EP3606349A1 - Procédé et système de classification d'une carcasse d'animal - Google Patents

Procédé et système de classification d'une carcasse d'animal

Info

Publication number
EP3606349A1
EP3606349A1 EP18723081.8A EP18723081A EP3606349A1 EP 3606349 A1 EP3606349 A1 EP 3606349A1 EP 18723081 A EP18723081 A EP 18723081A EP 3606349 A1 EP3606349 A1 EP 3606349A1
Authority
EP
European Patent Office
Prior art keywords
animal
animal carcass
image
carcass
operable
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.)
Withdrawn
Application number
EP18723081.8A
Other languages
German (de)
English (en)
Inventor
Ove KONRADSSON
Per EKE-GÖRANSSON
Matts LILJA
Helena BJÖRK
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Smart Agritech Solution Of Sweden AB
Original Assignee
Smart Agritech Solution Of Sweden AB
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Smart Agritech Solution Of Sweden AB filed Critical Smart Agritech Solution Of Sweden AB
Publication of EP3606349A1 publication Critical patent/EP3606349A1/fr
Withdrawn legal-status Critical Current

Links

Classifications

    • A—HUMAN NECESSITIES
    • A22—BUTCHERING; MEAT TREATMENT; PROCESSING POULTRY OR FISH
    • A22B—SLAUGHTERING
    • A22B5/00—Accessories for use during or after slaughtering
    • A22B5/0064—Accessories for use during or after slaughtering for classifying or grading carcasses; for measuring back fat
    • A—HUMAN NECESSITIES
    • A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
    • A01K29/00—Other apparatus for animal husbandry
    • A—HUMAN NECESSITIES
    • A22—BUTCHERING; MEAT TREATMENT; PROCESSING POULTRY OR FISH
    • A22B—SLAUGHTERING
    • A22B5/00—Accessories for use during or after slaughtering
    • A22B5/0064—Accessories for use during or after slaughtering for classifying or grading carcasses; for measuring back fat
    • A22B5/007—Non-invasive scanning of carcasses, e.g. using image recognition, tomography, X-rays, ultrasound
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/02—Food
    • G01N33/12—Meat; Fish
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30128—Food products

Definitions

  • the present disclosure relates generally to livestock farming; and more specifically, to a method and system for classifying an animal carcass.
  • animal farmers are raising large numbers of animals for providing commodities such as meat, fibre, and so forth, for use by humans. Therefore, the animals are raised and eventually slaughtered to provide such commodities. Specifically, the animals are slaughtered into animal carcasses.
  • factors such as age of an animal, environment in which the animal was raised, diet of the animal, breed of the animal, and so forth, influence quality of carcass of the animal. Therefore, the animal carcasses need to be correctly analysed to ensure quality and correct pricing of animal products associated therewith.
  • the present disclosure seeks to provide a method for classifying an animal carcass.
  • the present disclosure also seeks to provide a system for classifying an animal carcass.
  • an embodiment of the present disclosure provides a method for classifying an animal carcass, the method comprising:
  • the method comprises tagging the animal carcass to assist classification thereof by attaching a tag to the animal carcass, the tag comprising information associated with the animal.
  • the method further comprises detecting the tag, using the at least one imaging device.
  • the animal carcass is cut longitudinally and/or transversally.
  • the method comprises processing a captured at least a pair of images to form at least one three-dimensional image, using a computing device. More optionally, the method further comprises sending the at least one three-dimensional image to the server arrangement.
  • the classification system is one of: European Union EUROP grid classification system, United States Department of Agriculture grading system, South African Meat Industry Company meat classification system.
  • the method comprises associating the information in the tag with the determined class of the animal carcass.
  • the method further comprises receiving the determined class of the animal carcass from the server arrangement.
  • the method further comprises capturing at least one image of an animal prior to slaughtering of the animal, for identifying the information associated with the animal.
  • identifying the information associated with the animal comprises processing the captured at least one image of the animal.
  • an embodiment of the present disclosure provides a system for classifying an animal carcass, the system comprising: - at least one imaging device operable to capture at least one image of the animal carcass; and
  • a server arrangement communicably coupled to the at least one imaging device via a network, the server arrangement operable to receive and process the captured at least one image to determine a class of the animal carcass
  • server arrangement is operable to compare the captured at least one image with a pre-defined template of a classification system to determine grades corresponding to different attributes of animal carcass wherein the class of the animal carcass is determined by combining grades corresponding to different attributes of animal carcass.
  • the system further comprises a tag attached to the animal carcass, the tag comprising information associated with the animal. More optionally, the at least one imaging device is operable to detect the tag.
  • the system comprises a computing device communicably coupled to the at least one imaging device and the server arrangement.
  • the computing device is operable to:
  • the at least one imaging device comprises: a three- dimensional camera or at least one two-dimensional camera.
  • the at least one two-dimensional camera is operable to capture at least a pair of images of the animal carcass
  • the computing device is operable to process the captured at least the pair of images to form at least one three-dimensional image.
  • the computing device is further operable to send the at least one three-dimensional image to the server arrangement.
  • the classification system is one of: European Union EUROP grid classification system, United States Department of Agriculture grading system or South African Meat Industry Company meat classification system.
  • the server arrangement comprises a database for storing the pre-defined template of the classification system and information in the tag associated with the animal.
  • the computing device is operable to associate the information in the tag with the determined class of the animal carcass.
  • the computing device is operable to receive the determined class of the animal carcass from the server arrangement.
  • the at least one imaging device is operable to capture at least one image of an animal prior to slaughtering of the animal for identifying information associated with the animal.
  • the server arrangement is operable to process the captured at least one image of the animal for identifying the information associated with the animal.
  • the at least one imaging device is handheld by an operator and/or mounted on a slaughter line.
  • the present disclosure provides a method and system for classifying an animal carcass.
  • the described method and system are easy to implement and are time-efficient. Further, the described method is free from errors introduced by manual inspection techniques, and is therefore highly accurate and reliable. Consequently, the described method and system may be used to identify deformations or birth defects in the animal carcass. Optionally, detailed estimations of amount of fat and muscle in the animal carcass may be identified and utilised to correctly price the animal carcass for benefitting animal farmers. Additional aspects, advantages, features and objects of the present disclosure would be made apparent from the drawings and the detailed description of the illustrative embodiments construed in conjunction with the appended claims that follow.
  • FIGs. 1-2 are schematic illustrations of exemplary systems for classifying an animal carcass, in accordance with different embodiments of the present disclosure
  • FIGs. 3-4 are schematic illustrations of an animal carcass, in accordance with different embodiments of the present disclosure.
  • FIG. 5 illustrates steps of a method for classifying an animal carcass, in accordance with an embodiment of the present disclosure.
  • an underlined number is employed to represent an item over which the underlined number is positioned or an item to which the underlined number is adjacent.
  • a non-underlined number relates to an item identified by a line linking the non-underlined number to the item. When a number is non-underlined and accompanied by an associated arrow, the non-underlined number is used to identify a general item at which the arrow is pointing.
  • an embodiment of the present disclosure provides a method for classifying an animal carcass, the method comprising:
  • an embodiment of the present disclosure provides a system for classifying an animal carcass, the system comprising:
  • At least one imaging device operable to capture at least one image of the animal carcass
  • a server arrangement communicably coupled to the at least one imaging device via a network, the server arrangement operable to receive and process the captured at least one image to determine a class of the animal carcass
  • the server arrangement is operable to compare the captured at least one image with a pre-defined template of a classification system to determine grades corresponding to different attributes of animal carcass wherein the class of the animal carcass is determined by combining grades corresponding to different attributes of animal carcass.
  • the term 'animal' used herein refers to domestic animals reared to provide resources for human consumption. Specifically, the animal may be reared by animal farmers to provide resources such as meat, skin, wool, and so forth. In an example, the animals may include cattle, pigs, chickens, goats, sheep, and so forth. Optionally, the term 'animal' may include wild animals that may provide resources useful for human consumption.
  • the term 'animal carcass' used herein refers to a body of the animal.
  • the animal carcass may exclude undesirable parts of body of the animal. Therefore, the body of the animal may be processed to remove such undesirable parts to yield the animal carcass.
  • the undesirable parts of the body of the animal may relate to organs or parts that are exposed to the external environment and/or do not have any commercial utility for human consumption.
  • the undesirable parts may include head and feet of the animal.
  • the processing of the animal to yield the animal carcass may include removal of inedible organs, skin, and blood from the body of the animal.
  • the animal carcass may be cleaned and subjected to cold temperatures to prevent growth of micro-organisms thereon.
  • the method for classifying the animal carcass comprises capturing at least one image of the animal carcass, using at least one imaging device.
  • the at least one image of the animal carcass may be captured from different angles with respect to the animal carcass, using the at least one imaging device. More specifically, the at least one image may be captured so as to capture vital features of the animal carcass. Further, the at least one imaging device may be strategically positioned to capture different aspects of the animal carcass from different perspectives.
  • the system for classifying an animal carcass comprises at least one imaging device operable to capture at least one image of the animal carcass.
  • the at least one imaging device may comprise a three-dimensional camera or at least one two-dimensional camera.
  • the three-dimensional camera may capture at least one three-dimensional image of the animal carcass
  • the at least one two-dimensional camera may capture at least one two- dimensional image of the animal carcass.
  • the three-dimensional camera may be a stereo camera. Further the at least one three-dimensional image captured using the three-dimensional camera may provide an estimation of geometry of the animal carcass. Furthermore, the at least one three- dimensional image may assist in identifying any deformation or birth defects in the animal carcass.
  • the at least one two-dimensional camera is operable to capture at least a pair of images of the animal carcass.
  • the captured at least a pair of images may be captured from distinct perspectives and may be utilized to form a three-dimensional image of the animal carcass.
  • the system may include one two- dimensional camera.
  • the two-dimensional camera may capture the at least a pair of images of the animal carcass sequentially. It is to be understood that position of the animal carcass may be fixed during a time period of capturing the at least a pair of images. In such instance, the two-dimensional camera may be moved from a first position to a second position with respect to the animal carcass, to capture the at least a pair of images thereof.
  • At least a pair of two-dimensional images may be captured from different angles such that at least a pair of two-dimensional images shares a set of coincident pixels. Therefore, at least a pair of two-dimensional images may be processed to obtain at least one three-dimensional image using the shared set of coincident pixels.
  • the system may include at least two two- dimensional cameras.
  • the at least two two-dimensional cameras may be placed in a mutually-spaced apart configuration proximate to a slaughter line whereat the animal carcass may be positioned.
  • the at least two two-dimensional cameras may be placed in the mutually-spaced configuration such that the at least a pair of images captured by the at least two two-dimensional cameras shares a set of coincident pixels.
  • the at least a pair of images may be processed to obtain at least one three-dimensional image using the shared set of coincident pixels.
  • the at least a pair of two-dimensional images of the animal carcass may be captured simultaneously by externally synchronizing the at least two two-dimensional cameras.
  • two-dimensional cameras include, but are not limited to, digital cameras, smart-phone cameras, tablet cameras, action cameras and magnetic resonance imaging (MRI) cameras.
  • the at least one image of the animal carcass captured by the at least one two-dimensional camera such as a magnetic resonance imaging (MRI) camera, may provide an estimation of fat and muscle content, degree of marbling and bone structure of the animal carcass.
  • the animal carcass may be cut longitudinally and/or transversally. Further, the animal carcass may be cut to obtain at least one longitudinal and/or transversal sections of the animal carcass thereof. Therefore, the at least one imaging device may capture at least one image of each of the at least one longitudinal and/or transverse sections of the animal carcass.
  • the at least one imaging device may be handheld by an operator and/or mounted on the slaughter line.
  • the at least one imaging device may be mounted on the slaughter line at a pre-determined distance from the animal carcass.
  • the pre- determined distance may be in a range of 3 to 5 meters. More specifically, the pre-determined distance may be 3 meters, 3.5 meters, 4 meters, 4.5 meters, and so forth.
  • the at least one imaging device may be handheld by the operator to capture the at least one image of the animal carcass. The method further comprises sending the captured at least one image to a server arrangement, and processing the at least one image to determine a class of the animal carcass.
  • the at least one imaging device may be operable to send the captured at least one image to the server arrangement, and the server arrangement may be operable to process the captured at least one image.
  • the at least one imaging device comprises directly sending the captured at least one image to the server arrangement.
  • the at least one imaging device and the server arrangement may comprise compatible communication modules.
  • the captured at least one image may be sent from the at least one imaging device to the server arrangement via an intermediate devices, such as network devices, computing devices, and so forth.
  • the server arrangement is communicably coupled to the at least one imaging device via a network, the server arrangement operable to receive and process the captured at least one image to determine a class of the animal carcass.
  • the server arrangement may be hardware, software, firmware, or a combination of these, operable to facilitate classification of the animal carcass.
  • the network include, but are not limited to, internet, short range radio, and cellular network.
  • the system may further comprise a computing device communicably coupled to the at least one imaging device and a server arrangement.
  • the computing device may be hardware, software, firmware, or a combination of these, operable to communicate with each of the at least one imaging device and the server arrangement to facilitate classification of the animal carcass.
  • Examples of the computing device include, but are not limited to, a smart-phone, a desktop computer, a laptop computer, and a tablet computer.
  • the computing device may be operable to receive the captured at least one image from the at least one imaging device, and send the received at least one image to the server arrangement.
  • the computing device may comprise a transceiver module to receive and send the captured at least one image.
  • the computing device may receive two three-dimensional images of the animal carcass from the three-dimensional camera, and may send the two three-dimensional images to the server arrangement.
  • the method may comprise sending at the at least one three-dimensional image to the server arrangement.
  • the at least one three-dimensional image may be sent directly from the at least one imaging device to the server arrangement.
  • the computing device may be further operable to send the at least one three-dimensional image to the server arrangement.
  • the at least one three-dimensional image may be received by the computing device from the three- dimensional camera.
  • the computing device may be operable to process the captured at least the pair of images to form the at least one three-dimensional image.
  • the at least the pair of images may be two-dimensional, and may be obtained from the at least one two-dimensional camera. More specifically, the computing device may form at least one three-dimensional image using the shared set of coincident pixels, from at least a pair of images, as reference points. It is to be understood that the at least one three- dimensional image may provide an estimation of the geometry of the animal carcass. Therefore, in one embodiment, the method may comprise processing the captured at least a pair of images to form at least one three-dimensional image, using the computing device.
  • the method of classifying the animal carcass further comprises processing the at least one image to determine a class of the animal carcass.
  • the class of the animal carcass is determined by evaluating different attributes of the animal carcass depicted in the at least one image thereof, with known attributes pertaining to pre-defined (or known) classes of the animal carcass. Therefore, processing the at least one image may constitute a feature analysis step.
  • processing the captured at least one image comprises comparing the captured at least one image with a pre-defined template of a classification system to determine grades corresponding to different attributes of animal carcass.
  • the server arrangement is operable to compare the captured at least one image with the predefined template of the classification system to determine grades corresponding to different attributes of animal carcass.
  • the server arrangement may utilize pattern recognition and pattern comparison algorithms to identify similar patterns between the at least one image and the pre-defined template to determine the grades corresponding to different attributes of the animal carcass.
  • Such pattern recognition algorithms may be used for identifying different attributes in the captured at least one image.
  • each of the attributes of the animal carcass is assigned a corresponding grade based on quality and characteristics thereof.
  • the server arrangement may process the captured at least one image of the animal carcass to determine degree of fat marbling in the animal carcass by comparing with the pre-defined template.
  • the class of the animal carcass is determined by combining grades corresponding to different attributes of the animal carcass. Specifically, each of the grades corresponding to different attributes of the animal carcass is combined to determine the class of the animal carcass.
  • the class of the animal carcass takes into consideration different attributes thereof and thus, is a significant measure of the quality of the animal carcass.
  • the animal carcass may comprise a desired amount of fat marbling therein.
  • the animal carcass may have a diseased portion. Therefore, the class of such animal carcass is affected by presence of such diseased portions.
  • the grades corresponding to different attributes of the animal carcass may be combined using mathematical operations and/or computational algorithms.
  • processing the at least one image may comprise comparing the at least one three-dimensional image with a pre-defined template of the classification system to determine the class of the animal carcass.
  • the server arrangement may be operable to compare the at least one three-dimensional image with the pre-defined template of a classification system to determine the class of the animal carcass.
  • the server arrangement may compare the at least one three-dimensional image, captured by the three-dimensional camera, with the pre-defined template of the classification system.
  • the server may compare at least one three dimensional image, formed by processing at least the pair of two-dimensional images, with the pre-defined template of the classification system.
  • processing the at least one image may facilitate estimation of geometry of the animal carcass.
  • the geometry of the animal carcass may help in determination of the amount of weight, fat, conformation, and so forth of the animal carcass.
  • the server arrangement may identify any deformation or abnormalities in the animal carcass.
  • the server arrangement may identify any diseased portions of the animal carcass from the at least one three-dimensional image.
  • the classification system may be one of: European Union EUROP grid classification system, United States Department of Agriculture grading system, South African Meat Industry Company meat classification system. Specifically, the European Union EUROP grid classification system classifies the animal carcasses based on conformation and amount of fat in the animal carcass.
  • the conformation of the animal carcass is determined based on amount of muscle with respect to bones in the animal carcass.
  • the animal carcass may be provided with a conformation grade such as E, U+ , -U, R, O+ , -O, P+ , and -P based on the conformation of the animal carcass.
  • the animal carcass may be provided with a fatness grade such as 1 , 2, 3, 4L, 4H, 5L, and 5H based on the amount of fat in the animal carcass.
  • the class of the animal carcass may be determined by combining the conformation and fatness grade of the animal carcass.
  • the United States Department of Agriculture grading system classifies the animal carcass based on degree of maturity and degree of marbling of the animal carcass. It is to be understood that each of the aforementioned classification systems may have distinct pre-defined template associated therewith. Moreover, the pre-defined templates of the classification system may be defined on the basis of weight, fat, intramuscular fat, texture, color, conformation, and so forth, of the animal carcass.
  • the method may further comprise capturing at least one image of an animal prior to slaughtering of the animal, for identifying the information associated with the animal.
  • the at least one imaging device may be operable to capture at least one image of the animal prior to slaughtering of the animal for identifying the information associated with the animal.
  • the at least one image of the animal may be captured using the magnetic resonance imaging (MRI) camera.
  • the at least one image captured by the magnetic resonance imaging (MRI) camera may be indicative of attributes, such as weight, gender, age, and/or breed/race, of the animal.
  • the at least one image of the animal is captured at a slaughterhouse, and/or at a farm where the animal is reared.
  • identifying the information associated with the animal may comprise processing the captured at least one image of the animal.
  • the server arrangement may be operable to process the captured at least one image of the animal for identifying the information associated with the animal.
  • processing the captured at least one image may comprise comparing the captured at least one image with at least one pre-analysed image of an animal.
  • the "at least one pre- analysed image of the animal" may relate to an image that has been previously captured and the attributes of the animal thereof are known.
  • the at least one pre-analysed image may serve as a reference for the determining the attributes of the animal of the captured at least one image.
  • processing the captured at least one image of the animal may comprise employing image processing algorithms to determine the attributes of the animal.
  • the image processing algorithms may analyse distance between bone and skin of the animal to determine the amount of muscle with respect to bones in the animal.
  • the image processing algorithms may estimate the weight of the animal based on height and conformation thereof.
  • health of the animal may be estimated based on condition of skin and/or presence of any lesions or lacerations thereon.
  • the server arrangement may comprise a database for storing the pre-defined template of the classification system.
  • the database may be hardware, software, firmware, or a combination of these, suitable for storing the pre-defined template of the classification system.
  • the method may comprise tagging the animal carcass to assist classification thereof by attaching a tag to the animal carcass, the tag comprising information associated with the animal.
  • the system may further comprise the tag attached to the animal carcass.
  • the tag may be pasted or attached to a part of the animal carcass.
  • the information associated with the animal may include information relating to body, gender, age, breed/race, breeders, farm, and so forth pertaining to the animal. Examples of the tag include, but are not limited to, RFID tags, QR codes, barcodes, and electronic identification tags.
  • the method may further comprise detecting the tag, using the at least one imaging device.
  • the captured at least one image may depict the tag associated with the animal, and the tag may be detected upon sending the captured at least one image to the server arrangement.
  • the server arrangement may facilitate detection of the tag by recognizing shape and distinct features thereof, and identify the information associated with the tag.
  • the server arrangement may comprise the database for storing the information in the tag associated with the animal.
  • information in the tag associated with the animal may assist the server arrangement in determining the class of the animal carcass.
  • the information in tag may relate to age and gender of the animal, and may assist the server arrangement in determining the class the animal carcass according to the United States Department of Agriculture grading system.
  • computing device may process the captured at least one image to detect the tag and identify the information associated therewith.
  • the database may be further operable to store the at least one image of the animal carcass and/or the at least one image of the animal.
  • the database may be operable to associate the at least one image of the animal carcass and/or the at least one image of the animal with at least one of: the determined class of the animal, the information associated with the animal and the pre-defined template of the classification system.
  • the server arrangement may employ the at least one image of the animal carcass, associated with the determined class of the animal, along with the pre-defined template of the classification system, to determine a class of another animal carcass.
  • information stored on the database may provide a temporal log of the determined classes of the animal carcasses. Furthermore, such temporal log of the determined classes of the animal carcasses may assist future classification of other animal carcasses.
  • the method may comprise receiving the determined class of the animal carcass from the server arrangement. Further, the computing device is operable to receive the determined class of the animal carcass from the server arrangement. Additionally, the computing device may display the determined class of the animal in the slaughterhouse. In an example, the computing device may comprise a digital screen to display the determined class of the animal. In another example, the computing device may comprise a printer configured to print the determined class of the animal. In an embodiment, the method may further comprise associating the information in the tag with the determined class of the animal carcass. Further, the computing device is operable to associate the information in the tag with the determined class of the animal carcass. Specifically, the computing device may link the information in the tag that may be obtained via the server arrangement, with the received determined class of the animal carcass.
  • FIG. 1 illustrated is a schematic illustration of an exemplary system 100 for classifying an animal carcass, in accordance with an embodiment of the present disclosure.
  • the system 100 includes at least one imaging device, depicted as imaging devices 102 and 104, and a server arrangement 106 communicably coupled to the imaging devices 102 and 104 via a network 108.
  • FIG. 2 illustrated is a schematic illustration of an exemplary system 200 for classifying an animal carcass, in accordance with another embodiment of the present disclosure.
  • the system 200 includes at least one imaging device, depicted as imaging devices 202 and 204, a server arrangement 206 communicably coupled to the imaging devices 202 and 204 via a network 208, and a computing device 210 communicably coupled to the imaging devices 202 and 204, and the server arrangement 206.
  • imaging devices 202 and 204 depicted as imaging devices 202 and 204
  • server arrangement 206 communicably coupled to the imaging devices 202 and 204 via a network 208
  • a computing device 210 communicably coupled to the imaging devices 202 and 204, and the server arrangement 206.
  • an axis A-A' depicts a longitudinal axis of the animal carcass 302.
  • the animal carcass 302 may be cut along the longitudinal axis A-A'.
  • at least one imaging device (such as the imaging devices 102 and 104 of FIG. 1) is operable to capture at least one image of longitudinal halves of the animal carcass 302.
  • FIG. 4 illustrated is a schematic illustration of an animal carcass 402, in accordance with another embodiment of the present disclosure.
  • axes B-B' and C-C depict transverse axes of the animal carcass 402.
  • the animal carcass 402 may be cut along the transverse axis B-B' and/or axis C-C.
  • at least one imaging device (such as the imaging devices 102 and 104 of FIG. 1 ) is operable to capture at least one image of different transversal sections of the animal carcass 402.
  • steps of a method 500 for classifying an animal carcass (such as the animal carcasses 302 and 402 of FIG. 3 and FIG. 4), in accordance with an embodiment of the present disclosure.
  • at step 502 at least one image of an animal carcass is captured using at least one imaging device.
  • the captured at least one image is sent to a server arrangement.
  • the at least one image is processed to determine a class of the animal carcass.
  • the steps 502 to 506 are only illustrative and other alternatives can also be provided where one or more steps are added, one or more steps are removed, or one or more steps are provided in a different sequence without departing from the scope of the claims herein.

Landscapes

  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Food Science & Technology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Biophysics (AREA)
  • Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Environmental Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Medicinal Chemistry (AREA)
  • Immunology (AREA)
  • Theoretical Computer Science (AREA)
  • Radiology & Medical Imaging (AREA)
  • Medical Informatics (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • Quality & Reliability (AREA)
  • Pathology (AREA)
  • Animal Husbandry (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Image Analysis (AREA)
  • Sorting Of Articles (AREA)

Abstract

L'invention concerne un procédé de classification d'une carcasse d'animal. Le procédé consiste: à capturer au moins une image de la carcasse d'animal à l'aide d'au moins un dispositif d'imagerie; à envoyer ladite au moins une image capturée à un dispositif serveur; et à traiter ladite au moins une image pour déterminer une classe de la carcasse d'animal.
EP18723081.8A 2017-04-07 2018-04-05 Procédé et système de classification d'une carcasse d'animal Withdrawn EP3606349A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
SE1730100A SE1730100A1 (sv) 2017-04-07 2017-04-07 Method and system for classifying animal carcass
PCT/SE2018/050358 WO2018186796A1 (fr) 2017-04-07 2018-04-05 Procédé et système de classification d'une carcasse d'animal

Publications (1)

Publication Number Publication Date
EP3606349A1 true EP3606349A1 (fr) 2020-02-12

Family

ID=62116931

Family Applications (1)

Application Number Title Priority Date Filing Date
EP18723081.8A Withdrawn EP3606349A1 (fr) 2017-04-07 2018-04-05 Procédé et système de classification d'une carcasse d'animal

Country Status (3)

Country Link
EP (1) EP3606349A1 (fr)
SE (1) SE1730100A1 (fr)
WO (1) WO2018186796A1 (fr)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
IT201900015893A1 (it) 2019-09-09 2021-03-09 Farm4Trade S R L Metodo di valutazione di uno stato di salute di un elemento anatomico, relativo dispositivo di valutazione e relativo sistema di valutazione

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DK676487A (da) * 1987-12-22 1989-06-23 Slagteriernes Forskningsinst Fremgangsmaade ved bestemmelse af kvalitetsegenskaber ved individuelle kreaturslagtekroppe og anlaeg til brug ved bestemmelse af egenskaberne
GB9013983D0 (en) * 1990-06-22 1990-08-15 Nat Res Dev Automatic carcass grading apparatus and method
FR2672775B1 (fr) * 1991-02-14 1993-05-21 Normaclass Rd Procede pour le classement de carcasses de gros bovins, veaux, porcs ou ovins et dispositif pour sa mise en óoeuvre.

Also Published As

Publication number Publication date
SE1730100A1 (sv) 2018-10-08
WO2018186796A1 (fr) 2018-10-11

Similar Documents

Publication Publication Date Title
Qiao et al. Intelligent perception for cattle monitoring: A review for cattle identification, body condition score evaluation, and weight estimation
US11832595B2 (en) System and method for identification of individual animals based on images of the back
Halachmi et al. Automatic assessment of dairy cattle body condition score using thermal imaging
CN107635509B (zh) 用于确定体况评分、体重和生育状态的改进方法和相关设备
Nasirahmadi et al. Implementation of machine vision for detecting behaviour of cattle and pigs
Wang et al. ASAS-NANP SYMPOSIUM: Applications of machine learning for livestock body weight prediction from digital images
US11627726B2 (en) System and method of estimating livestock weight
US8538126B2 (en) Method and apparatus for the automatic grading of condition of livestock
US5474085A (en) Remote thermographic sensing of livestock
Halachmi et al. Cow body shape and automation of condition scoring
US20050011466A1 (en) System and method for measuring animals
US20230276773A1 (en) Systems and methods for automatic and noninvasive livestock health analysis
Pallottino et al. Comparison between manual and stereovision body traits measurements of Lipizzan horses
WO2016023075A1 (fr) Imagerie 3d
CN112288793B (zh) 畜类个体背膘检测方法、装置、电子设备及存储介质
CA3230401A1 (fr) Systemes et procedes pour la surveillance automatisee de conditions physiologiques d'animaux et pour la prediction de phenotypes et de resultats de sante des animaux
EP3606349A1 (fr) Procédé et système de classification d'une carcasse d'animal
KR102372107B1 (ko) 영상기반의 모돈 분만 알림 시스템
CN113532616A (zh) 基于计算机视觉的体重估计方法、装置及系统
Shukla et al. Fostering Smart Agriculture: Using Vision-Based AI for Livestock Managing
KR102598065B1 (ko) 한우 및 육우의 육량 예측 방법 및 그 시스템
Taylor et al. Digital imaging techniques to assess welfare at a cull sow harvest facility

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

17P Request for examination filed

Effective date: 20191106

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

AX Request for extension of the european patent

Extension state: BA ME

RIN1 Information on inventor provided before grant (corrected)

Inventor name: BJOERK, HELENA

Inventor name: LILJA, MATTS

Inventor name: KONRADSSON, OVE

Inventor name: EKE-GOERANSSON, PER

DAV Request for validation of the european patent (deleted)
DAX Request for extension of the european patent (deleted)
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: EXAMINATION IS IN PROGRESS

17Q First examination report despatched

Effective date: 20200811

18D Application deemed to be withdrawn

Effective date: 20201022