CN114943734B - Irrigation device abnormity detection method and system based on unmanned aerial vehicle aerial photography - Google Patents
Irrigation device abnormity detection method and system based on unmanned aerial vehicle aerial photography Download PDFInfo
- Publication number
- CN114943734B CN114943734B CN202210860229.7A CN202210860229A CN114943734B CN 114943734 B CN114943734 B CN 114943734B CN 202210860229 A CN202210860229 A CN 202210860229A CN 114943734 B CN114943734 B CN 114943734B
- Authority
- CN
- China
- Prior art keywords
- image
- water
- water column
- abnormal
- coefficient
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/77—Determining position or orientation of objects or cameras using statistical methods
-
- 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
- G06T2207/10004—Still image; Photographic image
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
- Y02A40/22—Improving land use; Improving water use or availability; Controlling erosion
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the field of identification methods by using electronic equipment, in particular to an irrigation device abnormity detection method and system based on unmanned aerial vehicle aerial photography, wherein the method comprises the steps of collecting a sprinkling irrigation image of a sprinkling irrigation area, and segmenting the sprinkling irrigation image to obtain a nozzle image, a water column area image and a water mist image; acquiring the height and the length of a water column in the water column area image, and acquiring a height abnormal coefficient and a length abnormal coefficient according to the length and the height of the water column; obtaining a target area image by taking the water outlet point of each spray head as the center in the water mist image, obtaining the peak value of a gray level histogram of the target area image, and determining the water mist abnormal coefficient of the water column according to the peak value; calculating a comprehensive abnormal coefficient of the nozzle according to the length abnormal coefficient, the height abnormal coefficient and the water mist abnormal coefficient; according to the comprehensive abnormal coefficient and the set threshold value, the abnormal spray head and the position of the abnormal spray head are determined and an alarm is given out.
Description
Technical Field
The invention relates to the field of identification methods by using electronic equipment, in particular to an irrigation device abnormity detection method and system based on unmanned aerial vehicle aerial photography.
Background
Irrigation equipment's use scene is mostly in the farmland field, changes the environment again under, often meets with heavy weather such as torrential rain, strong wind, and outdoor unexpected condition is also more, all can carry out erosion and destruction of different degrees to the device, and the most common impaired condition is like the fracture of irrigation water pipe, sensor trouble and shower nozzle wearing and tearing etc..
When overhauing sprinkling irrigation equipment, all send technical worker to patrol, however, its area in the farmland in plain area is bigger, and all for planting in batches to it is big to agricultural irrigation equipment coverage area, needs a large amount of manual works to inspect the shower nozzle one by one when carrying out artifical patrol inspection, and artifical patrol all uses regularly patrol to give first place to, can not inspect every shower nozzle in real time.
Therefore, a method and a system for identifying and processing irrigation device abnormity based on unmanned aerial vehicle aerial photography are needed to solve the above problems.
Disclosure of Invention
The invention provides an irrigation device abnormity detection method and system based on unmanned aerial vehicle aerial photography, and aims to solve the existing problems.
The invention discloses an irrigation device abnormity detection method based on unmanned aerial vehicle aerial photography, which adopts the following technical scheme: the method comprises the following steps:
acquiring a spray irrigation image of a spray irrigation area, segmenting the spray irrigation image to obtain a nozzle image and a water column area image, and obtaining a water mist image according to the nozzle image and the water column area image;
calculating the height and length of all water columns in each row in the water column area image, and obtaining a height abnormal coefficient and a length abnormal coefficient corresponding to each water column according to the length and height of the water column in the row;
acquiring the positions of the nozzles in the nozzle image, rounding the water outlet point of each nozzle position in the water mist image to obtain a target area image, wherein the adjacent target area images are not overlapped;
acquiring a gray level histogram of the target area image, acquiring peak values in the gray level histogram, and acquiring a water mist abnormal coefficient of each water column according to the peak values corresponding to the same row of target area images and the average value of all the peak values;
calculating a comprehensive abnormal coefficient of each corresponding nozzle according to the length abnormal coefficient, the height abnormal coefficient and the water mist abnormal coefficient;
and determining the abnormal spray head and the position of the abnormal spray head according to the comprehensive abnormal coefficient and the set threshold value and giving an alarm.
Further, the step of segmenting the spray irrigation image to obtain a water column area image comprises the following steps:
performing semantic segmentation on the spray irrigation image to obtain a background water column area image;
carrying out graying processing on the background water column area image to obtain a grayscale histogram of the grayed background water column area image;
acquiring a gray value corresponding to a valley between two peak values in a gray histogram, and recording the gray value as an optimal threshold value;
and performing threshold segmentation on the background water column area image according to the optimal threshold to obtain a water column area image.
Further, the step of obtaining the water mist image according to the nozzle image and the water column area image comprises the following steps:
acquiring a binary image corresponding to the nozzle image and a binary image corresponding to the water column area image;
and obtaining a background water mist image according to the binary image corresponding to the nozzle image, the binary image corresponding to the water column area image and the irrigation image, and recording the background water mist image as a water mist image.
Further, the step of calculating the height and length of all water columns in each row in the water column region image comprises:
establishing a two-dimensional coordinate system of the water column area image;
establishing a sliding window by taking a water outlet point of a spray head in the water column area image as a starting point;
setting the sliding step length of the sliding window as a pixel point, and sliding along the direction of the pixel point corresponding to the water column in the water column region image;
recording the final pixel coordinate of the current sliding window central point until the sliding window slides to the tail end of the water column;
and calculating the length and height of the water column according to the initial point coordinate and the final pixel coordinate of the sliding window.
Further, the step of calculating the length and height of the water column according to the starting point coordinate and the final pixel coordinate of the sliding window comprises the following steps:
obtaining the length of the water column according to all pixel points from the initial point coordinate of the sliding window to the final pixel coordinate;
and subtracting the ordinate value of the starting point from the ordinate value of the final pixel to obtain the height of the water column.
Further, the step of obtaining the height abnormal coefficient and the length abnormal coefficient corresponding to each water column according to the length and the height of the row of water columns comprises:
acquiring length medians and height medians corresponding to the lengths and heights of all water columns in the same row in the water column area image;
the difference value of the length of each water column in the same row and the median of the length is recorded as a length abnormal coefficient;
and the difference value of the height of each water column in the same row and the median of the height is recorded as a height abnormal coefficient.
Further, the step of obtaining the water mist abnormal coefficient of each water column according to the peak value corresponding to the same row of target area images and the average value of all the peak values comprises the following steps:
and obtaining the difference value of the average value and the peak value corresponding to the same row of target area images, and recording the difference value as the water mist abnormal coefficient corresponding to each target area image.
Further, the step of calculating the comprehensive abnormal coefficient of each corresponding nozzle according to the length abnormal coefficient, the height abnormal coefficient and the water mist abnormal coefficient comprises the following steps:
calculating a comprehensive abnormality coefficient according to the following formula (1):
wherein, the first and the second end of the pipe are connected with each other,
indicates the length anomaly coefficient,
Indicating a height anomaly coefficient,
Showing the water mist abnormality coefficient,
A weight coefficient representing the abnormality of the water column,
A weight coefficient representing the water mist abnormality.
Further, the step of determining the abnormal spray head and the position of the abnormal spray head according to the comprehensive abnormal coefficient and the set threshold value and giving an alarm comprises the following steps:
establishing two-dimensional coordinates of a sprinkling irrigation image;
when the comprehensive abnormal coefficient is larger than a set threshold value, determining the spray head corresponding to the water column and the water mist as an abnormal spray head;
and acquiring the two-dimensional coordinates of the abnormal spray head and giving an alarm.
The invention also discloses an irrigation device abnormity detection system based on unmanned aerial vehicle aerial photography, which comprises:
the image acquisition module is used for acquiring a sprinkling irrigation image of a sprinkling irrigation area, segmenting the sprinkling irrigation image to obtain a sprayer image and a water column area image, and obtaining a water mist image according to the sprayer image and the water column area image;
the first parameter calculation module is used for calculating the heights and the lengths of all water columns in each row in the water column region image and obtaining a height abnormal coefficient and a length abnormal coefficient corresponding to each water column according to the lengths and the heights of the water columns in the row;
the image processing module is used for acquiring the positions of the nozzles in the nozzle images, rounding the water outlet point of each nozzle position in the water mist images to obtain target area images, and the adjacent target area images are not overlapped;
the second parameter calculation module is used for acquiring a gray level histogram of the target area image, acquiring peak values in the gray level histogram, and acquiring the water mist abnormal coefficient of each water column according to the peak values corresponding to the same row of target area images and the average value of all the peak values;
the comprehensive parameter calculation module is used for calculating the comprehensive abnormal coefficient of each corresponding spray head according to the length abnormal coefficient, the height abnormal coefficient and the water mist abnormal coefficient;
and the alarm module is used for determining the abnormal spray head and the position of the abnormal spray head according to the comprehensive abnormal coefficient and the set threshold value and giving an alarm.
The beneficial effects of the invention are: according to the irrigation device abnormity detection method and system based on unmanned aerial vehicle aerial photography, the height abnormity coefficient and the length abnormity coefficient of the water column in the non-atomized area and the water mist abnormity coefficient in the atomized area are obtained to serve as comprehensive abnormity parameters for judging the irrigation device, the abnormal spray head is determined and the position of the abnormal spray head is determined according to the comprehensive abnormity parameters, so that an alarm is given out, the real-time detection of the irrigation abnormity is realized, the manual labor force is reduced, the maintenance worker can maintain the irrigation device in time, and the method is applied to the unmanned aerial vehicle aerial photography in the irrigation device for identifying and processing to realize the intelligent detection of the irrigation device.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of the general steps of an embodiment of a method and system for anomaly detection for irrigation devices based on aerial photography by unmanned aerial vehicles according to the present invention;
FIG. 2 is a flow chart of the water column area image acquisition of FIG. 1;
FIG. 3 is a flow chart of the method of FIG. 1 for obtaining the length and height of a water column;
FIG. 4 is a schematic diagram of a water column area image in the method;
fig. 5 is a schematic diagram of a target area image in the method.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
The embodiment of the invention relates to an irrigation device abnormity detection method based on unmanned aerial vehicle aerial photography, as shown in figure 1, the method comprises the following steps:
s1, collecting a spray irrigation image of a spray irrigation area, segmenting the spray irrigation image to obtain a nozzle image and a water column area image, and obtaining a water mist image according to the nozzle image and the water column area image.
Specifically, gather the irrigation image in sprinkling irrigation farmland irrigation region through unmanned aerial vehicle, adopt DNN semantic segmentation to cut apart the irrigation image, be about to the pixel that needs to cut apart in the irrigation image, divide into 2 types altogether, the mark that belongs to the pixel that the shower nozzle corresponds is 1, and the mark that other regions mark for the background type is 0 to obtain the shower nozzle image that only contains the shower nozzle region.
Specifically, because irrigate the region mostly outdoor, so do not atomize in the near nappe region of shower nozzle, can regard as the water column, the pixel of water column is compared in the density of the pixel of the water smoke after the atomizing great, so the luminance of the pixel of water column is higher than the grey scale value of the pixel of water smoke, S11, cut apart the step that obtains the regional image of water column to the sprinkling irrigation image and include: as shown in fig. 2, S111, according to the method for obtaining the sprinkler image, performing semantic segmentation on the irrigation image to obtain a background water column region image only including a background water column region, and S112, performing graying processing on the background water column region image to obtain a grayscale histogram of the grayed background water column region image; s113, obtaining a gray value corresponding to a valley between two peaks in the gray histogram, and marking the gray value as an optimal threshold, and S114, as shown in fig. 4, performing threshold segmentation on the background water column region image according to the optimal threshold to obtain a water column region image, specifically, S12, obtaining the water mist image according to the sprinkler image and the water column region image includes: s121, acquiring a binary image corresponding to the nozzle image and a binary image corresponding to the water column area image; and S122, obtaining a background water mist image according to the binary image corresponding to the nozzle image, the binary image corresponding to the water column region image and the irrigation image, wherein as shown in FIG. 5, the water mist is relatively dispersed, and the divided target region images all have water mist, so that the number of water mist pixel points in the target region image is the largest, the background pixel points in the background water mist image can be ignored, and the background water mist image is the water mist image.
S2, because the distribution of the irrigation device in the farmland is distributed according to rows or columns, the height and the length of all water columns in each row in the water column area image are calculated, because the water flow of the irrigation spray heads is dispersed and atomized along with the distance of the spray heads, the edge water flow of the water columns is dispersed and less dense than the middle water flow, and the gray level of the edge water flow image is lower than that of the middle water flow image in the gray level image, because the irrigation spray heads are positioned firstly, the judgment of the abnormal coefficient of the water columns is carried out secondly, when the irrigation device does not spray the water columns, the height and the length of the water columns are both 0, and the method can detect the abnormality of the spray heads; therefore, the height abnormal coefficient and the length abnormal coefficient corresponding to each water column are obtained according to the length and the height of the row of water columns.
Specifically, the step S21 of calculating the heights and lengths of all water columns in each row in the water column region image includes: as shown in fig. 3, S211, establishing a two-dimensional coordinate system of the water column area image; s212, establishing a sliding window by taking a water outlet point of a spray head in the water column area image as a starting point, specifically, setting the size of the sliding window to be 3x3, wherein the size of the sliding window can be set according to the specific situation of water flow of the spray can, and the set value is
The aim is to ensure the accuracy of the sliding window movement; setting the sliding step length of the sliding window as a pixel point, and sliding along the direction of the pixel point corresponding to the water column in the water column region image; s213, recording the final pixel coordinate of the current sliding window central point until the sliding window slides to the tail end of the water column; s214, calculating the length and the height of the water column according to the initial point coordinate and the final pixel coordinate of the sliding window, specifically, S2141, obtaining the length of the water column according to all pixel points from the initial point coordinate to the final pixel coordinate of the sliding window; specifically, the length of the water column corresponding to the central point of the initial sliding window is set
0 
Every time the sliding window is moved by one pixel unit, then
=
0 +1, until the sliding window moves to waterAt the end of the column, the sliding window stops moving and the pixel coordinate of the current sliding window center point is recorded, the current
The value of (2) is the length of the water column, S2142, the value obtained by subtracting the ordinate value of the starting point from the ordinate value of the final pixel is the height of the water column, specifically, the length of each row of the water column is sequentially marked as [ [ 2 ] ] [, ] [ [ 2 ] ]
1 ,
2 ,
3 …
n ]The height of the water column of each row is sequentially
1 ,
2 ,
3 …
n ]。
S22, the step of obtaining the height abnormal coefficient and the length abnormal coefficient corresponding to each water column according to the length and the height of the row of water columns comprises the following steps: acquiring length medians and height medians corresponding to the lengths and heights of all water columns in the same row in the water column area image; the difference value of the length of each water column in the same row and the median of the length is recorded as a length abnormal coefficient; the difference value of the height and the median of the height of each water column in the same row is recorded as a height abnormal coefficient,wherein, the length abnormity coefficient L =
0,1, 2- (8230); (n-1) wherein,
is the median of the length,
representing the same row of water column
The length corresponding to each water column; height anomaly coefficient H =
0,1, 2- (8230); (n-1) wherein,
in order to be the median of the height,
representing the same row of water column
The height corresponding to each water column.
S3, acquiring the positions of the nozzles in the nozzle images, wherein water mist is influenced by the external environment, for example, errors are generated along with the direction of wind, so that in order to basically include water mist pixel points, the accuracy is improved, a target area image is obtained by rounding the water outlet point of each nozzle position in the water mist image, and adjacent target area images are not overlapped;
s4, because each divided target area image has water mist, the number of water mist pixel points in the target area image is the largest, so that a gray histogram of the pixel points in the target area image is obtained, peak values in the gray histogram are obtained, the peak values correspond to the water mist pixel points, and the peak values corresponding to the target area image in the same row and the average value of all the peak values are obtainedAnd taking the water mist abnormal coefficient of each water column, specifically, obtaining the difference value of the average value and the peak value corresponding to the same row of target area images, and recording the difference value as the water mist abnormal coefficient corresponding to each target area image, wherein the water mist abnormal coefficient is recorded as the water mist abnormal coefficient corresponding to each target area image
，
A peak value representing the ith target area image,
the average of all peaks of the line of target images.
And S5, calculating a comprehensive abnormal coefficient of each corresponding nozzle according to the length abnormal coefficient, the height abnormal coefficient and the water mist abnormal coefficient.
Specifically, the comprehensive abnormality coefficient is calculated according to the following formula (1):
wherein the content of the first and second substances,
indicates the length anomaly coefficient,
Indicating a height anomaly coefficient,
Showing the water mist abnormality coefficient,
A weight coefficient representing the abnormality of the water column,
A weight coefficient representing the water mist abnormality.
S6, determining an abnormal spray head and the position of the abnormal spray head according to the comprehensive abnormal coefficient and a set threshold value, and giving an alarm; specifically, two-dimensional coordinates of a sprinkling irrigation image are established; when the comprehensive abnormal coefficient is larger than a set threshold value, determining the spray head corresponding to the water column and the water mist as an abnormal spray head; and acquiring the two-dimensional coordinates of the abnormal sprayer, uploading the two-dimensional coordinates of the abnormal sprayer to a system, and sending an abnormal alarm.
The invention also discloses an irrigation device abnormity detection system based on unmanned aerial vehicle aerial photography, which comprises: the device comprises an image acquisition module, a first parameter calculation module, an image processing module, a second parameter calculation module, a comprehensive parameter calculation module and an alarm module, wherein the image acquisition module is used for acquiring a spray irrigation image of a spray irrigation area, segmenting the spray irrigation image to obtain a spray head image and a water column area image, and obtaining a water mist image according to the spray head image and the water column area image; the first parameter calculation module is used for calculating the heights and the lengths of all water columns in each row in the water column region image and obtaining a height abnormal coefficient and a length abnormal coefficient corresponding to each water column according to the lengths and the heights of the water columns in the row; the image processing module is used for acquiring the positions of the nozzles in the nozzle images, rounding the water outlet point of each nozzle position in the water mist images to obtain target area images, and adjacent target area images are not overlapped; the second parameter calculation module is used for acquiring a gray level histogram of the target area image, acquiring peak values in the gray level histogram, and acquiring the water mist abnormal coefficient of each water column according to the peak values corresponding to the same row of target area images and the average value of all the peak values; the comprehensive parameter calculation module is used for calculating a comprehensive abnormal coefficient of each corresponding spray head according to the length abnormal coefficient, the height abnormal coefficient and the water mist abnormal coefficient; and the alarm module is used for determining the abnormal spray head and the position of the abnormal spray head according to the comprehensive abnormal coefficient and the set threshold value and giving an alarm.
In summary, the invention provides an irrigation device anomaly detection method and system based on unmanned aerial vehicle aerial photography, which are characterized in that the height anomaly coefficient, the length anomaly coefficient and the water mist anomaly coefficient of an unatomized area water column are obtained to serve as comprehensive anomaly parameters for judging a sprinkling irrigation device, and the determination of an abnormal spray head and the determination of the position of the abnormal spray head are realized according to the comprehensive anomaly parameters, so that an alarm is given out, the real-time detection of sprinkling irrigation anomaly is realized, the labor force is reduced, and the maintenance of a maintenance worker can be maintained in time.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (8)
1. An irrigation device abnormity detection method based on unmanned aerial vehicle aerial photography is characterized by comprising the following steps:
acquiring a spray irrigation image of a spray irrigation area, segmenting the spray irrigation image to obtain a nozzle image and a water column area image, and obtaining a water mist image according to the nozzle image and the water column area image;
the method comprises the steps of calculating the heights and the lengths of all water columns in each row in a water column area image, obtaining a height abnormal coefficient and a length abnormal coefficient corresponding to each water column according to the lengths and the heights of the water columns in the row, and obtaining the height abnormal coefficient and the length abnormal coefficient corresponding to each water column according to the lengths and the heights of the water columns in the row, wherein the step of: acquiring length medians and height medians corresponding to the lengths and heights of all water columns in the same row in the water column region image; the difference value of the length of each water column in the same row and the median of the length is recorded as a length abnormal coefficient; the difference value of the height and the height median of each water column in the same row is recorded as a height abnormal coefficient;
acquiring the positions of the nozzles in the nozzle images, rounding the water outlet point of each nozzle position in the water mist images to obtain target area images, wherein the adjacent target area images are not overlapped;
the method comprises the steps of obtaining a gray level histogram of a target area image, obtaining peak values in the gray level histogram, obtaining a water mist abnormal coefficient of each water column according to the peak values corresponding to the same row of target area images and the average value of all the peak values, and calculating a comprehensive abnormal coefficient of each corresponding nozzle according to the length abnormal coefficient, the height abnormal coefficient and the water mist abnormal coefficient, wherein the step comprises the following steps: obtaining the difference value between the average value and the peak value corresponding to the same row of target area images, and recording the difference value as the water mist abnormal coefficient corresponding to each target area image;
calculating a comprehensive abnormal coefficient of each corresponding spray head according to the length abnormal coefficient, the height abnormal coefficient and the water mist abnormal coefficient;
and determining the abnormal spray head and the position of the abnormal spray head according to the comprehensive abnormal coefficient and the set threshold value and giving an alarm.
2. The method of claim 1, wherein the step of segmenting the sprinkler irrigation image to obtain a water column region image comprises:
performing semantic segmentation on the spray irrigation image to obtain a background water column area image;
carrying out graying processing on the background water column area image to obtain a grayscale histogram of the grayed background water column area image;
acquiring a gray value corresponding to a valley between two peak values in the gray histogram, and recording the gray value as an optimal threshold value;
and performing threshold segmentation on the background water column area image according to the optimal threshold to obtain a water column area image.
3. The irrigation device abnormality detection method based on unmanned aerial vehicle aerial photography according to claim 1, wherein the step of obtaining a water mist image according to a nozzle image and a water column area image comprises:
acquiring a binary image corresponding to the nozzle image and a binary image corresponding to the water column area image;
and obtaining a background water mist image according to the binary image corresponding to the nozzle image, the binary image corresponding to the water column area image and the irrigation image, and recording the background water mist image as a water mist image.
4. The unmanned aerial vehicle aerial photography-based irrigation device abnormality detection method of claim 1, wherein the step of calculating the height and length of all water columns in each row in the water column region image comprises:
establishing a two-dimensional coordinate system of the water column area image;
establishing a sliding window by taking a water outlet point of a spray head in the water column area image as a starting point; setting the sliding step length of the sliding window as a pixel point, and sliding along the direction of the pixel point corresponding to the water column in the water column region image;
until the sliding window slides to the tail end of the water column, recording the final pixel coordinate of the current sliding window central point;
and calculating the length and height of the water column according to the starting point coordinate and the final pixel coordinate of the sliding window.
5. The irrigation device abnormality detection method based on unmanned aerial vehicle aerial photography of claim 4, wherein the step of calculating the length and height of the water column according to the starting point coordinates and the final pixel coordinates of the sliding window comprises:
obtaining the length of the water column according to all pixel points from the initial point coordinate of the sliding window to the final pixel coordinate;
and subtracting the ordinate value of the starting point from the ordinate value of the final pixel to obtain the height of the water column.
6. The irrigation device abnormality detection method based on unmanned aerial vehicle aerial photography of claim 1, wherein the step of calculating the comprehensive abnormality coefficient of each corresponding sprinkler according to the length abnormality coefficient, the height abnormality coefficient and the water mist abnormality coefficient comprises:
calculating a comprehensive abnormality coefficient according to the following formula (1):
wherein the content of the first and second substances,
indicates the length anomaly coefficient,
Indicating a height anomaly coefficient,
Showing the water mist abnormality coefficient,
A weight coefficient representing the abnormality of the water column,
A weight coefficient representing the water mist abnormality.
7. The irrigation device abnormality detection method based on unmanned aerial vehicle aerial photography of claim 1, wherein the steps of determining abnormal sprayers and abnormal sprayer positions according to the comprehensive abnormal coefficients and the set threshold values and giving an alarm comprise:
establishing two-dimensional coordinates of a sprinkling irrigation image;
when the comprehensive abnormal coefficient is larger than a set threshold value, determining the spray head corresponding to the water column and the water mist as an abnormal spray head;
and acquiring the two-dimensional coordinates of the abnormal sprayer and giving an alarm.
8. The utility model provides an irrigation equipment anomaly detection system based on unmanned aerial vehicle takes photo by plane which characterized in that includes:
the image acquisition module is used for acquiring a spray irrigation image of a spray irrigation area, segmenting the spray irrigation image to obtain a nozzle image and a water column area image, and obtaining a water mist image according to the nozzle image and the water column area image;
the first parameter calculation module is used for calculating the heights and the lengths of all water columns in each row in the water column region image, obtaining the height abnormal coefficient and the length abnormal coefficient corresponding to each water column according to the length and the height of the row of water columns, and obtaining the height abnormal coefficient and the length abnormal coefficient corresponding to each water column according to the length and the height of the row of water columns comprises the following steps: acquiring length medians and height medians corresponding to the lengths and heights of all water columns in the same row in the water column region image; the difference value of the length of each water column in the same row and the median of the length is recorded as a length abnormal coefficient; the difference value of the height and the height median of each water column in the same row is recorded as a height abnormal coefficient;
the image processing module is used for acquiring the positions of the nozzles in the nozzle images, rounding the water outlet point of each nozzle position in the water mist images to obtain target area images, and adjacent target area images are not overlapped;
the second parameter calculation module is used for acquiring a gray level histogram of the target area image, acquiring peak values in the gray level histogram, and acquiring the water mist abnormal coefficient of each water column according to the peak values corresponding to the same row of target area images and the average value of all the peak values;
the comprehensive parameter calculation module is used for calculating the comprehensive abnormal coefficient of each corresponding nozzle according to the length abnormal coefficient, the height abnormal coefficient and the water mist abnormal coefficient, and the step of calculating the comprehensive abnormal coefficient of each corresponding nozzle according to the length abnormal coefficient, the height abnormal coefficient and the water mist abnormal coefficient comprises the following steps: obtaining the difference value of the average value and the peak value corresponding to the same row of target area images, and recording the difference value as the water mist abnormal coefficient corresponding to each target area image;
and the alarm module is used for determining the abnormal spray head and the position of the abnormal spray head according to the comprehensive abnormal coefficient and the set threshold value and giving an alarm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210860229.7A CN114943734B (en) | 2022-07-22 | 2022-07-22 | Irrigation device abnormity detection method and system based on unmanned aerial vehicle aerial photography |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210860229.7A CN114943734B (en) | 2022-07-22 | 2022-07-22 | Irrigation device abnormity detection method and system based on unmanned aerial vehicle aerial photography |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114943734A CN114943734A (en) | 2022-08-26 |
| CN114943734B true CN114943734B (en) | 2023-03-10 |
Family
ID=82911437
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210860229.7A Active CN114943734B (en) | 2022-07-22 | 2022-07-22 | Irrigation device abnormity detection method and system based on unmanned aerial vehicle aerial photography |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114943734B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116210565B (en) * | 2023-03-29 | 2023-11-14 | 上海华维可控农业科技集团股份有限公司 | Liquid return treatment system and method for intelligent irrigation |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111357625A (en) * | 2020-04-22 | 2020-07-03 | 雪川农业发展股份有限公司 | Agricultural irrigation system irrigation water yield automated control device |
| CN114170565A (en) * | 2021-11-09 | 2022-03-11 | 广州市鑫广飞信息科技有限公司 | Image comparison method and device based on unmanned aerial vehicle aerial photography and terminal equipment |
| CN114451278B (en) * | 2022-02-18 | 2023-04-28 | 安徽金晥泵业科技股份有限公司 | Farmland irrigation analysis control system based on internet |
| CN114627110B (en) * | 2022-05-12 | 2022-08-16 | 济宁海富光学科技有限公司 | Detection method for light transmission abnormity of glass cover plate |
-
2022
- 2022-07-22 CN CN202210860229.7A patent/CN114943734B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114943734A (en) | 2022-08-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109024417B (en) | Intelligent road sweeper and road pollutant identification method and control method thereof | |
| CN106529493B (en) | Robust multi-lane line detection method based on perspective view | |
| CN105486228B (en) | A kind of trees target volume method for real-time measurement based on two dimensional laser scanning instrument | |
| CN114943734B (en) | Irrigation device abnormity detection method and system based on unmanned aerial vehicle aerial photography | |
| CN112418188A (en) | Crop growth whole-course digital assessment method based on unmanned aerial vehicle vision | |
| CN103891697A (en) | Drug spraying robot capable of moving indoors autonomously and variable drug spraying method thereof | |
| CN109471434A (en) | A kind of novel variable rate spray path planning autonomous navigation system and method | |
| CN112213735A (en) | Laser point cloud noise reduction method for rainy and snowy weather | |
| CN108710818A (en) | A kind of real-time monitoring and statistics system and method for number based on three-dimensional laser radar | |
| CN102722894B (en) | Intelligent video monitoring method based on automatic calibration of camera | |
| CN115049662B (en) | Sprayer flow control method based on image processing | |
| CN115272425B (en) | Railway site area intrusion detection method and system based on three-dimensional point cloud | |
| CN111288934B (en) | Target leaf area online calculation method based on mobile laser scanning | |
| CN116642420A (en) | Online glue type detection device and method for gluing automobile windshield glass | |
| CN116538924A (en) | Real-time monitoring method for sag of power transmission line in icing state | |
| CN115755088A (en) | Laser point cloud-based automatic measurement method for power transmission line engineering construction parameters | |
| CN113820682B (en) | Millimeter wave radar-based target detection method and device | |
| CN110675362B (en) | Method for acquiring horizon under curved road monitoring environment | |
| CN113553958B (en) | Expressway green belt detection method and device | |
| CN114445713A (en) | Multi-device linkage plant protection system and method | |
| CN114966732A (en) | Intelligent agricultural machinery combined navigation system based on machine vision | |
| CN113740847A (en) | Multi-radar cooperative detection alarm system based on humanoid target recognition | |
| CN115685222B (en) | Automatic power line tower detection method based on laser point cloud data | |
| CN112488113A (en) | Remote sensing image rotating ship target detection method based on local straight line matching | |
| CN111880197A (en) | Road boundary detection method based on four-line laser radar |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |