical solution of the present invention, the SAR data and visible light data fusion module obtains SAR and visible light fusion data.
作为本发明的一种优选技术方案，所述多源时空数据融合模组得出多源时空融合数据。As a preferred technical solution of the present invention, the multi-source spatiotemporal data fusion module obtains multi-source spatiotemporal fusion data.
作为本发明的一种优选技术方案，所述多光谱与全色融合数据、SAR与可见光融合数据和多源时空融合数据并行加速处理进入多源遥感数据变化检测模组进行多源遥感数据变化检测，随后，并行加速处理进入多源遥感数据协同检测模组进行多源遥感数据协同检测，最终实现水体信息快速提取、地质灾害信息提取、干旱信息反演和火灾信息提取。As a preferred technical solution of the present invention, the multi-spectral and panchromatic fusion data, SAR and visible light fusion data and multi-source spatiotemporal fusion data are processed in parallel and accelerated to enter the multi-source remote sensing data change detection module for multi-source remote sensing data change detection, and then, the parallel accelerated processing is entered into the multi-source remote sensing data collaborative detection module for multi-source remote sensing data collaborative detection, ultimately achieving rapid extraction of water body information, geological disaster information extraction, drought information inversion and fire information extraction.
作为本发明的一种优选技术方案，所述多源遥感数据融合灾害应急系统包括洪涝灾害监测模组、地质灾害监测模组、旱灾监测模组和火灾监测模组，所述多源遥感数据融合灾害应急系统还包括灾情分析与评估模组。As a preferred technical solution of the present invention, the multi-source remote sensing data fusion disaster emergency response system includes a flood disaster monitoring module, a geological disaster monitoring module, a drought monitoring module and a fire monitoring module, and the multi-source remote sensing data fusion disaster emergency response system also includes a disaster analysis and assessment module.
一种智能设备环境遥感监测方法，包括如下步骤：A method for remote sensing monitoring of an intelligent device environment comprises the following steps:
步骤一、数据准备以及预处理Step 1: Data preparation and preprocessing
通过可见光数据预处理模块、SAR遥感数据预处理模块、多时相数据预处理模块、高分辨率遥感数据预处理模块、高分辨率遥感数据预处理模块和其他遥感数据预处理模块分别对可见光数据、SAR遥感数据、多时相数据、高分辨率遥感数据、高分辨率遥感数据和其他遥感数据进行多源遥感数据预处理；Multi-source remote sensing data preprocessing is performed on visible light data, SAR remote sensing data, multi-temporal data, high-resolution remote sensing data, high-resolution remote sensing data and other remote sensing data through visible light data preprocessing module, SAR remote sensing data preprocessing module, multi-temporal data preprocessing module, high-resolution remote sensing data preprocessing module, and other remote sensing data preprocessing modules respectively;
步骤二、多源遥感数据融合与协同感知Step 2: Multi-source remote sensing data fusion and collaborative perception
通过多光谱数据与全色数据融合模组、SAR数据与可见光数据融合模组和多源时空数据融合模组分别得出多光谱与全色融合数据、SAR与可见光融合数据和多源时空融合数据；Through the multispectral data and panchromatic data fusion module, the SAR data and visible light data fusion module and the multi-source spatiotemporal data fusion module, the multispectral and panchromatic fusion data, the SAR and visible light fusion data and the multi-source spatiotemporal fusion data are obtained respectively;
随后，多光谱与全色融合数据、SAR与可见光融合数据和多源时空融合数据并行加速处理进入多源遥感数据变化检测模组进行多源遥感数据变化检测，随后，并行加速处理进入多源遥感数据协同检测模组进行多源遥感数据协同检测，最终实现水体信息快速提取、地质灾害信息提取、干旱信息反演和火灾信息提取；Subsequently, the multi-spectral and panchromatic fusion data, SAR and visible light fusion data, and multi-source spatiotemporal fusion data are processed in parallel and accelerated and then enter the multi-source remote sensing data change detection module for multi-source remote sensing data change detection. Subsequently, the parallel accelerated processing enters the multi-source remote sensing data collaborative detection module for multi-source remote sensing data collaborative detection, and finally realizes the rapid extraction of water body information, geological disaster information extraction, drought information inversion, and fire information extraction.
步骤三、多源遥感数据融合灾害应急Step 3: Multi-source remote sensing data fusion for disaster emergency response
提取的水体信息、地质灾害信息、干旱信息和火灾信息对应通过洪涝灾害监测模组、地质灾害监测模组、旱灾监测模组和火灾监测模组进行洪涝灾害监测、地质灾害监测、旱灾监测和火灾监测，随后使用灾情分析与评估模组进行灾情分析与评估。The extracted water body information, geological disaster information, drought information and fire information are correspondingly used for flood disaster monitoring, geological disaster monitoring, drought monitoring and fire monitoring through flood disaster monitoring module, geological disaster monitoring module, drought monitoring module and fire monitoring module, and then the disaster analysis and assessment module is used for disaster analysis and assessment.
与现有技术相比，本发明的有益效果在于：Compared with the prior art, the present invention has the following beneficial effects:
1、本发明可以整合不同平台、不同载荷的商业对地观测卫星数据，完善地面资源，解决遥感观测卫星数据源各为所有，相互独立问题；并通过与其他观测手段结合，形成全天候、全覆盖的对地观测能力；1. The present invention can integrate commercial earth observation satellite data from different platforms and different payloads, improve ground resources, and solve the problem that remote sensing observation satellite data sources are owned by each other and are independent of each other; and by combining with other observation means, it can form an all-weather and full-coverage earth observation capability;
2、结合大数据与人工智能等相关技术，突破遥感大数据融合共性关键技术；同时，开展遥感大数据融合在灾害应急中的应用，旨在维护区域战略安全和发展利益；2. Combine big data with artificial intelligence and other related technologies to break through the common key technologies of remote sensing big data fusion; at the same time, carry out the application of remote sensing big data fusion in disaster emergency response, aiming to maintain regional strategic security and development interests;
3、本发明是基于多源遥感数据融合技术的重大灾害监测、应急管理，是国家治理体系和治理能力的重要组成部分，承担防范化解重大安全风险、及时应对处置各类灾害事故的重要职责,担负保护人民群众生命财产安全和维护社会稳定的重要使命；3. This invention is a major disaster monitoring and emergency management based on multi-source remote sensing data fusion technology. It is an important part of the national governance system and governance capabilities. It undertakes the important responsibilities of preventing and resolving major security risks, responding to and handling various disasters and accidents in a timely manner, and shouldering the important mission of protecting the lives and property of the people and maintaining social stability.
4、加快发展多源遥感数据融合技术的重大灾害监测、应急管理产业，不仅能为重大灾害分析、预警及应急管理提供重要的图像基础，同时还能推动经济增长,形成新的经济增长点。4. Accelerate the development of major disaster monitoring and emergency management industries based on multi-source remote sensing data fusion technology, which can not only provide an important image basis for major disaster analysis, early warning and emergency management, but also promote economic growth and form new economic growth points.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例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，下面描述中的附图仅仅是本发明的一些实施例，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 embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments 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为本发明中智能设备环境遥感监测系统的示意图，FIG1 is a schematic diagram of a remote sensing monitoring system for an intelligent device environment in the present invention.
图2为本发明多光谱与全色融合技术路线图，FIG2 is a technical roadmap of multi-spectral and panchromatic fusion of the present invention,
图3为本发明多光谱与高光谱融合技术路线图，FIG3 is a technical roadmap of multi-spectral and hyper-spectral fusion of the present invention,
图4为本发明多源数据时空融合技术路线图，FIG4 is a technical roadmap of multi-source data spatiotemporal fusion in the present invention.
图5为本发明多源遥感数据变化检测技术路线图，FIG5 is a technical roadmap of multi-source remote sensing data change detection in the present invention,
图6为本发明SAR遥感影像分类技术路线图。FIG6 is a technical roadmap of SAR remote sensing image classification according to the present invention.
具体实施方式Detailed ways
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，所描述的实施例仅仅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。The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 creative work are within the scope of protection of the present invention.
实施例：如图1-6所示，本发明提供了一种智能设备环境遥感监测系统，包括多源遥感数据预处理系统，所述多源遥感数据预处理系统的终端设有多源遥感数据融合与协同感知系统，所述多源遥感数据融合与协同感知系统的终端设有多源遥感数据融合灾害应急系统。Embodiment: As shown in Figures 1-6, the present invention provides an intelligent device environment remote sensing monitoring system, including a multi-source remote sensing data preprocessing system, wherein the terminal of the multi-source remote sensing data preprocessing system is provided with a multi-source remote sensing data fusion and collaborative perception system, and the terminal of the multi-source remote sensing data fusion and collaborative perception system is provided with a multi-source remote sensing data fusion disaster emergency response system.
所述多源遥感数据预处理系统包括可见光数据预处理模块、SAR遥感数据预处理模块、多时相数据预处理模块、高分辨率遥感数据预处理模块、高分辨率遥感数据预处理模块和其他遥感数据预处理模块；The multi-source remote sensing data preprocessing system includes a visible light data preprocessing module, a SAR remote sensing data preprocessing module, a multi-phase data preprocessing module, a high-resolution remote sensing data preprocessing module, a high-resolution remote sensing data preprocessing module and other remote sensing data preprocessing modules;
所述多源遥感数据融合与协同感知系统包括多光谱数据与全色数据融合模组、SAR数据与可见光数据融合模组、多源时空数据融合模组。The multi-source remote sensing data fusion and collaborative perception system includes a multi-spectral data and panchromatic data fusion module, a SAR data and visible light data fusion module, and a multi-source spatiotemporal data fusion module.
所述多源遥感数据融合与协同感知系统还包括多源遥感数据变化检测模组、多源遥感数据协同检测模组。The multi-source remote sensing data fusion and collaborative perception system also includes a multi-source remote sensing data change detection module and a multi-source remote sensing data collaborative detection module.
所述多光谱数据与全色数据融合模组得出多光谱与全色融合数据；The multispectral data and panchromatic data fusion module obtains multispectral and panchromatic fusion data;
通过分析现有图像融合算法的基础上,为了在提高空间分辨率的同时保证光谱信息尽可能不失真，结合不同遥感图像的自身特点，提出新的多光谱与全色遥感图像融合算法；如图2所示。Based on the analysis of existing image fusion algorithms, in order to improve the spatial resolution while ensuring that the spectral information is as undistorted as possible, a new multispectral and panchromatic remote sensing image fusion algorithm is proposed in combination with the characteristics of different remote sensing images; as shown in Figure 2.
所述SAR数据与可见光数据融合模组得出SAR与可见光融合数据；The SAR data and visible light data fusion module obtains SAR and visible light fusion data;
所述多源时空数据融合模组得出多源时空融合数据。The multi-source spatiotemporal data fusion module obtains multi-source spatiotemporal fusion data.
针对光谱字典构建，提出两分支的分层字典学习算法，两个分支分别是基于聚类和基于细节感知的字典学习，基于聚类的字典学习将高光谱图像聚类，同一类的像素共享一个光谱字典；基于细节感知的光谱字典充分关注图像的边缘光谱的复杂性和多样性，构建边缘区域的光谱字典；分层光谱字典保证了融合图像优良的光谱特性；针对光谱字典重建图像会损失空间信息，构建高光谱图像和多光谱图像空间损失矩阵，通过对损失矩阵的字典学习和稀疏表示，估计融合图像的空间损失；将基于光谱字典的图像重建和基于空间字典的空间损失估计构成光谱一空间字典融合框架,使得融合结果整体的光谱信息与空间信息都能得到精确重建；如图3所示。For the construction of spectral dictionary, a two-branch hierarchical dictionary learning algorithm is proposed. The two branches are dictionary learning based on clustering and detail perception. The clustering-based dictionary learning clusters the hyperspectral image, and the pixels of the same class share a spectral dictionary; the detail-perception-based spectral dictionary fully pays attention to the complexity and diversity of the edge spectrum of the image and constructs a spectral dictionary for the edge area; the hierarchical spectral dictionary ensures the excellent spectral characteristics of the fused image; the spectral dictionary reconstruction image will lose spatial information, and the spatial loss matrix of the hyperspectral image and multispectral image is constructed. The spatial loss of the fused image is estimated through dictionary learning and sparse representation of the loss matrix; the image reconstruction based on the spectral dictionary and the spatial loss estimation based on the spatial dictionary constitute a spectral-spatial dictionary fusion framework, so that the overall spectral information and spatial information of the fusion result can be accurately reconstructed; as shown in Figure 3.
针对跨卫星图像,提出基于联合字典学习的传感器偏差映射模型减小了多源卫星之间的传感器偏差；针对变化区域难以准确表示问题，提出了跨时序寻找相似块构建变化区域的高低分辨率字典学习样本，来提高土地覆盖类型变化区域的预测精度；针对多源图像尺度差距过大，提出两层时空融合框架，降低字典的重建压力，提高了图像的融合精度；针对图像重构时，高低分辨率图像稀疏系数呈线性关系的假设并不成立，提出基于支持向量回归来构建高低分辨率稀疏系数之间的非线性关系，提升高分辨率稀疏系数估计精度，从而提升融合图像的质量；如图4所示。For cross-satellite images, a sensor bias mapping model based on joint dictionary learning is proposed to reduce the sensor bias between multi-source satellites; for the problem that changing areas are difficult to accurately represent, it is proposed to find similar blocks across time series to construct high- and low-resolution dictionary learning samples of changing areas to improve the prediction accuracy of land cover type changing areas; for the large scale gap between multi-source images, a two-layer spatiotemporal fusion framework is proposed to reduce the reconstruction pressure of the dictionary and improve the image fusion accuracy; for the assumption that the sparse coefficients of high and low resolution images are linearly related during image reconstruction, it is proposed to construct a nonlinear relationship between high and low resolution sparse coefficients based on support vector regression to improve the estimation accuracy of high-resolution sparse coefficients, thereby improving the quality of the fused image; as shown in Figure 4.
所述多光谱与全色融合数据、SAR与可见光融合数据和多源时空融合数据并行加速处理进入多源遥感数据变化检测模组进行多源遥感数据变化检测，随后，并行加速处理进入多源遥感数据协同检测模组进行多源遥感数据协同检测，最终实现水体信息快速提取、地质灾害信息提取、干旱信息反演和火灾信息提取。The multi-spectral and panchromatic fusion data, SAR and visible light fusion data and multi-source spatiotemporal fusion data are processed in parallel and accelerated and enter the multi-source remote sensing data change detection module for multi-source remote sensing data change detection. Subsequently, the parallel accelerated processing enters the multi-source remote sensing data collaborative detection module for multi-source remote sensing data collaborative detection, ultimately achieving rapid extraction of water body information, geological disaster information extraction, drought information inversion and fire information extraction.
针对多源遥感卫星数据多谱段多时空尺度的观测特性,研究多源遥感数据协同监测技术，最大化利用多源遥感图像的地物特征，提高灾害应急监测的时效性和准确性。In view of the multi-spectral and multi-temporal and multi-spatial scale observation characteristics of multi-source remote sensing satellite data, we study the collaborative monitoring technology of multi-source remote sensing data to maximize the use of the ground feature of multi-source remote sensing images and improve the timeliness and accuracy of disaster emergency monitoring.
通过利用一种多特征联合策略,对多源遥感数据协同的变化检测应用问题进行描述；该研究在降低多源遥感数据量的同时极大地保持了多源图像的特征信息，为多源遥感数据的快速协同变化检测提供特征支撑；利用一种特征融合的方法实现可见光图像的变化检测；如图5所示。By utilizing a multi-feature joint strategy, the application problem of collaborative change detection of multi-source remote sensing data is described; this study greatly maintains the feature information of multi-source images while reducing the amount of multi-source remote sensing data, providing feature support for rapid collaborative change detection of multi-source remote sensing data; a feature fusion method is used to realize change detection of visible light images, as shown in Figure 5.
通过基于深度学习的SAR图像地物分类并提出一系列算法，可以对地物类型进行解析和精准分割，得到不同位置对应的地表覆盖属性；如图6所示。By classifying SAR images based on deep learning and proposing a series of algorithms, the types of objects can be analyzed and accurately segmented to obtain the surface coverage attributes corresponding to different locations; as shown in Figure 6.
所述多源遥感数据融合灾害应急系统包括洪涝灾害监测模组、地质灾害监测模组、旱灾监测模组和火灾监测模组，所述多源遥感数据融合灾害应急系统还包括灾情分析与评估模组。The multi-source remote sensing data fusion disaster emergency response system includes a flood disaster monitoring module, a geological disaster monitoring module, a drought disaster monitoring module and a fire monitoring module. The multi-source remote sensing data fusion disaster emergency response system also includes a disaster situation analysis and assessment module.
采集多源遥感图像数据，建立区域多源遥感图像数据库；采用多源遥感数据协同灾害监测新技术，并通过高分多星多源遥感数据融合、高分多星多源遥感数据协同监测等实验，建立特征提取、分割及分类方法，实现区域多源遥感数据的灾害应急协同监测，并开展实地试验验证；在此基础上，综合历史多源遥感数据，开发基于多源遥感数据融合的灾害应急应用系统，包括洪涝灾害、地质灾害、干旱灾害等，多源异构多尺度、多传感器数据协同综合处理为灾害监测提供了很好的数据保障。Collect multi-source remote sensing image data and establish a regional multi-source remote sensing image database; adopt new technologies for collaborative disaster monitoring using multi-source remote sensing data, and through experiments such as high-resolution multi-satellite multi-source remote sensing data fusion and high-resolution multi-satellite multi-source remote sensing data collaborative monitoring, establish feature extraction, segmentation and classification methods to achieve disaster emergency collaborative monitoring of regional multi-source remote sensing data, and carry out field tests and verifications; on this basis, integrate historical multi-source remote sensing data to develop a disaster emergency application system based on multi-source remote sensing data fusion, including flood disasters, geological disasters, drought disasters, etc. The collaborative comprehensive processing of multi-source, heterogeneous, multi-scale and multi-sensor data provides a good data guarantee for disaster monitoring.
本系统可以整合不同平台、不同载荷的商业对地观测卫星数据，完善地面资源，解决遥感观测卫星数据源各为所有，相互独立问题；并通过与其他观测手段结合，形成全天候、全覆盖的对地观测能力；结合大数据与人工智能等相关技术，突破遥感大数据融合共性关键技术；同时，开展遥感大数据融合在灾害应急中的应用，旨在维护区域战略安全和发展利益。This system can integrate commercial earth observation satellite data from different platforms and with different payloads, improve ground resources, and solve the problem that remote sensing observation satellite data sources are owned by each and are independent of each other; and by combining with other observation methods, it can form an all-weather, full-coverage earth observation capability; by combining big data with artificial intelligence and other related technologies, it can break through the common key technologies of remote sensing big data fusion; at the same time, it can carry out the application of remote sensing big data fusion in disaster emergency response, aiming to safeguard regional strategic security and development interests.
其中，基于卷积神经网络的深度学习时空融合算法，实现了跨卫星、不同分辨率的图像的融合，同时提升了整体图像的分辨率；分别针对不同卫星的图像特征、不同分辨率特征和图像融合特征进行训练监督，从而减小误差，提升图像精度；Among them, the deep learning spatiotemporal fusion algorithm based on convolutional neural networks realizes the fusion of images across satellites and with different resolutions, while improving the resolution of the overall image. Training and supervision are carried out for the image features of different satellites, features of different resolutions, and image fusion features, thereby reducing errors and improving image accuracy.
基于双边加权核图割的图像变化检测算法可以将图像区域块均值的归一化比率作为图像局部区域的强度特征,结合边缘相似度特征作为局部斑块的区域级信息，以此增强图像边缘信息；不论在视觉上还是指标参数上都得到了有效提高,光谱分辨率和空间分辨率更接近于融合参考图像。The image change detection algorithm based on bilateral weighted kernel graph cut can use the normalized ratio of the image area block mean as the intensity feature of the local area of the image, and combine the edge similarity feature as the regional level information of the local patch to enhance the image edge information; both visual and indicator parameters have been effectively improved, and the spectral resolution and spatial resolution are closer to the fusion reference image.
一种智能设备环境遥感监测方法，包括如下步骤：A method for remote sensing monitoring of an intelligent device environment comprises the following steps:
步骤一、数据准备以及预处理Step 1: Data preparation and preprocessing
通过可见光数据预处理模块、SAR遥感数据预处理模块、多时相数据预处理模块、高分辨率遥感数据预处理模块、高分辨率遥感数据预处理模块和其他遥感数据预处理模块分别对可见光数据、SAR遥感数据、多时相数据、高分辨率遥感数据、高分辨率遥感数据和其他遥感数据进行多源遥感数据预处理；Multi-source remote sensing data preprocessing is performed on visible light data, SAR remote sensing data, multi-temporal data, high-resolution remote sensing data, high-resolution remote sensing data and other remote sensing data through visible light data preprocessing module, SAR remote sensing data preprocessing module, multi-temporal data preprocessing module, high-resolution remote sensing data preprocessing module, and other remote sensing data preprocessing modules respectively;
步骤二、多源遥感数据融合与协同感知Step 2: Multi-source remote sensing data fusion and collaborative perception
通过多光谱数据与全色数据融合模组、SAR数据与可见光数据融合模组和多源时空数据融合模组分别得出多光谱与全色融合数据、SAR与可见光融合数据和多源时空融合数据；Through the multispectral data and panchromatic data fusion module, the SAR data and visible light data fusion module and the multi-source spatiotemporal data fusion module, the multispectral and panchromatic fusion data, the SAR and visible light fusion data and the multi-source spatiotemporal fusion data are obtained respectively;
随后，多光谱与全色融合数据、SAR与可见光融合数据和多源时空融合数据并行加速处理进入多源遥感数据变化检测模组进行多源遥感数据变化检测，随后，并行加速处理进入多源遥感数据协同检测模组进行多源遥感数据协同检测，最终实现水体信息快速提取、地质灾害信息提取、干旱信息反演和火灾信息提取；Subsequently, the multi-spectral and panchromatic fusion data, SAR and visible light fusion data, and multi-source spatiotemporal fusion data are processed in parallel and accelerated and then enter the multi-source remote sensing data change detection module for multi-source remote sensing data change detection. Subsequently, the parallel accelerated processing enters the multi-source remote sensing data collaborative detection module for multi-source remote sensing data collaborative detection, and finally realizes the rapid extraction of water body information, geological disaster information extraction, drought information inversion, and fire information extraction.
步骤三、多源遥感数据融合灾害应急Step 3: Multi-source remote sensing data fusion for disaster emergency response
提取的水体信息、地质灾害信息、干旱信息和火灾信息对应通过洪涝灾害监测模组、地质灾害监测模组、旱灾监测模组和火灾监测模组进行洪涝灾害监测、地质灾害监测、旱灾监测和火灾监测，随后使用灾情分析与评估模组进行灾情分析与评估。The extracted water body information, geological disaster information, drought information and fire information are correspondingly used for flood disaster monitoring, geological disaster monitoring, drought monitoring and fire monitoring through flood disaster monitoring module, geological disaster monitoring module, drought monitoring module and fire monitoring module, and then the disaster analysis and assessment module is used for disaster analysis and assessment.
尽管已经示出和描述了本发明的实施例，对于本领域的普通技术人员而言，可以理解在不脱离本发明的原理和精神的情况下可以对这些实施例进行多种变化、修改、替换和变型，本发明的范围由所附权利要求及其等同物限定。Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310439367.2A CN117848979A (en) | 2023-04-21 | 2023-04-21 | A remote sensing monitoring system and method for intelligent device environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310439367.2A CN117848979A (en) | 2023-04-21 | 2023-04-21 | A remote sensing monitoring system and method for intelligent device environment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117848979A true CN117848979A (en) | 2024-04-09 |
Family
ID=90545383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310439367.2A Pending CN117848979A (en) | 2023-04-21 | 2023-04-21 | A remote sensing monitoring system and method for intelligent device environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117848979A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119418200A (en) * | 2024-10-17 | 2025-02-11 | 国家基础地理信息中心 | A method for constructing natural resource remote sensing monitoring process based on multidimensional knowledge reasoning |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105389559A (en) * | 2015-11-12 | 2016-03-09 | 中国科学院遥感与数字地球研究所 | System and method for identifying agricultural disaster scope based on high-resolution remote sensing image |
| US20180218197A1 (en) * | 2017-01-27 | 2018-08-02 | Signal Processing, Inc. | Method and System for Enhancing Predictive Accuracy of Planet Surface Characteristics from Orbit |
| CN108613933A (en) * | 2018-06-13 | 2018-10-02 | 中南林业科技大学 | Forest land arid space-time dynamic monitoring method based on multi-sources RS data fusion |
| CN112307901A (en) * | 2020-09-28 | 2021-02-02 | 国网浙江省电力有限公司电力科学研究院 | Landslide detection-oriented SAR and optical image fusion method and system |
-
2023
- 2023-04-21 CN CN202310439367.2A patent/CN117848979A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105389559A (en) * | 2015-11-12 | 2016-03-09 | 中国科学院遥感与数字地球研究所 | System and method for identifying agricultural disaster scope based on high-resolution remote sensing image |
| US20180218197A1 (en) * | 2017-01-27 | 2018-08-02 | Signal Processing, Inc. | Method and System for Enhancing Predictive Accuracy of Planet Surface Characteristics from Orbit |
| CN108613933A (en) * | 2018-06-13 | 2018-10-02 | 中南林业科技大学 | Forest land arid space-time dynamic monitoring method based on multi-sources RS data fusion |
| CN112307901A (en) * | 2020-09-28 | 2021-02-02 | 国网浙江省电力有限公司电力科学研究院 | Landslide detection-oriented SAR and optical image fusion method and system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119418200A (en) * | 2024-10-17 | 2025-02-11 | 国家基础地理信息中心 | A method for constructing natural resource remote sensing monitoring process based on multidimensional knowledge reasoning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Amarsaikhan et al. | Comparison of multisource image fusion methods and land cover classification | |
| Patino et al. | A review of regional science applications of satellite remote sensing in urban settings | |
| Singh et al. | Identification of flooded area from satellite images using Hybrid Kohonen Fuzzy C-Means sigma classifier | |
| Wei et al. | Real-time remote sensing detection framework of the earth's surface anomalies based on a priori knowledge base | |
| Muszynski et al. | Flood event detection from sentinel 1 and sentinel 2 data: Does land use matter for performance of U-net based flood segmenters? | |
| Wei et al. | Using object-oriented coupled deep learning approach for typical object inspection of transmission channel | |
| CN117848979A (en) | A remote sensing monitoring system and method for intelligent device environment | |
| Sambandham et al. | Deep learning-based harmonization and super-resolution of Landsat-8 and Sentinel-2 images | |
| Kolli et al. | Assessment of change in the extent of mangrove ecosystems using different spectral indices in Google Earth Engine based on random forest model | |
| Seong et al. | Crop classification in South Korea for multitemporal PlanetScope imagery using SFC-DenseNet-AM | |
| Wu et al. | Identification of native and invasive vegetation communities in a tidal flat wetland using gaofen-1 imagery | |
| Cao et al. | Posthurricane damage assessment using satellite imagery and geolocation features | |
| Sharma et al. | Delineation of frequently flooded areas using remote sensing: a case study in part of Indo-Gangetic basin | |
| Amatya et al. | Learnings from rapid response efforts to remotely detect landslides triggered by the August 2021 Nippes earthquake and Tropical Storm Grace in Haiti | |
| Fayad et al. | Vision transformers, a new approach for high-resolution and large-scale mapping of canopy heights | |
| Sakieh et al. | An integrated spectral-textural approach for environmental change monitoring and assessment: analyzing the dynamics of green covers in a highly developing region | |
| Dargahian et al. | Identifying dust sources affecting Southwestern Iran (Khuzestan Province) using remote sensing techniques and HYSPLIT Model | |
| Sui et al. | Processing of multitemporal data and change detection | |
| Wang et al. | [Retracted] Remote Sensing Satellite Image‐Based Monitoring of Agricultural Ecosystem | |
| Jenice Aroma et al. | A wavelet transform applied spectral index for effective water body extraction from moderate-resolution satellite images | |
| Gakhar et al. | Detection of engineered surfaces using deep learning approach in AVIRIS-NG hyperspectral data | |
| Bharathi et al. | Blending of Landsat and Sentinel images using Multi-sensor fusion | |
| Blais et al. | Advances in Remote Sensing and Deep Learning in Coastal Boundary Extraction for Erosion Monitoring. | |
| Wang et al. | Unsupervised deep clustering method for coseismic landslide recognition based on high-resolution images and implicit knowledge | |
| Devi et al. | Pansharpening of Remote Sensing Data of Earth Satellite Images |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20240409 |