University of Tasmania
Browse

File(s) under permanent embargo

Marine vertebrate predator detection and recognition in underwater videos by region convolutional neural network

conference contribution
posted on 2023-05-23, 14:15 authored by Mira ParkMira Park, Wenli YangWenli Yang, Cao, Z, Byeong KangByeong Kang, Connor, D, Mary-Anne LeaMary-Anne Lea
In this paper, we present R-CNN, Fast R-CNN and Faster R-CNN methods to automatically detect and recognise the predators in underwater videos. We compare the results of these methods on real data and discuss their strengths and weaknesses. We build a dataset using footage captured from representative environment of the wild and devise a data model with three classes (seal, dolphin, background). Following this, we train R-CNN, Fast R-CNN and Faster R-CNN, then evaluate them on a test dataset compose of challenging objects that had not been seen during training. We perform evaluation on GPU, acquiring information about the AP and IOU for each model and network based on various proposal numbers as well as runtime speeds. Based on the results, we found that the best model of predator detection using visual deep learning models is Faster R-CNN with 2000 proposals.

History

Publication title

Lecture Note in Computer Science: Proceedings of the 16th Pacific Rim Knowledge Acquisition Workshop: Knowledge Management and Acquisition for Intelligent Systems (PKAW 2019)

Volume

11669

Editors

K Ohara, Q Bai

Pagination

66-80

ISBN

978-3-030-30638-0

Department/School

School of Information and Communication Technology

Publisher

Springer

Place of publication

United Kingdom

Event title

Knowledge Management and Acquisition for Intelligent Systems (PKAW 2019)

Event Venue

Cuvu, Fiji

Date of Event (Start Date)

2019-08-26

Date of Event (End Date)

2019-08-27

Rights statement

Copyright 2019 Springer

Repository Status

  • Restricted

Socio-economic Objectives

Intelligence, surveillance and space

Usage metrics

    University Of Tasmania

    Categories

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC