WO2024016046A1 - Dispositif d'identification de phénotype - Google Patents

Dispositif d'identification de phénotype Download PDF

Info

Publication number
WO2024016046A1
WO2024016046A1 PCT/AU2023/050539 AU2023050539W WO2024016046A1 WO 2024016046 A1 WO2024016046 A1 WO 2024016046A1 AU 2023050539 W AU2023050539 W AU 2023050539W WO 2024016046 A1 WO2024016046 A1 WO 2024016046A1
Authority
WO
WIPO (PCT)
Prior art keywords
aquatic creature
holding chamber
chamber
aquatic
creature
Prior art date
Application number
PCT/AU2023/050539
Other languages
English (en)
Inventor
Melony SELLARS
Michael SPEIRS
Original Assignee
Genics Pty Ltd
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
Priority claimed from AU2022902001A external-priority patent/AU2022902001A0/en
Application filed by Genics Pty Ltd filed Critical Genics Pty Ltd
Publication of WO2024016046A1 publication Critical patent/WO2024016046A1/fr

Links

Classifications

    • 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
    • A01K61/00—Culture of aquatic animals
    • A01K61/90—Sorting, grading, counting or marking live aquatic animals, e.g. sex determination
    • 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
    • A01K63/00—Receptacles for live fish, e.g. aquaria; Terraria
    • A01K63/02—Receptacles specially adapted for transporting live fish
    • 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
    • A01K63/00—Receptacles for live fish, e.g. aquaria; Terraria
    • A01K63/06—Arrangements for heating or lighting in, or attached to, receptacles for live 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
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/58—Extraction of image or video features relating to hyperspectral data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
    • G06V20/698—Matching; Classification
    • 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
    • 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
    • A01K2227/00—Animals characterised by species
    • A01K2227/40—Fish
    • 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
    • A01K63/00—Receptacles for live fish, e.g. aquaria; Terraria
    • A01K63/003—Aquaria; Terraria
    • A01K63/006—Accessories for aquaria or terraria
    • 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
    • G06T7/0004—Industrial image inspection

Definitions

  • the present disclosure relates to a phenotype identification device.
  • phenotype identification of aquatic creatures for attributes of commercial relevance, such as health assessment and disease control.
  • the phenotype being a set of characteristics of a living thing, resulting from its combination of genes and the effect of its environment,
  • pathogens The presence of pathogens, genetics and the rate of growth are critical factors in the economic farming of aquatic animals. Historically, pathogens were detected when clinical symptoms appear. Often, this proved to be too late for effective intervention with wholesale stock losses often occurring. The analysis of the presence of pathogens or disease-causing agents was possible but prohibitively expensive.
  • a phenotype identification device for an aquatic creature including: a holding chamber for containing the aquatic creature; an illuminator mounted adjacent to the holding chamber, wherein the illuminator is configured to provide illumination at several different light wavelengths; and a plurality of imaging sensors mounted adjacent to the holding chamber; wherein the plurality of imaging sensors are configured to capture a plurality of images of the aquatic creature from different views, for phenotype identification, as the illuminator is activated at each of the different light wavelengths.
  • the phenotype identification device further includes a back plate, wherein the back plate is utilised as a reference point for the plurality of imaging sensors to enable correction of dimension measurements of the aquatic creature.
  • the phenotype identification device further includes: an entrance chamber adapted to receive the aquatic creature; and a first gate connecting the entrance chamber to the holding chamber; wherein the first gate is configured to transfer the aquatic creature from the entrance chamber to the holding chamber, and retain the aquatic creature within the holding chamber.
  • the first gate includes a plurality of electrodes to encourage the aquatic creature to transfer from the entrance chamber to the holding chamber, and retain it in the holding chamber.
  • the first gate includes a plurality of lights to encourage the aquatic creature to transfer from the entrance chamber to the holding chamber, and retain it in the holding chamber.
  • the first gate includes a plurality of acoustic transducers to encourage the aquatic creature to transfer from the entrance chamber to the holding chamber, and retain it in the holding chamber.
  • the first gate is configured as a liquid permeable physical barrier.
  • the phenotype identification device further includes: a collection chamber adapted to retain the aquatic creature prior to transfer to another container or containment zone; and a second gate connecting the holding chamber to the collection chamber; wherein the second gate is configured to transfer the aquatic creature from the holding chamber to the collection chamber, and retain the aquatic creature within the collection chamber.
  • the second gate includes a plurality of electrodes to encourage the aquatic creature to transfer from the holding chamber to the collection chamber, and retain it in the collection chamber.
  • the second gate includes a plurality of lights to encourage the aquatic creature to transfer from the holding chamber to the collection chamber, and retain it in the collection chamber.
  • the second gate includes a plurality of acoustic transducers to encourage the aquatic creature to transfer from the holding chamber to the collection chamber, and retain it in the collection chamber.
  • the second gate is configured as a liquid permeable physical barrier.
  • an RFID reader may be mounted to the exterior of the entrance chamber to automatically read a transponder tag attached to the animal as it passes through the entrance chamber. Individual animal identification can be linked to the software analysis record.
  • all gates are removed to encourage the aquatic creature to transfer from the entrance chamber to the holding chamber without restriction.
  • a method of identifying the phenotype of an aquatic creature including: positioning, in a holding chamber of a phenotype identification device, the aquatic creature; illuminating, in the holding chamber, the aquatic creature using an illuminator configured to provide illumination at several different light wavelengths; imaging, in the holding chamber, the aquatic creature using a plurality of imaging sensors configured to capture a plurality of images of the aquatic creature from different views as the illuminator is activated at each of the different light wavelengths; and analysing, with a software process, the plurality of images to determine the phenotype of the aquatic creature.
  • a system of identifying the phenotype of an aquatic creature including: a phenotype identification device including: a holding chamber for containing the aquatic creature; an illuminator mounted adjacent to the holding chamber, wherein the illuminator is configured to provide illumination at several different light wavelengths; and a plurality of imaging sensors mounted adjacent to the holding chamber; wherein the plurality of imaging sensors are configured to capture a plurality of images of the aquatic creature from different views, for phenotype identification, as the illuminator is activated at each of the different light wavelengths; and a computer device configured with a processor; wherein the processor is programmed to: retrieve the plurality of images from the phenotype identification device; correlate the plurality of images with existing images on a database; and present a list of phenotypes associated with the aquatic creature
  • Fig. 1 is a side view of the phenotype identification device.
  • Fig. 2 is a side view of the gate configured with electrodes.
  • Fig. 3 is a front view of the gate configured with electrodes.
  • Fig. 4 is a top view of the gate
  • a phenotype identification device designed to facilitate the collection of large data sets that are necessary to identify early signs of disease and provide general health data.
  • Fig. 1 shows the phenotype identification device including an entry chamber 1 and a holding chamber 10.
  • the entry chamber 1 is adapted to facilitate the introduction of a live aquatic creature, such as a decapod, fish or other aquatic species, to the phenotype identification device.
  • the holding chamber 10 is adapted to expose the aquatic creature to multiple wavelengths of light and capture a plurality of images.
  • the plurality of images may be stored on a data storage device, such as a SD card, or transmitted over a network connection to an external storage device or computer device.
  • the phenotype identification device includes an array of imaging sensors 7, 9 that enables the simultaneous and/or sequential collection of digital images or video at various light wavelengths displaying physical characteristics of decapods, fish, and other aquatic species.
  • the imaging sensors 7, 9 are an array of digital cameras having high-definition imaging sensors.
  • video sensors and other imaging sensors may be utilised.
  • Software may be used to analyse captured video to extract images at set time intervals.
  • an illuminator 6 may be used to illuminate the aquatic creature in a variety of wavelengths in addition to the underside of the creature.
  • the images may be correlated to different production related traits such as weight, length, sex (gender), ovarian maturation, impregnation, stomach content, internal organ quality, appendage condition, pathogen absence, presence, and profile, and genomic (genetic) traits.
  • An image and digitised database may be generated and subtle differences in digital images can be correlated to such traits and characteristics.
  • Software utilising artificial intelligence, may be used to analyse the images.
  • the artificial intellectual algorithms may be trained through relating weight, length, and physical condition assessments, taken immediately after the digital images, with a tissue or physical sample and tagged accordingly.
  • the tagged sample may then be assessed for pathogen burden by biochemical means and the complete dataset co-related.
  • the images of the side of the animal may be scaled accurately by reference to the underneath and above image by comparing the position and rotation with respect to the translucent back plate. All the datapoints can be mathematically rotated to present an accurate flat plane image.
  • the data may be categorised in the form of a decision tree to allow the data to be processed via a data set and an algorithm that continuously updates average, mean and standard deviations accurately to categorise the image in such a way that a later image may be compared to the derived data set to determine decision tree characteristics.
  • a means of release of the animal may be provided.
  • An artificial intelligence algorithm may be progressively fed with the data provided by the phenotype identification device to build and continuously improve a recognition dataset that will ultimately be able to recognise symptoms and characteristics from the digital images alone.
  • the entry chamber 1 is designed to facilitate the correct orientation of the animal for the imaging process and is adapted to allow and ensure stress free presentation for imaging. This allows for the capture of macro detail of pathogens, hair follicles and natural pigmentation and markings of the animal.
  • a gate 5 may include two sets of electrodes 15, 16 on either side of an entrance 5 and an exit 11 of the holding chamber 10 as shown in Fig. 1.
  • the electrodes 15, 16 may be charged with a pulsed, constant, or alternating voltage which is switched off to allow entry and on as soon as the aquatic creature reaches the holding chamber and further adjusted to discourage forward movement of the decapod whist imaging takes place.
  • the voltage at the exit electrodes is removed and the voltage at the entrance may be increased to encourage movement out of the holding chamber 10.
  • the electrodes 15, 16 will be controlled by a control circuit to drive the appropriate gate, either stimulating voltage, light pattern generator or sound generator, as appropriate 17
  • the gates 5 and 11 may include intense light beams at either end of the holding chamber 10 switched in a similar manner to control the movement and positioning of the aquatic creature.
  • the gates 5 and 11 may include two directed sound transducers 15, 16 at each end of the holding chamber 10 used in a similar way to control the movement and position of the animal.
  • the gates 5, 11 may be physical gates at either end operated manually or by means of an electrical or mechanical mechanism.
  • the phenotype identification device includes three chambers 1 , 10, 13 separated by gates 5, 11 to control the travers of the aquatic creature through the phenotype identification device.
  • the aquatic creature is first removed from its containment vessel and placed in the entrance chamber 1 .
  • the entrance chamber 1 allows a continual flow of water and the placement of the aquatic creature prior to imaging. The continuous flow of water will allow the level to remain constant and above the level of the holding chamber 10.
  • the entry gate 5 may be opened to admit the aquatic creature, and then closed to prevent it from returning to the entrance chamber 1 .
  • the aquatic creature Upon entering the holding chamber the aquatic creature is prevented from passing through by the exit gate 11 .
  • exit gate 11 parameters the aquatic creature can be positioned in the field of view 12.
  • the illuminator 6 may include a set of LEDs and light sources such that the aquatic creature can be illuminated at different light wavelengths and the plurality of images taken by a first imaging sensor 7 and a second imaging sensor 9. Simultaneously a machine-readable coded sample 8 is imaged and included for identification of the sample.
  • the exit gate 11 is opened and the aquatic creature encouraged to exit the holding chamber 10 by additional stimulation at the entry gate 5.
  • the aquatic creature is retrieved, and a tissue sample taken and deposited in a machine-readable coded container 8. The aquatic creature is then removed and returned to its original containment vessel
  • the plurality of images and the tissue sample is provided to the image analyser and software to characterise the sample set.
  • the tissue sample is analysed using a multiple pathogen analysis technique.
  • the pathogen status is determined, and the report added to the software database.
  • the phenotype identification device has a frame inside an exterior casing that is fabricated from plastic, metal, or timber.
  • the exterior casing may be constructed to enclose the entire device to provide physical protection and security.
  • the chambers may be constructed from a transparent material such as plexiglass with a transmission characteristic that allows the full spectrum of light to be passed that allows the illumination of the animal.
  • the back surface of chamber advantageously is manufactured from a translucent white material to provide a consistent background for the photography.
  • the phenotype identification device further includes a water inflow 2 and water outflow 14 that may be manually or automatically controlled to maintain the water level above the second chamber 10.
  • a portable computer device may employ proprietary software to operate the function of the imaging sensors and illuminator. This portable computer device may be mounted to the exterior casing of the phenotype identification device.
  • Each training image is related to pre- and -post recorded phenotype data including, weight and length of the animal, sex, overall physical condition, and the colour and condition of the uropods, pleopods, antenna, rostrum, and limbs.
  • DNA and RNA data is also related to each image to identify the presence or absence of a number of species-specific pathogens.
  • the data is stored in a digital relational database that maps image records to pathogen records via characteristic relationships.
  • the data can further refine the accuracy parameters of the models to improve the effectiveness and efficiency of the process chain, to the stage that the models will be capable of ingesting an image alone to produce accurate predictions of weight, length, sex, and an overall stressed determination based on the combined rating of physical conditions.
  • the Al algorithm may be derived by scaling the images accurately and using its area to compute expected weight and then using a series of decision trees whereby the first differentiation is disease present or not, subsequent trees by male or female, above or below the mean weight, above or below the mean lengths of limbs, antennae, and so on so that cross tree analysis can identify finer and finer differentiation of attribute until sufficient data is available such that a single image may determine the likely presence of typical malformation, poor genetics, poor nutrition or the presence of specific diseases. Further augmentation can be achieved using neural networks further to discriminate factors

Landscapes

  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Environmental Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Zoology (AREA)
  • Marine Sciences & Fisheries (AREA)
  • Animal Husbandry (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Human Computer Interaction (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Medical Informatics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)

Abstract

L'invention concerne un dispositif d'identification de phénotype pour une créature aquatique qui comprend une chambre de maintien, un illuminateur conçu pour fournir un éclairage à de multiples longueurs d'onde de lumière différentes, et des capteurs d'imagerie conçus pour capturer différentes vues des créatures aquatiques à partir de différentes vues pour une identification de phénotype lorsque l'illuminateur est activé à chaque longueur d'onde de lumière distincte.
PCT/AU2023/050539 2022-07-16 2023-06-16 Dispositif d'identification de phénotype WO2024016046A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
AU2022902001A AU2022902001A0 (en) 2022-07-16 Phenotype Identification Device
AU2022902001 2022-07-16

Publications (1)

Publication Number Publication Date
WO2024016046A1 true WO2024016046A1 (fr) 2024-01-25

Family

ID=89616598

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/AU2023/050539 WO2024016046A1 (fr) 2022-07-16 2023-06-16 Dispositif d'identification de phénotype

Country Status (1)

Country Link
WO (1) WO2024016046A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2201772A (en) * 1986-10-16 1988-09-07 Papirind Forskningsinst An opto-electronic method for determining by length-measurement the quality of cultured fish and a device for implementing the method
WO2004044829A1 (fr) * 2002-11-08 2004-05-27 Data Flow / Alaska, Inc. Systeme pour identifier de façon univoque des sujets pris dans une population cible
WO2018011744A1 (fr) * 2016-07-13 2018-01-18 Biosort As Dispositif pour trier des poissons nageant dans un courant
GB2555415A (en) * 2016-10-26 2018-05-02 Mckimm Robin Method and apparatus for orienting fish
WO2021064829A1 (fr) * 2019-09-30 2021-04-08 炎重工株式会社 Dispositif de tri d'organismes aquatiques

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2201772A (en) * 1986-10-16 1988-09-07 Papirind Forskningsinst An opto-electronic method for determining by length-measurement the quality of cultured fish and a device for implementing the method
WO2004044829A1 (fr) * 2002-11-08 2004-05-27 Data Flow / Alaska, Inc. Systeme pour identifier de façon univoque des sujets pris dans une population cible
WO2018011744A1 (fr) * 2016-07-13 2018-01-18 Biosort As Dispositif pour trier des poissons nageant dans un courant
GB2555415A (en) * 2016-10-26 2018-05-02 Mckimm Robin Method and apparatus for orienting fish
WO2021064829A1 (fr) * 2019-09-30 2021-04-08 炎重工株式会社 Dispositif de tri d'organismes aquatiques

Similar Documents

Publication Publication Date Title
EP3413708B1 (fr) Système et procédé d'enregistrement et de suivi de la santé et du développement chez des poissons vivants
Saberioon et al. Automated within tank fish mass estimation using infrared reflection system
Georgakopoulou et al. The influence of temperature during early life on phenotypic expression at later ontogenetic stages in sea bass
CN110929650B (zh) 豢养物身份识别方法、装置、计算设备、可读存储介质
de Lima Weber et al. Recognition of Pantaneira cattle breed using computer vision and convolutional neural networks
NO20220222A1 (fr)
Subedi et al. Tracking floor eggs with machine vision in cage-free hen houses
Falk et al. Male-like ornamentation in female hummingbirds results from social harassment rather than sexual selection
CN111274975A (zh) 猪只采食行为预测方法及装置
Hosseini et al. Efficient phenotypic sex classification of zebrafish using machine learning methods
Long et al. Automatic classification of cichlid behaviors using 3D convolutional residual networks
Lai et al. Automatic measuring shrimp body length using CNN and an underwater imaging system
Lubich et al. Identification and classification of poultry eggs: A case study utilizing computer vision and machine learning
CN117036820B (zh) 一种基于视觉图像的猪只分类模型及其方法
WO2024016046A1 (fr) Dispositif d'identification de phénotype
Hirsch et al. Individual identification of Eurasian perch Perca fluviatilis by means of their stripe patterns
Ienaga et al. Normal hatching rate estimation for bulk samples of Pacific bluefin tuna (Thunnus orientalis) eggs using deep learning
Zhao et al. Review on image-based animals weight weighing
Saifullah et al. Chicken Egg Detection Based-on Image Processing Concept: A Review
CN114241409A (zh) 一种基于笼养鸡异常粪便和解剖图像的疾病早期预警系统及方法
Çevik et al. Mask R-CNN Approach for Egg Segmentation and Egg Fertility Classification
Al-Jubouri Automatic Computer Vision Systems for Aquatic Research
Brock et al. Adaptive plasticity generates microclines in threespine stickleback male nuptial color
Al-Jubouri et al. Recognition of Individual Zebrafish Using Speed-Up Robust Feature Matching
Nasirahmadi Development of automated computer vision systems for investigation of livestock behaviours

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23841648

Country of ref document: EP

Kind code of ref document: A1

DPE1 Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101)