WO2021125936A1 - A rf model based insect identification method - Google Patents

A rf model based insect identification method Download PDF

Info

Publication number
WO2021125936A1
WO2021125936A1 PCT/MY2020/050199 MY2020050199W WO2021125936A1 WO 2021125936 A1 WO2021125936 A1 WO 2021125936A1 MY 2020050199 W MY2020050199 W MY 2020050199W WO 2021125936 A1 WO2021125936 A1 WO 2021125936A1
Authority
WO
WIPO (PCT)
Prior art keywords
insect
interest
points
image
species
Prior art date
Application number
PCT/MY2020/050199
Other languages
French (fr)
Inventor
Kumarasan YUKGEHNAISH
Parimannan SIVACHANDRAN
Sivaprakasam SUMITRA
Rajandas HEERA
Lee SU YIN
Chandrasekaran GIRISH KUMAR
Ravichandran Manickam
Original Assignee
Collaborative Research In Engineering, Science & Technology (Crest) Center
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 Collaborative Research In Engineering, Science & Technology (Crest) Center filed Critical Collaborative Research In Engineering, Science & Technology (Crest) Center
Publication of WO2021125936A1 publication Critical patent/WO2021125936A1/en

Links

Classifications

    • 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
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/24323—Tree-organised classifiers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/20—Ensemble learning
    • 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
    • G06T7/0008—Industrial image inspection checking presence/absence
    • 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
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • 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
    • G06T2207/10024—Color 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20076—Probabilistic image processing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/06—Recognition of objects for industrial automation

Definitions

  • the present invention generally relates to an organism identification method and particularly relates to a random forest model based insect identification method.
  • the present invention more particularly relates to an automated method for identification for an insect species.
  • the device comprises an image collection apparatus, a connecting rod, a display apparatus, and a work host, wherein the work host comprises a housing and an image processing apparatus.
  • the image processing apparatus is connected to one end of the connecting rod, and the other end of the connecting rod is connected to the housing of the work host.
  • the display apparatus is disposed on the work host.
  • the image collection apparatus is used for obtaining an image of insect pests of leaves and enables the obtained image to be transmitted to the work host.
  • the image processing apparatus carries out processing of the image of insect pests of leaves and enables the processed image to be transmitted to the display apparatus for display.
  • the device can greatly improve the detection efficiency and accuracy of insect pests of leaves and reduces the labor intensity of a technician.
  • the primary object of the present invention is to provide a standalone automated insect identification method in captured as well as flyaway condition of the insect.
  • Another objective of the present invention is to provide an automated method for estimating an area of an outbreak or infestation through an identified insect species.
  • Yet another object of the present invention is to provide a method for building a database of known as well as newly identified insect species.
  • the various embodiments of the present invention provide a method for insect identification in a captured as well as flyaway condition. Firstly, an image of an insect is captured during an appearance of the insect in a capturing range of an imaging unit followed by segmentation of an image based on a number of insect in the captured image. A plurality of point of interests in each segmented image is detected to predict an insect species on a basis of the plurality of points of interest by implementing a regressing model. A confidence score is derived from the regression model. The insect species is identified based on matching the confidence score with a predefined value and a number of insects found by the imaging belonging to the same identified insect species is updated.
  • an insect with the confidence score lower than the predefined value is stored under as new species in a database.
  • a mean coordinate of the points of interest is determined in a segmented to estimate a distance of the mean coordinate from remaining points of interest.
  • a distance between the mean coordinate and the points of interest within two times a standard deviation of the mean coordinate and a mean value is derived to train the regression model.
  • an area of identified insect species is estimated by mapping an outline of the points of interest by using a convex hull algorithm.
  • a pixel value of each point of interest is derived by estimating a number of pixels in an area covering 25 by 25 units around the point of interest.
  • FIG. 1 illustrates a flowchart for a method of an automated identification of an insect species, according to one embodiment of the present invention.
  • FIG. 2 illustrates a flowchart for a method of training a regression model for serving a reference data during identification of an insect species, according to one embodiment of the present invention.
  • FIG. 3a and 3b illustrates a points of interest selection through a captured image and a pixel selection for the points of interest respectively, according to one embodiment of the present invention.
  • FIG. 3c illustrates a distance identification between a mean coordinate and the points of interest, according to one embodiment of the present invention.
  • FIG. 3d illustrates a graphical representation of an area of the identified insect species derived through a convex hull algorithm, according to one embodiment of the present invention.
  • an image of an insect is captured during an appearance of the insect in a capturing range of an imaging unit.
  • the image is read for prediction of the insect species by converting the captured image into a grayscale (101-102).
  • the captured image is further segmented into a plurality of images based on a number of insect in the captured image to derive interested features or points of interest in each image (103-104).
  • a pixel value and a pixel RGB (red, green and blue colour) value of each point of interest is derived by estimating a number of pixels in an area covering 25 by 25 units around the point of interest (105).
  • An outline of the points of interest is drawn by using a convex hull algorithm which is further used to derive a surface area of an object (image of the insect) within the points of interest (106).
  • the surface area data is fed in to a random forest model to calculate to a confidence score (107).
  • the confidence score is relative value to the predetermined pixel value of the known insect species serving as reference value.
  • a plurality of point of interests in each segmented image is detected to predict an insect species on a basis of the plurality of points of interest by implementing a regressing model.
  • the insect species is identified based on matching the confidence score with a predefined value and a number of insects found by the imaging belonging to the same identified insect species is updated.
  • the insect species is known, otherwise a new insect species is detected (108).
  • the cumulative data counter is updated with storage of a data output of the identified insect species (109-110).
  • the data is stored for naming the insect species (111).
  • an insect with the confidence score lower than the predefined value is stored under as new species in a database.
  • a mean coordinate of the points of interest is determined in a segmented to estimate a distance of the mean coordinate from remaining points of interest.
  • a distance between the mean coordinate and the points of interest within two times a standard deviation of the mean coordinate and a mean value is derived to train the regression model.
  • an area of identified insect species is estimated by mapping an outline of the points of interest by using a convex hull algorithm.
  • the images are read for training the Random Forest model (201).
  • the image is converted into grayscale (202) and a pixel value and a pixel RGB (red, green and blue colour) value of each point of interest is derived by estimating a number of pixels in an area covering 25 by 25 units around the point of interest (203).
  • An outline of the points of interest is drawn by using a convex hull algorithm which is further used to derive a surface area of an object (image of the insect) within the points of interest (204).
  • a number of file in a reference data is equal to the number of files detected in the captured image data, then the data is fed into a Random Forest regression model (205-206).
  • the data is used for training the RF model on the detected species (207) and creating an insect identification training model (208).
  • the points of the interest in the captured image of an insect is based on python (good features) computer readable program.
  • the dots (301) indicate the points of interest obtained from good features to track algorithm, while the dot (302) indicates the mean coordinate of the points of interest.
  • the pixel value of the image or the segmented image is derived by estimating a number of pixels in an area covering 25 by 25 units around each point of interest. Then, the distance between the mean coordinate and the points of interest within two times standard deviation of the mean coordinate is obtained and averaged.
  • the green lines represent a connection between the mean coordinate and the points of interest within two times standard deviation of the mean coordinate.
  • the points of interest are used for determination of a surface area of the identified image and mapping between them through implementation of the convex hull algorithm.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Medical Informatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Evolutionary Biology (AREA)
  • Computational Mathematics (AREA)
  • Quality & Reliability (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Computing Systems (AREA)
  • Radiology & Medical Imaging (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Operations Research (AREA)
  • Probability & Statistics with Applications (AREA)
  • Geometry (AREA)
  • Algebra (AREA)
  • Databases & Information Systems (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Catching Or Destruction (AREA)

Abstract

The various embodiments of the present invention provide an image of an insect is captured. The image is read for prediction of the insect species by converting the captured image into a grayscale (101-102). The captured image is further segmented into a plurality of images based on a number of insect in the captured image to derive interested features or points of interest in each image (103-104). Then, a pixel value of each point of interest is derived (105). An outline of the points of interest is drawn by using a convex hull algorithm which is further used to derive a surface area of an object (image of the insect) within the points of interest (106). The surface area data is fed in to a random forest model to calculate to a confidence score (107). The confidence score is used to predict the insect species.

Description

A RF MODEL BASED INSECT IDENTIFICATION METHOD
FIELD OF INVENTION The present invention generally relates to an organism identification method and particularly relates to a random forest model based insect identification method. The present invention more particularly relates to an automated method for identification for an insect species. BACKGROUND OF THE INVENTION
With increase in human waste, the species of insects is also evolving and many times a source of newly identified disease can’t be identified due to lack of an updated database on insect species. To enhance the knowledge pertaining to identification of insects or pests, various prior art systems were developed.
One of such prior arts discloses a device and method for detecting the insect pests of leaves of crops. The device comprises an image collection apparatus, a connecting rod, a display apparatus, and a work host, wherein the work host comprises a housing and an image processing apparatus. The image processing apparatus is connected to one end of the connecting rod, and the other end of the connecting rod is connected to the housing of the work host. The display apparatus is disposed on the work host. The image collection apparatus is used for obtaining an image of insect pests of leaves and enables the obtained image to be transmitted to the work host. The image processing apparatus carries out processing of the image of insect pests of leaves and enables the processed image to be transmitted to the display apparatus for display. The device can greatly improve the detection efficiency and accuracy of insect pests of leaves and reduces the labor intensity of a technician.
However, the prior arts have limited activity in identification of an insect species as such prior arts are dependent on capturing of an insect followed by detection or identification of the captured insect species. This limits the database as a plurality of first time insect species are less in number, thus reducing a chance of capture. In the view of foregoing, there is a need for a standalone automated insect identification method in captured as well as flyaway condition of the insect.
SUMMARY OF THE INVENTION
The primary object of the present invention is to provide a standalone automated insect identification method in captured as well as flyaway condition of the insect.
Another objective of the present invention is to provide an automated method for estimating an area of an outbreak or infestation through an identified insect species.
Yet another object of the present invention is to provide a method for building a database of known as well as newly identified insect species. The various embodiments of the present invention provide a method for insect identification in a captured as well as flyaway condition. Firstly, an image of an insect is captured during an appearance of the insect in a capturing range of an imaging unit followed by segmentation of an image based on a number of insect in the captured image. A plurality of point of interests in each segmented image is detected to predict an insect species on a basis of the plurality of points of interest by implementing a regressing model. A confidence score is derived from the regression model. The insect species is identified based on matching the confidence score with a predefined value and a number of insects found by the imaging belonging to the same identified insect species is updated.
According to one embodiment of the present invention, an insect with the confidence score lower than the predefined value is stored under as new species in a database.
According to one embodiment of the present invention, a mean coordinate of the points of interest is determined in a segmented to estimate a distance of the mean coordinate from remaining points of interest.
According to one embodiment of the present invention, a distance between the mean coordinate and the points of interest within two times a standard deviation of the mean coordinate and a mean value is derived to train the regression model. According to one embodiment of the present invention, an area of identified insect species is estimated by mapping an outline of the points of interest by using a convex hull algorithm. According to one embodiment of the present invention, a pixel value of each point of interest is derived by estimating a number of pixels in an area covering 25 by 25 units around the point of interest.
These and other aspects of the embodiments herein will be better appreciated and understood when considered in conjunction with the following description and the accompanying drawings. It should be understood, however, that the following descriptions, while indicating preferred embodiments and numerous specific details thereof, are given by way of illustration and not of limitation. Many changes and modifications may be made within the scope of the embodiments herein without departing from the spirit thereof, and the embodiments herein include all such modifications.
BRIEF DESCRIPTION OF THE DRAWINGS Other objects, features, and advantages of the invention will be apparent from the following description when read with reference to the accompanying drawings. In the drawings, wherein like reference numerals denote corresponding parts throughout the several views: FIG. 1 illustrates a flowchart for a method of an automated identification of an insect species, according to one embodiment of the present invention.
FIG. 2 illustrates a flowchart for a method of training a regression model for serving a reference data during identification of an insect species, according to one embodiment of the present invention.
FIG. 3a and 3b illustrates a points of interest selection through a captured image and a pixel selection for the points of interest respectively, according to one embodiment of the present invention. FIG. 3c illustrates a distance identification between a mean coordinate and the points of interest, according to one embodiment of the present invention.
FIG. 3d illustrates a graphical representation of an area of the identified insect species derived through a convex hull algorithm, according to one embodiment of the present invention.
DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS With respect to FIG. 1 , an image of an insect is captured during an appearance of the insect in a capturing range of an imaging unit. The image is read for prediction of the insect species by converting the captured image into a grayscale (101-102). The captured image is further segmented into a plurality of images based on a number of insect in the captured image to derive interested features or points of interest in each image (103-104). Then, a pixel value and a pixel RGB (red, green and blue colour) value of each point of interest is derived by estimating a number of pixels in an area covering 25 by 25 units around the point of interest (105). An outline of the points of interest is drawn by using a convex hull algorithm which is further used to derive a surface area of an object (image of the insect) within the points of interest (106). The surface area data is fed in to a random forest model to calculate to a confidence score (107). The confidence score is relative value to the predetermined pixel value of the known insect species serving as reference value. A plurality of point of interests in each segmented image is detected to predict an insect species on a basis of the plurality of points of interest by implementing a regressing model. The insect species is identified based on matching the confidence score with a predefined value and a number of insects found by the imaging belonging to the same identified insect species is updated. If confidence is higher than the predetermined value then the insect species is known, otherwise a new insect species is detected (108). In case of known species identification, the cumulative data counter is updated with storage of a data output of the identified insect species (109-110). In case of determination of a new or unknown insect species, the data is stored for naming the insect species (111).
According to one embodiment of the present invention, an insect with the confidence score lower than the predefined value is stored under as new species in a database. According to one embodiment of the present invention, a mean coordinate of the points of interest is determined in a segmented to estimate a distance of the mean coordinate from remaining points of interest. According to one embodiment of the present invention, a distance between the mean coordinate and the points of interest within two times a standard deviation of the mean coordinate and a mean value is derived to train the regression model.
According to one embodiment of the present invention, an area of identified insect species is estimated by mapping an outline of the points of interest by using a convex hull algorithm.
With respect to FIG. 2, the images are read for training the Random Forest model (201). The image is converted into grayscale (202) and a pixel value and a pixel RGB (red, green and blue colour) value of each point of interest is derived by estimating a number of pixels in an area covering 25 by 25 units around the point of interest (203). An outline of the points of interest is drawn by using a convex hull algorithm which is further used to derive a surface area of an object (image of the insect) within the points of interest (204). A number of file in a reference data is equal to the number of files detected in the captured image data, then the data is fed into a Random Forest regression model (205-206). The data is used for training the RF model on the detected species (207) and creating an insect identification training model (208). With respect to FIG. 2a and 2b, the points of the interest in the captured image of an insect is based on python (good features) computer readable program. The dots (301) indicate the points of interest obtained from good features to track algorithm, while the dot (302) indicates the mean coordinate of the points of interest. The pixel value of the image or the segmented image is derived by estimating a number of pixels in an area covering 25 by 25 units around each point of interest. Then, the distance between the mean coordinate and the points of interest within two times standard deviation of the mean coordinate is obtained and averaged. The green lines represent a connection between the mean coordinate and the points of interest within two times standard deviation of the mean coordinate. With respect to FIG. 3d, the points of interest are used for determination of a surface area of the identified image and mapping between them through implementation of the convex hull algorithm.
As will be readily apparent to those skilled in the art, the present invention may easily be produced in other specific forms without departing from its essential characteristics. The present embodiments are, therefore, to be considered as merely illustrative and not restrictive, the scope of the invention being indicated by the claims rather than the foregoing description, and all changes which come within therefore intended to be embraced therein.

Claims

1. A method for insect identification in a captured as well as flyaway condition, the method comprises the steps of: capturing an image of an insect during an appearance of the insect in a capturing range of an imaging unit (101); segmenting an image based on a number of insect in the captured image
(102); detecting a plurality of point of interests in each segmented image (103-105); predicting an insect species on a basis of the plurality of points of interest by implementing a regressing model (107), wherein a confidence score is derived from the regression model; identifying the insect species based on matching the confidence score with a predefined value (108-109); updating a number of insects found by the imaging belonging to the same identified insect species (110).
2. The method as claimed in claim 1 , wherein an insect with the confidence score lower than the predefined value is stored under as new species in a database.
3. The method as claimed in claim 1 , wherein a mean coordinate of the points of interest is determined in a segmented to estimate a distance of the mean coordinate from remaining points of interest. 4. The method as claimed in claim 3, wherein a distance between the mean coordinate and the points of interest within two times a standard deviation of the mean coordinate and a mean value is derived to train the regression model.
5. The method as claimed in claim 1 , wherein an area of identified insect species is estimated by mapping an outline of the points of interest by using a convex hull algorithm.
6. The method as claimed in claim 1 , wherein a pixel value of each point of interest is derived by estimating a number of pixels in an area covering 25 by 25 units around the point of interest.
PCT/MY2020/050199 2019-12-20 2020-12-17 A rf model based insect identification method WO2021125936A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
MYPI2019007656 2019-12-20
MYPI2019007656 2019-12-20

Publications (1)

Publication Number Publication Date
WO2021125936A1 true WO2021125936A1 (en) 2021-06-24

Family

ID=76478462

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/MY2020/050199 WO2021125936A1 (en) 2019-12-20 2020-12-17 A rf model based insect identification method

Country Status (1)

Country Link
WO (1) WO2021125936A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023215630A1 (en) * 2022-05-06 2023-11-09 Board Of Trustees Of The University Of Arkansas Smart insect control device via artificial intelligence in real time

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050025357A1 (en) * 2003-06-13 2005-02-03 Landwehr Val R. Method and system for detecting and classifying objects in images, such as insects and other arthropods
CN110516712A (en) * 2019-08-01 2019-11-29 仲恺农业工程学院 Insect pest image recognition method, insect pest monitoring method, insect pest image recognition device, insect pest monitoring equipment and insect pest monitoring medium
US10496893B2 (en) * 2016-08-11 2019-12-03 DiamondFox Enterprises, LLC Handheld arthropod detection device

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050025357A1 (en) * 2003-06-13 2005-02-03 Landwehr Val R. Method and system for detecting and classifying objects in images, such as insects and other arthropods
US10496893B2 (en) * 2016-08-11 2019-12-03 DiamondFox Enterprises, LLC Handheld arthropod detection device
CN110516712A (en) * 2019-08-01 2019-11-29 仲恺农业工程学院 Insect pest image recognition method, insect pest monitoring method, insect pest image recognition device, insect pest monitoring equipment and insect pest monitoring medium

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
NATALIA LARIOS ; HONGLI DENG ; WEI ZHANG ; MATT SARPOLA ; JENNY YUEN ; ROBERT PAASCH ; ANDREW MOLDENKE ; DAVID A. LYTLE ; SALVADOR: "Automated insect identification through concatenated histograms of local appearance features: feature vector generation and region detection for deformable objects", MACHINE VISION AND APPLICATIONS (2008, vol. 19, no. 2, 7 July 2007 (2007-07-07), pages 105 - 123, XP019583387, ISSN: 1432-1769 *
ZHONG YUANHONG, GAO JUNYUAN, LEI QILUN, ZHOU YAO: "A Vision-Based Counting and Recognition System for Flying Insects in Intelligent Agriculture", SENSORS 2018, vol. 18, no. 5, 1489, 9 May 2018 (2018-05-09), pages 1 - 19, XP055837677, DOI: 10.3390/s18051489 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023215630A1 (en) * 2022-05-06 2023-11-09 Board Of Trustees Of The University Of Arkansas Smart insect control device via artificial intelligence in real time

Similar Documents

Publication Publication Date Title
Bercovich et al. Development of an automatic cow body condition scoring using body shape signature and Fourier descriptors
Reddy et al. Analysis of classification algorithms for plant leaf disease detection
US11954598B2 (en) Matching network for medical image analysis
US8343053B2 (en) Detection of structure in ultrasound M-mode imaging
US20150327518A1 (en) Method of monitoring infectious disease, system using the same, and recording medium for performing the same
KR102045223B1 (en) Apparatus, method and computer program for analyzing bone age
CN111639629B (en) Pig weight measurement method and device based on image processing and storage medium
CN116935327B (en) Aquaculture monitoring method, device, equipment and storage medium based on AI vision
CN111862044A (en) Ultrasonic image processing method and device, computer equipment and storage medium
Xu et al. Recognition method for apple fruit based on SUSAN and PCNN
JP7006776B2 (en) Analytical instruments, analytical methods, programs and aquatic organism monitoring systems
CN106934337A (en) Visual object and event detection and the forecasting system using pan
CN112257702A (en) Crop disease identification method based on incremental learning
CN116229189B (en) Image processing method, device, equipment and storage medium based on fluorescence endoscope
CN111860196A (en) Hand operation action scoring device and method and computer readable storage medium
JPWO2019198611A1 (en) Feature estimation device and feature estimation method
WO2021125936A1 (en) A rf model based insect identification method
CN104766068A (en) Random walk tongue image extraction method based on multi-rule fusion
US20230342902A1 (en) Method and system for automated evaluation of animals
CN104200460A (en) Image registration method based on images characteristics and mutual information
US20230180999A1 (en) Learning apparatus, learning method, program, trained model, and endoscope system
JP6311461B2 (en) Gaze analysis system and gaze analysis apparatus
JP6855175B2 (en) Image processing equipment, image processing methods and programs
Wirthgen et al. Level-set based infrared image segmentation for automatic veterinary health monitoring
CN111460864A (en) Animal disease detection method based on image recognition

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: 20903723

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)
NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20903723

Country of ref document: EP

Kind code of ref document: A1