CN112288793B - Method and device for detecting backfat of livestock individuals, electronic equipment and storage medium - Google Patents
Method and device for detecting backfat of livestock individuals, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112288793B CN112288793B CN202011232362.5A CN202011232362A CN112288793B CN 112288793 B CN112288793 B CN 112288793B CN 202011232362 A CN202011232362 A CN 202011232362A CN 112288793 B CN112288793 B CN 112288793B
- Authority
- CN
- China
- Prior art keywords
- backfat
- livestock
- data
- detected
- individuals
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/70—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in livestock or poultry
Abstract
The embodiment of the invention provides a method, a device, electronic equipment and a storage medium for detecting backfat of livestock individuals, which can automatically determine body size data of the livestock individuals to be detected through three-dimensional point cloud data; the backfat information of the livestock individuals to be detected can be rapidly and accurately determined through the body ruler data; identity information of the livestock individuals to be detected is introduced, and the identity information is combined with body size data of the livestock individuals to be detected, so that the accuracy of backfat information of the livestock individuals to be detected can be further improved. The whole detection process can realize automation without manual participation, so that not only can the manpower consumption brought in the complex backfat detection process be reduced, but also the detection efficiency can be improved, and the phenomenon that the livestock and poultry generate stress response or the disease probability of the livestock and poultry is increased due to human and animal contact can be avoided. In addition, the detection process does not need to consider limiting conditions such as animal body gestures, ambient light and the like, so that the detection method can be suitable for detection of animal body backfat information in various different scenes.
Description
Technical Field
The invention relates to the technical field of agriculture and animal husbandry cultivation, in particular to a method and a device for detecting backfat of an individual animal, electronic equipment and a storage medium.
Background
The measurement of backfat of individual animals plays a vital role in the whole feeding process of animals, especially female animals, and the backfat thickness of individual female animals at each stage reflects the health condition and nutrition level of individual female animals.
In the prior art, the method for acquiring backfat of the livestock individuals mainly comprises the steps of manually realizing by a breeder and automatically identifying two-dimensional images of the livestock individuals. However, in the mode of manual implementation by a breeder, the efficiency is low, misjudgment is easy to cause, and close contact between people and livestock is required, so that on one hand, stress response of the livestock can be caused, and on the other hand, the disease probability of the people and the livestock can be increased; and still require close contact of people and livestock; by means of the method for automatically identifying the two-dimensional images of the livestock individuals, the close contact of people and livestock can be avoided, but deviation is easy to occur when the two-dimensional images of the livestock individuals are identified, and the real backfat of the livestock individuals cannot be truly reflected; moreover, the two-dimensional images of the livestock individuals are acquired with high requirements on the gestures, the ambient light and the like of the livestock individuals, and the method cannot be suitable for detecting backfat of the livestock individuals in various different scenes.
Disclosure of Invention
The embodiment of the invention provides a method and a device for detecting backfat of livestock individuals, electronic equipment and a storage medium, which are used for solving the defects in the prior art.
The embodiment of the invention provides a method for detecting backfat of livestock individuals, which comprises the following steps:
determining three-dimensional point cloud data of an individual to be tested, and determining body scale data of the individual to be tested based on the three-dimensional point cloud data;
and determining backfat information of the livestock individuals to be tested based on the body ruler data of the livestock individuals to be tested or based on the body ruler data of the livestock individuals to be tested and the identity information of the livestock individuals to be tested.
According to an embodiment of the present invention, the method for detecting backfat of livestock individuals, which determines body ruler data of the livestock individuals to be detected based on the three-dimensional point cloud data, specifically includes:
projecting the three-dimensional point cloud data to a horizontal plane to obtain the back profile of the livestock to be tested, or respectively projecting the three-dimensional point cloud data to the horizontal plane and a vertical plane perpendicular to the trunk of the livestock to be tested to obtain the back profile and the hip profile of the livestock to be tested;
based on the back profile and/or the hip profile, a hip width in the body scale data is determined, and based on the back profile, a shoulder width, a waist width, and a chest circumference in the body scale data are determined.
According to an embodiment of the present invention, the method for detecting backfat of individual animals, determining shoulder width, waist width and chest circumference in the body size data based on the back contour specifically includes:
determining two shoulder width key points and two waist width key points in the back profile, determining the shoulder width based on the two shoulder width key points, and determining the waist width based on the two waist width key points;
determining chest contours of the to-be-tested livestock individuals based on the three-dimensional point cloud data and a vertical plane containing the two shoulder width key points;
and determining the chest circumference of the livestock individual to be tested based on the chest outline.
According to an embodiment of the present invention, the determining the backfat information of the livestock individuals to be tested based on the body ruler data of the livestock individuals to be tested or based on the body ruler data of the livestock individuals to be tested and the identity information of the livestock individuals to be tested specifically includes:
inputting the body ruler data or the body ruler data and the identity information into a backfat detection model to obtain backfat information output by the backfat detection model;
the backfat detection model is obtained based on body size data of sample livestock individuals carrying backfat information labels or based on body size data training of sample livestock individuals carrying backfat information labels and identity information labels.
According to the backfat detection method for the livestock individuals, the backfat detection model comprises a plurality of backfat detection layers corresponding to different identity information;
correspondingly, the step of inputting the body size data into a backfat detection model to obtain backfat information output by the backfat detection model specifically comprises the following steps:
and inputting the body size data to a backfat detection layer corresponding to the identity information in the backfat detection model to obtain backfat information output by the backfat detection layer corresponding to the identity information.
According to an embodiment of the present invention, the method for detecting backfat of livestock individuals, in which the body ruler data is input to a backfat detection layer corresponding to the identity information in the backfat detection model, obtains the backfat information output by the backfat detection layer corresponding to the identity information, further includes:
and inputting the body ruler data to an identity classification layer in the backfat detection model to obtain the identity information output by the identity classification layer.
According to an embodiment of the present invention, the determining the backfat information of the livestock individuals to be tested based on the body ruler data of the livestock individuals to be tested or based on the body ruler data of the livestock individuals to be tested and the identity information of the livestock individuals to be tested specifically includes:
And if the body ruler data is in a preset general body ruler data interval, determining the backfat information based on the body ruler data or based on the body ruler data and the identity information.
The embodiment of the invention also provides a backfat detection device for livestock individuals, which comprises the following components: a body ruler data determining module and a backfat information determining module. Wherein, the liquid crystal display device comprises a liquid crystal display device,
the body ruler data determining module is used for determining three-dimensional point cloud data of the livestock individuals to be detected and determining the body ruler data of the livestock individuals to be detected based on the three-dimensional point cloud data;
the backfat information determining module is used for determining backfat information of the livestock individuals to be detected based on the body ruler data of the livestock individuals to be detected or based on the body ruler data of the livestock individuals to be detected and the identity information of the livestock individuals to be detected.
The embodiment of the invention also provides electronic equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the steps of the animal individual backfat detection method are realized when the processor executes the program.
The embodiment of the invention also provides a non-transitory computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of the animal individual backfat detection method as described in any one of the above.
According to the animal individual backfat detection method, the device, the electronic equipment and the storage medium provided by the embodiment of the invention, the body ruler data of an animal individual to be detected can be automatically determined through the three-dimensional point cloud data; the backfat information of the livestock individuals to be detected can be rapidly and accurately determined through the body ruler data of the livestock individuals to be detected; identity information of the livestock individuals to be detected is introduced, and the identity information is combined with body size data of the livestock individuals to be detected, so that the accuracy of backfat information of the livestock individuals to be detected can be further improved. The whole detection process can realize automation without manual participation, so that not only can the manpower consumption brought in the complex backfat detection process be reduced, but also the detection efficiency can be improved, and the phenomenon that the livestock and poultry generate stress response or the disease probability of the livestock and poultry is increased due to human and animal contact can be avoided. In addition, the detection process does not need to consider limiting conditions such as animal body gestures, ambient light and the like, so that the detection method can be suitable for detection of animal body backfat information in various different scenes.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can 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 method for detecting backfat of livestock individuals, which is provided by the embodiment of the invention;
fig. 2 is a schematic structural diagram of a backfat detection device for livestock individuals according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
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 of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
At present, backfat information detection of pigs, cattle, sheep, horses, donkeys and other domestic animals is of great importance to the whole feeding process of domestic animals, and the backfat thickness of a sow individual at each stage reflects the nutrition level and health condition of the sow individual by taking the sow feeding process as an example. In the modern intensive, automatic and intelligent cultivation scene, the automatic and intelligent measurement of the backfat thickness of the individual sows in a non-contact manner can be realized, the nutrition level of the individual sows and the health condition of the sows can be known, the feeding level feeding quantity of the individual sows can be further adjusted, and the method has great significance in reducing the feed-meat ratio of fattening pigs and improving the economic benefit. Most of the existing sow body condition assessment methods are that a scoring staff visually evaluates and scores the sow body condition according to experience, but the body condition scoring is not objective, has large errors, and cannot accurately reflect the backfat level of the overall fertility of the pig farm. At present, three main ways of obtaining backfat of livestock individuals are as follows: 1) The backfat instrument is held by a breeder, and is attached to the skin surface of an individual animal to carry out backfat measurement; 2) Estimating buttocks of the livestock individuals through human eye observation, and further roughly estimating backfat of the livestock individuals; 3) And obtaining key point information of animals by using the two-dimensional image, and identifying individual backfat by using a body type template obtained by similarity transformation so as to obtain backfat value.
However, 1) the scheme of measuring by a backfat instrument held by a breeder has higher measuring precision, but needs manual participation, has lower efficiency, and needs close contact of people and livestock, so that on one hand, stress response of the livestock can be caused, and on the other hand, the disease probability of the people and the livestock can be increased; 2) The scheme for estimating the buttocks of the livestock individuals through human eye observation has higher requirements on the experience of staff, is easy to cause misjudgment, and still needs close contact of people and livestock; 3) Although the two-dimensional image mode can avoid close contact of people and livestock, the determination of the key point information of the livestock individuals is easy to deviate, and the real backfat of the livestock individuals cannot be truly reflected; moreover, the two-dimensional image acquisition has high requirements on animal body gestures, environmental light and the like, and cannot be suitable for measuring animal body backfat of various different scenes. Based on the detection, the embodiment of the invention provides a method for detecting backfat of an individual animal, which aims to solve the technical problems in the prior art.
Fig. 1 is a schematic flow chart of a method for detecting backfat of livestock individuals, which is provided in an embodiment of the invention, as shown in fig. 1, and includes:
s1, determining three-dimensional point cloud data of an individual to be tested, and determining body scale data of the individual to be tested based on the three-dimensional point cloud data;
S2, determining backfat information of the livestock individuals to be tested based on the body ruler data of the livestock individuals to be tested or based on the body ruler data of the livestock individuals to be tested and the identity information of the livestock individuals to be tested.
Specifically, the method for detecting backfat of livestock individuals provided by the embodiment of the invention aims to automatically detect backfat information of the livestock individuals to be detected by acquiring point cloud data of the livestock individuals to be detected. The backfat information may specifically be a backfat thickness.
Step S1 is first performed. The livestock to be detected is a target object to be detected for backfat information detection, and the variety of the livestock to be detected can specifically comprise pigs, cattle, sheep, horses, donkeys and the like. The individual animal to be tested is an independent individual animal in the animal to be tested, such as a pig, a cow, a horse, etc. In the embodiment of the invention, the sex of the individual livestock to be tested is not particularly limited.
The three-dimensional point cloud data of the livestock individuals to be detected refer to point cloud data representing a three-dimensional overall model of the livestock individuals to be detected, in the embodiment of the invention, the point cloud data of the livestock individuals to be detected can be obtained from different angles through a point cloud capturing device such as a depth camera, and the three-dimensional point cloud data of the livestock individuals to be detected can be further obtained through preprocessing and three-dimensional reconstruction of a registration algorithm. Compared with the traditional mode of carrying out two-dimensional image acquisition on the livestock individuals to be detected, the method has the advantage that the requirements of acquiring the point cloud data of the livestock individuals to be detected on the gestures, the ambient light and the like of the livestock individuals are lower.
The body ruler data of the individual livestock to be detected can be determined by carrying out subsequent processing such as projection on the three-dimensional point cloud data and combining the characteristics of each part of the individual livestock to be detected. The body ruler data can comprise shoulder width, waist width, hip width, waistline, chest circumference, chest depth, body length, height and other data of an individual to be tested, and can also comprise proportion data such as a back width-to-length ratio, a chest depth-to-leg height ratio and the like, wherein the back width-to-length ratio is the ratio of the hip width to the body length, and the chest depth-to-leg height ratio is the ratio of the chest depth to the height.
Step S2 is then performed. In the embodiment of the invention, the backfat information of the livestock individuals to be detected can be determined by the body ruler data of the livestock individuals to be detected, or the backfat information of the livestock individuals to be detected can be determined by combining the identity information of the livestock individuals to be detected on the basis of the body ruler data of the livestock individuals to be detected. When determining backfat information of an individual animal to be tested, the method can be realized through a pre-trained backfat detection model, or can be determined through a corresponding relation between pre-determined body size data and backfat information or a corresponding relation among pre-determined body size data, identity information and backfat information, and the method is not particularly limited in the embodiment of the invention.
The identity information can comprise information of varieties, growth stages and the like of the livestock individuals to be detected. Each animal to be tested is fed in the corresponding column, and each animal to be tested has a unique ID, and as the identification of the animal to be tested, the ID and the identity information have a corresponding relation. When the identity information of the livestock individuals to be detected is obtained, the identity information of the livestock individuals to be detected and the corresponding IDs can be stored in the tag, and the identity information of the livestock individuals to be detected can be obtained through equipment which can be in communication connection with the tag. The tag can be worn on the body of the livestock individual to be detected or fixed in a column where the livestock individual to be detected is located, and the identity information stored in the tag can be automatically updated along with the state of the livestock individual to be detected. The tag may in particular be a radio frequency identification (Radio Frequency Identification, RFID) tag and the device with which the tag may be communicatively connected may accordingly be an RFID reader.
According to the animal individual backfat detection method provided by the embodiment of the invention, the body ruler data of the animal individual to be detected can be automatically determined through the three-dimensional point cloud data; the backfat information of the livestock individuals to be detected can be rapidly and accurately determined through the body ruler data of the livestock individuals to be detected; in addition, identity information of the livestock individuals to be detected is also introduced, and the identity information is combined with body size data of the livestock individuals to be detected, so that the accuracy of backfat information of the livestock individuals to be detected can be further improved. The whole detection process can realize automation without manual participation, so that not only can the manpower consumption brought in the complex backfat detection process be reduced, but also the detection efficiency can be improved, and the phenomenon that the livestock and poultry generate stress response or the disease probability of the livestock and poultry is increased due to human and animal contact can be avoided. In addition, the detection process does not need to consider limiting conditions such as animal body gestures, ambient light and the like, so that the detection method can be suitable for detection of animal body backfat information in various different scenes.
On the basis of the embodiment, according to the animal backfat detection method provided by the embodiment of the invention, when point cloud data of an animal to be detected is acquired from different angles through the point cloud capturing device, a region of interest (Region of Interest, ROI) can be set up by using straight-through filtering, and then the number of sampling points can be reduced by using filtering algorithms such as voxel filtering. And the color image of the livestock individuals to be detected can be obtained while the point cloud data are obtained, and the point cloud data are combined with the color image to obtain four-dimensional data which are related to the position information and RGB color information of the livestock individuals to be detected in the three directions of x, y and z under the three-dimensional coordinate system, so that the determination of each part of the livestock individuals to be detected is conveniently realized.
The point cloud capturing device can be a movable telescopic artificial image collecting device with a depth camera, and can acquire point cloud data of an individual animal to be tested in real time. Specifically, a patrol track is arranged around the columns where the livestock individuals to be detected are located, and the point cloud capturing device can move on the patrol track. In the motion process of the point cloud capturing device, the same livestock individual to be detected can be subjected to multiple times of point cloud data acquisition at different angles through the depth camera. It should be noted that, the point cloud data of all angles of the livestock individuals to be detected need to be collected synchronously, and meanwhile, it needs to be ensured that the point cloud data of all angles can cover the whole range of the livestock individuals to be detected and that partial point cloud data overlap between the point cloud data of two adjacent angles. The depth camera can specifically adopt kinect, axon and the like.
After the point cloud data of the livestock individuals to be detected are obtained from different angles, the point cloud data of the livestock individuals to be detected under different angles can be preprocessed, specifically, a point cloud transformation matrix is firstly determined, namely, a rotation translation matrix between the point cloud data of the livestock individuals to be detected under different angles is obtained, and the point cloud transformation matrix can be a rigid transformation matrix or an European transformation matrix. Then, transforming the point cloud data under different angles to the same coordinate system through a registration algorithm; and finally, carrying out three-dimensional reconstruction by using an irregular triangular network algorithm to obtain three-dimensional point cloud data of the individual livestock to be detected, and obtaining a three-dimensional integral model of the closed individual livestock to be detected.
In order to ensure that the determined three-dimensional point cloud data show that the livestock individuals to be tested have the same orientation in space, in the embodiment of the invention, firstly, clustering operation is carried out on the three-dimensional point cloud data, a clustering center is determined as the mass center of the livestock individuals to be tested, the mass center is taken as the origin of coordinates, and a principal component analysis (Principal Compoent Analysis, PCA) method is adopted to determine the principal axis of the three-dimensional point cloud data, wherein the principal axis comprises axes in the x, y and z directions. The x direction is the direction from the origin of coordinates to the head of the individual animal to be tested, the z direction is the direction from the origin of coordinates to the vertical upwards, and the z direction is the direction perpendicular to the x direction and the y direction. The plane xoz is a vertical plane parallel to the trunk of the individual to be tested, the xoy plane is a horizontal plane, and the plane yoz is a vertical plane perpendicular to the trunk of the individual to be tested. Through the PCA method, coordinate values of all three-dimensional point cloud data can be subjected to linear transformation, so that correlation of coordinate components of all three-dimensional point cloud data in the directions of 3 principal axes is minimized, and three-dimensional point cloud data are obtained.
On the basis of the above embodiment, the method for detecting backfat of livestock individuals provided in the embodiment of the present invention, which determines body scale data of the livestock individuals to be detected based on the three-dimensional point cloud data, specifically includes:
projecting the three-dimensional point cloud data to a horizontal plane to obtain the back profile of the livestock to be tested, or respectively projecting the three-dimensional point cloud data to the horizontal plane and a vertical plane perpendicular to the trunk of the livestock to be tested to obtain the back profile and the hip profile of the livestock to be tested;
based on the back profile and/or the hip profile, a hip width in the body scale data is determined, and based on the back profile, a shoulder width, a waist width, and a chest circumference in the body scale data are determined.
Specifically, in the embodiment of the invention, when body scale data of an individual animal to be detected is determined based on three-dimensional point cloud data, the three-dimensional point cloud data can be projected downwards to a horizontal plane, namely to an xoy plane, so that a two-dimensional back projection image can be obtained. After the two-dimensional back projection image is obtained, the plane shape can be reconstructed through the point set on the back projection image, so that the outline of the two-dimensional back projection shape is extracted, and the back outline of the livestock to be detected is obtained. The three-dimensional point cloud data can be projected to the vertical plane perpendicular to the trunk of the livestock to be detected on the basis of determining the back profile, namely to the yoz plane, so that a two-dimensional buttock projection image can be obtained. After the two-dimensional buttock projection image is obtained, the plane shape can be reconstructed through the point set on the buttock projection image, so that the outline of the two-dimensional buttock projection shape is extracted, and the buttock outline of the individual livestock to be detected is obtained. Here, reconstructing the planar shape may be achieved by a concave-convex algorithm.
In the embodiment of the invention, the hip width in the body scale data of the individual to be tested can be determined according to the back profile, the hip width in the body scale data of the individual to be tested can be determined according to the hip profile, and the hip width in the body scale data of the individual to be tested can be determined by combining the back profile and the hip profile.
For example, the shoulders and buttocks of the individual to be tested can be distinguished by the contour of the back, and then the shoulder width and buttocks width can be further determined. Specifically, the back contour can be divided into four quadrants according to the x axis and the y axis, and the maximum distances from contour points at two ends of the back contour to a xoz plane in each quadrant are calculated respectively to obtain four scale key points respectively located in the four quadrants. Two of the four body rule key points are shoulder width key points, two of the four body rule key points are hip width key points, and the two shoulder width key points and the two hip width key points are respectively positioned at two ends of the back outline. Then, the curvature radius and the characteristic histogram of the point cloud data at the two ends of the back outline can be further determined, whether the curvature radius at the two ends of the back outline is smaller than a preset curvature radius or not is respectively compared, the distance between the characteristic histogram at the two ends of the back outline and the characteristic histogram of the template hip point cloud data in the characteristic space is respectively calculated, one end, close to the characteristic histogram distance of the template hip point cloud data, or one end, smaller than the preset curvature radius, corresponds to the hip, the corresponding two body ruler key points are hip width key points, and the distance between the two hip width key points is the hip width.
The maximum value and the minimum value y of the coordinates on the y axis can also be found by measuring the width between the contour points which are most protruded outwards in the buttock contour max And y min The width of the buttocks is d width ＝y max -y min . The hip widths determined based on the back contour and the hip contour, respectively, may also be compared on the basis of these, and if the difference between the two is within a preset range, both are considered to be correct, either one is selected as the hip width or the average value of both is selected as the hip width.
The shoulder width, waist width and chest circumference in the body ruler data of the livestock individuals to be tested can be determined specifically through the back outline of the livestock individuals to be tested, for example, after the buttocks and the buttocks width are determined through the back outline, the shoulder and the shoulder width can be determined; the distance between two contour points near the y axis and farthest from the origin of coordinates in the back contour can be used as the waist width; because the shoulder width can be equivalent to the chest width, the circumference of the tangent plane outline of the three-dimensional point cloud data formed by the chest width in the vertical plane is the chest circumference under the condition of determining the chest width.
In addition, after the back contour and/or the hip contour are determined, a first center point between the two shoulder width key points and a second center point between the two hip width key points can be obtained, wherein the first center point and the second center point are two long key points, and the distance between the two long key points is the body length. The back contour and the hip contour area can also be calculated respectively, and the back area and the hip area in the body ruler data can be obtained respectively.
In the embodiment of the invention, the back contour of the livestock to be detected or the buttock contour is combined, the buttock width, the shoulder width, the waist width and the chest circumference in the body ruler data are determined, the accuracy of the body ruler data can be ensured by means of the three-dimensional point cloud data, the accuracy of backfat detection results is further ensured, and higher requirements on environment or light are not needed.
Based on the above embodiments, in the method for detecting backfat of an individual animal provided in the embodiments of the present invention, the radius of curvature of each end of the backface profile may be specifically determined by the following method: and at the two body rule key points of the end, reserving points larger than the z coordinates of the two body rule key points, discarding the points with the z coordinates smaller than the z coordinates of the two body rule key points, performing polynomial fitting by using a curve fitting algorithm, and calculating to obtain the curvature radius according to the fitted curve.
On the basis of the above embodiment, the method for detecting backfat of an individual animal provided in the embodiment of the present invention, wherein the step of determining the shoulder width, the waist width and the chest circumference in the body ruler data based on the backface profile specifically includes:
determining two shoulder width key points and two waist width key points in the back profile, determining the shoulder width based on the two shoulder width key points, and determining the waist width based on the two waist width key points;
Determining chest contours of the to-be-tested livestock individuals based on the three-dimensional point cloud data and a vertical plane containing the two shoulder width key points;
and determining the chest circumference of the livestock individual to be tested based on the chest outline.
Specifically, in the embodiment of the invention, after two hip width key points are determined through the back outline, the other end of the back outline opposite to the two hip width key points is a shoulder, the corresponding two body ruler key points are shoulder width key points, and the distance between the two shoulder width key points is the shoulder width.
The back contour is divided into two parts according to positive and negative values of the y axis, namely the back contour is divided into two parts by taking the x axis as an axis, the distances from contour points close to the center point in the two parts to the yoz plane are respectively calculated, and two contour points with the minimum distances in the two parts are found and are respectively waist width key points. The distance between two key points of waist width is the waist width.
Under the condition that the chest width is determined to be the shoulder width, the line segment between the two shoulder width key points can be equivalent to the chest width line segment, a plane perpendicular to the horizontal plane is made by using a slicing method to pass the chest width line segment, and then a vertical plane containing the two shoulder width key points is obtained, and the outline formed by the vertical plane and the three-dimensional point cloud data is the chest outline of the individual livestock to be tested. The circumference of the chest outline is the chest circumference of the individual to be tested.
In the embodiment of the invention, the back contour is adopted, the shoulder width and the waist width are determined by determining the shoulder width key points and the waist width key points, the chest circumference is determined by combining a slicing method, and the accuracy of body size data can be ensured by means of three-dimensional point cloud data, so that the accuracy of backfat detection results is ensured, and high requirements on environment or light are not needed.
Based on the embodiment, the animal backfat detection method provided by the embodiment of the invention can also determine the height, waist circumference, chest depth and the like in the body scale data of the animal to be detected through the three-dimensional point cloud data.
Specifically, the height in the body ruler data refers to the vertical distance from the highest position of the hip joint and the hip of the individual to be tested to the ground. In the embodiment of the invention, the coordinate value of the z-axis can be determined firstlyThe large point coordinates are the highest point z of the buttocks max The point coordinate with the smallest coordinate value on the z-axis is a point z on the ground min The height calculation formula is D tall ＝z max -z min 。
Further, the posture in the body ruler data of the individual to be tested can be determined according to the height. When the height D tall When the height threshold value is larger than the height threshold value, the individual of the livestock to be tested can be judged to be in a standing posture, and when the height D is the height tall When the height threshold value is smaller than the height threshold value, the animal to be tested can be judged to be in a lying posture.
The waistline in the body size data can be specifically determined by the following method: and determining a waist width line segment between two waist width key points in the back profile, then using a slicing method to make a vertical plane perpendicular to a horizontal plane through the waist width line segment, thereby obtaining the waist profile, and calculating the circumference of the waist profile, namely the waistline.
The chest depth in the body ruler data can be determined specifically by the following method: taking the maximum value and the minimum value of the z coordinate in the chest outline, and obtaining the difference value of the maximum value and the minimum value as the chest depth.
In the embodiment of the invention, the body ruler data is supplemented, so that the body ruler data is more complete, and further, the factors considered when backfat information is detected through the body ruler data are more comprehensive, and the detection result is more accurate.
On the basis of the embodiment, since actions such as twisting the head and bending the body of the livestock individuals to be detected can have certain influence on the finally detected backfat information, the livestock individual backfat detection method provided by the embodiment of the invention can also carry out symmetry detection on the livestock individuals to be detected on the basis of obtaining the shoulder profile so as to determine whether the actions such as twisting the head and bending the body of the livestock individuals to be detected occur when the point cloud data are acquired. The symmetry of the livestock individuals to be detected can also be used as a part of body ruler data and used as a consideration factor for subsequently detecting backfat information, so that the symmetry of the livestock individuals to be detected is considered when backfat information is detected, and the accuracy of a detection result is ensured. The symmetry detection assumes that one point exists on one side of the symmetry plane, and one point also exists on the other side of the symmetry plane, the distances between the two points and the symmetry plane are equal, the distance difference is 0, and the connecting line of the two points is perpendicular to the symmetry plane. In the embodiment of the invention, the symmetrical plane is a xoz plane, the back contour is divided into two parts according to the xoz plane, the sum of the distances from all contour points of the two parts to the xoz plane is calculated respectively, and if the difference of the distances between the two parts is smaller than a distance threshold value, the back contour is symmetrical.
In the embodiment of the invention, symmetry detection is carried out on the individual livestock to be detected, the obtained symmetry is used as a part of body ruler data, and backfat information can be detected under the condition of considering the factors without collecting posture information of the individual livestock to be detected, so that the workload of a data preparation stage is reduced, and the accuracy of a detection result is ensured.
On the basis of the foregoing embodiments, the method for detecting backfat of an animal in the embodiment of the present invention determines backfat information of the animal to be detected based on body scale data of the animal to be detected or based on body scale data of the animal to be detected and identity information of the animal to be detected, and specifically includes:
inputting the body ruler data or the body ruler data and the identity information into a backfat detection model to obtain backfat information output by the backfat detection model;
the backfat detection model is obtained based on body size data of sample livestock individuals carrying backfat information labels or based on body size data training of sample livestock individuals carrying backfat information labels and identity information labels.
Specifically, when determining backfat information of an individual animal to be tested, the backfat detection model can be adopted, and the backfat detection model can have two types of input, wherein the first type of input is body ruler data, and the second type of input is body ruler data and identity information. The backfat detection model can output backfat information no matter what kind of input. The backfat detection model may specifically be a machine learning model, such as: linear regression, random forests, xgboost, etc. For the first type of input, the backfat detection model can be obtained through body scale data training of sample livestock individuals carrying backfat information labels. After the body ruler data are input into the backfat detection model, the backfat detection model can determine identity information of the livestock individuals to be detected through the body ruler data, and then the backfat information is detected by combining the identity information and the body ruler information. For the second type of input, the backfat detection model can be obtained through body size data training of sample livestock individuals carrying backfat information labels and identity information labels.
In the embodiment of the invention, the backfat detection model is introduced to realize the detection of backfat information, so that the detection process is simplified, and the detection efficiency and accuracy can be improved.
On the basis of the embodiment, in the backfat detection method for the livestock individuals provided by the embodiment of the invention, the backfat detection model comprises a plurality of backfat detection layers corresponding to different identity information;
correspondingly, the step of inputting the body size data into a backfat detection model to obtain backfat information output by the backfat detection model specifically comprises the following steps:
and inputting the body size data to a backfat detection layer corresponding to the identity information in the backfat detection model to obtain backfat information output by the backfat detection layer corresponding to the identity information.
Specifically, since there is a difference in correspondence between size data and backfat information of livestock individuals to be tested having different identity information, backfat detection layers for detecting backfat information are respectively constructed for the livestock individuals having different identity information in the embodiment of the invention, each backfat detection layer corresponds to one identity information, and the backfat detection model includes all backfat detection layers.
When the body scale data of the livestock individuals to be detected are input into the backfat detection model, specifically, the body scale data of the livestock individuals to be detected are input into the backfat detection layer corresponding to the identity information of the livestock individuals to be detected, and the backfat detection layer detects and outputs the backfat information of the livestock individuals to be detected. As a preferred scheme, the identity information in the embodiment of the invention can be a variety, a growth stage and the like, namely, the backfat detection layer can be corresponding to the variety of the individual livestock, the growth stage of the individual livestock or the different growth stages of different varieties. The growth stage may be a unit of month or a unit of ten days, which is not particularly limited in the embodiment of the present invention.
When each backfat detection layer is trained, the body rule data of a sample animal with certain identity information is taken as an independent variable, backfat information of the sample animal is taken as an independent variable, a plurality of models are used for training, and then a model structure and parameters with the minimum detection error are selected as layer structures and layer parameters of the backfat detection layer corresponding to the identity information.
In the embodiment of the invention, the backfat detection model is divided into a plurality of backfat detection layers corresponding to the identity information, and the backfat information of the livestock individuals to be detected is detected through the backfat detection layers corresponding to the identity information of the livestock individuals to be detected, so that the backfat detection error can be effectively reduced, and the backfat detection accuracy is provided.
On the basis of the foregoing embodiment, in the method for detecting backfat of an individual animal provided in the embodiment of the present invention, the inputting the body size data to the backfat detection layer corresponding to the identity information in the backfat detection model, to obtain the backfat information output by the backfat detection layer corresponding to the identity information, includes:
and inputting the body ruler data to an identity classification layer in the backfat detection model to obtain the identity information output by the identity classification layer.
Specifically, in the embodiment of the invention, the identity information of the livestock individuals to be detected can be specifically obtained by automatically classifying backfat detection models through input body size data. When the identity information of the livestock individuals to be detected is obtained through automatic classification of the backfat detection model, the backfat detection model can also comprise an identity classification layer for determining the identity information of the livestock individuals to be detected according to the input body size data of the livestock individuals to be detected.
The identity classification layer may be constructed based on a generalized linear model, a classification tree, or the like model. When the identity classification layer is trained, the body ruler data of the sample animal individuals are used as independent variables, the identity information of the sample animal individuals are used as dependent variables, a plurality of models are used for training, and then the model structure and parameters with the minimum classification errors are selected as the layer structure and layer parameters of the identity classification layer.
In the embodiment of the invention, the identity information of the driving processing individual can be automatically classified and acquired through the identity classification layer in the backfat detection model, so that the inconvenience of manually acquiring the identity information can be avoided, and the automaticity and convenience of acquiring the identity information are improved.
On the basis of the foregoing embodiments, the method for detecting backfat of an animal in the embodiment of the present invention determines backfat information of the animal to be detected based on body scale data of the animal to be detected or based on body scale data of the animal to be detected and identity information of the animal to be detected, and specifically includes:
and if the body ruler data is in a preset general body ruler data interval, determining the backfat information based on the body ruler data or based on the body ruler data and the identity information.
Specifically, in the embodiment of the invention, after the body ruler data of the livestock individuals to be detected are determined, the usability of the body ruler data can be judged, namely whether the calculated body ruler data are accurate or not can be judged by combining the body ruler data of the livestock individuals under the normal condition.
Judging whether the body ruler data of the livestock individuals to be tested are in a preset general body ruler data interval, if so, indicating that the body ruler data are accurately available, and determining backfat information according to the body ruler data or the body ruler data and combining identity information. Otherwise, if the position is not found, the problem that the body size data is possibly missing due to acquisition or equipment conditions and the like is described, and the availability is further unavailable, and backfat information cannot be determined continuously according to the body size data or according to the body size data and combining identity information. And subsequently, the body ruler data can be re-acquired and judged. The universal body rule data interval may be an interval range determined by body rule data of a large number of livestock individuals under normal conditions, for example, the shoulder width in the body rule data may correspond to a universal shoulder width interval.
In the embodiment of the invention, the availability judgment is carried out on the obtained body size data so as to ensure that backfat information can be successfully detected and the high accuracy of the detection result is ensured.
Fig. 2 is a schematic structural diagram of a backfat detection device for livestock individuals according to an embodiment of the present invention, as shown in fig. 2, the backfat detection device for livestock individuals includes: a body size data determination module 21 and a backfat information determination module 22. Wherein, the liquid crystal display device comprises a liquid crystal display device,
the body ruler data determining module 21 is used for determining three-dimensional point cloud data of an individual to be tested, and determining body ruler data of the individual to be tested based on the three-dimensional point cloud data;
the backfat information determining module 22 is configured to determine backfat information of the individual to be tested based on the body scale data of the individual to be tested, or based on the body scale data of the individual to be tested and identity information of the individual to be tested.
Specifically, the functions of each module in the animal individual backfat detection device provided in the embodiment of the present invention are in one-to-one correspondence with the operation flow of each step in the above method embodiment, and the achieved effects are consistent.
On the basis of the above embodiment, the animal backfat detection device provided in the embodiment of the present invention, the body ruler data determining module is specifically configured to:
projecting the three-dimensional point cloud data to a horizontal plane to obtain the back profile of the livestock to be tested, or respectively projecting the three-dimensional point cloud data to the horizontal plane and a vertical plane perpendicular to the trunk of the livestock to be tested to obtain the back profile and the hip profile of the livestock to be tested;
based on the back profile and/or the hip profile, a hip width in the body scale data is determined, and based on the back profile, a shoulder width, a waist width, and a chest circumference in the body scale data are determined.
On the basis of the above embodiment, the animal backfat detection device provided in the embodiment of the present invention, the body ruler data determining module is specifically configured to:
determining two shoulder width key points and two waist width key points in the back profile, determining the shoulder width based on the two shoulder width key points, and determining the waist width based on the two waist width key points;
determining chest contours of the to-be-tested livestock individuals based on the three-dimensional point cloud data and a vertical plane containing the two shoulder width key points;
And determining the chest circumference of the livestock individual to be tested based on the chest outline.
On the basis of the foregoing embodiments, the backfat information determining module is specifically configured to:
inputting the body ruler data or the body ruler data and the identity information into a backfat detection model to obtain backfat information output by the backfat detection model;
the backfat detection model is obtained based on body size data of sample livestock individuals carrying backfat information labels or based on body size data training of sample livestock individuals carrying backfat information labels and identity information labels.
On the basis of the embodiment, the backfat detection device for the livestock individuals provided by the embodiment of the invention comprises a plurality of backfat detection layers corresponding to different identity information in a backfat detection model;
correspondingly, the backfat information determining module is specifically configured to:
and inputting the body size data to a backfat detection layer corresponding to the identity information in the backfat detection model to obtain backfat information output by the backfat detection layer corresponding to the identity information.
On the basis of the above embodiment, the backfat detection device for livestock individuals provided in the embodiment of the present invention further includes: an identity classification layer;
Correspondingly, the backfat information determining module is specifically configured to: and inputting the body ruler data to an identity classification layer in the backfat detection model to obtain the identity information output by the identity classification layer.
On the basis of the foregoing embodiments, the backfat information determining module is specifically configured to:
and if the body ruler data is in a preset general body ruler data interval, determining the backfat information based on the body ruler data or based on the body ruler data and the identity information.
Fig. 3 illustrates a physical schematic diagram of an electronic device, as shown in fig. 3, where the electronic device may include: processor 310, communication interface (Communications Interface) 320, memory 330 and communication bus 340, wherein processor 310, communication interface 320, memory 330 accomplish communication with each other through communication bus 340. Processor 310 may invoke logic instructions in memory 330 to perform a stock individual backfat detection method comprising: determining three-dimensional point cloud data of an individual to be tested, and determining body scale data of the individual to be tested based on the three-dimensional point cloud data; and determining backfat information of the livestock individuals to be tested based on the body ruler data of the livestock individuals to be tested or based on the body ruler data of the livestock individuals to be tested and the identity information of the livestock individuals to be tested.
Further, the logic instructions in the memory 330 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, an embodiment of the present invention further provides a computer program product, including a computer program stored on a non-transitory computer readable storage medium, the computer program including program instructions, which when executed by a computer, are capable of executing the animal backfat detection method provided in the above method embodiments, including: determining three-dimensional point cloud data of an individual to be tested, and determining body scale data of the individual to be tested based on the three-dimensional point cloud data; and determining backfat information of the livestock individuals to be tested based on the body ruler data of the livestock individuals to be tested or based on the body ruler data of the livestock individuals to be tested and the identity information of the livestock individuals to be tested.
In still another aspect, an embodiment of the present invention further provides a non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor is implemented to perform the method for detecting backfat of an individual animal provided in the above embodiments, including: determining three-dimensional point cloud data of an individual to be tested, and determining body scale data of the individual to be tested based on the three-dimensional point cloud data; and determining backfat information of the livestock individuals to be tested based on the body ruler data of the livestock individuals to be tested or based on the body ruler data of the livestock individuals to be tested and the identity information of the livestock individuals to be tested.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. A method for detecting backfat of an individual animal, comprising:
determining three-dimensional point cloud data of an individual to be tested, and determining body scale data of the individual to be tested based on the three-dimensional point cloud data;
determining backfat information of the livestock individuals to be tested based on body ruler data of the livestock individuals to be tested and identity information of the livestock individuals to be tested; the identity information comprises the variety and growth stage of the individual livestock to be detected;
the determining the backfat information of the to-be-detected livestock individuals based on the body ruler data of the to-be-detected livestock individuals and the identity information of the to-be-detected livestock individuals specifically comprises the following steps:
inputting the body ruler data to an identity classification layer in a backfat detection model to obtain the identity information output by the identity classification layer;
inputting the body size data to a backfat detection layer corresponding to the identity information in the backfat detection model to obtain backfat information output by the backfat detection layer corresponding to the identity information;
the backfat detection model is obtained based on body size data training of sample livestock individuals carrying backfat information labels and identity information labels.
2. The method for detecting backfat of livestock individuals according to claim 1, wherein determining body size data of the livestock individuals to be detected based on the three-dimensional point cloud data specifically comprises:
Projecting the three-dimensional point cloud data to a horizontal plane to obtain the back profile of the livestock to be tested, or respectively projecting the three-dimensional point cloud data to the horizontal plane and a vertical plane perpendicular to the trunk of the livestock to be tested to obtain the back profile and the hip profile of the livestock to be tested;
based on the back profile and/or the hip profile, a hip width in the body scale data is determined, and based on the back profile, a shoulder width, a waist width, and a chest circumference in the body scale data are determined.
3. The method for detecting backfat of individual animals according to claim 2, wherein said determining shoulder width, waist width and chest circumference in said body size data based on said back profile comprises:
determining two shoulder width key points and two waist width key points in the back profile, determining the shoulder width based on the two shoulder width key points, and determining the waist width based on the two waist width key points;
determining chest contours of the to-be-tested livestock individuals based on the three-dimensional point cloud data and a vertical plane containing the two shoulder width key points;
and determining the chest circumference of the livestock individual to be tested based on the chest outline.
4. A method of backfat detection of livestock individuals as claimed in claim 1 wherein the backfat detection model includes a plurality of backfat detection layers corresponding to different identity information.
5. A method for backfat detection of livestock individuals according to any of claims 1-4, wherein the determining backfat information of the livestock individuals to be detected based on body size data of the livestock individuals to be detected and identity information of the livestock individuals to be detected specifically comprises:
and if the body ruler data is in a preset general body ruler data interval, determining the backfat information based on the body ruler data and the identity information.
6. A backfat detection device for livestock individuals, comprising:
the body ruler data determining module is used for determining three-dimensional point cloud data of the livestock individuals to be detected and determining the body ruler data of the livestock individuals to be detected based on the three-dimensional point cloud data;
the backfat information determining module is used for determining backfat information of the livestock individuals to be detected based on body ruler data of the livestock individuals to be detected and identity information of the livestock individuals to be detected; the identity information comprises the variety and growth stage of the individual livestock to be detected;
The backfat information determining module is specifically configured to:
inputting the body ruler data to an identity classification layer in a backfat detection model to obtain the identity information output by the identity classification layer;
inputting the body size data to a backfat detection layer corresponding to the identity information in the backfat detection model to obtain backfat information output by the backfat detection layer corresponding to the identity information;
the backfat detection model is obtained based on body size data training of sample livestock individuals carrying backfat information labels and identity information labels.
7. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor performs the steps of the method for detecting backfat of an individual animal as claimed in any one of claims 1 to 5 when the program is executed.
8. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor performs the steps of the method for backfat detection of an individual animal as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011232362.5A CN112288793B (en) | 2020-11-06 | 2020-11-06 | Method and device for detecting backfat of livestock individuals, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011232362.5A CN112288793B (en) | 2020-11-06 | 2020-11-06 | Method and device for detecting backfat of livestock individuals, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112288793A CN112288793A (en) | 2021-01-29 |
| CN112288793B true CN112288793B (en) | 2023-05-26 |
Family
ID=74351690
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011232362.5A Active CN112288793B (en) | 2020-11-06 | 2020-11-06 | Method and device for detecting backfat of livestock individuals, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112288793B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113124802A (en) * | 2021-03-30 | 2021-07-16 | 章瀚文 | Method and device for rapidly measuring shin circumference of poultry |
| CN114051973A (en) * | 2022-01-17 | 2022-02-18 | 北京探感科技股份有限公司 | Intelligent feeding method, device and system based on visual animal body ruler |
| CN116363141B (en) * | 2023-06-02 | 2023-08-18 | 四川省畜牧科学研究院 | Pregnant sow intelligent body type evaluation device and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108733751A (en) * | 2018-04-09 | 2018-11-02 | 广东温氏食品集团股份有限公司 | Fat information monitoring system and method are surveyed in a kind of pig farm |
| CN111353416A (en) * | 2020-02-26 | 2020-06-30 | 广东温氏种猪科技有限公司 | Posture detection method, system and storage medium based on livestock three-dimensional measurement |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203206909U (en) * | 2013-05-09 | 2013-09-25 | 中国农业大学 | Data acquisition device and pig growth form detection system using same |
| US10489643B2 (en) * | 2016-12-30 | 2019-11-26 | Morphotrust Usa, Llc | Identity document validation using biometric image data |
| CN108416003B (en) * | 2018-02-27 | 2021-12-21 | 百度在线网络技术（北京）有限公司 | Picture classification method and device, terminal and storage medium |
| CN110837768B (en) * | 2018-08-16 | 2023-06-20 | 武汉大学 | Online detection and identification method for rare animal protection |
| US11564634B2 (en) * | 2019-03-27 | 2023-01-31 | Panasonic Intellectual Property Management Co., Ltd. | Determining health state of individuals |
| CN110986788B (en) * | 2019-11-15 | 2020-10-23 | 华南农业大学 | Automatic measurement method based on three-dimensional point cloud livestock phenotype body size data |
| CN110754426B (en) * | 2019-11-28 | 2022-01-07 | 深圳市慧农科技有限公司 | Method and system for automatically detecting backfat body and automatically feeding animals |
| CN111243005B (en) * | 2020-01-07 | 2023-05-23 | 洛阳语音云创新研究院 | Livestock weight estimation method, apparatus, device and computer readable storage medium |
-
2020
- 2020-11-06 CN CN202011232362.5A patent/CN112288793B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108733751A (en) * | 2018-04-09 | 2018-11-02 | 广东温氏食品集团股份有限公司 | Fat information monitoring system and method are surveyed in a kind of pig farm |
| CN111353416A (en) * | 2020-02-26 | 2020-06-30 | 广东温氏种猪科技有限公司 | Posture detection method, system and storage medium based on livestock three-dimensional measurement |
Non-Patent Citations (1)
| Title |
|---|
| Martin Engelcke et.al.Vote3Deep: Fast Object Detection in 3D Point Clouds Using Efficient Convolutional Neural Networks.《arXiv:1609.06666v2 [cs.RO]》.2017,第1-7页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112288793A (en) | 2021-01-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112288793B (en) | Method and device for detecting backfat of livestock individuals, electronic equipment and storage medium | |
| Qiao et al. | Intelligent perception for cattle monitoring: A review for cattle identification, body condition score evaluation, and weight estimation | |
| Wang et al. | ASAS-NANP SYMPOSIUM: Applications of machine learning for livestock body weight prediction from digital images | |
| CN107635509B (en) | Improved method for determining body condition score, body weight and fertility status and related device | |
| CN111243005B (en) | Livestock weight estimation method, apparatus, device and computer readable storage medium | |
| CA2949768C (en) | Non-invasive multimodal biometrical identification system of animals | |
| JP4128791B2 (en) | Sexual differentiation technology for sperm eggs | |
| Zhang et al. | Algorithm of sheep body dimension measurement and its applications based on image analysis | |
| Jia et al. | Segmentation of body parts of cows in RGB-depth images based on template matching | |
| Tscharke et al. | Review of methods to determine weight and size of livestock from images | |
| Lu et al. | Extracting body surface dimensions from top-view images of pigs | |
| Li et al. | A posture-based measurement adjustment method for improving the accuracy of beef cattle body size measurement based on point cloud data | |
| Ling et al. | Point cloud-based pig body size measurement featured by standard and non-standard postures | |
| CN110414369B (en) | Cow face training method and device | |
| Burke et al. | An analysis of the feasibility of using image processing to estimate the live weight of sheep | |
| Weales et al. | A robust machine vision system for body measurements of beef calves | |
| WO2023034834A1 (en) | Artificial intelligence and vision-based broiler body weight measurement system and process | |
| Wu et al. | Body condition score for dairy cows method based on vision transformer | |
| CN113762745A (en) | Live pig body shape assessment method and device based on machine vision | |
| Yuan et al. | Stress-free detection technologies for pig growth based on welfare farming: A review | |
| Li et al. | Extraction of key regions of beef cattle based on bidirectional tomographic slice features from point cloud data | |
| Ai et al. | SOLOv2-based multi-view contactless bovine body size measurement | |
| CN113221704A (en) | Animal posture recognition method and system based on deep learning and storage medium | |
| Thomas et al. | The use of image data in the assessment of equine conformation-“limitations and solutions” | |
| EP3606349A1 (en) | Method and system for classifying animal carcass |
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 |