Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

A comparison of image processing techniques for bird recognition.

Uma D Nadimpalli1, Randy R Price, Steven G Hall

  • 1Department of Biological and Agricultural Engineering, LSU AgCenter, Louisiana 70803, USA.

Biotechnology Progress
|February 4, 2006
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Potential of <i>Synechococcus elongatus</i> UTEX 2973 as a feedstock for sugar production during mixed aquaculture and swine wastewater bioremediation.

Heliyon·2024
Same author

Depuration of live oysters to reduce Vibrio parahaemolyticus and Vibrio vulnificus: A review of ecology and processing parameters.

Comprehensive reviews in food science and food safety·2022
Same author

Development of a suitability assessment model for the cultivation of intertidal macroalgae in the United States.

The Science of the total environment·2019
Same author

Physicochemical data of <i>p</i>-cresol, butyric acid, and ammonia.

Data in brief·2019
Same author

The effect of salinity and alkalinity on growth and the accumulation of copper and zinc in the Chlorophyta Ulva fasciata.

Ecotoxicology and environmental safety·2019

Autonomous vehicles equipped with image recognition can deter bird predation in fish farms. This study tested various image processing techniques, finding template matching effective across image clarity levels for bird detection.

Area of Science:

  • Aquaculture technology
  • Computer vision
  • Robotics

Background:

  • Bird predation poses a significant threat to fish culture in open ponds.
  • Autonomous vehicles offer a novel solution for bird dispersal.
  • Image recognition software is key to enhancing the efficiency of these vehicles.

Purpose of the Study:

  • To evaluate image processing techniques for bird recognition in aquaculture.
  • To assess the effectiveness of different algorithms under varying image clarity conditions.
  • To lay the groundwork for autonomous bird dispersal systems.

Main Methods:

  • Image classification into three types (Type 1: clear, Type 2: medium, Type 3: unclear).
  • Implementation of morphological operations and local thresholding using HSV, GRAY, and RGB color models.

Related Experiment Videos

  • Application of template matching (normal correlation) and artificial neural networks (ANN) for bird detection.

    • Main Results:

    • Template matching demonstrated consistent performance across all image types.
    • Artificial neural networks achieved accuracies of 100%, 60%, and 50% for Type 1, Type 2, and Type 3 images, respectively.
    • Results indicate potential for improved classification rates with further ANN training.

    Conclusions:

    • Image recognition techniques, particularly template matching, show promise for autonomous bird dispersal in aquaculture.
    • Further development and training of artificial neural networks are recommended for enhanced accuracy.
    • Future research will focus on real-world testing in aquacultural settings and broader industrial applications.