AU2019101786A4 - Intelligent pig group rearing weighing method and apparatus, electronic device and storage medium - Google Patents
Intelligent pig group rearing weighing method and apparatus, electronic device and storage medium Download PDFInfo
- Publication number
- AU2019101786A4 AU2019101786A4 AU2019101786A AU2019101786A AU2019101786A4 AU 2019101786 A4 AU2019101786 A4 AU 2019101786A4 AU 2019101786 A AU2019101786 A AU 2019101786A AU 2019101786 A AU2019101786 A AU 2019101786A AU 2019101786 A4 AU2019101786 A4 AU 2019101786A4
- Authority
- AU
- Australia
- Prior art keywords
- group
- pig
- barns
- pigs
- image information
- 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
- 230000000384 rearing effect Effects 0.000 title claims abstract description 60
- 238000005303 weighing Methods 0.000 title claims abstract description 57
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000003860 storage Methods 0.000 title claims abstract description 8
- 241000282887 Suidae Species 0.000 claims abstract description 105
- 238000005259 measurement Methods 0.000 claims abstract description 52
- 238000012549 training Methods 0.000 claims abstract description 41
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 22
- 238000004590 computer program Methods 0.000 claims description 14
- 239000003651 drinking water Substances 0.000 claims description 12
- 235000020188 drinking water Nutrition 0.000 claims description 12
- 238000010801 machine learning Methods 0.000 claims description 8
- 230000035622 drinking Effects 0.000 claims description 7
- 230000036544 posture Effects 0.000 claims description 6
- 238000013481 data capture Methods 0.000 abstract description 8
- 230000003938 response to stress Effects 0.000 abstract description 5
- 230000035611 feeding Effects 0.000 description 21
- 238000013480 data collection Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 210000002700 urine Anatomy 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01G—WEIGHING
- G01G17/00—Apparatus for or methods of weighing material of special form or property
- G01G17/08—Apparatus for or methods of weighing material of special form or property for weighing livestock
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K29/00—Other apparatus for animal husbandry
- A01K29/005—Monitoring or measuring activity, e.g. detecting heat or mating
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Environmental Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Animal Husbandry (AREA)
- Biodiversity & Conservation Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Image Analysis (AREA)
Abstract
Disclosed in the present application are an intelligent group rearing weighing method
and apparatus for pigs, electronic device and storage medium. The weighing method
includes: Si, obtaining image information of group barns in a pig farm on which
intelligent group rearing weighing is to be performed (101); S2, obtaining image
information of each pig in the group barns based on the image information of the
group barns (102); and S3, obtaining weight information of each pig in the group
barns based on the image information of each pig in the group barns by a preset
weight measurement model; wherein the preset weight measurement model is
obtained by training based on image sample input data and weight sample result data
of the pigs in the group barns (103). According to the intelligent group rearing
weighing method for pigs in the present application, the problem of stress response
caused by pigs being driven to be weighed on a common ground scale in the
traditional pig rearing process may be effectively solved.
1/4
DRAWINGS
Obtaining image information of group barns in a pig farm on which
intelligent group rearing weighing is to be performed
-02
Obtaining image information of each pig in the group barns based
on the image information of the group barns
Obtaining weight information of each pig in the group barns based on the image information 03
of each pig in the group barns by a preset weight measurement model; wherein the preset
weight measurement model is obtained by training based on image sample input data and
weight sample result data of the pigs in the group barns
Fig. 1
Water tan ,
Data capture
device
Electronic
ground scale Feed tank
Longitudinally
telescopic data
capture
device array
Fig. 2
Description
1/4
Obtaining image information of group barns in a pig farm on which intelligent group rearing weighing is to be performed
-02 Obtaining image information of each pig in the group barns based on the image information of the group barns
Obtaining weight information of each pig in the group barns based on the image information 03 of each pig in the group barns by a preset weight measurement model; wherein the preset weight measurement model is obtained by training based on image sample input data and weight sample result data of the pigs in the group barns
Fig. 1
Water tan ,
Data capture device
Electronic ground scale Feed tank
Longitudinally telescopic data capture device array
Fig. 2
[0001] The present application claims priority to Chinese Application No. 2018115255707 filed on December 13, 2018, entitled "Intelligent Group Rearing Weighing Method and Apparatus for Pigs, Electronic Device and Storage Medium", the disclosure of which is hereby incorporated by reference in its entirety.
[0002] The present application relates to the field of computer technology, in particular to an intelligent group rearing weighing method and apparatus for pigs, an electronic device and a storage medium.
[0003] At present, during the pig breeding process on pig farms, it is necessary to obtain information on the weight of the pigs at different stages of growth in order to keep abreast of the growth of the pigs.
[0004] With respect to the weighing of pigs in group barns, a ground scale is generally placed on each pig's group barn for weighing so as to minimize the stress response caused by pigs being driven away when common ground scales are used. However, the disadvantages of this approach include not only higher cost, but also unstable measurement data with sometimes an error of 10 to 20 kg due to the wobble of ground scales in that the pigs may move back and forth on the ground scales. In addition, due to the poor environment of the pig farms, the ground scales are often damaged due to the erosion by excrement and urine after a period of use on the pig farms, which further increases replacement costs.
[0005] In order to overcome the defects in the prior art, the present application provides an intelligent group rearing weighing method and apparatus for pigs, an electronic device and a storage medium.
[0006] The present application provides the following technical solutions.
[0007] In a first aspect, the present application provides an intelligent group rearing weighing method for pigs, including:
[0008] Si, obtaining image information of group barns in a pig farm on which intelligent group rearing weighing is to be performed;
[0009] S2, obtaining image information of each pig in the group barns based on the image information of the group barns; and
[0010] S3, obtaining weight information of each pig in the group barns based on the image information of each pig in the group barns by a preset weight measurement model;
[0011] wherein the preset weight measurement model is obtained by training based on image sample input data and weight sample result data of the pigs in the group barns.
[0012] In an embodiment, before the Si, the method further includes:
[0013] SO, establishing the preset weight measurement model.
[0014] In an embodiment, the SO includes:
[0015] SO1, preparing training sample data which includes image data and weight data of pigs in a designated group barn in the pig farm on which the intelligent group rearing weighing is to be performed; and
[0016] S02, training an initial weight measurement model based on a machine learning method according to the prepared training sample data to obtain the preset weight measurement model.
[0017] In an embodiment, the SO1 includes:
[0018] periodically collecting the weight information and the image information of each pig in the designated group barn in the pig farm on which the intelligent group rearing weighing is to be performed, combining the weight information and the image information collected each time into data pairs and storing the data pairs; and
[0019] accordingly, the S02 includes:
[0020] taking the image information in the collected data pair including weight information and image information of each pig as input and taking the weight information in the corresponding data pair as output, training the initial weight measurement model based on a machine learning method to obtain the preset weight measurement model.
[0021] In an embodiment, the periodically collecting the weight information and the image information of each pig in the designated group barn in the pig farm on which the intelligent group rearing weighing is to be performed, combining the weight information and the image information collected each time into data pairs and storing the data pairs includes:
[0022] collecting multi-pose data of single pig in the group barn; and collecting comprehensive position data of pigs in the group barn;
[0023] wherein the collecting multi-pose data of single pig in the group barn includes:
[0024] collecting image information and corresponding weight information of a single pig with various poses in the group barn during drinking water and feeding; wherein a preset number of square ground scales are placed in the group barn, an image capture device is disposed above each ground scale, and each ground scale is surrounded by a fence; one pig is placed on each ground scale, a feed tank is mounted on one side of each ground scale, and a water tank is mounted on the other side thereof; the pig walks back and forth on the ground scale during drinking water and feeding;
[0025] wherein the collecting comprehensive position data of pigs in the group barn includes:
[0026] collecting image information and corresponding weight information of pigs in the group barn at the comprehensive positions; wherein image capture devices and ear tag recognition devices are disposed at preset positions around the group barn; the group barn is divided into two areas by a middle fence, the feed tank is placed in one area, i.e., a feeding area, the water feed tank is placed in the other area, i.e., a water-drinking area, two electronic ground scales are placed at the middle fence, and both electronic ground scales are provided with one-way doors; pigs may only enter the feeding area from the water-drinking area on one ground scale, and may only enter the water-drinking area from the feeding area on the other ground scale; the pigs walk back and forth on the two ground scales during drinking water and feeding, and each pig in the group barn wears an ear tag to indicate identity information.
[0027] In an embodiment, the Si includes:
[0028] obtaining the image information of the group barns in the pig farm on which intelligent group rearing weighing is to be performed using fixed image capture devices mounted above the feed tanks or the water tanks or using slide-way image capture devices; wherein the fixed image capture devices are used when the image information of pigs in a single group barn needs to be captured, and the slide-way image capture devices are used when the image information of pigs in a plurality of group barns needs to be captured. Wherein, slide ways are mounted above the plurality of group barns in the pig farm, and the image capture device slides on the slide ways, and collects the image information of the pigs in the corresponding group barn when sliding to the position above the feed tank or water feed tank of the corresponding group barn; a charging module is mounted at one end or each end of the slide way for charging the image capture device, the image capture device returns into the charging module to be charged after finishing sliding on the slide way.
[0029] In an embodiment, the method further includes:
[0030] S4, obtaining average weight information of a barn according to the weight information of each pig and the number of pigs in the group barn; wherein duplicated weight information is deleted based on the pigs' identity information when the average weight information of the barn is obtained.
[0031] In a second aspect, the present application further provides an intelligent group rearing weighing apparatus for pigs, including:
[0032] a first catcher configured to obtain image information of group barns in a pig farm on which intelligent group rearing weighing is to be performed;
[0033] a second catcher configured to obtain image information of each pig in the group barns based on the image information of the group barns; and
[0034] a weigher configured to obtain weight information of each pig in the group barns based on the image information of each pig in the group barns by a preset weight measurement model;
[0035] wherein the preset weight measurement model is obtained by training based on image sample input data and weight sample result data of the pigs in the group barns.
[0036] In a third aspect, the present application further provides an electronic device, including a memory, a processor, and computer programs stored in the memory and executable by the processor, wherein the processor is configured to implement steps of the intelligent group rearing weighing method for pigs described in the first aspect when executing the computer programs.
[0037] In a fourth aspect, the present application further provides a computer-readable storage medium, in which computer programs are stored, wherein steps of the intelligent group rearing weighing method for pigs described in the first aspect are implemented when the computer programs are executed by a processor.
[0038] From the technical solutions above, according to the intelligent group rearing weighing method for pigs provided by the present application, firstly, image information of group barns in a pig farm on which intelligent group rearing weighing is to be performed is obtained, then image information of each pig in the group barns is obtained based on the image information of the group barns, and finally weight information of each pig in the group barns is obtained based on the image information of each pig in the group barns by a preset weight measurement model; wherein the preset weight measurement model is obtained by training based on image sample input data and weight sample result data of the pigs in the group barns. It can be seen that the intelligent group rearing weighing method for pigs provided by the present application overcomes the various drawbacks of the traditional methods of using ground scales for weight measurement, especially the stress response caused by driving pigs. The present application solves the sore point in the traditional pig rearing process and enables stress-free weight measurement.
[0039] In order to more clearly illustrate the technical solutions disclosed in the embodiments of the present application or the related art, drawings needed in the descriptions of the embodiments or the related art will be briefly introduced below.
Obviously, the drawings in the following description are only some of the embodiments of the present application, and other drawings can be obtained according to these drawings without any creative effort for those skilled in the art.
[0040] FIG. 1 is a flowchart of an intelligent group rearing weighing method for pigs according to an embodiment of the present application;
[0041] FIG. 2 is a schematic diagram of a method for collecting multi-pose data of a single pig in a model training stage according to an embodiment of the present application;
[0042] FIG. 3 is a schematic diagram of a method for collecting comprehensive position data of pigs in a model training stage according to an embodiment of the present application;
[0043] FIG. 4 is a schematic diagram of a fixed image capture device located above a feed tank in a model application stage according to an embodiment of the present application;
[0044] FIG. 5 is a schematic diagram of a fixed image capture device located above a water tank in a model application stage according to an embodiment of the present application;
[0045] FIG. 6 is a schematic diagram of a slide-way image capture device located above group barns in a model application stage according to an embodiment of the present application;
[0046] FIG. 7 is a schematic structural diagram of an intelligent group rearing weighing apparatus for pigs according to another embodiment of the present application; and
[0047] FIG. 8 is a schematic structural diagram of an electronic device according to still another embodiment of the present application.
[0048] In order to give clear illustration of the objectives, technical solutions and advantages of the embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without any creative effort fall within the protection scope of the present application.
[0049] As shown in FIG. 1, an embodiment of the present application provides an intelligent group rearing weighing method for pigs, including:
[0050] Step 101, obtaining image information of group barns in a pig farm on which intelligent group rearing weighing is to be performed.
[0051] In this step, since the method of predicting the weight of pigs in the group barns based on the image of the pigs in the group barns is adopted, it is necessary to obtain the image information of the group barns first, and here the image information of the group barns contains the image information of pigs in the group barns.
[0052] Step 102, obtaining image information of each pig in the group barns based on the image information of the group barns.
[0053] In this step, the image information of the group barns is processed, using, such as image segmentation algorithm and the like to obtain the image information of each pig in the group barns.
[0054] Step 103, obtaining weight information of each pig in the group barns based on the image information of each pig in the group barns by a preset weight measurement model;
[0055] wherein the preset weight measurement model is obtained by training based on image sample input data and weight sample result data of the pigs in the group barns.
[0056] In this step, the image information of each pig in the group barns is input to a pre-trained weight measurement model to obtain the weight information of each pig in the group barns.
[0057] From the technical solutions above, according to the intelligent group rearing weighing method for pigs provided by this embodiment, firstly, image information of group barns in a pig farm on which intelligent group rearing weighing is to be performed is obtained, then image information of each pig in the group barns is obtained based on the image information of the group barns, and finally weight information of each pig in the group barns is obtained based on the image information of each pig in the group barns by a preset weight measurement model; wherein the preset weight measurement model is obtained by training based on image sample input data and weight sample result data of the pigs in the group barns. It can be seen that by the intelligent group rearing weighing method for pigs in this embodiment, the weight information of the pigs may be obtained based on the image information of the pigs, thereby overcoming the various drawbacks (such as time-consuming, labor-intensive, low efficiency, inaccurate, prone to stress response) of the traditional weighing methods using ground scales, especially the stress response caused by driving pigs. This embodiment solves the sore point in the traditional pig rearing process and enables stress-free weight measurement, having significant market and practical value.
[0058] On the basis of the foregoing embodiment, in an alternative embodiment, before the step 101, the method further includes:
[0059] step 100: establishing the preset weight measurement model.
[0060] In this embodiment, the intelligent group rearing weighing method for pigs further includes a process of establishing a weight measurement model.
[0061] On the basis of the foregoing embodiments, in an alternative embodiment, the step 100 includes:
[0062] step 100a: preparing training sample data which includes image data and weight data of pigs in a designated group barn in the pig farm on which the intelligent group rearing weighing is to be performed; and
[0063] step 100b: training an initial weight measurement model based on a machine learning method according to the prepared training sample data to obtain the preset weight measurement model.
[0064] In this embodiment, when establishing the weight measurement model, the training sample data is prepared first; the training sample data includes image data and weight data of pigs in the designated group barns on the same pig farm, both of which need to be in pairs, namely an image should correspond to the weight information of the pig at the time the image is captured. Then, based on the prepared training sample data, a machine learning method is used to train the initial weight measurement model until the accuracy meets the preset requirements to obtain the preset weight measurement model.
[0065] It should be noted that when the initial model is trained based on the machine learning method, CNN or RNN can be used for model learning and training.
[0066] On the basis of the foregoing embodiments, in an alternative embodiment, the step 100a may be implemented in the following manner:
[0067] periodically collecting the weight information and the image information of each pig in the designated group barn in the pig farm on which the intelligent group rearing weighing is to be performed, and combining the weight information and the image information collected each time into data pairs and storing the data pairs; and
[0068] accordingly, the step 100b may be implemented in the following manner:
[0069] taking the image information in the collected data pair including weight information and image information of each pig as input and taking the weight information in the corresponding data pair as output, training the initial weight measurement model based on the machine learning method to obtain the preset weight measurement model.
[0070] On the basis of the foregoing embodiments, in an alternative embodiment, the periodically collecting the weight information and the image information of each pig in the designated group barn in the pig farm on which the intelligent group rearing weighing is to be performed, and combining the weight information and the image information collected each time into data pairs and storing the data pairs includes:
[0071] collecting multi-pose data of single pig in the group barn; and collecting comprehensive position data of pigs in the group barn;
[0072] wherein the collecting multi-pose data of single pig in the group barn includes:
[0073] collecting image information and corresponding weight information of a single pig with various poses in the group barn during drinking water and feeding; wherein a preset number of square ground scales are placed in the group barn, an image capture device is disposed above each ground scale, and each ground scale is surrounded by a fence; one pig is placed on each ground scale, a feed tank is mounted on one side of each ground scale, and a water tank is mounted on the other side thereof; the pig walks back and forth on the ground scale during drinking water and feeding;
[0074] wherein the collecting comprehensive position data of pigs in the group barn includes:
[0075] collecting image information and corresponding weight information of pigs in the group barn at the comprehensive positions; wherein image capture devices and ear tag recognition devices are disposed at preset positions around the group barn; the group barn is divided into two areas by a middle fence, the feed tank is placed in one area, i.e., a feeding area, the water feed tank is placed in the other area, i.e., a water-drinking area, two electronic ground scales are placed at the middle fence, and both electronic ground scales are provided with one-way doors; pigs may only enter the feeding area from the drinking area on one ground scale, and may only enter the drinking area from the feeding area on the other ground scale; the pigs walk back and forth on the two ground scales during drinking water and feeding, and each pig in the group barn wears an ear tag to indicate identity information.
[0076] In this embodiment, the step 100 actually belongs to the model training stage, in which the main purpose is to collect data for model training. In this embodiment, data collection includes two aspects, one is single pig multi-pose data collection, and the other is comprehensive position data collection. It should be noted that, for the single pig multi-pose data collection mentioned on the one hand, the purpose is to acquire as many images as possible of a single pig in a free state in a group rearing environment; and for the comprehensive position data collection mentioned on the other hand, the purpose is to acquire images of pigs in actual group rearing application scenarios. The two types of data collection can be combined to acquire more abundant data, which is closer to the actual scene, which can help establish a more accurate model.
[0077] To be specific, the single pig multi-pose data collection is to mainly acquire the video and image data of each posture of the pigs when the pigs are moving as freely as possible, including the posture image data of walking, drinking water and feeding under the condition of moving as freely as possible. In a specific implementation, an area is isolated in the group bam, and a certain number of square ground scales as shown in FIG. 2 are placed in the area. Each ground scale is surrounded by a fence, a feed tank is mounted on one side of the ground scale, and a water tank is mounted on the other side. Pigs walk back and forth when drinking water and feeding, so that it is convenient to collect richer image data. One pig is placed in each ground scale, and video and image information of the pig is collected for 24 hours. Equipped with a data acquisition software system, the overall collection process is fully automated without human intervention. The data capture device located above the center of the ground scale provides part of the modeling data for the solutions of fixed image capture device scheme and the sliding-way image capture device scheme. It should be noted that the longitudinally telescopic data capture device array located above the feed tank side of the ground scale in FIG. 2 can acquire images above the feed tank side in a telescopic manner.
[0078] In an embodiment, the comprehensive position data collection is to mainly acquire various posture video and image data in the actual group rearing scenario. What is needed is an appropriate number of group barns and some modifications to the group barns as follows: dividing the group barn into two areas by a middle fence, placing the food feed tank in one area and the water tank in the other area, and placing two electronic ground scales (upper and lower electronic ground scales as shown in FIG. 3) at the middle fence. Ear tags are placed on the pigs to be collected and markings are made on the back of the pigs. Equipped with a data acquisition software system, the overall acquisition process is fully automated without human intervention. The collection scenario is shown in FIG.3 after the modification, where two of the electronic ground scales are equipped with one-way doors, which means pigs may only enter the feeding area from the drinking area on one of the ground scales, and may only enter the drinking area from the feeding area on the other ground scale. Image data capture devices are mounted at suitable positions above the area marked with numbers, tracing devices are mounted at suitable positions above the area marked with capital letter to assist in data collection, and individual identification data capture devices are mounted at suitable positions near the area marked with lowercase letters. Ear tag reading devices are mounted at suitable positions of the feed tank and the electronic ground scale to assist in data collection, and isolation facilities are mounted around the ear tag reading devices at the feed tank to ensure that the reading devices do not interfere with each other.
[0079] It should be noted that through the above two data collection methods, it can be ensured that the image information and the corresponding weight information of the pigs in various postures such as walking, drinking water, and feeding can be fully collected, thereby providing sufficient sample data for model training, and after training the model with these sample data, the model can be adapted to pig pose images in various scenarios.
[0080] On the basis of the foregoing embodiments, in an alternative embodiment, the step 101 may be implemented in the following manner:
[0081] obtaining the image information of the group barns in the pig farm on which intelligent group rearing weighing is to be performed using fixed image capture devices (such as cameras in FIGS. 4 and 5) mounted above the feed tank or the water tank, or using slide-way image capture devices (such as cameras in FIG. 6);
[0082] wherein the fixed image capture devices are used when the image information of pigs in a single group barn is to be captured, and the sliding image capture devices are used when the image information of pigs in a plurality of group barns is to be captured; wherein slide ways are mounted above the plurality of group barns in the pig farm, and the image capture device slides on the slide ways, and collects the image information of the pigs in the corresponding group barn when sliding to the position above the feed tank or water feed tank of the corresponding group barn; a charging module is mounted at one end or each end of the slide way for charging the image capture device; the image capture device returns into the charging compartment to be charged after finishing sliding on the slide way.
[0083] In this embodiment, after the completion of the model training stage of the step 100, the model application stage is entered, namely the step 101 actually belongs to the model application stage in which it will no longer be necessary to install ground scales for group barns, but only need to obtain image information of pigs in each group barn. Then, the weight information of pigs in the corresponding group barn may be obtained using the obtained image information and the trained model.
[0084] In this embodiment, in the model application stage, it is necessary to obtain the image information of the pigs in the group barn on the pig farm, thus fixed image capture devices (shown as cameras in FIGS. 4 and 5) may be mounted above each or each group of water tanks or feed tanks to collect image information during the water drinking or feeding process of pigs. It should be noted that when it is necessary to collect image information of pigs in multiple group barns, the cameras may be mounted on the slide ways as shown in FIG. 6, and the cameras move on the slide ways to collect images of pigs in different group barns. One or both ends of the slide way are equipped with charging modules (FIG. 6 shows an example with charging modules mounted at both ends) for charging the image capture device. The image capture device returns into the charging module mounted at one end or each end of the slide way to be charged after finishing sliding on the slide way, so as to perform the next slide and image acquisition.
[0085] It should be noted that it is mainly based on the user scenario to decide whether to collect data at the water tank or the feed tank. Generally speaking, the postures of pigs when they eat are better than those when they drink. Therefore, measurements may be taken at the feed tank position when rectangular feed tanks are used, but some farms use round feed tanks, in which case data collection is required to be carried out at the water tank position. In addition, for pig image acquisition scenarios in large group barns or pig image acquisition scenarios in multiple group barns, it is recommended to use sliding-way image capture devices.
[0086] It should be noted that the stage of training the model can be understood as the stage of customization, during which it is necessary to collect weight information and image information to form data pairs for training the model. When the model training stage is finished, that is, after the customization stage is over, the model application stage, namely the product promotion stage is entered. In this stage, an extension intelligent group rearing weighting system is provided for specific customers. The important weight measurement algorithm model in the system comes from the data obtained by the customized system and the model obtained after training and optimization. In the model application stage, it is no longer necessary to install the ground scales for the group barn, but only to install the fixed capture devices (i.e., the "camera" in FIGS. 4 and 5) above the water tank or feed tank in the group barn, or to install the slide ways above the group barn, and then install the sliding-way image capture devices (i.e., the "camera" in FIG. 6) onto the slide ways, install the wireless charging modules on one or both sides of the slide ways, and connect the hardware equipment to a remote cloud platform. During working, the sliding-way image capture devices conduct daily inspections in accordance with the customer's working strategy preset on the cloud platform, that is, sliding along the slide ways to collect image data, and transmitting the data that meets the requirements to the cloud. After finishing sliding along the slide ways, the slid-way image capture devices return into the charging modules to be charged, and all qualified data collected along the way has been transmitted to the cloud which performs pig image segmentation on the images, and then inputs the segmented pig images into the model to obtain weight information of each pig, which is then returned to the clients such as laptops, desktops and cell phones. Therefore, the customer can obtain the weight information of each pig in real time, as well as the average weight information of a barn, then data analysis can be performed for the customer based on this information to evaluate the growth and feeding level of the pigs and to make recommendations for subsequent feeding.
[0087] It should be noted that the tracing camera in FIG. 4 is used to trace each pig in the barn in real time and its role is to record the trajectory of each pig as well as to assist in individual identification for identify verification. For the tracing camera, an artificial intelligence algorithm is used to obtain a tracing model through data training to provide real-time tracing of all pigs within a specific range. In addition, the individual identification devices in FIG. 4 are used to identify individual pigs to prevent deviations in the overall average weight of a barn due to repeated weight calculation by the system caused by multiple feedings of the pigs.
[0088] On the basis of the foregoing embodiments, in an alternative embodiment, the method further includes:
[0089] step 104: obtaining average weight information of a barn according to the weight information of each pig and the number of pigs in the group barn; wherein duplicated weight information is deleted based on the pigs' identity information when the average weight information of the barn is obtained.
[0090] It should be noted that since each pig in the group barn has an ear tag indicating identity information, the duplicated pig weight information is deleted according to the pig's identity information when the average weight information of the barn is obtained, so that the average weight information is more accurate.
[0091] As shown in FIG. 7, based on the same inventive concept, another embodiment of the present application provides an intelligent group rearing weighing apparatus for pigs, including: a first catcher 21, a second catcher 22, and a weigher 23, wherein:
[0092] the first catcher 21 is configured to obtain image information of group barns in a pig farm on which intelligent group rearing weighing is to be performed;
[0093] the second catcher 22 is configured to obtain image information of each pig in the group barns based on the image information of the group barns; and
[0094] the weigher 23 is configured to obtain weight information of each pig in the group barns based on the image information of each pig in the group barns by a preset weight measurement model;
[0095] wherein the preset weight measurement model is obtained by training based on image sample input data and weight sample result data of the pigs in the group barns.
[0096] It should be noted that the intelligent group rearing weighing apparatus for pigs provided in this embodiment may be used to implement the intelligent group rearing weighing methods for pigs described in the above embodiments, and the working principles and technical effects of the intelligent group rearing weighing apparatus are similar as those of the intelligent group rearing weighing methods. For details, please refer to the foregoing embodiments, which will not be repeated here.
[0097] As shown in FIG. 8, based on the same inventive concept, still another embodiment of the present application provides an electronic device, including a processor 801, a memory 802, a communication interface 803 and a bus 804;
[0098] wherein the processor 801, the memory 802, and the communication interface 803 communicate with each other through the bus 804; the communication interface 803 is configured to realize information transmission between various modeling software and intelligent manufacturing equipment module libraries and other related devices;
[0099] the processor 801 is configured to call computer programs in the memory
802, and all the steps in the first embodiment are implemented when the processor executes the computer programs. For example, when the processor executes the computer programs, the following steps are implemented:
[00100] step 101: obtaining image information of group barns in a pig farm on which intelligent group rearing weighing is to be performed;
[00101] step 102: obtaining image information of each pig in the group barns based on the image information of the group barns; and
[00102] step 103: obtaining weight information of each pig in the group barns based on the image information of each pig in the group barns by a preset weight measurement model;
[00103] wherein the preset weight measurement model is obtained by training based on image sample input data and weight sample result data of the pigs in the group barns.
[00104] Based on the same inventive concept, still another embodiment of the present application provides a computer-readable storage medium, in which computer programs are stored, and all the steps of the first embodiment are implemented when the computer programs are executed by a processor. For example, when the processor executes the computer programs, the following steps are implemented:
[00105] step 101: obtaining image information of group barns in a pig farm on which intelligent group rearing weighing is to be performed;
[00106] step 102: obtaining image information of each pig in the group barns based on the image information of the group barns; and
[00107] step 103: obtaining weight information of each pig in the group barns based on the image information of each pig in the group barns by a preset weight measurement model;
[00108] wherein the preset weight measurement model is obtained by training based on image sample input data and weight sample result data of the pigs in the group barns.
[00109] It should be noted that in the present application, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relation or order between these entities or operations. Furthermore, the terms "including", "comprising" or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or apparatus including a set of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article or apparatus. Unless otherwise further defined, an element defined by the phrase "including a..." does not exclude the existence of other identical elements in the process, method, article or apparatus that includes the element.
[00110] The above embodiments are only used to explain the technical solutions of the present application, and are not limited thereto; although the present application is described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that they can still modify the technical solutions described in the foregoing embodiments and make equivalent substitutions to a part of the technical features, and these modifications and substitutions do not cause the essence of the corresponding technical solutions to depart from the spirit and scope of the technical solutions of various embodiments of the present application.
Claims (10)
1. An intelligent group rearing weighing method for pigs, comprising: S1, obtaining image information of group barns in a pig farm on which intelligent group rearing weighing is to be performed; S2, obtaining image information of each pig in the group barns based on the image information of the group barns; and S3, obtaining weight information of each pig in the group barns based on the image information of each pig in the group barns by a preset weight measurement model; wherein the preset weight measurement model is obtained by training based on image sample input data and weight sample result data of the pigs in the group barns.
2. The method of claim 1, wherein before the Sl, the method further comprises: SO, establishing the preset weight measurement model.
3. The method of claim 2, wherein the SO comprises: S01, preparing training sample data which includes image data and weight data of pigs in a designated group barn in the pig farm on which the intelligent group rearing weighing is to be performed; and S02, training an initial weight measurement model based on a machine learning method according to the prepared training sample data to obtain the preset weight measurement model.
4. The method of claim 3, wherein the SO Icomprises: periodically collecting the weight information and the image information of each pig in the designated group barn in the pig farm on which the intelligent group rearing weighing is to be performed, and combining the weight information and the image information collected each time into data pairs and storing the data pairs; and accordingly, the S02 comprises: taking the image information in the collected data pair including weight information and image information of each pig as input and taking the weight information in the corresponding data pair as output, training the initial weight measurement model based on the machine learning method to obtain the preset weight measurement model.
5. The method of claim 4, wherein the periodically collecting the weight information and the image information of each pig in the designated group barn in the pig farm on which the intelligent group rearing weighing is to be performed, and combining the weight information and the image information collected each time into data pairs and storing the data pairs comprises: collecting multi-pose data of single pig in the group barn; and collecting comprehensive position data of pigs in the group barn; wherein the collecting multi-pose data of single pig in the group barn comprises: collecting image information and corresponding weight information of a single pig with various postures in the group barn during drinking water and feeding; wherein a preset number of square ground scales are placed in the group barn, an image capture device is disposed above each ground scale, and each ground scale is surrounded by a fence; one pig is placed on each ground scale, a feed tank is mounted on one side of each ground scale, and a water tank is mounted on the other side thereof; the pig walks back and forth on the ground scale during drinking water and feeding; wherein the collecting comprehensive position data of pigs in the group barn comprises: collecting image information and corresponding weight information of pigs in the group barn at the comprehensive positions; wherein image capture devices and ear tag recognition devices are disposed at preset positions around the group barn; the group barn is divided into two areas by a middle fence, the feed tank is placed in one area, i.e., a feeding area, the water feed tank is placed in the other area, i.e., a water-drinking area, two electronic ground scales are placed at the middle fence, and both electronic ground scales are provided with one-way doors; pigs may only enter the feeding area from the drinking area on one of the ground scales, and may only enter the drinking area from the feeding area on the other ground scale; the pigs walk back and forth on the two ground scales during drinking water and feeding, and each pig in the group barn wears an ear tag to indicate identity information.
6. The method of claim 5, wherein the S comprises: obtaining the image information of the group barn in the pig farm on which intelligent group rearing weighing is to be performed using fixed image capture devices mounted above the feed tank or the water tank or using slide-way image capture devices; wherein the fixed image capture devices are used when the image information of pigs in a single group barn needs to be captured, and the slide-way image capture devices are used when the image information of pigs in a plurality of group barns needs to be captured; slide ways are mounted above the plurality of group barns in the pig farm, and the image capture devices slide on the slide ways, and collect the image information of the pigs in the corresponding group barn when sliding to the position above the feed tank or water feed tank of the corresponding group barn; a charging module is mounted at one end or each end of the slide way for charging the image capture device, the image capture device returns into the charging module mounted at one end or each end of the slide way to be charged after finishing sliding on the slide way.
7. The method of claim 5, further comprising: S4, obtaining average weight information of a barn according to the weight information of each pig and the number of pigs in the group barn; wherein duplicated weight information is deleted based on the pigs' identity information when the average weight information of the barn is obtained.
8. An intelligent group rearing weighing apparatus for pigs, comprising: a first catcher configured to obtain image information of group barns in a pig farm on which intelligent group rearing weighing is to be performed; a second catcher configured to obtain image information of each pig in the group barns based on the image information of the group barns; and a weigher configured to obtain weight information of each pig in the group barns based on the image information of each pig in the group barns by a preset weight measurement model; wherein the preset weight measurement model is obtained by training based on image sample input data and weight sample result data of the pigs in the group barns.
9. An electronic device, comprising a memory, a processor, and computer programs stored in the memory and executable by the processor, wherein the processor is configured to implement steps of the intelligent group rearing weighing method for pigs of any one of claims 1 to 7 when executing the computer programs.
10. A computer-readable storage medium, in which computer programs are stored, wherein steps of the intelligent group rearing weighing method for pigs of any one of claims 1 to 7 are implemented when the computer programs are executed by a processor.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811525570.7 | 2018-12-13 | ||
| CN201811525570.7A CN109632058B (en) | 2018-12-13 | 2018-12-13 | Intelligent pig raising group weight measuring method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| AU2019101786A4 true AU2019101786A4 (en) | 2021-04-01 |
Family
ID=66073671
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| AU2019101786A Active AU2019101786A4 (en) | 2018-12-13 | 2019-12-10 | Intelligent pig group rearing weighing method and apparatus, electronic device and storage medium |
| AU2019399813A Pending AU2019399813A1 (en) | 2018-12-13 | 2019-12-10 | Intelligent pig group rearing weighing method and apparatus, electronic device and storage medium |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| AU2019399813A Pending AU2019399813A1 (en) | 2018-12-13 | 2019-12-10 | Intelligent pig group rearing weighing method and apparatus, electronic device and storage medium |
Country Status (3)
| Country | Link |
|---|---|
| CN (1) | CN109632058B (en) |
| AU (2) | AU2019101786A4 (en) |
| WO (1) | WO2020119659A1 (en) |
Families Citing this family (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109632058B (en) * | 2018-12-13 | 2020-06-02 | 北京小龙潜行科技有限公司 | Intelligent pig raising group weight measuring method and device, electronic equipment and storage medium |
| CN110426112B (en) * | 2019-07-04 | 2022-05-13 | 平安科技（深圳）有限公司 | Live pig weight measuring method and device |
| CN110580916B (en) * | 2019-08-13 | 2022-01-14 | 北京农业信息技术研究中心 | Weight acoustic measurement model creation method and weight measurement method and device |
| CN110612921A (en) * | 2019-09-25 | 2019-12-27 | 农芯科技(广州)有限责任公司 | Monitoring system and method for positioning gilts |
| CN110558248B (en) * | 2019-09-27 | 2022-06-28 | 重庆大直科技有限公司 | Pig quantity monitoring device |
| CN110672189A (en) * | 2019-09-27 | 2020-01-10 | 北京海益同展信息科技有限公司 | Weight estimation method, device, system and storage medium |
| CN111183917B (en) * | 2019-11-14 | 2022-02-01 | 京东科技信息技术有限公司 | Animal abnormity monitoring and image processing method and device |
| CN111418509A (en) * | 2020-01-16 | 2020-07-17 | 秒针信息技术有限公司 | Method and device for feeding livestock, storage medium and electronic device |
| CN111264405A (en) * | 2020-02-19 | 2020-06-12 | 北京海益同展信息科技有限公司 | Feeding method, system, device, equipment and computer readable storage medium |
| CN111369378A (en) * | 2020-02-25 | 2020-07-03 | 成都睿畜电子科技有限公司 | Live pig supervision method and system based on computer vision recognition |
| CN111507432A (en) * | 2020-07-01 | 2020-08-07 | 四川智迅车联科技有限公司 | Intelligent weighing method and system for agricultural insurance claims, electronic equipment and storage medium |
| CN112106689A (en) * | 2020-10-16 | 2020-12-22 | 中国农业大学 | Prawn feed platform observation system |
| CN112841074A (en) * | 2020-12-31 | 2021-05-28 | 京东数科海益信息科技有限公司 | Detection method, device, equipment and storage medium |
| CN112903078B (en) * | 2021-01-21 | 2023-01-10 | 核工业四一六医院 | Laboratory mouse data acquisition device and acquisition method |
| CN113063479A (en) * | 2021-03-16 | 2021-07-02 | 深圳市归位科技有限公司 | Animal husbandry weight estimation device and method combining tracking system and platform scale |
| CN112990073A (en) * | 2021-03-31 | 2021-06-18 | 南京农业大学 | Suckling period piglet activity rule statistical system based on edge calculation |
| CN113124971A (en) * | 2021-05-14 | 2021-07-16 | 深圳市路安仪器设备有限公司 | Linear weighing method |
| CN113780073B (en) * | 2021-08-03 | 2023-12-05 | 华南农业大学 | Device and method for auxiliary estimation of chicken flock uniformity |
| CN114067364B (en) * | 2021-11-23 | 2023-10-03 | 江苏省家禽科学研究所 | Chicken automatic weighing device based on image acquisition |
| CN114543674B (en) * | 2022-02-22 | 2023-02-07 | 成都睿畜电子科技有限公司 | Detection method and system based on image recognition |
| CN115226644A (en) * | 2022-08-05 | 2022-10-25 | 中国农业大学 | Pig grouping feeding management device and system |
| CN115226651B (en) * | 2022-08-19 | 2023-09-19 | 深圳进化动力数码科技有限公司 | Live pig weight estimation method and device for intelligent pig raising, electronic equipment and medium |
| CN115331266B (en) * | 2022-10-17 | 2023-02-10 | 天津大学四川创新研究院 | Pig unique identification duplicate removal alarm method |
| CN116058302B (en) * | 2023-03-15 | 2023-08-29 | 江苏省家禽科学研究所 | Automatic weighing broiler chicken raising cage |
| CN116091786B (en) * | 2023-04-11 | 2023-06-20 | 厦门农芯数字科技有限公司 | Holographic body ruler self-coding method, system, equipment and storage medium for pig weight estimation |
| CN116206342B (en) * | 2023-04-27 | 2023-07-25 | 广东省农业科学院动物科学研究所 | Pig weight detection method, device, equipment and storage medium |
| CN117528034B (en) * | 2023-12-29 | 2024-03-12 | 常州辉途智能科技有限公司 | Pasture intelligent breeding system and working method |
| CN117718244A (en) * | 2024-02-08 | 2024-03-19 | 中国农业科学院北京畜牧兽医研究所 | Grouping weighing system for cattle groups |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2010219406B2 (en) * | 2010-05-19 | 2013-01-24 | Plf Agritech Pty Ltd | Image analysis for making animal measurements |
| CN103884280A (en) * | 2014-03-14 | 2014-06-25 | 中国农业大学 | Mobile system for monitoring body sizes and weights of pigs in multiple pigsties |
| CN105784083B (en) * | 2016-04-05 | 2018-05-18 | 北京农业信息技术研究中心 | Dairy cow's conformation measuring method and system based on stereovision technique |
| CN206177429U (en) * | 2016-11-04 | 2017-05-17 | 北京农业信息技术研究中心 | Meat chicken weight estimation device based on range image |
| CN107667903B (en) * | 2017-07-27 | 2020-04-07 | 北京奥云牧数据科技有限公司 | Livestock breeding living body weight monitoring method based on Internet of things |
| CN108871520A (en) * | 2018-07-06 | 2018-11-23 | 平安科技（深圳）有限公司 | Livestock body weight measurement and device |
| CN109632058B (en) * | 2018-12-13 | 2020-06-02 | 北京小龙潜行科技有限公司 | Intelligent pig raising group weight measuring method and device, electronic equipment and storage medium |
| CN109579956B (en) * | 2018-12-13 | 2021-05-14 | 北京小龙潜行科技有限公司 | Intelligent pig raising limiting weight measuring method and device, electronic equipment and storage medium |
-
2018
- 2018-12-13 CN CN201811525570.7A patent/CN109632058B/en active Active
-
2019
- 2019-12-10 AU AU2019101786A patent/AU2019101786A4/en active Active
- 2019-12-10 AU AU2019399813A patent/AU2019399813A1/en active Pending
- 2019-12-10 WO PCT/CN2019/124174 patent/WO2020119659A1/en active Application Filing
Also Published As
| Publication number | Publication date |
|---|---|
| AU2019399813A1 (en) | 2021-02-25 |
| CN109632058B (en) | 2020-06-02 |
| WO2020119659A1 (en) | 2020-06-18 |
| CN109632058A (en) | 2019-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2019101786A4 (en) | Intelligent pig group rearing weighing method and apparatus, electronic device and storage medium | |
| CN108875647B (en) | Moving track monitoring method and system based on livestock identity | |
| CN110426112B (en) | Live pig weight measuring method and device | |
| CN109632059B (en) | Intelligent pig raising method and system, electronic equipment and storage medium | |
| CN105784083A (en) | Cow shape measuring method and cow shape measuring system based on stereo vision technology | |
| CN110991222B (en) | Object state monitoring and sow oestrus monitoring method, device and system | |
| CN108229351B (en) | Animal breeding method, animal breeding device and electronic equipment | |
| CN109579956B (en) | Intelligent pig raising limiting weight measuring method and device, electronic equipment and storage medium | |
| CN109784200B (en) | Binocular vision-based cow behavior image acquisition and body condition intelligent monitoring system | |
| Lu et al. | An automatic splitting method for the adhesive piglets’ gray scale image based on the ellipse shape feature | |
| CN115294185B (en) | Pig weight estimation method and related equipment | |
| CN112861734A (en) | Trough food residue monitoring method and system | |
| CN114898405B (en) | Portable broiler chicken anomaly monitoring system based on edge calculation | |
| CN112906734A (en) | Intelligent livestock breeding method and device, computer equipment and storage medium | |
| CN111713427B (en) | Suckling pig health condition monitoring system | |
| CN115777560A (en) | Intelligent sow feeding system based on machine vision analysis technology | |
| CN113743324A (en) | Automatic updating type fish identification system based on Internet of things | |
| CN115294448A (en) | Method, device and system for counting seedlings in crop breeding community | |
| CN205608801U (en) | Automatic device of grading of milk cow body condition | |
| CN114358163A (en) | Food intake monitoring method and system based on twin network and depth data | |
| Wang et al. | Vision-based measuring method for individual cow feed intake using depth images and a Siamese network | |
| CN113989745A (en) | Non-contact monitoring method for feeding condition of ruminants | |
| CN111507432A (en) | Intelligent weighing method and system for agricultural insurance claims, electronic equipment and storage medium | |
| CN109620150B (en) | Intelligent pig-raising limiting fat-measuring method and device, electronic equipment and storage medium | |
| CN116206342B (en) | Pig weight detection method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FGI | Letters patent sealed or granted (innovation patent) |