CN111985445A - Grassland insect pest monitoring system and method based on unmanned aerial vehicle multispectral remote sensing - Google Patents
Grassland insect pest monitoring system and method based on unmanned aerial vehicle multispectral remote sensing Download PDFInfo
- Publication number
- CN111985445A CN111985445A CN202010907338.0A CN202010907338A CN111985445A CN 111985445 A CN111985445 A CN 111985445A CN 202010907338 A CN202010907338 A CN 202010907338A CN 111985445 A CN111985445 A CN 111985445A
- Authority
- CN
- China
- Prior art keywords
- image
- insect
- grassland
- module
- remote sensing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06N3/045—Combinations of networks
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- 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
Abstract
The invention belongs to the technical field of grassland insect pest monitoring, and discloses a grassland insect pest monitoring system and method based on unmanned aerial vehicle multispectral remote sensing, wherein the grassland insect pest monitoring system based on unmanned aerial vehicle multispectral remote sensing comprises: the system comprises a remote sensing image acquisition module, a grassland temperature and humidity acquisition module, a main control module, a flight module, a remote sensing image enhancement module, an image feature extraction module, a pest damage analysis module, an early warning module and a display module. According to the invention, the balance coefficient alpha and the broadening coefficient beta are introduced through the remote sensing image enhancement module, and the gray scale range is linearly expanded while the histogram equalization is maintained, so that the purpose of flexibly controlling the image quality of the grassland insects is achieved, and the enhancement effect is good; meanwhile, the insect image of the insect plate is collected through the early warning module, the pest increment in the insect image is determined according to the insect image and a preset contrast image, the grassland pest number threshold range to which the pest increment belongs is determined, early warning information is generated, and early warning can be carried out in time.
Description
Technical Field
The invention belongs to the technical field of grassland insect pest monitoring, and particularly relates to a grassland insect pest monitoring system and method based on unmanned aerial vehicle multispectral remote sensing.
Background
At present: in recent years, under the background of factors such as global warming, the population distribution and the occurrence rule of insect pests are changed significantly, the insect pests tend to expand and aggravate, the damage degree of the insect pests to crops, forests and grassland vegetation is increasingly serious, and the insect pests bring great threat to the safety of human living environment. The loss caused by insect damage and billions jin of reduction of various economic crops in each year is immeasurable. The monitoring and forecasting of insect situations are the key for controlling insect pests, the monitoring and forecasting are accurate and timely, measures can be taken in advance to control the extended spread of the pests, and the loss is reduced.
The grassland pests have various types, wide distribution, quick propagation and large quantity, and not only directly cause the loss of grasslands, pastures and products thereof, but also are media for spreading the diseases of the grasslands and the pastures. The harmful insects mainly comprise harmful species of Insecta orthoptera, Hemiptera, Homoptera, Coleoptera, Lepidoptera, Diptera and the like. However, the grassland insect images acquired by the conventional grassland insect pest monitoring system based on unmanned aerial vehicle multispectral remote sensing are not clear; meanwhile, the grassland pests cannot be warned in time.
Through the above analysis, the problems and defects of the prior art are as follows: the grassland insect images acquired by the existing grassland insect pest monitoring system based on unmanned aerial vehicle multispectral remote sensing are not clear; meanwhile, the grassland pests cannot be warned in time.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a grassland insect pest monitoring system and method based on unmanned aerial vehicle multispectral remote sensing.
The invention is realized in such a way that a grassland insect pest monitoring method based on unmanned aerial vehicle multispectral remote sensing comprises the following steps:
acquiring a grassland insect image by using a spectrum remote sensing detector on an unmanned aerial vehicle through a remote sensing image acquisition module;
acquiring the ambient temperature and humidity data of the grassland by using a temperature and humidity sensor through a grassland temperature and humidity acquisition module;
thirdly, the main control module controls each module to work normally by using the main controller;
fourthly, performing flight operation by using the unmanned aerial vehicle through a flight module;
fifthly, enhancing the acquired image by using an image enhancement program through a remote sensing image enhancement module;
the method for enhancing the collected image by using the image enhancement program through the remote sensing image enhancement module comprises the following steps: acquiring grassland insect image data of a grassland insect image through a spectrum remote sensing detector on an unmanned aerial vehicle; calculating a histogram of the acquired grassland insect image data; respectively carrying out equalization processing and widening processing on the calculated histogram; synthesizing the histogram after the equalization treatment and the histogram after the broadening treatment to obtain an enhanced grassland insect image;
the equalizing and widening of the calculated histogram respectively includes:
introducing an equalization coefficient alpha and a broadening coefficient beta, wherein the value ranges of the equalization coefficient alpha and the broadening coefficient beta are [0, 1 ]; the values of the equalization coefficient alpha and the broadening coefficient beta can be determined through manual intervention, and can also be automatically determined according to the distribution of the histogram h; the values of the balance coefficient alpha and the broadening coefficient beta are automatically determined, specifically, the values of alpha and beta when the evaluation value H (alpha, beta) obtains the maximum value; the evaluation value H (alpha, beta) is a function of the quality Q of the processed grassland insect image and the contrast increment C of the processed grassland insect image;
combining a mathematical pattern g (x, y) of histogram equalization with a mathematical pattern E (x, y) of gray-scale stretching processing to perform histogram equalization processing and stretching processing;
the equalization processing specifically comprises: when equalization processing is performed, the range of the value of the equalization coefficient α is [0, a ], and a histogram after equalization adjustment processing is obtained by calculation and synthesis according to a formula G1(x, y) ═ α f (x, y)/a + (1- α/a) G (x, y);
when the broadening processing is performed, the range of the broadening coefficient beta value is [0, B ], and a histogram after linear broadening processing is obtained through calculation and synthesis according to a formula G2(x, y) ═ β f (x, y)/B + (1- β/B) e (x, y);
sixthly, extracting insect characteristic elements in the image by using an image characteristic extraction program through an image characteristic extraction module;
analyzing the insect attributes by using a pest analysis program through a pest analysis module;
step eight, early warning the quantity of the pests in the insects by using an early warning program through an early warning module; and the display is used for displaying the acquired grassland insect images, the grassland environment temperature and humidity, the analysis result and the early warning information through the display module.
Further, in step five, the values of the equalization coefficient α and the broadening coefficient β are automatically determined, specifically, the values of α and β when the evaluation value H (α, β) takes the maximum value include:
when the histogram of the processed grassland insect image is uniformly distributed, alpha is 0; when the histogram of the processed grassland insect image is absolutely unbalanced, alpha is 1; when the variance or the sharpness statistic of the histogram of the processed grassland insect image is minimum and is uniformly distributed, the beta is 1, and the beta value is reduced as the variance or the sharpness statistic of the histogram is increased.
Further, in the fifth step, the values of the equalization coefficient α and the broadening coefficient β are automatically determined according to the following formula:
α＝∑(h(i)–1/L)2/(2×(1-1/L))；
β＝1–exp(-∑(h(i)–average(h))4)；
when the difference ratio of h and the uniformly distributed histogram is small, namely when the grassland insect image has L gray levels, the occurrence frequency of each gray level is 1/L, alpha is a small value, otherwise, a value close to 1 is taken, namely the value of alpha is increased along with the increase of the difference value of h and the uniformly distributed histogram; when the sharpness of h distribution is larger, the expansion range is large, namely the value of beta is increased along with the increase of the sharpness of h.
Further, in step six, the extracting, by the image feature extracting module, insect feature elements in the image by using an image feature extracting program includes:
1) constructing an image feature extraction model based on a deep convolutional neural network;
2) training the image feature extraction model;
3) extracting image characteristic data of an image to be recognized by applying the trained image characteristic extraction model to obtain the image characteristic data of the image to be recognized;
4) and carrying out similarity analysis on the image characteristic data and the target characteristic data to obtain a recognition result.
Further, in step 2), the training of the image feature extraction model includes the following steps:
(1) carrying out convolution calculation on the image feature extraction model based on the deep convolution neural network layer by layer;
(2) under the condition that the image feature extraction model completes convolution calculation, classifying image feature data output by the last convolution layer of the image feature extraction model by using a classifier to obtain a classification result;
(3) determining whether to continue training or finish training according to the classification result;
(4) if the training is determined to be continued according to the classification result, optimizing the image feature extraction model by using an optimizer, taking the optimized image feature extraction model as a new image feature extraction model, and performing convolution calculation again;
(5) under the condition that the image feature extraction model completes convolution calculation, classifying image feature data output by the last convolution layer of the image feature extraction model by using a classifier to obtain a classification result;
(6) and determining whether to continue training or finish training according to the classification result until finishing training is determined according to the classification result to obtain a trained image feature extraction model.
Further, in the step (1), the image feature data of each input channel of at least one convolution layer in the image feature extraction model based on the deep convolutional neural network and the convolution kernel of each input channel are respectively subjected to convolution calculation, so as to obtain image feature data corresponding to each input channel of the next layer of the convolution layer.
Further, in step eight, utilize early warning program to carry out the early warning to the pest quantity in the insect through early warning module, include:
a, performing partitioned background reconstruction on an image or a video image of a grassland, and performing self-adaptive updating on the image background;
b, detecting the moving crop pests by using a background difference method, acquiring crop pest images, and acquiring insect images of the insect plate according to a preset acquisition frequency;
step C, determining the increase of pests in the insect image according to the insect image and a preset comparison image; and generating early warning information according to the early warning grade corresponding to the increase of the pests.
Further, in step B, the detecting the moving crop pests by using the background subtraction method, before obtaining the crop pest image according to the preset collection frequency, further includes:
and presetting a corresponding relation between the increase of the pests and the early warning grade.
Further, in step C, determining an increase of the pest in the insect image according to the insect image and a preset comparison image, includes:
when the insect image is collected for the first time, taking a blank image of the insect plate as the preset contrast image; generating a binary image of the insect image; performing image segmentation on the region with the gray value of 255 in the binary image to form a plurality of segmented regions; and counting the number of the plurality of segmentation areas to determine the number of the grassland pests in the insect image as the increase amount of the pests.
Another object of the present invention is to provide a grassland insect pest monitoring system based on unmanned aerial vehicle multispectral remote sensing for the grassland insect pest monitoring method based on unmanned aerial vehicle multispectral remote sensing, which comprises:
the remote sensing image acquisition module is connected with the main control module and used for acquiring grassland insect images through a spectrum remote sensing detector on the unmanned aerial vehicle;
the grassland temperature and humidity acquisition module is connected with the main control module and is used for acquiring the ambient temperature and humidity data of the grassland through a temperature and humidity sensor;
the main control module is connected with the remote sensing image acquisition module, the grassland temperature and humidity acquisition module, the flight module, the remote sensing image enhancement module, the image feature extraction module, the insect pest analysis module, the early warning module and the display module and is used for controlling each module to normally work through the main controller;
the flight module is connected with the main control module and used for carrying out flight operation through the unmanned aerial vehicle;
the remote sensing image enhancement module is connected with the main control module and is used for enhancing the acquired image through an image enhancement program;
the image feature extraction module is connected with the main control module and used for extracting insect feature elements in the image through an image feature extraction program;
the insect pest analysis module is connected with the main control module and used for analyzing the insect attributes through an insect pest analysis program;
the early warning module is connected with the main control module and is used for early warning the number of pests in the insects through an early warning program;
and the display module is connected with the main control module and used for displaying the acquired grassland insect images, the grassland environment temperature and humidity, the analysis result and the early warning information through the display.
The invention has the advantages and positive effects that: according to the invention, the balance coefficient alpha and the broadening coefficient beta are introduced through the remote sensing image enhancement module, and the gray scale range is linearly expanded while the histogram equalization is maintained, so that the purpose of flexibly controlling the image quality of the grassland insects is achieved, and the enhancement effect is good; meanwhile, the insect image of the insect plate is collected through the early warning module, the pest increment in the insect image is determined according to the insect image and the preset contrast image, the grassland pest quantity threshold range to which the pest increment belongs is determined, early warning information is further generated according to the grassland pest grade corresponding to the grassland pest quantity threshold range, and early warning can be carried out in time.
Drawings
Fig. 1 is a flow chart of a grassland insect pest monitoring method based on unmanned aerial vehicle multispectral remote sensing provided by the embodiment of the invention.
Fig. 2 is a flowchart of extracting insect feature elements in an image by an image feature extraction module using an image feature extraction program according to an embodiment of the present invention.
Fig. 3 is a flowchart of training an image feature extraction model according to an embodiment of the present invention.
Fig. 4 is a flowchart of warning the number of pests in the insect by using a warning program through a warning module according to an embodiment of the present invention.
Fig. 5 is a structural block diagram of the grassland insect pest monitoring system based on unmanned aerial vehicle multispectral remote sensing provided by the embodiment of the invention.
In fig. 5: 1. a remote sensing image acquisition module; 2. a grassland temperature and humidity acquisition module; 3. a main control module; 4. a flight module; 5. a remote sensing image enhancement module; 6. an image feature extraction module; 7. a pest analysis module; 8. an early warning module; 9. and a display module.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Aiming at the problems in the prior art, the invention provides a grassland insect pest monitoring system and method based on unmanned aerial vehicle multispectral remote sensing, and the invention is described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the grassland insect pest monitoring method based on unmanned aerial vehicle multispectral remote sensing provided by the embodiment of the invention comprises the following steps:
and S101, acquiring the grassland insect image by using a spectrum remote sensing detector on the unmanned aerial vehicle through a remote sensing image acquisition module.
And S102, acquiring the ambient temperature and humidity data of the grassland by utilizing a temperature and humidity sensor through a grassland temperature and humidity acquisition module.
And S103, controlling each module to normally work by the main control module and the main controller.
And S104, carrying out flying operation by using the unmanned aerial vehicle through the flying module.
And S105, enhancing the acquired image by using an image enhancement program through a remote sensing image enhancement module.
And S106, extracting insect characteristic elements in the image by using an image characteristic extraction program through an image characteristic extraction module.
And S107, analyzing the insect attributes by using a pest analysis program through a pest analysis module.
S108, early warning is carried out on the number of pests in the insects by an early warning program through an early warning module; and the display is used for displaying the acquired grassland insect images, the grassland environment temperature and humidity, the analysis result and the early warning information through the display module.
In step S105, the automatic determination of the values of the equalization coefficient α and the broadening coefficient β provided in the embodiment of the present invention, specifically, the values of α and β when the evaluation value H (α, β) takes the maximum value, includes:
when the histogram of the processed grassland insect image is uniformly distributed, alpha is 0; when the histogram of the processed grassland insect image is absolutely unbalanced, alpha is 1; when the variance or the sharpness statistic of the histogram of the processed grassland insect image is minimum and is uniformly distributed, the beta is 1, and the beta value is reduced as the variance or the sharpness statistic of the histogram is increased.
In step S105, the values of the equalization coefficient α and the broadening coefficient β provided in the embodiment of the present invention are automatically determined according to the following formula:
α＝∑(h(i)–1/L)2/(2×(1-1/L))；
β＝1–exp(-∑(h(i)–average(h))4)；
when the difference ratio of h and the uniformly distributed histogram is small, namely when the grassland insect image has L gray levels, the occurrence frequency of each gray level is 1/L, alpha is a small value, otherwise, a value close to 1 is taken, namely the value of alpha is increased along with the increase of the difference value of h and the uniformly distributed histogram; when the sharpness of h distribution is larger, the expansion range is large, namely the value of beta is increased along with the increase of the sharpness of h.
As shown in fig. 2, in step S106, the extracting, by the image feature extraction module, insect feature elements in the image by using the image feature extraction program according to the embodiment of the present invention includes:
s201, constructing an image feature extraction model based on a deep convolutional neural network.
S202, training the image feature extraction model.
And S203, extracting image characteristic data of the image to be recognized by applying the trained image characteristic extraction model to obtain the image characteristic data of the image to be recognized.
And S204, carrying out similarity analysis on the image characteristic data and the target characteristic data to obtain a recognition result.
As shown in fig. 3, in step S202, the training of the image feature extraction model provided in the embodiment of the present invention includes the following steps:
s301, carrying out convolution calculation on the image feature extraction model based on the deep convolution neural network layer by layer.
S302, under the condition that the image feature extraction model completes convolution calculation, a classifier is used for classifying the image feature data output by the last convolution layer of the image feature extraction model to obtain a classification result.
S303, determining whether to continue training or finish training according to the classification result.
S304, if the training is determined to be continued according to the classification result, the image feature extraction model is optimized by using an optimizer, the optimized image feature extraction model is used as a new image feature extraction model, and the convolution calculation is carried out again.
S305, under the condition that the image feature extraction model completes convolution calculation, a classifier is used for classifying the image feature data output by the last convolution layer of the image feature extraction model to obtain a classification result.
And S306, determining whether to continue training or finish training according to the classification result until finishing training is determined according to the classification result to obtain the trained image feature extraction model.
In step S301, in the image feature extraction model based on the deep convolutional neural network provided in the embodiment of the present invention, convolution calculation is performed on image feature data of each input channel of at least one convolutional layer and a convolution kernel of each input channel, so as to obtain image feature data corresponding to each input channel of a next layer of the convolutional layer.
As shown in fig. 4, in step S108, the early warning module for early warning the number of pests in the insect by using the early warning program according to the embodiment of the present invention includes:
s401, block background reconstruction is carried out on the image or the video image of the grassland, and self-adaptive updating is adopted on the image background.
S402, detecting the moving crop pests by using a background difference method, obtaining crop pest images, and collecting insect images of the insect plate according to a preset collecting frequency.
S403, determining the pest increment in the insect image according to the insect image and a preset comparison image; and generating early warning information according to the early warning grade corresponding to the increase of the pests.
In step S402, before detecting moving crop pests by using a background subtraction method and obtaining a crop pest image according to a preset collection frequency, the method further includes:
and presetting a corresponding relation between the increase of the pests and the early warning grade.
In step S403, determining an increase of pests in the insect image according to the insect image and a preset comparison image provided in the embodiment of the present invention includes:
when the insect image is collected for the first time, taking a blank image of the insect plate as the preset contrast image; generating a binary image of the insect image; performing image segmentation on the region with the gray value of 255 in the binary image to form a plurality of segmented regions; and counting the number of the plurality of segmentation areas to determine the number of the grassland pests in the insect image as the increase amount of the pests.
As shown in fig. 5, the grassland insect pest monitoring system based on unmanned aerial vehicle multispectral remote sensing provided by the embodiment of the invention comprises:
the remote sensing image acquisition module 1 is connected with the main control module 3 and is used for acquiring grassland insect images through a spectrum remote sensing detector on the unmanned aerial vehicle;
the grassland temperature and humidity acquisition module 2 is connected with the main control module 3 and is used for acquiring the ambient temperature and humidity data of the grassland through a temperature and humidity sensor;
the main control module 3 is connected with the remote sensing image acquisition module 1, the grassland temperature and humidity acquisition module 2, the flight module 4, the remote sensing image enhancement module 5, the image feature extraction module 6, the insect pest analysis module 7, the early warning module 8 and the display module 9 and is used for controlling each module to normally work through the main controller;
the flight module 4 is connected with the main control module 3 and used for carrying out flight operation through the unmanned aerial vehicle;
the remote sensing image enhancement module 5 is connected with the main control module 3 and is used for enhancing the acquired image through an image enhancement program;
the image feature extraction module 6 is connected with the main control module 3 and used for extracting insect feature elements in the image through an image feature extraction program;
the insect pest analysis module 7 is connected with the main control module 3 and used for analyzing the insect attributes through an insect pest analysis program;
the early warning module 8 is connected with the main control module 3 and is used for early warning the number of pests in the insects through an early warning program;
and the display module 9 is connected with the main control module 3 and used for displaying the acquired grassland insect images, the grassland environment temperature and humidity, the analysis result and the early warning information through a display.
When the system works, firstly, a remote sensing image acquisition module 1 is used for acquiring grassland insect images by utilizing a spectrum remote sensing detector on an unmanned aerial vehicle; the grassland temperature and humidity data are acquired by a grassland temperature and humidity acquisition module 2 by using a temperature and humidity sensor; secondly, the main control module 3 utilizes the unmanned aerial vehicle to carry out flight operation through the flight module 4; enhancing the acquired image by using an image enhancement program through a remote sensing image enhancement module 5; extracting insect characteristic elements in the image by using an extraction program through an image characteristic extraction module 6; insect attributes are analyzed by a pest analysis module 7 by using an analysis program; then, the number of pests in the insects is pre-warned by a pre-warning program through a pre-warning module 8; and finally, displaying the acquired grassland insect image, the grassland environment temperature and humidity, the analysis result and the early warning information by using a display through a display module 9.
In the description of the present invention, "a plurality" means two or more unless otherwise specified; the terms "upper", "lower", "left", "right", "inner", "outer", "front", "rear", "head", "tail", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are only for convenience in describing and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed in a particular orientation, and be operated, and thus, should not be construed as limiting the invention. Furthermore, the terms "first," "second," "third," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The above description is only for the purpose of illustrating the present invention and the appended claims are not to be construed as limiting the scope of the invention, which is intended to cover all modifications, equivalents and improvements that are within the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A grassland insect pest monitoring method based on unmanned aerial vehicle multispectral remote sensing is characterized by comprising the following steps:
acquiring a grassland insect image by using a spectrum remote sensing detector on an unmanned aerial vehicle through a remote sensing image acquisition module;
acquiring the ambient temperature and humidity data of the grassland by using a temperature and humidity sensor through a grassland temperature and humidity acquisition module;
thirdly, the main control module controls each module to work normally by using the main controller;
fourthly, performing flight operation by using the unmanned aerial vehicle through a flight module;
fifthly, enhancing the acquired image by using an image enhancement program through a remote sensing image enhancement module;
the method for enhancing the collected image by using the image enhancement program through the remote sensing image enhancement module comprises the following steps: acquiring grassland insect image data of a grassland insect image through a spectrum remote sensing detector on an unmanned aerial vehicle; calculating a histogram of the acquired grassland insect image data; respectively carrying out equalization processing and widening processing on the calculated histogram; synthesizing the histogram after the equalization treatment and the histogram after the broadening treatment to obtain an enhanced grassland insect image;
the equalizing and widening of the calculated histogram respectively includes:
introducing an equalization coefficient alpha and a broadening coefficient beta, wherein the value ranges of the equalization coefficient alpha and the broadening coefficient beta are [0, 1 ]; the values of the equalization coefficient alpha and the broadening coefficient beta can be determined through manual intervention, and can also be automatically determined according to the distribution of the histogram h; the values of the balance coefficient alpha and the broadening coefficient beta are automatically determined, specifically, the values of alpha and beta when the evaluation value H (alpha, beta) obtains the maximum value; the evaluation value H (alpha, beta) is a function of the quality Q of the processed grassland insect image and the contrast increment C of the processed grassland insect image;
combining a mathematical pattern g (x, y) of histogram equalization with a mathematical pattern E (x, y) of gray-scale stretching processing to perform histogram equalization processing and stretching processing;
the equalization processing specifically comprises: when equalization processing is performed, the range of the value of the equalization coefficient α is [0, a ], and a histogram after equalization adjustment processing is obtained by calculation and synthesis according to a formula G1(x, y) ═ α f (x, y)/a + (1- α/a) G (x, y);
when the broadening processing is performed, the range of the broadening coefficient beta value is [0, B ], and a histogram after linear broadening processing is obtained through calculation and synthesis according to a formula G2(x, y) ═ β f (x, y)/B + (1- β/B) e (x, y);
sixthly, extracting insect characteristic elements in the image by using an image characteristic extraction program through an image characteristic extraction module;
analyzing the insect attributes by using a pest analysis program through a pest analysis module;
step eight, early warning the quantity of the pests in the insects by using an early warning program through an early warning module; and the display is used for displaying the acquired grassland insect images, the grassland environment temperature and humidity, the analysis result and the early warning information through the display module.
2. The method for monitoring insect pests in grasslands based on multispectral remote sensing of unmanned aerial vehicles according to claim 1, wherein in the fifth step, values of the equilibrium coefficient α and the broadening coefficient β are automatically determined, specifically, values of α and β when the evaluation value H (α, β) reaches a maximum value include:
when the histogram of the processed grassland insect image is uniformly distributed, alpha is 0; when the histogram of the processed grassland insect image is absolutely unbalanced, alpha is 1; when the variance or the sharpness statistic of the histogram of the processed grassland insect image is minimum and is uniformly distributed, the beta is 1, and the beta value is reduced as the variance or the sharpness statistic of the histogram is increased.
3. The grassland insect pest monitoring method based on unmanned aerial vehicle multispectral remote sensing as claimed in claim 1, wherein in step five, the values of the equilibrium coefficient α and the broadening coefficient β are automatically determined according to the following formula:
α＝∑(h(i)–1/L)2/(2×(1-1/L))；
β＝1–exp(-∑(h(i)–average(h))4)；
when the difference ratio of h and the uniformly distributed histogram is small, namely when the grassland insect image has L gray levels, the occurrence frequency of each gray level is 1/L, alpha is a small value, otherwise, a value close to 1 is taken, namely the value of alpha is increased along with the increase of the difference value of h and the uniformly distributed histogram; when the sharpness of h distribution is larger, the expansion range is large, namely the value of beta is increased along with the increase of the sharpness of h.
4. The method for monitoring insect pests in grasslands based on multispectral remote sensing of unmanned aerial vehicles according to claim 1, wherein in step six, the extracting of the insect feature elements in the image by the image feature extraction module by using an image feature extraction program comprises:
1) constructing an image feature extraction model based on a deep convolutional neural network;
2) training the image feature extraction model;
3) extracting image characteristic data of an image to be recognized by applying the trained image characteristic extraction model to obtain the image characteristic data of the image to be recognized;
4) and carrying out similarity analysis on the image characteristic data and the target characteristic data to obtain a recognition result.
5. The grassland insect pest monitoring method based on unmanned aerial vehicle multispectral remote sensing as claimed in claim 4, wherein in the step 2), the training of the image feature extraction model comprises the following steps:
(1) carrying out convolution calculation on the image feature extraction model based on the deep convolution neural network layer by layer;
(2) under the condition that the image feature extraction model completes convolution calculation, classifying image feature data output by the last convolution layer of the image feature extraction model by using a classifier to obtain a classification result;
(3) determining whether to continue training or finish training according to the classification result;
(4) if the training is determined to be continued according to the classification result, optimizing the image feature extraction model by using an optimizer, taking the optimized image feature extraction model as a new image feature extraction model, and performing convolution calculation again;
(5) under the condition that the image feature extraction model completes convolution calculation, classifying image feature data output by the last convolution layer of the image feature extraction model by using a classifier to obtain a classification result;
(6) and determining whether to continue training or finish training according to the classification result until finishing training is determined according to the classification result to obtain a trained image feature extraction model.
6. The method for monitoring insect pests in grassland based on unmanned aerial vehicle multispectral remote sensing as claimed in claim 5, wherein in step (1), the image feature data of each input channel of at least one convolution layer in the image feature extraction model based on the deep convolutional neural network and the convolution kernel of each input channel are respectively subjected to convolution calculation to obtain the image feature data corresponding to each input channel of the next layer of the convolution layer.
7. The method for monitoring insect pests in grasslands based on multispectral remote sensing of unmanned aerial vehicles according to claim 1, wherein in step eight, the early warning of the quantity of the pests in the insects by the early warning module through an early warning program comprises the following steps:
a, performing partitioned background reconstruction on an image or a video image of a grassland, and performing self-adaptive updating on the image background;
b, detecting the moving crop pests by using a background difference method, acquiring crop pest images, and acquiring insect images of the insect plate according to a preset acquisition frequency;
step C, determining the increase of pests in the insect image according to the insect image and a preset comparison image; and generating early warning information according to the early warning grade corresponding to the increase of the pests.
8. The method for monitoring insect pests in grasslands based on multispectral remote sensing of unmanned aerial vehicles according to claim 7, wherein in the step B, the step of detecting the moving crop pests by using a background subtraction method to obtain the crop pest image further comprises the following steps of:
and presetting a corresponding relation between the increase of the pests and the early warning grade.
9. The method for monitoring insect pests in grasslands based on multispectral remote sensing of unmanned aerial vehicles according to claim 7, wherein in the step C, determining the increase of the pests in the insect image according to the insect image and a preset comparison image comprises:
when the insect image is collected for the first time, taking a blank image of the insect plate as the preset contrast image; generating a binary image of the insect image; performing image segmentation on the region with the gray value of 255 in the binary image to form a plurality of segmented regions; and counting the number of the plurality of segmentation areas to determine the number of the grassland pests in the insect image as the increase amount of the pests.
10. An unmanned aerial vehicle multispectral remote sensing-based grassland insect pest monitoring system applying the unmanned aerial vehicle multispectral remote sensing-based grassland insect pest monitoring method of claims 1-9, wherein the unmanned aerial vehicle multispectral remote sensing-based grassland insect pest monitoring system comprises:
the remote sensing image acquisition module is connected with the main control module and used for acquiring grassland insect images through a spectrum remote sensing detector on the unmanned aerial vehicle;
the grassland temperature and humidity acquisition module is connected with the main control module and is used for acquiring the ambient temperature and humidity data of the grassland through a temperature and humidity sensor;
the main control module is connected with the remote sensing image acquisition module, the grassland temperature and humidity acquisition module, the flight module, the remote sensing image enhancement module, the image feature extraction module, the insect pest analysis module, the early warning module and the display module and is used for controlling each module to normally work through the main controller;
the flight module is connected with the main control module and used for carrying out flight operation through the unmanned aerial vehicle;
the remote sensing image enhancement module is connected with the main control module and is used for enhancing the acquired image through an image enhancement program;
the image feature extraction module is connected with the main control module and used for extracting insect feature elements in the image through an image feature extraction program;
the insect pest analysis module is connected with the main control module and used for analyzing the insect attributes through an insect pest analysis program;
the early warning module is connected with the main control module and is used for early warning the number of pests in the insects through an early warning program;
and the display module is connected with the main control module and used for displaying the acquired grassland insect images, the grassland environment temperature and humidity, the analysis result and the early warning information through the display.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010907338.0A CN111985445B (en) | 2020-09-02 | 2020-09-02 | Grassland insect pest monitoring system and method based on unmanned aerial vehicle multispectral remote sensing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010907338.0A CN111985445B (en) | 2020-09-02 | 2020-09-02 | Grassland insect pest monitoring system and method based on unmanned aerial vehicle multispectral remote sensing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111985445A true CN111985445A (en) | 2020-11-24 |
| CN111985445B CN111985445B (en) | 2023-05-30 |
Family
ID=73446814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010907338.0A Active CN111985445B (en) | 2020-09-02 | 2020-09-02 | Grassland insect pest monitoring system and method based on unmanned aerial vehicle multispectral remote sensing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111985445B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113189015A (en) * | 2021-04-23 | 2021-07-30 | 宿州学院 | Hyperspectral remote sensing-based insect pest monitoring system and method |
| CN113378700A (en) * | 2021-06-08 | 2021-09-10 | 四川农业大学 | Grassland rat damage dynamic monitoring method based on unmanned aerial vehicle aerial image |
| CN115879773A (en) * | 2023-02-22 | 2023-03-31 | 广东省农业科学院植物保护研究所 | Intelligent pest and disease early warning method and system based on Internet of things |
| CN116029430A (en) * | 2022-12-27 | 2023-04-28 | 江苏师范大学科文学院 | Grassland ecological environment monitoring system based on aerial image |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102750684A (en) * | 2012-06-07 | 2012-10-24 | 邝君 | Method, program and device for image enhancement |
| CN104881865A (en) * | 2015-04-29 | 2015-09-02 | 北京林业大学 | Forest disease and pest monitoring and early warning method and system based on unmanned plane image analysis |
| CN106650750A (en) * | 2016-11-21 | 2017-05-10 | 云南电网有限责任公司电力科学研究院 | UAV remote sensing image processing system for transmission line geological hazard detection |
| CN111460990A (en) * | 2020-03-31 | 2020-07-28 | 青海省草原总站 | Big data-based alpine pastoral area grassland insect pest monitoring and early warning system and method |
-
2020
- 2020-09-02 CN CN202010907338.0A patent/CN111985445B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102750684A (en) * | 2012-06-07 | 2012-10-24 | 邝君 | Method, program and device for image enhancement |
| CN104881865A (en) * | 2015-04-29 | 2015-09-02 | 北京林业大学 | Forest disease and pest monitoring and early warning method and system based on unmanned plane image analysis |
| CN106650750A (en) * | 2016-11-21 | 2017-05-10 | 云南电网有限责任公司电力科学研究院 | UAV remote sensing image processing system for transmission line geological hazard detection |
| CN111460990A (en) * | 2020-03-31 | 2020-07-28 | 青海省草原总站 | Big data-based alpine pastoral area grassland insect pest monitoring and early warning system and method |
Non-Patent Citations (1)
| Title |
|---|
| 李风贤;: "无人机技术在草原生态遥感监测中的应用与探讨", 测绘通报 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113189015A (en) * | 2021-04-23 | 2021-07-30 | 宿州学院 | Hyperspectral remote sensing-based insect pest monitoring system and method |
| CN113378700A (en) * | 2021-06-08 | 2021-09-10 | 四川农业大学 | Grassland rat damage dynamic monitoring method based on unmanned aerial vehicle aerial image |
| CN116029430A (en) * | 2022-12-27 | 2023-04-28 | 江苏师范大学科文学院 | Grassland ecological environment monitoring system based on aerial image |
| CN115879773A (en) * | 2023-02-22 | 2023-03-31 | 广东省农业科学院植物保护研究所 | Intelligent pest and disease early warning method and system based on Internet of things |
| CN115879773B (en) * | 2023-02-22 | 2023-05-16 | 广东省农业科学院植物保护研究所 | Intelligent disease and pest early warning method and system based on Internet of things |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111985445B (en) | 2023-05-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111985445A (en) | Grassland insect pest monitoring system and method based on unmanned aerial vehicle multispectral remote sensing | |
| US11334983B2 (en) | Anomaly detection | |
| CN108537215B (en) | Flame detection method based on image target detection | |
| CN116092018B (en) | Fire-fighting hidden danger monitoring method and system based on intelligent building | |
| CN104050478A (en) | Smog detection method and system | |
| CN112329569B (en) | Freight vehicle state real-time identification method based on image deep learning system | |
| CN111274926B (en) | Image data screening method, device, computer equipment and storage medium | |
| CN110363246A (en) | A kind of fusion method of high-spatial and temporal resolution vegetation index NDVI | |
| CN112419202B (en) | Automatic wild animal image recognition system based on big data and deep learning | |
| CN110929944A (en) | Wheat scab disease severity prediction method based on hyperspectral image and spectral feature fusion technology | |
| CN109684986B (en) | Vehicle analysis method and system based on vehicle detection and tracking | |
| CN111724566A (en) | Pedestrian falling detection method and device based on intelligent lamp pole video monitoring system | |
| CN116386120A (en) | Noninductive monitoring management system | |
| CN116258956A (en) | Unmanned aerial vehicle tree recognition method, unmanned aerial vehicle tree recognition equipment, storage medium and unmanned aerial vehicle tree recognition device | |
| CN116448760A (en) | Agricultural intelligent monitoring system and method based on machine vision | |
| CN115330833A (en) | Fruit yield estimation method with improved multi-target tracking | |
| CN111695561A (en) | License plate detection and correction recognition method and recognition system based on SSD | |
| CN114596509A (en) | Machine vision-based rice seedling leaf age period identification method | |
| CN114119551A (en) | Quantitative analysis method for human face image quality | |
| CN116630815B (en) | Intelligent agricultural pest detection method | |
| CN114973104A (en) | Dynamic flame detection algorithm and system based on video image | |
| CN114022831A (en) | Binocular vision-based livestock body condition monitoring method and system | |
| CN110427961B (en) | Building information extraction method and system based on rule and sample fusion | |
| CN111967424A (en) | Buckwheat disease identification method based on convolutional neural network | |
| CN113705672A (en) | Threshold value selection method, system and device for image target detection and storage medium |
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 |