CN117076941A - Optical cable bird damage monitoring method, system, electronic equipment and readable storage medium - Google Patents
Optical cable bird damage monitoring method, system, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN117076941A CN117076941A CN202310863772.7A CN202310863772A CN117076941A CN 117076941 A CN117076941 A CN 117076941A CN 202310863772 A CN202310863772 A CN 202310863772A CN 117076941 A CN117076941 A CN 117076941A
- Authority
- CN
- China
- Prior art keywords
- bird
- sound
- optical cable
- target
- targets
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000003287 optical effect Effects 0.000 title claims abstract description 59
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000012544 monitoring process Methods 0.000 title claims abstract description 29
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 241000894007 species Species 0.000 claims abstract description 55
- 241000607479 Yersinia pestis Species 0.000 claims abstract description 18
- 230000001846 repelling effect Effects 0.000 claims abstract description 14
- 238000001228 spectrum Methods 0.000 claims description 58
- 238000001514 detection method Methods 0.000 claims description 27
- 238000005070 sampling Methods 0.000 claims description 20
- 238000009826 distribution Methods 0.000 claims description 14
- 238000012216 screening Methods 0.000 claims description 14
- 230000009466 transformation Effects 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 10
- 239000000835 fiber Substances 0.000 claims description 6
- 230000002940 repellent Effects 0.000 claims description 6
- 239000005871 repellent Substances 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000001131 transforming effect Effects 0.000 claims description 2
- 230000002265 prevention Effects 0.000 abstract description 7
- 241000271566 Aves Species 0.000 description 13
- 230000008569 process Effects 0.000 description 12
- 238000004891 communication Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 241000287509 Piciformes Species 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01M—CATCHING, TRAPPING OR SCARING OF ANIMALS; APPARATUS FOR THE DESTRUCTION OF NOXIOUS ANIMALS OR NOXIOUS PLANTS
- A01M29/00—Scaring or repelling devices, e.g. bird-scaring apparatus
- A01M29/16—Scaring or repelling devices, e.g. bird-scaring apparatus using sound waves
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/907—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/908—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- 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
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Library & Information Science (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Computing Systems (AREA)
- Pest Control & Pesticides (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Birds (AREA)
- Insects & Arthropods (AREA)
- Evolutionary Biology (AREA)
- Wood Science & Technology (AREA)
- Zoology (AREA)
- Environmental Sciences (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Image Analysis (AREA)
Abstract
The invention provides an optical cable bird damage monitoring method, an optical cable bird damage monitoring system, electronic equipment and a readable storage medium, wherein the method comprises the following steps: acquiring live image data and live sound data at a target optical cable; extracting bird images from the live image data; extracting bird sounds from the live sound data; and respectively extracting image features and sound features of the bird images and the bird sounds, carrying out matching identification in a preset bird database according to the image features and the sound features to obtain bird species identification results, and formulating a bird species identification result according to the bird species identification results so as to execute bird species repelling work based on the bird species identification results. The bird species is taken as the center, bird species identification is carried out through the images and sounds of birds, the bird pest characteristics of different time periods are analyzed, a personalized and accurate bird pest prevention strategy is formulated, intelligent bird expelling is realized, and further automation of optical cable bird pest protection is realized.
Description
Technical Field
The invention relates to the technical field of optical cable maintenance, in particular to an optical cable bird damage monitoring method, an optical cable bird damage monitoring system, electronic equipment and a readable storage medium.
Background
In the maintenance process of the optical cable, aiming at the damage of birds, the method which is commonly used at present is to additionally install a bird repellent and lay a special optical cable for preventing bird damage, wherein the prevention and control effect of the first method is not obvious, and the maintenance cost of the second method is high.
The patent document with the patent application number of CN201521130045.7U discloses an optical cable anti-bird trouble installation device, and each electric pole is provided with a clamping hoop, and each clamping hoop is connected with a hanging piece; the scrapped optical cable and the used optical cable are fixed through the hanging pieces. However, the scheme still needs to lay the bird damage prevention device on site, and due to the wide range of optical cable laying, many of the devices are arranged in remote areas, the mode obviously has high cost, and meanwhile, the device is difficult to apply on a large scale in practice due to the fixity of the device and the characteristic of needing periodic maintenance.
The patent document of the patent application number CN201410797847.7A discloses an anti-bird pecking optical cable, but the proposal still starts from the optical cable itself, various protection measures are added for the optical cable, and the defect of high cost still exists although bird damage can be prevented to a certain extent; meanwhile, the protection measures are broken and damaged along with the time, so that the cables need to be replaced regularly, and the cost is further increased.
In addition, although the conventional method for bird identification is used for identifying by voice, in the case of various bird sounds and environmental noise, there is a limitation in identifying birds only from bird sounds, and there is a certain influence on the accuracy of bird identification.
Disclosure of Invention
Aiming at the problems, the invention aims to provide an optical cable bird damage monitoring method, an optical cable bird damage monitoring system, electronic equipment and a readable storage medium, which take bird types as a center, identify the bird types through images and sounds of birds, analyze bird damage characteristics of different time periods, formulate a personalized and accurate bird damage prevention strategy, realize intelligent bird driving and further realize automation of optical cable bird damage protection.
The invention aims to achieve the aim, and the aim is achieved by the following technical scheme:
in a first aspect, the present invention provides a method for monitoring bird damage on an optical cable, comprising:
acquiring live image data and live sound data at a target optical cable;
detecting bird gestures of the field image data to obtain bird targets and corresponding key point information, screening effective targets from the bird targets, determining the positions of the effective targets according to the key point information of the effective targets, and intercepting the field image data according to the positions of the effective targets to obtain bird images;
after each sound segment obtained by dividing the on-site sound data is transformed, a frequency spectrum sound segment is formed, and noise in the frequency spectrum sound segment is judged according to the estimation of the real part and the imaginary part of the frequency spectrum sound segment, so that bird sound is obtained based on the frequency spectrum sound segment after the noise is removed;
and respectively extracting image features and sound features of the bird images and the bird sounds, carrying out matching identification in a preset bird database according to the image features and the sound features to obtain bird species identification results, and formulating a bird species identification result according to the bird species identification results so as to execute bird species repelling work based on the bird species identification results.
As an optional implementation manner, the determining the position of the effective target according to the key point information of the effective target includes:
performing extension treatment on the set height and width of the bird candidate frame according to a preset extension proportion, and obtaining corresponding bird posture information according to the bird candidate frame after the extension treatment;
screening bird targets and key point information of each bird target from the bird candidate frames according to bird posture information; the key point information comprises coordinate information and confidence;
obtaining comprehensive confidence coefficient of each bird target according to the confidence coefficient of the key point corresponding to each bird target, and screening effective targets from the bird targets according to the comprehensive confidence coefficient;
and determining the position of the effective target according to the coordinate information of the effective target.
In an alternative embodiment, the capturing the bird image from the live image data according to the position of the effective target includes:
according to the position of the effective target, determining the center of the target detection frame on the field image data to obtain an initial target detection frame;
intercepting a rectangular area with the size of M times of the initial target detection frame as a target local area on the field image data, wherein the initial target detection frame is taken as a center;
image threshold segmentation is carried out on the target local area to obtain a plurality of super pixel blocks, and the super pixel blocks are combined to obtain an adjusted target detection frame;
and intercepting a rectangular area with the size of M times of the target detection frame as a bird image by taking the adjusted target detection frame as a center on the field image data.
As an alternative embodiment, image features are extracted for bird images by the following formula:
wherein D is a key point, and D (D) is the Euclidean distance between each key point in the on-site image data and the origin; f is a threshold value when the image threshold value is segmented;average pixel values for live image data; c is the confidence of each key point; image is an Image feature; n is the number of key points.
Alternatively, the process of extracting bird sounds from live sound data includes:
performing short-time Fourier transform on sound segments obtained after the field sound data are divided to obtain transformed sound segments of each sound segment, and forming frequency spectrum sound segments by taking each sound segment as a real part and the transformed sound segments as imaginary parts;
simulating probability density distribution of a real part and an imaginary part of a frequency spectrum sound segment, and respectively calculating conditional expectation values of the real part and the imaginary part to be used as estimation of the real part and the imaginary part;
correcting the estimation of a real part and an imaginary part according to the prior missing probability of each frequency component of the frequency spectrum sound segment;
calculating the phase variance, the power variance and the amplitude variance of the spectrum sound segment according to the corrected real part and imaginary part estimation, and calculating the likelihood ratio of the spectrum sound segment according to the phase variance, the power variance and the amplitude variance, so as to judge the noise in the spectrum sound segment;
after removing noise in the frequency spectrum sound section, adopting short-time Fourier inverse transformation and overlap-add to obtain the bird sound of the sound section, and splicing all the bird sounds according to time sequence to obtain the final bird sound.
Alternatively, the sound characteristics are extracted for the bird sounds by the following formula:
wherein, STFT Z Transforming for short-time sampling;average power of transformed sound segment after short-time sampling transformation, +.>Mean phase of transformed sound segment after short-time sampling transformation,/>The average amplitude of the converted sound segment after short-time sampling conversion is obtained; />For average power +.>For average phase +.>I is a complex symbol for average amplitude; voice is a sound feature; k is the number of sound segments.
Alternatively, the setting a driving policy according to the bird species identification result includes: and obtaining bird species identification results within a set time period, analyzing bird distribution characteristics at the target optical cable, and formulating a driving strategy according to the bird distribution characteristics.
As an alternative embodiment, the performing bird repellent work based on the repellent strategy includes: periodically playing sound data of natural enemies corresponding to the bird species at the target optical cable based on the driving strategy; and according to the bird species identification result, playing the sound data of the natural enemies corresponding to the bird species at the target optical cable in real time.
In a second aspect, the present invention provides an optical cable bird damage monitoring system, comprising:
an acquisition module configured to acquire live image data and live sound data at a target optical cable;
the image extraction module is configured to perform bird gesture detection on the field image data to obtain contained bird targets and corresponding key point information, screen effective targets from the bird targets according to the bird gesture detection, determine the positions of the effective targets according to the key point information of the effective targets, and intercept the field image data according to the positions of the effective targets to obtain bird images;
the sound extraction module is configured to transform each sound segment obtained by dividing the live sound data to form a frequency spectrum sound segment, and judge noise in the frequency spectrum sound segment according to the estimation of the real part and the imaginary part of the frequency spectrum sound segment so as to obtain bird sound based on the frequency spectrum sound segment from which the noise is removed;
the execution module is configured to extract image features and sound features of the bird images and the bird sounds respectively, match and identify the bird images and the bird sounds in a preset bird database according to the image features and the sound features to obtain bird type identification results, and formulate a driving strategy according to the bird type identification results so as to execute bird driving work based on the driving strategy.
In a third aspect, the present invention provides an electronic device comprising:
the memory is used for storing an optical cable bird damage monitoring program;
a processor for implementing the steps of the cable bird pest monitoring method as described in any one of the preceding claims when executing the cable bird pest monitoring program.
In a fourth aspect, the present invention provides a computer readable storage medium having stored thereon a cable bird pest monitoring program which when executed by a processor implements the steps of the cable bird pest monitoring method of any one of the preceding claims.
Compared with the prior art, the invention has the beneficial effects that:
the invention innovatively provides an optical cable bird damage monitoring method, a system for monitoring the optical cable bird damage is developed, a technology for identifying the bird type by taking the bird type as a center and through images and sounds of the bird is designed, the limitation of bird identification only according to bird sounds is avoided, and the accuracy of bird type identification is improved; analyzing the bird pest characteristics in different time periods, and formulating a personalized and accurate bird pest prevention strategy so as to ensure that bird pest prevention is more accurate; according to the recognized bird types, the sound corresponding to the natural enemies is found, the natural enemies are used for expelling the sound, the optical cable is not required to be improved, the manufacturing cost of the optical cable is reduced, the intelligent bird expelling is realized, and the automation of the bird damage protection of the optical cable is realized.
It can be seen that the present invention has outstanding substantial features and significant advances over the prior art, as well as the benefits of its implementation.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method of an embodiment of the present invention.
Fig. 2 is a system configuration diagram of an embodiment of the present invention.
In the figure, 1, an acquisition module; 2. an image extraction module; 3. a sound extraction module; 4. and executing the module.
Detailed Description
In order to better understand the aspects of the present invention, the present invention will be described in further detail with reference to the accompanying drawings and detailed description. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the invention provides a method for monitoring bird damage of an optical cable, which comprises the following steps:
s1: live image data and live sound data at a target fiber optic cable are acquired.
S2: and detecting bird gestures of the field image data to obtain bird targets and corresponding key point information, screening effective targets from the bird targets, determining the positions of the effective targets according to the key point information of the effective targets, and intercepting the field image data according to the positions of the effective targets to obtain bird images.
S3: after each sound segment obtained by dividing the live sound data is transformed, a frequency spectrum sound segment is formed, and noise in the frequency spectrum sound segment is judged according to the estimation of the real part and the imaginary part of the frequency spectrum sound segment, so that bird sound is obtained based on the frequency spectrum sound segment after the noise is removed.
S4: and respectively extracting image features and sound features of the bird images and the bird sounds, carrying out matching identification in a preset bird database according to the image features and the sound features to obtain bird species identification results, and formulating a bird species identification result according to the bird species identification results so as to execute bird species repelling work based on the bird species identification results.
In the specific embodiment, the means for acquiring live image data may be any image acquisition means, but the image acquisition means is at least capable of acquiring an image within a circumferential range centered on the position where the image acquisition means is located and having a set observation distance as a radius; the set observation distance can be specifically determined according to actual requirements, but it is required to ensure that the part of the optical cable exposed to the ground can be completely covered by the observation range of the image acquisition device.
In a specific embodiment, before identifying and screening the bird image and the bird sound from the live image data and the live sound data, and before extracting the image features of the bird image and extracting the sound features of the bird sound, whether the bird exists or not may be determined from the acquired data; if the determination result is that no bird is present, the subsequent step may be directly omitted, and if the determination result is that a bird is present, the subsequent step may be performed.
In a specific embodiment, the process of identifying and screening bird images from live image data includes:
(1) According to the field image data, a pre-trained target detection and recognition neural network model is adopted to detect bird gestures, so that bird targets contained in the field image data and key point information corresponding to each bird target are obtained; the key point information comprises coordinate information and confidence degrees of N key points, wherein N is a positive integer; specifically:
(1-1) performing bird target recognition on field image data by using a single-point multi-box detection (SSD) network with a deep defect network as a backbone network to obtain bird candidate frames;
(1-2) performing extension treatment on the height and the width of the bird candidate frame according to a preset extension proportion, and inputting the bird candidate frame subjected to the extension treatment into a preset regional posture estimation (RMPE) frame to obtain bird posture information corresponding to the bird candidate frame;
(1-3) screening avian targets and key point information of each avian target from avian candidate frames according to avian attitude information.
(2) Calculating the comprehensive confidence coefficient of each bird target according to the confidence coefficient of N key points corresponding to each bird target, and screening effective targets from the bird targets according to the comprehensive confidence coefficient;
(3) Determining the position of the effective target according to the coordinate information in the key point information contained in the effective target;
(4) Intercepting and obtaining a bird image from the site image data according to the position of the effective target; specifically:
(4-1) determining the center of the target detection frame on the on-site image data according to the position of the effective target to obtain an initial target detection frame;
(4-2) intercepting a rectangular area with the size of M times that of the initial target detection frame as a target local area;
(4-3) performing image threshold segmentation on the target local area to obtain a plurality of super pixel blocks, and merging the super pixel blocks by adopting a multi-threshold fusion strategy to obtain an adjusted target detection frame;
(4-4) intercepting a rectangular area with the adjusted target detection frame as a center and the size of M times of the target detection frame on the field image data as a bird image.
In a specific embodiment, the process of identifying and screening bird sounds from live sound data comprises:
(1) Dividing the site sound data into K segments on average to obtain K sound segments;
(2) Performing short-time Fourier transform on each sound segment to obtain a transformed sound segment of each sound segment;
(3) Each sound segment is taken as a real part, and the converted sound segment is taken as an imaginary part to form a frequency spectrum sound segment;
(4) Simulating probability density distribution of a real part and an imaginary part of a spectrum sound segment by using Laplace distribution and gamma distribution, and respectively calculating conditional expectation values of the real part and the imaginary part according to a minimum mean square error criterion by using the probability density distribution of the real part and the imaginary part to be used as estimation of the real part and the imaginary part;
(5) Calculating the prior missing probability of each frequency component of the frequency spectrum sound segment, and further correcting the estimation of the real part and the imaginary part according to the prior missing probability;
(6) Calculating a phase variance, a power variance and an amplitude variance of the spectrum sound segment according to the corrected real part and imaginary part of the spectrum sound segment, and calculating a likelihood ratio of the spectrum sound segment according to the phase variance, the power variance and the amplitude variance to be used for judging noise in the spectrum sound segment;
(7) After removing noise in the frequency spectrum sound section, adopting short-time Fourier inverse transformation and overlap-add to obtain the bird sound of the sound section, and splicing all the bird sounds according to time sequence to obtain the final bird sound.
In a specific embodiment, the process of extracting image features from bird images is implemented using the following formula:
wherein d represents a key point; d (D) represents calculating a euclidean distance of each key point in the live image data from the origin; f is a threshold value when the image threshold value is segmented;average pixel values for live image data; c is the confidence of each key point; image is an Image feature, which is a calculated value; n is the number of key points.
In this embodiment, the process of extracting sound features from bird sounds is implemented using the following formula:
wherein, STFT Z Representing a short-time sampling transformation;representing the average power of the transformed sound segments after the short-time sampling transformation and so on +.>Representing the average phase of the transformed sound segment after the short-time sampling transformation,representing the average amplitude of the converted sound segment after short-time sampling conversion; />For average power +.>Is averaged toPhase (I)>I is a complex symbol for average amplitude; voice is a sound feature, which is a calculated value; k is the number of sound segments.
Wherein, the short-time sampling transformation general expression is:
one parameter is time, and the other parameter is variable; z (t) is the source signal and g (t) is the window function.
In a specific embodiment, when determining relevant parameters, setting a certain parameter of the changed sound section as a source signal, and setting other parameters such as a window function, a window length, overlapping points, sampling frequency, sampling points and the like according to actual needs; the sampling point is mainly used in the sampling transformation process, and when the signal length is smaller than the sampling point, the system automatically performs zero padding and then performs rapid sampling transformation. The source signal and the window function are converted into column vectors, the signal length is calculated, and the number of window sliding times n, namely the number of columns of the signal when the source signal is divided into columns, is calculated according to the signal length nx, the window length WinLen and the number of overlapping points novelap. And (3) representing signals selected by each window function sliding as columns, and determining the value of each column to obtain a matrix FIG with the column number of n and the line number of WinLen. And expanding the window function converted into the column vector into a matrix w of n columns, performing point multiplication on the matrices FIG and w, and performing rapid sampling transformation on the point multiplication result to obtain a time-frequency matrix.
In a specific embodiment, the process of matching and identifying in a preset bird database according to the image features and the sound features comprises the following steps: when the image feature matching similarity and the sound feature matching similarity respectively exceed a set threshold value, matching identification is successful, and a bird type identification result is obtained;
the set threshold value of the image feature matching similarity is 80%; the set threshold for similarity of acoustic feature matches is 60%.
Wherein, a plurality of birds data are stored in the birds database, and each bird data corresponds to a kind of birds; each bird data includes: category, image characteristics, sound characteristics, natural enemies, and sound data; wherein, the variety is the main key of each bird data; the image features and the sound features are the image features and the sound features of birds of corresponding types in the bird data; the natural enemy is the natural enemy of the bird of the corresponding kind in the bird data; the sound data is sound data of natural enemies of birds of corresponding types in the bird data; the kind of each piece of bird data is a primary key, the primary key is stored in a primary key table in a database, and other data are associated with the primary key.
In a specific embodiment, the process of formulating the driving strategy according to the bird species identification result includes: obtaining bird species identification results in a set time period, analyzing bird distribution characteristics at a target site, and formulating a driving strategy according to the bird distribution characteristics;
the bird distribution is characterized in that: the characteristic of the variation of the bird species at the target site during the day, i.e. the characteristic of the relationship of the bird species at the corresponding distribution at each different time of the day at the target site.
In a specific embodiment, based on the formulated repelling strategy, periodically performing bird repelling work at the target fiber optic cable, and performing bird repelling work at the target fiber optic cable in real time according to bird type recognition results; specifically:
the periodically performing bird repellent work includes: according to the driving strategy, playing sound data of natural enemies of bird types corresponding to different times of the day, and executing bird driving work;
the performing bird repelling work in real time includes: according to the bird species identification result, playing sound data of natural enemies of the bird species corresponding to the bird species identification result in real time at a target place, and executing bird repelling work;
wherein, the natural enemy refers to the natural enemy of the bird of the kind in practice, and can also represent the sound which is offensive or afraid of the bird of the kind in practice; in practice, 8 to 10 points in the day are set, and woodpecker is active, then the sound or fear of natural enemy of woodpecker is played periodically during this period, and if it is detected at this time that other kinds of birds fly onto the optical cable, then the sound or fear of natural enemy of the kind of birds can be emitted in real time.
Referring to fig. 2, the invention also discloses a system for monitoring bird damage of optical cable, which comprises: an acquisition module 1, an image extraction module 2, a sound extraction module 3 and an execution module 4.
An acquisition module 1 configured to acquire live image data and live sound data at a target optical cable.
The image extraction module 2 is configured to perform bird gesture detection on the field image data to obtain the contained bird targets and corresponding key point information, screen effective targets from the bird targets according to the bird gesture detection, determine the positions of the effective targets according to the key point information of the effective targets, and intercept the field image data according to the positions of the effective targets to obtain bird images.
The sound extraction module 3 is configured to transform each sound segment obtained by dividing the live sound data to form a spectrum sound segment, and determine noise in the spectrum sound segment according to the estimation of the real part and the imaginary part of the spectrum sound segment, so as to obtain bird sound based on the spectrum sound segment from which the noise is removed.
And the execution module 4 is configured to extract image features and sound features of the bird images and the bird sounds respectively, perform matching recognition in a preset bird database according to the image features and the sound features to obtain bird species recognition results, and formulate a driving strategy according to the bird species recognition results so as to execute bird driving work based on the driving strategy.
It should be noted that the above modules correspond to the steps disclosed in the foregoing optical cable bird damage monitoring method, and the above modules are the same as examples and application scenarios implemented by the corresponding steps, but are not limited to what is disclosed in the foregoing optical cable bird damage monitoring method. It should be noted that the modules described above may be implemented as part of a system in a computer system, such as a set of computer-executable instructions.
The invention also discloses an electronic device, which comprises a processor and a memory; the processor executes the optical cable bird damage monitoring program stored in the memory to realize the following steps:
1. live image data and live sound data at a target fiber optic cable are acquired.
2. And detecting bird gestures of the field image data to obtain bird targets and corresponding key point information, screening effective targets from the bird targets, determining the positions of the effective targets according to the key point information of the effective targets, and intercepting the field image data according to the positions of the effective targets to obtain bird images.
3. Each sound segment obtained after the on-site sound data are divided is transformed to form a frequency spectrum sound segment; and judging the noise in the frequency spectrum sound segment according to the estimation of the real part and the imaginary part of the frequency spectrum sound segment, so that the bird sound is obtained based on the frequency spectrum sound segment after the noise is removed.
4. And respectively extracting image features and sound features of the bird images and the bird sounds, carrying out matching identification in a preset bird database according to the image features and the sound features to obtain bird species identification results, and formulating a bird species identification result according to the bird species identification results so as to execute bird species repelling work based on the bird species identification results.
Further, the electronic device in this embodiment may further include:
the input interface is used for acquiring an externally imported optical cable bird damage monitoring program, storing the acquired optical cable bird damage monitoring program into the memory, and acquiring various instructions and parameters transmitted by external terminal equipment and transmitting the various instructions and parameters into the processor so that the processor can develop corresponding processing by utilizing the various instructions and parameters. In this embodiment, the input interface may specifically include, but is not limited to, a USB interface, a serial interface, a voice input interface, a fingerprint input interface, a hard disk reading interface, and the like.
And the output interface is used for outputting various data generated by the processor to the terminal equipment connected with the output interface so that other terminal equipment connected with the output interface can acquire various data generated by the processor. In this embodiment, the output interface may specifically include, but is not limited to, a USB interface, a serial interface, and the like.
And the communication unit is used for establishing remote communication connection between the electronic equipment and the external server so that the electronic equipment can mount the image file to the external server. In this embodiment, the communication unit may specifically include, but is not limited to, a remote communication unit based on a wireless communication technology or a wired communication technology.
And the keyboard is used for acquiring various parameter data or instructions input by a user by knocking the key cap in real time.
And the display is used for displaying related information of the optical cable bird damage monitoring process in real time.
A mouse may be used to assist a user in inputting data and to simplify user operations.
The invention also discloses a readable storage medium, which includes Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art. The readable storage medium stores an optical cable bird pest monitoring program which when executed by the processor realizes the following steps:
1. live image data and live sound data at a target fiber optic cable are acquired.
2. And detecting bird gestures of the field image data to obtain bird targets and corresponding key point information, screening effective targets from the bird targets, determining the positions of the effective targets according to the key point information of the effective targets, and intercepting the field image data according to the positions of the effective targets to obtain bird images.
3. Each sound segment obtained after the on-site sound data are divided is transformed to form a frequency spectrum sound segment; and judging the noise in the frequency spectrum sound segment according to the estimation of the real part and the imaginary part of the frequency spectrum sound segment, so that the bird sound is obtained based on the frequency spectrum sound segment after the noise is removed.
4. And respectively extracting image features and sound features of the bird images and the bird sounds, carrying out matching identification in a preset bird database according to the image features and the sound features to obtain bird species identification results, and formulating a bird species identification result according to the bird species identification results so as to execute bird species repelling work based on the bird species identification results.
In summary, the bird species is taken as the center, bird species identification is carried out through images and sounds of birds, bird pest characteristics in different time periods are analyzed, and a personalized and accurate bird pest prevention strategy is formulated, so that intelligent bird expelling is realized, and further automation of optical cable bird pest protection is realized.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, so that the same or similar parts between the embodiments are referred to each other. For the method disclosed in the embodiment, since it corresponds to the system disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the several embodiments provided by the present invention, it should be understood that the disclosed systems, and methods may be implemented in other ways. For example, the system embodiments described above are merely illustrative, e.g., the division of the elements is merely a logical functional division, and there may be additional divisions when actually implemented, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interface, system or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each module may exist alone physically, or two or more modules may be integrated in one unit.
Similarly, each processing unit in the embodiments of the present invention may be integrated in one functional module, or each processing unit may exist physically, or two or more processing units may be integrated in one functional module.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The method, the system, the electronic equipment and the readable storage medium for monitoring the bird damage of the optical cable provided by the invention are described in detail. The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to facilitate an understanding of the method of the present invention and its core ideas. It should be noted that it will be apparent to those skilled in the art that various modifications and adaptations of the invention can be made without departing from the principles of the invention and these modifications and adaptations are intended to be within the scope of the invention as defined in the following claims.
Claims (10)
1. A method for monitoring bird damage in an optical cable comprising:
acquiring live image data and live sound data at a target optical cable;
detecting bird gestures of the field image data to obtain bird targets and corresponding key point information, screening effective targets from the bird targets, determining the positions of the effective targets according to the key point information of the effective targets, and intercepting the field image data according to the positions of the effective targets to obtain bird images;
each sound segment obtained after the on-site sound data are divided is transformed to form a frequency spectrum sound segment; according to the estimation of the real part and the imaginary part of the frequency spectrum sound section, judging the noise in the frequency spectrum sound section, so as to obtain bird sounds based on the frequency spectrum sound section after the noise is removed;
and respectively extracting image features and sound features of the bird images and the bird sounds, carrying out matching identification in a preset bird database according to the image features and the sound features to obtain bird species identification results, and formulating a bird species identification result according to the bird species identification results so as to execute bird species repelling work based on the bird species identification results.
2. The method for monitoring bird damage on optical cable according to claim 1, wherein determining the position of the effective target based on the key point information of the effective target comprises:
performing extension treatment on the set height and width of the bird candidate frame according to a preset extension proportion, and obtaining corresponding bird posture information according to the bird candidate frame after the extension treatment;
screening bird targets and key point information of each bird target from the bird candidate frames according to bird posture information; the key point information comprises coordinate information and confidence;
obtaining comprehensive confidence coefficient of each bird target according to the confidence coefficient of the key point corresponding to each bird target, and screening effective targets from the bird targets according to the comprehensive confidence coefficient;
and determining the position of the effective target according to the coordinate information of the effective target.
3. The method for monitoring bird damage by optical cable of claim 1, wherein the capturing bird images from the field image data based on the location of the effective target comprises:
according to the position of the effective target, determining the center of the target detection frame on the field image data to obtain an initial target detection frame;
intercepting a rectangular area with the size of M times of the initial target detection frame as a target local area on the field image data, wherein the initial target detection frame is taken as a center;
image threshold segmentation is carried out on the target local area to obtain a plurality of super pixel blocks, and the super pixel blocks are combined to obtain an adjusted target detection frame;
and intercepting a rectangular area with the size of M times of the target detection frame as a bird image by taking the adjusted target detection frame as a center on the field image data.
4. A method of cable bird damage monitoring according to claim 3, wherein the image features are extracted for the bird image by the formula:
wherein D is a key point, and D (D) is the Euclidean distance between each key point in the on-site image data and the origin; f is a threshold value when the image threshold value is segmented;average pixel values for live image data; c is the confidence of each key point; image is an Image feature; n is the number of key points.
5. The method for monitoring bird damage by optical cable according to claim 1, wherein each sound segment obtained by dividing the live sound data is transformed to form a frequency spectrum sound segment; according to the estimation of the real part and the imaginary part of the spectrum sound section, the noise in the spectrum sound section is judged, so that the bird sound is obtained based on the spectrum sound section after the noise is removed, and the method comprises the following steps:
performing short-time Fourier transform on sound segments obtained after the field sound data are divided to obtain transformed sound segments of each sound segment, and forming frequency spectrum sound segments by taking each sound segment as a real part and the transformed sound segments as imaginary parts;
simulating probability density distribution of a real part and an imaginary part of a frequency spectrum sound segment, and respectively calculating conditional expectation values of the real part and the imaginary part to be used as estimation of the real part and the imaginary part;
correcting the estimation of a real part and an imaginary part according to the prior missing probability of each frequency component of the frequency spectrum sound segment;
calculating the phase variance, the power variance and the amplitude variance of the spectrum sound segment according to the corrected real part and imaginary part estimation, and calculating the likelihood ratio of the spectrum sound segment according to the phase variance, the power variance and the amplitude variance, so as to judge the noise in the spectrum sound segment;
after removing noise in the frequency spectrum sound section, adopting short-time Fourier inverse transformation and overlap-add to obtain the bird sound of the sound section, and splicing all the bird sounds according to time sequence to obtain the final bird sound.
6. The method of claim 1, wherein the sound characteristics are extracted from the bird sounds by the following formula:
wherein, STFT Z Transforming for short-time sampling;for short-time sampling the average power of the transformed sound segment after transformation,mean phase of transformed sound segment after short-time sampling transformation,/>The average amplitude of the converted sound segment after short-time sampling conversion is obtained; />For average power +.>For average phase +.>I is a complex symbol for average amplitude; voice is a sound feature; k is the number of sound segments.
7. A method for monitoring bird damage by fiber optic cable according to claim 1,
the method for formulating the driving strategy according to the bird species identification result comprises the following steps: obtaining bird species identification results within a set time period, so as to analyze bird distribution characteristics at a target optical cable, and formulating a driving strategy according to the bird distribution characteristics;
the performing bird repellent work based on the repellent strategy includes: periodically playing sound data of natural enemies corresponding to the bird species at the target optical cable based on the driving strategy; and according to the bird species identification result, playing the sound data of the natural enemies corresponding to the bird species at the target optical cable in real time.
8. An optical cable bird damage monitoring system, comprising:
an acquisition module configured to acquire live image data and live sound data at a target optical cable;
the image extraction module is configured to perform bird gesture detection on the field image data to obtain bird targets and corresponding key point information, screen effective targets from the bird targets according to the bird targets, determine the positions of the effective targets according to the key point information of the effective targets, and intercept the field image data according to the positions of the effective targets to obtain bird images;
the sound extraction module is configured to transform each sound segment obtained by dividing the live sound data to form a frequency spectrum sound segment, and judge the noise in the frequency spectrum sound segment according to the estimation of the real part and the imaginary part of the frequency spectrum sound segment so as to obtain bird sound based on the frequency spectrum sound segment from which the noise is removed;
the execution module is configured to extract image features and sound features of the birds respectively, match and identify the images and the sound features in a preset bird database according to the image features and the sound features, obtain bird species identification results, and formulate a bird repelling strategy according to the bird species identification results so as to execute bird repelling work based on the repelling strategy.
9. An electronic device, comprising:
the memory is used for storing an optical cable bird damage monitoring program;
a processor for implementing the steps of the cable bird pest monitoring method of any one of claims 1 to 7 when executing the cable bird pest monitoring program.
10. A readable storage medium, characterized by: the readable storage medium having stored thereon a cable bird pest monitoring program which when executed by a processor implements the steps of the cable bird pest monitoring method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310863772.7A CN117076941A (en) | 2023-07-13 | 2023-07-13 | Optical cable bird damage monitoring method, system, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310863772.7A CN117076941A (en) | 2023-07-13 | 2023-07-13 | Optical cable bird damage monitoring method, system, electronic equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117076941A true CN117076941A (en) | 2023-11-17 |
Family
ID=88705182
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310863772.7A Pending CN117076941A (en) | 2023-07-13 | 2023-07-13 | Optical cable bird damage monitoring method, system, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117076941A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117392551A (en) * | 2023-12-12 | 2024-01-12 | 国网江西省电力有限公司电力科学研究院 | Power grid bird damage identification method and system based on bird droppings image features |
| CN117746318A (en) * | 2023-12-07 | 2024-03-22 | 三峡新能源海上风电运维江苏有限公司 | Intelligent bird repelling method and system for offshore wind farm |
| CN117981744A (en) * | 2024-04-07 | 2024-05-07 | 国网山东省电力公司淄博供电公司 | System and method for protecting transmission line from bird damage, electronic equipment and storage medium |
-
2023
- 2023-07-13 CN CN202310863772.7A patent/CN117076941A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117746318A (en) * | 2023-12-07 | 2024-03-22 | 三峡新能源海上风电运维江苏有限公司 | Intelligent bird repelling method and system for offshore wind farm |
| CN117392551A (en) * | 2023-12-12 | 2024-01-12 | 国网江西省电力有限公司电力科学研究院 | Power grid bird damage identification method and system based on bird droppings image features |
| CN117392551B (en) * | 2023-12-12 | 2024-04-02 | 国网江西省电力有限公司电力科学研究院 | Power grid bird damage identification method and system based on bird droppings image features |
| CN117981744A (en) * | 2024-04-07 | 2024-05-07 | 国网山东省电力公司淄博供电公司 | System and method for protecting transmission line from bird damage, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117076941A (en) | Optical cable bird damage monitoring method, system, electronic equipment and readable storage medium | |
| CN110797021B (en) | Hybrid speech recognition network training method, hybrid speech recognition device and storage medium | |
| CN106131071B (en) | A kind of Web method for detecting abnormality and device | |
| CN106657057B (en) | Anti-crawler system and method | |
| CN111508480B (en) | Training method of audio recognition model, audio recognition method, device and equipment | |
| WO2019227716A1 (en) | Method for generating influenza prediction model, apparatus, and computer readable storage medium | |
| CN108985061B (en) | Webshell detection method based on model fusion | |
| CN112183212B (en) | Weed identification method, device, terminal equipment and readable storage medium | |
| CN110797031A (en) | Voice change detection method, system, mobile terminal and storage medium | |
| CN106850511B (en) | Method and device for identifying access attack | |
| KR20170101500A (en) | Method and apparatus for identifying audio signal using noise rejection | |
| CN113127864B (en) | Feature code extraction method, device, computer equipment and readable storage medium | |
| CN109064464B (en) | Method and device for detecting burrs of battery pole piece | |
| CN110797033A (en) | Artificial intelligence-based voice recognition method and related equipment thereof | |
| CN117527401A (en) | Network attack identification method and device for traffic log and electronic equipment | |
| CN111797690A (en) | Optical fiber perimeter intrusion identification method and device based on wavelet neural network grating array | |
| CN116740586A (en) | Hail identification method, hail identification device, electronic equipment and computer readable storage medium | |
| CN113408374B (en) | Yield estimation method, device, equipment and storage medium based on artificial intelligence | |
| KR20150120805A (en) | Method and system for detecting human in range image | |
| CN113113051A (en) | Audio fingerprint extraction method and device, computer equipment and storage medium | |
| CN113837091A (en) | Identification method, identification device, electronic equipment and computer-readable storage medium | |
| CN110376436B (en) | Multi-scale noise power spectral line spectrum detection method | |
| CN113805105A (en) | Three-phase transformer detection method and system | |
| CN113591570A (en) | Video processing method and device, electronic equipment and storage medium | |
| CN113935034A (en) | Malicious code family classification method and device based on graph neural network 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 |