CN112906452A - Automatic identification, tracking and statistics method and system for antelope buffalo deer - Google Patents

Automatic identification, tracking and statistics method and system for antelope buffalo deer Download PDF

Info

Publication number
CN112906452A
CN112906452A CN202011454404.XA CN202011454404A CN112906452A CN 112906452 A CN112906452 A CN 112906452A CN 202011454404 A CN202011454404 A CN 202011454404A CN 112906452 A CN112906452 A CN 112906452A
Authority
CN
China
Prior art keywords
image
target
target animal
animal
video
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
Application number
CN202011454404.XA
Other languages
Chinese (zh)
Inventor
叶平
刘成龙
何廷美
施晓刚
伏彦林
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Priority to CN202011454404.XA priority Critical patent/CN112906452A/en
Publication of CN112906452A publication Critical patent/CN112906452A/en
Pending legal-status Critical Current

Links

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
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/292—Multi-camera tracking
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
    • H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30242—Counting objects in image

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Signal Processing (AREA)
  • Image Analysis (AREA)
  • Catching Or Destruction (AREA)

Abstract

The invention relates to a method and a system for automatically identifying, tracking and counting antelope buffalo deer, which are used for decoding a continuous video picture into an image frame sequence by utilizing the characteristic that the position of each target in continuous frame images is almost unchanged in a short time, and then sequentially identifying the image frame sequence, thereby not only obtaining the track of each target in the image, but also exposing the originally shielded target after the position of the target is changed, so as to identify the target.

Description

Automatic identification, tracking and statistics method and system for antelope buffalo deer
Technical Field
The invention relates to the technical field, in particular to an automatic identification, tracking and statistics system for antelope buffalo deer.
Background
In the 'five sheds' area of the national level nature reserve administration of Sichuan sleeping, the altitude is about 2500 m, the site is in a panda channel for global 24-hour direct broadcast, the attention is very high, and the salt slurry is licked by the grouped antelope and buffalo. At present, the scientific researchers can only manually identify the categories (adult male, adult female, sub-adult male, sub-adult female and larva) of antelope and buffalo, the behavior modes (drinking, resting, rumination, warning, moving, lactation, urination, interaction and the like), the approach and departure time and the like of the antelope and the buffalo through a mode of reviewing videos by a client, and the data counted in 15 minutes are analyzed according to the statistical principle, so that no automatic identification and tracking statistical device exists. The prior art aims to solve the problems that time is inaccurate in manual statistics, and the time cannot be accurately identified by naked eyes due to the change of station positions of a large group of wild antelopes and water deer, wind and snow weather at night.
The prior art has the defects that the behavior analysis accuracy is caused by factors such as light, climate and the like, and the situations that antelope and buffalo are shielded and cannot be accurately identified when the population is large.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides an automatic antelope buffalo deer identification, tracking and statistics system which can effectively solve the problem of inaccurate group identification caused by light or group shielding.
The purpose of the invention is realized by the following technical scheme:
an automatic identification, tracking and statistical method for antelope buffalo deer comprises the following steps:
step S100: video monitoring is utilized to obtain video pictures of a monitored area,and judging the time node t of the target animal entering the picture based on the image recognition technology1And time node t of leaving picture2；
Step S200: extraction of t1-t2One or more pieces of video within a time period, or extracting t1-t2All videos within a time period;
step S300: converting the extracted video into corresponding image frame sequence in time sequence based on video decoding technology, and marking out initial frame image M1And an end frame image MnWherein n is the number of image frames in the image frame sequence;
step S400: sequentially putting the image frame sequence into the same coordinate system to identify the start frame image M1The coordinates of each target animal are marked as D-H (x)1,y1) Wherein D represents the species of the target animal, and H represents the number of the target animal in the same species;
step S500: judging the next frame image M2The coordinates of each target animal are recorded as D-H (x)2,y2) Because the displacement of the target animal between two continuous frames is almost 0, the target animal can be accurately tracked;
step S600: sequentially traversing all the frame images to obtain the image M of the same target animal at the initial frame1To the end frame image MnCoordinate trajectories in the process;
step S700: between the step S500 and the step S600, re-identifying the image every f frames, judging whether a newly added target animal appears, and marking the coordinate identification as (D + j) - (H + e) (x)1,y1) Wherein j represents the type and the type of the newly added target animals, and e represents the number of the added target animals;
step S800: when a new target animal appears in a certain image frame, repeating the steps S500-S600 on the basis of the image frame, and traversing all the frame images until the end frame image MnAnd obtaining the number and the type of the corresponding target animals.
Furthermore, D and H are represented by Arabic numerals, and the background stores the type of the target animal corresponding to the D digit.
Further, in step S300, the video frame per second may be converted into 5-20 frames of images.
Further, said t1-t2After the time period exceeds 1 hour, t is extracted1-t2One or more segments of video within the time period, wherein each segment of video is no longer than 15 minutes in length.
Further, in steps S500 to S600, the number of departure pictures of the target animal is recorded as g.
Further, when the newly added target animal appears, judging the position of the target animal appearing in the image for the first time, marking the position, recording the number of the target animals entering from the edge of the image as c, and recording the rest as r;
meanwhile, judging the overlapped part of the newly added target animal c and the separated target animal g by means of the peripheral lens, and marking as v;
the total number of the target animals in the category is H + c + r-v, wherein H is the initial frame image M1The number of target animals of the species.
And further, the method also comprises an animal behavior recognition method, wherein behavior models of various target animals are trained based on machine learning, and are matched with the target animals extracted from each frame of image, so that corresponding target animal behavior analysis results are obtained.
Further, the behavioral model includes drinking, resting, ruminating, warning, moving, nursing, and urinating.
Further, the target animal marked in step S400 is an animal that can be identified completely and accurately, and does not include an animal whose body is exposed and cannot be identified.
A system for realizing an automatic identification, tracking and statistical method of antelope buffalo deer comprises the following steps:
the system comprises a main camera and an auxiliary camera, wherein the main camera is arranged in a monitoring area to acquire a video picture, and the auxiliary camera is arranged at the periphery of the monitoring area;
the image recognition module is connected with the main camera and the auxiliary camera and used for recognizing the approach of the target animal, and the database is connected with the image recognition module and used for storing the animal model;
a clock module for recording the approach and departure of the target animal and obtaining corresponding time period t1-t2；
A video extraction module connected with the main camera and the auxiliary camera for extracting the time period t1-t2One or more segments of video within, or extracting t1-t2All videos within a time period;
the video decoding module is used for decoding the extracted video into an image frame sequence;
the image recognition module recognizes the target animal according to the steps S300-S800;
and the processor and the communication module are connected with each module and are used for uploading the identification result to the server.
The invention has the beneficial effects that: the method decodes a continuous video picture into an image frame sequence by utilizing the characteristic that the position of each target in continuous frame images is almost unchanged in a short time, and then sequentially identifies the image frame sequence, so that not only can the track of each target in the image be obtained, but also the originally shielded target can be exposed after the position of the target is changed, so that the identification is carried out, the problem that the target cannot be accurately identified due to the fact that the target is shielded by adjacent targets in the traditional identification mode is solved, the method is applied to the automatic identification of the antelope buffalo deer, and because two species have higher identification degrees, the identification accuracy is greatly improved, the population quantity statistical accuracy is improved, and ecological statistics can be better carried out.
Drawings
Fig. 1 is a schematic block diagram of the present invention.
Detailed Description
The technical solution of the present invention is further described in detail with reference to the following specific examples, but the scope of the present invention is not limited to the following.
As shown in fig. 1, an automatic identification, tracking and statistical method for antelope buffalo deer includes:
step S100: video images of a monitored area are obtained by utilizing video monitoring, and time nodes t of target animals entering the images are judged based on an image recognition technology1And time node t of leaving picture2；
Step S200: extraction of t1-t2One or more pieces of video within a time period, or extracting t1-t2All videos within a time period;
step S300: converting the extracted video into corresponding image frame sequence in time sequence based on video decoding technology, and marking out initial frame image M1And an end frame image MnWherein n is the number of image frames in the image frame sequence;
step S400: sequentially putting the image frame sequence into the same coordinate system to identify the start frame image M1The coordinates of each target animal are marked as D-H (x)1,y1) Wherein D represents the species of the target animal, and H represents the number of the target animal in the same species;
step S500: judging the next frame image M2The coordinates of each target animal are recorded as D-H (x)2,y2) Because the displacement of the target animal between two continuous frames is almost 0, the target animal can be accurately tracked;
step S600: sequentially traversing all the frame images to obtain the image M of the same target animal at the initial frame1To the end frame image MnCoordinate trajectories in the process;
step S700: between the step S500 and the step S600, re-identifying the image every f frames, judging whether a newly added target animal appears, and marking the coordinate identification as (D + j) - (H + e) (x)1,y1) Wherein j represents the type and the type of the newly added target animals, and e represents the number of the added target animals;
step S800: when a new target animal appears in a certain image frame, repeating the steps S500-S600 on the basis of the image frame, and traversing all the frame images until the end frame image MnAnd obtaining the number and the type of the corresponding target animals.
Optionally, in the implementation, the target animals only include antelope and buffalo, and other species are not statistically analyzed in an neglect manner, so as to reduce the computation load of the system.
More preferably, in the antelope buffalo automatic identification tracking statistical method, for the target animal track analysis of different species, the multithreading mode can be adopted for parallel operation, and meanwhile, the image frame sequence obtained by decoding a single video end can be segmented again and then the multithreading parallel processing is adopted, so that the operation speed of the system is greatly improved.
Optionally, an automatic antelope buffalo deer identification, tracking and statistics method, D and H are represented by arabic numbers, and the background stores the target animal type corresponding to D-bit number, for example, in the automatic antelope buffalo deer identification, the number 1 represents antelope, the number 2 represents buffalo, and the number is 1-10 (x)1,y1) Antelope image M with reference number 10 at the start frame1Is measured.
Optionally, in the statistical method for automatic identification and tracking of antelope buffalo, in step S300, a video picture per second is converted into 5-20 frames of images, the number of decoded image frames depends on an identification object, for a target animal moving fast, the decoded image frames should be sufficient in a unit time, and for a target animal moving slowly, the decoded image frames can be reduced appropriately, so as to reduce the operation load of the system.
Optionally, an automatic identification, tracking and statistical method for antelope's buffalo, t1-t2After the time period exceeds 1 hour, t is extracted1-t2One or more segments of video within the time period, wherein each segment of video is no longer than 15 minutes in length.
Optionally, in steps S500 to S600, the number of the target animals leaving the screen is recorded as g.
Optionally, in the automatic identification, tracking and statistics method for the gazelle, when a newly added target animal appears, the position of the target animal appearing in the image for the first time is judged, the position is marked, the number of the target animals entering from the edge of the image is recorded as c, and the rest are recorded as r;
meanwhile, judging the overlapped part of the newly added target animal c and the separated target animal g by means of the peripheral lens, and marking as v;
the total number of the target animals in the category is H + c + r-v, wherein H is the initial frame image M1The number of target animals of the species.
Optionally, the method for automatically identifying, tracking and counting antelope buffalo deer further comprises an animal behavior identification method, wherein behavior models of various target animals are trained based on machine learning, and are matched with the target animals extracted from each frame of image, so that corresponding target animal behavior analysis results are obtained.
Optionally, the behavior model includes drinking water, resting, rumination, warning, moving, nursing, and urination.
Optionally, in the method for automatically identifying, tracking and counting antelope buffalo deer, the target animal marked in step S400 is an animal that can be completely and accurately identified, and does not include an animal whose body is only exposed and cannot be identified.
Referring to fig. 1, the present invention further provides a system for implementing an automatic antelope buffalo deer identification, tracking and statistics method, the system comprising:
the system comprises a main camera and an auxiliary camera, wherein the main camera is arranged in a monitoring area to acquire a video picture, and the auxiliary camera is arranged at the periphery of the monitoring area;
the image recognition module is connected with the main camera and the auxiliary camera and used for recognizing the approach of the target animal, and the database is connected with the image recognition module and used for storing the animal model;
a clock module for recording the approach and departure of the target animal and obtaining corresponding time period t1-t2；
A video extraction module connected with the main camera and the auxiliary camera for extracting the time period t1-t2One or more segments of video within, or extracting t1-t2All videos within a time period;
the video decoding module is used for decoding the extracted video into an image frame sequence;
the image recognition module recognizes the target animal according to the steps S300-S800;
and the processor and the communication module are connected with each module and are used for uploading the identification result to the server.
The auxiliary camera in the system mainly aims to realize repeated elimination of the target animal after leaving and entering the picture, namely, the auxiliary camera is used as the peripheral lens to analyze
The foregoing is illustrative of the preferred embodiments of this invention, and it is to be understood that the invention is not limited to the precise form disclosed herein and that various other combinations, modifications, and environments may be resorted to, falling within the scope of the concept as disclosed herein, either as described above or as apparent to those skilled in the relevant art. And that modifications and variations may be effected by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.

Claims (10)

1. An automatic identification, tracking and statistical method for antelope buffalo deer is characterized by comprising the following steps:
step S100: video images of a monitored area are obtained by utilizing video monitoring, and time nodes t of target animals entering the images are judged based on an image recognition technology1And time node t of leaving picture2；
Step S200: extraction of t1-t2One or more pieces of video within a time period, or extracting t1-t2All videos within a time period;
step S300: converting the extracted video into corresponding image frame sequence in time sequence based on video decoding technology, and marking out initial frame image M1And an end frame image MnWherein n is the number of image frames in the image frame sequence;
step S400: sequentially putting the image frame sequence into the same coordinate system to identify the start frame image M1Coordinates of each target animal and advancing the coordinatesThe row number is marked D-H (x)1,y1) Wherein D represents the species of the target animal, and H represents the number of the target animal in the same species;
step S500: judging the next frame image M2The coordinates of each target animal are recorded as D-H (x)2,y2) Because the displacement of the target animal between two continuous frames is almost 0, the target animal can be accurately tracked;
step S600: sequentially traversing all the frame images to obtain the image M of the same target animal at the initial frame1To the end frame image MnCoordinate trajectories in the process;
step S700: between the step S500 and the step S600, re-identifying the image every f frames, judging whether a newly added target animal appears, and marking the coordinate identification as (D + j) - (H + e) (x)1,y1) Wherein j represents the type and the type of the newly added target animals, and e represents the number of the added target animals;
step S800: when a new target animal appears in a certain image frame, repeating the steps S500-S600 on the basis of the image frame, and traversing all the frame images until the end frame image MnAnd obtaining the number and the type of the corresponding target animals.
2. The method as claimed in claim 1, wherein D and H are represented by arabic numerals, and the background stores the type of target animal corresponding to D digits.
3. The method as claimed in claim 2, wherein the video frames per second are converted into 5-20 frames of images in step S300.
4. The method as claimed in claim 3, wherein t is the value of the statistical method for automatic identification and tracking of antelope buffalo deer1-t2After the time period exceeds 1 hour, t is extracted1-t2One or more segments of video within a time segment, wherein each segmentThe video length does not exceed 15 minutes.
5. The method as claimed in claim 4, wherein the number of departure pictures of the target animal is recorded as g in steps S500-S600.
6. The method according to claim 5, wherein when the new target animal appears, the position of the target animal in the image is determined and marked, the number of target animals entering from the edge of the image is marked as c, and the rest are marked as r;
meanwhile, judging the overlapped part of the newly added target animal c and the separated target animal g by means of the peripheral lens, and marking as v;
the total number of the target animals in the category is H + c + r-v, wherein H is the initial frame image M1The number of target animals of the species.
7. The method of claim 6, further comprising an animal behavior recognition method for training behavior models of various target animals based on machine learning and matching the models with the target animals extracted from each frame of image, thereby obtaining corresponding target animal behavior analysis results.
8. The automated antelope buffalo deer identification, tracking and statistics method according to claim 7, wherein the behavior model comprises drinking, resting, rumination, warning, moving, nursing, urination.
9. The method as claimed in claim 8, wherein the target animal marked in step S400 is an animal that can be identified with complete accuracy, and includes not only an animal whose body is partially exposed but also an animal whose body cannot be identified.
10. A system for implementing the automated antelope buffalo deer identification tracking statistical method of any one of claims 1-9, the system comprising:
the system comprises a main camera and an auxiliary camera, wherein the main camera is arranged in a monitoring area to acquire a video picture, and the auxiliary camera is arranged at the periphery of the monitoring area;
the image recognition module is connected with the main camera and the auxiliary camera and used for recognizing the approach of the target animal, and the database is connected with the image recognition module and used for storing the animal model;
a clock module for recording the approach and departure of the target animal and obtaining corresponding time period t1-t2；
A video extraction module connected with the main camera and the auxiliary camera for extracting the time period t1-t2One or more segments of video within, or extracting t1-t2All videos within a time period;
the video decoding module is used for decoding the extracted video into an image frame sequence;
the image recognition module recognizes the target animal according to the steps S300-S800;
and the processor and the communication module are connected with each module and are used for uploading the identification result to the server.
CN202011454404.XA 2020-12-10 2020-12-10 Automatic identification, tracking and statistics method and system for antelope buffalo deer Pending CN112906452A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011454404.XA CN112906452A (en) 2020-12-10 2020-12-10 Automatic identification, tracking and statistics method and system for antelope buffalo deer

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011454404.XA CN112906452A (en) 2020-12-10 2020-12-10 Automatic identification, tracking and statistics method and system for antelope buffalo deer

Publications (1)

Publication Number Publication Date
CN112906452A true CN112906452A (en) 2021-06-04

Family

ID=76111670

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011454404.XA Pending CN112906452A (en) 2020-12-10 2020-12-10 Automatic identification, tracking and statistics method and system for antelope buffalo deer

Country Status (1)

Country Link
CN (1) CN112906452A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115063378A (en) * 2022-06-27 2022-09-16 中国平安财产保险股份有限公司 Intelligent counting method, device, equipment and storage medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101751677A (en) * 2008-12-17 2010-06-23 中国科学院自动化研究所 Target continuous tracking method based on multi-camera
CN109657577A (en) * 2018-12-07 2019-04-19 重庆理工大学 A kind of animal detection method based on entropy and motion excursion amount
CN109960965A (en) * 2017-12-14 2019-07-02 翔升（上海）电子技术有限公司 Methods, devices and systems based on unmanned plane identification animal behavior
CN110765972A (en) * 2019-10-31 2020-02-07 秒针信息技术有限公司 Animal monitoring method and device, electronic equipment and storage medium
CN111145213A (en) * 2019-12-10 2020-05-12 中国银联股份有限公司 Target tracking method, device and system and computer readable storage medium
CN111325089A (en) * 2018-12-13 2020-06-23 安讯士有限公司 Method and apparatus for tracking object
CN111340848A (en) * 2020-02-26 2020-06-26 重庆中科云从科技有限公司 Object tracking method, system, device and medium for target area

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101751677A (en) * 2008-12-17 2010-06-23 中国科学院自动化研究所 Target continuous tracking method based on multi-camera
CN109960965A (en) * 2017-12-14 2019-07-02 翔升（上海）电子技术有限公司 Methods, devices and systems based on unmanned plane identification animal behavior
CN109657577A (en) * 2018-12-07 2019-04-19 重庆理工大学 A kind of animal detection method based on entropy and motion excursion amount
CN111325089A (en) * 2018-12-13 2020-06-23 安讯士有限公司 Method and apparatus for tracking object
CN110765972A (en) * 2019-10-31 2020-02-07 秒针信息技术有限公司 Animal monitoring method and device, electronic equipment and storage medium
CN111145213A (en) * 2019-12-10 2020-05-12 中国银联股份有限公司 Target tracking method, device and system and computer readable storage medium
CN111340848A (en) * 2020-02-26 2020-06-26 重庆中科云从科技有限公司 Object tracking method, system, device and medium for target area

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115063378A (en) * 2022-06-27 2022-09-16 中国平安财产保险股份有限公司 Intelligent counting method, device, equipment and storage medium
CN115063378B (en) * 2022-06-27 2023-12-05 中国平安财产保险股份有限公司 Intelligent point counting method, device, equipment and storage medium

Similar Documents

Publication Publication Date Title
CN108717523B (en) Sow oestrus behavior detection method based on machine vision
WO2021051885A1 (en) Target labeling method and apparatus
CN111727457B (en) Cotton crop row detection method and device based on computer vision and storage medium
CN111914685B (en) Sow oestrus detection method and device, electronic equipment and storage medium
US20190073538A1 (en) Method and system for classifying objects from a stream of images
CN112541432A (en) Video livestock identity authentication system and method based on deep learning
CN115830490A (en) Multi-target tracking and behavior statistical method for herd health pigs
Noe et al. Automatic detection and tracking of mounting behavior in cattle using a deep learning-based instance segmentation model
CN111881320A (en) Video query method, device, equipment and readable storage medium
CN112836683A (en) License plate recognition method, device, equipment and medium for portable camera equipment
CN112906452A (en) Automatic identification, tracking and statistics method and system for antelope buffalo deer
CN113808113A (en) Channel type intelligent swinery weighing and counting method based on computer vision assistance
CN117437792B (en) Real-time road traffic state monitoring method, device and system based on edge calculation
CN113068657B (en) Intelligent efficient pig raising method and system
CN113743261A (en) Pig body trauma detection method and device and readable storage medium
CN114898250B (en) Multi-target tracking method for suckling piglets based on self-attention mechanism
CN112906511B (en) Wild animal intelligent monitoring method combining individual image and footprint image
CN115914560A (en) Intelligent accurate feeding method and device for sows, electronic equipment and storage medium
KR102424901B1 (en) method for detecting estrus of cattle based on object detection algorithm
CN113822367B (en) Regional behavior analysis method, system and medium based on human face
CN113239931A (en) Logistics station license plate recognition method
CN114219767B (en) Sheep flock counting management method based on Internet of things edge box
CN114842470B (en) Egg counting and positioning system in stacked cage raising mode
CN114937263B (en) Vehicle axle number counting method and system based on video intelligent analysis
TWM638503U (en) System for biological gender recognition

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