CN116453061A - Remote pig selling supervision method, device and equipment based on image recognition - Google Patents
Remote pig selling supervision method, device and equipment based on image recognition Download PDFInfo
- Publication number
- CN116453061A CN116453061A CN202310672928.3A CN202310672928A CN116453061A CN 116453061 A CN116453061 A CN 116453061A CN 202310672928 A CN202310672928 A CN 202310672928A CN 116453061 A CN116453061 A CN 116453061A
- Authority
- CN
- China
- Prior art keywords
- pig
- pigs
- weight
- image recognition
- key points
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 241000282887 Suidae Species 0.000 claims abstract description 91
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 3
- 230000002123 temporal effect Effects 0.000 claims description 2
- 230000008901 benefit Effects 0.000 abstract description 4
- 238000009395 breeding Methods 0.000 abstract description 2
- 230000001488 breeding effect Effects 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 9
- 230000006870 function Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 230000009466 transformation Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000036544 posture Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000010992 reflux Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a remote pig selling supervision method, device and equipment based on image recognition and a storage medium, which comprise the following steps: obtaining pig output videos according to a pig output plan, wherein the pig output videos are obtained by shooting through cameras preset in a pig output channel; identifying pigs in each frame of image in the pig outputting video, and predicting key points of the identified pigs through a key point identification algorithm to obtain key points of the pigs; analyzing the identified pigs based on the key points of the pigs to obtain the sizes and the weights of the pigs; counting pigs in the pig output video by a preset multi-dividing line weight counting method to obtain the number of pigs; the resulting pig size, pig weight and pig number were formed into a pig record. The method can ensure the accuracy of the quantity and quality of pigs, reduce management risk and labor cost so as to reduce the operation cost of breeding enterprises and improve economic benefit.
Description
Technical Field
The invention relates to the technical field of live pig transaction management, in particular to a remote pig selling supervision method, device and equipment based on image recognition.
Background
Because the live pig asset owners are inconsistent with actual management staff, the difficulty of manual statistics is high, inventory errors can be caused, or deception factors exist in the manual inventory behaviors, so that the pig farm is difficult to control the flow direction and the quantity of pigs, and asset loss is easy to cause. In addition, due to the fact that management requirements of trans-province forbidden transportation, quantity counting, video recording and the like are increased, and the pig selling process is mostly carried out in the early morning, a large amount of labor cost investment is needed for pig selling, and accordingly personnel operation cost is high.
Disclosure of Invention
In view of the above, the invention aims to provide a remote pig selling supervision method, device and equipment based on image recognition, which aim to solve the problems that the supervision of the flow direction and the quantity of pigs is not in place, the personnel operation cost is high due to manual operation and the like in the existing live pig selling process.
In order to achieve the above purpose, the invention provides a remote pig selling supervision method based on image recognition, which comprises the following steps:
obtaining pig output videos according to a pig output plan, wherein the pig output videos are obtained by shooting through cameras preset in a pig output channel;
identifying pigs in each frame of image in the pig outputting video, and predicting key points of the identified pigs through a key point identification algorithm to obtain key points of the pigs;
analyzing the identified pigs based on the key points of the pigs to obtain the sizes and the weights of the pigs;
counting pigs in the pig output video by a preset multi-dividing line weight counting method to obtain the number of pigs;
the resulting pig size, pig weight and pig number were formed into a pig record.
Preferably, the analyzing the identified pig based on the pig key points to obtain pig size and pig weight comprises:
analyzing the identified pig by a preset net body size algorithm based on the pig key points to obtain the pig size;
and calculating according to the pig size and a preset regression formula to obtain the pig weight.
Preferably, the analyzing the identified pig based on the pig key point and through a preset net body size algorithm to obtain the pig size includes:
and converting the pig key points into corresponding world coordinates, and calculating the pig body length and pig body width according to the world coordinates to obtain the pig size.
Preferably, the preset regression formula is thatWhere weight represents the weight of the pig, w represents the body width of the pig, and l represents the body length of the pig.
Preferably, the counting of the pigs in the pig output video by a preset multi-dividing line weight counting method to obtain the number of pigs comprises the following steps:
drawing an identification area based on a preset range of the pig outlet channel, and carrying out equidistant division according to the length of the identification area to obtain a plurality of statistical lines;
and counting pigs passing through the statistical line based on the spatial weight and the time weight to obtain the number of pigs.
Preferably, the counting the pigs passing through the statistical line based on the spatial weight and the temporal weight to obtain the number of pigs, including:
identifying pigs in the identification area, and drawing a pig identification frame according to each pig;
calculating the numerical value on the statistical line according to the source direction of the pig identification frame passing through the statistical line;
and carrying out normalization treatment on the numerical values of all the statistical lines according to time to obtain the pig numbers.
Preferably, the calculating the value on the statistical line according to the source direction of the pig identification frame passing through the statistical line includes:
when the center point of the pig identification frame passes through the statistical line from left to right, increasing the numerical value on the statistical line;
and when the center point of the pig identification frame passes through the statistical line from right to left, reducing the numerical value on the statistical line.
Preferably, the normalizing the values of all the statistical lines according to time to obtain the pig number includes:
and based on preset time, when judging that no pig is on each statistical line in the identification area, taking the numerical values on all the statistical lines in the identification area as the number of pigs.
In order to achieve the above object, the present invention further provides a remote pig selling supervision device based on image recognition, the device comprising:
the pig output system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring pig output videos according to a pig output plan, and the pig output videos are obtained by shooting through cameras preset in a pig output channel;
the prediction unit is used for identifying pigs in each frame of image in the pig outputting video, and predicting key points of the identified pigs through a key point identification algorithm to obtain key points of the pigs;
the analysis unit is used for analyzing the identified pig on the basis of the pig key points to obtain the size and weight of the pig;
the counting unit is used for counting pigs in the pig output video through a preset multi-dividing line weight counting method to obtain the number of the pigs;
and the recording unit is used for forming the obtained pig record by the pig size, the pig weight and the pig number.
In order to achieve the above object, the present invention further provides a remote pig sales supervision device based on image recognition, which comprises a processor, a memory and a computer program stored in the memory, wherein the computer program is executed by the processor to implement the steps of the remote pig sales supervision method based on image recognition according to the above embodiment.
To achieve the above object, the present invention also proposes a computer-readable storage medium having stored thereon a computer program to be executed by a processor to implement the steps of a remote pig sales supervision method based on image recognition as described in the above embodiments.
The beneficial effects are that:
according to the scheme, real-time tracking analysis and accurate weight estimation are performed on pigs in the pig output video through various algorithms, pig output records are formed, so that remote selling of pigs in the whole process of before, during and after sale is achieved, incorrect behaviors can be avoided through standardization, optimization and retrospective selling of pigs, the accuracy of the quantity and quality of the pigs can be ensured, management risks and labor cost are reduced, management cost of a breeding enterprise is reduced, economic benefits are improved, and pig selling efficiency and transaction transparency are improved.
According to the scheme, the space weight and the time weight introduced in the multi-dividing line weight counting method are preset to count pigs, so that the number of the pigs is obtained, the situation that the counting error is large due to misidentification of the pigs can be avoided, and the counting precision is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a remote pig selling supervision method based on image recognition according to an embodiment of the present invention.
Fig. 2 is a display diagram of identification area drawing according to an embodiment of the present invention.
Fig. 3 is a display diagram of a statistical line process in an identification area according to an embodiment of the present invention.
Fig. 4 is a schematic structural diagram of a remote pig selling supervision device based on image recognition according to an embodiment of the present invention.
The realization of the object, the functional characteristics and the advantages of the invention will be further described with reference to the accompanying drawings in connection with the embodiments.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, based on the embodiments of the invention, which are apparent to those of ordinary skill in the art without inventive faculty, are intended to be within the scope of the invention. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, based on the embodiments of the invention, which are apparent to those of ordinary skill in the art without inventive faculty, are intended to be within the scope of the invention.
The following describes the invention in detail with reference to examples.
Referring to fig. 1, a flow chart of a remote pig selling supervision method based on image recognition according to an embodiment of the present invention is shown.
In this embodiment, the method includes:
s11, obtaining pig video according to a pig outputting plan, wherein the pig outputting video is obtained by shooting through a camera preset in a pig outputting channel.
In this embodiment, intelligent devices (including cameras) are installed on pig-out platforms and pig-out channels of the farm, so that relevant operations are performed on a visual interface of the system. The pig-selling system can select a pig-selling plan according to requirements, or can select to create a temporary pig-selling plan, and after relevant operation, the pig-selling system shoots by controlling a camera so as to obtain pig videos. And (3) forming a video acquisition decoding stream by using modules of the gstreamer, and carrying out frame-by-frame identification analysis on the acquired video stream. Rendering, re-encoding of the video stream into h264 and using webtc push for live viewing is supported.
And S12, identifying the pig in each frame of image in the pig outputting video, and predicting the key points of the identified pig by a key point identification algorithm to obtain the key points of the pig.
In this embodiment, the image features may be extracted by performing convolution and pooling operations based on a Convolutional Neural Network (CNN) key point recognition algorithm, and finally, the feature points of the pig are located according to the prediction category and the full connection layer, so as to obtain the pig key points.
S13, analyzing the identified pig based on the pig key points to obtain the size and weight of the pig.
In step S13, the analyzing the identified pig based on the pig keypoints to obtain a pig size and a pig weight includes:
s13-1, analyzing the identified pig on the basis of the pig key points and through a preset net body size algorithm to obtain the pig size;
s13-2, calculating according to the pig size and a preset regression formula to obtain the pig weight.
The method for analyzing the identified pig based on the pig key points and through a preset net body size algorithm to obtain the pig size comprises the following steps:
and converting the pig key points into corresponding world coordinates, and calculating the pig body length and pig body width according to the world coordinates to obtain the pig size.
Wherein the preset regression formula is as followsWhere weight represents the weight of the pig, w represents the body width of the pig, and l represents the body length of the pig.
In this embodiment, as the relationship between the sizes and the weights of the pigs in different postures is corresponding, the difference between the weight change curves and the weight values of the GT in different postures is analyzed, and the difference is reduced optimally, the obtained key points of the pigs are converted into corresponding world coordinates, and the body length and the body width of the pigs are calculated according to the world coordinates, so as to obtain the sizes of the pigs; and then according to the formulaPig weight was calculated. Wherein, the process of converting the pig key points into corresponding world coordinates comprises the following steps:
(1) Using the camera reference matrix a, pixel coordinates (pixel coordinates of the pig key on the image) p: (u, v) projected to a 3D spatial point Pc under the camera coordinate system: (Xc, yc, zc), assuming projection to a unit space point, i.e., specifying zc=1, wherein the camera internal reference matrix a is composed of focal lengths fx, fy in x and y directions in pixels. Cx and Cy are the principal projection points, usually the center position of the projected image, s is an arbitrary scaling constant, and 1 is not written. The following formula is shown:
that is to say,
(2) With the point Pc in the camera coordinate system, the camera coordinate system point is then converted into a world coordinate system point. A combination of projective transformation and homogeneous transformation is performed using pre-calibrated external parameters, including a rotational translation matrix. Thus, the projection Pw in world coordinates is obtained from the Pc point given in the camera coordinate system.
That is to say,
wherein, all r and t are obtained in advance through calibration.
In summary, the above two transformations are combined to obtain a projective transformation relationship that maps 3D points in world coordinates to image pixels:
that is to say,
so far, the pixel coordinate points corresponding to the key points of the pigs are converted into space points of a world coordinate system.
S14, counting pigs in the pig output video by a preset multi-dividing line weight counting method to obtain the number of pigs.
In step S14, counting pigs in the pig output video by a preset multi-dividing line weight counting method to obtain the number of pigs, including:
s14-1, drawing an identification area based on a preset range of a pig outlet channel, and dividing the identification area at equal intervals according to the length of the identification area to obtain a plurality of statistical lines;
s14-2, counting the pigs passing through the statistical line based on the spatial weight and the time weight to obtain the number of the pigs.
Wherein, based on space weight and time weight, statistics is carried out on the pigs passing through the statistical line, and the number of the pigs is obtained, and the method comprises the following steps:
identifying pigs in the identification area, and drawing a pig identification frame according to each pig;
calculating the numerical value on the statistical line according to the source direction of the pig identification frame passing through the statistical line;
and carrying out normalization treatment on the numerical values of all the statistical lines according to time to obtain the pig numbers.
Wherein, the calculating the numerical value on the statistical line according to the source direction of the pig identification frame passing through the statistical line comprises:
when the center point of the pig identification frame passes through the statistical line from left to right, increasing the numerical value on the statistical line;
and when the center point of the pig identification frame passes through the statistical line from right to left, reducing the numerical value on the statistical line.
And normalizing the numerical values of all the statistical lines according to time to obtain the pig numbers, wherein the method comprises the following steps:
and based on preset time, when judging that no pig is on each statistical line in the identification area, taking the numerical values on all the statistical lines in the identification area as the number of pigs.
In this embodiment, since the pig count is repeated due to the position pause of the pig in the current identification area, or due to the pig bundling or pig stacking, or the error of the staff in various situations such as partial entry at the edge, there is a large error in the pig count, the pig count is performed by the preset multi-split line weight count method introducing the spatial weight and the time weight, so as to improve the accuracy of the pig count. Referring to fig. 2, an operation interface in a pig vending system draws an identification area by entering a working area function module of equipment management, and generally the drawing range of the identification area is drawn close to the range of a pig channel. Referring to fig. 3, after drawing the identification area, dividing the identification area equally according to the length of the identification area to generate a plurality of statistical lines (e.g. 20) wherein the numerical value on the statistical line represents the number of passing pigs, and the labeling direction of the identification area is set from left to right (the purpose of setting the direction is to prevent the reflux phenomenon of pigs when counting pigs, and to avoid affecting the accuracy of pig statistics). Identifying pig targets in the identification area by using a target detection algorithm, drawing a pig identification frame (Box) in real time, and calculating according to the source direction of a statistic line passed by the pig identification frame; further comprises: when the central point of a pig identification frame passes through the statistical line, calculating by judging the source direction of the pig identification frame, if the pig identification frame passes from left to right, adding 1 to the value on the statistical line, and if the pig identification frame passes from right to left, subtracting 1 from the value on the statistical line, wherein the value of each statistical line is counted independently. In order to reduce accumulated errors, solve personnel interference to cause abnormal number of statistical lines in space, further perform time weight correction on data, and normalize the numerical values of all the statistical lines in space to one value, including: by detecting the identification area at a preset time (such as every second), when all the statistic lines in the identification area have no pigs, the numerical value of 20 statistic lines on the identification area is subjected to mode selection (the result of each detection is selected from the modes of the previous statistics) to determine the number of the passed pigs, and all the statistic lines are assigned, otherwise, no operation is performed.
And S15, forming a pig record by the obtained pig size, the pig weight and the pig number.
In this embodiment, a pig output record report is obtained after the above processing, and according to the pig output record and pig output planned pig data, if there is a deviation of pig data, information can be timely pushed on a display page of the system to give an early warning, and a user can make a decision about pig output according to the data display condition. In addition, the situation of pig output of each batch, including quantity, weight and the like, can be checked in the system, and video recording during pig output can be traced back, so that the whole process of remote pig selling before, during and after sale is standardized, the accuracy of quantity and quality of pigs is ensured, and management risk is reduced.
Referring to fig. 4, a schematic structural diagram of a remote pig selling supervision device based on image recognition according to an embodiment of the present invention is shown.
In this embodiment, the apparatus 40 includes:
an obtaining unit 41, configured to obtain a pig video according to a pig output plan, where the pig output video is obtained by capturing a pig output video with a camera preset in a pig output channel;
the prediction unit 42 is configured to identify a pig for each frame of image in the pig output video, and predict a key point of the identified pig by using a key point identification algorithm, so as to obtain a key point of the pig;
an analysis unit 43 for analyzing the identified pig based on the pig key points to obtain a pig size and a pig weight;
the statistics unit 44 is configured to count pigs in the pig output video by a preset multiple dividing line weight count method to obtain the number of pigs;
a recording unit 45 for forming a pig record of the obtained pig size, pig weight and pig number.
The respective unit modules of the apparatus 40 may perform the corresponding steps in the above method embodiments, so that the detailed description of the respective unit modules is omitted herein.
The embodiment of the invention also provides a device, which comprises the remote pig selling supervision device based on image recognition, wherein the remote pig selling supervision device based on image recognition can adopt the structure of the embodiment of fig. 4, correspondingly, the technical scheme of the method embodiment shown in fig. 1 can be executed, the implementation principle and the technical effect are similar, and details can be referred to the relevant records in the embodiment and are not repeated here.
The apparatus comprises: a device with a photographing function such as a mobile phone, a digital camera or a tablet computer, or a device with an image processing function, or a device with an image display function. The device may include a memory, a processor, an input unit, a display unit, a power source, and the like.
The memory may be used to store software programs and modules, and the processor executes the software programs and modules stored in the memory to perform various functional applications and data processing. 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 (e.g., an image playing function, etc.) required for at least one function, and the like; the storage data area may store data created according to the use of the device, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory may also include a memory controller to provide access to the memory by the processor and the input unit.
The input unit may be used to receive input digital or character or image information and to generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control. Specifically, the input unit of the present embodiment may include a touch-sensitive surface (e.g., a touch display screen) and other input devices in addition to the camera.
The display unit may be used to display information entered by a user or provided to a user as well as various graphical user interfaces of the device, which may be composed of graphics, text, icons, video and any combination thereof. The display unit may include a display panel, and alternatively, the display panel may be configured in the form of an LCD (Liquid Crystal Display ), an OLED (organic light-Emitting Diode), or the like. Further, the touch-sensitive surface may overlay the display panel, and upon detection of a touch operation thereon or thereabout, the touch-sensitive surface is communicated to the processor to determine the type of touch event, and the processor then provides a corresponding visual output on the display panel based on the type of touch event.
The embodiment of the present invention also provides a computer readable storage medium, which may be a computer readable storage medium contained in the memory in the above embodiment; or may be a computer-readable storage medium, alone, that is not assembled into a device. The computer readable storage medium has stored therein at least one instruction that is loaded and executed by a processor to implement the image recognition based remote pig sales administration method shown in fig. 1. The computer readable storage medium may be a read-only memory, a magnetic disk or optical disk, etc.
It should be noted that, in the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described as different from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other. For the device embodiments, the apparatus embodiments and the storage medium embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.
Also, herein, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
While the foregoing description illustrates and describes the preferred embodiments of the present invention, it is to be understood that the invention is not limited to the forms disclosed herein, but is not to be construed as limited to other embodiments, but is capable of use in various other combinations, modifications and environments and is capable of changes or modifications within the scope of the inventive concept, either as described above or as a matter of skill or knowledge in the relevant art. And that modifications and variations which do not depart from the spirit and scope of the invention are intended to be within the scope of the appended claims.
Claims (10)
1. The method for remotely supervising the pig selling based on the image recognition is characterized by comprising the following steps:
obtaining pig output videos according to a pig output plan, wherein the pig output videos are obtained by shooting through cameras preset in a pig output channel;
identifying pigs in each frame of image in the pig outputting video, and predicting key points of the identified pigs through a key point identification algorithm to obtain key points of the pigs;
analyzing the identified pigs based on the key points of the pigs to obtain the sizes and the weights of the pigs;
counting pigs in the pig output video by a preset multi-dividing line weight counting method to obtain the number of pigs;
the resulting pig size, pig weight and pig number were formed into a pig record.
2. The method for remotely supervising the sale of pigs based on image recognition according to claim 1, wherein the analyzing the identified pigs based on the pig key points to obtain pig sizes and pig weights comprises:
analyzing the identified pig by a preset net body size algorithm based on the pig key points to obtain the pig size;
and calculating according to the pig size and a preset regression formula to obtain the pig weight.
3. The method for remotely selling pigs and supervising based on image recognition according to claim 2, wherein the analyzing the identified pigs based on the pig key points and by a preset net body size algorithm to obtain pig sizes comprises:
and converting the pig key points into corresponding world coordinates, and calculating the pig body length and pig body width according to the world coordinates to obtain the pig size.
4. The image recognition-based remote pig sales supervision method as recited in claim 2, wherein the preset regression formula isWhere weight represents the weight of the pig, w represents the body width of the pig, and l represents the body length of the pig.
5. The method for remotely selling pigs and supervising based on image recognition according to claim 1, wherein counting pigs in the pig output video by a preset multi-split line weight counting method to obtain the number of pigs comprises the following steps:
drawing an identification area based on a preset range of the pig outlet channel, and carrying out equidistant division according to the length of the identification area to obtain a plurality of statistical lines;
and counting pigs passing through the statistical line based on the spatial weight and the time weight to obtain the number of pigs.
6. The image recognition-based remote pig sales supervision method according to claim 5, wherein the counting of pigs passing through the statistical line based on spatial weight and temporal weight to obtain the number of pigs comprises:
identifying pigs in the identification area, and drawing a pig identification frame according to each pig;
calculating the numerical value on the statistical line according to the source direction of the pig identification frame passing through the statistical line;
and carrying out normalization treatment on the numerical values of all the statistical lines according to time to obtain the pig numbers.
7. A method of remotely selling pigs in accordance with image recognition of claim 6, wherein said calculating a value on said statistical line based on the direction of origin of said pig identification frame through said statistical line comprises:
when the center point of the pig identification frame passes through the statistical line from left to right, increasing the numerical value on the statistical line;
and when the center point of the pig identification frame passes through the statistical line from right to left, reducing the numerical value on the statistical line.
8. The method for remotely supervising the sale of pigs based on image recognition according to claim 6, wherein the normalizing the values of all the statistical lines according to time to obtain the number of pigs comprises:
and based on preset time, when judging that no pig is on each statistical line in the identification area, taking the numerical values on all the statistical lines in the identification area as the number of pigs.
9. A remote pig sales supervision device based on image recognition, the device comprising:
the pig output system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring pig output videos according to a pig output plan, and the pig output videos are obtained by shooting through cameras preset in a pig output channel;
the prediction unit is used for identifying pigs in each frame of image in the pig outputting video, and predicting key points of the identified pigs through a key point identification algorithm to obtain key points of the pigs;
the analysis unit is used for analyzing the identified pig on the basis of the pig key points to obtain the size and weight of the pig;
the counting unit is used for counting pigs in the pig output video through a preset multi-dividing line weight counting method to obtain the number of the pigs;
and the recording unit is used for forming the obtained pig record by the pig size, the pig weight and the pig number.
10. A remote pig sales supervision device based on image recognition, comprising a processor, a memory and a computer program stored in the memory, the computer program being executed by the processor to implement the steps of a remote pig sales supervision method based on image recognition as claimed in any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310672928.3A CN116453061B (en) | 2023-06-08 | 2023-06-08 | Remote pig selling supervision method, device and equipment based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310672928.3A CN116453061B (en) | 2023-06-08 | 2023-06-08 | Remote pig selling supervision method, device and equipment based on image recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116453061A true CN116453061A (en) | 2023-07-18 |
| CN116453061B CN116453061B (en) | 2023-10-03 |
Family
ID=87125899
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310672928.3A Active CN116453061B (en) | 2023-06-08 | 2023-06-08 | Remote pig selling supervision method, device and equipment based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116453061B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117746344A (en) * | 2024-02-21 | 2024-03-22 | 厦门农芯数字科技有限公司 | Event analysis method, device and equipment for pig farm monitoring video |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106940789A (en) * | 2017-03-10 | 2017-07-11 | 广东数相智能科技有限公司 | A kind of method, system and device of the quantity statistics based on video identification |
| WO2021000423A1 (en) * | 2019-07-04 | 2021-01-07 | 平安科技（深圳）有限公司 | Pig weight measurement method and apparatus |
| CN113537175A (en) * | 2021-09-16 | 2021-10-22 | 长沙鹏阳信息技术有限公司 | Same-fence swinery average weight estimation method based on computer vision |
| CN113920453A (en) * | 2021-10-13 | 2022-01-11 | 华南农业大学 | Pig body size weight estimation method based on deep learning |
| CN114119648A (en) * | 2021-11-12 | 2022-03-01 | 史缔纳农业科技(广东)有限公司 | Pig counting method for fixed channel |
| CN114495284A (en) * | 2022-02-28 | 2022-05-13 | 厦门农芯数字科技有限公司 | Pig shoal shielding segmentation identification method and device based on example segmentation |
| CN115830078A (en) * | 2023-02-13 | 2023-03-21 | 山东科技大学 | Live pig multi-target tracking and behavior recognition method, computer equipment and storage medium |
-
2023
- 2023-06-08 CN CN202310672928.3A patent/CN116453061B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106940789A (en) * | 2017-03-10 | 2017-07-11 | 广东数相智能科技有限公司 | A kind of method, system and device of the quantity statistics based on video identification |
| WO2021000423A1 (en) * | 2019-07-04 | 2021-01-07 | 平安科技（深圳）有限公司 | Pig weight measurement method and apparatus |
| CN113537175A (en) * | 2021-09-16 | 2021-10-22 | 长沙鹏阳信息技术有限公司 | Same-fence swinery average weight estimation method based on computer vision |
| CN113920453A (en) * | 2021-10-13 | 2022-01-11 | 华南农业大学 | Pig body size weight estimation method based on deep learning |
| WO2023060777A1 (en) * | 2021-10-13 | 2023-04-20 | 华南农业大学 | Pig body size and weight estimation method based on deep learning |
| CN114119648A (en) * | 2021-11-12 | 2022-03-01 | 史缔纳农业科技(广东)有限公司 | Pig counting method for fixed channel |
| CN114495284A (en) * | 2022-02-28 | 2022-05-13 | 厦门农芯数字科技有限公司 | Pig shoal shielding segmentation identification method and device based on example segmentation |
| CN115830078A (en) * | 2023-02-13 | 2023-03-21 | 山东科技大学 | Live pig multi-target tracking and behavior recognition method, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 李卓;杜晓冬;毛涛涛;滕光辉;: "基于深度图像的猪体尺检测***", 猪业观察, no. 04, pages 28 - 35 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117746344A (en) * | 2024-02-21 | 2024-03-22 | 厦门农芯数字科技有限公司 | Event analysis method, device and equipment for pig farm monitoring video |
| CN117746344B (en) * | 2024-02-21 | 2024-05-14 | 厦门农芯数字科技有限公司 | Event analysis method, device and equipment for pig farm monitoring video |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116453061B (en) | 2023-10-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210248734A1 (en) | Method and apparatus for detecting pixel defect of optical module, and device | |
| US8941645B2 (en) | Comparing virtual and real images in a shopping experience | |
| US11312020B2 (en) | System and method for fast object detection in robot picking | |
| US8854474B2 (en) | System and method for quick object verification | |
| CN109117824B (en) | Commodity management method and device, electronic equipment and storage medium | |
| US20210174299A1 (en) | Method, system and device for collecting sales information of commodities in cabinet, and storage medium | |
| US20230052727A1 (en) | Method and system for detecting physical features of objects | |
| CN116453061B (en) | Remote pig selling supervision method, device and equipment based on image recognition | |
| CN110336691B (en) | Management method, device, equipment and communication system of equipment in data center | |
| WO2020233221A1 (en) | Heatmap analysis method, device, and system | |
| CN113689578B (en) | Human body data set generation method and device | |
| US20190213755A1 (en) | Image labeling for cleaning robot deep learning system | |
| JP7250155B2 (en) | Fish counting system, fish counting method and program | |
| CN111008561A (en) | Livestock quantity determination method, terminal and computer storage medium | |
| US20240005524A1 (en) | Video-based systems and methods for generating compliance-annotated motion trails in a video sequence for assessing rule compliance for moving objects | |
| CN114998768B (en) | Intelligent construction site management system and method based on unmanned aerial vehicle | |
| US20230274226A1 (en) | Retail shelf image processing and inventory tracking system | |
| CN113743492B (en) | Method and device for ordering positions of rows and columns of pressing plates | |
| CN114022070A (en) | Disc library method, device, equipment and storage medium | |
| CN111145674B (en) | Display panel detection method, electronic device and storage medium | |
| CN114004891A (en) | Distribution network line inspection method based on target tracking and related device | |
| CN114170373A (en) | Target object labeling method, processor, device and mixing station | |
| CN112395208A (en) | Automatic test method, device, equipment and storage medium for AI recognition device | |
| CN111553210B (en) | Training method of lane line detection model, lane line detection method and device | |
| US20230386211A1 (en) | Method and device for cargo inventorying and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231113 Address after: A1, Unit 1601, No. 50, Chengyi North Street, Phase III, Software Park, Jimei District, Xiamen, Fujian Province, 361000 Patentee after: Xiamen Nongxin Digital Technology Co.,Ltd. Patentee after: Beijing Nongxin Shuzhi Technology Co.,Ltd. Address before: A1, Unit 1601, No. 50, Chengyi North Street, Phase III, Software Park, Jimei District, Xiamen, Fujian Province, 361000 Patentee before: Xiamen Nongxin Digital Technology Co.,Ltd. |