CN115294486B - Method for identifying and judging illegal garbage based on unmanned aerial vehicle and artificial intelligence - Google Patents

Method for identifying and judging illegal garbage based on unmanned aerial vehicle and artificial intelligence Download PDF

Info

Publication number
CN115294486B
CN115294486B CN202211219087.2A CN202211219087A CN115294486B CN 115294486 B CN115294486 B CN 115294486B CN 202211219087 A CN202211219087 A CN 202211219087A CN 115294486 B CN115294486 B CN 115294486B
Authority
CN
China
Prior art keywords
artificial intelligence
unmanned aerial
aerial vehicle
image
substances
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
Application number
CN202211219087.2A
Other languages
Chinese (zh)
Other versions
CN115294486A (en
Inventor
陈钢
刘攀
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Byte Technology Qingdao Co Ltd
Original Assignee
Byte Technology Qingdao Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Byte Technology Qingdao Co Ltd filed Critical Byte Technology Qingdao Co Ltd
Priority to CN202211219087.2A priority Critical patent/CN115294486B/en
Publication of CN115294486A publication Critical patent/CN115294486A/en
Application granted granted Critical
Publication of CN115294486B publication Critical patent/CN115294486B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06V20/17—Terrestrial scenes taken from planes or by drones
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Remote Sensing (AREA)
  • Image Analysis (AREA)

Abstract

The invention relates to the technical field of image processing, in particular to a violation garbage identification and judgment method based on an unmanned aerial vehicle and artificial intelligence, which comprises the following steps: collecting a high-definition video by an unmanned aerial vehicle; performing interframe difference processing on a high-definition video acquired by an unmanned aerial vehicle to acquire an effective high-definition picture; transmitting the obtained high-definition picture to a ground workstation by a 5G technology, and further preprocessing the picture; and (4) calculating the preprocessed pictures through an artificial intelligence algorithm, and further realizing the identification and judgment of the garbage. According to the invention, the image data is acquired by the unmanned aerial vehicle, and by improving the frame difference algorithm and expanding the target with slow frame difference detection change, useless or repeated pictures can be obtained and discarded by effective high-definition pictures, so that the 5G transmission speed and the detection efficiency of the artificial intelligence algorithm are further improved; the garbage data image is combined with an artificial intelligence algorithm to realize automatic recognition and judgment of garbage.

Description

Method for identifying and judging illegal garbage based on unmanned aerial vehicle and artificial intelligence
Technical Field
The invention relates to the technical field of image processing, in particular to a violation garbage identification and judgment method based on an unmanned aerial vehicle and artificial intelligence.
Background
In the past, informatization technology is not common, and the illegal building management department usually adopts a manual inspection means to manually find rubbish. In recent years, a method for performing remote monitoring by using a camera is also presented for monitoring nearby the illegal buildings, but the method has some defects, such as dead monitoring corners, large capital investment and the like. Although the methods can be used for collecting the garbage images, the garbage identification and judgment are mainly carried out in a manual identification mode, when the number of the obtained images is large or the image range is large, huge workload can be generated in the manual identification mode, and meanwhile, the identification efficiency is relatively low. And the current technologies such as intelligent identification and automatic feature extraction are still in the research stage and cannot be widely applied, so that the unmanned aerial vehicle inspection effect is greatly reduced. .
Disclosure of Invention
The invention aims to solve the defects in the background technology by providing a violation garbage identification and judgment method based on an unmanned aerial vehicle and artificial intelligence.
The technical scheme adopted by the invention is as follows:
the method for identifying and judging the illegal garbage based on the unmanned aerial vehicle and the artificial intelligence comprises the following steps:
s1.1: collecting a high-definition video by an unmanned aerial vehicle;
s1.2: performing interframe difference processing on the high-definition video acquired by the unmanned aerial vehicle to acquire an effective high-definition picture;
s1.3: transmitting the obtained high-definition pictures to a ground workstation by a 5G technology, and further preprocessing the pictures;
s1.4: and (4) carrying out operation on the preprocessed pictures through an artificial intelligence algorithm, and further realizing the identification and judgment of the garbage.
As a preferred technical scheme of the invention: in the step S1.2, an improved inter-frame difference method is adopted for inter-frame difference processing, and the improved inter-frame difference method performs difference operation on images of a current frame and previous and next frames by using three frames of image information.
As a preferred technical scheme of the invention: the improved interframe difference method formula is as follows:
Figure 649777DEST_PATH_IMAGE001
；
Figure 629234DEST_PATH_IMAGE002
and
Figure 471288DEST_PATH_IMAGE003
the images are respectively the difference between the front frame and the back frame and the current frame,
Figure 928814DEST_PATH_IMAGE004
and
Figure 805503DEST_PATH_IMAGE005
、
Figure 696142DEST_PATH_IMAGE006
the gray values of the image at time t, time t-1 and time t +1 respectively,
Figure 759913DEST_PATH_IMAGE007
is a coefficient of gray scale to be used,
Figure 21130DEST_PATH_IMAGE008
is the total number of pixels of the region to be detected,
Figure 549063DEST_PATH_IMAGE009
an image to be detected is obtained;
and then, performing binarization processing on the frame difference image obtained by threshold T processing:
Figure 604744DEST_PATH_IMAGE010
；
wherein the content of the first and second substances,
Figure 155811DEST_PATH_IMAGE011
or
Figure 955140DEST_PATH_IMAGE012
，
Figure 212946DEST_PATH_IMAGE013
Or both results are obtained by binarization.
As a preferred technical scheme of the invention: in the S1.3, the preprocessing method comprises image gray processing, color inversion and a canny edge detection algorithm;
the picture gray level processing formula is as follows:
Figure 705107DEST_PATH_IMAGE014
；
wherein the content of the first and second substances,
Figure 9049DEST_PATH_IMAGE015
、
Figure 346490DEST_PATH_IMAGE016
and
Figure 786699DEST_PATH_IMAGE017
respectively representing components of red, green and blue colors, and solving the average value of the three components of the color image to obtain a gray value;
the color inversion formula is as follows:
Figure 184182DEST_PATH_IMAGE018
；
wherein the content of the first and second substances,
Figure 772158DEST_PATH_IMAGE019
for the value of the current pixel, it is,
Figure 913289DEST_PATH_IMAGE020
is the pixel value after color inversion;
the canny edge detection algorithm is as follows:
Figure 208004DEST_PATH_IMAGE021
；
Figure 41968DEST_PATH_IMAGE022
is the standard deviation of the Gaussian distribution,
Figure 727027DEST_PATH_IMAGE023
the pixel points are set;
multiplying each pixel point and the neighborhood thereof by a Gaussian matrix, and taking the weighted average value as the final gray value:
Figure 665990DEST_PATH_IMAGE024
；
Figure 80791DEST_PATH_IMAGE025
；
wherein the content of the first and second substances,
Figure 820077DEST_PATH_IMAGE026
in order to be the amplitude value,
Figure 320329DEST_PATH_IMAGE027
in the form of a direction of rotation,
Figure 600000DEST_PATH_IMAGE028
and
Figure 134887DEST_PATH_IMAGE029
respectively the image at a pixel point
Figure 45074DEST_PATH_IMAGE030
Horizontal gradient magnitude and vertical gradient magnitude.
As a preferred technical scheme of the invention: after the canny edge detection algorithm is detected, calculating a gradient value and a gradient direction through a sobel operator, and filtering out a maximum value; eight gradient directions are set, including:
Figure 32621DEST_PATH_IMAGE031
；
and setting a threshold value:
Figure 991350DEST_PATH_IMAGE032
；
wherein the content of the first and second substances,
Figure 115164DEST_PATH_IMAGE033
gray values of all points to be measured;
and filtering the noise according to the image definition evaluation value:
Figure 461832DEST_PATH_IMAGE034
；
wherein the content of the first and second substances,
Figure 671096DEST_PATH_IMAGE035
is effective.
As a preferred technical scheme of the invention: in S1.4, the artificial intelligence algorithm includes: image input, basic feature extraction, multi-layer complex feature extraction, feature learning and classification detection results; the method comprises the steps of carrying out convolution calculation on an image, outputting a classification result by a Softmax classifier through a pooling layer, an activation function and a full connection layer, and realizing the identification and judgment of garbage.
As a preferred technical scheme of the invention: the convolution calculation is that a small matrix slides on an image or an input characteristic diagram, the output classification result is obtained by multiplication and addition of the matrix, and the calculation method is as follows:
Figure 558150DEST_PATH_IMAGE036
；
wherein the content of the first and second substances,
Figure 802049DEST_PATH_IMAGE037
is the number of convolution kernel channels, sum is the matrix addition operator,bin order to be a characteristic parameter of the device,
performing aggregation statistics through the features of different positions, and selecting a representative value to represent the original feature; by adopting the maxporoling method, the calculation formula is as follows:
Figure 788460DEST_PATH_IMAGE038
；
wherein the content of the first and second substances,
Figure 750599DEST_PATH_IMAGE039
characteristic values of different positions.
Introducing an activation function relu function into the neural network, wherein the calculation formula is as follows:
Figure 51131DEST_PATH_IMAGE040
；
wherein x is a characteristic value used for improving the characterization capability of the artificial intelligence algorithm.
As a preferred technical scheme of the invention: the convolution layer, the pooling layer and the activation function structure map original data to a feature vector space, and the full connection layer is obtained by a calculation formula:
Figure 415116DEST_PATH_IMAGE041
；
wherein the content of the first and second substances,
Figure 578287DEST_PATH_IMAGE042
for the mapped feature samples, the learned distributed features are integrated and summarized and then mapped to a sample label space.
As a preferred technical scheme of the invention: softmax maps the feature vectors of the input neural network to (0,1) space, the sum of these values is 1, and the maximum probability value is selected as the classification result:
Figure 27723DEST_PATH_IMAGE043
；
wherein, the first and the second end of the pipe are connected with each other,
Figure 256579DEST_PATH_IMAGE044
is a classification vector.
As a preferred technical scheme of the invention: and after the artificial intelligence algorithm is processed, performing garbage detection, and summarizing detection results to terminal equipment for visual display and information storage.
Compared with the prior art, the violation garbage identification and judgment method based on the unmanned aerial vehicle and the artificial intelligence has the beneficial effects that:
according to the invention, the unmanned aerial vehicle is used for acquiring image data, and by improving the frame difference algorithm and expanding the target with slow frame difference detection change, useless or repeated pictures discarded by effective high-definition pictures can be obtained, and the 5G transmission speed and the detection efficiency of the artificial intelligence algorithm are further improved; the garbage data image is combined with an artificial intelligence algorithm to realize automatic recognition and judgment of garbage. The unmanned aerial photography technology is used for photography, and a remote sensing platform which is convenient to operate and easy to transition is provided for aerial photography. The take-off and landing are less limited by the field, and the landing can be carried out on playgrounds, highways or other wider ground, so that the stability and the safety are good, and the transition is very easy.
Drawings
FIG. 1 is a flow chart of a method of a preferred embodiment of the present invention;
fig. 2 is a technical structural view of a preferred embodiment of the present invention.
Detailed Description
It should be noted that, in the case of no conflict, the embodiments and the features in the embodiments may be combined with each other, and the technical solution 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. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the preferred embodiment of the present invention provides a violation garbage identification and determination method based on unmanned aerial vehicles and artificial intelligence, which comprises the following steps:
s1.1: collecting a high-definition video by an unmanned aerial vehicle;
s1.2: performing interframe difference processing on a high-definition video acquired by an unmanned aerial vehicle to acquire an effective high-definition picture;
s1.3: transmitting the obtained high-definition picture to a ground workstation by a 5G technology, and further preprocessing the picture;
s1.4: and (4) calculating the preprocessed pictures through an artificial intelligence algorithm, and further realizing the identification and judgment of the garbage.
In the step S1.2, an improved inter-frame difference method is adopted for inter-frame difference processing, and the improved inter-frame difference method performs difference operation on images of a current frame and previous and next frames by using three frames of image information.
The improved interframe difference method formula is as follows:
Figure 209492DEST_PATH_IMAGE045
；
Figure 68863DEST_PATH_IMAGE046
and
Figure 474437DEST_PATH_IMAGE047
the images are respectively the difference between the front frame and the back frame and the current frame,
Figure 710246DEST_PATH_IMAGE004
and
Figure 455348DEST_PATH_IMAGE005
、
Figure 485621DEST_PATH_IMAGE006
the gray values of the image at time t, time t-1 and time t +1 respectively,
Figure 644070DEST_PATH_IMAGE007
is a coefficient of gray scale to be used,
Figure 152412DEST_PATH_IMAGE008
is the total number of pixels of the region to be detected,
Figure 79916DEST_PATH_IMAGE009
an image to be detected is obtained;
and then, performing binarization processing on the frame difference image obtained by threshold T processing:
Figure 77828DEST_PATH_IMAGE048
；
wherein the content of the first and second substances,
Figure 457994DEST_PATH_IMAGE011
or
Figure 770027DEST_PATH_IMAGE012
，
Figure 817617DEST_PATH_IMAGE013
Or all areThe result obtained is binarized.
In the S1.3, the preprocessing method comprises image gray processing, color inversion and a canny edge detection algorithm;
the picture gray level processing formula is as follows:
Figure 861796DEST_PATH_IMAGE049
wherein the content of the first and second substances,
Figure 994838DEST_PATH_IMAGE015
、
Figure 940639DEST_PATH_IMAGE016
and
Figure 577157DEST_PATH_IMAGE017
respectively representing components of red, green and blue colors, and solving the average value of the three components of the color image to obtain a gray value;
the color inversion formula is as follows:
Figure 120134DEST_PATH_IMAGE050
；
wherein the content of the first and second substances,
Figure 271629DEST_PATH_IMAGE019
it is the current value of the pixel that is being displayed,
Figure 191044DEST_PATH_IMAGE051
the pixel values after color inversion;
the canny edge detection algorithm is as follows:
Figure 682068DEST_PATH_IMAGE052
；
wherein the content of the first and second substances,
Figure 395946DEST_PATH_IMAGE053
is the standard deviation of the Gaussian distribution,
Figure 503579DEST_PATH_IMAGE030
is a pixel point;
multiplying each pixel point and the neighborhood thereof by a Gaussian matrix, and taking the weighted average value as the final gray value:
Figure 633209DEST_PATH_IMAGE054
；
Figure 244319DEST_PATH_IMAGE055
；
wherein the content of the first and second substances,
Figure 129099DEST_PATH_IMAGE026
is the amplitude of the received signal and is,
Figure 458449DEST_PATH_IMAGE027
in the form of a direction of rotation,
Figure 516404DEST_PATH_IMAGE028
and
Figure 982020DEST_PATH_IMAGE029
respectively the image at a pixel point
Figure 37701DEST_PATH_IMAGE030
Horizontal gradient magnitude and vertical gradient magnitude.
After the canny edge detection algorithm is detected, calculating a gradient value and a gradient direction through a sobel operator, and filtering out a maximum value; setting eight gradient directions, including:
Figure 854347DEST_PATH_IMAGE031
；
and setting a threshold value:
Figure 653676DEST_PATH_IMAGE056
；
wherein the content of the first and second substances,
Figure 245237DEST_PATH_IMAGE057
gray values of all points to be measured;
and filtering the noise according to the image definition evaluation value:
Figure 737399DEST_PATH_IMAGE058
；
wherein the content of the first and second substances,
Figure 447866DEST_PATH_IMAGE059
is effective.
In S1.4, the artificial intelligence algorithm includes: image input, basic feature extraction, multi-layer complex feature extraction, feature learning and classification detection results; the method comprises the steps of carrying out convolution calculation on an image, outputting a classification result by a Softmax classifier through a pooling layer, an activation function and a full connection layer, and realizing the identification and judgment of the garbage.
The convolution calculation is that a small matrix slides on an image or an input characteristic diagram, the output classification result is a result obtained by matrix multiplication and addition, and the calculation method comprises the following steps:
Figure 50885DEST_PATH_IMAGE060
；
wherein the content of the first and second substances,
Figure 756673DEST_PATH_IMAGE061
is the number of convolution kernel channels, sum is the matrix addition operator,bin order to be a characteristic parameter of the device,
performing aggregation statistics through the features of different positions, and selecting a representative value to represent the original feature; by adopting the maxporoling method, the calculation formula is as follows:
Figure 888577DEST_PATH_IMAGE062
；
wherein the content of the first and second substances,
Figure 679816DEST_PATH_IMAGE063
characteristic values of different positions.
Introducing an activation function relu function into the neural network, wherein the calculation formula is as follows:
Figure 617685DEST_PATH_IMAGE064
；
wherein x is a characteristic value used for improving the characterization capability of the artificial intelligence algorithm.
Mapping the original data to a characteristic vector space by the convolution layer, the pooling layer and the activation function structure, wherein the full connection layer is obtained by the calculation formula:
Figure 177979DEST_PATH_IMAGE065
；
wherein the content of the first and second substances,
Figure 480784DEST_PATH_IMAGE066
for the mapped feature samples, the learned distributed features are integrated and summarized and then mapped to a sample label space.
Softmax maps the input feature vectors of the neural network to (0,1) space, and the sum of these values is 1, selecting the maximum probability value as the classification result:
Figure 759319DEST_PATH_IMAGE067
；
wherein the content of the first and second substances,
Figure 376245DEST_PATH_IMAGE068
is a classification vector.
And after the artificial intelligence algorithm is processed, performing garbage detection, and summarizing detection results to terminal equipment for visual display and information storage.
In this embodiment, referring to fig. 2, the garbage data identification algorithm based on the unmanned aerial vehicle and the artificial intelligence mainly comprises three parts: unmanned aerial vehicle, 5G technology, artificial intelligence algorithm. The artificial intelligence algorithm comprises image input, basic feature extraction, multi-layer complex feature extraction, feature learning and classification detection results.
The unmanned aerial vehicle plays a role in collecting high-definition videos, interframe difference processing is carried out on the videos, effective high-definition pictures are obtained, useless or repeated pictures are abandoned, and the 5G transmission speed and the detection efficiency of an artificial intelligence algorithm are further improved. The implementation principle mathematical formula of the interframe difference method is expressed as follows:
Figure 791046DEST_PATH_IMAGE069
；
wherein the content of the first and second substances,
Figure 795911DEST_PATH_IMAGE070
is a difference image between two successive frame images,
Figure 30583DEST_PATH_IMAGE071
and
Figure 513517DEST_PATH_IMAGE072
are respectively as
Figure 845141DEST_PATH_IMAGE073
And
Figure 489749DEST_PATH_IMAGE074
the image of the moment in time,
Figure 471438DEST_PATH_IMAGE075
the threshold value selected during the binarization of the differential image,
Figure 758062DEST_PATH_IMAGE076
the representation of the foreground is performed,
Figure 819559DEST_PATH_IMAGE077
representing the background.
The method is characterized in that an inter-frame difference method is improved, and a target with slow change is detected by expanding a frame difference, wherein the improved inter-frame difference method utilizes three frames of image information and carries out difference operation on images of a current frame and a front frame and a rear frame.
The improved interframe difference method formula is as follows:
Figure 900648DEST_PATH_IMAGE078
；
Figure 375491DEST_PATH_IMAGE046
and
Figure 200228DEST_PATH_IMAGE047
the images are respectively the difference between the front frame and the back frame and the current frame,
Figure 240865DEST_PATH_IMAGE004
and
Figure 758434DEST_PATH_IMAGE005
、
Figure 454995DEST_PATH_IMAGE006
the gray values of the image at the time t, the time t-1 and the time t +1 respectively,
Figure 83422DEST_PATH_IMAGE007
is a coefficient of gray scale to be used,
Figure 181828DEST_PATH_IMAGE008
is the total number of pixels of the region to be detected,
Figure 542402DEST_PATH_IMAGE009
an image to be detected is obtained;
and then, performing binarization processing on the frame difference image obtained by threshold T processing:
Figure 991838DEST_PATH_IMAGE079
；
wherein the content of the first and second substances,
Figure 486274DEST_PATH_IMAGE011
or
Figure 376869DEST_PATH_IMAGE012
，
Figure 236241DEST_PATH_IMAGE013
Or both results are obtained by binarization.
And transmitting the image processed by the interframe difference method to a ground workstation by using a 5G technology, and further preprocessing the image, wherein the preprocessing method comprises image gray processing, color inversion and canny edge detection.
The mathematical expression formula of the picture gray processing is as follows:
Figure 641814DEST_PATH_IMAGE080
；
wherein the content of the first and second substances,
Figure 877624DEST_PATH_IMAGE015
、
Figure 956481DEST_PATH_IMAGE016
and
Figure 783492DEST_PATH_IMAGE017
the three components respectively represent red, green and blue components, and the three component brightness in the color image is averaged to obtain a gray value.
The color inversion mathematical expression is as follows:
Figure 941941DEST_PATH_IMAGE081
；
wherein the content of the first and second substances,
Figure 184703DEST_PATH_IMAGE019
for the value of the current pixel, it is,
Figure 377787DEST_PATH_IMAGE051
is the pixel value after color inversion; the inverted pixel value is equal to 255 minus the current pixel value.
The mathematical expression for canny edge detection is as follows:
Figure 251065DEST_PATH_IMAGE082
wherein the content of the first and second substances,
Figure 896810DEST_PATH_IMAGE053
is the standard deviation of the Gaussian distribution,
Figure 208843DEST_PATH_IMAGE030
for pixel points, multiplying each pixel point and the neighborhood thereof by a Gaussian matrix, and taking the weighted average value as the final gray value:
Figure 990854DEST_PATH_IMAGE083
；
Figure 362929DEST_PATH_IMAGE084
；
wherein the content of the first and second substances,
Figure 292708DEST_PATH_IMAGE026
in order to be the amplitude value,
Figure 408432DEST_PATH_IMAGE027
in the form of a direction of rotation,
Figure 310529DEST_PATH_IMAGE028
and
Figure 853505DEST_PATH_IMAGE029
respectively the image at a pixel point
Figure 208263DEST_PATH_IMAGE030
Horizontal gradient amplitude and verticalA straight gradient magnitude.
Calculating gradient values and gradient directions through a sobel operator, and filtering out a maximum value; eight gradient directions are set, including:
Figure 127678DEST_PATH_IMAGE031
；
and setting a threshold value:
Figure 884281DEST_PATH_IMAGE085
；
wherein the content of the first and second substances,
Figure 615738DEST_PATH_IMAGE086
gray values of all points to be measured;
and filtering the noise according to the image definition evaluation value:
Figure 457792DEST_PATH_IMAGE087
；
wherein the content of the first and second substances,
Figure 915318DEST_PATH_IMAGE088
it is effective.
And (3) sending the preprocessed image to an artificial intelligence algorithm, performing convolution calculation on the image, and outputting a classification result by a Softmax classifier after passing through a pooling layer, an activation function and a full connection layer. And then realize discernment and judgement to rubbish.
Convolution calculation is that some small matrixes slide on an image or an input characteristic graph, the result obtained by multiplication and addition of the matrixes is the output classification result, and the calculation method comprises the following steps:
Figure 526428DEST_PATH_IMAGE089
；
wherein the content of the first and second substances,
Figure 348890DEST_PATH_IMAGE061
for convolution kernel channel number, sum is matrix addition operationThe character is that,bis a characteristic parameter.
The feature size extracted after convolutional layer is still too large, and it is very inconvenient to directly use for training and easy to overfit. And performing aggregate statistics on the features at different positions, and selecting a representative value to represent the original feature. The model selection is a maxporoling method, and the calculation formula is as follows:
Figure 678240DEST_PATH_IMAGE090
；
wherein the content of the first and second substances,
Figure 673878DEST_PATH_IMAGE091
characteristic values of different positions.
In order for an artificial intelligence algorithm to have good characterization capabilities, nonlinear elements must be introduced. Therefore, an activation function is introduced in the neural network. The activation function introduced by the model is a relu function, and the calculation formula is as follows:
Figure 139495DEST_PATH_IMAGE092
；
wherein x is a characteristic value.
The convolution layer, the pooling layer, the activation function and other structures map original data to a feature vector space, the full-connection layer is used for integrating and summarizing learned distributed features and then mapping the integrated and summarized distributed features to a sample mark space, and the calculation formula is as follows:
Figure 460755DEST_PATH_IMAGE093
；
wherein the content of the first and second substances,
Figure 11822DEST_PATH_IMAGE094
are mapped feature samples.
Softmax maps the feature vectors of the input neural network to (0,1) space, and the sum of these values is 1, and the output value can be understood as a probability value. So when outputting the result, the classification result with the highest probability value is selected.
Figure 76730DEST_PATH_IMAGE095
；
Wherein the content of the first and second substances,
Figure 459169DEST_PATH_IMAGE044
is a classification vector.
After the processing of the artificial intelligence algorithm, the garbage can be accurately detected, and the detection result is gathered to the terminal equipment for visual display and information storage.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.

Claims (8)

1. The utility model provides a rubbish discernment and decision-making method violating regulations based on unmanned aerial vehicle and artificial intelligence which characterized in that: the method comprises the following steps:
s1.1: collecting a high-definition video by an unmanned aerial vehicle;
s1.2: performing interframe difference processing on the high-definition video acquired by the unmanned aerial vehicle to acquire an effective high-definition picture;
s1.3: transmitting the obtained high-definition picture to a ground workstation by a 5G technology, and further preprocessing the picture;
s1.4: carrying out operation on the preprocessed pictures through an artificial intelligence algorithm, and further realizing the recognition and judgment of the garbage;
in the S1.2, an improved inter-frame difference method is adopted for inter-frame difference processing, and the improved inter-frame difference method utilizes three frames of image information and performs difference operation on images of a current frame and previous and next frames;
the improved interframe difference method formula is as follows:
Figure 667172DEST_PATH_IMAGE001
；
Figure 849891DEST_PATH_IMAGE002
and
Figure 832891DEST_PATH_IMAGE004
the images are respectively the difference between the front frame and the back frame and the current frame,
Figure 165783DEST_PATH_IMAGE005
and
Figure 121101DEST_PATH_IMAGE006
、
Figure 881246DEST_PATH_IMAGE007
the gray values of the image at time t, time t-1 and time t +1 respectively,
Figure 372050DEST_PATH_IMAGE008
is a coefficient of gray scale to be used,Nis the total number of pixels of the region to be detected,
Figure 836529DEST_PATH_IMAGE009
for the image to be detected；
And then, performing binarization processing on the frame difference image obtained by threshold T processing:
Figure 708670DEST_PATH_IMAGE010
；
wherein the content of the first and second substances,
Figure 842980DEST_PATH_IMAGE011
or
Figure 534992DEST_PATH_IMAGE012
，
Figure 475266DEST_PATH_IMAGE013
Or both results are obtained by binarization.
2. The violation garbage identification and determination method based on unmanned aerial vehicle and artificial intelligence as recited in claim 1, wherein: in the S1.3, the preprocessing method comprises image gray processing, color inversion and a canny edge detection algorithm;
the picture gray level processing formula is as follows:
Figure DEST_PATH_IMAGE014
；
wherein the content of the first and second substances,
Figure 201914DEST_PATH_IMAGE015
、
Figure DEST_PATH_IMAGE016
and
Figure 772704DEST_PATH_IMAGE017
respectively representing components of red, green and blue colors, and solving the average value of the three components of the color image to obtain a gray value;
the color inversion formula is as follows:
Figure DEST_PATH_IMAGE018
；
wherein the content of the first and second substances,
Figure 90028DEST_PATH_IMAGE019
for the value of the current pixel, it is,
Figure 302835DEST_PATH_IMAGE020
the pixel values after color inversion;
the canny edge detection algorithm is as follows:
Figure 149568DEST_PATH_IMAGE021
；
wherein the content of the first and second substances,
Figure 422417DEST_PATH_IMAGE022
is the standard deviation of the Gaussian distribution,
Figure 416918DEST_PATH_IMAGE023
is a pixel point;
multiplying each pixel point and the neighborhood thereof by a Gaussian matrix, and taking the weighted average value as the final gray value:
Figure 698995DEST_PATH_IMAGE024
；
Figure 337918DEST_PATH_IMAGE025
；
wherein the content of the first and second substances,
Figure 47248DEST_PATH_IMAGE026
in order to be the amplitude value,
Figure 198219DEST_PATH_IMAGE027
in the form of a direction of rotation,
Figure 346303DEST_PATH_IMAGE028
and
Figure 636470DEST_PATH_IMAGE029
respectively the image at a pixel point
Figure 782281DEST_PATH_IMAGE030
Horizontal gradient magnitude and vertical gradient magnitude.
3. The violation garbage identification and determination method based on unmanned aerial vehicle and artificial intelligence as recited in claim 2, wherein: after the canny edge detection algorithm is detected, calculating a gradient value and a gradient direction through a sobel operator, and filtering out a maximum value; eight gradient directions are set, including: 0 °,45 °,90 °,135 °,180 °,225 °,270 °,315 °;
and setting a threshold value:
Figure 157899DEST_PATH_IMAGE031
；
wherein the content of the first and second substances,
Figure 719461DEST_PATH_IMAGE032
gray values of all points to be measured;
and filtering the noise according to the image definition evaluation value:
Figure 926452DEST_PATH_IMAGE033
；
wherein the content of the first and second substances,
Figure 180847DEST_PATH_IMAGE034
it is effective.
4. The violation garbage identification and determination method based on unmanned aerial vehicle and artificial intelligence as recited in claim 1, wherein: in S1.4, the artificial intelligence algorithm includes: image input, basic feature extraction, multi-layer complex feature extraction, feature learning and classification detection results; the method comprises the steps of carrying out convolution calculation on an image, outputting a classification result by a Softmax classifier through a pooling layer, an activation function and a full connection layer, and realizing the identification and judgment of the garbage.
5. The violation garbage identification and determination method based on unmanned aerial vehicle and artificial intelligence as recited in claim 4, wherein: the convolution calculation is that a small matrix slides on an image or an input characteristic diagram, the output classification result is a result obtained by matrix multiplication and addition, and the calculation method comprises the following steps:
Figure 43760DEST_PATH_IMAGE035
；
wherein the content of the first and second substances,
Figure 468401DEST_PATH_IMAGE036
is the number of convolution kernel channels, sum is the matrix addition operator,bis a characteristic parameter;
performing aggregation statistics through the features of different positions, and selecting a representative value to represent the original feature; by adopting the maxporoling method, the calculation formula is as follows:
Figure 467581DEST_PATH_IMAGE037
；
wherein the content of the first and second substances,
Figure 17511DEST_PATH_IMAGE038
characteristic values of different positions;
introducing an activation function relu function into the neural network, wherein the calculation formula is as follows:
Figure 367721DEST_PATH_IMAGE039
；
wherein x is a characteristic value used for improving the characterization capability of the artificial intelligence algorithm.
6. The violation garbage identification and determination method based on unmanned aerial vehicle and artificial intelligence as recited in claim 4, wherein: the convolution layer, the pooling layer and the activation function structure map original data to a feature vector space, and the full connection layer is obtained by a calculation formula:
Figure 598982DEST_PATH_IMAGE040
；
wherein, the first and the second end of the pipe are connected with each other,
Figure 718248DEST_PATH_IMAGE042
and b, integrating and summarizing the learned distributed features for the mapped feature samples and the feature parameters, and then mapping the integrated distributed features to a sample mark space.
7. The violation rubbish identification and determination method based on the unmanned aerial vehicle and the artificial intelligence as recited in claim 4, wherein: softmax maps the input feature vectors of the neural network to (0,1) space, the sum of these values is 1, and the maximum probability value is selected as the classification result:
Figure 48866DEST_PATH_IMAGE043
；
wherein the content of the first and second substances,
Figure 886372DEST_PATH_IMAGE044
is a classification vector.
8. The violation garbage identification and determination method based on unmanned aerial vehicle and artificial intelligence as recited in claim 4, wherein: and after the artificial intelligence algorithm is processed, performing garbage detection, and summarizing detection results to terminal equipment for visual display and information storage.
CN202211219087.2A 2022-10-08 2022-10-08 Method for identifying and judging illegal garbage based on unmanned aerial vehicle and artificial intelligence Active CN115294486B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211219087.2A CN115294486B (en) 2022-10-08 2022-10-08 Method for identifying and judging illegal garbage based on unmanned aerial vehicle and artificial intelligence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211219087.2A CN115294486B (en) 2022-10-08 2022-10-08 Method for identifying and judging illegal garbage based on unmanned aerial vehicle and artificial intelligence

Publications (2)

Publication Number Publication Date
CN115294486A CN115294486A (en) 2022-11-04
CN115294486B true CN115294486B (en) 2023-01-13

Family

ID=83834617

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211219087.2A Active CN115294486B (en) 2022-10-08 2022-10-08 Method for identifying and judging illegal garbage based on unmanned aerial vehicle and artificial intelligence

Country Status (1)

Country Link
CN (1) CN115294486B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115588145B (en) * 2022-12-12 2023-03-21 深圳联和智慧科技有限公司 Unmanned aerial vehicle-based river channel garbage floating identification method and system

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109472200A (en) * 2018-09-29 2019-03-15 深圳市锦润防务科技有限公司 A kind of intelligent sea rubbish detection method, system and storage medium
CN112581492A (en) * 2019-09-27 2021-03-30 北京京东尚科信息技术有限公司 Moving target detection method and device

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9111444B2 (en) * 2012-10-31 2015-08-18 Raytheon Company Video and lidar target detection and tracking system and method for segmenting moving targets
CN108230368A (en) * 2016-12-14 2018-06-29 贵港市瑞成科技有限公司 A kind of fast-moving target detection method
CN109460764B (en) * 2018-11-08 2022-02-18 中南大学 Satellite video ship monitoring method combining brightness characteristics and improved interframe difference method
CN110298323B (en) * 2019-07-02 2021-10-15 中国科学院自动化研究所 Frame-fighting detection method, system and device based on video analysis
CN110599523A (en) * 2019-09-10 2019-12-20 江南大学 ViBe ghost suppression method fused with interframe difference method
CN110910318A (en) * 2019-10-21 2020-03-24 中国科学院西安光学精密机械研究所 Weak contrast schlieren small ball center calculation method for comprehensive diagnosis light path quick automatic collimation system
CN111539296B (en) * 2020-04-17 2022-09-23 河海大学常州校区 Method and system for identifying illegal building based on remote sensing image change detection
CN114120120A (en) * 2021-11-25 2022-03-01 广东电网有限责任公司 Method, device, equipment and medium for detecting illegal building based on remote sensing image
CN114241364A (en) * 2021-11-30 2022-03-25 南京理工大学 Method for quickly calibrating foreign object target of overhead transmission line

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109472200A (en) * 2018-09-29 2019-03-15 深圳市锦润防务科技有限公司 A kind of intelligent sea rubbish detection method, system and storage medium
CN112581492A (en) * 2019-09-27 2021-03-30 北京京东尚科信息技术有限公司 Moving target detection method and device

Also Published As

Publication number Publication date
CN115294486A (en) 2022-11-04

Similar Documents

Publication Publication Date Title
CN106651872B (en) Pavement crack identification method and system based on Prewitt operator
CN108615226B (en) Image defogging method based on generation type countermeasure network
CN109657632B (en) Lane line detection and identification method
US9418402B2 (en) System for improving foggy luminance image using fog reduction estimation model
CN103400150B (en) A kind of method and device that road edge identification is carried out based on mobile platform
US9384532B2 (en) Apparatus for improving fogged image using user-controllable root operator
CN104766071B (en) A kind of traffic lights fast algorithm of detecting applied to pilotless automobile
CN109918971B (en) Method and device for detecting number of people in monitoring video
CN103034983B (en) A kind of defogging method capable based on anisotropic filtering
CN103824081A (en) Method for detecting rapid robustness traffic signs on outdoor bad illumination condition
CN112149543B (en) Building dust recognition system and method based on computer vision
CN109345547A (en) Traffic lane line detecting method and device based on deep learning multitask network
CN102881160B (en) Outdoor traffic sign identification method under low-illumination scene
CN103198459A (en) Haze image rapid haze removal method
CN105976338A (en) Dark channel prior defogging method based on sky recognition and segmentation
CN115294486B (en) Method for identifying and judging illegal garbage based on unmanned aerial vehicle and artificial intelligence
CN111815528A (en) Bad weather image classification enhancement method based on convolution model and feature fusion
CN111611861A (en) Image change detection method based on multi-scale feature association
CN106657948A (en) low illumination level Bayer image enhancing method and enhancing device
CN107636724A (en) The adaptive demister of wavelength and method of image
Sahu et al. Image dehazing based on luminance stretching
CN116052090A (en) Image quality evaluation method, model training method, device, equipment and medium
Wang et al. Haze removal algorithm based on single-images with chromatic properties
Alami et al. Local fog detection based on saturation and RGB-correlation
Khan et al. Recent advancement in haze removal approaches

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