CN111680551B - Method, device, computer equipment and storage medium for monitoring livestock quantity - Google Patents
Method, device, computer equipment and storage medium for monitoring livestock quantity Download PDFInfo
- Publication number
- CN111680551B CN111680551B CN202010350129.0A CN202010350129A CN111680551B CN 111680551 B CN111680551 B CN 111680551B CN 202010350129 A CN202010350129 A CN 202010350129A CN 111680551 B CN111680551 B CN 111680551B
- Authority
- CN
- China
- Prior art keywords
- frame
- livestock
- tracking
- detection
- model
- 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
- 244000144972 livestock Species 0.000 title claims abstract description 245
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000012544 monitoring process Methods 0.000 title claims abstract description 37
- 238000001514 detection method Methods 0.000 claims abstract description 188
- 238000013145 classification model Methods 0.000 claims abstract description 22
- 230000002159 abnormal effect Effects 0.000 claims abstract description 15
- 239000013598 vector Substances 0.000 claims description 54
- 241001465754 Metazoa Species 0.000 claims description 25
- 239000000523 sample Substances 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 15
- 239000012805 animal sample Substances 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 7
- 230000008439 repair process Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000004422 calculation algorithm Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 241000283690 Bos taurus Species 0.000 description 1
- 241001494479 Pecora Species 0.000 description 1
- 241000282887 Suidae Species 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Probability & Statistics with Applications (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the application belongs to the technical field of artificial intelligence, and relates to a method for monitoring the quantity of livestock, which comprises the steps of detecting the acquired pictures according to a target detection AI model to obtain a detection frame; intercepting an image of a single livestock in the detection frame to obtain a livestock sample graph, and processing the livestock sample graph through a depth tracking model and a livestock classification model to obtain a tracking detection matching frame, a redundant tracking frame and a tracking leakage repairing detection frame; adding the number of the obtained tracking leakage repairing detection frames with the number of the tracking detection matching frames to obtain the number of actual livestock, and taking the actual livestock as a statistical result; comparing the statistical result with the quantity of livestock stored in the database; if the statistical result is inconsistent with the quantity of the livestock stored in the database, judging that the quantity of the livestock is abnormal, and sending an abnormal alarm to the user. The application also provides a device for monitoring the quantity of livestock, computer equipment and a storage medium. The application effectively reduces the multi-detection rate and the omission rate of livestock.
Description
Technical Field
The present application relates to the field of artificial intelligence technology, and in particular, to a method, an apparatus, a computer device, and a storage medium for monitoring the quantity of livestock.
Background
The traditional livestock number statistics of the farm is completely dependent on manual work, the manual work walks to the farm to record the number of the livestock in each column, and a manual calculation mode is adopted to easily generate calculation errors, so that the situation that the number is difficult to correspond occurs; and when the quantity of the livestock is found to be abnormal, the causes are difficult to find in time by the breeding personnel, so that the bred livestock are lost.
At present, modern farms introduce automation equipment and intelligent software algorithms to improve the cultivation efficiency and the cultivation quality, most of the existing modes adopt a combination of a camera and a single model to count the number of livestock in the farms and monitor the livestock, and in the model identification process, non-livestock objects can be identified as livestock by mistake, so that the problem of multiple detection rates is generated. In the process of carrying out model statistics on the quantity of livestock, the condition of missed detection of the livestock is caused due to different adopted models.
Disclosure of Invention
The embodiment of the application aims to provide a method, a device, computer equipment and a storage medium for monitoring the quantity of livestock, and the conditions of multiple detection rate and omission rate are reduced.
In order to solve the above technical problems, the embodiment of the present application provides a method for monitoring the number of livestock, which adopts the following technical scheme:
A method of monitoring the quantity of livestock comprising the steps of:
controlling cameras arranged in livestock pens to acquire videos, and capturing the videos according to frames to obtain acquired pictures;
Detecting livestock on the acquired pictures according to a pre-trained target detection AI model to obtain at least one detection frame, wherein the content in the detection frame is an image of a single livestock judged by the model;
Intercepting an image of a single livestock in the detection frame to obtain a livestock sample graph, and comparing all the livestock sample graphs of the current frame with all the livestock sample graphs of the previous frame through a pre-trained depth tracking model to obtain a tracking detection matching frame and an redundant tracking frame;
Judging the content of each redundant tracking frame in sequence through a pre-trained livestock classification model, and taking the redundant tracking frame as a tracking, repairing and leakage and detecting frame if the content judgment result in the redundant tracking frame is true livestock;
Adding the number of the obtained tracking leakage repairing detection frames with the number of the tracking detection matching frames to obtain the number of actual livestock, and taking the actual livestock as a statistical result;
comparing the statistical result with the quantity of livestock stored in a database; and
If the statistical result is inconsistent with the quantity of the livestock stored in the database, judging that the quantity of the livestock is abnormal, and sending an abnormal alarm to the user.
Further, the depth tracking model includes an animal re-identification model and an animal tracking AI model, and the step of comparing all animal sample graphs of the current frame with all animal sample graphs of the previous frame through the pre-trained depth tracking model to obtain a tracking detection matching frame and an unnecessary tracking frame includes:
Performing livestock re-recognition on the livestock sample graph through the livestock re-recognition model to obtain feature vectors with the same number as the detection frames;
And comparing all the characteristic vectors of the current frame with all the characteristic vectors of the previous frame through the motion matching degree and the apparent matching degree in the livestock tracking AI model to obtain a tracking detection matching frame and an redundant tracking frame of the current frame.
Further, the step of comparing all feature vectors of the current frame with all feature vectors of the previous frame to obtain a tracking detection matching frame and an unnecessary tracking frame of the current frame through the motion matching degree and the apparent matching degree in the livestock tracking AI model includes:
inputting the acquired pictures into the livestock tracking AI model, and outputting a tracking frame by the livestock tracking AI model;
Comparing all feature vectors of the current frame with all feature vectors of the previous frame through the motion matching degree and the apparent matching degree in the livestock tracking AI model, and taking a detection frame with the same feature vector of the current frame and the previous frame as a tracking detection matching frame;
comparing all feature vectors of the current frame with all feature vectors in a tracking frame of the previous frame, and taking a tracking frame which is different from the feature vector of the current frame detection frame in the tracking frame of the previous frame as an unnecessary tracking frame to obtain a tracking detection matching frame and an unnecessary tracking frame of the current frame.
Further, the step of obtaining the tracking detection matching frame and the redundant tracking frame of the current frame includes:
Taking a detection frame with different characteristic vectors of the current frame and the previous frame as an excessive detection frame;
Calculating whether the sum of the number of the tracking detection matching frames and the number of the redundant detection frames is consistent with the number of the current frame detection frames or not;
if the number is consistent, respectively taking the tracking detection matching frame and the redundant tracking frame as the tracking detection matching frame and the redundant tracking frame of the current frame;
if the number is inconsistent, repeating the feature vector comparison to reacquire the tracking detection matching frame, the redundant tracking frame and the redundant detection frame for recalculation, and sending an error report to appointed personnel when the recalculated number is still inconsistent.
Further, the step of sequentially determining the content in each redundant tracking frame through a pre-trained livestock classification model, and taking the redundant tracking frame as a tracking and repairing leakage detection frame if the content determination result in the redundant tracking frame is true livestock comprises the following steps:
acquiring the content in an excessive tracking frame of the acquired picture, wherein the content in the excessive tracking frame is an image of a single livestock judged by a model;
Classifying the content in each redundant tracking frame in turn through the livestock classification model;
And judging the redundant tracking frames with the classification probability larger than a preset threshold value as the positions of the real livestock, and obtaining the tracking leakage repairing detection frames.
Further, the step of determining the redundant tracking frame with the classification probability greater than the preset threshold value as the position of the real livestock includes:
calculating classification probability through a classification probability formula, and judging the redundant tracking frames with the classification probability larger than a preset threshold value as positions of the real livestock;
The calculation formula of the classification probability is as follows
Wherein i is a category, e is a natural index, P is a probability, and Vi is a classification network output value of the livestock classification model corresponding to the category i.
Further, the step of controlling the camera installed in the livestock pen to perform video acquisition comprises the following steps:
And controlling a camera arranged in the livestock pen to acquire video of the livestock pen at a frequency of 1 time/second and a duration of 1 second/time.
In order to solve the technical problems, the embodiment of the application also provides a device for monitoring the quantity of livestock, which adopts the following technical scheme:
an apparatus for monitoring the quantity of livestock comprising:
the acquisition module is used for controlling cameras arranged in livestock pens to acquire video, and intercepting the video according to frames to obtain acquisition pictures;
the detection module is used for detecting the livestock of the acquired pictures according to a pre-trained target detection AI model to obtain at least one detection frame, wherein the content in the detection frame is an image of a single livestock judged by the model;
The acquisition module is used for intercepting the image of a single livestock in the detection frame to obtain a livestock sample graph, and comparing all the livestock sample graphs of the current frame with all the livestock sample graphs of the previous frame through a pre-trained depth tracking model to obtain a tracking detection matching frame and an redundant tracking frame;
The judging module is used for judging the content in each redundant tracking frame in sequence through a pre-trained livestock classification model, and if the content judgment result in the redundant tracking frame is true livestock, the redundant tracking frame is used as a tracking leakage repairing detection frame;
the calculation module is used for adding the number of the obtained tracking leakage repairing detection frames with the number of the tracking detection matching frames to obtain the number of actual livestock, and taking the actual livestock as a statistical result;
The comparison module is used for comparing the statistical result with the quantity of livestock stored in the database; and
And the alarm module is used for judging that the quantity of the livestock is abnormal if the statistical result is inconsistent with the quantity of the livestock stored in the database, and sending an abnormal alarm to a user.
In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical schemes:
a computer device comprising a memory and a processor, said memory having stored therein a computer program, said processor, when executing said computer program, performing the steps of the method of monitoring the number of livestock as described above.
In order to solve the above technical problems, an embodiment of the present application further provides a computer readable storage medium, which adopts the following technical schemes:
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method of monitoring a number of livestock as described above. Further, the computer-usable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created from the use of blockchain nodes, and the like.
Compared with the prior art, the embodiment of the application has the following main beneficial effects:
The application takes the target detection AI model as the basis, introduces the depth tracking model and the livestock classification model, makes full use of video information captured by the camera, and further takes the obtained tracking detection matching frame as one of the livestock statistics data instead of directly carrying out subsequent calculation by the number of the detection frames by comparing the detected livestock images of the current frame and the previous frame, thereby effectively reducing the multi-detection rate. And the true livestock judgment is carried out on the obtained content in the redundant tracking frame, so that the omission ratio is reduced, and the accuracy of the detection of the model is further improved. Meanwhile, the application can automatically count the number of livestock in the farm, automatically report the statistical result and achieve the purpose of automatic real-time early warning. When the later period of livestock loss occurs, the livestock can be helped to find reasons by finding the time point when the predicted quantity of the livestock is reduced and playing back the video of the descending time period, so that the damage can be timely stopped.
Drawings
In order to more clearly illustrate the solution of the present application, a brief description will be given below of the drawings required for the description of the embodiments of the present application, it being apparent that the drawings in the following description are some embodiments of the present application, and that other drawings may be obtained from these drawings without the exercise of inventive effort for a person of ordinary skill in the art.
FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 is a flow chart of one embodiment of a method of monitoring the number of livestock in accordance with the present application;
FIG. 3 is a schematic view of an embodiment of an apparatus for monitoring the number of animals according to the present application;
FIG. 4 is a schematic structural diagram of one embodiment of a computer device in accordance with the present application.
Reference numerals: 200. a computer device; 201. a memory; 202. a processor; 203. a network interface; 300. means for monitoring the number of livestock; 301. an acquisition module; 302. a detection module; 303. an acquisition module; 304. a judgment module; 305. a computing module; 306. a comparison module; 307. and an alarm module.
Detailed Description
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the applications herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having" and any variations thereof in the description of the application and the claims and the description of the drawings above are intended to cover a non-exclusive inclusion. The terms first, second and the like in the description and in the claims or in the above-described figures, are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
In order to make the person skilled in the art better understand the solution of the present application, the technical solution of the embodiment of the present application will be clearly and completely described below with reference to the accompanying drawings.
As shown in fig. 1, a system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various communication client applications, such as a web browser application, a shopping class application, a search class application, an instant messaging tool, a mailbox client, social platform software, etc., may be installed on the terminal devices 101, 102, 103.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablet computers, electronic book readers, MP3 players (Moving Picture Experts Group Audio Layer III, dynamic video expert compression standard audio plane 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic video expert compression standard audio plane 4) players, laptop and desktop computers, and the like.
The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the terminal devices 101, 102, 103.
It should be noted that, the method for monitoring the number of livestock provided by the embodiment of the present application is generally executed by a server/terminal device, and accordingly, the device for monitoring the number of livestock is generally disposed in the server/terminal device.
It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to fig. 2, a flow chart of one embodiment of a method of monitoring a quantity of livestock in accordance with the present application is shown. The method for monitoring the livestock quantity comprises the following steps:
s1: and controlling cameras arranged in livestock pens to acquire videos, and capturing the videos according to frames to obtain acquired pictures.
In this embodiment, a monitoring camera is deployed for each livestock farm to be monitored, so as to achieve the purpose of acquiring videos of the livestock farm, where the camera is a wide-angle camera, so as to ensure that images of the whole livestock farm can be acquired, and in the process of acquiring the videos, livestock in the livestock farm are not missed, and the livestock can be animals such as cattle, sheep, pigs, and the like. The video is intercepted according to the frame, so that the time interval between acquired collected pictures is small, and the situation that the pictures have large differences due to long time interval is avoided.
The step of controlling the camera installed in the livestock pen to acquire video comprises the following steps of:
And controlling a camera arranged in the livestock pen to acquire video of the livestock pen at a frequency of 1 time/second and a duration of 1 second/time.
In this embodiment, the frame rate of the camera is generally 30 frames or 60 frames, and compared with the scheme of acquiring multiple times per second, the application acquires once per second, thereby reducing the density of data transmission. The duration of the acquired video is 1 second, so that the video cannot be excessively large, and the transmission speed is improved.
S2: and detecting the livestock of the acquired pictures according to a pre-trained target detection AI model to obtain at least one detection frame, wherein the content in the detection frame is an image of a single livestock judged by the model.
In this embodiment, the target detection AI model is a generic object detection model, and as a pre-training model, the target detection AI model is pre-trained based on a data set of livestock types, and the object detection model is a model pre-constructed using one of the following algorithms: SSD algorithm, fast RCNN algorithm, FASTER RCNN algorithm. All three algorithms are algorithms in the convolutional neural network technology, and the specific algorithm is adopted to construct an object detection model, so that the algorithm can be determined according to the actual requirement of object detection. And adopting an object detection AI model to ensure that the position of the livestock can be detected initially, and selecting the livestock in the picture by a frame.
S3: and intercepting the image of a single livestock in the detection frame to obtain a livestock sample graph, and comparing all the livestock sample graphs of the current frame with all the livestock sample graphs of the previous frame through a pre-trained depth tracking model to obtain a tracking detection matching frame and an redundant tracking frame.
In this embodiment, the matching frame for tracking detection and the redundant tracking frame are determined by comparing the depth tracking models, so that livestock determination can be performed subsequently.
Specifically, the depth tracking model includes an animal re-identification model and an animal tracking AI model, and the step of comparing all animal sample graphs of the current frame with all animal sample graphs of the previous frame through the pre-trained depth tracking model to obtain a tracking detection matching frame and an unnecessary tracking frame includes:
Performing livestock re-recognition on the livestock sample graph through the livestock re-recognition model to obtain feature vectors with the same number as the detection frames;
And comparing all the characteristic vectors of the current frame with all the characteristic vectors of the previous frame through the motion matching degree and the apparent matching degree in the livestock tracking AI model to obtain a tracking detection matching frame and an redundant tracking frame of the current frame.
In this embodiment, because the moving speed of livestock in the farm is not fast compared with the frame rate of the camera, the information of the motion matching degree has a better effect on detecting the number of the livestock, specifically, the similarity of the motion is obtained through kalman filtering, and the motion matching degree is obtained through cascade matching. And then extracting and calculating apparent matching degree through a deep neural network. The matching degree of the detection frame can be obtained frame by frame through the motion matching degree and the apparent matching degree, so that the tracking detection matching frame and the redundant tracking frame of the current frame are obtained according to the matching degree. The Re-recognition model adopts a Re-recognition model DSA-reID (DENSELY SEMANTICALLY ALIGNED Person Re-identfication) based on dense semantic alignment, so that the problem of spatial semantic misalignment widely existing in Re-recognition is effectively solved, and the algorithm precision of the Re-recognition technology is remarkably improved. The dense semantics better solve the problems of different shooting visual angles, large obstacle shielding and background difference and the like in practical application.
Further, the step of comparing all feature vectors of the current frame with all feature vectors of the previous frame to obtain a tracking detection matching frame and an unnecessary tracking frame of the current frame through the motion matching degree and the apparent matching degree in the livestock tracking AI model includes:
inputting the acquired pictures into the livestock tracking AI model, and outputting a tracking frame by the livestock tracking AI model;
Comparing all feature vectors of the current frame with all feature vectors of the previous frame through the motion matching degree and the apparent matching degree in the livestock tracking AI model, and taking a detection frame with the same feature vector of the current frame and the previous frame as a tracking detection matching frame;
comparing all feature vectors of the current frame with all feature vectors in a tracking frame of the previous frame, and taking a tracking frame which is different from the feature vector of the current frame detection frame in the tracking frame of the previous frame as an unnecessary tracking frame to obtain a tracking detection matching frame and an unnecessary tracking frame of the current frame.
In this embodiment, the method further includes comparing all feature vectors of the current frame with all feature vectors in a tracking frame of a previous frame, and using a detection frame different from the feature vectors of the previous frame as an unnecessary detection frame. The tracking detection matching frame, the redundant detection frame and the redundant detection frame are obtained through the comparison between the feature vectors of the upper frame and the lower frame, and the accuracy of the matching result is ensured.
The step of obtaining the tracking detection matching frame and the redundant tracking frame of the current frame comprises the following steps:
Taking a detection frame with different characteristic vectors of the current frame and the previous frame as an excessive detection frame;
Calculating whether the sum of the number of the tracking detection matching frames and the number of the redundant detection frames is consistent with the number of the current frame detection frames or not;
if the number is consistent, respectively taking the tracking detection matching frame and the redundant tracking frame as the tracking detection matching frame and the redundant tracking frame of the current frame;
if the number is inconsistent, repeating the feature vector comparison to reacquire the tracking detection matching frame, the redundant tracking frame and the redundant detection frame for recalculation, and sending an error report to appointed personnel when the recalculated number is still inconsistent.
In this embodiment, the number of tracking detection matching frames and the number of redundant detection frames should be added to the number of current frame detection frames. And adding the q redundant detection frames and the tracking detection matching frames to be equal to the m detection frames, and carrying out mathematical checking calculation. And if the numbers are equal, respectively taking the tracking detection matching frame and the redundant tracking frame as the tracking detection matching frame and the redundant tracking frame of the current frame. If the numbers are unequal, the obtained redundant detection frame q or the tracking detection matching frame l is considered to have errors, the feature vector comparison is conducted again to acquire the tracking detection matching frame, the redundant tracking frame and the redundant detection frame again for recalculation, and error reports are sent to related personnel when the recalculated numbers are still inconsistent, so that verification in the detection process is realized, and the error rate of a computer is reduced.
In other embodiments, the feature vector comparison is not repeated, and an error report is directly sent to the related personnel when the numbers are not equal.
S4: and judging the content of each redundant tracking frame in sequence through a pre-trained livestock classification model, and taking the redundant tracking frame as a tracking leakage repairing detection frame if the content judgment result in the redundant tracking frame is true livestock.
In the embodiment, the method can be used as a good supplement, the content in the redundant tracking frames is judged through an animal classification model, and when the content is judged to be true animals, the real animals are used as tracking and repairing and missing detection frames, so that missing detection animals aiming at single-frame images are retrieved.
The step of sequentially judging the content in each redundant tracking frame through the pre-trained livestock classification model, and taking the redundant tracking frame as a tracking and repairing leakage detection frame if the content judgment result in the redundant tracking frame is true livestock comprises the following steps:
acquiring the content in an excessive tracking frame of the acquired picture, wherein the content in the excessive tracking frame is an image of a single livestock judged by a model;
Classifying the content in each redundant tracking frame in turn through the livestock classification model;
And judging the redundant tracking frames with the classification probability larger than a preset threshold value as the positions of the real livestock, and obtaining the tracking leakage repairing detection frames.
In this embodiment, whether the livestock is a true livestock is determined by the classification model, a threshold is preset, when the classification probability exceeds the threshold, it is determined that the livestock in the current redundant tracking frame belongs to the livestock type of the present application, and the livestock is determined to be the true livestock, so that other livestock not belonging to the livestock type of the present application are prevented from being mixed into the livestock pen, further the calculation of the number of the livestock is affected, and the multi-detection rate of the output result of the computer is reduced.
Further, the step of determining the redundant tracking frame with the classification probability greater than the preset threshold value as the position of the real livestock includes:
calculating classification probability through a classification probability formula, and judging the redundant tracking frames with the classification probability larger than a preset threshold value as positions of the real livestock;
The calculation formula of the classification probability is as follows
Wherein i is a category, e is a natural index, P is a probability, and Vi is a classification network output value of the livestock classification model corresponding to the category i.
In this embodiment, by calculating the classification probability, it is determined whether the animal is a real animal, and the occurrence of erroneous recognition is prevented, and the occurrence of multiple inspection is prevented.
S5: and adding the number of the obtained tracking leakage repairing detection frames with the number of the tracking detection matching frames to obtain the actual livestock number as a statistical result.
In this embodiment, the object detection AI model, the depth tracking model, and the livestock classification model are all pre-trained based on a dataset of livestock types. The depth tracking model includes an animal re-identification model and an animal tracking AI model. The livestock re-identification model, the livestock tracking AI model and the livestock classification model are all universal re-identification, tracking and classification models. The number of the tracking and repairing detection frames is added with the number of the tracking and detecting matching frames to serve as the actual livestock number, so that the multi-detection rate and the omission rate of the computer on livestock detection are reduced.
S6: and comparing the statistical result with the quantity of livestock stored in the database.
In this embodiment, the number of the livestock of the farm is pre-stored in the database, and the statistics result is compared with the pre-stored number to determine whether the number of the livestock of the farm is changed.
S7: if the statistical result is inconsistent with the quantity of the livestock stored in the database, judging that the quantity of the livestock is abnormal, and sending an abnormal alarm to the user.
In this embodiment, when the livestock is lost, the user is timely reminded, and the livestock can be helped to find the reason and timely stop loss by finding the time point when the predicted quantity of the livestock is reduced and playing back the video of the descending time period.
Wherein after the step of comparing the statistics with the number of livestock stored in the database, the method further comprises:
And if the statistical result is consistent with the quantity of the livestock stored in the database, judging that the quantity of the livestock is normal.
In this embodiment, if the numbers are consistent, it is determined that the livestock is not increased or decreased, and the monitoring of the farm is continued.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored in a computer-readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. The storage medium may be a nonvolatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a random access Memory (Random Access Memory, RAM).
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.
With further reference to fig. 3, as an implementation of the method shown in fig. 2 described above, the present application provides an embodiment of an apparatus for monitoring the number of animals, which corresponds to the embodiment of the method shown in fig. 2, which is particularly applicable in various electronic devices.
As shown in fig. 3, the apparatus 300 for monitoring the number of livestock according to the present embodiment includes: the system comprises an acquisition module 301, a detection module 302, an acquisition module 303, a judgment module 304, a calculation module 305, a comparison module 306 and an alarm module 307. Wherein:
The acquisition module 301 is used for controlling a camera installed in the livestock pen to acquire video, and intercepting the video according to frames to obtain an acquisition picture;
The detection module 302 is configured to detect the collected image according to a pre-trained target detection AI model, so as to obtain at least one detection frame, where the content in the detection frame is an image of a single animal determined by the model;
an obtaining module 303, configured to intercept an image of a single animal in the detection frame, obtain an animal sample map, compare all animal sample maps of a current frame with all animal sample maps of a previous frame through a pre-trained depth tracking model, and obtain a tracking detection matching frame and an redundant tracking frame;
the judging module 304 is configured to judge, through a pre-trained livestock classification model, content in each redundant tracking frame in sequence, and if the content judgment result in the redundant tracking frame is true livestock, use the redundant tracking frame as a tracking leakage repairing detection frame;
The calculation module 305 is configured to add the number of the obtained tracking repair leak detection frames to the number of the tracking detection matching frames, so as to obtain the actual number of livestock, which is used as a statistical result;
a comparison module 306, configured to compare the statistical result with the number of livestock stored in the database; and
And the alarm module 307 is used for judging that the livestock quantity is abnormal when the statistical result is inconsistent with the livestock quantity stored in the database, and sending an abnormal alarm to the user.
In the embodiment, a depth tracking model and a livestock classification model are introduced based on an object detection AI model, so that time information captured by a camera is fully utilized, and a false recognition detection frame is determined by comparing detected livestock images of a current frame and a previous frame, so that the multi-detection rate is reduced; and the true livestock judgment is carried out on the obtained content in the redundant tracking frame, so that the omission ratio is reduced, and the accuracy of the detection of the model is further improved.
The acquisition module 301 is further configured to control a camera installed in the livestock pen to perform video acquisition on the livestock pen at a frequency of1 time/second for a duration of1 second/time. The depth tracking model includes an animal re-identification model and an animal tracking AI model, and the acquisition module 303 includes a re-identification sub-module and an acquisition sub-module. And the re-recognition sub-module is used for re-recognizing the livestock sample graph through the livestock re-recognition model to obtain feature vectors with the same number as the detection frames. The obtaining submodule is used for comparing all the characteristic vectors of the current frame with all the characteristic vectors of the previous frame through the motion matching degree and the apparent matching degree in the livestock tracking AI model to obtain a tracking detection matching frame and an redundant tracking frame of the current frame.
The acquisition submodule comprises an input unit and a comparison unit, wherein the input unit is used for inputting an acquired picture into the livestock tracking AI model, and the livestock tracking AI model outputs a tracking frame; the comparison unit is used for comparing all feature vectors of the current frame with all feature vectors of the previous frame through the motion matching degree and the apparent matching degree in the livestock tracking AI model, taking a detection frame with the same feature vector of the current frame and the previous frame as a tracking detection matching frame, and taking a tracking frame which is different from the feature vector of the detection frame of the current frame in the tracking frame of the previous frame as an unnecessary tracking frame to obtain the tracking detection matching frame and the unnecessary tracking frame of the current frame.
The comparison unit comprises a comparison subunit, a calculation subunit, an output subunit and a re-identification subunit, wherein the comparison subunit is used for taking a detection frame with different characteristic vectors of a current frame and a previous frame as an unnecessary detection frame; the calculating subunit is used for calculating whether the sum of the number of the tracking detection matching frames and the number of the redundant detection frames is consistent with the number of the current frame detection frames or not; the output subunit is used for respectively taking the tracking detection matching frame and the redundant tracking frame as the tracking detection matching frame and the redundant tracking frame of the current frame when the quantity is consistent; and the re-identification subunit is used for repeatedly comparing the feature vectors to re-acquire the tracking detection matching frame, the redundant tracking frame and the redundant detection frame for re-calculation when the number is inconsistent, and sending an error report to appointed personnel when the number after re-calculation is still inconsistent.
The determining module 304 includes an acquiring sub-module, a classifying sub-module and a threshold sub-module, where the acquiring sub-module is configured to acquire contents in an extra tracking frame of the acquired picture, where the contents in the extra tracking frame are images of a single livestock determined by a model; the classifying sub-module is used for sequentially classifying the content in each redundant tracking frame through the livestock classifying model; and the threshold sub-module is used for judging the redundant tracking frames with the classification probability larger than a preset threshold as the positions of the real livestock to obtain tracking repair leakage detection frames.
In order to solve the technical problems, the embodiment of the application also provides computer equipment. Referring specifically to fig. 4, fig. 4 is a basic structural block diagram of a computer device according to the present embodiment.
The computer device 200 includes a memory 201, a processor 202, and a network interface 203 communicatively coupled to each other via a system bus. It should be noted that only computer device 200 having components 201-203 is shown in the figures, but it should be understood that not all of the illustrated components are required to be implemented and that more or fewer components may be implemented instead. It will be appreciated by those skilled in the art that the computer device herein is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and its hardware includes, but is not limited to, a microprocessor, an Application SPECIFIC INTEGRATED Circuit (ASIC), a Programmable gate array (Field-Programmable GATE ARRAY, FPGA), a digital Processor (DIGITAL SIGNAL Processor, DSP), an embedded device, and the like.
The computer equipment can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing equipment. The computer equipment can perform man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch pad or voice control equipment and the like.
The memory 201 includes at least one type of readable storage medium including flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the storage 201 may be an internal storage unit of the computer device 200, such as a hard disk or a memory of the computer device 200. In other embodiments, the memory 201 may also be an external storage device of the computer device 200, such as a plug-in hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD) or the like, which are provided on the computer device 200. Of course, the memory 201 may also include both internal storage units of the computer device 200 and external storage devices. In this embodiment, the memory 201 is generally used to store an operating system and various types of application software installed in the computer device 200, such as program codes of a method for monitoring the number of livestock, and the like. In addition, the memory 201 may be used to temporarily store various types of data that have been output or are to be output.
The processor 202 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 202 is generally used to control the overall operation of the computer device 200. In this embodiment, the processor 202 is configured to execute the program code stored in the memory 201 or process data, such as the program code of the method of monitoring the number of animals.
The network interface 203 may comprise a wireless network interface or a wired network interface, which network interface 203 is typically used to establish communication connections between the computer device 200 and other electronic devices.
In the embodiment, the time information captured by the camera is fully utilized, and the false recognition detection frame is determined by comparing the detected livestock images of the current frame and the previous frame, so that the multiple detection rate is reduced; and the true livestock judgment is carried out on the obtained content in the redundant tracking frame, so that the omission ratio is reduced, and the accuracy of the detection of the model is further improved.
The present application also provides another embodiment, namely, a computer-readable storage medium storing a program for monitoring a quantity of livestock, the program for monitoring the quantity of livestock being executable by at least one processor to cause the at least one processor to perform the steps of the method for monitoring the quantity of livestock as described above. Further, the computer-usable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created from the use of blockchain nodes, and the like.
The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The blockchain (Blockchain), essentially a de-centralized database, is a string of data blocks that are generated in association using cryptographic methods, each of which contains information from a batch of network transactions for verifying the validity (anti-counterfeit) of its information and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
In the embodiment, the time information captured by the camera is fully utilized, and the false recognition detection frame is determined by comparing the detected livestock images of the current frame and the previous frame, so that the multiple detection rate is reduced; and the true livestock judgment is carried out on the obtained content in the redundant tracking frame, so that the omission ratio is reduced, and the accuracy of the detection of the model is further improved.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present application.
It is apparent that the above-described embodiments are only some embodiments of the present application, but not all embodiments, and the preferred embodiments of the present application are shown in the drawings, which do not limit the scope of the patent claims. This application may be embodied in many different forms, but rather, embodiments are provided in order to provide a thorough and complete understanding of the present disclosure. Although the application has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described in the foregoing description, or equivalents may be substituted for elements thereof. All equivalent structures made by the content of the specification and the drawings of the application are directly or indirectly applied to other related technical fields, and are also within the scope of the application.
Claims (6)
1. A method of monitoring the quantity of livestock comprising the steps of:
controlling cameras arranged in livestock pens to acquire videos, and capturing the videos according to frames to obtain acquired pictures;
Detecting livestock on the acquired pictures according to a pre-trained target detection AI model to obtain at least one detection frame, wherein the content in the detection frame is an image of a single livestock judged by the model;
Intercepting the image of single livestock in the detection frame to obtain livestock sample graph, comparing all livestock sample graph of the current frame with all livestock sample graph of the previous frame by pre-trained depth tracking model to obtain tracking detection matching frame and redundant tracking frame, wherein the depth tracking model comprises livestock re-identification model and livestock tracking AI model,
The step of comparing all animal sample graphs of the current frame with all animal sample graphs of the previous frame through a pre-trained depth tracking model to obtain a tracking detection matching frame and an redundant tracking frame comprises the following steps:
Performing livestock re-recognition on the livestock sample graph through the livestock re-recognition model to obtain feature vectors with the same number as the detection frames;
comparing all feature vectors of the current frame with all feature vectors of the previous frame through the motion matching degree and the apparent matching degree in the livestock tracking AI model to obtain a tracking detection matching frame and an redundant tracking frame of the current frame, wherein the step of comparing all feature vectors of the current frame with all feature vectors of the previous frame through the motion matching degree and the apparent matching degree in the livestock tracking AI model to obtain the tracking detection matching frame and the redundant tracking frame of the current frame comprises the following steps:
inputting the acquired pictures into the livestock tracking AI model, and outputting a tracking frame by the livestock tracking AI model;
Comparing all feature vectors of the current frame with all feature vectors of the previous frame through the motion matching degree and the apparent matching degree in the livestock tracking AI model, and taking a detection frame with the same feature vector of the current frame and the previous frame as a tracking detection matching frame;
Comparing all feature vectors of the current frame with all feature vectors in a tracking frame of a previous frame, taking a tracking frame which is different from the feature vectors of a detection frame of the current frame in the tracking frame of the previous frame as an unnecessary tracking frame, and obtaining a tracking detection matching frame and an unnecessary tracking frame of the current frame, wherein the step of obtaining the tracking detection matching frame and the unnecessary tracking frame of the current frame comprises the following steps:
Taking a detection frame with different characteristic vectors of the current frame and the previous frame as an excessive detection frame;
Calculating whether the sum of the number of the tracking detection matching frames and the number of the redundant detection frames is consistent with the number of the current frame detection frames or not;
if the number is consistent, respectively taking the tracking detection matching frame and the redundant tracking frame as the tracking detection matching frame and the redundant tracking frame of the current frame;
If the number is inconsistent, repeating the feature vector comparison to reacquire the tracking detection matching frame, the redundant tracking frame and the redundant detection frame for recalculation, and sending an error report to appointed personnel when the recalculated number is still inconsistent;
Judging the content of each redundant tracking frame in sequence through a pre-trained livestock classification model, and taking the redundant tracking frame as a tracking, repairing and leakage and detecting frame if the content judgment result in the redundant tracking frame is true livestock;
Adding the number of the obtained tracking leakage repairing detection frames with the number of the tracking detection matching frames to obtain the number of actual livestock, and taking the actual livestock as a statistical result;
comparing the statistical result with the quantity of livestock stored in a database; and
If the statistical result is inconsistent with the quantity of the livestock stored in the database, judging that the quantity of the livestock is abnormal, and sending an abnormal alarm to the user.
2. The method of monitoring the quantity of livestock according to claim 1, wherein the step of sequentially determining the content of each redundant tracking frame by a pre-trained livestock classification model, and if the content determination result in the redundant tracking frame is a real livestock, using the redundant tracking frame as a tracking patch-leak detection frame comprises:
acquiring the content in an excessive tracking frame of the acquired picture, wherein the content in the excessive tracking frame is an image of a single livestock judged by a model;
Classifying the content in each redundant tracking frame in turn through the livestock classification model;
Determining the redundant tracking frame with the classification probability larger than a preset threshold value as the position of the real livestock to obtain a tracking repair leakage detection frame, wherein the step of determining the redundant tracking frame with the classification probability larger than the preset threshold value as the position of the real livestock comprises the following steps: and calculating the classification probability through a classification probability formula, and judging the redundant tracking frame with the classification probability larger than a preset threshold value as the position of the real livestock.
3. The method of monitoring a quantity of livestock of claim 1, wherein the step of controlling video capture by cameras mounted to the livestock pens comprises:
And controlling a camera arranged in the livestock pen to acquire video of the livestock pen at a frequency of 1 time/second and a duration of 1 second/time.
4. An arrangement for monitoring a number of animals, characterized in that the arrangement for monitoring a number of animals is adapted to carry out the steps of the method for monitoring a number of animals as claimed in any one of claims 1 to 3, the arrangement for monitoring a number of animals comprising:
the acquisition module is used for controlling cameras arranged in livestock pens to acquire video, and intercepting the video according to frames to obtain acquisition pictures;
the detection module is used for detecting the livestock of the acquired pictures according to a pre-trained target detection AI model to obtain at least one detection frame, wherein the content in the detection frame is an image of a single livestock judged by the model;
The acquisition module is used for intercepting the image of a single livestock in the detection frame to obtain a livestock sample graph, and comparing all the livestock sample graphs of the current frame with all the livestock sample graphs of the previous frame through a pre-trained depth tracking model to obtain a tracking detection matching frame and an redundant tracking frame;
The judging module is used for judging the content in each redundant tracking frame in sequence through a pre-trained livestock classification model, and if the content judgment result in the redundant tracking frame is true livestock, the redundant tracking frame is used as a tracking leakage repairing detection frame;
the calculation module is used for adding the number of the obtained tracking leakage repairing detection frames with the number of the tracking detection matching frames to obtain the number of actual livestock, and taking the actual livestock as a statistical result;
The comparison module is used for comparing the statistical result with the quantity of livestock stored in the database; and
And the alarm module is used for judging that the quantity of the livestock is abnormal if the statistical result is inconsistent with the quantity of the livestock stored in the database, and sending an abnormal alarm to a user.
5. A computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor, when executing the computer program, performing the steps of the method of monitoring the number of animals as claimed in any one of claims 1 to 3.
6. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the method of monitoring the number of livestock as claimed in any of claims 1 to 3.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010350129.0A CN111680551B (en) | 2020-04-28 | 2020-04-28 | Method, device, computer equipment and storage medium for monitoring livestock quantity |
| PCT/CN2020/105770 WO2021217934A1 (en) | 2020-04-28 | 2020-07-30 | Method and apparatus for monitoring number of livestock, and computer device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010350129.0A CN111680551B (en) | 2020-04-28 | 2020-04-28 | Method, device, computer equipment and storage medium for monitoring livestock quantity |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111680551A CN111680551A (en) | 2020-09-18 |
| CN111680551B true CN111680551B (en) | 2024-06-11 |
Family
ID=72433890
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010350129.0A Active CN111680551B (en) | 2020-04-28 | 2020-04-28 | Method, device, computer equipment and storage medium for monitoring livestock quantity |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111680551B (en) |
| WO (1) | WO2021217934A1 (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112150506A (en) * | 2020-09-27 | 2020-12-29 | 成都睿畜电子科技有限公司 | Target state detection method, device, medium and electronic equipment |
| CN112101291B (en) * | 2020-09-27 | 2024-01-30 | 成都睿畜电子科技有限公司 | Livestock nursing method, device, medium and electronic equipment |
| CN112734730B (en) * | 2021-01-11 | 2023-07-28 | 牧原食品股份有限公司 | Livestock quantity identification method, device, equipment and storage medium |
| CN112906483B (en) * | 2021-01-25 | 2024-01-23 | ***股份有限公司 | Target re-identification method, device and computer readable storage medium |
| CN113219964A (en) * | 2021-03-30 | 2021-08-06 | 广州朗国电子科技有限公司 | Poultry house environment inspection and regulation method, equipment and medium |
| CN113221776B (en) * | 2021-05-19 | 2024-05-28 | 彭东乔 | Method for identifying general behaviors of ruminants based on artificial intelligence |
| CN114120185B (en) * | 2021-11-16 | 2022-08-09 | 东莞先知大数据有限公司 | Three-bird-gear cage clearing determination method, electronic device and storage medium |
| CN113984767A (en) * | 2021-11-24 | 2022-01-28 | 牧原肉食品有限公司 | System, method, apparatus and computer storage medium for livestock carcass quality detection |
| CN114494863A (en) * | 2022-01-12 | 2022-05-13 | 北京小龙潜行科技有限公司 | Animal cub counting method and device based on Blend Mask algorithm |
| CN115100807A (en) * | 2022-06-17 | 2022-09-23 | 贵州东彩供应链科技有限公司 | System for realizing supervision of animal farm based on camera abnormity monitoring alarm |
| 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 |
| CN115546192B (en) * | 2022-11-03 | 2023-03-21 | 中国平安财产保险股份有限公司 | Livestock quantity identification method, device, equipment and storage medium |
| CN115861644A (en) * | 2022-11-21 | 2023-03-28 | 广东鉴面智能科技有限公司 | Biodiversity identification and analysis method, system and medium |
| CN115601401B (en) * | 2022-12-01 | 2023-04-07 | 中国平安财产保险股份有限公司 | Tracking counting method based on livestock group movement characteristics and related equipment thereof |
| CN116363494B (en) * | 2023-05-31 | 2023-08-04 | 睿克环境科技(中国)有限公司 | Fish quantity monitoring and migration tracking method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107680080A (en) * | 2017-09-05 | 2018-02-09 | 翔创科技（北京）有限公司 | The Sample Storehouse method for building up and counting method of livestock, storage medium and electronic equipment |
| CN108932496A (en) * | 2018-07-03 | 2018-12-04 | 北京佳格天地科技有限公司 | The quantity statistics method and device of object in region |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9084411B1 (en) * | 2014-04-10 | 2015-07-21 | Animal Biotech Llc | Livestock identification system and method |
| US10354342B2 (en) * | 2017-06-02 | 2019-07-16 | Performance Livestock Analytics, Inc. | Adaptive livestock growth modeling using machine learning approaches to predict growth and recommend livestock management operations and activities |
| CN108921105B (en) * | 2018-07-06 | 2020-11-03 | 京东数字科技控股有限公司 | Method and device for identifying target number and computer readable storage medium |
| DK3866587T3 (en) * | 2018-10-17 | 2023-05-01 | Groupe Ro Main Inc | MONITORING OF LIVESTOCK |
| CN109801260B (en) * | 2018-12-20 | 2021-01-26 | 北京海益同展信息科技有限公司 | Livestock number identification method and device, control device and readable storage medium |
| CN111008561B (en) * | 2019-10-31 | 2023-07-21 | 重庆小雨点小额贷款有限公司 | Method, terminal and computer storage medium for determining quantity of livestock |
| CN111008560A (en) * | 2019-10-31 | 2020-04-14 | 重庆小雨点小额贷款有限公司 | Livestock weight determination method, device, terminal and computer storage medium |
| CN110853076B (en) * | 2019-11-08 | 2023-03-31 | 重庆市亿飞智联科技有限公司 | Target tracking method, device, equipment and storage medium |
-
2020
- 2020-04-28 CN CN202010350129.0A patent/CN111680551B/en active Active
- 2020-07-30 WO PCT/CN2020/105770 patent/WO2021217934A1/en active Application Filing
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107680080A (en) * | 2017-09-05 | 2018-02-09 | 翔创科技（北京）有限公司 | The Sample Storehouse method for building up and counting method of livestock, storage medium and electronic equipment |
| CN108932496A (en) * | 2018-07-03 | 2018-12-04 | 北京佳格天地科技有限公司 | The quantity statistics method and device of object in region |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111680551A (en) | 2020-09-18 |
| WO2021217934A1 (en) | 2021-11-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111680551B (en) | Method, device, computer equipment and storage medium for monitoring livestock quantity | |
| CN110033018B (en) | Graph similarity judging method and device and computer readable storage medium | |
| CN109034069B (en) | Method and apparatus for generating information | |
| WO2021041176A1 (en) | Shuffle, attend, and adapt: video domain adaptation by clip order prediction and clip attention alignment | |
| CN110610125A (en) | Ox face identification method, device, equipment and storage medium based on neural network | |
| CN110969045B (en) | Behavior detection method and device, electronic equipment and storage medium | |
| CN110795714A (en) | Identity authentication method and device, computer equipment and storage medium | |
| CN114550053A (en) | Traffic accident responsibility determination method, device, computer equipment and storage medium | |
| CN112231038B (en) | Work order information display method, device, computer equipment and storage medium | |
| CN112529939A (en) | Target track matching method and device, machine readable medium and equipment | |
| CN113591758A (en) | Human behavior recognition model training method and device and computer equipment | |
| CN116311370A (en) | Multi-angle feature-based cow face recognition method and related equipment thereof | |
| CN111325181A (en) | State monitoring method and device, electronic equipment and storage medium | |
| CN112396048B (en) | Picture information extraction method and device, computer equipment and storage medium | |
| CN113239883A (en) | Method and device for training classification model, electronic equipment and storage medium | |
| CN115424335B (en) | Living body recognition model training method, living body recognition method and related equipment | |
| CN115757075A (en) | Task abnormity detection method and device, computer equipment and storage medium | |
| CN112784691B (en) | Target detection model training method, target detection method and device | |
| JPWO2019187107A1 (en) | Information processing equipment, control methods, and programs | |
| CN115393755A (en) | Visual target tracking method, device, equipment and storage medium | |
| CN112989869B (en) | Optimization method, device, equipment and storage medium of face quality detection model | |
| CN114385993A (en) | Identity detection method, device and readable medium | |
| CN112364683A (en) | Case evidence fixing method and device | |
| CN112733645A (en) | Handwritten signature verification method and device, computer equipment and storage medium | |
| TWI823478B (en) | Method, electronic equipment and storage medium for action management for artificial intelligence |
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 |