CN111832430A - Mountain torrent disaster hyperspectral remote sensing image identification method and identification system thereof - Google Patents
Mountain torrent disaster hyperspectral remote sensing image identification method and identification system thereof Download PDFInfo
- Publication number
- CN111832430A CN111832430A CN202010580725.8A CN202010580725A CN111832430A CN 111832430 A CN111832430 A CN 111832430A CN 202010580725 A CN202010580725 A CN 202010580725A CN 111832430 A CN111832430 A CN 111832430A
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- aerial vehicle
- unmanned aerial
- mountain torrent
- hyperspectral
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000012544 monitoring process Methods 0.000 claims abstract description 56
- 230000003595 spectral effect Effects 0.000 claims abstract description 39
- 238000012360 testing method Methods 0.000 claims abstract description 8
- 238000001228 spectrum Methods 0.000 claims description 32
- 239000002689 soil Substances 0.000 claims description 27
- 238000000701 chemical imaging Methods 0.000 claims description 24
- 238000009825 accumulation Methods 0.000 claims description 21
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 14
- 238000004458 analytical method Methods 0.000 claims description 12
- 230000005540 biological transmission Effects 0.000 claims description 9
- 238000005259 measurement Methods 0.000 claims description 7
- 239000011435 rock Substances 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 6
- 238000011161 development Methods 0.000 claims description 5
- 238000013461 design Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000013500 data storage Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 230000035508 accumulation Effects 0.000 description 16
- 238000005516 engineering process Methods 0.000 description 14
- 238000002310 reflectometry Methods 0.000 description 7
- 230000002265 prevention Effects 0.000 description 6
- 238000011156 evaluation Methods 0.000 description 5
- 238000003384 imaging method Methods 0.000 description 4
- 238000006424 Flood reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000009795 derivation Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012502 risk assessment Methods 0.000 description 2
- 229910052710 silicon Inorganic materials 0.000 description 2
- 239000010703 silicon Substances 0.000 description 2
- 241000272814 Anser sp. Species 0.000 description 1
- 238000004497 NIR spectroscopy Methods 0.000 description 1
- 238000004468 VIS-NIR spectroscopy Methods 0.000 description 1
- 230000003750 conditioning effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000005375 photometry Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/194—Terrestrial scenes using hyperspectral data, i.e. more or other wavelengths than RGB
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Abstract
The invention discloses a method for identifying hyperspectral remote sensing images of mountain torrent disasters. The method comprises the following steps: constructing an unmanned aerial vehicle remote sensing system: step two: compiling an unmanned aerial vehicle preparation working manual and an unmanned aerial vehicle operation manual before flight; step three: testing the working state of the unmanned aerial vehicle-mounted micro hyperspectral imager; step four: determining image recognition performance and parameters: step five: unmanned aerial vehicle remote sensing image system on-the-spot data acquisition: step six: the image recognition system judges the spectral characteristics of the ground features and analyzes and recognizes the evolution of mountain torrent characteristic factors: step seven: the identification method subsystem calculates and distinguishes: step eight: and identifying the mountain torrent characteristic factors, and outputting a mountain torrent ditch mountain torrent characteristic factor spatial distribution map of the monitoring area. The method has the advantages of realizing the accuracy, reliability and timeliness of basic data information of landslides and debris flow areas in areas where mountain torrents are prone to occur. The invention also discloses a system for identifying the hyperspectral remote sensing image of the mountain torrent disaster.
Description
Technical Field
The invention relates to the technical field of monitoring and early warning of mountain torrent disasters, in particular to a hyperspectral remote sensing image identification method of the mountain torrent disasters. The invention also relates to an identification system adopted by the mountain torrent disaster hyperspectral remote sensing image identification method.
Background
Under the background of global warming and frequent extreme weather, in recent years, China is facing to the rising of natural disaster risks and is entering a period of frequent natural disasters. Among the disasters, mountain floods and secondary disasters face the most severe flood disaster problem every year, and particularly, a plurality of towns or residential points in a hilly area are located at debris flow gullies, river valley coasts and even landslides. The mountainous areas of China occupy about two thirds of the area of the soil, and many areas lack debris flow and landslide disaster monitoring facilities induced by mountain floods, and the monitoring of the debris flow and the landslide is mainly realized by group measurement and group defense, so that the monitoring of dangerous points in the areas where the mountain floods are easy to occur is insufficient. The existing various field torrent disaster monitoring, forecasting and early warning methods and equipment have the defects of low technological content, poor monitoring precision, untimely result and insufficient reliability, and become prominent difficulties in the current flood control and disaster reduction work. Since the implementation of 'national mountain torrent disaster prevention and control planning' in 2006, the enhancement of mountain torrent disaster prevention and control becomes important content for natural disaster prevention and control, wherein the monitoring and evaluation of mountain torrent disaster-prone areas is one of key technologies for realizing effective prevention and control of mountain torrent disasters, and the establishment of a set of mountain torrent disaster situation rapid monitoring, statistics, analysis and evaluation methods is urgently needed for disaster prevention and reduction work of the mountain torrent disaster-prone areas at present.
In recent years, China has made certain progress in monitoring and evaluating mountain torrent disasters, and a plurality of advanced monitoring devices and technologies comprise application of a satellite remote sensing technology, a radar monitoring technology, an unmanned aerial vehicle remote sensing monitoring technology and the like, so that the early-stage forecasting and early-warning capacity of the mountain torrent disaster monitoring technology, particularly in a regional large-scale range, is improved to a certain extent. However, the satellite is restricted by the operation orbit and the operation cycle, the radar detection has strict requirements on the monitoring environment, and the like, so that the application range of the prior technologies is limited, and the application fields of advancing performance, mobility, timeliness and the like of monitoring and forecasting of the mountain torrent disaster can not be met. An unmanned aerial vehicle monitoring technology with the advantages of convenience, rapidness and remote sensing becomes a first choice for carrying out real-time, dynamic and complex environment monitoring on large-scale mountain torrent disasters.
Unmanned aerial vehicle remote sensing is the third generation remote sensing platform behind traditional aviation, space remote sensing platform. Compared with the traditional aviation and aerospace remote sensing platforms, the remote sensing data acquisition system has the advantages of low remote sensing data acquisition cost, strong safety operation guarantee capability, high remote sensing data precision, rapid emergency response capability, capability of acquiring data in the cloud, and capability of realizing remote sensing monitoring in large areas, long voyage, fixed points and fixed areas. The hyperspectral imager combines an imaging technology and a spectrum technology, detects two-dimensional geometric space and one-dimensional spectral information of a target, and acquires continuous and narrow-band image data (spectrum cube) with high spectral resolution. The micro hyperspectral imager can clearly focus in the whole spectral range, has high photometric measurement accuracy, and is particularly suitable for collecting imaging spectral data of plants, soil, minerals and the like. The hyperspectral remote sensing image system carried by the unmanned aerial vehicle platform is applied to the field of mountain torrent disaster monitoring, and can effectively improve the accuracy, reliability and timeliness of mountain torrent disaster basic data. However, the technology is still in the starting and exploring stages in the mountain torrent disaster monitoring application in China.
Therefore, the development of the method for identifying the hyperspectral remote sensing images of the mountain torrent disasters has a wide application prospect.
Disclosure of Invention
The invention aims to provide a mountain torrent disaster hyperspectral remote sensing image identification method, which is based on an unmanned aerial vehicle hyperspectral remote sensing image identification technology, can be used for quickly and remotely sensing and monitoring mountain torrent disaster easily-occurring areas, realizes the remote sensing image characteristic spectrum identification and mountain torrent disaster factor calculation and discrimination of landslide bodies, debris flow accumulation bodies and debris flow gully beds, and generates a mountain torrent disaster easily-occurring area characteristic factor space-time distribution map.
The second purpose of the invention is to provide a mountain torrent disaster hyperspectral remote sensing image identification system, which can be used for rapidly remotely sensing and monitoring mountain torrent disaster-prone areas and realizing remote sensing image identification of landslides, debris flow accumulation bodies and debris flow gully beds.
In order to achieve the first object of the present invention, the technical solution of the present invention is: the identification method of the mountain torrent disaster hyperspectral remote sensing image identification system is characterized by comprising the following steps of: comprises the following steps of (a) carrying out,
the method comprises the following steps: constructing an unmanned aerial vehicle remote sensing system:
based on the regional characteristics of the underlying surface in the mountain torrent disaster prone area and the characteristics of the mountain torrent disasters, an unmanned aerial vehicle remote sensing platform and a micro hyperspectral imaging system are optimally combined to form an unmanned aerial vehicle remote sensing image system, and the unmanned aerial vehicle remote sensing image system meets the requirements of remote sensing image identification performance and parameter selection of a micro hyperspectral imager under flight conditions;
step two: preparing a working manual and an unmanned aerial vehicle operation manual before the unmanned aerial vehicle flies, and testing and standardizing a measurement and control system, a data transmission system and a dynamic monitoring support system of the unmanned aerial vehicle remote sensing platform;
step three: compiling an operation manual of the unmanned aerial vehicle-mounted micro hyperspectral imager by combining with an unmanned aerial vehicle remote sensing platform, testing the working state of the unmanned aerial vehicle-mounted micro hyperspectral imager, and determining the stability and flexibility of an unmanned aerial vehicle remote sensing image system;
step four: determining image recognition performance and parameters:
calibrating spectral features of ground objects by using remote sensing images of an unmanned airborne micro hyperspectral imager, analyzing the reflection spectral features of different factors in a region in different environments, establishing a regional factor spectral identification method under a dynamic condition, and providing a precondition for identifying remote sensing images of landslides, debris flow accumulation bodies and debris flow gully beds;
carrying out typical torrent ditch spectral feature monitoring, and establishing a torrent disaster feature factor database in a specific area;
step five: unmanned aerial vehicle remote sensing image system on-the-spot data acquisition:
the unmanned airborne micro hyperspectral imager collects and processes image information of a mountain torrent disaster site, and transmits the image information to a mountain torrent disaster characteristic factor database in a wireless and airborne memory transmission and recording mode;
step six: the image recognition system judges the spectral characteristics of the ground features and analyzes and recognizes the evolution of mountain torrent characteristic factors:
the image recognition system subsystem automatically classifies the spectral characteristics of the mountain torrent disaster factors according to the regional spectral characteristic database;
step seven: the identification method subsystem calculates and distinguishes:
according to the characteristic spectra of different mountain torrent disaster factors, calculating, judging and determining each factor by using an identification index set of loose deposits, vegetation, soil and water in an identification method subsystem;
step eight: and identifying the mountain torrent characteristic factors by adopting the normalized vegetation index and geographic information system software, realizing remote sensing image identification of the landslide body, the debris flow accumulation body and the debris flow gully bed, and outputting a mountain torrent gully mountain torrent characteristic factor spatial distribution map of the monitoring area.
In the above technical solution, further comprising a ninth step,
the ninth step specifically comprises: based on the identification of different factors, the landslide body, the debris flow accumulation body and the debris flow gully bed are monitored, the monitoring result is analyzed, summarized and summarized by adopting a spectral evolution characteristic analysis method, and the law of the occurrence and development of disasters such as landslide, debris flow and the like is researched.
In the technical scheme, in the fifth step, the functions of the unmanned aerial vehicle remote sensing system comprise data storage, extraction, spectrum identification, analysis and derivation;
in the fourth step, the factors comprise vegetation, rocks, soil and moisture content;
in the sixth step, the mountain torrent disaster factors comprise loose accumulation bodies, vegetation, soil and water bodies.
In the technical scheme, in the fifth step, the unmanned aerial vehicle remote sensing image system is composed of an unmanned aerial vehicle remote sensing platform and a miniature airborne hyperspectral imaging system; the micro airborne hyperspectral imaging system comprises an unmanned airborne micro hyperspectral imager and airborne platform data acquisition software;
the unmanned aerial vehicle-mounted micro hyperspectral imager works on the spot, and the unmanned aerial vehicle remote sensing platform can be selected according to actual conditions in two modes of automatic air route design and manual control according to flight operation conditions in different areas;
the remote sensing data image is automatically transmitted to an acquisition processing system of the unmanned airborne micro hyperspectral imager on line and is simultaneously written into a characteristic factor database.
In the technical scheme, the unmanned aerial vehicle-mounted micro hyperspectral imager selects a full-field hyperspectral imaging system.
In order to achieve the second object of the present invention, the technical solution of the present invention is: mountain torrent calamity hyperspectral remote sensing image identification system, its characterized in that: the system comprises an unmanned aerial vehicle remote sensing image system, a characteristic factor database and a remote sensing image identification system;
the unmanned aerial vehicle remote sensing system consists of an unmanned aerial vehicle remote sensing platform and a miniature airborne hyperspectral imaging system; the unmanned aerial vehicle remote sensing platform provides a real-time measurement and control system and a monitoring data transmission link for the micro airborne hyperspectral imaging system;
the micro airborne hyperspectral imaging system comprises an unmanned airborne micro hyperspectral imager and airborne platform data acquisition software;
the unmanned aerial vehicle remote sensing image system collects and processes the mountain torrent disaster site image information and transmits the mountain torrent disaster site image information to the characteristic factor database;
the image recognition system automatically classifies the characteristic factor database, the spectrum acquisition software interprets the relevant parameters of the remote sensing image data of the torrent disaster factors, and the corresponding indexes of the remote sensing image data are calculated and determined.
In the technical scheme, the characteristic factor database comprises a factor spectrum identification subsystem, a landslide mass debris flow accumulation body and a debris flow gully bed remote sensing image identification subsystem under the dynamic condition.
In the technical scheme, the remote sensing image recognition system comprises a micro hyperspectral imager monitoring subsystem, a reflected spectrum feature recognition subsystem and a spectrum evolution feature analysis subsystem.
The invention has the following advantages:
(1) according to the invention, a micro hyperspectral imager and supporting equipment are matched with an unmanned aerial vehicle carrier for the first time, the micro hyperspectral imager is applied to monitoring and evaluation of a regional mountain torrent disaster vulnerable area, and an unmanned aerial vehicle-mounted hyperspectral remote sensing image identification key technology is developed; the method has the advantages of extracting the spectral characteristics of the ground objects with high precision and high efficiency, quickly identifying landslide and debris flow areas in the area where the mountain torrent disasters easily occur, and monitoring and evaluating; the problems of narrow monitoring surface and low efficiency in large-scale disaster monitoring in the prior art are solved, and the technical problem of casualties caused by monitoring of mountain torrent disasters in dangerous complex environments is solved;
(2) the invention introduces holographic reflection grating type high spectrum imaging technology, optical devices formed by a large number of parallel narrow slits with equal width and equal spacing on the grating have uniform light splitting, and can be used in the whole spectrum waveband range; the unmanned airborne micro hyperspectral imager adopts a grating light splitting method, the photosensitive wavelength range of a silicon CCD is 300-1000nm, the C-T (Czerny-Turner) coaxial reflection optical design based on the holographic grating is adopted, the micro hyperspectral imager is completely achromatic, and the technical advantages of no image distortion and no spectrum distortion, convex reflection holographic grating and the like are realized;
(3) according to the method, the mountain torrent characteristic factor database is established as a basis, the spectral characteristics of the factors are identified and classified, and the regional mountain torrent disaster factor spectral characteristic database is established, so that the synchronous monitoring of mountain torrent characteristic factors and the rapid and accurate discrimination of the spectral characteristics can be guaranteed under various weather conditions, the identification precision and classification of various ground objects in a mountain torrent disaster monitoring region are greatly improved, and the method has practical values for analyzing and judging mountain torrent disaster prevention and avoidance risk assessment and the like;
(4) the unmanned aerial vehicle-mounted hyperspectral imager can realize automatic classification of bare soil and bare rock; the outstanding difficult problems that the traditional remote sensing image and the common camera cannot solve are solved (for example, the traditional remote sensing image and the common camera have small wave band range and are difficult to distinguish bare soil and bare rock); the unmanned airborne hyperspectral imager reflects the spectral characteristics of vegetation in detail and is used for distinguishing the type and the growth state of the vegetation; the unmanned aerial vehicle-mounted hyperspectral imager can distinguish dry soil from wet soil, can invert the water content of the soil after calibration, and is used for monitoring the occurrence and development of mountain torrent disasters;
(5) according to different mountain torrent disaster factor characteristic spectra, the invention provides a set of factor identification method and an index calculation formula, and the indexes of loose deposits, vegetation, soil, water bodies and the like are accurately calculated and accurately analyzed and judged; adopting ENVI and ArcGIS software to quickly identify the characteristic factors of the torrential flood disaster area and outputting a typical torrential flood ditch torrential flood characteristic factor spatial distribution map; the technical problem of a core for monitoring and evaluating regional mountain torrent disasters is solved, namely, the accuracy, reliability and timeliness of basic data information of landslides and debris flow regions where mountain torrent disasters are prone to occur are achieved.
Drawings
FIG. 1 is a schematic flow chart of the method of the present invention.
FIG. 2 is a diagram of the photosensitive wavelength range of the silicon CCD of the micro hyperspectral imager.
Fig. 3 is a partial torrent feature factor database according to an embodiment of the present invention.
Fig. 4 is a typical mountain torrent gutter feature spectrum characteristic diagram in the embodiment of the invention.
Fig. 5 is a partial torrent feature factor spectral feature database in an embodiment of the present invention.
Fig. 6 is a typical mountain torrent gutter torrent feature factor spatial distribution diagram in the embodiment of the present invention.
In fig. 2, a1 represents a CCD response curve; a2 denotes the blue channel; a3 denotes a heat mirror; a4 denotes the green channel; a5 denotes the red channel.
In fig. 5, B1 represents vegetation; b2 denotes rock; b3 denotes dry soil; b4 represents wet soil.
In fig. 6, N represents north.
Detailed Description
The embodiments of the present invention will be described in detail with reference to the accompanying drawings, which are not intended to limit the present invention, but are merely exemplary. While the advantages of the invention will be clear and readily understood by the description.
With reference to the accompanying drawings: the identification method of the mountain torrent disaster hyperspectral remote sensing image identification system comprises the following steps,
the method comprises the following steps: constructing an unmanned aerial vehicle remote sensing system: based on the regional characteristics of the underlying surface in the mountain torrent disaster prone area and the characteristics of the mountain torrent disasters, an unmanned aerial vehicle remote sensing platform and a micro hyperspectral imaging system are optimally combined to form an unmanned aerial vehicle remote sensing image system, and the unmanned aerial vehicle remote sensing image system meets the requirements of remote sensing image identification performance and parameter selection of a micro hyperspectral imager under flight conditions;
step two: preparing a working manual and an unmanned aerial vehicle operation manual before the unmanned aerial vehicle flies, and testing and standardizing a measurement and control system, a data transmission system, a dynamic monitoring support system and the like of the unmanned aerial vehicle remote sensing platform;
step three: compiling an operation manual of the unmanned aerial vehicle-mounted micro hyperspectral imager by combining with an unmanned aerial vehicle remote sensing platform, testing the working state of the unmanned aerial vehicle-mounted micro hyperspectral imager, and determining the stability and flexibility of an unmanned aerial vehicle remote sensing image system;
step four: determining image recognition performance and parameters: calibrating spectral features of ground objects by using remote sensing images of an unmanned airborne micro hyperspectral imager, analyzing the reflection spectral features of different factors in a region in different environments, establishing a regional factor spectral identification method under a dynamic condition, and providing a precondition for identifying remote sensing images of landslides, debris flow accumulation bodies and debris flow gully beds;
carrying out typical torrent ditch spectral feature monitoring, and establishing a torrent disaster feature factor database in a specific area;
step five: unmanned aerial vehicle remote sensing image system on-the-spot data acquisition: the unmanned airborne micro hyperspectral imager collects and processes image information of a mountain torrent disaster site, and transmits the image information to a mountain torrent disaster characteristic factor database in a wireless and airborne memory transmission and recording mode;
step six: the image recognition system judges the spectral characteristics of the ground features and analyzes and recognizes the evolution of mountain torrent characteristic factors: the image recognition system subsystem automatically classifies the spectral characteristics of the mountain torrent disaster factors according to the regional spectral characteristic database;
step seven: the identification method subsystem calculates and distinguishes:
according to the characteristic spectra of different mountain torrent disaster factors, calculating, judging and determining each factor by using an identification index set of loose deposits, vegetation, soil and water in an identification method subsystem;
step eight: and identifying the mountain torrent characteristic factors by adopting a normalized vegetation index (ENVI) and geographic information system (ArcGIS) software, realizing remote sensing image identification of a landslide body, a debris flow accumulation body and a debris flow gully bed, and outputting a mountain torrent gutter characteristic factor spatial distribution map of the monitoring area.
Further, the method also comprises a step nine,
the ninth step specifically comprises: based on the identification of different factors, the landslide body, the debris flow accumulation body and the debris flow gully bed are monitored, the monitoring results are analyzed, summarized and summarized by adopting a spectral evolution characteristic analysis method, and the occurrence and development rules of disasters such as landslide, debris flow and the like are researched (as shown in figure 1).
Further, in the fifth step, the functions of the unmanned aerial vehicle remote sensing system comprise data storage, extraction, spectrum identification, analysis, derivation and the like;
in the fourth step, the factors comprise vegetation, rocks, soil, moisture content and the like;
in the sixth step, the mountain torrent disaster factors comprise loose heaps, vegetation, soil, water bodies and the like.
Furthermore, in the fifth step, the unmanned aerial vehicle remote sensing image system is composed of an unmanned aerial vehicle remote sensing platform and a miniature airborne hyperspectral imaging system; the micro airborne hyperspectral imaging system comprises an unmanned airborne micro hyperspectral imager and airborne platform data acquisition software;
the unmanned aerial vehicle-mounted micro hyperspectral imager works on the field to collect data images, and the unmanned aerial vehicle remote sensing platform can be selected according to actual conditions under two modes of automatic air route design and manual control according to flight operating conditions of different areas;
the remote sensing data image acquired by the unmanned airborne micro hyperspectral imager is automatically transmitted to an acquisition processing system of airborne platform data acquisition software on line and is simultaneously written into a characteristic factor database;
the unmanned aerial vehicle carries miniature hyperspectral imager and selects the slot (16um-100um) of multiple specifications and replaceable width according to the actual application requirement, satisfies the application requirement of different weather, improves the remote sensing image spatial resolution and spectral resolution.
Furthermore, the unmanned airborne micro hyperspectral imager selects a full-field hyperspectral imaging system;
the full-field hyperspectral imaging system selected by the unmanned airborne micro hyperspectral imager generates two image deformations (minimum wedge deformation (Smile) and trapezoidal deformation (Keystone)) and is controlled in 1 pixel of the CCD (almost no deformation), and the full-field hyperspectral imaging system is not required to be corrected again when in use; the full-field hyperspectral imaging system actually applies and measures the obtained image deformation:
smile is less than or equal to 0.12pixels @1550nm, Keystone is less than or equal to 0.04pixels, the application requirements of different climates are met, and the spatial resolution and the spectral resolution of the remote sensing image are improved;
wherein CCD is charge coupled device, which is a detecting element using charge to represent signal magnitude and using coupling mode to transmit signal, and has self-scanning and sensing functionsWave spectrumWide range, small distortion, small size, light weight, low system noise, low power consumption, long service life, high reliability and other advantages, and may be used in making very high integrated assembly.
With reference to the accompanying drawings: the mountain torrent disaster hyperspectral remote sensing image identification system comprises an unmanned aerial vehicle remote sensing image system, a characteristic factor database and a remote sensing image identification system;
the unmanned aerial vehicle remote sensing system consists of an unmanned aerial vehicle remote sensing platform and a miniature airborne hyperspectral imaging system; the unmanned aerial vehicle remote sensing platform provides a real-time measurement and control system and a monitoring data transmission link for the micro airborne hyperspectral imaging system;
the micro airborne hyperspectral imaging system comprises an unmanned airborne micro hyperspectral imager and airborne platform data acquisition software;
the unmanned aerial vehicle remote sensing image system collects and processes the mountain torrent disaster site image information and transmits the mountain torrent disaster site image information to the characteristic factor database;
the image recognition system automatically classifies the characteristic factor database, obtains relevant parameters of remote sensing image data of the mountain torrent disaster factors interpreted by software, and calculates and determines corresponding indexes of the remote sensing image data; identifying the mountain torrent characteristic factors by using normalized vegetation index (ENVI) software and geographic information system (ArcGIS) software, and outputting a regional mountain torrent ditch mountain torrent characteristic factor spatial distribution map;
among them, ENVI and ArcGIS are both prior art.
Further, the characteristic factor database comprises a factor spectrum identification subsystem, a landslide mass debris flow accumulation body and a debris flow gully bed remote sensing image identification subsystem under the dynamic condition;
the factor identification of the monitoring area mainly comprises reflection spectrum characteristics of vegetation, rocks, soil, water content and the like in the area where the mountain torrent disaster is easy to occur under different environments and a factor spectrum identification system.
Further, the remote sensing image recognition system comprises a micro hyperspectral imager monitoring subsystem, a reflected spectrum feature recognition subsystem and a spectrum evolution feature analysis subsystem (as shown in fig. 1).
Furthermore, the unmanned airborne micro hyperspectral imager is an unmanned airborne micro hyperspectral imager with high spatial resolution and ultrahigh imaging performance;
the resolution ratio of the unmanned airborne micro hyperspectral imager is 3.5 nm;
the unmanned airborne micro hyperspectral imager comprises more than 200 wave bands (shown in figure 2) in NIR (900-1700nm) and VNIR (400-1000 nm);
wherein NIR and VNIR are both prior art; NIR is a modern near infrared spectroscopy technique; VNIR is a visible near infrared spectroscopy analysis technique.
The airborne platform data acquisition software is HDPU spectrum acquisition software; the instrument can acquire images at a faster frame rate to meet the shooting requirement of high-speed flight motion.
Examples
The present invention will now be described in detail with reference to the accompanying drawings, using the embodiment of the present invention as an example, but the present invention is not limited to the embodiment, and is only exemplary. While the advantages of the invention will be apparent and readily appreciated by the description. The embodiment has guiding significance for the application of the method in the rapid remote sensing monitoring of the mountain torrent disaster-prone area in other areas and the realization of the remote sensing image recognition and monitoring evaluation of landslides, debris flow accumulation bodies and debris flow gully beds.
The method for identifying the hyperspectral remote sensing images of the mountain torrent disasters comprises the following steps:
the method comprises the following steps: regional data collection
Collecting earthquake district regional characteristics based on earthquake and flood disaster risk assessment needs in a county of Qiang autonomous State of the Tibetan nationality of the Abam of a certain province: the method comprises the steps of carrying out investigation and evaluation and reason analysis on the mountain torrent disaster according to geographic positions, topographic characteristics, geological characteristics, meteorological characteristics and mountain torrent disaster characteristics, and establishing a geographic information basic database;
step two: mountain torrent disaster characteristic factor database
Classifying and naming aerial images according to ground feature characteristics, and establishing a complete typical torrential gutter characteristic factor library (as shown in figure 3) in a monitoring area according to color tone, shape, texture and other characteristic difference descriptions;
step three: implementation steps of remote sensing image identification method
S7.1: identifying and comparing the spectral characteristics of the ground features for carrying out typical torrential flood ditch monitoring and surveying, and selecting and determining representative spectra of all factors (as shown in figure 4);
s7.2: classifying and determining the name of each factor and extracting a corresponding spectrum by taking a remote sensing image spectrum cube as a basis, and firstly establishing a spectral feature database (shown in figure 5) of each factor;
s7.3: determining an identification method of each factor according to the characteristic spectrum of different torrential flood disaster factors, wherein the identification method of each factor comprises the following specific steps:
1) loose bulk identification
The soil regulation vegetation index (SAVI) is used for identifying loose accumulations on a debris flow gully bed and a slope, L is 0.5 in a test (L can be other values according to actual conditions), and the method for identifying the loose accumulations is as follows (1):
in the above formula (1): rhoNIRIs the infrared band reflectivity; rhoREDIs the red band reflectivity;
SAVI is the soil conditioning vegetation index;
l is a parameter which changes along with the density of the vegetation and has a value range of 0-1;
2) vegetation identification
Utilizing the enii software (enii for visualization images) as a complete remote sensing image processing platform, which is the prior art, the Vegetation identification method using the normalized Vegetation Index NDVI (normalized difference Vegetation Index) is as follows (2):
in the above formula (2): rhoNIRIs the infrared band reflectivity, pREDIs the red band reflectivity;
NDVIVis NDVI of vegetation-covered portion;
NDVI0NDVI of non-vegetation covered portions;
NDVI is the normalized vegetation index;
fvis the vegetation coverage;
NDVIVand NDVI0The determination of two parameters is critical; in practice, due to the lack of reference to large area surface survey data, confidence intervals are usually given according to the histogram, and the minimum and maximum values in the interval are used as the NDVIVAnd NDVI0The value, or NDVI values of 5% and 95% frequency are taken as NDVIVAnd NDVI0A value;
the latter method is used in this embodiment (i.e., taking 5% and 95% frequenciesNDVI value of the ratio was taken as NDVIVAnd NDVI0A value);
in ENVI, the concrete implementation steps are as follows:
selecting a main menu → Transform → NDVI, and calculating a normalized vegetation index NDVI;
② selecting the main menu → Basic Tools → Statistics → computer Statistics to perform statistical analysis and obtain NDVIVAnd NDVI0A value;
③ selecting the main menu → Basic Tools → Band Math, and calculating the vegetation coverage fv；
3) Soil identification
Soil index (SBI) for identifying soil, the method for identifying soil being as follows (3):
in the above formula (3): rhoNIRIs the infrared band reflectivity, pREDIs the red band reflectivity;
SBI is soil index;
4) water body identification
The normalized water body index (NDWI) is used for identifying the water body, and the water body identification method is as follows (4):
in the above formula (3): rhoREDIs the red band reflectivity;
NDWI is the normalized water body index;
step four: identifying torrent characteristic factors (the identified torrent characteristic factors are shown in figure 6) based on seven ditches and goose gate ditches in an earthquake area of a certain county of Qiang nationality of Tibetan nationality of Aba, province by adopting ENVI and ArcGIS software, realizing remote sensing image identification of landslide bodies, debris flow accumulation bodies and debris flow ditch beds in the earthquake area of the certain county of Qiang nationality of Zang nationality of Arab, province, and outputting a spatial distribution map of the torrent characteristic factors of the torrent ditches in the monitoring area.
And (4) conclusion: the embodiment can realize rapid remote sensing monitoring and realize remote sensing image identification of landslide bodies, debris flow accumulation bodies and debris flow gully beds.
Other parts which are not described belong to the prior art.
Claims (8)
1. The method for identifying the hyperspectral remote sensing images of the mountain torrent disasters is characterized by comprising the following steps of: comprises the following steps of (a) carrying out,
the method comprises the following steps: constructing an unmanned aerial vehicle remote sensing system:
based on the regional characteristics of the underlying surface in the mountain torrent disaster prone area and the characteristics of the mountain torrent disasters, an unmanned aerial vehicle remote sensing platform and a micro hyperspectral imaging system are optimally combined to form an unmanned aerial vehicle remote sensing image system, and the unmanned aerial vehicle remote sensing image system meets the requirements of remote sensing image identification performance and parameter selection of a micro hyperspectral imager under flight conditions;
step two: preparing a working manual and an unmanned aerial vehicle operation manual before the unmanned aerial vehicle flies, and testing and standardizing a measurement and control system, a data transmission system and a dynamic monitoring support system of the unmanned aerial vehicle remote sensing platform;
step three: compiling an operation manual of the unmanned aerial vehicle-mounted micro hyperspectral imager by combining with an unmanned aerial vehicle remote sensing platform, testing the working state of the unmanned aerial vehicle-mounted micro hyperspectral imager, and determining the stability and flexibility of an unmanned aerial vehicle remote sensing image system;
step four: determining image recognition performance and parameters:
calibrating spectral features of ground objects by using remote sensing images of an unmanned airborne micro hyperspectral imager, analyzing the reflection spectral features of different factors in a region in different environments, establishing a regional factor spectral identification method under a dynamic condition, and providing a precondition for identifying remote sensing images of landslides, debris flow accumulation bodies and debris flow gully beds;
carrying out typical torrent ditch spectral feature monitoring, and establishing a torrent disaster feature factor database in a specific area;
step five: unmanned aerial vehicle remote sensing image system on-the-spot data acquisition:
the unmanned airborne micro hyperspectral imager collects and processes image information of a mountain torrent disaster site, and transmits the image information to a mountain torrent disaster characteristic factor database in a wireless and airborne memory transmission and recording mode;
step six: the image recognition system judges the spectral characteristics of the ground features and analyzes and recognizes the evolution of mountain torrent characteristic factors:
the image recognition system subsystem automatically classifies the spectral characteristics of the mountain torrent disaster factors according to the regional spectral characteristic database;
step seven: the identification method subsystem calculates and distinguishes:
according to the characteristic spectra of different mountain torrent disaster factors, calculating, judging and determining each factor by using an identification index set of loose deposits, vegetation, soil and water in an identification method subsystem;
step eight: and identifying the mountain torrent characteristic factors by adopting the normalized vegetation index and geographic information system software, realizing remote sensing image identification of the landslide body, the debris flow accumulation body and the debris flow gully bed, and outputting a mountain torrent gully mountain torrent characteristic factor spatial distribution map of the monitoring area.
2. The method for hyperspectral remote sensing image recognition of mountain torrent disasters according to claim 1, characterized by comprising the following steps: the method also comprises the step nine of,
the ninth step specifically comprises: based on the identification of different factors, the landslide body, the debris flow accumulation body and the debris flow gully bed are monitored, the monitoring result is analyzed, summarized and summarized by adopting a spectral evolution characteristic analysis method, and the law of the occurrence and development of disasters such as landslide, debris flow and the like is researched.
3. The method for hyperspectral remote sensing image recognition of mountain torrent disasters according to claim 2, characterized in that: in the fourth step, the factors comprise vegetation, rocks, soil and moisture content;
in the fifth step, the functions of the unmanned aerial vehicle remote sensing system comprise data storage, extraction, spectrum identification, analysis and export;
in the sixth step, the mountain torrent disaster factors comprise loose accumulation bodies, vegetation, soil and water bodies.
4. The method for hyperspectral remote sensing image identification of mountain torrent disasters according to claim 3, characterized in that: in the fifth step, the unmanned aerial vehicle remote sensing image system is composed of an unmanned aerial vehicle remote sensing platform and a miniature airborne hyperspectral imaging system; the micro airborne hyperspectral imaging system comprises an unmanned airborne micro hyperspectral imager and airborne platform data acquisition software;
the unmanned aerial vehicle-mounted micro hyperspectral imager works on the spot, and the unmanned aerial vehicle remote sensing platform can be selected according to actual conditions in two modes of automatic air route design and manual control according to flight operation conditions in different areas;
the remote sensing data image is automatically transmitted to an acquisition processing system of the unmanned airborne micro hyperspectral imager on line and is simultaneously written into a characteristic factor database.
5. The method for hyperspectral remote sensing image identification of mountain torrent disasters according to claim 4, characterized in that: the unmanned aerial vehicle-mounted micro hyperspectral imager selects a full-field hyperspectral imaging system.
6. The identification system adopted by the mountain torrent disaster hyperspectral remote sensing image identification method according to any one of claims 1 to 5 is characterized in that: the system comprises an unmanned aerial vehicle remote sensing image system, a characteristic factor database and a remote sensing image identification system;
the unmanned aerial vehicle remote sensing system consists of an unmanned aerial vehicle remote sensing platform and a miniature airborne hyperspectral imaging system; the unmanned aerial vehicle remote sensing platform provides a real-time measurement and control system and a monitoring data transmission link for the micro airborne hyperspectral imaging system;
the micro airborne hyperspectral imaging system comprises an unmanned airborne micro hyperspectral imager and airborne platform data acquisition software;
the unmanned aerial vehicle remote sensing image system collects and processes the mountain torrent disaster site image information and transmits the mountain torrent disaster site image information to the characteristic factor database;
the image recognition system automatically classifies the characteristic factor database, obtains relevant parameters of remote sensing image data of the mountain torrent disaster factors interpreted by software, and calculates and determines corresponding indexes of the remote sensing image data.
7. The mountain torrent disaster hyperspectral remote sensing image recognition system according to claim 6, wherein: the characteristic factor database comprises a factor spectrum identification subsystem under a dynamic condition, a landslide mass debris flow accumulation body and a debris flow gully bed remote sensing image identification subsystem.
8. The mountain torrent disaster hyperspectral remote sensing image recognition system according to claim 7, wherein: the remote sensing image recognition system comprises a micro hyperspectral imager monitoring subsystem, a reflected spectrum feature recognition subsystem and a spectrum evolution feature analysis subsystem.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010580725.8A CN111832430B (en) | 2020-06-23 | 2020-06-23 | Mountain torrent disaster hyperspectral remote sensing image identification method and identification system thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010580725.8A CN111832430B (en) | 2020-06-23 | 2020-06-23 | Mountain torrent disaster hyperspectral remote sensing image identification method and identification system thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111832430A true CN111832430A (en) | 2020-10-27 |
| CN111832430B CN111832430B (en) | 2024-01-09 |
Family
ID=72898294
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010580725.8A Active CN111832430B (en) | 2020-06-23 | 2020-06-23 | Mountain torrent disaster hyperspectral remote sensing image identification method and identification system thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111832430B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112801007A (en) * | 2021-02-07 | 2021-05-14 | 中国科学院空天信息创新研究院 | Hot melt pond state identification method combining long time sequence data and machine learning algorithm |
| CN115272874A (en) * | 2022-09-28 | 2022-11-01 | 中国科学院、水利部成都山地灾害与环境研究所 | Debris flow disaster identification and frequency calculation method based on remote sensing image |
| CN115290578A (en) * | 2022-08-15 | 2022-11-04 | 中国科学院空天信息创新研究院 | High-spectrum detection method and system for cohesive force of debris flow channel fine particle accumulation |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140019166A1 (en) * | 2012-07-13 | 2014-01-16 | Aaron L. Swanson | Spectral image classification of rooftop condition for use in property insurance |
| CN107195164A (en) * | 2017-07-03 | 2017-09-22 | 长江水利委员会长江科学院 | Mountain flood on-line monitoring identification method for early warning and its early warning system |
| CN110570462A (en) * | 2019-09-12 | 2019-12-13 | 中山大学 | flood inundation range automatic extraction method based on polarized radar remote sensing image |
| KR20200055388A (en) * | 2018-11-13 | 2020-05-21 | 한국건설기술연구원 | Information analysis system of rivers |
-
2020
- 2020-06-23 CN CN202010580725.8A patent/CN111832430B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140019166A1 (en) * | 2012-07-13 | 2014-01-16 | Aaron L. Swanson | Spectral image classification of rooftop condition for use in property insurance |
| CN107195164A (en) * | 2017-07-03 | 2017-09-22 | 长江水利委员会长江科学院 | Mountain flood on-line monitoring identification method for early warning and its early warning system |
| KR20200055388A (en) * | 2018-11-13 | 2020-05-21 | 한국건설기술연구원 | Information analysis system of rivers |
| CN110570462A (en) * | 2019-09-12 | 2019-12-13 | 中山大学 | flood inundation range automatic extraction method based on polarized radar remote sensing image |
Non-Patent Citations (1)
| Title |
|---|
| 李珊珊;宫辉力;范一大;陈世荣;温奇;胡卓玮;: "舟曲特大山洪泥石流灾害遥感应急监测评估方法研究", 农业灾害研究, no. 01 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112801007A (en) * | 2021-02-07 | 2021-05-14 | 中国科学院空天信息创新研究院 | Hot melt pond state identification method combining long time sequence data and machine learning algorithm |
| CN115290578A (en) * | 2022-08-15 | 2022-11-04 | 中国科学院空天信息创新研究院 | High-spectrum detection method and system for cohesive force of debris flow channel fine particle accumulation |
| CN115272874A (en) * | 2022-09-28 | 2022-11-01 | 中国科学院、水利部成都山地灾害与环境研究所 | Debris flow disaster identification and frequency calculation method based on remote sensing image |
| CN115272874B (en) * | 2022-09-28 | 2022-12-09 | 中国科学院、水利部成都山地灾害与环境研究所 | Debris flow disaster identification and frequency calculation method based on remote sensing image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111832430B (en) | 2024-01-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111832430B (en) | Mountain torrent disaster hyperspectral remote sensing image identification method and identification system thereof | |
| Kääb et al. | The new remote-sensing-derived Swiss glacier inventory: II. First results | |
| Adams et al. | Multitemporal accuracy and precision assessment of unmanned aerial system photogrammetry for slope-scale snow depth maps in Alpine terrain | |
| Polcyn | Monsoon flood boundary delineation and damage assessment using space borne imaging radar and Landsat data | |
| Bühler et al. | Where are the avalanches? Rapid SPOT6 satellite data acquisition to map an extreme avalanche period over the Swiss Alps | |
| Bühler et al. | Automated detection and mapping of avalanche deposits using airborne optical remote sensing data | |
| de Colstoun et al. | Improving global scale land cover classifications with multi-directional POLDER data and a decision tree classifier | |
| Deysher | Evaluation of remote sensing techniques for monitoring giant kelp populations | |
| CN111781146A (en) | Wave parameter inversion method using high-resolution satellite optical image | |
| Nuthammachot et al. | Fusion of Sentinel-1A and Landsat-8 images for improving land use/land cover classification in Songkla Province, Thailand. | |
| Lu et al. | Integration of optical, SAR and DEM data for automated detection of debris-covered glaciers over the western Nyainqentanglha using a random forest classifier | |
| Mora et al. | Evaluation of single-band snow-patch mapping using high-resolution microwave remote sensing: An application in the maritime Antarctic | |
| US20230412777A1 (en) | Data analysis apparatus, method, and program | |
| CN113191292A (en) | Method for rapidly extracting bursting flood submerging range | |
| Liu et al. | Development of building height data in Peru from high-resolution SAR imagery | |
| Brigante et al. | USE OF MULTISPECTRAL SENSORS WITH HIGH SPATIAL RESOLUTION FOR TERRITORIAL AND ENVIRONMENTAL ANALYSIS. | |
| Falcone et al. | Mapping impervious surface type and sub‐pixel abundance using hyperion hyperspectral imagery | |
| Villa | Imperviousness indexes performance evaluation for mapping urban areas using remote sensing data | |
| Jensen et al. | Remote sensing of impervious surfaces and building infrastructure | |
| Bühler et al. | Spatially continuous mapping of snow depth in high alpine catchments using digital photogrammetry | |
| Mahboubi et al. | Detection of Wet Riparian Areas using Very High Resolution Multispectral UAS Imagery Based on a Feature-based Machine Learning Algorithm | |
| Asad et al. | Use of remote sensing for urban impervious surfaces: a case study of Lahore | |
| TWI597405B (en) | System and method for monitoring slope with tree displacement | |
| NS et al. | Greenness visualization in Al-Ain using landsat imagery | |
| King et al. | Evaluation of MK-4 multispectral satellite photography in land cover classification of eastern Ontario |
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 |