CN111860203B - Abnormal pig identification device, system and method based on image and audio mixing - Google Patents
Abnormal pig identification device, system and method based on image and audio mixing Download PDFInfo
- Publication number
- CN111860203B CN111860203B CN202010600412.4A CN202010600412A CN111860203B CN 111860203 B CN111860203 B CN 111860203B CN 202010600412 A CN202010600412 A CN 202010600412A CN 111860203 B CN111860203 B CN 111860203B
- Authority
- CN
- China
- Prior art keywords
- group
- pig
- sound data
- image
- sample
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/26—Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/80—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides an abnormal pig identification device, system and method based on image and audio mixing, which are used for acquiring a group image set and group sound data of pigs in a group raising fence and identifying whether each pig is an abnormal pig or not according to the group image set and the group sound data through an identification model in an identification module. The identification model comprises a fusion processing sub-model, and the fusion processing sub-model outputs an identification result of whether any pig is an abnormal pig according to sign change information and individual sound data of any pig determined by the group image set and the group sound data. Through the combination of the image and the sound, the method is favorable for improving the accuracy of identifying the abnormal pigs, and the reliability of the detection result is high. Meanwhile, manual detection is not needed, so that the detection efficiency of abnormal pigs is improved, epidemic situation prevention and control are effectively carried out, and loss is reduced.
Description
Technical Field
The invention relates to the technical field of machine learning, in particular to an abnormal pig identification device, system and method based on image and audio mixing.
Background
The health of pigs only has serious influence on the growth and farrowing of pigs, thereby bringing about economic loss. Early discovery and early treatment are important means for epidemic prevention and control. In the existing method, each pig is usually detected periodically by manpower or abnormal pigs are screened from the herd fence through manual observation. Further tests are carried out on the pigs with abnormal performances so as to prevent and control possible infectious diseases through the tests or treat the problems of the pigs as soon as possible, thereby reducing the loss.
Therefore, the existing method can prevent and control the epidemic situation of pigs through manual detection, so that loss is reduced, manual detection efficiency is low, and detection result reliability is low.
Disclosure of Invention
The embodiment of the invention provides an abnormal pig identification device, system and method based on image and audio mixing, which are used for solving the problems that the loss is reduced, the manual detection efficiency is low and the reliability of detection results is low by manually detecting epidemic prevention and control on pigs in the existing method.
In order to solve the technical problems, in a first aspect, an embodiment of the present invention provides an abnormal pig identification device based on image and audio mixing, including an acquisition module and an identification module;
The acquisition module acquires a group image set obtained by carrying out infrared image acquisition and/or image shooting on a group-rearing fence in which pigs are reared in a preset time period, and group sound data acquired by the pigs in the group-rearing fence in the preset time period;
the identification module inputs the group image set and the group sound data into an identification model to obtain an identification result of whether each pig in the group raising fence output by the identification model is an abnormal pig;
the recognition model comprises a fusion processing sub-model, and the fusion processing sub-model outputs a result of whether any pig is an abnormal pig according to the combination of sign change information and individual sound data of any pig; the sign change information of any pig is determined according to the individual image set corresponding to any pig in the group image set; the individual sound data of any pig is determined according to the group sound data and the group image set.
Alternatively, the process may be carried out in a single-stage,
the recognition model further comprises an image segmentation sub-model, a sign extraction sub-model, an input sub-unit, a sound localization sub-model and a sound segmentation sub-unit:
The image segmentation sub-model performs image segmentation according to the group images to obtain individual image sets corresponding to each pig; for any pig, the sign extraction sub-model is used for extracting sign change information of any pig according to an individual image set corresponding to the any pig;
the input subunit is used for acquiring group sound data acquired at any time point according to the group sound data, and inputting the group sound data acquired at any time point into the sound positioning sub-model;
the sound positioning sub-model determines the position of a primary sound source corresponding to the group sound data acquired at any time point according to the position of the pickup device acquiring the group sound data in the group sound raising column and the group sound data acquired at any time point; the sound separation sub-unit outputs individual sound data corresponding to each pig according to the main sound source position corresponding to the group sound data acquired at each time point output by the sound positioning sub-model and the pig positions of each pig at different time points determined according to the group image set;
the fusion processing sub-model outputs a result of whether any pig is an abnormal pig according to the combination of the sign change information output by the sign extraction sub-model to any pig and the individual sound data corresponding to any pig output by the sound separation sub-unit;
The main sound source position represents the position of the pig which emits the maximum decibel sound in the group-raising fence at any time point.
Alternatively, the process may be carried out in a single-stage,
the sound separation sub-unit is used for:
acquiring a single frame image obtained by carrying out infrared image acquisition and/or image shooting on the group-fed fence at any time point according to the group image set, and acquiring a main sound source position corresponding to group sound data acquired at any time point according to the sound positioning sub-model;
judging whether pigs with the distance between the position of the main sound source and the position of each pig being smaller than or equal to a preset distance threshold value exist according to the position of each pig in the single-frame image, if so, taking the pig with the nearest distance to the position of the main sound source as a positioning pig, and taking group sound data acquired at any time point as group sound data corresponding to the positioning pig;
and acquiring group sound data corresponding to any pig from the group sound data acquired at each time point in the preset time period, and denoising the group sound data corresponding to any pig to acquire individual sound data corresponding to any pig.
Alternatively, the process may be carried out in a single-stage,
the image segmentation sub-model building process comprises the following steps:
acquiring a plurality of group image sets obtained by carrying out infrared image acquisition and/or image shooting on pigs in a group raising fence in a sampling time period, and taking the group image sets as sample group image sets, and dividing sample individual image sets corresponding to each pig from the sample group image sets;
and taking the sample group image set as input, taking the sample individual image set corresponding to each segmented pig as output, and carrying out model training through machine learning to obtain the image segmentation sub-model.
Alternatively, the process may be carried out in a single-stage,
the establishment process of the sign extraction sub-model comprises the following steps:
obtaining a sample individual image set of any sample pig, wherein the sample individual image set comprises at least one of the following images: continuously collecting a first image subset of any sample pig in a first time period of a cough state, continuously collecting a second image subset of any sample pig in a second time period of a dozing state, and continuously collecting an infrared image subset of any sample pig in a sampling time period;
taking the sample individual image set as input, taking sample sign change information as output, and performing model training through machine learning to obtain the sign extraction sub-model; wherein the sample sign change information includes at least one of the following information: information of coughing only of any sample pig in the first time period corresponding to the first image subset, information of dozing only of any sample pig in the second time period corresponding to the second image subset, and pig body temperature change information corresponding to the infrared image subset;
The first time period and the second time period are sub-time periods in a sampling time period for collecting a sample group image set; the first subset of images, the second subset of images, and the infrared subset of images are subsets of the sample individual image set.
Optionally, the process for establishing the sound localization submodel includes:
acquiring the position of each pickup device for collecting group sound data of pigs in a group raising fence in the group raising fence, and taking the group sound data collected by each pickup device at a set sampling time point as sample group sound data; at the set sampling time point, the sample pigs which emit the maximum decibel sound in the group raising fence are only positioned at the position of the sample primary sound source;
and taking the position of each pickup device for collecting the sample group sound data in the group-keeping fence and the sample group sound data collected at the set sampling time point as input, taking the sample primary sound source position as output, and performing model training through machine learning to obtain the sound positioning sub-model.
Optionally, the sound separation sub-unit is configured to:
acquiring a single-frame sample image obtained by carrying out infrared image acquisition and/or image shooting on the group-fed fence at the set sampling time point according to the sample group image set, and acquiring a sample primary sound source position corresponding to group sound data acquired at the set sampling time point according to the sound positioning sub-model;
Judging whether pigs with the distance between the position of the main sound source of the sample being smaller than or equal to a preset distance threshold exist according to the position of each pig in the single-frame sample image, if so, taking the pig with the nearest distance to the position of the main sound source of the sample as a positioning pig, and taking the group sound data acquired at the set sampling time point as the group sound data corresponding to the positioning pig;
and acquiring group sound data corresponding to any sample pig from group sound data acquired at each sampling time point in a sampling time period, and denoising the group sound data corresponding to any sample pig to obtain sample individual sound data corresponding to any sample pig.
Optionally, the process of establishing the fusion processing submodel includes:
acquiring an image segmentation sub-model, a physical sign extraction sub-model and a sound positioning sub-model which are obtained by model training through machine learning, and an input sub-unit and a sound segmentation sub-unit;
inputting a sample group image set into the image segmentation sub-model, and acquiring sample sign change information extracted from any sample pig by the sign extraction sub-model according to the individual image set of any sample pig in the image segmentation sub-model; the sample group image set is obtained by carrying out infrared image acquisition and/or image shooting on pigs in a group raising fence;
Inputting sample group sound data into the input subunit, inputting the sample group sound data acquired at the set sampling time point into the sound positioning sub-model by the input subunit, outputting sample individual sound data of any sample pig by the sound separation subunit according to the sample main sound source position corresponding to the group sound data acquired at each sampling time point in the sampling time period and the position of each pig in the sample group image, wherein the sample main sound source position corresponds to the group sound data acquired at each sampling time point in the sampling time period;
and taking the combination of the sample sign change information of any sample pig and the sample individual sound data as input, taking the result of whether any sample pig is an abnormal pig as output, and performing model training through machine learning to obtain the fusion processing sub-model.
In a second aspect, an embodiment of the present invention provides an abnormal pig recognition system based on image and audio mixing, including infrared cameras and/or video cameras disposed at different positions of a group-rearing fence, pickup devices disposed at different positions of the group-rearing fence, and the abnormal pig recognition device based on image and audio mixing described in any of the above;
The infrared camera is used for collecting infrared images of the group-rearing fence in which pigs are reared, obtaining a group image set comprising infrared images, and sending the obtained group image set to the abnormal pig recognition device based on image and audio mixing;
the camera is used for shooting the group breeding fence to obtain a group image set comprising shooting images, and sending the obtained group image set to the abnormal pig recognition device based on image and audio mixing;
the pickup device is used for carrying out sound collection on the group raising fence to obtain group sound data, and sending the obtained group sound data to the abnormal pig recognition device based on image and audio mixing.
In a third aspect, an embodiment of the present invention provides a method for identifying abnormal pigs based on image and audio mixing, including:
the method comprises the steps that an acquisition module acquires a group image set obtained by carrying out infrared image acquisition and/or image shooting on a group-rearing fence in which pigs are reared in a preset time period, and group sound data acquired by the pigs in the group-rearing fence in the preset time period;
the identification module inputs the group image set and the group sound data into an identification model to obtain an identification result of whether each pig in the group raising fence output by the identification model is an abnormal pig;
The recognition model comprises a fusion processing sub-model, and the fusion processing sub-model outputs a result of whether any pig is an abnormal pig according to the combination of sign change information and individual sound data of any pig; the sign change information of any pig is determined according to the individual image set corresponding to any pig in the group image set; the individual sound data of any pig is determined according to the group sound data and the group image set.
The embodiment of the invention provides an abnormal pig identification device, system and method based on image and audio mixing, which are used for acquiring a group image set and group sound data of pigs in a group raising fence and identifying whether each pig is an abnormal pig or not according to the group image set and the group sound data through an identification model in an identification module. The identification model comprises a fusion processing sub-model, and the fusion processing sub-model outputs an identification result of whether any pig is an abnormal pig according to sign change information and individual sound data of any pig determined by the group image set and the group sound data. Through the combination of the image and the sound, the method is favorable for improving the accuracy of identifying the abnormal pigs, and the reliability of the detection result is high. Meanwhile, manual detection is not needed, so that the detection efficiency of abnormal pigs is improved, epidemic situation prevention and control are effectively carried out, and loss is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a block diagram of an abnormal pig recognition device based on image and audio mixing according to an embodiment of the present invention;
fig. 2 is a schematic diagram of an identification model for identifying abnormal pigs according to another embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present 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.
Fig. 1 is a block diagram of an abnormal pig recognition device based on image and audio mixing according to the present embodiment, referring to fig. 1, the abnormal pig recognition device based on image and audio mixing includes an acquisition module 101 and a recognition module 102;
the acquiring module 101 acquires a group image set obtained by infrared image acquisition and/or image shooting of a group raising fence in which pigs are raised in a preset time period, and group sound data acquired by the pigs in the group raising fence in the preset time period;
the recognition module 102 inputs the group image set and the group sound data into a recognition model to obtain a recognition result of whether each pig in the group raising fence output by the recognition model is an abnormal pig;
the recognition model comprises a fusion processing sub-model, and the fusion processing sub-model outputs a result of whether any pig is an abnormal pig according to the combination of sign change information and individual sound data of any pig; the sign change information of any pig is determined according to the individual image set corresponding to any pig in the group image set; the individual sound data of any pig is determined according to the group sound data and the group image set.
The group image set is an image set obtained by continuously acquiring images of the group culture fence in the preset time period, and can be an image set formed by infrared images, an image set formed by shooting images or an image set formed by infrared images and shooting images together.
The group sound data are data obtained by continuously collecting sound of the group raising fence in the preset time period.
After the group image set and the group sound data are input into the recognition model, the recognition model extracts the sign change information and the individual sound data corresponding to each pig from the group image set and the group sound data, so that the fusion processing sub-model in the recognition model recognizes whether each pig is an abnormal pig according to the combination of the sign change information and the individual sound data corresponding to each pig, provides the reference of whether the pig is the abnormal pig for the breeder, is beneficial to the breeder to early check the abnormal pig, effectively prevents the transmission of infectious diseases and avoids the economic loss.
The embodiment provides an abnormal pig identification device based on image and audio mixing, which is used for acquiring a group image set and group sound data of pigs in a group raising fence and identifying whether each pig is an abnormal pig according to the group image set and the group sound data through an identification model in an identification module. The identification model comprises a fusion processing sub-model, and the fusion processing sub-model outputs an identification result of whether any pig is an abnormal pig according to sign change information and individual sound data of any pig determined by the group image set and the group sound data. Through the combination of the image and the sound, the method is favorable for improving the accuracy of identifying the abnormal pigs, and the reliability of the detection result is high. Meanwhile, manual detection is not needed, so that the detection efficiency of abnormal pigs is improved, epidemic situation prevention and control are effectively carried out, and loss is reduced.
Further, on the basis of the above embodiment, the recognition model further includes an image segmentation sub-model, a sign extraction sub-model, an input sub-unit, a sound localization sub-model, and a sound segmentation sub-unit;
the image segmentation sub-model performs image segmentation according to the group images to obtain individual image sets corresponding to each pig; for any pig, the sign extraction sub-model is used for extracting sign change information of any pig according to an individual image set corresponding to the any pig;
the input subunit is used for acquiring group sound data acquired at any time point according to the group sound data, and inputting the group sound data acquired at any time point into the sound positioning sub-model;
the sound positioning sub-model determines the position of a primary sound source corresponding to the group sound data acquired at any time point according to the position of the pickup device acquiring the group sound data in the group sound raising column and the group sound data acquired at any time point; the sound separation sub-unit outputs individual sound data corresponding to each pig according to the main sound source position corresponding to the group sound data acquired at each time point output by the sound positioning sub-model and the pig positions of each pig at different time points determined according to the group image set;
The fusion processing sub-model outputs a result of whether any pig is an abnormal pig according to the combination of the sign change information output by the sign extraction sub-model to any pig and the individual sound data corresponding to any pig output by the sound separation sub-unit;
the main sound source position represents the position of the pig which emits the maximum decibel sound in the group-raising fence at any time point.
Fig. 2 is a schematic diagram of the recognition model provided in this embodiment for recognizing abnormal pigs, referring to fig. 2, the image segmentation sub-model and the sign extraction sub-model extract sign change information of any pig according to the input group image set. The input subunit, the sound positioning subunit model and the sound separation subunit extract individual sound data of any pig according to the group image set and the group sound data. The fusion processing sub-model realizes the identification of whether any pig is an abnormal pig according to the combination of the sign change information and the individual sound data of any pig.
It should be noted that the image segmentation sub-model, the sign extraction sub-model and the sound localization sub-model may be models obtained by training through machine learning, or may be models in which corresponding functions are realized through a combination of functions, which is not particularly limited in this embodiment.
According to the method, the device and the system for identifying the abnormal pigs, the identification model composed of the image segmentation sub-model, the physical sign extraction sub-model, the input sub-unit, the sound positioning sub-model, the sound separation sub-unit and the fusion processing sub-module in the identification model is used for identifying the abnormal pigs by combining images and sounds, and the accuracy of identifying the abnormal pigs is improved.
Further, on the basis of the above embodiments, the sound separation unit is configured to:
acquiring a single frame image obtained by carrying out infrared image acquisition and/or image shooting on the group-fed fence at any time point according to the group image set, and acquiring a main sound source position corresponding to group sound data acquired at any time point according to the sound positioning sub-model;
judging whether pigs with the distance between the position of the main sound source and the position of each pig being smaller than or equal to a preset distance threshold value exist according to the position of each pig in the single-frame image, if so, taking the pig with the nearest distance to the position of the main sound source as a positioning pig, and taking group sound data acquired at any time point as group sound data corresponding to the positioning pig;
and acquiring group sound data corresponding to any pig from the group sound data acquired at each time point in the preset time period, and denoising the group sound data corresponding to any pig to acquire individual sound data corresponding to any pig.
In brief, the sound separation sub-unit is used for combining the positions of pigs in the group image set and the primary sound source positions corresponding to the group sound data collected at each time point in the preset time period determined by the sound positioning sub-model, and the group sound data collected at each time point is corresponding to pigs so as to obtain individual sound data corresponding to each pig.
The position of each pig in the single frame image can be determined according to the mark positions preset in the group-raising columns, for example, two or more mark positions are marked in the group-raising columns in advance, and the position of each pig in the actual group-raising columns can be determined by combining the relative distance between each mark position and any mark position according to the relative distance between each mark position and the image when the actual relative distance between each mark position and the image is known.
Wherein the preset distance threshold is a set value, for example, 3 meters.
If it is judged that no pig with the distance smaller than or equal to the preset distance threshold exists, processing is not performed, and whether the group sound data collected at the next time point exist corresponding positioning pigs is continuously judged until the operation of judging whether the pig with the distance smaller than or equal to the preset distance threshold exists or not is performed on the group sound data collected at each time point in the preset time period.
After determining pigs corresponding to the group sound data collected at each time point by combining the positions of the pigs in the single frame image at each time point and the group sound data collected at each time point, obtaining the group sound data collected at each time point corresponding to any pig, and supplementing reference sound data to the time point without the group sound data corresponding to any pig, thereby obtaining the individual sound data of any pig. The individual sound data of any pig comprises reference sound data or group sound data corresponding to any pig at each time point of the preset time period. The reference sound data is sound data collected for normal pigs or set sound data for a section, the reference sound data does not influence the data characteristics of group sound data expression in individual sound data, namely, the judging process of abnormal pigs is not influenced, and the reference sound data is only used for supplementing the sound data for a preset time period completely.
In this embodiment, the sound separation unit combines the positions of pigs in a single frame image and the positions of primary sound sources for locating group sound data, so as to separate sound data, determine individual sound data corresponding to each pig, and identify abnormal pigs according to the individual sound data and sign change information.
Further, on the basis of the above embodiments, the process for establishing the image segmentation sub-model includes:
acquiring a plurality of group image sets obtained by carrying out infrared image acquisition and/or image shooting on pigs in a group raising fence in a preset sampling time period, and taking the group image sets as sample group image sets, and dividing sample individual image sets corresponding to each pig from the sample group image sets;
and taking the sample group image set as input, taking the sample individual image set corresponding to each segmented pig as output, and carrying out model training through machine learning to obtain the image segmentation sub-model.
Wherein the image segmentation sub-model may be a model of convolutional neural network type.
And obtaining the image segmentation sub-model through a training process of a model by taking a plurality of sample group image sets as input and taking a sample individual image set corresponding to each segmented pig as output.
According to the embodiment, training of the image segmentation sub-model is achieved through machine learning, so that the image segmentation sub-model can separate individual image sets corresponding to each pig from the group image sets.
Further, on the basis of the above embodiments, the process for establishing the sign extraction sub-model includes:
Obtaining a sample individual image set of any sample pig, wherein the sample individual image set comprises at least one of the following images: continuously collecting a first image subset of any sample pig in a first time period of a cough state, continuously collecting a second image subset of any sample pig in a second time period of a dozing state, and continuously collecting an infrared image subset of any sample pig in a preset sampling time period;
taking the sample individual image set as input, taking sample sign change information as output, and performing model training through machine learning to obtain the sign extraction sub-model; wherein the sample sign change information includes at least one of the following information: information of coughing only of any sample pig in the first time period corresponding to the first image subset, information of dozing only of any sample pig in the second time period corresponding to the second image subset, and pig body temperature change information corresponding to the infrared image subset;
the first time period and the second time period are sub-time periods in a sampling time period for collecting a sample group image set; the first subset of images, the second subset of images, and the infrared subset of images are subsets of the sample individual image set.
The image segmentation sub-model can also be a model of a convolutional neural network type.
The sample sign change information may be marked in advance according to a sample individual image set, for example, the sample sign change information is a sampling time period before a first time period, the any sample pig has no abnormal sign, the any sample pig has a cough in the first time period, and the any sample pig has no abnormal sign in the sampling time period after the first time period.
Typically, the information of the change in body temperature extracted by the infrared image subset and the information of the occurrence of coughing and/or dozing extracted by the image capturing image (including the first image subset and/or the second image subset) are two-dimensional information among the sample sign change information. The two-dimensional information can be used as a part of the change information of the sample body sign together to participate in the subsequent identification process of abnormal pigs.
And training the model through a plurality of sample individual image sets and sample sign change information extracted from the sample individual image sets to obtain a sign extraction sub-model.
According to the embodiment, the training of the sign extraction sub-model is realized through the sample sign change information extracted from the sample individual image set in advance, and the sign change information of each pig is extracted through the sign extraction sub-model, so that the identification of abnormal pigs is realized based on the combination of the sign change information and the individual sound data.
Further, on the basis of the above embodiments, the process for establishing the sound localization submodel includes:
acquiring the position of each pickup device for collecting group sound data of pigs in a group raising fence in the group raising fence, and taking the group sound data collected by each pickup device at a set sampling time point as sample group sound data; at the set sampling time point, the sample pigs which emit the maximum decibel sound in the group raising fence are only positioned at the position of the sample primary sound source;
and taking the position of each pickup device for collecting the sample group sound data in the group-keeping fence and the sample group sound data collected at the set sampling time point as input, taking the sample primary sound source position as output, and performing model training through machine learning to obtain the sound positioning sub-model.
The sample group sound data includes sample group sound data collected by a plurality of sound pickup devices. In the process of determining the sound data of the sample group, the position of the sample pig which emits the maximum decibel sound in the group raising fence at the set sampling time point can be determined by a raising personnel and used as the position of the sample primary sound source.
The sound localization sub-model may also be a model of convolutional neural network type.
And training through a plurality of groups of training samples to obtain the sound positioning sub-model. The training sample is data which takes the position of each pickup device for collecting the sample group sound data in the group culture fence and takes the sample group sound data collected at the set sampling time point as input and takes the sample primary sound source position as output.
According to the method, training of the sound positioning sub-model is achieved through machine learning, positioning pigs corresponding to group sound data collected at each time point are separated through the sound positioning sub-model, individual sound data corresponding to each pig are determined, and recognition of abnormal pigs is achieved through combination of sign change information and the individual sound data, so that accuracy is higher.
Further, on the basis of the above embodiments, the sound separation unit is configured to:
acquiring a single-frame sample image obtained by carrying out infrared image acquisition and/or image shooting on the group-fed fence at the set sampling time point according to the sample group image set, and acquiring a sample primary sound source position corresponding to group sound data acquired at the set sampling time point according to the sound positioning sub-model;
Judging whether pigs with the distance between the position of the main sound source of the sample being smaller than or equal to a preset distance threshold exist according to the position of each pig in the single-frame sample image, if so, taking the pig with the nearest distance to the position of the main sound source of the sample as a positioning pig, and taking the group sound data acquired at the set sampling time point as the group sound data corresponding to the positioning pig;
and acquiring group sound data corresponding to any sample pig from group sound data acquired at each sampling time point in a sampling time period, and denoising the group sound data corresponding to any sample pig to obtain sample individual sound data corresponding to any sample pig.
The noise reduction is performed on the group sound data corresponding to any one of the sample pigs, so as to reduce the noise generated by the sound data corresponding to the largest decibel in the group sound data corresponding to any one of the sample pigs, namely, the sound data corresponding to the largest decibel of the background noise.
According to the embodiment, the determination of the individual sound data corresponding to each pig is realized by combining the main sound source position corresponding to the group sound data acquired by the sound positioning sub-model at each set sampling time point and the position corresponding to each sample pig in the group image set through the sound separation sub-unit, so that the identification of abnormal pigs is realized by combining the sign change information and the individual sound data, and the accuracy is higher.
Further, on the basis of the above embodiments, the process of establishing the fusion processing submodel includes:
acquiring an image segmentation sub-model, a physical sign extraction sub-model and a sound positioning sub-model which are obtained by model training through machine learning, and an input sub-unit and a sound segmentation sub-unit;
inputting a sample group image set into the image segmentation sub-model, and acquiring sample sign change information extracted from any sample pig by the sign extraction sub-model according to the individual image set of any sample pig in the image segmentation sub-model; the sample group image set is obtained by carrying out infrared image acquisition and/or image shooting on pigs in a group raising fence;
inputting sample group sound data into the input subunit, inputting the sample group sound data acquired at the set sampling time point into the sound positioning sub-model by the input subunit, outputting sample individual sound data of any sample pig by the sound separation subunit according to the sample main sound source position corresponding to the group sound data acquired at each sampling time point in the sampling time period and the position of each pig in the sample group image, wherein the sample main sound source position corresponds to the group sound data acquired at each sampling time point in the sampling time period;
And taking the combination of the sample sign change information of any sample pig and the sample individual sound data as input, taking the result of whether any sample pig is an abnormal pig as output, and performing model training through machine learning to obtain the fusion processing sub-model.
The fusion processing sub-model can also be a model of a convolutional neural network type.
The training of the fusion processing submodel is realized by combining an input subunit and a sound separation subunit based on the trained image segmentation submodel, the sign extraction submodel and the sound positioning submodel. The results of whether the sample pigs are abnormal pigs are marked manually.
And training the model through machine learning through a plurality of groups of training samples to obtain a fusion processing sub-model. The training sample comprises a sample which takes the combination of sample sign change information and sample individual sound data as input and takes the result of whether the sample pig is an abnormal pig or not as output.
The embodiment realizes the training process of the fusion processing submodel through the image segmentation submodel, the sign extraction submodel, the sound positioning submodel, the input subunit and the sound separation subunit. The fusion processing sub-model is combined with the sign change information and the individual sound data to realize the identification of the abnormal pigs, and the accuracy of the identification of the abnormal pigs is higher.
The embodiment provides an abnormal pig identification system based on image and audio mixing, which comprises infrared cameras and/or video cameras arranged at different positions of a group-rearing fence, pickup devices arranged at different positions of the group-rearing fence, and the abnormal pig identification device based on image and audio mixing;
the infrared camera is used for collecting infrared images of the group-rearing fence in which pigs are reared, obtaining a group image set comprising infrared images, and sending the obtained group image set to the abnormal pig recognition device based on image and audio mixing;
the camera is used for shooting the group breeding fence to obtain a group image set comprising shooting images, and sending the obtained group image set to the abnormal pig recognition device based on image and audio mixing;
the pickup device is used for carrying out sound collection on the group raising fence to obtain group sound data, and sending the obtained group sound data to the abnormal pig recognition device based on image and audio mixing.
The infrared camera is arranged around and/or above the top of the group-raising fence and used for collecting infrared images of pigs in the group-raising fence in all directions. The camera is also arranged around and/or above the top of the group-raising fence and used for collecting images of pigs in the group-raising fence in all directions. The pickup device includes a plurality of, sets up in the different positions of group's fence, for example, four positions each set up a pickup device in the southeast northwest of the fence is supported to the group.
The embodiment provides an abnormal pig identification system based on image and audio mixing, which comprises an infrared camera and/or a camera, pick-up equipment and an abnormal pig identification device based on image and audio mixing. The system acquires a group image set and group sound data of pigs in a group raising fence, and identifies whether each pig is an abnormal pig according to the group image set and the group sound data through an identification model in an identification module. The identification model comprises a fusion processing sub-model, and the fusion processing sub-model outputs an identification result of whether any pig is an abnormal pig according to sign change information and individual sound data of any pig determined by the group image set and the group sound data. Through the combination of the image and the sound, the method is favorable for improving the accuracy of identifying the abnormal pigs, and the reliability of the detection result is high. Meanwhile, manual detection is not needed, so that the detection efficiency of abnormal pigs is improved, epidemic situation prevention and control are effectively carried out, and loss is reduced.
The embodiment provides an abnormal pig identification method based on image and audio mixing, which comprises the following steps:
s1: the method comprises the steps that an acquisition module acquires a group image set obtained by carrying out infrared image acquisition and/or image shooting on a group-rearing fence in which pigs are reared in a preset time period, and group sound data acquired by the pigs in the group-rearing fence in the preset time period;
S2: the identification module inputs the group image set and the group sound data into an identification model to obtain an identification result of whether each pig in the group raising fence output by the identification model is an abnormal pig;
the recognition model comprises a fusion processing sub-model, and the fusion processing sub-model outputs a result of whether any pig is an abnormal pig according to the combination of sign change information and individual sound data of any pig; the sign change information of any pig is determined according to the individual image set corresponding to any pig in the group image set; the individual sound data of any pig is determined according to the group sound data and the group image set.
The method for identifying abnormal pigs based on image and audio mixing provided in this embodiment is applicable to the device for identifying abnormal pigs based on image and audio mixing provided in each embodiment, and is not described herein.
The embodiment provides an abnormal pig identification method based on image and audio mixing, which is used for acquiring a group image set and group sound data of pigs in a group raising fence and identifying whether each pig is an abnormal pig according to the group image set and the group sound data through an identification model in an identification module. The identification model comprises a fusion processing sub-model, and the fusion processing sub-model outputs an identification result of whether any pig is an abnormal pig according to sign change information and individual sound data of any pig determined by the group image set and the group sound data. Through the combination of the image and the sound, the method is favorable for improving the accuracy of identifying the abnormal pigs, and the reliability of the detection result is high. Meanwhile, manual detection is not needed, so that the detection efficiency of abnormal pigs is improved, epidemic situation prevention and control are effectively carried out, and loss is reduced.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. The abnormal pig identification device based on the image and audio mixing is characterized by comprising an acquisition module and an identification module;
the acquisition module acquires a group image set obtained by carrying out infrared image acquisition and/or image shooting on a group-rearing fence in which pigs are reared in a preset time period, and group sound data acquired by the pigs in the group-rearing fence in the preset time period;
the identification module inputs the group image set and the group sound data into an identification model to obtain an identification result of whether each pig in the group raising fence output by the identification model is an abnormal pig;
the recognition model comprises a fusion processing sub-model, and the fusion processing sub-model outputs a result of whether any pig is an abnormal pig according to the combination of sign change information and individual sound data of any pig; the sign change information of any pig is determined according to the individual image set corresponding to any pig in the group image set; the individual sound data of any pig is determined according to the group sound data and the group image set;
The recognition model further comprises an image segmentation sub-model, a sign extraction sub-model, an input sub-unit, a sound localization sub-model and a sound segmentation sub-unit:
the image segmentation sub-model performs image segmentation according to the group images to obtain individual image sets corresponding to each pig; for any pig, the sign extraction sub-model is used for extracting sign change information of any pig according to an individual image set corresponding to the any pig;
the input subunit is used for acquiring group sound data acquired at any time point according to the group sound data, and inputting the group sound data acquired at any time point into the sound positioning sub-model;
the sound positioning sub-model determines the position of a primary sound source corresponding to the group sound data acquired at any time point according to the position of the pickup device acquiring the group sound data in the group sound raising column and the group sound data acquired at any time point; the sound separation sub-unit outputs individual sound data corresponding to each pig according to the main sound source position corresponding to the group sound data acquired at each time point output by the sound positioning sub-model and the pig positions of each pig at different time points determined according to the group image set; the main sound source position represents the position of the pig which emits the maximum decibel sound in the group-raising fence at any time point;
The fusion processing sub-model outputs a result of whether any pig is an abnormal pig according to the combination of the sign change information output by the sign extraction sub-model to any pig and the individual sound data corresponding to any pig output by the sound separation sub-unit;
the sound separation sub-unit is used for acquiring a single frame image obtained by carrying out infrared image acquisition and/or image shooting on the group-raising fence at any time point according to the group image set, and acquiring a primary sound source position corresponding to group sound data acquired at any time point according to the sound positioning sub-model;
judging whether pigs with the distance between the position of the main sound source and the position of each pig being smaller than or equal to a preset distance threshold value exist according to the position of each pig in the single-frame image, if so, taking the pig with the nearest distance to the position of the main sound source as a positioning pig, and taking group sound data acquired at any time point as group sound data corresponding to the positioning pig;
acquiring group sound data corresponding to any pig from group sound data acquired at each time point in the preset time period, and denoising the group sound data corresponding to any pig to acquire individual sound data corresponding to any pig;
The group sound data corresponding to any sample pig is used for reducing noise, and the noise is used for reducing sound data corresponding to the largest decibel in the group sound data corresponding to any sample pig, so that interference generated by the sound data corresponding to the largest decibel of background noise is reduced.
2. The abnormal pig recognition device based on image and audio mixing according to claim 1, wherein the image segmentation sub-model building process comprises:
acquiring a plurality of group image sets obtained by carrying out infrared image acquisition and/or image shooting on pigs in a group raising fence in a sampling time period, and taking the group image sets as sample group image sets, and dividing sample individual image sets corresponding to each pig from the sample group image sets;
and taking the sample group image set as input, taking the sample individual image set corresponding to each segmented pig as output, and carrying out model training through machine learning to obtain the image segmentation sub-model.
3. The abnormal pig recognition device based on image and audio mixing according to claim 1, wherein the establishment process of the sign extraction sub-model comprises:
obtaining a sample individual image set of any sample pig, wherein the sample individual image set comprises at least one of the following images: continuously collecting a first image subset of any sample pig in a first time period of a cough state, continuously collecting a second image subset of any sample pig in a second time period of a dozing state, and continuously collecting an infrared image subset of any sample pig in a sampling time period;
Taking the sample individual image set as input, taking sample sign change information as output, and performing model training through machine learning to obtain the sign extraction sub-model; wherein the sample sign change information includes at least one of the following information: information of coughing only of any sample pig in the first time period corresponding to the first image subset, information of dozing only of any sample pig in the second time period corresponding to the second image subset, and pig body temperature change information corresponding to the infrared image subset;
the first time period and the second time period are sub-time periods in a sampling time period for collecting a sample group image set; the first subset of images, the second subset of images, and the infrared subset of images are subsets of the sample individual image set.
4. The abnormal pig recognition device based on image and audio mixing according to claim 1, wherein the process of creating the sound localization submodel comprises:
acquiring the position of each pickup device for collecting group sound data of pigs in a group raising fence in the group raising fence, and taking the group sound data collected by each pickup device at a set sampling time point as sample group sound data; at the set sampling time point, the sample pigs which emit the maximum decibel sound in the group raising fence are only positioned at the position of the sample primary sound source;
And taking the position of each pickup device for collecting the sample group sound data in the group-keeping fence and the sample group sound data collected at the set sampling time point as input, taking the sample primary sound source position as output, and performing model training through machine learning to obtain the sound positioning sub-model.
5. The abnormal swine identifying device based on image and audio mixing of claim 4, wherein the sound separation sub-unit is configured to:
acquiring a single-frame sample image obtained by carrying out infrared image acquisition and/or image shooting on the group-fed fence at the set sampling time point according to the sample group image set, and acquiring a sample primary sound source position corresponding to group sound data acquired at the set sampling time point according to the sound positioning sub-model;
judging whether pigs with the distance between the position of the main sound source of the sample being smaller than or equal to a preset distance threshold exist according to the position of each pig in the single-frame sample image, if so, taking the pig with the nearest distance to the position of the main sound source of the sample as a positioning pig, and taking the group sound data acquired at the set sampling time point as the group sound data corresponding to the positioning pig;
And obtaining group sound data corresponding to any sample pig from group sound data collected at each sampling time point in a sampling time period, and carrying out noise reduction on the group sound data corresponding to any sample pig to obtain sample individual sound data corresponding to any sample pig.
6. The abnormal pig recognition device based on image and audio mixing according to claim 5, wherein the process of establishing the fusion processing submodel comprises:
acquiring an image segmentation sub-model, a physical sign extraction sub-model and a sound positioning sub-model which are obtained by model training through machine learning, and an input sub-unit and a sound segmentation sub-unit;
inputting a sample group image set into the image segmentation sub-model, and acquiring sample sign change information extracted from any sample pig by the sign extraction sub-model according to the individual image set of any sample pig in the image segmentation sub-model; the sample group image set is obtained by carrying out infrared image acquisition and/or image shooting on pigs in a group raising fence;
inputting sample group sound data into the input subunit, inputting the sample group sound data acquired at the set sampling time point into the sound positioning sub-model by the input subunit, outputting sample individual sound data of any sample pig by the sound separation subunit according to the sample main sound source position corresponding to the group sound data acquired at each sampling time point in the sampling time period and the position of each pig in the sample group image, wherein the sample main sound source position corresponds to the group sound data acquired at each sampling time point in the sampling time period;
And taking the combination of the sample sign change information of any sample pig and the sample individual sound data as input, taking the result of whether any sample pig is an abnormal pig as output, and performing model training through machine learning to obtain the fusion processing sub-model.
7. An abnormal pig recognition system based on image and audio mixing, which is characterized by comprising an infrared camera and/or a video camera arranged at different positions of a group-rearing fence, pickup equipment arranged at different positions of the group-rearing fence, and the abnormal pig recognition device based on image and audio mixing, as defined in any one of claims 1 to 6;
the infrared camera is used for collecting infrared images of the group-rearing fence in which pigs are reared, obtaining a group image set comprising infrared images, and sending the obtained group image set to the abnormal pig recognition device based on image and audio mixing;
the camera is used for shooting the group breeding fence to obtain a group image set comprising shooting images, and sending the obtained group image set to the abnormal pig recognition device based on image and audio mixing;
the pickup device is used for carrying out sound collection on the group raising fence to obtain group sound data, and sending the obtained group sound data to the abnormal pig recognition device based on image and audio mixing.
8. An abnormal pig identification method based on image and audio mixing is characterized by comprising the following steps:
the method comprises the steps that an acquisition module acquires a group image set obtained by carrying out infrared image acquisition and/or image shooting on a group-rearing fence in which pigs are reared in a preset time period, and group sound data acquired by the pigs in the group-rearing fence in the preset time period;
the recognition module inputs the group image set and the group sound data into a recognition model to obtain a recognition result of whether each pig in the group raising fence output by the recognition model is an abnormal pig;
the recognition model comprises a fusion processing sub-model, and the fusion processing sub-model outputs a result of whether any pig is an abnormal pig according to the combination of sign change information and individual sound data of any pig; the sign change information of any pig is determined according to the individual image set corresponding to any pig in the group image set; the individual sound data of any pig is determined according to the group sound data and the group image set;
the recognition model further comprises an image segmentation sub-model, a sign extraction sub-model, an input sub-unit, a sound localization sub-model and a sound segmentation sub-unit:
The image segmentation sub-model performs image segmentation according to the group images to obtain individual image sets corresponding to each pig; for any pig, the sign extraction sub-model extracts sign change information of any pig according to an individual image set corresponding to the any pig;
the input subunit acquires group sound data acquired at any time point according to the group sound data, and inputs the group sound data acquired at any time point into the sound positioning sub-model;
the sound positioning sub-model determines the position of a primary sound source corresponding to the group sound data acquired at any time point according to the position of the pickup device acquiring the group sound data in the group sound raising column and the group sound data acquired at any time point; the sound separation sub-unit outputs individual sound data corresponding to each pig according to the main sound source position corresponding to the group sound data acquired at each time point output by the sound positioning sub-model and the pig positions of each pig at different time points determined according to the group image set; the main sound source position represents the position of the pig which emits the maximum decibel sound in the group-raising fence at any time point;
The fusion processing sub-model outputs a result of whether any pig is an abnormal pig according to the combination of the sign change information output by the sign extraction sub-model to any pig and the individual sound data corresponding to any pig output by the sound separation sub-unit;
the sound separation sub-unit acquires a single frame image obtained by infrared image acquisition and/or shooting of the group-raising fence at any time point according to the group image set, and acquires a main sound source position corresponding to group sound data acquired at any time point according to the sound positioning sub-model;
judging whether pigs with the distance between the position of the main sound source and the position of each pig being smaller than or equal to a preset distance threshold value exist according to the position of each pig in the single-frame image, if so, taking the pig with the nearest distance to the position of the main sound source as a positioning pig, and taking group sound data acquired at any time point as group sound data corresponding to the positioning pig;
acquiring group sound data corresponding to any pig from group sound data acquired at each time point in the preset time period, and denoising the group sound data corresponding to any pig to acquire individual sound data corresponding to any pig;
The group sound data corresponding to any sample pig is used for reducing noise, and the noise is used for reducing sound data corresponding to the largest decibel in the group sound data corresponding to any sample pig, so that interference generated by the sound data corresponding to the largest decibel of background noise is reduced.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010600412.4A CN111860203B (en) | 2020-06-28 | 2020-06-28 | Abnormal pig identification device, system and method based on image and audio mixing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010600412.4A CN111860203B (en) | 2020-06-28 | 2020-06-28 | Abnormal pig identification device, system and method based on image and audio mixing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111860203A CN111860203A (en) | 2020-10-30 |
| CN111860203B true CN111860203B (en) | 2023-09-01 |
Family
ID=72988744
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010600412.4A Active CN111860203B (en) | 2020-06-28 | 2020-06-28 | Abnormal pig identification device, system and method based on image and audio mixing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111860203B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113537064A (en) * | 2021-07-16 | 2021-10-22 | 河南牧原智能科技有限公司 | Weak pig automatic detection marking method and system |
| CN113709378A (en) * | 2021-09-08 | 2021-11-26 | 联想(北京)有限公司 | Processing method and device, camera equipment and electronic system |
| CN113762219A (en) * | 2021-11-03 | 2021-12-07 | 恒林家居股份有限公司 | Method, system and storage medium for identifying people in mobile conference room |
| CN117423342A (en) * | 2023-10-27 | 2024-01-19 | 东北农业大学 | Pig abnormal state monitoring method and system based on edge calculation |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104064011A (en) * | 2014-07-02 | 2014-09-24 | 江苏大学 | Breeding pig delivery room monitoring system and method based on wireless transmission |
| CN107182830A (en) * | 2017-06-09 | 2017-09-22 | 中国农业科学院农业信息研究所 | A kind of sow farrowing bed monitoring warning device, method and system |
| 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 |
| CN109637549A (en) * | 2018-12-13 | 2019-04-16 | 北京小龙潜行科技有限公司 | A kind of pair of pig carries out the method, apparatus and detection system of sound detection |
| CN109684953A (en) * | 2018-12-13 | 2019-04-26 | 北京小龙潜行科技有限公司 | The method and device of pig tracking is carried out based on target detection and particle filter algorithm |
| CN110598643A (en) * | 2019-09-16 | 2019-12-20 | 上海秒针网络科技有限公司 | Method and device for monitoring piglet compression |
-
2020
- 2020-06-28 CN CN202010600412.4A patent/CN111860203B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104064011A (en) * | 2014-07-02 | 2014-09-24 | 江苏大学 | Breeding pig delivery room monitoring system and method based on wireless transmission |
| CN107182830A (en) * | 2017-06-09 | 2017-09-22 | 中国农业科学院农业信息研究所 | A kind of sow farrowing bed monitoring warning device, method and system |
| 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 |
| CN109637549A (en) * | 2018-12-13 | 2019-04-16 | 北京小龙潜行科技有限公司 | A kind of pair of pig carries out the method, apparatus and detection system of sound detection |
| CN109684953A (en) * | 2018-12-13 | 2019-04-26 | 北京小龙潜行科技有限公司 | The method and device of pig tracking is carried out based on target detection and particle filter algorithm |
| CN110598643A (en) * | 2019-09-16 | 2019-12-20 | 上海秒针网络科技有限公司 | Method and device for monitoring piglet compression |
Non-Patent Citations (1)
| Title |
|---|
| 基于深层神经网络的猪声音分类;苍岩;罗顺元;乔玉龙;;农业工程学报(第09期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111860203A (en) | 2020-10-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111860203B (en) | Abnormal pig identification device, system and method based on image and audio mixing | |
| CN110473192B (en) | Digestive tract endoscope image recognition model training and recognition method, device and system | |
| CN110705405B (en) | Target labeling method and device | |
| ZA202300610B (en) | System and method for crop monitoring | |
| CN111968152B (en) | Dynamic identity recognition method and device | |
| CN109993130A (en) | One kind being based on depth image dynamic sign language semantics recognition system and method | |
| CN113435355A (en) | Multi-target cow identity identification method and system | |
| CN111325133A (en) | Image processing system based on artificial intelligence recognition | |
| CN110613417A (en) | Method, equipment and storage medium for outputting upper digestion endoscope operation information | |
| KR102163108B1 (en) | Method and system for detecting in real time an object of interest in image | |
| CN111783751A (en) | Rifle ball linkage and BIM-based breeding house piglet abnormity early warning method | |
| CN110941992A (en) | Smile expression detection method and device, computer equipment and storage medium | |
| CN109949272A (en) | Identify the collecting method and system of skin disease type acquisition human skin picture | |
| CN115376210B (en) | Drowning behavior identification method, device, equipment and medium for preventing drowning in swimming pool | |
| CN111753925A (en) | Multi-model fusion medical image classification method and equipment | |
| Mar et al. | A hybrid approach: image processing techniques and deep learning method for cow detection and tracking system | |
| CN113553965B (en) | Person identity recognition method combining face recognition and human body recognition | |
| KR20200123324A (en) | A method for pig segmentation using connected component analysis and yolo algorithm | |
| CN115205747A (en) | Automatic road detection system based on image recognition | |
| CN113627255A (en) | Mouse behavior quantitative analysis method, device, equipment and readable storage medium | |
| CN106599764A (en) | Lip-shape-characteristic-based living body determination method and equipment | |
| CN111860415A (en) | Cough detection method, device, storage medium and electronic device | |
| CN111353511A (en) | Number recognition device and method | |
| CN115909464B (en) | Self-adaptive weak supervision tag marking method for pedestrian re-identification | |
| CN110889411B (en) | Universal image recognition model based on AI chip |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |