CN117423010A - River and lake demarcation recognition monitoring method based on remote sensing data - Google Patents
River and lake demarcation recognition monitoring method based on remote sensing data Download PDFInfo
- Publication number
- CN117423010A CN117423010A CN202311345714.1A CN202311345714A CN117423010A CN 117423010 A CN117423010 A CN 117423010A CN 202311345714 A CN202311345714 A CN 202311345714A CN 117423010 A CN117423010 A CN 117423010A
- Authority
- CN
- China
- Prior art keywords
- lake
- boundary
- morphological
- river
- image
- 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 64
- 238000012544 monitoring process Methods 0.000 title claims abstract description 23
- 230000000877 morphologic effect Effects 0.000 claims abstract description 102
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 62
- 238000012937 correction Methods 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 230000009466 transformation Effects 0.000 claims abstract description 8
- 238000001514 detection method Methods 0.000 claims abstract description 7
- 230000008859 change Effects 0.000 claims description 54
- 238000005516 engineering process Methods 0.000 claims description 20
- 239000011159 matrix material Substances 0.000 claims description 18
- 230000004660 morphological change Effects 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 16
- 238000000605 extraction Methods 0.000 claims description 11
- 238000003709 image segmentation Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 238000003708 edge detection Methods 0.000 claims description 9
- 230000005855 radiation Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 5
- 238000005452 bending Methods 0.000 claims description 4
- 238000006073 displacement reaction Methods 0.000 claims description 4
- 230000004927 fusion Effects 0.000 claims description 4
- 238000003384 imaging method Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 230000001681 protective effect Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000004445 quantitative analysis Methods 0.000 description 2
- 238000012300 Sequence Analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
- G06V10/806—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/182—Network patterns, e.g. roads or rivers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Remote Sensing (AREA)
- Astronomy & Astrophysics (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a river and lake demarcation recognition monitoring method based on remote sensing data, which particularly relates to the field of river and lake demarcation, and comprises the following steps: s1, preprocessing a remote sensing image: preprocessing the acquired remote sensing image, including denoising, correction and projective transformation, ensures the accuracy and consistency of the data. According to the method, morphological characteristics of different time points are aligned by using a dynamic time regulation method, time variation of a river and lake boundary is accurately captured, in a boundary variation detection stage, a region where boundary variation is likely to occur is identified by combining characteristic variation amplitude information, then the aligned morphological characteristic sequences are fused with an original remote sensing image, a water body is separated from a land region, and an accurate river and lake boundary line is generated.
Description
Technical Field
The invention relates to the technical field of river and lake demarcation, in particular to a river and lake demarcation identification and monitoring method based on remote sensing data.
Background
The river and lake play an important role in a natural geographic system, have profound effects on ecological balance, water resource management and social and economic development, and have important significance on ecological protection, water resource management and disaster prevention in the fields of natural resource management and environmental monitoring through accurate demarcation and change monitoring of the river and lake;
the Chinese patent discloses a river and lake demarcation measuring device, and the patent application number is 202121955020, and the disclosure is: the unmanned aerial vehicle comprises an unmanned aerial vehicle body and a plurality of wings which are distributed on the periphery of the unmanned aerial vehicle body at equal intervals in an annular mode, wherein the top of each wing is provided with a fan blade, the top of each wing is provided with a protective cover, each fan blade is arranged inside the corresponding protective cover, the top of each protective cover is inserted with a protective ring, and the inside of each protective ring is fixedly connected with a protective grating plate; the bottom of the unmanned aerial vehicle body is rotationally connected with a rotating frame, a mapping camera is arranged in the rotating frame, and an arc-shaped glass baffle is fixedly connected with the bottom of the rotating frame;
above-mentioned this river lake demarcation measuring device adopts unmanned aerial vehicle to take photo by plane and draws peripheral topography, however unmanned aerial vehicle monitoring accuracy is limited, is difficult to realize the river lake boundary of high accuracy and draws, and secondly, unmanned aerial vehicle is taken photo by plane and is influenced by factors such as weather, environment, leads to data collection's instability, influences the uniformity of drawing, has restricted the accuracy of river lake management and environmental monitoring.
Therefore, we propose a river and lake demarcation recognition monitoring method based on remote sensing data to solve the above problems.
Disclosure of Invention
In order to overcome the above-mentioned drawbacks of the prior art, an embodiment of the present invention provides a method for identifying and monitoring a boundary of a river and a lake based on remote sensing data, so as to solve the problems set forth in the background art.
In order to achieve the above purpose, the present invention provides the following technical solutions: a river and lake demarcation identification monitoring method based on remote sensing data comprises the following steps:
s1, preprocessing a remote sensing image: preprocessing the acquired remote sensing image, including denoising, correction and projective transformation, so as to ensure the accuracy and consistency of the data;
s2, morphological feature extraction: extracting morphological characteristics of rivers and lakes, including width, length and shape of water bodies, from the remote sensing images by utilizing an image processing technology;
s3, morphological characteristic evolution analysis: combining the morphological characteristics with remote sensing data at different time points to form a time sequence, analyzing the morphological characteristics of the time sequence, and finding out a region with larger morphological change;
s4, preparing dynamic time warping: selecting a dynamic time regularization method, and preparing time sequences required by the regularization, including morphological characteristics of different time points;
s5, dynamic time warping: using a selected method, aligning the morphological feature sequences at different time points to capture minute time shifts;
s6, detecting boundary change: in the aligned morphological feature sequences, comparing areas with larger feature variation amplitude, and identifying boundary variation;
s7, fusing the characteristics and time: fusing the regular morphological feature sequence with the original remote sensing image to prepare comprehensive information for subsequent boundary division;
s8, accurate boundary division: based on the result of the steps, accurately dividing the boundary of the river and the lake by using an image processing method, and ensuring that the region with the changed boundary is identified;
s9, analyzing results: and analyzing the obtained river and lake boundary dividing result, comparing the obtained river and lake boundary dividing result with actual geographic information, and evaluating the accuracy of the method.
In a preferred embodiment, in the step S1, random noise in the image is eliminated by applying a filter and image enhancement, which helps to improve the definition of details of the image, reduce the influence on noise in subsequent processing, and secondly, correct geometric and radiation correction errors existing in the image to maintain spatial consistency of the image, achieve accurate positioning of the image by photogrammetry techniques, convert the image from its original imaging coordinate system to a specific geographic coordinate system by projective transformation, so that the image corresponds to the actual geographic space for analysis and comparison in the geographic information system, and ensure consistency of pixels of the image with geographic positions by using parameters of the geographic coordinate system and digital elevation model data.
In a preferred embodiment, in the step S2, the remote sensing image is preprocessed to remove noise and artifacts, so as to ensure that the extracted features are accurate and reliable, then, an edge between the water body and the land is identified by adopting an edge detection algorithm Canny for the boundary of the water body, then, the water body is separated from the background by adopting an image segmentation technology to form a binary image, then, a connected region analysis is utilized to find out the connected region of the water body, the morphological properties of the area, the perimeter and the mass center of the water body are further calculated, the width, the length, the aspect ratio and the compactness of the water body are calculated based on the morphological properties, and the shape analysis of the water body is performed to obtain the appearance features of the water body by adopting a minimum circumscribed rectangle method, so as to quantify the irregularity and the bending degree information of the water body and distinguish different types of the water body and the regions with changed boundary.
In a preferred embodiment, in the step S3, remote sensing data of different time points are collected, the data are obtained from river and lake images acquired by a satellite platform, then, morphological characteristics of width, length and shape of the river and lake are extracted from the images of each time point through a morphological characteristic extraction method of the step S2, then, the morphological characteristics are formed into a time sequence according to time sequence, morphological characteristics of different time points are compared, morphological changes of the river and lake including expansion, shrinkage and shape change of a water body are observed, when the morphological characteristics are analyzed, amplitude and trend of the morphological changes are evaluated in a quantitative and qualitative mode through a statistical method and a graph drawing mode, and areas with larger morphological changes, namely areas with boundary changes of the river and the lake are found through comparing the morphological characteristics.
In a preferred embodiment, in the step S4, a suitable dynamic time warping method DTW is selected, required time series data including morphological features at different time points are prepared, the morphological features obtained from previous morphological feature extraction and morphological feature evolution analysis should be formed into a time series in time sequence, the morphological features at each time point are expressed as a vector, and the vector contains water width, length and shape information, the preparation of the time series data considers the quality and consistency of the data, so that the features at different time points can be correctly corresponded to perform comparison in a subsequent DTW method, in addition, the time series data are normalized, the influence possibly caused by different feature dimensions is eliminated, and the accuracy of the comparison is ensured.
In a preferred embodiment, in the step S5, when performing dynamic time warping, the morphological feature sequences of different time points are first placed in a two-dimensional matrix, where a row represents a feature of one time point and a feature of another time point is represented, the matrix is called a distance matrix, and is used to store a similarity distance between two time sequences, initially, each element of the matrix is initialized to a larger value, then, the elements in the distance matrix are gradually updated to the distance between the features of the corresponding time points, and when nonlinear alignment of the time sequences is considered, small time displacement and deformation are captured, and an optimal path is formed from the upper left corner to the lower right corner of the distance matrix, that is, from the first time point to the last time point, representing an alignment relationship of the morphological feature sequences, so as to provide a basis for subsequent boundary change detection and accurate demarcation, and can capture the time change of the river and lake boundary more accurately.
In a preferred embodiment, in the step S6, an aligned morphological feature sequence is obtained from the result of dynamic time warping, the sequence reflects the variation trend of the river and the lake at different time points, wherein the feature of each time point represents the morphological state of the river and the lake, then, the variation situation of the river and the lake morphology is measured through the feature variation amplitude of the adjacent time points, the region with larger difference means that the morphology variation is larger, the boundary variation exists, the threshold value is set in advance for screening out the region with larger feature variation amplitude, and the region with larger feature variation amplitude is further analyzed and verified at the place where the region exceeding the threshold value is considered to be subjected to boundary variation.
In a preferred embodiment, in the step S7, the morphological feature sequence after the dynamic time warping corresponds to the original remote sensing image, the feature of each time point is ensured to be matched with the corresponding area of the original image through the time mark, then the matched feature sequence is fused with the original remote sensing image, the fusion mode is the area-level fusion, the feature sequence information is associated with different geographical areas in the image, the fused image has the visual information of the remote sensing image and the information of the morphological feature sequence after the time warping, and the fused image realizes the accurate boundary division through the image segmentation.
In a preferred embodiment, in the step S8, the fused image data is first utilized, then the segmentation method is adopted to separate the water body from the land area through the image processing technology, the preliminary boundary information is obtained, then the preliminary boundary line is further optimized and refined through the edge detection technology, the boundary change area is identified, then the feature change amplitude information obtained in the previous step is utilized to combine with the image data, the area with larger feature change amplitude is screened through the preset threshold value, the position of the boundary change is determined, and then the accurate river and lake boundary line is generated according to the processed image and the feature information, and the boundary change area and the boundary condition of the water body and the land are accurately captured by the boundary line.
In a preferred embodiment, in the step S9, the river and lake boundary division result is compared with the actual geographic information, and the division result is superimposed on the actual map by using the geographic information system tool, so that the consistency of the two is intuitively compared.
The invention has the technical effects and advantages that:
the method comprises the steps of eliminating random noise through filtering and image enhancement, correcting geometric and radiation correction errors, ensuring image definition and space consistency, realizing accurate image positioning by utilizing a photogrammetry technology, extracting morphological characteristics of rivers and lakes by adopting edge detection and image segmentation, aligning the morphological characteristics of different time points by utilizing a dynamic time alignment method, accurately capturing time variation of the boundaries of the rivers and the lakes, identifying regions possibly suffering from boundary variation by combining characteristic variation amplitude information in a boundary variation detection stage, and then fusing an aligned morphological characteristic sequence with an original remote sensing image to separate a water body from a land region to generate accurate boundary lines of the rivers and the lakes.
Drawings
FIG. 1 is a step diagram of a method for identifying and monitoring river and lake demarcation based on remote sensing data.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1 of the specification, the method for identifying and monitoring river and lake demarcation based on remote sensing data according to an embodiment of the invention comprises the following steps:
s1, preprocessing a remote sensing image: preprocessing the acquired remote sensing image, including denoising, correction and projective transformation, so as to ensure the accuracy and consistency of the data;
the method is characterized in that random noise in an image is eliminated by applying a filter and image enhancement, the definition of image details is improved, the influence on noise in subsequent processing is reduced, geometric and radiation correction errors existing in the image are corrected to keep the spatial consistency of the image, accurate positioning of the image is realized by a photogrammetry technology, the image is converted from an original imaging coordinate system to a specific geographic coordinate system by projection transformation, so that the image corresponds to the actual geographic space, analysis and comparison are performed in the geographic information system, and consistency of image pixels and geographic positions is ensured by utilizing geographic coordinate system parameters and digital elevation model data; through a filter and an image enhancement technology, random noise is reduced, details of an image are enhanced, the image is easier to interpret and analyze, meanwhile, noise is eliminated to help reduce the influence of the noise on a result in a subsequent processing step, the subsequent analysis and interpretation are more accurate and reliable, geometric and radiation errors are corrected to help improve the spatial consistency of the image, the position of an object in the image in a geographic space is ensured to be more accurate, the accurate geographic positioning of the image is realized by utilizing a photogrammetry technology and projection transformation, the pixels in the image correspond to the actual geographic position, and the corresponding relation between the image and the actual geographic space is ensured;
s2, morphological feature extraction: extracting morphological characteristics of rivers and lakes, including width, length and shape of water bodies, from the remote sensing images by utilizing an image processing technology;
in the process of morphological feature extraction, firstly, preprocessing a remote sensing image, removing noise and artifacts, ensuring that the extracted features are accurate and reliable, then, adopting an edge detection algorithm Canny to identify the edge between the water body and the land aiming at the boundary of the water body, then, separating the water body from the background by applying an image segmentation technology to form a binary image, then, utilizing a communication area analysis to find out the communication area of the water body, further calculating the morphological attributes of the area, the perimeter and the mass center of the water body, calculating the width, the length, the aspect ratio and the compactness of the water body based on the morphological attributes, and for the shape analysis of the water body, obtaining the appearance feature of the water body by applying a minimum circumscribed rectangle method, quantifying the irregularity and the bending degree information of the water body, and distinguishing the areas of different types of water bodies and boundary changes; the noise and the artifact are removed through pretreatment, the extracted morphological characteristics are ensured to be more accurate and reliable, an edge detection algorithm Canny is adopted to identify the edge between the water body and the land, the distinction of different ground object types is facilitated, the peripheral outline of the water body is determined, the water body is separated from the background through an image segmentation technology to obtain a binary image of the water body, then the communication area is analyzed through a communication area, the area circumference and the mass center morphological attribute of the water body are found out, the area, the circumference and the mass center morphological attribute of the water body are calculated, the morphological attribute of the water body is calculated according to the analysis result of the communication area, the basic morphological characteristic of the water body is reflected, the more detailed quantitative analysis of the water body is facilitated, the appearance characteristic of the water body is acquired through the application of a minimum external rectangle method, the irregularity and the bending degree information of the water body are quantified, and the areas with different types of the water body and the boundary change are distinguished;
s3, morphological characteristic evolution analysis: combining the morphological characteristics with remote sensing data at different time points to form a time sequence, analyzing the morphological characteristics of the time sequence, and finding out a region with larger morphological change;
firstly collecting remote sensing data of different time points, wherein the data are from river and lake images acquired by a satellite platform, then extracting the width, length and shape morphological characteristics of the river and the lake from the images of each time point by a morphological characteristic extraction method of S2, then forming the morphological characteristics into a time sequence according to time sequence, observing morphological changes of the river and the lake, including expansion, shrinkage and shape change of a water body by comparing the morphological characteristics of different time points, evaluating the amplitude and trend of the morphological changes in a quantitative and qualitative mode by adopting a statistical method and a graph drawing mode when analyzing the morphological characteristics, and finding out a region with larger morphological changes, namely a region with boundary change of the river and the lake by comparing the change conditions of the morphological characteristics; by utilizing morphological feature extraction and time sequence analysis, morphological changes of rivers and lakes are identified and quantified by comparing morphological features at different time points, and a boundary change area is found out by quantitative and qualitative analysis;
s4, preparing dynamic time warping: selecting a dynamic time regularization method, and preparing time sequences required by the regularization, including morphological characteristics of different time points;
selecting a proper dynamic time-warping method DTW, preparing needed time sequence data comprising morphological characteristics at different time points, forming a time sequence according to time sequence, wherein the morphological characteristics at each time point are expressed as a vector and comprise water width, length and shape information; by utilizing a Dynamic Time Warping (DTW) method, morphological characteristics of different time points are compared in a time sequence mode, so that morphological change trends of the river and the lake are compared, and an accurate time sequence basis is provided for further analysis of the morphological changes of the river and the lake;
s5, dynamic time warping: using a selected method, aligning the morphological feature sequences at different time points to capture minute time shifts;
when dynamic time warping is executed, firstly, morphological feature sequences of different time points are required to be put into a two-dimensional matrix, wherein rows represent features of one time point, the other time point is represented by the features of the other time point, the matrix is called a distance matrix and is used for storing similarity distances between the two time sequences, initially, each element of the matrix is initialized to a larger value, then, the elements in the distance matrix are gradually updated to be distances between the features of the corresponding time points, when nonlinear alignment of the time sequences is considered, tiny time displacement and deformation are captured, an optimal path is formed from the upper left corner to the lower right corner of the distance matrix, namely, from the first time point to the last time point, the alignment relation of the morphological feature sequences is represented, a foundation is provided for subsequent boundary change detection and accurate demarcation, and the time change of a river boundary can be captured more accurately; capturing tiny displacement and deformation of the morphological change of the river and the lake by a Dynamic Time Warping (DTW) method, and providing accurate relevance for subsequent boundary change detection and accurate demarcation, wherein the method is helpful for analyzing the evolution process of the river and the lake from a time sequence when comparing the change trend in the time sequence data;
s6, detecting boundary change: in the aligned morphological feature sequences, comparing areas with larger feature variation amplitude, and identifying boundary variation;
obtaining an aligned morphological feature sequence from a dynamic time-ordered result, wherein the sequence reflects the change trend of the river and the lake at different time points, the feature of each time point represents the morphological state of the river and the lake, then, the change condition of the river and the lake morphology is measured through the feature change amplitude of the adjacent time points, the region with larger difference means that the morphology change is larger, the boundary change exists, the threshold value is set in advance for screening out the region with larger feature change amplitude, and the region with larger feature change amplitude is further analyzed and verified at the place where the region exceeding the threshold value is considered to have boundary change; the aligned morphological feature sequences are obtained from the dynamic time warping result, then the areas with larger morphological changes are identified and screened through the measurement of the feature change amplitude, the places with boundary changes are rapidly positioned, and the boundary changes can be rapidly identified in a large range;
s7, fusing the characteristics and time: fusing the regular morphological feature sequence with the original remote sensing image to prepare comprehensive information for subsequent boundary division;
the method comprises the steps of corresponding a morphological feature sequence after dynamic time warping with an original remote sensing image, realizing that the feature of each time point is matched with a corresponding region of the original image through a time mark, then fusing the matched feature sequence with the original remote sensing image in a region-level fusion mode, associating the feature sequence information with different geographic regions in the image, enabling the fused image to have visual information of the remote sensing image and information of the morphological feature sequence after time warping, and realizing accurate boundary division through image segmentation; correlating and fusing the morphological feature sequence with the original remote sensing image, so that the fused image can simultaneously present the appearance information and morphological feature change information of the river and the lake, and the accurate division of the boundary of the river and the lake is realized through image segmentation, thereby providing the visualized and accurate information based on the time regularity for the boundary of the river and the lake;
s8, accurate boundary division: based on the result of the steps, accurately dividing the boundary of the river and the lake by using an image processing method, and ensuring that the region with the changed boundary is identified;
firstly, utilizing the fused image data, then adopting a segmentation method to separate a water body from a land area by an image processing technology, obtaining preliminary boundary information, then, further optimizing and refining the preliminary boundary line by an edge detection technology, identifying a boundary change area, combining the boundary change amplitude information obtained by the previous steps with the image data, screening the area with larger characteristic change amplitude by a preset threshold value, determining the position of boundary change, and then, generating an accurate river and lake boundary line according to the processed image and the characteristic information, wherein the boundary line accurately captures the boundary change area and the boundary condition of the water body and the land; gradually extracting and optimizing boundary information from the fused image data, and combining the characteristic variation amplitude information and threshold screening to generate an accurate river and lake boundary line;
s9, analyzing results: analyzing the obtained river and lake boundary dividing result, comparing the obtained river and lake boundary dividing result with actual geographic information, and evaluating the accuracy of the method;
comparing the river and lake boundary dividing result with actual geographic information, and using a geographic information system tool to superimpose the dividing result on an actual map to intuitively compare the consistency of the river and lake boundary dividing result and the actual geographic information; the river and lake boundary dividing result is visually compared with the actual geographic information, and the accuracy of the dividing result and the consistency with the actual situation can be more clearly evaluated through the superposition function of the geographic information system tool.
The working principle of the invention is as follows: the method comprises the steps of eliminating random noise through filtering and image enhancement, correcting geometric and radiation correction errors, guaranteeing image definition and space consistency, realizing accurate image positioning by utilizing a photogrammetry technology, extracting morphological characteristics of rivers and lakes by adopting an edge detection and image segmentation technology, aligning the morphological characteristics of different time points by utilizing a dynamic time alignment method through time sequence data, accurately capturing time variation of boundaries of the rivers and the lakes, identifying areas which are likely to generate boundary variation in a boundary variation detection stage by combining characteristic variation amplitude information, fusing the aligned morphological characteristic sequences with an original remote sensing image to prepare for accurate boundary division, finally separating water bodies from land areas by utilizing an image processing technology, generating accurate boundary lines of the rivers and the lakes, comparing division results with actual geographic information, and evaluating division accuracy by superposing results on an actual map by a geographic information system tool.
The last points to be described are: first, in the description of the present application, it should be noted that, unless otherwise specified and defined, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be mechanical or electrical, or may be a direct connection between two elements, and "upper," "lower," "left," "right," etc. are merely used to indicate relative positional relationships, which may be changed when the absolute position of the object being described is changed;
secondly: in the drawings of the disclosed embodiments, only the structures related to the embodiments of the present disclosure are referred to, and other structures can refer to the common design, so that the same embodiment and different embodiments of the present disclosure can be combined with each other under the condition of no conflict;
finally: the foregoing is only illustrative of the present invention and is not to be construed as limiting thereof, but rather, any modifications, equivalent arrangements, improvements, etc., which fall within the spirit and principles of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. A river and lake demarcation identification monitoring method based on remote sensing data is characterized by comprising the following steps:
s1, preprocessing a remote sensing image: preprocessing the acquired remote sensing image, including denoising, correction and projective transformation, so as to ensure the accuracy and consistency of the data;
s2, morphological feature extraction: extracting morphological characteristics of rivers and lakes, including width, length and shape of water bodies, from the remote sensing images by utilizing an image processing technology;
s3, morphological characteristic evolution analysis: combining the morphological characteristics with remote sensing data at different time points to form a time sequence, analyzing the morphological characteristics of the time sequence, and finding out a region with larger morphological change;
s4, preparing dynamic time warping: selecting a dynamic time regularization method, and preparing time sequences required by the regularization, including morphological characteristics of different time points;
s5, dynamic time warping: using a selected method, aligning the morphological feature sequences at different time points to capture minute time shifts;
s6, detecting boundary change: in the aligned morphological feature sequences, comparing areas with larger feature variation amplitude, and identifying boundary variation;
s7, fusing the characteristics and time: fusing the regular morphological feature sequence with the original remote sensing image to prepare comprehensive information for subsequent boundary division;
s8, accurate boundary division: based on the result of the steps, accurately dividing the boundary of the river and the lake by using an image processing method, and ensuring that the region with the changed boundary is identified;
s9, analyzing results: and analyzing the obtained river and lake boundary dividing result, comparing the obtained river and lake boundary dividing result with actual geographic information, and evaluating the accuracy of the method.
2. The method for identifying and monitoring river and lake demarcation based on remote sensing data according to claim 1, wherein the method comprises the following steps: in the step S1, random noise in the image is eliminated by applying a filter and image enhancement, and then geometric and radiation correction errors existing in the image are corrected to maintain spatial consistency of the image, accurate positioning of the image is realized by a photogrammetry technique, the image is converted from an original imaging coordinate system thereof to a specific geographic coordinate system by projection transformation, so that the image corresponds to an actual geographic space for analysis and comparison in a geographic information system, and consistency of pixels of the image and geographic positions is ensured by utilizing geographic coordinate system parameters and digital elevation model data.
3. The method for identifying and monitoring river and lake demarcation based on remote sensing data according to claim 1, wherein the method comprises the following steps: in the S2, the remote sensing image is preprocessed firstly in the process of morphological feature extraction, noise and artifacts are removed, the extracted features are ensured to be accurate and reliable, then, an edge between the water body and the land is identified by adopting an edge detection algorithm Canny aiming at the boundary of the water body, then, the water body and the background are separated by applying an image segmentation technology to form a binary image, then, a connected region is utilized to analyze, the connected region of the water body is found, the morphological attributes of the area, the perimeter and the mass center of the water body are further calculated, the width, the length, the aspect ratio and the compactness of the water body are calculated based on the morphological attributes, and for the shape analysis of the water body, the appearance features of the water body are obtained by applying a minimum circumscribed rectangle method, the irregularity and the bending degree information of the water body are quantized, and different types of the water body and the regions with boundary changes are distinguished.
4. The method for identifying and monitoring river and lake demarcation based on remote sensing data according to claim 1, wherein the method comprises the following steps: in the step S3, remote sensing data of different time points are collected firstly, the data are from river and lake images acquired by a satellite platform, then, the width, the length and the shape morphological characteristics of the river and the lake are extracted from the images of each time point by the morphological characteristic extraction method of the step S2, then, the morphological characteristics are formed into a time sequence according to time sequence, morphological characteristics of different time points are compared, morphological change conditions of the river and the lake, including expansion, shrinkage and shape change of a water body are observed, when the morphological characteristics are analyzed, the amplitude and trend of the morphological change are evaluated in a quantitative and qualitative mode by adopting a statistical method and a graph drawing mode, and a region with larger morphological change, namely a region with boundary change of the river and the lake is found out by comparing the change conditions of the morphological characteristics.
5. The method for identifying and monitoring river and lake demarcation based on remote sensing data according to claim 1, wherein the method comprises the following steps: in the step S4, a suitable dynamic time-warping method DTW is selected, and required time-series data including morphological features at different time points are prepared, and the obtained morphological features from the previous morphological feature extraction and morphological feature evolution analysis should be formed into a time series according to time sequence, and the morphological features at each time point are represented as a vector, wherein the vector contains the width, length and shape information of the water body.
6. The method for identifying and monitoring river and lake demarcation based on remote sensing data according to claim 1, wherein the method comprises the following steps: in the step S5, when performing dynamic time warping, morphological feature sequences of different time points are first placed in a two-dimensional matrix, wherein a row represents features of one time point, a column represents features of another time point, the matrix is called a distance matrix, and is used for storing similarity distances between two time sequences, each element of the matrix is initialized to a larger value initially, then elements in the distance matrix are gradually updated to be distances between features of corresponding time points, when nonlinear alignment of the time sequences is considered, tiny time displacement and deformation are captured, an optimal path is formed from the upper left corner to the lower right corner of the distance matrix, namely, from the first time point to the last time point, and alignment relation of the morphological feature sequences is represented, so that a basis is provided for subsequent boundary change detection and accurate demarcation.
7. The method for identifying and monitoring river and lake demarcation based on remote sensing data according to claim 1, wherein the method comprises the following steps: in the step S6, an aligned morphological characteristic sequence is obtained from a dynamic time-ordered result, the sequence reflects the change trend of the river and the lake at different time points, wherein the characteristic of each time point represents the morphological state of the river and the lake, then the change condition of the river and the lake morphology is measured through the characteristic change amplitude of adjacent time points, the region with larger difference means that the morphology change is larger, the boundary change exists, a threshold value is set in advance for screening out the region with larger characteristic change amplitude, and the region with larger characteristic change amplitude is further analyzed and verified in the place where the region exceeding the threshold value is considered to be subjected to boundary change.
8. The method for identifying and monitoring river and lake demarcation based on remote sensing data according to claim 1, wherein the method comprises the following steps: in the step S7, the morphological feature sequence after the dynamic time warping corresponds to the original remote sensing image, the feature of each time point is matched with the corresponding area of the original image through the time mark, then the matched feature sequence is fused with the original remote sensing image in an area-level fusion mode, the feature sequence information is associated with different geographic areas in the image, the fused image has visual information of the remote sensing image and information of the morphological feature sequence after the time warping, and the fused image realizes accurate boundary division through image segmentation.
9. The method for identifying and monitoring river and lake demarcation based on remote sensing data according to claim 1, wherein the method comprises the following steps: in the step S8, the fused image data is first utilized, then the segmentation method is adopted to separate the water body from the land area through the image processing technology, the preliminary boundary information is obtained, then the preliminary boundary line is further optimized and refined through the edge detection technology, the boundary change area is identified, then the characteristic change amplitude information obtained through the steps is utilized to combine the boundary change area with the image data, the area with larger characteristic change amplitude is screened through the preset threshold value, the position of the boundary change is determined, and then the accurate river and lake boundary line is generated according to the processed image and the characteristic information, and the boundary line accurately captures the boundary change area and the boundary condition of the water body and the land.
10. The method for identifying and monitoring river and lake demarcation based on remote sensing data according to claim 1, wherein the method comprises the following steps: in the S9, comparing the river and lake boundary dividing result with the actual geographic information, and using a geographic information system tool to superimpose the dividing result on the actual map to intuitively compare the consistency of the river and lake boundary dividing result and the actual geographic information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311345714.1A CN117423010B (en) | 2023-10-18 | 2023-10-18 | River and lake demarcation recognition monitoring method based on remote sensing data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311345714.1A CN117423010B (en) | 2023-10-18 | 2023-10-18 | River and lake demarcation recognition monitoring method based on remote sensing data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117423010A true CN117423010A (en) | 2024-01-19 |
| CN117423010B CN117423010B (en) | 2024-05-03 |
Family
ID=89525707
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311345714.1A Active CN117423010B (en) | 2023-10-18 | 2023-10-18 | River and lake demarcation recognition monitoring method based on remote sensing data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117423010B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102216957A (en) * | 2008-10-09 | 2011-10-12 | 埃西斯创新有限公司 | Visual tracking of objects in images, and segmentation of images |
| CN102542551A (en) * | 2010-12-13 | 2012-07-04 | 北京师范大学 | Automatic change detection technology for floating ice at edges of polar ice sheets |
| CN112100301A (en) * | 2020-08-30 | 2020-12-18 | 山东锋士信息技术有限公司 | Method for realizing dynamic monitoring of water area shoreline by using high-resolution remote sensing technology |
| CN114241336A (en) * | 2021-12-30 | 2022-03-25 | 河南祥宇工程勘察设计有限公司 | River and lake water area right-determining demarcation method based on dynamic low-resolution remote sensing image |
| CN115601549A (en) * | 2022-12-07 | 2023-01-13 | 山东锋士信息技术有限公司（Cn） | River and lake remote sensing image segmentation method based on deformable convolution and self-attention model |
-
2023
- 2023-10-18 CN CN202311345714.1A patent/CN117423010B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102216957A (en) * | 2008-10-09 | 2011-10-12 | 埃西斯创新有限公司 | Visual tracking of objects in images, and segmentation of images |
| CN102542551A (en) * | 2010-12-13 | 2012-07-04 | 北京师范大学 | Automatic change detection technology for floating ice at edges of polar ice sheets |
| CN112100301A (en) * | 2020-08-30 | 2020-12-18 | 山东锋士信息技术有限公司 | Method for realizing dynamic monitoring of water area shoreline by using high-resolution remote sensing technology |
| CN114241336A (en) * | 2021-12-30 | 2022-03-25 | 河南祥宇工程勘察设计有限公司 | River and lake water area right-determining demarcation method based on dynamic low-resolution remote sensing image |
| CN115601549A (en) * | 2022-12-07 | 2023-01-13 | 山东锋士信息技术有限公司（Cn） | River and lake remote sensing image segmentation method based on deformable convolution and self-attention model |
Non-Patent Citations (2)
| Title |
|---|
| JIASHUO CHEN: "study of non-point pollution in the ashe river basin based on swat model with different land use", 《WATER》, 7 July 2022 (2022-07-07), pages 1 - 24 * |
| 刘月阳 等: "基于地学图谱的县级尺度土地利用时空变化特征研究-以酉阳土家族苗族自治县为例", 《中国农学通报》, vol. 37, no. 14, 12 May 2021 (2021-05-12), pages 123 - 135 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117423010B (en) | 2024-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tian et al. | Building change detection based on satellite stereo imagery and digital surface models | |
| US11244197B2 (en) | Fast and robust multimodal remote sensing image matching method and system | |
| Huang et al. | Individual tree crown detection and delineation from very-high-resolution UAV images based on bias field and marker-controlled watershed segmentation algorithms | |
| Cheng et al. | 3D building model reconstruction from multi-view aerial imagery and lidar data | |
| Lu et al. | Object-oriented change detection for landslide rapid mapping | |
| EP3382644A1 (en) | Method for 3d modelling based on structure from motion processing of sparse 2d images | |
| CN110120046B (en) | Potential landslide identification method integrating DEM (digital elevation model), optical remote sensing and deformation information | |
| CN114549835B (en) | Pointer instrument correction identification method and device based on deep learning | |
| CN112818988A (en) | Automatic reading identification method and system for pointer instrument | |
| CN111797744B (en) | Multimode remote sensing image matching method based on co-occurrence filtering algorithm | |
| Moriondo et al. | Use of digital images to disclose canopy architecture in olive tree | |
| Li et al. | Post-earthquake assessment of building damage degree using LiDAR data and imagery | |
| Yuan et al. | Combining maps and street level images for building height and facade estimation | |
| CN111597930A (en) | Coastline extraction method based on remote sensing cloud platform | |
| CN116844147A (en) | Pointer instrument identification and abnormal alarm method based on deep learning | |
| Tian et al. | 3D building change detection from high resolution spaceborne stereo imagery | |
| CN104966283A (en) | Imaging layered registering method | |
| CN113408519A (en) | Method and system for reading pointer instrument based on template rotation matching | |
| Kim et al. | Tree and building detection in dense urban environments using automated processing of IKONOS image and LiDAR data | |
| Peng et al. | Building change detection by combining lidar data and ortho image | |
| Kim et al. | Automatic pseudo-invariant feature extraction for the relative radiometric normalization of hyperion hyperspectral images | |
| Michelin et al. | Quality evaluation of 3D city building models with automatic error diagnosis | |
| CN117423010B (en) | River and lake demarcation recognition monitoring method based on remote sensing data | |
| Sidike et al. | Automatic building change detection through adaptive local textural features and sequential background removal | |
| Tian et al. | Multitemporal 3D change detection in urban areas using stereo information from different sensors |
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 |