CN110338092A - A kind of pig Activity recognition method and system based on sound - Google Patents
A kind of pig Activity recognition method and system based on sound Download PDFInfo
- Publication number
- CN110338092A CN110338092A CN201910584148.7A CN201910584148A CN110338092A CN 110338092 A CN110338092 A CN 110338092A CN 201910584148 A CN201910584148 A CN 201910584148A CN 110338092 A CN110338092 A CN 110338092A
- Authority
- CN
- China
- Prior art keywords
- pig
- module
- audio
- sound
- behavior
- 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
- 230000000694 effects Effects 0.000 title claims abstract description 25
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000001914 filtration Methods 0.000 claims abstract description 24
- 238000012545 processing Methods 0.000 claims abstract description 16
- 238000012544 monitoring process Methods 0.000 claims abstract description 5
- 238000001228 spectrum Methods 0.000 claims description 28
- 239000000284 extract Substances 0.000 claims description 7
- 230000009466 transformation Effects 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000005236 sound signal Effects 0.000 claims description 3
- 230000003321 amplification Effects 0.000 claims 1
- 238000003032 molecular docking Methods 0.000 claims 1
- 238000003199 nucleic acid amplification method Methods 0.000 claims 1
- 206010000117 Abnormal behaviour Diseases 0.000 abstract description 5
- 230000006870 function Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000012634 fragment Substances 0.000 description 3
- 206010011224 Cough Diseases 0.000 description 2
- 230000003542 behavioural effect Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 206010018762 Grunting Diseases 0.000 description 1
- 201000009906 Meningitis Diseases 0.000 description 1
- 208000002193 Pain Diseases 0.000 description 1
- 206010037423 Pulmonary oedema Diseases 0.000 description 1
- 206010037660 Pyrexia Diseases 0.000 description 1
- 206010041235 Snoring Diseases 0.000 description 1
- 241000282887 Suidae Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000036461 convulsion Effects 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 235000003642 hunger Nutrition 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 244000144972 livestock Species 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 239000002985 plastic film Substances 0.000 description 1
- 244000144977 poultry Species 0.000 description 1
- 230000035935 pregnancy Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 208000005333 pulmonary edema Diseases 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 208000023504 respiratory system disease Diseases 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000037351 starvation Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K29/00—Other apparatus for animal husbandry
- A01K29/005—Monitoring or measuring activity, e.g. detecting heat or mating
-
- 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
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Environmental Sciences (AREA)
- Computational Linguistics (AREA)
- Biodiversity & Conservation Biology (AREA)
- Animal Husbandry (AREA)
- Biophysics (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The pig Activity recognition method and system based on sound that the present invention is more particularly directed to a kind of, including pig bed body module, lie down for pig, and during the break to the place of pig monitoring;Audio collection module, the acquisition of the voice data for being issued to pig in pig bed ontology;Audio processing and identification module for being collected storage to audio data, and carry out identification classification to the behavior of pig in audio-frequency information, and audio playing module plays out the audio file being collected into;Audio processing and identification module are made of signal receiving module, storage hard disk, loudspeaker, Time alignment, Windowed filtering, frequency-domain transform, behavior prediction functional module;The invention makes pig bed that can perceive the sounding of pig, it identifies the behavior classification of pig representated by pig sound, finds the abnormal behaviour of pig in time, such as fight, is sick, it reminds administrative staff to take targetedly intervening measure in time, improves automation, the intelligent level of pig raising.
Description
Technical field
The invention belongs to livestock and poultry cultivation intelligence Processes and apparatus technical field, in particular to a kind of pig row based on sound
For recognition methods and system.
Background technique
The cry of pig is generally possible to express certain behavioural information.Pig is in healthy, sick, hungry, angry, heat, gestation
The sound issued under equal different conditions is not quite similar.For example, pig in fever, pulmonary edema or when suffering from meningitis, issues droning, short
Promote, hoarse twitch sound;It emits a shrill cry when stinging ear, tail biting, fighting;The sending when catching a cold or suffering from other respiratory diseases
Cough;It is issued under starvation and starves cry.
Voice recognition technology has the characteristics that respond fast, contactless, non-intruding.If pig can be found in time by sound
Behavior state, it will be able to cope with various abnormal conditions in time, realize the intelligence of pig raising.Currently, people carried out it is some
The research of grunting of hogs sound identification.
Pig bed is the important life area of pig in pig-breeding, has most of the time pig all to spend on pig bed in one day,
If can allow pig bed real-time monitoring, Intellisense, identify pig sounding and its behavior, help to improve pig raising automation,
Intelligent level finds the abnormal behavior of pig in time, makes and pointedly handling.Currently, people design have temperature sensing and
The pig bed of function of temperature control can acquire the temperature in pig bed, and adjust temperature by heating, cooling system, and pig bed accessory is made to have one
Fixed intelligence.But current pig bed effectively can't monitor and identify the sounding information of pig.
In response to this problem, the present invention proposes a kind of pig Activity recognition method and system based on sound, feel pig bed can
Know the sounding of pig, identify behavior classification representated by sounding, finds the abnormal behaviour of pig in time, improve automation, the intelligence of pig raising
Energyization is horizontal.
Summary of the invention
The pig Activity recognition method and system based on sound that it is an object of the present invention to provide a kind of collect pig bed by pig bed
The voice data that pig issues in ontology, and then intellectual analysis identification is carried out to the behavioural characteristic of pig, help people to find pig in time
Abnormal behaviour, and make specific aim measure.
The pig Activity recognition system based on sound that the present invention provides a kind of to solve above-mentioned technical problem, including successively connect
Connect: pig bed body module lies down for pig, and during the break to the place of pig monitoring;Audio collection module is used for
Acquisition to the voice data that pig in pig bed ontology issues;Audio processing and identification module, for being collected to audio data
Storage, and identification classification is carried out to the behavior of pig in audio-frequency information;Audio playing module, to the audio file and identification being collected into
As a result it plays out.
The pig bed body module is made of bottom plate, top plate, side plate, bed curtain, and bottom plate left and right sides and rear side are provided with
Side plate, side plate upper end are connected with top plate, and the front end of top plate, which is provided with, hangs curtain, and pig can pass in and out pig bed ontology by hanging curtain.
The audio collection module is made of microphone, and microphone acquires the sound that pig issues in pig bed ontology, and by audio
File sends audio processing and identification module to.
The audio processing and identification module is made of computer hardware and software systems, and computer hardware includes signal
Receiving module, storage hard disk, loudspeaker, software systems are by Time alignment, Windowed filtering, frequency-domain transform, behavior prediction function mould
Block is constituted.
The audio playing module is made of speaker, and speaker is used to play received audio file and prediction result.
The behavior prediction module includes disaggregated model module, offline update module, and disaggregated model module can identify
Out in spectrum sequence pig behavior classification, offline update module by update pig behavior audio file to disaggregated model carry out more
Newly.
The signal receiving module receives the audio file of audio collection module transmission, and audio file is stored in storage
It deposits in hard disk;Loudspeaker plays out the audio file received, and the Time alignment module in the software systems is from sound
The sound clip of certain time length is extracted in frequency signal, Windowed filtering module is added the sound clip that Time alignment module is extracted
The filter result of Windowed filtering module is carried out the transformation of fast discrete Fourier spectrum by window filtering, frequency-domain transform module, obtain with
Spectrum sequence is sent into the preset pig behavior based on sounding in computer and classified by the isometric spectrum sequence of time-domain signal before converting
Model, behavior prediction module carry out Classification and Identification by sound spectrum signal of the disaggregated model to input, predict the signal
Pig behavior classification, and prediction result is exported to audio playing module, offline update module is using the labeled data updated to classification
Model is updated.
The pig Activity recognition method based on sound that the present invention also provides a kind of, comprising:
S1: installing microphone in pig bed ontology, and microphone is mounted on pig and cannot touch and can acquire whole areas in pig bed ontology
The sound position of domain pig completes the acquisition to pig acoustic information by microphone;
S2: Time alignment, Windowed filtering, frequency-domain transform processing are carried out to collected audio file, then by behavior prediction module
The behavior of pig is predicted by collected audio, and exports prediction result to audio playing module;
S3: audio playing module broadcasts prediction result and collected audio file.
The step S2 includes:
S21: signal receiving module receives audio file, while playing out audio file using loudspeaker, and by sound
Frequency file is stored in storage hard disk;
S22: the sound clip of certain time length, adding window filter are extracted from audio file by the Time alignment module in software systems
The sound clip that wave module extracts Time alignment module carries out Windowed filtering;
S23: the filter result of Windowed filtering module is carried out by the transformation of fast discrete Fourier spectrum by frequency-domain transform module, is obtained
To the spectrum sequence isometric with preceding time-domain signal is converted, spectrum sequence is then sent into the preset pig based on sounding in computer
Behavior disaggregated model;
S24: behavior prediction module, to the classification results of the sound spectrum signal of input, predicts the pig of the signal according to disaggregated model
Behavior classification, and prediction result is exported to audio playing module;
S25: offline update module is updated disaggregated model using the labeled data of update.
A kind of pig Activity recognition method and system based on sound of the invention are adopted by the microphone being arranged in pig bed ontology
Collect pig to be stored in storage hard disk in the intrinsic sounding data of pig bed, and by collected audio, then audio file is transmitted
To software systems, processing analysis is carried out to audio file by software systems,
Behavior by behavior prediction module to the identification classification prediction pig of audio file, by audio playing module to prediction result
Broadcasted with audio file, the invention can behavior classification representated by the sounding, identification sounding of pig in real-time perception pig bed,
The abnormal behaviour of discovery pig in time, improves automation, the intelligent level of pig raising.
Detailed description of the invention
Fig. 1 is a kind of pig Activity recognition system module composition schematic diagram based on sound of the invention.
Fig. 2 is a kind of pig Activity recognition system structure diagram based on sound of the invention.
Fig. 3 be a kind of pig Activity recognition method based on sound of the invention in audio collection module, audio processing with
Workflow schematic diagram between identification module, audio playing module.
Fig. 4 is a 1s intercepted from received audio in a kind of pig Activity recognition method based on sound of the invention
Duration audio fragment time domain waveform.
Fig. 5 is (to filter) knot to the one-dimensional convolution of Fig. 4 in a kind of pig Activity recognition method based on sound of the invention
Fruit.
Fig. 6 is the Fast Fourier Transform (FFT) result in a kind of pig Activity recognition method based on sound of the invention to Fig. 5.
Specific embodiment
Embodiment 1, as shown in Figure 1 and Figure 2, a kind of pig Activity recognition system based on sound, including sequentially connected: pig
Bed body module 1, lies down during the break for pig, and to the place of pig monitoring, pig bed body module is by bottom plate, top
Plate, side plate, bed curtain are constituted, and bottom plate uses 20mm thickness density board, and left and right, rear 3 side plates use 12mm thickness density board, and top plate is adopted
With 12mm thickness hollow plastic sheet, bottom plate left and right sides and rear side are provided with side plate, and side plate upper end is connected with top plate, before top plate
End, which is provided with, hangs curtain, and hanging curtain is preferably that curtain is hung in PVC bar shaped, and the length size of pig bed ontology can customize according to actual needs,
Pig can pass in and out pig bed ontology by hanging curtain.Audio collection module 2, the voice data for issuing to pig in pig bed ontology are adopted
Collection, the audio file formats of acquisition are wav, and sample rate is 22050 frames/second, and audio collection module is made of microphone, and microphone can be with
It is provided with multiple, to guarantee to collect the sound that pig issues in pig bed ontology completely, microphone installation site is preferably top plate
Lower surface, microphone are connected to a computer, and acquire the intrinsic sound of pig bed in real time, and send audio file to audio processing
With identification module 3.Audio processing and identification module 3, for being collected storage to audio data, and to pig in audio data
Behavior carries out identification classification;Audio processing is made of with identification module 3 computer hardware and software systems, and computer hardware includes
Signal receiving module, storage hard disk, loudspeaker, software systems use Python programming language and TensorFlow, Wave,
The API such as Numpy, Struct, SciPy, Matplotlib exploitation, by Time alignment, Windowed filtering, frequency-domain transform, behavior prediction
Functional module is constituted;Behavior prediction module includes disaggregated model module, offline update module, and disaggregated model is by supporting vector mechanism
At disaggregated model module can recognize that the behavior classification of pig in spectrum sequence, the pig behavior that offline update module passes through update
Audio file is updated disaggregated model.Signal receiving module receives the audio file of audio collection module transmission, and by sound
Frequency file is stored in storage hard disk;Loudspeaker plays out the audio file received, the Time alignment in software systems
Module extracts the sound clip of certain time length, the sound piece that Windowed filtering module extracts Time alignment module from audio signal
The filter result of Windowed filtering module is carried out the change of fast discrete Fourier spectrum by Duan Jinhang Windowed filtering, frequency-domain transform module
Change, obtain with convert before the isometric spectrum sequence of time-domain signal, spectrum sequence is sent into preset based on sounding in computer
Pig behavior disaggregated model, behavior prediction module carry out Classification and Identification, prediction according to sound spectrum signal of the disaggregated model to input
The pig behavior classification of the signal, and prediction result is exported to audio playing module 4, audio playing module 4 is made of speaker, is used to
Received audio file and prediction result are played, offline update module carries out more disaggregated model using the labeled data updated
Newly.
Embodiment 2, a kind of method for the song behavior collected, analyze pig as shown in Fig. 3-6 characterized by comprising
S1: installing microphone in pig bed ontology, and microphone is mounted on the position that pig cannot touch, and microphone can be set multiple to protect
Card can acquire the sound of whole region pig in pig bed ontology, and microphone installation site is preferably on the top plate of pig bed ontology, in this way
The sound that can guarantee that pig issues in pig bed ontology can be clearly collected, and be adopted by microphone completion to pig acoustic information
Collection, the 24 hours intrinsic sound of continuous acquisition pig bed of microphone, the audio format of acquisition is wav, and sample rate is 22050 frames/second,
And send collected audio file to computer hardware in real time;
S2: Time alignment, Windowed filtering, frequency-domain transform processing are carried out to collected audio file, then by behavior prediction module
The behavior of pig is predicted by collected audio, and exports prediction result to audio playing module;
S3: audio playing module is made of speaker, by behavior prediction module predict as a result, and collected audio file into
Row casting.
The step S2 includes:
S21: signal receiving module receives the collected audio file of audio collection module, while being carried out using loudspeaker
Audio file is played, and audio file is stored in storage hard disk;
S22: the audio fragment of 1s duration, one sound are extracted from audio file by the Time alignment module in software systems
The time domain waveform of frequency segment is as shown in figure 4, the sound clip that Windowed filtering module extracts Time alignment module carries out adding window filter
Wave carries out 1 dimension convolution, i.e. glide filter using audio fragment of the window function to extraction, and filtering window width is 220 frames
(20ms duration), step-length are 110 frames (10ms duration), and window function obtains a sequence of values, to Fig. 4's using being averaged
Filter result is as shown in Figure 5;
S23: the filter result of Windowed filtering module is carried out by the transformation of fast discrete Fourier spectrum by frequency-domain transform module, is obtained
To a spectrum sequence, the filter result of the spectrum sequence and previous step is isometric, and the input required with next step disaggregated model
Isometric, the Fast Fourier Transform (FFT) to the filter result of Fig. 4 is preset as shown in figure 5, then spectrum sequence is sent into computer
The pig behavior disaggregated model based on sounding, which is support vector cassification model, using linear kernel function, input
Feature quantity be 100, export as 0 or 1 or 2(for example: 0 represent cough, 1 represent snore, 2 represent scream);
S24: behavior prediction module, to the classification results of the sound spectrum signal of input, predicts the pig of the signal according to disaggregated model
Behavior classification, and prediction result is exported to audio playing module;
S25: offline update module is updated disaggregated model using the labeled data of update.
A kind of pig Activity recognition method and system based on sound of the invention are adopted by the microphone being arranged in pig bed ontology
Collection pig audio signal for issuing in pig bed ontology, and collected audio file is stored in storage hard disk, to collecting
Audio file carry out Time alignment, Windowed filtering, frequency-domain transform processing, then collected audio is passed through by behavior prediction module
The behavior of pig is predicted, and exports prediction result to audio playing module, audio playing module is to prediction result and audio
File is broadcasted, and is designed offline update module and is updated using the labeled data of update to disaggregated model, makes disaggregated model
Can timely renolation, so that behavior prediction module is accurately identified the row of pig according to the sounding of pig much sooner
For the invention makes pig bed that can perceive the sounding of pig, identifies the behavior classification of pig representated by sounding, finds the exception of pig in time
Behavior, such as fight, is sick, it reminds administrative staff to take targetedly intervening measure in time, improves automation, the intelligence of pig raising
Energyization is horizontal.
The foregoing is only a preferred embodiment of the present invention, is not intended to limit the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied, all within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (9)
1. a kind of pig Activity recognition system based on sound, which is characterized in that including sequentially connected:
Pig bed body module, lies down for pig, and during the break to the place of pig monitoring;
Audio collection module, the acquisition of the voice data for being issued to pig in pig bed ontology;
Audio processing and identification module for being collected storage to audio data, and carry out the behavior of pig in audio-frequency information
Identification classification;
Audio playing module plays out the audio file and recognition result that are collected into.
2. a kind of pig Activity recognition system based on sound according to claim 1, it is characterised in that: the pig bed is originally
Module is made of bottom plate, top plate, side plate, bed curtain, and bottom plate left and right sides and rear side are provided with side plate, and side plate upper end is connected with top
Plate, the front end of top plate, which is provided with, hangs curtain, and pig can pass in and out pig bed ontology by hanging curtain.
3. a kind of pig Activity recognition system based on sound according to claim 1, it is characterised in that: the audio is adopted
Collection module be made of microphone, microphone acquire pig bed ontology in pig issue sound, and by audio file send to audio processing with
Identification module.
4. a kind of pig Activity recognition system based on sound according to claim 1, it is characterised in that: at the audio
Reason and identification module are made of computer hardware and software systems, and computer hardware includes signal receiving module, storage hard disk, raises
Sound device, software systems are made of Time alignment, Windowed filtering, frequency-domain transform, behavior prediction functional module.
5. a kind of pig Activity recognition system based on sound according to claim 1, it is characterised in that: the audio is broadcast
Amplification module is made of speaker, and speaker is used to play received audio file and prediction result.
6. a kind of pig Activity recognition system based on sound according to claim 4, it is characterised in that: the behavior is pre-
Surveying module includes disaggregated model module, offline update module, and disaggregated model module can recognize that the behavior of pig in spectrum sequence
Classification, offline update module are updated disaggregated model by the pig behavior audio file updated.
7. a kind of pig Activity recognition system based on sound according to claim 4, it is characterised in that: the signal connects
The audio file that module receives audio collection module transmission is received, and audio file is stored in storage hard disk;Loudspeaker docking
The audio file received plays out, and the Time alignment module in the software systems extracts certain time length from audio signal
Sound clip, the sound clip that Windowed filtering module extracts Time alignment module carries out Windowed filtering, frequency-domain transform module
The filter result of Windowed filtering module is subjected to the transformation of fast discrete Fourier spectrum, is obtained isometric with time-domain signal before transformation
Spectrum sequence is sent into the preset pig behavior disaggregated model based on sounding in computer by spectrum sequence, and behavior prediction module is logical
It crosses disaggregated model and Classification and Identification is carried out to the sound spectrum signal of input, predict the pig behavior classification of the signal, and export pre-
Result is surveyed to audio playing module, offline update module is updated disaggregated model using the labeled data of update.
8. a kind of pig Activity recognition method based on sound characterized by comprising
S1: installing microphone in pig bed ontology, and microphone is mounted on pig and cannot touch and can acquire whole areas in pig bed ontology
The acquisition to pig acoustic information is completed by microphone in the position of the sound of domain pig;
S2: Time alignment, Windowed filtering, frequency-domain transform processing are carried out to collected audio file, then by behavior prediction module
The behavior of pig is predicted by collected audio, and exports prediction result to audio playing module;
S3: audio playing module broadcasts prediction result and collected audio file.
9. a kind of pig Activity recognition method based on sound as claimed in claim 8, it is characterised in that: the step S2 packet
It includes:
S21: signal receiving module receives audio file, while playing out audio file using loudspeaker, and by sound
Frequency file is stored in storage hard disk;
S22: the sound clip of certain time length, adding window filter are extracted from audio file by the Time alignment module in software systems
The sound clip that wave module extracts Time alignment module carries out Windowed filtering;
S23: the filter result of Windowed filtering module is carried out by the transformation of fast discrete Fourier spectrum by frequency-domain transform module, is obtained
To the spectrum sequence isometric with preceding time-domain signal is converted, spectrum sequence is then sent into the preset pig based on sounding in computer
Behavior disaggregated model;
S24: behavior prediction module carries out Classification and Identification by sound spectrum signal of the disaggregated model to input, predicts the signal
Pig behavior classification, and prediction result is exported to computer screen and audio playing module;
S25: offline update module is updated disaggregated model using the labeled data of update.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910584148.7A CN110338092A (en) | 2019-07-01 | 2019-07-01 | A kind of pig Activity recognition method and system based on sound |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910584148.7A CN110338092A (en) | 2019-07-01 | 2019-07-01 | A kind of pig Activity recognition method and system based on sound |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110338092A true CN110338092A (en) | 2019-10-18 |
Family
ID=68177732
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910584148.7A Pending CN110338092A (en) | 2019-07-01 | 2019-07-01 | A kind of pig Activity recognition method and system based on sound |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110338092A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111239597A (en) * | 2020-01-14 | 2020-06-05 | 温州大学乐清工业研究院 | Method for representing electric life of alternating current contactor based on audio signal characteristics |
CN111770427A (en) * | 2020-06-24 | 2020-10-13 | 杭州海康威视数字技术股份有限公司 | Microphone array detection method, device, equipment and storage medium |
CN112715408A (en) * | 2020-12-29 | 2021-04-30 | 重庆电子工程职业学院 | Intelligent pig raising system based on Internet of things |
CN112989101A (en) * | 2019-12-18 | 2021-06-18 | 深圳市三诺数字科技有限公司 | Reminding method, device, equipment and storage medium suitable for hearing-impaired patients |
CN114041779A (en) * | 2021-11-26 | 2022-02-15 | 河南牧原智能科技有限公司 | Identification system and computer device for identifying respiratory diseases of livestock |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2014174738A1 (en) * | 2013-04-26 | 2014-10-30 | 日本電気株式会社 | Monitoring device, monitoring method and monitoring program |
CN105336331A (en) * | 2015-11-21 | 2016-02-17 | 太原理工大学 | Intelligent monitoring method and intelligent monitoring system for abnormal behaviors of pigs on basis of sound |
CN106781397A (en) * | 2016-12-30 | 2017-05-31 | 浙江大学 | A kind of cattle and sheep supervisory systems |
CN106847293A (en) * | 2017-01-19 | 2017-06-13 | 内蒙古农业大学 | Facility cultivation sheep stress behavior acoustical signal monitoring method |
CN109493874A (en) * | 2018-11-23 | 2019-03-19 | 东北农业大学 | A kind of live pig cough sound recognition methods based on convolutional neural networks |
-
2019
- 2019-07-01 CN CN201910584148.7A patent/CN110338092A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2014174738A1 (en) * | 2013-04-26 | 2014-10-30 | 日本電気株式会社 | Monitoring device, monitoring method and monitoring program |
CN105336331A (en) * | 2015-11-21 | 2016-02-17 | 太原理工大学 | Intelligent monitoring method and intelligent monitoring system for abnormal behaviors of pigs on basis of sound |
CN106781397A (en) * | 2016-12-30 | 2017-05-31 | 浙江大学 | A kind of cattle and sheep supervisory systems |
CN106847293A (en) * | 2017-01-19 | 2017-06-13 | 内蒙古农业大学 | Facility cultivation sheep stress behavior acoustical signal monitoring method |
CN109493874A (en) * | 2018-11-23 | 2019-03-19 | 东北农业大学 | A kind of live pig cough sound recognition methods based on convolutional neural networks |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112989101A (en) * | 2019-12-18 | 2021-06-18 | 深圳市三诺数字科技有限公司 | Reminding method, device, equipment and storage medium suitable for hearing-impaired patients |
CN111239597A (en) * | 2020-01-14 | 2020-06-05 | 温州大学乐清工业研究院 | Method for representing electric life of alternating current contactor based on audio signal characteristics |
CN111770427A (en) * | 2020-06-24 | 2020-10-13 | 杭州海康威视数字技术股份有限公司 | Microphone array detection method, device, equipment and storage medium |
CN112715408A (en) * | 2020-12-29 | 2021-04-30 | 重庆电子工程职业学院 | Intelligent pig raising system based on Internet of things |
CN114041779A (en) * | 2021-11-26 | 2022-02-15 | 河南牧原智能科技有限公司 | Identification system and computer device for identifying respiratory diseases of livestock |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110338092A (en) | A kind of pig Activity recognition method and system based on sound | |
CN109243470B (en) | Broiler cough monitoring method based on audio technology | |
Carpentier et al. | Automatic cough detection for bovine respiratory disease in a calf house | |
Fontana et al. | An innovative approach to predict the growth in intensive poultry farming | |
CN109431470B (en) | Sleep respiration monitoring method and device | |
CN112164408A (en) | Pig coughing sound monitoring and early warning system based on deep learning | |
CN110265041A (en) | A kind of method and system for the song behavior collected, analyze pig | |
CN108198562A (en) | A kind of method and system for abnormal sound in real-time positioning identification animal house | |
JP5704598B2 (en) | Animal-machine voice interaction system | |
US9659149B2 (en) | Medical monitoring system based on sound analysis in a medical environment | |
Moura et al. | Real time computer stress monitoring of piglets using vocalization analysis | |
CN108922548A (en) | A kind of bird based on deep learning, frog intelligent monitoring method | |
CN109145032A (en) | A kind of bee raising intelligent monitoring method and system | |
US9113837B2 (en) | Drowsiness detection method and associated device | |
CN111583962A (en) | Sheep rumination behavior monitoring method based on acoustic analysis | |
CN110189756A (en) | It is a kind of for monitoring the method and system of live pig abnormal sound | |
Carroll et al. | Detecting symptoms of diseases in poultry through audio signal processing | |
CN105336331A (en) | Intelligent monitoring method and intelligent monitoring system for abnormal behaviors of pigs on basis of sound | |
CN103914732A (en) | Chewer rumination and swallowing frequency audio recognition algorithm | |
BE1026886A1 (en) | METHOD FOR MONITORING A LIVESTOCK FACILITY AND / OR LIVESTOCK ANIMALS IN A LIVESTOCK FACILITY USING IMPROVED SOUND PROCESSING TECHNIQUES | |
US9089123B1 (en) | Wild game information system | |
CN110111815A (en) | Animal anomaly sound monitoring method and device, storage medium, electronic equipment | |
CN106781397A (en) | A kind of cattle and sheep supervisory systems | |
Manikanta et al. | Deep learning based effective baby crying recognition method under indoor background sound environments | |
CN115810365A (en) | Pig health early warning method and system based on pig sound |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191018 |
|
RJ01 | Rejection of invention patent application after publication |