CN111340801A - Livestock checking method, device, equipment and storage medium - Google Patents
Livestock checking method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN111340801A CN111340801A CN202010216268.4A CN202010216268A CN111340801A CN 111340801 A CN111340801 A CN 111340801A CN 202010216268 A CN202010216268 A CN 202010216268A CN 111340801 A CN111340801 A CN 111340801A
- Authority
- CN
- China
- Prior art keywords
- livestock
- image
- gaussian
- checked
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 244000144972 livestock Species 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000013135 deep learning Methods 0.000 claims abstract description 24
- 238000003062 neural network model Methods 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 22
- 238000012549 training Methods 0.000 claims abstract description 17
- 238000004590 computer program Methods 0.000 claims description 22
- 241000282887 Suidae Species 0.000 claims description 15
- 241001465754 Metazoa Species 0.000 claims description 13
- 238000002372 labelling Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000010354 integration Effects 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 description 10
- 238000001514 detection method Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000009395 breeding Methods 0.000 description 2
- 230000001488 breeding effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- 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
- G06T2207/10004—Still image; Photographic image
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a livestock checking method, a device, equipment and a storage medium, wherein the livestock checking method comprises the steps of obtaining an image to be checked of a place where livestock is located; respectively marking coordinate points at the geometric center point and a plurality of characteristic points of each target in the image to be checked; establishing an elliptical Gaussian model with the geometric central point as a Gaussian kernel based on the coordinate point, and obtaining a Gaussian density map; and inputting the image to be checked and the corresponding Gaussian density map into a deep learning neural network model, and performing regression training and integral processing to obtain the quantity of livestock. According to the embodiment of the invention, the accuracy of the pig number statistical result can be effectively improved.
Description
Technical Field
The invention relates to the field of cultivation, in particular to a livestock checking method, a device, equipment and a storage medium.
Background
The live pigs have very important significance as the biological assets of a company, and the number of the live pigs directly reflects the assets condition of the company. Therefore, the breeding companies need to count the number of pigs at regular intervals. The traditional checking method is that the statistics is carried out on each farm manually, a rough data is obtained through the superposition calculation of the number, the mode is time-consuming and labor-consuming, the efficiency is low, human factors exist, and the accuracy is not guaranteed.
With the development of computer technology, especially in recent years, computer vision, deep learning and other technologies fall on the ground in terms of engineering application, a live pig checking method by using the computer technology appears. The specific method in the prior art is to install a camera on a column of a live pig in a pig farm to acquire a picture or a video, mainly identify a live pig target in the picture or the video by adopting a target detection technology, and further count the number of the target pigs. However, the target detection technology is suitable for scenes with large targets, small quantity and low density, and the result accuracy of the technology adopted in scenes with small targets or large quantity and high density is reduced, one reason is that the recognition rate is low due to high density, serious shielding and small exposed area; another reason is that before training the model by using these target detection algorithms, the targets in the picture need to be labeled, as shown in fig. 1a, the targets are framed by rectangular frames, and labeling is relatively simple, however, this labeling method is poor in detection effect for the overlapped targets. Therefore, the target detection technology has higher labeling cost and certain influence on the labeling accuracy rate for scenes with numerous targets and higher density as shown in fig. 1b and fig. 1c, namely, the to-be-trained labeling file is not accurate, so that the model prediction error is larger, and the accuracy rate of the live pig inventory result is influenced.
Disclosure of Invention
The invention provides a livestock checking method, a livestock checking device, livestock checking equipment and a storage medium, which are used for solving the technical problem that the accuracy of the target detection technology adopted by the existing pig number of a farm is not high, and the accuracy of the statistical result of the pig number can be effectively improved.
In a first aspect, an embodiment of the present invention provides a livestock checking method, which at least includes the following steps:
acquiring an image to be checked of a place where livestock is located;
respectively marking coordinate points at the geometric center point and a plurality of characteristic points of each target in the image to be checked;
establishing an elliptical Gaussian model with the geometric central point as a Gaussian kernel based on the coordinate point, and obtaining a Gaussian density map;
and inputting the image to be checked and the corresponding Gaussian density map into a deep learning neural network model, and performing regression training and integral processing to obtain the quantity of livestock.
In a first implementation manner of the first aspect, the step of labeling coordinate points at a geometric center point and a plurality of feature points of each target in the image to be inventoried respectively specifically includes:
and when all targets in the image to be checked contain at least one partially-shielded target, selecting the geometric center of the maximum exposed area of the partially-shielded target to label the coordinate point.
In a second implementation manner of the first aspect, the feature points are two vertices on a longest longitudinal line segment and two vertices on a longest transverse line segment on the target.
In a third implementation manner of the first aspect, the step of establishing an elliptic gaussian model with the geometric center point as a gaussian kernel based on the coordinate point and obtaining a gaussian density map specifically includes:
taking the geometric central point and four vertexes of each target as parameter points, and establishing an elliptic Gaussian model taking the geometric central point as a Gaussian kernel;
and carrying out normalization processing on all the Gaussian models to obtain the Gaussian density map.
In a fourth implementation manner of the first aspect, the step of inputting the image to be inventoried and the corresponding gaussian density map into a deep learning neural network model and performing regression training and integral processing to obtain the number of livestock specifically includes:
establishing a deep learning neural network model;
inputting the image to be checked and the corresponding Gaussian density map into the deep learning neural network model for regression training;
and after the deep learning neural network model is trained, performing integral processing on the Gaussian density map mapped from the image to be inventoried to obtain the quantity of livestock.
In a fifth implementation form of the first aspect, the livestock is live pigs.
In a sixth implementation manner of the first aspect, the image to be inventoried is a top view image of a place where the livestock is located.
In a second aspect, an embodiment of the present invention further provides an animal checking device, including:
the image processing module is used for acquiring an image to be checked of a place where the livestock is located;
the marking module is used for marking coordinate points at the geometric center point and a plurality of characteristic points of each target in the image to be inventoried respectively;
the model establishing module is used for establishing an elliptic Gaussian model taking the geometric central point as a Gaussian kernel based on the coordinate point and obtaining a Gaussian density map;
and the data calculation module is used for inputting the image to be checked and the corresponding Gaussian density map into a deep learning neural network model and performing regression training and integral processing to obtain the quantity of the livestock.
In a third aspect, the embodiment of the present invention further provides an apparatus for livestock inventory, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor implements the above-mentioned livestock inventory method when executing the computer program.
In a fourth aspect, the embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, where when the computer program runs, the apparatus where the computer-readable storage medium is located is controlled to execute the above-mentioned livestock inventory method.
One of the above technical solutions has the following advantages: generating an image to be checked based on the acquired checking image; respectively marking coordinate points at the geometric center point and a plurality of characteristic points of each target in the image to be checked; establishing an elliptic Gaussian model taking the geometric central point as a Gaussian kernel based on the coordinate point, and obtaining a Gaussian density map; and inputting the image to be checked and the corresponding Gaussian density map into a deep learning neural network model, and performing regression training and integral processing to obtain the quantity of livestock. The density statistical technology replaces the existing target detection technology, an elliptic Gaussian density model is adopted to model the image, and a deep learning neural network model is combined, so that the accuracy of livestock number statistics can be effectively improved, the statistical cost is reduced, and the accuracy of the statistical result of the number of the live pigs can be improved when the statistical method is applied to the number statistics of the live pigs in a farm.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIGS. 1a to 1c show a target detection technique adopted in the prior art, wherein FIG. 1a is a rectangular frame used for framing a target for labeling, and FIGS. 1b and 1c are live pig breeding scene images with numerous targets and high density;
FIG. 2 is a schematic flow chart of a livestock inventory method provided by an embodiment of the invention;
FIG. 3 is a schematic flow chart of a livestock inventory method provided by an embodiment of the invention;
fig. 4a to 4b are schematic application diagrams of the livestock inventory method provided by the embodiment of the invention;
fig. 5a to 5c are gaussian model diagrams of the livestock inventory method according to the embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 2 and 3, a preferred embodiment of the present invention provides a livestock inventory method, comprising at least the steps of:
s10, acquiring an image to be checked of the place where the livestock is located; wherein, the livestock includes but not limited to live pigs, and the image to be checked is a density chart or thermodynamic diagram;
s20, respectively marking coordinate points at the geometric center point and a plurality of characteristic points of each target in the image to be checked;
s30, establishing an elliptical Gaussian model with the geometric center point as a Gaussian kernel based on the coordinate points, and obtaining a Gaussian density map;
and S40, inputting the image to be checked and the corresponding Gaussian density map into the deep learning neural network model, and performing regression training and integral processing to obtain the quantity of the livestock.
In this embodiment, the density statistical technique replaces the existing target detection technique, and a gaussian density model and a deep learning neural network model are adopted, so that the accuracy of livestock number statistics can be effectively improved, the statistical cost is reduced, and the accuracy of the statistical result of the number of live pigs can be improved when the livestock number statistical technique is applied to the number statistics of live pigs in a farm.
It should be noted that, in the embodiment of the present invention, the elliptical gaussian model is used to model the image to be inventoried with higher density, and the repeated tests prove that the final statistical result is improved by at least 10% in accuracy compared with the conventional standard circular gaussian model, so that the biological assets of livestock such as live pigs and the like can be inventoried more accurately.
In this embodiment of the present invention, in step S20, labeling coordinate points at the geometric center point and a plurality of feature points of each target in the to-be-checked image respectively, specifically:
and when all targets in the image to be checked contain at least one partially-shielded target, selecting the geometric center of the maximum exposed area of the partially-shielded target to label the coordinate point.
In one possible design, the feature points are two vertices on the longest longitudinal line segment and two vertices on the longest transverse line segment on the target. For the convenience of understanding, taking the inventory of the live pig as an example, as shown in fig. 5a, when the elliptical gaussian model is established, a total of 5 points are taken as parameter points for establishing the elliptical gaussian when two vertexes with the largest body length, two vertexes with the largest body width and the geometric central point of the whole pig body in the image to be invented are taken as the initialization central point of the gaussian kernel.
Specifically, as shown in fig. 4a to 4b, an image acquisition device is installed above a column of a live pig in each pig farm, and image data of the pig farm is acquired to perform punctuation on each live pig target. The labeling method may be performed by using tools such as labelImg, which are well known to those skilled in the art, and will not be described herein.
In order to reduce occlusion to a certain extent, the camera collects images from the right above, a point to be marked (a point replaces a pig) is selected to mark the geometric center of a live pig target, if occlusion exists, a target point is selected to mark the geometric center of an exposed part, and if the live pig is divided into a plurality of parts due to occlusion, the geometric center of the largest exposed area is selected.
Therefore, data such as pictures and videos are acquired through image acquisition equipment such as a camera, and then each target to be counted of the image to be checked is punctuated through a manual marking mode by utilizing a special picture marking tool. One coordinate point (x1, y2), (x2, y2) … … for each live pig target in the image to be checked until all targets are marked. Establishing an elliptic Gaussian model by using marked data, namely data with a plurality of coordinates on the marked data, wherein the size of the data is the same as that of the image, and each coordinate point is taken as a center, namely each live pig target is an elliptic Gaussian model; after normalization processing, the sum of each elliptical Gaussian model is 1, so that the number of pigs is the number of the elliptical Gaussian models, the sum of all the elliptical Gaussian models is the number of the pigs, a Gaussian density map is built, the Gaussian density map is used as a regression target, the original image is used as input, a deep learning neural network model is built, and end-to-end training is carried out. Through a large number of images and a plurality of iterations, the model has the capability of mapping from the original image to the Gaussian density image, and the number of the pigs in the image can be obtained through integration, namely accumulation, of the Gaussian density image.
In the embodiment of the present invention, in step S30, an elliptic gaussian model with the geometric center point as a gaussian kernel is established based on the coordinate point, and a gaussian density map is obtained, specifically:
s31, taking the geometric center point and the four vertexes of each target as parameter points, and establishing an elliptical Gaussian model taking the geometric center point as a Gaussian kernel;
and S32, performing normalization processing on all the elliptical Gaussian models to obtain a Gaussian density map.
In the embodiment of the invention, the Gaussian model is an elliptical Gaussian model, and the image to be checked is an overlook image of the activity place where the livestock is located. In this embodiment, compared with the general gaussian model, the embodiment of the present invention uses a special gaussian model, i.e. an elliptical gaussian model. When the camera head observes a live pig from a top view, the external shape of the camera head is more like an ellipse instead of a circle. The advantages of such a design are:
even if the live pig is crowded and partially sheltered, the part of the live pig which is exposed is similar to an ellipse. The contour of the high-density pig is simulated approximately by adopting elliptical gauss to replace circular gauss and controlling the major axis, the minor axis and the angle of the ellipse, as shown in 5 a-5 b. The effect of modeling the whole picture by adopting the elliptic gaussians is shown in fig. 5c, the pig image with higher density is modeled by adopting the elliptic gaussians, the final statistical result is improved by about 10% in accuracy compared with the standard circular gaussians, and the biological asset of the pig can be accurately checked.
In the embodiment of the present invention, in step S40, the image to be inventoried and the corresponding gaussian density map are input into the deep learning neural network model and subjected to regression training and integration processing to obtain the number of livestock, which specifically includes:
s41, establishing a deep learning neural network model;
s42, inputting the image to be checked and the corresponding Gaussian density map into a deep learning neural network model for regression training;
and S43, after the training of the deep learning neural network model is completed, performing integration processing on the Gaussian density map mapped from the image to be inventoried to obtain the quantity of livestock.
In a second aspect, an embodiment of the present invention further provides an animal checking device, including:
the image processing module is used for acquiring an image to be checked of a place where the livestock is located;
the marking module is used for marking coordinate points at the geometric center point and a plurality of characteristic points of each target in the image to be inventoried respectively;
the model establishing module is used for establishing an elliptic Gaussian model taking the geometric central point as a Gaussian kernel based on the coordinate point and obtaining a Gaussian density map;
and the data calculation module is used for inputting the image to be checked and the corresponding Gaussian density map into the deep learning neural network model and performing regression training and integral processing to obtain the quantity of the livestock.
In a third aspect, an embodiment of the present invention further provides an apparatus for livestock inventory, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor, when executing the computer program, implements the livestock inventory method described above.
In a fourth aspect, the embodiment of the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program runs, the apparatus in which the computer-readable storage medium is located is controlled to execute the above-mentioned livestock inventory method.
Illustratively, the computer program may be partitioned into one or more modules that are stored in the memory and executed by the processor to implement the invention. The one or more modules may be a series of computer program instruction segments capable of performing specific functions for describing the execution of the computer program in the apparatus for livestock inventorying.
The livestock checking equipment can be computing equipment such as a desktop computer, a notebook computer, a palm computer and a cloud server. The livestock inventory device may include, but is not limited to, a processor, memory, and a display. It will be appreciated by those skilled in the art that the above components are merely examples of an animal inventorying device and do not constitute a limitation of an animal inventorying device and may comprise more or less components than those described, or some components may be combined, or different components, e.g. the animal inventorying device may further comprise input output devices, network access devices, buses, etc.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general processor may be a microprocessor or the processor may be any conventional processor or the like, said processor being the control centre of said animal inventorying device, the various parts of the whole of said animal inventorying device being connected by means of various interfaces and lines.
The memory may be used to store the computer programs and/or modules, and the processor may perform the various functions of the livestock inventory device by running or executing the computer programs and/or modules stored in the memory, as well as invoking data stored in the memory. The memory 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 by at least one function (such as a sound playing function, a text conversion function, etc.), and the like; the storage data area may store data (such as audio data, text message data, etc.) created according to the use of the cellular phone, etc. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
Wherein the device integrated module for livestock inventory, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
It should be noted that the above-described device embodiments are merely illustrative, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the embodiment of the apparatus provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, and may be specifically implemented as one or more communication buses or signal lines. One of ordinary skill in the art can understand and implement it without inventive effort.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (10)
1. A method of livestock inventorying, comprising at least the steps of:
acquiring an image to be checked of a place where livestock is located;
respectively marking coordinate points at the geometric center point and a plurality of characteristic points of each target in the image to be checked;
establishing an elliptical Gaussian model with the geometric central point as a Gaussian kernel based on the coordinate point, and obtaining a Gaussian density map;
and inputting the image to be checked and the corresponding Gaussian density map into a deep learning neural network model, and performing regression training and integral processing to obtain the quantity of livestock.
2. The livestock inventory method of claim 1, wherein said step of labeling coordinate points at a geometric center point and a plurality of feature points of each target in said image to be inventory, respectively, comprises:
and when all targets in the image to be checked contain at least one partially-shielded target, selecting the geometric center of the maximum exposed area of the partially-shielded target to label the coordinate point.
3. The animal inventory method of claim 1 or 2, wherein said plurality of feature points are two vertices on the longest longitudinal line segment and two vertices on the longest transverse line segment on said target.
4. The livestock inventory method of claim 3, wherein said step of building an elliptical gaussian model with said geometric center point as a gaussian kernel based on said coordinate points and obtaining a gaussian density map comprises:
taking the geometric central point and four vertexes of each target as parameter points, and establishing an elliptic Gaussian model taking the geometric central point as a Gaussian kernel;
and carrying out normalization processing on all the elliptical Gaussian models to obtain the Gaussian density map.
5. The livestock inventory method of claim 1, wherein said step of inputting said images to be inventoried and said corresponding gaussian density maps into a deep learning neural network model and performing regression training and integration processing to obtain the quantity of livestock comprises:
establishing a deep learning neural network model;
inputting the image to be checked and the corresponding Gaussian density map into the deep learning neural network model for regression training;
and after the deep learning neural network model is trained, performing integral processing on the Gaussian density map mapped from the image to be inventoried to obtain the quantity of livestock.
6. The livestock inventory method of claim 1, wherein said livestock includes live pigs.
7. The animal inventory method of claim 1, wherein said image to be inventoried is a top view image of the locus of the animal.
8. An animal inventory device, comprising:
the image processing module is used for acquiring an image to be checked of a place where the livestock is located;
the marking module is used for marking coordinate points at the geometric center point and a plurality of characteristic points of each target in the image to be inventoried respectively;
the model establishing module is used for establishing an elliptic Gaussian model taking the geometric central point as a Gaussian kernel based on the coordinate point and obtaining a Gaussian density map;
and the data calculation module is used for inputting the image to be checked and the corresponding Gaussian density map into a deep learning neural network model and performing regression training and integral processing to obtain the quantity of the livestock.
9. An apparatus for animal inventorying, comprising a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, the processor when executing the computer program implementing the animal inventorying method of any of claims 1-7.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises a stored computer program, wherein the computer program, when running, controls an apparatus in which the computer-readable storage medium is located to perform the livestock inventory method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010216268.4A CN111340801A (en) | 2020-03-24 | 2020-03-24 | Livestock checking method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010216268.4A CN111340801A (en) | 2020-03-24 | 2020-03-24 | Livestock checking method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111340801A true CN111340801A (en) | 2020-06-26 |
Family
ID=71186178
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010216268.4A Pending CN111340801A (en) | 2020-03-24 | 2020-03-24 | Livestock checking method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111340801A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112036817A (en) * | 2020-08-24 | 2020-12-04 | 新希望六和股份有限公司 | Livestock information processing method and device and computer equipment |
| CN112070621A (en) * | 2020-09-09 | 2020-12-11 | 新希望六和股份有限公司 | Pig feeding management method, pig feeding management system, computer equipment and storage medium |
| CN112070791A (en) * | 2020-09-21 | 2020-12-11 | 深圳喜为智慧科技有限公司 | Method and system for improving accuracy and efficiency of animal husbandry individual points |
| CN112200003A (en) * | 2020-09-14 | 2021-01-08 | 浙江大华技术股份有限公司 | Method and device for determining feed feeding amount of pig farm |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104240243A (en) * | 2014-09-05 | 2014-12-24 | 南京农业大学 | Adhered piglet automatic counting method based on ellipse fitting |
| CN107624189A (en) * | 2015-05-18 | 2018-01-23 | 北京市商汤科技开发有限公司 | Method and apparatus for generating forecast model |
| CN107886086A (en) * | 2017-12-01 | 2018-04-06 | 中国农业大学 | A kind of target animal detection method and device based on image/video |
| CN107944327A (en) * | 2016-10-10 | 2018-04-20 | 杭州海康威视数字技术股份有限公司 | A kind of demographic method and device |
| CN108549835A (en) * | 2018-03-08 | 2018-09-18 | 深圳市深网视界科技有限公司 | Crowd counts and its method, terminal device and the storage medium of model construction |
| CN108876774A (en) * | 2018-06-07 | 2018-11-23 | 浙江大学 | A kind of people counting method based on convolutional neural networks |
| CN109241941A (en) * | 2018-09-28 | 2019-01-18 | 天津大学 | A method of the farm based on deep learning analysis monitors poultry quantity |
| CN110688928A (en) * | 2019-09-20 | 2020-01-14 | 北京海益同展信息科技有限公司 | Model training method and device, electronic equipment and computer readable storage medium |
| CN110718137A (en) * | 2018-07-13 | 2020-01-21 | 广州极飞科技有限公司 | Method and device for constructing density distribution map of target object, terminal and mobile device |
-
2020
- 2020-03-24 CN CN202010216268.4A patent/CN111340801A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104240243A (en) * | 2014-09-05 | 2014-12-24 | 南京农业大学 | Adhered piglet automatic counting method based on ellipse fitting |
| CN107624189A (en) * | 2015-05-18 | 2018-01-23 | 北京市商汤科技开发有限公司 | Method and apparatus for generating forecast model |
| CN107944327A (en) * | 2016-10-10 | 2018-04-20 | 杭州海康威视数字技术股份有限公司 | A kind of demographic method and device |
| CN107886086A (en) * | 2017-12-01 | 2018-04-06 | 中国农业大学 | A kind of target animal detection method and device based on image/video |
| CN108549835A (en) * | 2018-03-08 | 2018-09-18 | 深圳市深网视界科技有限公司 | Crowd counts and its method, terminal device and the storage medium of model construction |
| CN108876774A (en) * | 2018-06-07 | 2018-11-23 | 浙江大学 | A kind of people counting method based on convolutional neural networks |
| CN110718137A (en) * | 2018-07-13 | 2020-01-21 | 广州极飞科技有限公司 | Method and device for constructing density distribution map of target object, terminal and mobile device |
| CN109241941A (en) * | 2018-09-28 | 2019-01-18 | 天津大学 | A method of the farm based on deep learning analysis monitors poultry quantity |
| CN110688928A (en) * | 2019-09-20 | 2020-01-14 | 北京海益同展信息科技有限公司 | Model training method and device, electronic equipment and computer readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| CLAUDIA ARELLANO等: "Robust ellipse detection with Gaussian mixture models" * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112036817A (en) * | 2020-08-24 | 2020-12-04 | 新希望六和股份有限公司 | Livestock information processing method and device and computer equipment |
| CN112036817B (en) * | 2020-08-24 | 2023-12-22 | 新希望六和股份有限公司 | Livestock information processing method, device and computer equipment |
| CN112070621A (en) * | 2020-09-09 | 2020-12-11 | 新希望六和股份有限公司 | Pig feeding management method, pig feeding management system, computer equipment and storage medium |
| CN112070621B (en) * | 2020-09-09 | 2023-10-20 | 新希望六和股份有限公司 | Live pig raising management method, system, computer equipment and storage medium |
| CN112200003A (en) * | 2020-09-14 | 2021-01-08 | 浙江大华技术股份有限公司 | Method and device for determining feed feeding amount of pig farm |
| CN112200003B (en) * | 2020-09-14 | 2024-02-20 | 浙江大华技术股份有限公司 | Method and device for determining feed feeding amount in pig farm |
| CN112070791A (en) * | 2020-09-21 | 2020-12-11 | 深圳喜为智慧科技有限公司 | Method and system for improving accuracy and efficiency of animal husbandry individual points |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111340801A (en) | Livestock checking method, device, equipment and storage medium | |
| WO2020207190A1 (en) | Three-dimensional information determination method, three-dimensional information determination device, and terminal apparatus | |
| CN109934065B (en) | Method and device for gesture recognition | |
| WO2020244075A1 (en) | Sign language recognition method and apparatus, and computer device and storage medium | |
| CN110163831B (en) | Method and device for dynamically displaying object of three-dimensional virtual sand table and terminal equipment | |
| CN108090486B (en) | Image processing method and device in billiard game | |
| CN110688928A (en) | Model training method and device, electronic equipment and computer readable storage medium | |
| CN111160242A (en) | Image target detection method, system, electronic terminal and storage medium | |
| CN110599520B (en) | Open field experiment data analysis method, system and terminal equipment | |
| CN112001331A (en) | Image recognition method, device, equipment and storage medium | |
| WO2022247126A1 (en) | Visual localization method and apparatus, and device, medium and program | |
| CN111368860B (en) | Repositioning method and terminal equipment | |
| CN111753858A (en) | Point cloud matching method and device and repositioning system | |
| CN113516697A (en) | Image registration method and device, electronic equipment and computer-readable storage medium | |
| CN114627438A (en) | Target detection model generation method, target detection method, device and medium | |
| CN116245915A (en) | Target tracking method based on video | |
| US11599743B2 (en) | Method and apparatus for obtaining product training images, and non-transitory computer-readable storage medium | |
| CN113724176A (en) | Multi-camera motion capture seamless connection method, device, terminal and medium | |
| CN109286798B (en) | Frame position identification method and system of projection screen and terminal equipment | |
| CN116468804B (en) | Laser radar and camera external parameter calibration precision evaluation method and device | |
| CN111160133A (en) | Method and device for evaluating similarity of copybook characters | |
| CN115546192B (en) | Livestock quantity identification method, device, equipment and storage medium | |
| US20210218883A1 (en) | Learning apparatus, image generation apparatus, learning method, image generation method, and program | |
| CN110991235A (en) | State monitoring method and device, electronic equipment and storage medium | |
| CN112464753B (en) | Method and device for detecting key points in image and terminal equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200626 |