CN112541432A - Video livestock identity authentication system and method based on deep learning - Google Patents
Video livestock identity authentication system and method based on deep learning Download PDFInfo
- Publication number
- CN112541432A CN112541432A CN202011457933.5A CN202011457933A CN112541432A CN 112541432 A CN112541432 A CN 112541432A CN 202011457933 A CN202011457933 A CN 202011457933A CN 112541432 A CN112541432 A CN 112541432A
- Authority
- CN
- China
- Prior art keywords
- livestock
- video
- identity
- module
- deep learning
- 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
- 244000144972 livestock Species 0.000 title claims abstract description 245
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000013135 deep learning Methods 0.000 title claims abstract description 33
- 238000001514 detection method Methods 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 22
- 238000012549 training Methods 0.000 claims abstract description 16
- 230000000007 visual effect Effects 0.000 claims abstract description 11
- 230000000694 effects Effects 0.000 claims abstract description 9
- 230000008569 process Effects 0.000 claims description 13
- 238000009395 breeding Methods 0.000 claims description 7
- 230000001488 breeding effect Effects 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 4
- 238000013145 classification model Methods 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 239000013598 vector Substances 0.000 claims description 3
- 238000007726 management method Methods 0.000 abstract 2
- 238000013500 data storage Methods 0.000 abstract 1
- 210000000887 face Anatomy 0.000 description 10
- 210000003128 head Anatomy 0.000 description 6
- 230000008901 benefit Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 241000283690 Bos taurus Species 0.000 description 1
- 241000283086 Equidae Species 0.000 description 1
- 241000283074 Equus asinus Species 0.000 description 1
- 241001331845 Equus asinus x caballus Species 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 241000282887 Suidae Species 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 238000009360 aquaculture Methods 0.000 description 1
- 244000144974 aquaculture Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/49—Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes
Abstract
The invention discloses a video livestock identity authentication system and method based on deep learning, and relates to the technical field of deep learning. The system comprises a livestock identity establishing module, a video processing module, a livestock detecting module, a livestock tracking module, a livestock identity identifying module and a visual recording module; the method comprises the following steps: s1, acquiring video pictures by livestock; s2, manual marking; s3, training a detection model; s4, training a livestock identity recognition model; s5, feature storage and image data storage; s6, using the identity authentication model to extract the characteristics and compare the characteristics with the livestock with the established library; s7, identifying the livestock identity by using a tracking module; and S8, effectively identifying unknown livestock. The invention can be compatible with livestock in various activity states, has high identification accuracy, can be shot by a mobile phone conveniently and quickly, can be used for feeding management of farmers and insurance company insurance claim settlement and driving protection, and realizes efficient and accurate management and control.
Description
Technical Field
The invention belongs to the technical field of deep learning, and particularly relates to a video livestock identity authentication system based on deep learning and a video livestock identity authentication method based on deep learning.
Background
For the traditional livestock industry, effective management of livestock and control of the dynamics of livestock are of great importance, and with the national emphasis on the livestock industry, the breeding insurance is successively released in a plurality of areas of China so as to reduce the loss of farmers. As a policy insurance benefiting three farmers, the livestock insurance can effectively reduce the disaster risks caused by various diseases or natural disasters and enhance the capability of farmers in resisting the natural disasters and coping with the risks. In order to better serve farmers and guarantee the benefits of insurance companies, the identification work of the insurable livestock needs to be done.
The livestock insurance uses cattle, horses, mules, donkeys, pigs and other livestock as insurance targets. Livestock insurance is one of the agricultural insurance, and entails the loss of livestock due to death from disease or other accidents (wind, rain, water, fire, etc.). The traditional insurance claim settlement evidence collection mainly combines two modes of ear tag number and photo comparison. The ear tag number is usually taken as a unique identification mark for confirming the identity of the livestock, after the livestock is in danger, an indemnifier firstly confirms whether the livestock is a security mark according to the ear tag number, and then compares live livestock photos with dead livestock photos through naked eyes, but the ear tag number is added manually, so that the problems of falling off and manual change in the feeding process can occur, and the photos are easily misjudged by comparing the photos through the naked eyes.
With the introduction and popularization of network and computer technologies, deep learning drives the rapid development and landing of artificial intelligence, and in recent years, a method for carrying out livestock identity authentication by adopting deep learning is not rarely tried, but livestock is photographed and identified in most cases.
Traditional aquaculture manages the livestock or the insurance trade certifies the livestock of insuring, generally speaking for every livestock customization an ear tag that symbolizes the livestock identity, the ear tag drops easily or can be changed by the people, and the binding process causes certain injury to the animal, also propose the mode that adopts the degree of depth learning method to carry out livestock identity authentication, but carry out data acquisition in the breeding process and be difficult to gather the data that accord with the image quality requirement, the acquisition process is more difficult, it is bigger to the authentication stage examination.
The invention provides a video livestock identity authentication system and method based on deep learning aiming at the defects of the traditional livestock identity identification.
Disclosure of Invention
The invention provides a video livestock identity authentication system and method based on deep learning, which solve the problems.
In order to solve the technical problems, the invention is realized by the following technical scheme:
the invention discloses a video livestock identity authentication system based on deep learning, which comprises a livestock identity establishing module, a video processing module, a livestock detecting module, a livestock tracking module, a livestock identity recognition module and a visual recording module, wherein the livestock identity establishing module is used for establishing a video file;
the livestock identity creation module: the system is used for creating identities for livestock needing to be built and storing livestock image data in a warehouse;
the video processing module: the livestock video processing module is used for processing shot livestock video pictures and sending the processed video pictures to the livestock detection module;
the livestock detection module: the system is used for detecting and identifying livestock individuals and livestock faces in the video pictures sent by the video processing module, and livestock ear tags can be detected if the original livestock is bound with the ear tags;
the livestock tracking module: the livestock detection device is used for judging the livestock with the same head in the continuous frame frames according to the livestock detection result of the continuous frame video frames;
the livestock identity recognition module: the system is used for identifying the identity of each tracked livestock, and the identity is completed in the livestock data acquisition and warehousing stage;
the visual recording module: the livestock image display method is used for displaying the number of the livestock identified in the shot video, displaying the identity number of each head of livestock identified in the video picture, the image information for identifying the head of livestock in the video and the image information of the livestock during early warehousing, and allowing a viewer to verify the identification accuracy.
A video livestock identity authentication method based on deep learning comprises the following steps:
s1, acquiring video pictures of livestock to be subjected to identity recognition or library building in a breeding plant, and acquiring livestock data in different activity scenes and different time periods;
s2, carrying out manual marking on the collected video information, marking livestock individuals and livestock faces in the video pictures, and marking ear tags if the ear tags exist, wherein the marking process is to mark positions and types, and the types comprise the livestock individuals, the livestock faces and the livestock ear tags;
s3, training the detection model of the manually marked data by adopting a yolov4 target detection model;
s4, cutting all livestock face pictures in the data after the artificial marking to obtain multiple livestock face picture data of each livestock in different states, and training an livestock identity recognition model by adopting a deep learning method;
s5, performing feature warehousing and image data warehousing on the livestock needing to be warehoused by using the trained detection model and the trained identity recognition model;
s6, when shooting a video for identity recognition, firstly, detecting livestock individuals and livestock faces by using a detection model, tracking the same livestock by using iou tracking on the detected livestock individuals with continuous frames, extracting features of the detected livestock faces by using an identity authentication model, comparing the extracted features with the livestock with a built library, calculating the distance between vectors, and determining the identity of the livestock;
s7, tracking the same livestock by using the tracking module, recognizing the livestock identity by using the continuous frames, taking the continuous frames to recognize the identity with the most identity in the process of recognizing the identity of the same livestock, improving the recognition accuracy again on the recognized relatively accurate result, having high fault tolerance and being capable of recognizing each activity state of the livestock;
s8, in the process of video shooting identification, if livestock individuals which are not warehoused appear, unknown livestock can be effectively identified through a threshold value set by feature matching, and if new livestock need to be warehoused, the livestock can be warehoused in one key.
Further, the video processing module is used for performing segmentation processing on the video image and segmenting the video into image data according to the number of frames.
Further, the step S2 is specifically to perform manual labeling on a plurality of image data obtained by segmenting the acquired video image.
Further: the step S3 performs data cleaning on all video frames before training, including very fuzzy discarding, discarding of livestock individuals in the video frames, and performs data enhancement on the marked image data, wherein the data enhancement includes but is not limited to image brightness change, clipping, rotation, and noising.
Further, in the step S5, the livestock face data after being manually marked is deducted to train a deep learning classification model, the livestock identity recognition model is trained by using resnet50, including building a neural network model, and by using the idea of face recognition, a loss function is independently modified, center _ loss is used to reduce the distance between different images of each livestock, and amsoftmax is used to effectively distinguish different livestock.
Compared with the prior art, the invention has the following beneficial effects:
according to the method, a deep learning method is adopted to detect and identify shot livestock video pictures in a farm to realize the functions of video livestock individual counting and identity authentication, the identification result is transmitted to a visual management interface, visual verification of identification identity can be carried out, model training is not required to be carried out again for newly appeared livestock individuals, identity authentication can be carried out on the newly appeared individuals only by characteristic warehousing, video shooting of livestock is carried out, livestock under various activity states can be compatible, the identification accuracy is high, mobile phone shooting can be convenient and rapid, and the method can be used for raising management of farmers and application of protection claims and driving protection of insurance companies, and efficient and accurate management and control are realized.
Of course, it is not necessary for any product in which the invention is practiced to achieve all of the above-described advantages at the same time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a block diagram of a deep learning based video livestock identity authentication system of the present invention;
FIG. 2 is a step diagram of a deep learning-based video livestock identity authentication method according to the present invention;
fig. 3 is a schematic diagram of a video livestock identity authentication method based on deep learning according to the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a video livestock identity authentication system and method based on deep learning, which can realize high-efficiency and accurate counting in livestock breeding management and can help the insurance industry to authenticate the identity of an insuring livestock to avoid cheating insurance. According to the invention, livestock in a shot video picture is accurately detected and identified, so that the high efficiency, accuracy, intellectualization and visualization of supervision in the breeding and insurance industry are ensured.
Referring to fig. 1, the video livestock identity authentication system based on deep learning of the present invention includes a livestock identity creation module, a video processing module, a livestock detection module, a livestock tracking module, a livestock identity recognition module, and a visual recording module;
a livestock identity creation module: the system is used for creating identities for livestock needing to be built and storing livestock image data in a warehouse;
the video processing module: the livestock video processing module is used for processing shot livestock video pictures and sending the processed video pictures to the livestock detection module;
livestock detection module: the system is used for detecting and identifying livestock individuals and livestock faces in the video pictures sent by the video processing module, and livestock ear tags can be detected if the original livestock is bound with the ear tags;
a livestock tracking module: the livestock detection device is used for judging the livestock with the same head in the continuous frame frames according to the livestock detection result of the continuous frame video frames;
livestock identity identification module: the system is used for identifying the identity of each tracked livestock, and the identity is completed in the livestock data acquisition and warehousing stage;
a visual recording module: the livestock image display method is used for displaying the number of the livestock identified in the shot video, displaying the identity number of each head of livestock identified in the video picture, the image information for identifying the head of livestock in the video and the image information of the livestock during early warehousing, and allowing a viewer to verify the identification accuracy.
As shown in fig. 2, a video livestock identity authentication method based on deep learning includes the following steps:
s1, acquiring video pictures of livestock to be subjected to identity recognition or library building in a breeding plant, and acquiring livestock data in different activity scenes and different time periods;
s2, carrying out manual marking on the collected video information, marking livestock individuals and livestock faces in the video pictures, and marking ear tags if the ear tags exist, wherein the marking process is to mark positions and types, and the types comprise the livestock individuals, the livestock faces and the livestock ear tags;
s3, training the detection model of the manually marked data by adopting a yolov4 target detection model;
s4, cutting all livestock face pictures in the data after the artificial marking to obtain multiple livestock face picture data of each livestock in different states, and training an livestock identity recognition model by adopting a deep learning method;
s5, performing feature warehousing and image data warehousing on the livestock needing to be warehoused by using the trained detection model and the trained identity recognition model;
s6, when shooting a video for identity recognition, firstly, detecting livestock individuals and livestock faces by using a detection model, tracking the same livestock by using iou tracking on the detected livestock individuals with continuous frames, extracting features of the detected livestock faces by using an identity authentication model, comparing the extracted features with the livestock with a built library, calculating the distance between vectors, and determining the identity of the livestock;
s7, tracking the same livestock by using the tracking module, recognizing the livestock identity by using the continuous frames, taking the continuous frames to recognize the identity with the most identity in the process of recognizing the identity of the same livestock, improving the recognition accuracy again on the recognized relatively accurate result, having high fault tolerance and being capable of recognizing each activity state of the livestock;
s8, in the process of video shooting identification, if livestock individuals which are not warehoused appear, unknown livestock can be effectively identified through a threshold value set by feature matching, and if new livestock need to be warehoused, the livestock can be warehoused in one key.
The video processing module is used for carrying out segmentation processing on the video image and segmenting the video into image data according to the number of frames.
Step S2 is specifically to perform manual labeling on a plurality of image data obtained by segmenting the acquired video image.
Wherein, step S3 performs data cleaning on all video frames before training, including very fuzzy discarding, discarding of livestock individuals in the video frames, and performs data enhancement on the marked image data, wherein the data enhancement includes but is not limited to image brightness change, cropping, rotation, and noising.
Specifically, in the step S5, the livestock face data after being manually marked is deducted to perform deep learning classification model training, the livestock identity recognition model is trained by using resnet50, the training includes building a neural network model, the idea of face recognition is used for reference, a loss function is independently modified, the center _ loss is used for reducing the distance between different images of each livestock, and the amsoftmax is used for effectively distinguishing different livestock.
Has the advantages that:
according to the method, a deep learning method is adopted to detect and identify shot livestock video pictures in a farm to realize the functions of video livestock individual counting and identity authentication, the identification result is transmitted to a visual management interface, visual verification of identification identity can be carried out, model training is not required to be carried out again for newly appeared livestock individuals, identity authentication can be carried out on the newly appeared individuals only by characteristic warehousing, video shooting of livestock is carried out, livestock under various activity states can be compatible, the identification accuracy is high, mobile phone shooting can be convenient and rapid, and the method can be used for raising management of farmers and application of protection claims and driving protection of insurance companies, and efficient and accurate management and control are realized.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (6)
1. A video livestock identity authentication system based on deep learning is characterized by comprising a livestock identity creating module, a video processing module, a livestock detecting module, a livestock tracking module, a livestock identity recognition module and a visual recording module;
the livestock identity creation module: the system is used for creating identities for livestock needing to be built and storing livestock image data in a warehouse;
the video processing module: the livestock video processing module is used for processing shot livestock video pictures and sending the processed video pictures to the livestock detection module;
the livestock detection module: the system is used for detecting and identifying livestock individuals and livestock faces in the video pictures sent by the video processing module, and livestock ear tags can be detected if the original livestock is bound with the ear tags;
the livestock tracking module: the livestock detection device is used for judging the livestock with the same head in the continuous frame frames according to the livestock detection result of the continuous frame video frames;
the livestock identity recognition module: the system is used for identifying the identity of each tracked livestock, and the identity is completed in the livestock data acquisition and warehousing stage;
the visual recording module: the livestock image display method is used for displaying the number of the livestock identified in the shot video, displaying the identity number of each head of livestock identified in the video picture, the image information for identifying the head of livestock in the video and the image information of the livestock during early warehousing, and allowing a viewer to verify the identification accuracy.
2. A video livestock identity authentication method based on deep learning is characterized by comprising the following steps:
s1, acquiring video pictures of livestock to be subjected to identity recognition or library building in a breeding plant, and acquiring livestock data in different activity scenes and different time periods;
s2, carrying out manual marking on the collected video information, marking livestock individuals and livestock faces in the video pictures, and marking ear tags if the ear tags exist, wherein the marking process is to mark positions and types, and the types comprise the livestock individuals, the livestock faces and the livestock ear tags;
s3, training the detection model of the manually marked data by adopting a yolov4 target detection model;
s4, cutting all livestock face pictures in the data after the artificial marking to obtain multiple livestock face picture data of each livestock in different states, and training an livestock identity recognition model by adopting a deep learning method;
s5, performing feature warehousing and image data warehousing on the livestock needing to be warehoused by using the trained detection model and the trained identity recognition model;
s6, when shooting a video for identity recognition, firstly, detecting livestock individuals and livestock faces by using a detection model, tracking the same livestock by using iou tracking on the detected livestock individuals with continuous frames, extracting features of the detected livestock faces by using an identity authentication model, comparing the extracted features with the livestock with a built library, calculating the distance between vectors, and determining the identity of the livestock;
s7, tracking the same livestock by using the tracking module, recognizing the livestock identity by using the continuous frames, taking the continuous frames to recognize the identity with the most identity in the process of recognizing the identity of the same livestock, improving the recognition accuracy again on the recognized relatively accurate result, having high fault tolerance and being capable of recognizing each activity state of the livestock;
s8, in the process of video shooting identification, if livestock individuals which are not warehoused appear, unknown livestock can be effectively identified through a threshold value set by feature matching, and if new livestock need to be warehoused, the livestock can be warehoused in one key.
3. The video livestock identity authentication method based on deep learning of claim 2, wherein the video processing module is used for performing segmentation processing on video images, and segmenting the video into image data according to the number of frames.
4. The video livestock identity authentication method based on deep learning of claim 2, wherein said step S2 is specifically to perform manual labeling on a plurality of image data obtained by segmenting the acquired video image.
5. The video livestock identity authentication method based on deep learning of claim 2, characterized in that: the step S3 performs data cleaning on all video frames before training, including very fuzzy discarding, discarding of livestock individuals in the video frames, and performs data enhancement on the marked image data, wherein the data enhancement includes but is not limited to image brightness change, clipping, rotation, and noising.
6. The video livestock identity authentication method based on deep learning of claim 2, characterized in that: in the step S5, the livestock face data after being manually marked is deducted to train a deep learning classification model, the livestock identity recognition model is trained by using resnet50, the training includes building a neural network model, the idea of face recognition is used for reference, a loss function is independently modified, the center _ loss is used for reducing the distance between different images of each livestock, and the amsoftmax is used for effectively distinguishing different livestock.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011457933.5A CN112541432A (en) | 2020-12-11 | 2020-12-11 | Video livestock identity authentication system and method based on deep learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011457933.5A CN112541432A (en) | 2020-12-11 | 2020-12-11 | Video livestock identity authentication system and method based on deep learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112541432A true CN112541432A (en) | 2021-03-23 |
Family
ID=75018592
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011457933.5A Pending CN112541432A (en) | 2020-12-11 | 2020-12-11 | Video livestock identity authentication system and method based on deep learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112541432A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113077485A (en) * | 2021-04-28 | 2021-07-06 | 北京神州慧达信息技术有限公司 | Artificial intelligence-based reference-free measuring method |
CN113762089A (en) * | 2021-08-16 | 2021-12-07 | 北京神州慧达信息技术有限公司 | Artificial intelligence-based livestock left face identification system and use method |
CN113792603A (en) * | 2021-08-16 | 2021-12-14 | 北京神州慧达信息技术有限公司 | Livestock body identification system based on artificial intelligence and use method |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107229947A (en) * | 2017-05-15 | 2017-10-03 | 邓昌顺 | A kind of banking and insurance business method and system based on animal identification |
CN107766807A (en) * | 2017-09-30 | 2018-03-06 | 平安科技(深圳)有限公司 | Electronic installation, insure livestock recognition methods and computer-readable recording medium |
CN107992903A (en) * | 2017-09-20 | 2018-05-04 | 翔创科技(北京)有限公司 | Livestock personal identification method, device, storage medium and electronic equipment |
CN108492198A (en) * | 2018-03-27 | 2018-09-04 | 平安科技(深圳)有限公司 | Livestock insurance Claims Resolution method, apparatus, computer equipment and storage medium |
CN111160203A (en) * | 2019-12-23 | 2020-05-15 | 中电科新型智慧城市研究院有限公司 | Loitering and lingering behavior analysis method based on head and shoulder model and IOU tracking |
CN111368766A (en) * | 2020-03-09 | 2020-07-03 | 云南安华防灾减灾科技有限责任公司 | Cattle face detection and identification method based on deep learning |
CN111709421A (en) * | 2020-06-18 | 2020-09-25 | 深圳市赛为智能股份有限公司 | Bird identification method and device, computer equipment and storage medium |
CN111709287A (en) * | 2020-05-15 | 2020-09-25 | 南京农业大学 | Weaned piglet target tracking method based on deep learning |
-
2020
- 2020-12-11 CN CN202011457933.5A patent/CN112541432A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107229947A (en) * | 2017-05-15 | 2017-10-03 | 邓昌顺 | A kind of banking and insurance business method and system based on animal identification |
CN107992903A (en) * | 2017-09-20 | 2018-05-04 | 翔创科技(北京)有限公司 | Livestock personal identification method, device, storage medium and electronic equipment |
CN107766807A (en) * | 2017-09-30 | 2018-03-06 | 平安科技(深圳)有限公司 | Electronic installation, insure livestock recognition methods and computer-readable recording medium |
CN108492198A (en) * | 2018-03-27 | 2018-09-04 | 平安科技(深圳)有限公司 | Livestock insurance Claims Resolution method, apparatus, computer equipment and storage medium |
CN111160203A (en) * | 2019-12-23 | 2020-05-15 | 中电科新型智慧城市研究院有限公司 | Loitering and lingering behavior analysis method based on head and shoulder model and IOU tracking |
CN111368766A (en) * | 2020-03-09 | 2020-07-03 | 云南安华防灾减灾科技有限责任公司 | Cattle face detection and identification method based on deep learning |
CN111709287A (en) * | 2020-05-15 | 2020-09-25 | 南京农业大学 | Weaned piglet target tracking method based on deep learning |
CN111709421A (en) * | 2020-06-18 | 2020-09-25 | 深圳市赛为智能股份有限公司 | Bird identification method and device, computer equipment and storage medium |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113077485A (en) * | 2021-04-28 | 2021-07-06 | 北京神州慧达信息技术有限公司 | Artificial intelligence-based reference-free measuring method |
CN113762089A (en) * | 2021-08-16 | 2021-12-07 | 北京神州慧达信息技术有限公司 | Artificial intelligence-based livestock left face identification system and use method |
CN113792603A (en) * | 2021-08-16 | 2021-12-14 | 北京神州慧达信息技术有限公司 | Livestock body identification system based on artificial intelligence and use method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112541432A (en) | Video livestock identity authentication system and method based on deep learning | |
CN110826538B (en) | Abnormal off-duty identification system for electric power business hall | |
Vahab et al. | Applications of object detection system | |
CN110705405A (en) | Target labeling method and device | |
CN104408780A (en) | Face recognition attendance system | |
CN107133611A (en) | A kind of classroom student nod rate identification with statistical method and device | |
CN106650623A (en) | Face detection-based method for verifying personnel and identity document for exit and entry | |
CN110096945B (en) | Indoor monitoring video key frame real-time extraction method based on machine learning | |
CN112580657B (en) | Self-learning character recognition method | |
CN112528823B (en) | Method and system for analyzing batcharybus movement behavior based on key frame detection and semantic component segmentation | |
CN109409250A (en) | A kind of across the video camera pedestrian of no overlap ken recognition methods again based on deep learning | |
CN110222630A (en) | One boar identification system | |
Zin et al. | Cow identification system using ear tag recognition | |
CN110807356A (en) | Living body detection method based on image lip language identification verification code | |
CN112084986A (en) | Real-time safety helmet detection method based on image feature extraction | |
CN202815870U (en) | Certificate photograph and face automatic identification system | |
CN113780207A (en) | System and method for goat face recognition | |
WO2022121021A1 (en) | Identity card number detection method and apparatus, and readable storage medium and terminal | |
CN113553965B (en) | Person identity recognition method combining face recognition and human body recognition | |
CN113068657B (en) | Intelligent efficient pig raising method and system | |
CN111209863B (en) | Living model training and human face living body detection method and device and electronic equipment | |
CN113762089A (en) | Artificial intelligence-based livestock left face identification system and use method | |
CN113343889A (en) | Face recognition system based on silence live body detection | |
CN112733738A (en) | Method for comparing face recognition data | |
CN111144378B (en) | Target object identification method and device |
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: 20210323 |
|
RJ01 | Rejection of invention patent application after publication |