CN116935236A - Irrigation pit water storage capacity monitoring method and device, electronic equipment and storage medium - Google Patents

Irrigation pit water storage capacity monitoring method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN116935236A
CN116935236A CN202310684818.9A CN202310684818A CN116935236A CN 116935236 A CN116935236 A CN 116935236A CN 202310684818 A CN202310684818 A CN 202310684818A CN 116935236 A CN116935236 A CN 116935236A
Authority
CN
China
Prior art keywords
irrigation
pit
water
remote sensing
data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202310684818.9A
Other languages
Chinese (zh)
Inventor
王轶璇
闫娜娜
吴炳方
朱伟伟
马宗瀚
朱亮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Aerospace Information Research Institute of CAS
Original Assignee
Aerospace Information Research Institute of CAS
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Aerospace Information Research Institute of CAS filed Critical Aerospace Information Research Institute of CAS
Priority to CN202310684818.9A priority Critical patent/CN116935236A/en
Publication of CN116935236A publication Critical patent/CN116935236A/en
Pending legal-status Critical Current

Links

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
    • G01—MEASURING; TESTING
    • G01F—MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
    • G01F23/00—Indicating or measuring liquid level or level of fluent solid material, e.g. indicating in terms of volume or indicating by means of an alarm
    • G01F23/22—Indicating or measuring liquid level or level of fluent solid material, e.g. indicating in terms of volume or indicating by means of an alarm by measuring physical variables, other than linear dimensions, pressure or weight, dependent on the level to be measured, e.g. by difference of heat transfer of steam or water
    • G01F23/28—Indicating or measuring liquid level or level of fluent solid material, e.g. indicating in terms of volume or indicating by means of an alarm by measuring physical variables, other than linear dimensions, pressure or weight, dependent on the level to be measured, e.g. by difference of heat transfer of steam or water by measuring the variations of parameters of electromagnetic or acoustic waves applied directly to the liquid or fluent solid material
    • G01F23/284—Electromagnetic waves
    • G01F23/292—Light, e.g. infrared or ultraviolet
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • 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
    • G06V10/40—Extraction of image or video features
    • G06V10/54—Extraction of image or video features relating to texture
    • 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
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • 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
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10032—Satellite or aerial image; Remote sensing

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Business, Economics & Management (AREA)
  • Electromagnetism (AREA)
  • Data Mining & Analysis (AREA)
  • Economics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Databases & Information Systems (AREA)
  • Molecular Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Medical Informatics (AREA)
  • Remote Sensing (AREA)
  • Public Health (AREA)
  • Tourism & Hospitality (AREA)
  • Water Supply & Treatment (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Geometry (AREA)
  • General Business, Economics & Management (AREA)
  • Astronomy & Astrophysics (AREA)
  • Thermal Sciences (AREA)
  • Fluid Mechanics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Radar, Positioning & Navigation (AREA)

Abstract

The invention provides a method, a device, electronic equipment and a storage medium for monitoring the water storage capacity of an irrigation pit, which belong to the technical field of image processing and comprise the following steps: determining the water surface area of each irrigation pit in the target area based on the initial remote sensing data of the target area, and acquiring the water level information of each irrigation pit; and generating the water storage capacity of each irrigation pit according to the type, the water surface area and the water level information of each irrigation pit. According to the method, the device, the electronic equipment and the storage medium for monitoring the water storage capacity of the irrigation pit, provided by the invention, the object-oriented multi-scale segmentation is utilized to combine the characteristics of the irrigation pit to identify the pit and calculate the water surface area, and the water depth of the irrigation pit is collected, so that the accurate water storage capacity of the irrigation pit is calculated rapidly and timely, the monitoring efficiency is improved, the obtained water storage capacity data is more visual, basic data is provided for water filling area water capacity accounting and water distribution scheme optimization, and the economic benefit and the water resource utilization efficiency are improved.

Description

Irrigation pit water storage capacity monitoring method and device, electronic equipment and storage medium
Technical Field
The invention relates to the technical field of image processing, in particular to a method and a device for monitoring the water storage capacity of an irrigation pit, electronic equipment and a storage medium.
Background
The water storage capacity monitoring of the irrigation pit is an important link in the evaluation of the drought resistance of the land, and the water storage capacity change is also an important reference index for water resource management.
The satellite remote sensing information has the characteristics of periodicity, macroscopicity, behavior and the like, and the existing irrigation pit water storage monitoring method generally utilizes satellite remote sensing images to observe the water surface area and water storage of the pits to establish a unified statistical relationship, and then estimates the water storage of each pit.
The method has the defects of non-intuitiveness, low precision and inadaptation of statistical relationship to the monitoring of the pit and the pond to the water body of the partial irrigation pit and pond.
Disclosure of Invention
The method, the device, the electronic equipment and the storage medium for monitoring the water storage capacity of the irrigation pit provided by the invention are used for solving the defects that the monitoring of the pit is not intuitive, the accuracy is low and the monitoring is not suitable for part of water bodies of the irrigation pit in the prior art, realizing rapid and timely calculation of the accurate water storage capacity of the irrigation pit, improving the monitoring efficiency, simultaneously, obtaining more intuitive water storage capacity data, providing basic data for accounting the irrigation water capacity of a irrigation area and optimizing a water distribution scheme, and promoting the improvement of economic benefit and water resource utilization efficiency.
The invention provides a method for monitoring the water storage capacity of an irrigation pit, which comprises the following steps:
determining the water surface area of each irrigation pit in the target area based on initial remote sensing data of the target area, and acquiring water level information of each irrigation pit; the water surface area is determined based on multi-scale segmentation of the water surface of the irrigation pit of the high-resolution remote sensing data in the initial remote sensing data;
and generating the water storage capacity of each irrigation pit according to the type, the water surface area and the water level information of each irrigation pit, wherein the type of each irrigation pit comprises regular type and irregular type.
According to the method for monitoring the water storage capacity of the irrigation pit, provided by the invention, the initial remote sensing data comprise a plurality of time sequence low-resolution remote sensing data and single-time phase high-resolution remote sensing data; the resolution of the time sequence low resolution remote sensing data is lower than that of the high resolution remote sensing data;
the determining the water surface area of each irrigation pit in the target area based on the initial remote sensing data of the target area comprises the following steps:
extracting irrigation pit areas in the target area from each time sequence low-resolution remote sensing data, and generating first irrigation pit data sets of all the irrigation pits in the target area;
Acquiring the central point position of each irrigation pit in the target area by using the first irrigation pit data set;
migrating the central point position of each irrigation pit to the high-resolution remote sensing data;
in the high-resolution remote sensing data, taking the central point position of each irrigation pit as the center, and generating a regional mask according to a defined radius to acquire irrigation pit range remote sensing data; the defined radius is determined based on a maximum defined water surface area for each irrigation pit in the first set of irrigation pit data;
and based on the segmentation scale threshold value of the irrigation pits, carrying out pixel combination on the irrigation pits in the remote sensing data of the irrigation pit range, generating second irrigation pit data sets of all the irrigation pits, and acquiring the water surface area of the irrigation pits.
According to the method for monitoring the water storage capacity of the irrigation pits, provided by the invention, the water level information of each irrigation pit is obtained, and the method comprises the following steps:
acquiring water level information of an irrigation pit in the target area by using a laser radar; or alternatively, the first and second heat exchangers may be,
acquiring an image to be identified of an irrigation pit in the target area;
and inputting the image to be identified into a water level identification model, and acquiring the water level information output by the water level identification model, wherein the water level identification model is obtained after training based on a sample pit image with a water level information label.
According to the method for monitoring the water storage capacity of the irrigation pits, provided by the invention, in each time sequence low-resolution remote sensing data, the irrigation pit area in the target area is extracted, and a first irrigation pit data set of all the irrigation pits in the target area is generated, wherein the method comprises the following steps:
masking any time-sequence low-resolution remote sensing data by utilizing the maximum NDVI (non-uniform density differential) of the vegetation growth period acquired by the large water body information and the time-sequence low-resolution remote sensing data of the target area to generate mask remote sensing data of the any time-sequence low-resolution remote sensing data so as to acquire mask remote sensing data of each time-sequence low-resolution remote sensing data; the mask remote sensing data comprises small-sized water body remote sensing data and soil remote sensing data;
binary classification is carried out on each scene mask remote sensing data by utilizing a water index, and a small water body data set in the target area in each scene mask remote sensing data is obtained;
and determining the first irrigation pit data set according to the small water body data set.
According to the method for monitoring the water storage capacity of the irrigation pit, the first irrigation pit data set is determined according to the small water body data set, and the method comprises the following steps:
Screening each water body in the small water body data set of each scene mask remote sensing data according to pit size limiting conditions to obtain a screened water body data set of each time phase; the pit size limiting condition is determined based on the maximum defined water surface area of the pit water body;
carrying out space superposition analysis on the screened water body data sets of all time phases, and calculating the average water body frequency of pixels in the target area to determine the seasonal variation rule of the water quantity of each small water body;
determining an irregular irrigation pit water body area according to the seasonal variation rule of the water quantity; the pit type of each irrigation pit in the irregular irrigation pit water body area is irregular;
screening each water body in the screened water body data set according to the outline characteristics of the irrigation pits and the irregular irrigation pits water body areas to obtain the regular irrigation pits water body areas; the irrigation pit type of each irrigation pit in the regular irrigation pit water body area is regular;
and combining the irregular type irrigation pit water body area and the regular type irrigation pit water body area as the first irrigation pit data set.
According to the method for monitoring the water storage capacity of the irrigation pits, the water storage capacity of each irrigation pit is generated according to pit type, water surface area and water level information of each irrigation pit, and the method comprises the following steps:
under the condition that the type of any irrigation pit is regular, determining the water storage capacity of any irrigation pit according to the water level information and the water surface area of any irrigation pit;
and under the condition that the type of any irrigation pit is irregular, determining the water storage capacity of any irrigation pit based on the construction data of any irrigation pit according to the water level information or the water surface area of any irrigation pit.
The invention also provides a device for monitoring the water storage capacity of the irrigation pit, which comprises:
the determining module is used for determining the water surface area of each irrigation pit in the target area based on the initial remote sensing data of the target area and acquiring the water level information of each irrigation pit; the water surface area is determined based on multi-scale segmentation of the water surface of the irrigation pit of the high-resolution remote sensing data in the initial remote sensing data;
the generation module is used for generating the water storage capacity of each irrigation pit according to the irrigation pit type, the water surface area and the water level information of each irrigation pit, and the irrigation pit type comprises regular type and irregular type.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and operable on the processor, wherein the processor implements the method for monitoring the water storage capacity of an irrigation pit as described above when executing the program.
The invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which when executed by a processor implements a method of monitoring the water storage capacity of an irrigation pit as described in any of the above.
The invention also provides a computer program product comprising a computer program which when executed by a processor implements a method of monitoring the water storage capacity of an irrigation pit as described in any of the above.
According to the method, the device, the electronic equipment and the storage medium for monitoring the water storage capacity of the irrigation pit, provided by the invention, the recognition and the water surface area calculation of the pit are carried out by combining the object-oriented multi-scale segmentation with the characteristics of the irrigation pit, and the water depth of the pit is collected, so that the accurate water storage capacity of the pit is calculated rapidly and timely, the monitoring efficiency is improved, the obtained water storage capacity data are more visual, the method and the device are suitable for all water bodies of the irrigation pit, basic data are provided for water volume accounting in a water filling area and optimizing a water distribution scheme, and the economic benefit and the water resource utilization efficiency are improved.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for monitoring the water storage capacity of an irrigation pit;
FIG. 2 is a schematic flow chart of model training provided by the present invention;
FIG. 3 is a second flow chart of the method for monitoring the water storage capacity of an irrigation pit provided by the invention;
FIG. 4 is a third flow chart of the method for monitoring the water storage capacity of an irrigation pit provided by the invention;
FIG. 5 is a flow chart of a method for monitoring the water storage capacity of an irrigation pit provided by the invention;
FIG. 6 is a schematic diagram of the structure of the irrigation pit water storage monitoring device provided by the invention;
fig. 7 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, 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.
Currently, most of the research on irrigation pits focuses on pit identification and water surface area extraction, and less research on estimation of the water storage capacity of the irrigation pits is performed. In addition, the existing water storage amount estimation method is mostly based on the area-water storage amount statistical relation, and under the condition that the water level cannot be directly obtained, the water storage amount of the pit with the water storage amount which does not change along with the water surface area is difficult to accurately estimate. Accurate irrigation pit water storage capacity acquisition can not leave the identification of irrigation pit, water surface area extraction and water storage capacity calculation.
In the study of pit identification, the main methods include artificial visual interpretation of the characteristics of irrigation pits, automatic screening methods based on shape indexes, and object-oriented methods. Part of the research utilizes high-resolution NAIP data, google images and the like to visually interpret and identify the position of the pit and digitize the pit in combination with characteristics of the irrigation pit, wherein the identification characteristics comprise irrigation regulating ditches, water supply pipes, water drainage pipes or pump rooms around the pit, one or more adjacent farmlands, nearby ditches, river channels and other surface water sources. And screening according to the size and shape index characteristics of the pits and identifying the pits by combining OSTU threshold segmentation. The pit water body identification is based on an object-oriented method, and automatic pit identification is mainly carried out according to spectral characteristic wave bands, texture characteristics, fusion edge characteristics and semantic information.
In terms of pit water surface area extraction, many studies for large scale long-time-series pit variation detection use optical imaging, a topic map instrument (TM)/enhanced topic map instrument+ (ETM 1) on land satellite, and a medium resolution imaging spectrometer (MODIS) on Earth Observation System (EOS) Terra and Aqua satellites may be used. However, the extraction accuracy for small water bodies is low due to limitations in terms of low resolution, poor data quality, and the like. With the increase of the space-time resolution of the available satellites, more researches are conducted to extract the precise water surface edge profile through high space-time resolution images, such as Sentinel2 (Sentinel 2), plane, GF-1/2, world view, rapid Eye (RE), etc. The advent of high space-time resolution satellite data and SAR data, multi-source data fusion has provided more possibilities for small pit identification. The SAR data is not affected by cloud interference and solar radiation, and can work day and night under any weather condition. Radar observations can therefore be used as an alternative to hydrologic monitoring or as a method to supplement optical images.
However, more researches at present pay attention to pit water surface area extraction, water storage capacity calculation is not carried out by combining water level elevation information, and partial researches add water level elevation difference information into pit water body identification and extraction. And creating a fusion classification model of three water level depth data sets based on the image of the optical satellite and heterogeneous data of the laser radar, and identifying by using a multi-level decision tree. Or the water level is acquired by using high-precision radar data. In the aspect of water storage calculation, a mode of multi-source remote sensing satellite data fusion makes great contribution to solving the aspects of data deficiency and precision improvement, most researches relate multi-source elevation data with area estimation of an optical satellite, and an empirical relationship between the elevation and the water surface area is established to calculate the water storage, so that the multi-source data are mutually complementary to estimate the water storage. And the water storage capacity calculation is also partially studied by combining satellite data and ground measured data, the water level information is obtained by combining the height measurement data of a laser altimeter or a radar, the relation between the water level and the water surface area is established, the water level is corrected and evaluated through the measured data, and the water storage capacity is calculated by utilizing the corrected water level and the area information. However, for ponds with water storage capacity which does not change obviously with water surface area, the method is not suitable for accurately estimating the water storage capacity of various irrigation ponds.
Especially, key water level information in water storage capacity calculation is difficult to obtain, on one hand, because the water level information is limited by small form of an irrigation pit, a low-coverage laser radar satellite remote sensing altimeter can not be widely applied to all irrigation pits, and planar coverage radar satellite data has a limiting factor with lower resolution; on the other hand, the data acquisition of the actually measured hydrologic stations is limited by the quantity and distribution of the water level monitoring stations in different areas, and the time and the labor are consumed when the monitoring instrument and the control system are arranged in a large range, so that the hydrologic water level measurement data actually measured on the current ground are limited.
Both of the above aspects limit the efficient monitoring of the water storage capacity of an irrigation pit.
The invention discloses an irrigation pit water storage amount estimation method comprehensively considering remote sensing and ground observation, which comprises the steps of firstly, based on data of a sentinel No. 1 and a sentinel No. 2, carrying out rapid identification of a pit by combining OSTU segmentation with irrigation pit characteristics; then, obtaining a high-precision irrigation pit water surface area data set by utilizing object-oriented multi-scale segmentation of single-phase high-resolution high-score 2 data; then, the water level information of the irrigation pit is obtained by combining with the laser radar ICESat2 data and ground photo observation; and finally, providing an irrigation pit water storage amount estimation method with the integration of the heaven and earth data. The invention provides a multisource data supported irrigation pit water storage amount estimation method, which provides basic data for water storage amount accounting in irrigation areas and exploration of an optimized water distribution scheme, and promotes economic benefit and water resource utilization efficiency to be improved.
The invention provides a multi-source data supported irrigation pit water storage estimation thought, overcomes the defect that the water storage information of the irrigation pit is difficult to comprehensively obtain in the single-mode calculation of the water storage of the irrigation pit, and solves the problem that the water storage of the irrigation pit which does not change along with the water surface area is difficult to calculate in an area-water storage statistical mode.
Irrigation pit water storage capacity estimation thought combining satellite and ground data
The following describes, with reference to fig. 1 to 7, a method, an apparatus, an electronic device, and a storage medium for monitoring the water storage capacity of an irrigation pit according to an embodiment of the present invention.
According to the method for monitoring the water storage capacity of the irrigation pit, the execution main body can be electronic equipment or software or a functional module or a functional entity capable of realizing the method for monitoring the water storage capacity of the irrigation pit in the electronic equipment, and the electronic equipment in the embodiment of the invention comprises a server but is not limited to the server. The execution body is not limited to the present invention.
Fig. 1 is a schematic flow chart of a method for monitoring the water storage capacity of an irrigation pit, provided by the invention, as shown in fig. 1, including but not limited to the following steps:
firstly, in step S1, determining the water surface area of each irrigation pit in a target area based on initial remote sensing data of the target area, and acquiring water level information of each irrigation pit; the water surface area is determined based on multi-scale segmentation of the water surface of the irrigation pit of the high-resolution remote sensing data in the initial remote sensing data.
Two satellites in total are used for long-time monitoring of a target area, wherein the guard 1 collects two radar data of VV and VH polarization values and is used for judging whether the target area is an irrigation pit, the guard 2 collects optical remote sensing data of near infrared, red and green light wave bands, and the two satellite data correspond to two water indexes of SDWI and NDWI respectively.
A plurality of irrigation pits are built in the target area and are used for irrigation of the target area; the initial remote sensing data is remote sensing data which is acquired by the sentry 2 for a long time and has time sequence, the remote sensing data is stored in a grid form, and the sentry 2 data is acquired by the GEE platform.
Identifying each irrigation pit in the target area according to the collected remote sensing data, and calculating the water surface area of each irrigation pit by utilizing multi-scale segmentation; in addition, the water level information of each irrigation pit is required to be obtained, and the water level information of each irrigation pit can be directly read, can be acquired by using a laser radar, or can be obtained by carrying out water level identification on an acquired image.
Optionally, the initial telemetry data includes a plurality of time-series low-resolution telemetry data and single-phase high-resolution telemetry data; the resolution of the time sequence low resolution remote sensing data is lower than that of the high resolution remote sensing data;
The determining the water surface area of each irrigation pit in the target area based on the initial remote sensing data of the target area comprises the following steps:
extracting irrigation pit areas in the target area from each time sequence low-resolution remote sensing data, and generating first irrigation pit data sets of all the irrigation pits in the target area;
acquiring the central point position of each irrigation pit in the target area by using the first irrigation pit data set;
migrating the central point position of each irrigation pit to the high-resolution remote sensing data;
in the high-resolution remote sensing data, taking the central point position of each irrigation pit as the center, and generating a regional mask according to a defined radius to acquire irrigation pit range remote sensing data; the defined radius is determined based on a maximum defined water surface area for each irrigation pit in the first set of irrigation pit data;
and based on the segmentation scale threshold value of the irrigation pits, carrying out pixel combination on the irrigation pits in the remote sensing data of the irrigation pit range, generating second irrigation pit data sets of all the irrigation pits, and acquiring the water surface area of the irrigation pits.
The maximum defined water surface area may be a defined maximum area among all the irrigation pits, i.e. a defined maximum area in the definition of the irrigation pits, based on a statistical number of irrigation pit areas, e.g. a maximum defined water surface area of 100000 square meters is set. Firstly, in initial remote sensing data, primarily extracting an irrigation pit area in a target area to obtain irrigation pit water body remote sensing data.
For example, the remote sensing data collected by the sentry 1 and the sentry 2 are time sequence low resolution remote sensing data, and the resolution is 10 meters; the system comprises single-phase high-resolution remote sensing data acquired by high-resolution 2, wherein the single-phase high-resolution remote sensing data comprises multispectral remote sensing data and panchromatic data, the resolution of the multispectral remote sensing data is 4 meters, and the resolution of the panchromatic data is 1 meter.
The remote sensing data range of the irrigation pit range is larger than the second irrigation pit data set of all the irrigation pits, and the water surface area of the irrigation pits can be obtained through object-oriented multi-scale segmentation and combination.
In the method for monitoring the water storage capacity of the irrigation pit provided by the invention, the time sequence low-resolution remote sensing data is firstly used for defining the area, and then the single-time phase high-resolution remote sensing data is used for realizing accurate extraction.
Optionally, extracting an irrigation pit area in the target area from each time sequence low resolution remote sensing data, and generating a first irrigation pit data set of all irrigation pits in the target area, including:
masking any time-sequence low-resolution remote sensing data by utilizing the maximum NDVI (non-uniform density differential) of the vegetation growth period acquired by the large water body information and the time-sequence low-resolution remote sensing data of the target area to generate mask remote sensing data of the any time-sequence low-resolution remote sensing data so as to acquire mask remote sensing data of each time-sequence low-resolution remote sensing data; the mask remote sensing data comprises small-sized water body remote sensing data and soil remote sensing data;
Binary classification is carried out on each scene mask remote sensing data by utilizing a water index, and a small water body data set in the target area in each scene mask remote sensing data is obtained;
and determining the first irrigation pit data set according to the small water body data set.
The vegetation growth period may be a season in which vegetation is growing, such as 6 and 7 months per year.
First, the area is masked to remove vegetation and large bodies of water.
Specifically, the sentinel 2 data is used to calculate a normalized vegetation index (NDVI) for the vegetation growth period, and a current year vegetation area mask is generated by limiting the threshold.
Acquiring a normalized vegetation index NDVI of a target area in a vegetation growing period by using a sentinel 2, and judging the vegetation area in a threshold limiting mode to remove the vegetation area;
the normalized vegetation index NDVI is calculated as follows:
wherein ρ is NIR Is the reflectivity of the near infrared band; ρ RED Is the infrared band reflectivity.
And removing vegetation through NDVI and a part of large water body area through mask, wherein the rest part is bare soil and rest water body, and the binary classification can be carried out by using an OSTU threshold method.
Then, mask removal is performed on the large-sized water body, the wetland, the lake and the irrigation canal according to the geographic information of the existing target areas such as the GlobeLand30, the Open Street Map (OSM) and the like, so that mask area image files of the areas such as the small-sized water body, the bare soil and the like are obtained.
And secondly, removing non-irrigation pit water bodies in the remote sensing data by using an law method (OSTU) threshold segmentation method, and realizing crude extraction of water surface area.
The maximum inter-class difference method (OSTU), also known as the Ojin method, can select an optimal threshold between the body of water and bare soil by an automatic threshold segmentation method. The OSTU method is applied to binary classification scenes, is an automatic method for distinguishing two relatively homogeneous things based on pixel value distribution, and is often used for distinguishing objects from backgrounds, bare soil from water bodies, forests from grasslands and the like. It is necessary to calculate the specific gravity omega of the picture elements smaller and larger than a certain threshold value 0 And omega 1 The average value and variance of all pixel values with gray values smaller than the threshold value are mu respectively 0 The average value and variance of pixel values with all gray values larger than the threshold are mu respectively 1 Through continuous iterative calculation, a threshold value for maximizing the inter-class variance, namely a threshold value corresponding to the maximum BSS, is found, and the specific calculation is as follows:
BSS＝ω 0 ω 1 (μ 0 -μ 1 ) 2 2, 2
And extracting water bodies in the mask area, namely the area where irrigation pits possibly appear, including the irrigation pits, the tail water pool and the fish ponds by using a gray threshold segmentation method. And respectively calculating a water body index (SDWI) by using the data VV of the sentinel 1 and the VH polarization value, calculating a normalized difference water body index (NDWI) by using the data of the sentinel 2, and identifying the area where the small artificial water body is located by using an OSTU threshold segmentation method to obtain a small water body data set in the target area. And simultaneously, comparing the performances of the different indexes in the identification of the irrigation pits, and selecting an optimal threshold segmentation index.
Sdwi=ln (10×vv×vh) -8 formula 3
SDWI is a sentinel 1 dual-polarized water index; VV is sentinel 1 data for vertical transmit and vertical receive (VV) dual polarized data; VH is sentinel 1 data for vertical transmission and horizontal reception (VH) dual polarized data; NDWI is normalized water index; ρ GREEN Is the reflectivity of the green wave band; ρ NIR Is the reflectivity of the near infrared band.
The water body indexes SDWI and NDWI are used for realizing the rough extraction of the irrigation pit area.
Optionally, determining the first irrigation pit dataset from the small body of water dataset includes:
screening each water body in the small water body data set of each scene mask remote sensing data according to pit size limiting conditions to obtain a screened water body data set of each time phase; the pit size limiting condition is determined based on the maximum defined water surface area of the pit water body;
carrying out space superposition analysis on the screened water body data sets of all time phases, and calculating the average water body frequency of pixels in the target area to determine the seasonal variation rule of the water quantity of each small water body;
determining an irregular irrigation pit water body area according to the seasonal variation rule of the water quantity; the irrigation pit type of each irrigation pit in the irregular irrigation pit water body area is irregular;
Screening each water body in the screened water body data set according to the outline characteristics of the irrigation pits and the irregular irrigation pits water body areas to obtain the regular irrigation pits water body areas; the irrigation pit type of each irrigation pit in the regular irrigation pit water body area is regular;
and combining the irregular type irrigation pit water body area and the regular type irrigation pit water body area as the first irrigation pit data set.
Because the water quantity of each irrigation pit is different in states of different time sequences, the pixel average water body frequency needs to be calculated, and the omission of single remote sensing data in the process of counting the irrigation pits is avoided.
For example, setting a maximum defined water surface area of 100000 square meters, a pit size constraint may include screening out water data having a water surface area of less than 100000 square meters, forming a screened water data set for each phase.
The first irrigation pit dataset comprises: the irregular type irrigation pit water body area and the regular type irrigation pit water body area are the results of rough extraction of the irrigation area.
And identifying the irrigation pits in the water body area, and comprehensively considering the size, shape and seasonal variation factors of the water surface area.
(1) Aiming at the region where the small artificial water body identified in the screening water body data set is located, utilizing a multi-stage small artificial water body image layer extracted for 2-6 months, and calculating the average water body frequency of pixels in the region through space superposition analysis;
(2) Removing areas which are accidentally identified as water bodies, such as bare soil areas with high short-term humidity;
(3) Screening according to irrigation pit characteristics, wherein the irrigation pit characteristics comprise pit size and shape.
Because the area of the water area of the irrigation pit is smaller, the size of the irrigation pit in the field investigation data display area is between 5000 square meters and 100000 square meters, and the excessive water bodies identified by the parts are removed; by limiting the shape index S i To remove the water body with extremely irregular shape.
Finally, the characteristic of the quaternary water body change of the irrigation pit is also considered.
For example, as the morphological characteristics of the irrigation ponds in the R irrigation areas are mainly divided into two types of irregular water bodies and regular rectangular water bodies, wherein the irregular water bodies are generally built by cement, the boundary gradient is smaller, the slope surface is slower, the water surface area can be obviously changed along with the processes of irrigation, precipitation and the like, the identification of the irregular ponds can be carried out by identifying the water surface area change characteristics, and the water bodies with obvious early water storage-irrigation water processes are identified as irrigation ponds;
The general boundary gradient of part of rectangular water body is larger, the slope is steeper, and the water surface area does not change obviously; therefore, after seasonal selection, the shape index S is used in the remaining region i As the appearance characteristic of the irrigation pit, judging the type of the irrigation pit, if S i If not less than 0.5, it is regular, if S i And < 0.5, the product is irregular.
Wherein Si is a shape index; a is pit area; p is the circumference of the pit.
Generating an irrigation pit data set according to Google Earth (Google Earth) or other map software and field investigation results, and judging whether a certain data is an irrigation pit and whether the data is used for irrigation:
(1) Visually interpreting the water body area, and judging whether the water body area is an irrigation pit or not according to the profile elevation;
(2) And judging whether related water facilities such as a water well, a water house, a water outlet channel and the like exist around the high-resolution image of the map software.
And (3) carrying out irrigation pit identification by combining the characteristics and the field investigation conditions, and generating an irrigation pit ground verification data set, wherein the total number of the irrigation pits is 16 in the irrigation area. Comparing the extraction results based on the SDWI index and the NDWI index, the method for dividing the threshold value of the SDWI index based on the sentinel 1 and the method for dividing the threshold value of the NDWI index based on the sentinel 2 can accurately identify irrigation pits in the area, and the overall precision reaches 94.1%.
And then, precisely extracting the water surface area of the pit by combining semantic information of an object-oriented multi-scale segmentation algorithm with water indexes.
The object-oriented multi-scale segmentation method can accurately extract boundary information of ground objects by combining a high-resolution remote sensing image, and the basic principle is that pixels with the same characteristics are divided into an image object according to the characteristics of shapes, colors, textures and the like of pixels.
The method comprises the steps that object-oriented remote sensing analysis is adopted by Ecognition (Ecogenation) software, objects are generated by image multi-scale segmentation, characteristics such as spectrum, shape, texture and the like are packaged for each object, and the relation between the object and adjacent objects, father objects and child objects is established; and judging the types of the ground objects according to the generated information, and generating objects of different types.
The concept of multi-scale segmentation mesoscale, the macro angle is the granularity of an object to be processed, and the micro angle can be understood as the allowable heterogeneity in the merging process of the object of the current layer.
The image object has a hierarchy, the lowest layer is a pixel layer, the uppermost layer is the whole scene of the image, the abstraction level is higher and higher from bottom to top, and the heterogeneity (namely the segmentation scale) allowed by the object is larger.
The multi-scale image segmentation adopts a region merging algorithm with minimum heterogeneity, pixels are merged into smaller image objects, and then the smaller objects are merged into larger objects layer by layer through heterogeneity calculation and comparison.
Each merging step is to judge whether the regional heterogeneity after merging is larger than the scale, if so, merging is not performed, otherwise, merging is not performed. Until the whole area heterogeneity is greater than the scale or the whole object is merged. The heterogeneity calculation in Yikang software mainly considers the spectral characteristics and shape characteristics inside the object, and the calculation formula is as follows:
f＝ω color h color +(1-ω color )h shape 6. The method is to
h sha ＝ω compact h compact +(1-ω compact )h smoo 8. The method is used for preparing the product
h smooth =l/b type 10
Wherein f is the totalHeterogeneity; omega color Is a spectral weight; (1-. Omega.) color ) Is a shape weight; omega compact Is a compactness weight; (1-. Omega.) compact ) Is a smoothness weight; omega c Spectral weight for multispectral c band; h is a color Is spectral heterogeneity; h is a shape Is shape heterogeneity; h is a compact Is the degree of compactness; h is a smooth Is smooth; sigma (sigma) c The standard deviation of the spectrum value of the c wave band in the object S; l is the number of pixels contained in the boundary of the object S; n is the number of pixels contained in the object S; b is the boundary length of the minimum bounding rectangle of the object S.
In multi-scale segmentation, the segmentation is incomplete due to the fact that the scale is too large, the segmentation is too broken due to the fact that the scale is too small, therefore an optimal scale threshold value needs to be determined, an ESP2 plug-in is used for finding a peak value, the corresponding threshold value is the optimal scale threshold value, and the optimal scale threshold value obtained by identifying an irrigation pit is 53.
According to the obtained irrigation pit positions and by combining an object-oriented method, the identified two types of pits used for irrigation are subjected to high-score 2 data, so that the water surface area of the irrigation pits is accurately extracted, and a second irrigation pit data set is generated.
Because the area of the water area of the irrigation pit is smaller, the water surface area is extracted by using the remote sensing data acquired by the sentinel 2 with the resolution of 10 meters to generate obvious zigzag boundaries, so that a larger area calculation error is caused. Therefore, only the irrigation pits are identified and positioned based on the data of the sentinel 2, and the identified extracted central point positions of the irrigation pits are spatially connected with the high-resolution image segmentation object.
And carrying out multi-scale segmentation on the high-resolution 2-multispectral image with the resolution of 1 meter after image fusion by utilizing Yikang software, and carrying out object classification by combining with an NDWI index, thereby realizing accurate extraction of the water surface area and generating a second irrigation pit data set.
Compared with the extraction result of the sentinel, the multiscale segmentation algorithm based on the high-resolution image is more accurate, and the edge processing is more careful, so that more accurate water surface area can be obtained. However, segmentation based on the shape, color and texture of the object has higher requirements on image quality, and if the cloud content of the used image is higher, the image quality is poorer, so that the boundary extraction result is wrong.
And comparing the water surface area obtained by remote sensing with the water surface area of the actual measured water level calculation current period, and evaluating the accuracy of the water surface area extraction method of the irrigation pit.
For an irrigation pit with a flat bottom and regular shape, an irregular triangular net (Triangulated Irregular Network, TIN) model of the irrigation pit is constructed by using known construction parameters, and the water surface area and the water storage capacity of the irrigation pit can be calculated for any input water level.
The average value of the water level measured in the field in multiple periods can be used as a ground truth value of the water level in the adjacent period, the real water level is used as input data, the real water level is combined with a TIN model to obtain the truth value of the water surface area in the current period, and the truth value is compared with the remote sensing estimated water surface area to evaluate the water surface area extraction method. The water surface areas of 5 irrigation pits are verified, RMSE and MAE are 962 square meters and 766 square meters respectively, the extraction error is within the range (namely + -1060 square meters), the resolution of the high-resolution No. 2 image after image fusion is 1 meter, and the overall extraction error is within the allowable range of the resolution error. Therefore, a method of extracting the water surface area of an irrigation pit by combining the sentinel 2 with the high-resolution remote sensing image is feasible.
Optionally, obtaining the water level information of each irrigation pit includes:
Acquiring water level information of an irrigation pit in the target area by using a laser radar; or alternatively, the first and second heat exchangers may be,
acquiring an image to be identified of an irrigation pit in the target area;
and inputting the image to be identified into a water level identification model, and acquiring the water level information output by the water level identification model, wherein the water level identification model is obtained after training based on a sample pit image with a water level information label.
And acquiring water level information by using laser radar data.
The lidar IceSat2 data may provide ground elevation (relative to ground level) of land, water, vegetation. Using acquired elevation substitutes for adjacent ground surfacesAnd (3) calculating the height difference between the value and the water surface instead of the upper boundary elevation of the irrigation pit, and calculating the current water depth by combining the construction depth of the irrigation pit. Peripheral boundary elevation H of irrigation pit b Water surface elevation H w The difference between the two can be used for obtaining the height h of the current water surface from the upper boundary of the building 1 Then the obtained irrigation pit is utilized to build depth h c And h 1 The difference can be used for obtaining the water depth h w The method is characterized by comprising the following steps:
H b -H w ＝h 1 11. The method of the invention
h c -h 1 ＝h w 12. Fig.
Wherein H is b And H w The boundary elevation and the water surface elevation around the irrigation pit pool are respectively; h is a 1 Is the height of the upper boundary of the current water surface from the construction; h is a c Is the construction depth of the irrigation pit; h is a w Is the water depth.
The water level is obtained through image observation, and firstly, the photo set is obtained under the constraint that certain conditions are needed, so that the comparability of the photos is ensured. The serial photos in the images to be identified are guaranteed to have the same camera, a fixed visual angle, a fixed distance, adjacent dates and consistent weather conditions.
Fig. 2 is a schematic flow chart of model training provided in the present invention, as shown in fig. 2, first, a part of measured water level data corresponding to original fig. 1, original fig. 2, …, and original fig. n is needed.
Then, the original image 1, the original image 2, the original image … and the original image n are subjected to image preprocessing by using an oxford threshold segmentation method, the original image 1, the original image 2, the original image … and the original image n are converted into a gray image 1, a gray image 2, a gray image … and a gray image n, and the gray image 1, the gray image 2, the gray image … and the gray image n are subjected to parallel smoothing processing to obtain a smooth image 1, a smooth image 2, a smooth image … and a smooth image n.
Then, the water level identification feature is acquired, and the water level identification feature mainly comprises the area of the lake surface and the leftmost/rightmost edge pixel row where the lake surface is photographed. The input characteristic parameters of the model training, namely the characteristic 1 and the characteristic 2, are obtained by setting the center point of the lake surface and combining the breadth to search the area of the lake surface and the pixel array of the rightmost or leftmost edge of the lake surface (determined according to the shooting angle of the photo).
Finally, water level prediction is performed by using a water level identification model constructed based on an error Back propagation artificial neural network (Back-propagation Neural Networks, BPNNs), wherein in a model training stage, image features are trained by using 80% of sample sets, and 20% are used for verification.
The water level identification model comprises an input layer, an hidden layer and an output layer, wherein the input quantity Xj of the input layer, the hidden layer output quantity Oj of the hidden layer and the output quantity Yk of the output layer.
And verifying the accuracy of the two water level acquisition modes by using the actually measured water level data. And comparing the ground actually measured water depth with the water level acquired by the laser radar data and the water level acquired by the photo automatically, and analyzing the accuracy of water depth measurement based on remote sensing and ground observation methods. And (3) selecting a No. 1 irrigation pit with ICESat2 track passing, ground construction data and ground actual measurement data to verify a water level acquisition method. Taking the average value of the measured data of the water level of the field for 4 months as the ground water level true value, and taking the water level of the ICESat2 data as 1.04 m and the photo observation water level as 1.10 m. The ICESat2 acquired water level is more accurate than the photo observed water level, the error is 2 cm, and the photo observed error is 8 cm.
Wherein the build data comprises: degree of inclination, bottom area, opening area, slope change area and depth, etc.
Further, in step S2, the water storage capacity of each irrigation pit is generated according to the type, the water surface area and the water level information of each irrigation pit, and the type of each irrigation pit includes regular type and irregular type.
Wherein, the water surface area of the regular type irrigation pit is not changed along with the water storage amount, and the water surface area of the irregular type irrigation pit is changed along with the water storage amount.
For a regular irrigation pit, the water storage capacity of the irrigation pit can be directly obtained according to the product of the water surface area and the water level information; for all the irrigation pits, the water surface area, the pit bottom form TIN model generated by combining the ground data can be utilized to input the water surface area of the irrigation pit to correspondingly obtain the pit water storage capacity, and the water level information, the pit bottom form TIN model generated by combining the ground data can also be utilized to input the water level of the irrigation pit to correspondingly obtain the pit water storage capacity.
Optionally, generating the water storage capacity of each irrigation pit according to the pit type, the water surface area and the water level information of each irrigation pit, including:
under the condition that the type of any irrigation pit is regular, determining the water storage capacity of any irrigation pit according to the water level information and the water surface area of any irrigation pit;
And under the condition that the type of any irrigation pit is irregular, determining the water storage capacity of any irrigation pit based on the construction data of any irrigation pit according to the water level information or the water surface area of any irrigation pit.
The water storage capacity of the irrigation pit can be directly calculated by combining two water level acquisition modes of image recognition and radar measurement with the construction data of the irrigation pit, and the method is applicable to the two types of irrigation pits, and particularly applicable to the irrigation pit with the water storage capacity which does not change along with the water surface area.
In addition, for the irrigation pit which can not directly acquire water level information and the water storage capacity of which varies along with the water surface area, the water storage capacity of the irrigation pit is calculated according to the water surface area-water storage capacity relation by utilizing accurate water surface area identification data and combining with an irrigation pit bottom form TIN model generated by ground data. The water level of the irrigation pit is obtained by the two different modes, different methods are required to be selected according to the current data availability, the processing efficiency and the final precision, the final water storage capacity is obtained, and the comprehensive use of three water storage capacity calculation ideas can provide guarantee for the calculation of the water storage capacity of the multi-type irrigation pit under various conditions:
(1) Calculating water level depth according to laser radar data in combination with irrigation pit construction data, and then carrying out water storage capacity calculation in combination with the accurately extracted water surface area information of the irrigation pit;
(2) Automatically acquiring the water level of the irrigation pit through a series of water surface change photos, and then carrying out water storage calculation by combining with the accurately extracted water surface area information of the irrigation pit;
(3) And obtaining the water storage capacity by combining the water surface area in the current period by utilizing the relation between the irrigation pit construction data and the water surface area change.
For an irrigation pit with the water surface area changing along with the water level, the water storage capacity can be calculated by three methods; for an irrigation pit with the water surface area not changing along with the water level, the water level can be obtained only in the former two modes, and the water storage capacity is calculated.
Each water level obtaining mode has advantages and disadvantages:
the mode of extracting water level information based on the laser radar ICESat2 is quicker, but because the water body of the irrigation pit is smaller, the condition of no track passing can occur in the observation key time interval, so that data is lost, and the water storage capacity of the irrigation pit cannot be calculated;
although a certain early-stage sample collection and instrument erection are needed in the method based on photo observation, the method can ensure that the water level information of all irrigation ponds is timely and efficiently obtained, can supplement and guarantee the calculation of the water storage capacity under the condition of remote sensing data loss through automatic identification of multiple-stage photos and combination of accurately extracted water surface areas, and is used for preferentially using the photo observation method for regular irrigation ponds.
(1) The water storage capacity estimation for regular irrigation pits requires the water surface area and the current water level to be obtained respectively to calculate the water storage capacity. Therefore, the water level can be obtained only by laser radar data and a water surface photo observation mode, and then the water storage capacity calculation is performed by combining the accurately extracted water surface area information of the irrigation pit.
(2) According to the water storage capacity calculation of the irregular irrigation pit, the water storage capacity of the irrigation pit can be calculated according to the water level-water storage capacity and the area-water storage capacity lookup table relationship respectively by combining with the ground data to generate the irrigation pit bottom form TIN model as long as the current water level or the current water surface area is arbitrarily obtained. Therefore, the three modes can be used for calculating the water storage capacity of the irrigation pit, the area-water storage capacity relation method has the advantage of large-range planar recognition, and the area recognition error has smaller influence on the result compared with the water level recognition error, has higher precision, and is a method for preferentially using the area-water storage capacity relation for the regular irrigation pit.
And (5) carrying out precision assessment on the calculation results of the water storage quantities of the two different types of irrigation pits. And (3) comparing the water storage capacity of the irrigation pits 1 and 2 calculated based on the method with the result calculated based on the ground actual measurement in the actually measured 2 irrigation pits, wherein the irrigation pit 1 represents the type that the water surface area does not change along with the water level, and the irrigation pit 2 represents the type that the water surface area changes along with the water level. The results showed that the accuracy was 98.8%,95.2%,94.1% based on the area-water storage calculation method, the ICESat2 (lidar) -water storage calculation method, and the photo observation-water storage calculation method, respectively, all performed well.
According to the method for monitoring the water storage capacity of the irrigation pit, provided by the invention, the object-oriented multi-scale segmentation is utilized to combine the characteristics of the irrigation pit to identify the irrigation pit and calculate the water surface area, and the water depth of the irrigation pit is collected, so that the accurate water storage capacity of the irrigation pit is calculated rapidly and timely, the monitoring efficiency is improved, the obtained water storage capacity data is more visual, basic data is provided for water volume accounting in an irrigation area and optimizing a water distribution scheme, and the economic benefit and the water resource utilization efficiency are improved.
Fig. 3 is a second flow chart of the method for monitoring the water storage capacity of an irrigation pit, as shown in fig. 3, including:
irrigation pit identification is carried out by utilizing data collected by the sentry 1 and the sentry 2:
respectively constructing a dual-polarized water index SDWI and a normalized water index NDWI, and extracting water;
furthermore, according to the area and shape characteristics of the irrigation pits and seasonal changes of the water surface area, the extraction of the irrigation pits is realized;
according to the high score 2 data, the accurate extraction of the water surface area of the irrigation pit is realized on the basis of the extracted irrigation pit, and the water surface area of the irrigation pit is obtained by specifically using an object-oriented multi-scale segmentation method;
for regular irrigation pits, building data or observing photos by using IceSat2 to obtain water level information of the irrigation pits, estimating water storage capacity of the irrigation pits, and finally obtaining water storage capacity of the irrigation pits;
And (5) estimating the water storage capacity of the irregular irrigation pits, and finally obtaining the water storage capacity of the irrigation pits.
Fig. 4 is a third flow chart of the method for monitoring the water storage capacity of an irrigation pit, provided by the invention, as shown in fig. 4, including: the water level monitoring of the irrigation pit comprises laser radar and photo observation, wherein data acquired by the laser radar are preprocessed, elevation points are obtained, the water surface-pit top height is obtained, and the water depth is calculated by combining the construction depth; and collecting a sample, preprocessing, extracting water level characteristics, and inputting the water level characteristics into the BP neural network for water level prediction.
For an irregular irrigation pit, constructing a TIN model at the bottom of the irrigation pit, acquiring a dynamic water surface area, further obtaining the depth of a water body, and finally calculating the water storage capacity;
for a regular irrigation pit, acquiring the water depth after acquiring the water surface area, and finally calculating the water storage capacity.
Fig. 5 is a flow chart of a method for monitoring the water storage capacity of an irrigation pit, provided by the invention, as shown in fig. 5, comprising:
first, in step 501, irrigation pits are identified;
secondly, in step 502, accurately extracting the water surface area of an irrigation pit;
Furthermore, in step 503, irrigation pond water level information of the world data fusion is obtained;
finally, in step 504, the multi-source and data fused irrigation pit water storage capacity is estimated.
The invention provides three kinds of irrigation pit water storage quantity calculation ideas by constructing an irrigation pit water storage quantity remote sensing model and combining satellite data with ground photo observation, and realizes effective calculation of regular and irregular irrigation pit water storage quantity by combining water surface area, laser radar water level acquisition and photo observation water level acquisition modes. Especially, the method based on ground photo observation can solve the problem that the water storage capacity of the irrigation pit is difficult to calculate in a single mode of water surface area-water storage capacity, makes up the defects of a single model and single data, and effectively improves the accuracy and coverage of the water storage capacity of the irrigation pit.
The device for monitoring the water storage capacity of the irrigation pit provided by the invention is described below, and the device for monitoring the water storage capacity of the irrigation pit described below and the method for monitoring the water storage capacity of the irrigation pit described above can be correspondingly referred to each other.
Fig. 6 is a schematic structural diagram of an irrigation pit water storage monitoring device provided by the invention, as shown in fig. 6, including:
The determining module 601 is configured to determine a water surface area of each irrigation pit in the target area based on initial remote sensing data of the target area, and obtain water level information of each irrigation pit; the water surface area is determined based on object-oriented multi-scale segmentation of the water surface of an irrigation pit of high-resolution remote sensing data in the initial remote sensing data;
the generating module 602 is configured to generate the water storage capacity of each irrigation pit according to the irrigation pit type, the water surface area and the water level information of each irrigation pit, where the irrigation pit type includes regular type and irregular type.
In the running process of the device, a determining module 601 determines the water surface area of each irrigation pit in a target area based on initial remote sensing data of the target area, and acquires water level information of each irrigation pit; the water surface area is determined based on object-oriented multi-scale segmentation of the water surface of an irrigation pit of high-resolution remote sensing data in the initial remote sensing data; the generation module 602 generates the water storage capacity of each irrigation pit according to the irrigation pit type, the water surface area and the water level information of each irrigation pit, wherein the irrigation pit type comprises a regular type and an irregular type.
According to the irrigation pit water storage monitoring device provided by the invention, the object-oriented multi-scale segmentation is utilized to combine the characteristics of the irrigation pits to identify the irrigation pits and calculate the water surface area, and the water depth of the irrigation pits is collected, so that the accurate water storage of the irrigation pits is calculated rapidly and timely, the monitoring efficiency is improved, the obtained water storage data is more visual, basic data is provided for water storage accounting and water distribution scheme optimization in an irrigation area, and the economic benefit and the water resource utilization efficiency are improved.
Fig. 7 is a schematic structural diagram of an electronic device according to the present invention, and as shown in fig. 7, the electronic device may include: processor 710, communication interface (Communications Interface) 720, memory 730, and communication bus 740, wherein processor 710, communication interface 720, memory 730 communicate with each other via communication bus 740. Processor 710 may invoke logic instructions in memory 730 to perform an irrigation pit water storage monitoring method comprising: determining the water surface area of each irrigation pit in the target area based on initial remote sensing data of the target area, and acquiring water level information of each irrigation pit; the water surface area is determined based on object-oriented multi-scale segmentation of the water surface of an irrigation pit of high-resolution remote sensing data in the initial remote sensing data; and generating the water storage capacity of each irrigation pit according to the type, the water surface area and the water level information of each irrigation pit, wherein the type of each irrigation pit comprises regular type and irregular type.
Further, the logic instructions in the memory 730 described above may be implemented in the form of software functional units and may be stored in a computer readable storage medium when sold or used as a stand alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product comprising a computer program, the computer program being storable on a non-transitory computer readable storage medium, the computer program, when executed by a processor, being capable of performing the method of monitoring the water storage capacity of an irrigation pit provided by the methods described above, the method comprising: determining the water surface area of each irrigation pit in the target area based on initial remote sensing data of the target area, and acquiring water level information of each irrigation pit; the water surface area is determined based on multi-scale segmentation of the water surface of the irrigation pit of the high-resolution remote sensing data in the initial remote sensing data; and generating the water storage capacity of each irrigation pit according to the type, the water surface area and the water level information of each irrigation pit, wherein the type of each irrigation pit comprises regular type and irregular type.
In yet another aspect, the present invention provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the method of monitoring the water storage capacity of an irrigation pit provided by the above methods, the method comprising: determining the water surface area of each irrigation pit in the target area based on initial remote sensing data of the target area, and acquiring water level information of each irrigation pit; the water surface area is determined based on multi-scale segmentation of the water surface of the irrigation pit of the high-resolution remote sensing data in the initial remote sensing data; and generating the water storage capacity of each irrigation pit according to the type, the water surface area and the water level information of each irrigation pit, wherein the type of each irrigation pit comprises regular type and irregular type.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (9)

1. A method for monitoring the water storage capacity of an irrigation pit, comprising the steps of:
determining the water surface area of each irrigation pit in the target area based on initial remote sensing data of the target area, and acquiring water level information of each irrigation pit; the water surface area is determined based on multi-scale segmentation of the water surface of the irrigation pit of the high-resolution remote sensing data in the initial remote sensing data;
and generating the water storage capacity of each irrigation pit according to the type, the water surface area and the water level information of each irrigation pit, wherein the type of each irrigation pit comprises regular type and irregular type.
2. The method of claim 1, wherein the initial telemetry data comprises a plurality of time-series low-resolution telemetry data and single-phase high-resolution telemetry data; the resolution of the time sequence low resolution remote sensing data is lower than that of the high resolution remote sensing data;
the determining the water surface area of each irrigation pit in the target area based on the initial remote sensing data of the target area comprises the following steps:
extracting irrigation pit areas in the target area from each time sequence low-resolution remote sensing data, and generating first irrigation pit data sets of all the irrigation pits in the target area;
Acquiring the central point position of each irrigation pit in the target area by using the first irrigation pit data set;
migrating the central point position of each irrigation pit to the high-resolution remote sensing data;
in the high-resolution remote sensing data, taking the central point position of each irrigation pit as the center, and generating a regional mask according to a defined radius to acquire irrigation pit range remote sensing data; the defined radius is determined based on a maximum defined water surface area for each irrigation pit in the first set of irrigation pit data;
and based on the segmentation scale threshold value of the irrigation pits, carrying out pixel combination on the irrigation pits in the remote sensing data of the irrigation pit range, generating second irrigation pit data sets of all the irrigation pits, and acquiring the water surface area of the irrigation pits.
3. The method of claim 1, wherein obtaining water level information for each of the irrigation pits comprises:
acquiring water level information of an irrigation pit in the target area by using a laser radar; or alternatively, the first and second heat exchangers may be,
acquiring an image to be identified of an irrigation pit in the target area;
and inputting the image to be identified into a water level identification model, and acquiring the water level information output by the water level identification model, wherein the water level identification model is obtained after training based on a sample pit image with a water level information label.
4. The method of claim 2, wherein extracting the irrigation pit area within the target area in each time series low resolution remote sensing data generates a first irrigation pit data set for all of the irrigation pits within the target area, comprising:
masking any time-sequence low-resolution remote sensing data by utilizing the maximum NDVI (non-uniform density differential) of the vegetation growth period acquired by the large water body information and the time-sequence low-resolution remote sensing data of the target area to generate mask remote sensing data of the any time-sequence low-resolution remote sensing data so as to acquire mask remote sensing data of each time-sequence low-resolution remote sensing data; the mask remote sensing data comprises small-sized water body remote sensing data and soil remote sensing data;
binary classification is carried out on each scene mask remote sensing data by utilizing a water index, and a small water body data set in the target area in each scene mask remote sensing data is obtained;
and determining the first irrigation pit data set according to the small water body data set.
5. The method of monitoring the water storage capacity of an irrigation pit of claim 4, wherein determining the first irrigation pit data set from the small body of water data set comprises:
Screening each water body in the small water body data set of each scene mask remote sensing data according to pit size limiting conditions to obtain a screened water body data set of each time phase; the pit size limiting condition is determined based on the maximum defined water surface area of the pit water body;
carrying out space superposition analysis on the screened water body data sets of all time phases, and calculating the average water body frequency of pixels in the target area to determine the seasonal variation rule of the water quantity of each small water body;
determining an irregular irrigation pit water body area according to the seasonal variation rule of the water quantity; the irrigation pit type of each irrigation pit in the irregular irrigation pit water body area is irregular;
screening each water body in the screened water body data set according to the outline characteristics of the irrigation pits and the irregular irrigation pits water body areas to obtain the regular irrigation pits water body areas; the irrigation pit type of each irrigation pit in the regular irrigation pit water body area is regular;
and combining the irregular type irrigation pit water body area and the regular type irrigation pit water body area as the first irrigation pit data set.
6. The method of monitoring the water storage capacity of each irrigation pit according to any one of claims 1-5, wherein generating the water storage capacity of each irrigation pit based on the pit type, water surface area, and water level information of each irrigation pit comprises:
under the condition that the type of any irrigation pit is regular, determining the water storage capacity of any irrigation pit according to the water level information and the water surface area of any irrigation pit;
and under the condition that the type of any irrigation pit is irregular, determining the water storage capacity of any irrigation pit based on the construction data of any irrigation pit according to the water level information or the water surface area of any irrigation pit.
7. An irrigation pit water storage monitoring device, comprising:
the determining module is used for determining the water surface area of each irrigation pit in the target area based on the initial remote sensing data of the target area and acquiring the water level information of each irrigation pit; the water surface area is determined based on multi-scale segmentation of the water surface of the irrigation pit of the high-resolution remote sensing data in the initial remote sensing data;
the generation module is used for generating the water storage capacity of each irrigation pit according to the irrigation pit type, the water surface area and the water level information of each irrigation pit, and the irrigation pit type comprises regular type and irregular type.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of monitoring the water storage capacity of an irrigation pit as claimed in any one of claims 1 to 6 when the program is executed by the processor.
9. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the method of monitoring the water storage capacity of an irrigation pit as claimed in any of claims 1-6.
CN202310684818.9A 2023-06-09 2023-06-09 Irrigation pit water storage capacity monitoring method and device, electronic equipment and storage medium Pending CN116935236A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310684818.9A CN116935236A (en) 2023-06-09 2023-06-09 Irrigation pit water storage capacity monitoring method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310684818.9A CN116935236A (en) 2023-06-09 2023-06-09 Irrigation pit water storage capacity monitoring method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN116935236A true CN116935236A (en) 2023-10-24

Family

ID=88390300

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310684818.9A Pending CN116935236A (en) 2023-06-09 2023-06-09 Irrigation pit water storage capacity monitoring method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN116935236A (en)

Similar Documents

Publication Publication Date Title
Kraaijenbrink et al. Object-based analysis of unmanned aerial vehicle imagery to map and characterise surface features on a debris-covered glacier
Chen et al. Isolating individual trees in a savanna woodland using small footprint lidar data
Koukoulas et al. Mapping individual tree location, height and species in broadleaved deciduous forest using airborne LIDAR and multi‐spectral remotely sensed data
CN111242224B (en) Multi-source remote sensing data classification method based on unmanned aerial vehicle extraction classification sample points
CN101840581B (en) Method for extracting profile of building from satellite remote sensing image
CN111046613B (en) Optimal river channel calculation method based on path tracking and river network extraction method based on multi-temporal remote sensing image
González-Yebra et al. Methodological proposal to assess plastic greenhouses land cover change from the combination of archival aerial orthoimages and Landsat data
CN106501186B (en) A kind of soil moisture content product NO emissions reduction method
WO2014054042A1 (en) Device and method for detecting plantation rows
Ban et al. EO4Urban: Sentinel-1A SAR and Sentinel-2A MSI data for global urban services
Ainiwaer et al. Deep learning-based rapid recognition of oasis-desert ecotone plant communities using UAV low-altitude remote-sensing data
Li et al. Integrating multiple textural features for remote sensing image change detection
Lei et al. A novel algorithm of individual tree crowns segmentation considering three-dimensional canopy attributes using UAV oblique photos
CN107194857B (en) Available land resource analysis system based on high-resolution satellite remote sensing data
Mao et al. Advances and prospects on estimating solar photovoltaic installation capacity and potential based on satellite and aerial images
Kim et al. Tree and building detection in dense urban environments using automated processing of IKONOS image and LiDAR data
Nelson et al. Spatial statistical techniques for aggregating point objects extracted from high spatial resolution remotely sensed imagery
Han et al. Refined land-cover classification mapping using a multi-scale transformation method from remote sensing, unmanned aerial vehicle, and field surveys in Sanjiangyuan National Park, China
CN115063437B (en) Mangrove canopy visible light image index feature analysis method and system
CN116561509A (en) Urban vegetation overground biomass accurate inversion method and system considering vegetation types
Lu et al. Mapping the terraces on the Loess Plateau based on a deep learning-based model at 1.89 m resolution
CN116935236A (en) Irrigation pit water storage capacity monitoring method and device, electronic equipment and storage medium
Li et al. Measuring detailed urban vegetation with multisource high-resolution remote sensing imagery for environmental design and planning
CN110688990B (en) Rice planting candidate area determination method
CN114550005A (en) Method and system for identifying buildings in natural protection area

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