Comparison of machine learning algorithms for detecting coral reef

Authors

  • Eduardo Tusa Universidad Técnica de Machala; Heriot-Watt University
  • Alan Reynolds Heriot-Watt University
  • Neil Robertson Heriot-Watt University
  • David Lane Heriot-Watt University
  • Hyxia Villegas Universidad de Carabobo; Universidad Técnica de Machala
  • Antonio Bosnjak Universidad de Carabobo

DOI:

https://doi.org/10.29019/enfoqueute.v5n3.43

Keywords:

Coralbot, coral reef, machine learning, Gabor Wavelets filters, OpenCV

Abstract

(Received: 2014/07/31 - Accepted: 2014/09/23)

This work focuses on developing a fast coral reef detector, which is used for an autonomous underwater vehicle, AUV. A fast detection secures the AUV stabilization respect to an area of reef as fast as possible, and prevents devastating collisions. We use the algorithm of Purser et al. (2009) because of its precision. This detector has two parts: feature extraction that uses Gabor Wavelet filters, and feature classification that uses machine learning based on Neural Networks. Due to the extensive time of the Neural Networks, we exchange for a classification algorithm based on Decision Trees. We use a database of 621 images of coral reef in Belize (110 images for training and 511 images for testing). We implement the bank of Gabor Wavelets filters using C++ and the OpenCV library. We compare the accuracy and running time of 9 machine learning algorithms, whose result was the selection of the Decision Trees algorithm. Our coral detector performs 70ms of running time in comparison to 22s executed by the algorithm of Purser et al. (2009).

Downloads

Download data is not yet available.

Downloads

Published

2014-09-30

How to Cite

Tusa, E., Reynolds, A., Robertson, N., Lane, D., Villegas, H., & Bosnjak, A. (2014). Comparison of machine learning algorithms for detecting coral reef. Enfoque UTE, 5(3), pp. 45 – 56. https://doi.org/10.29019/enfoqueute.v5n3.43

Issue

Vol. 5 No. 3 (2014)

Section

Miscellaneous

License

The articles and research published by the UTE University are carried out under the Open Access regime in electronic format.  This means that all content is freely available without charge to the user or his/her institution. Users are allowed to read, download, copy, distribute, print, search, or link to the full texts of the articles, or use them for any other lawful purpose, without asking prior permission from the publisher or the author. This is in accordance with the BOAI definition of open access. By submitting an article to any of the scientific journals of the UTE University, the author or authors accept these conditions.

The UTE applies the Creative Commons Attribution (CC-BY) license to articles in its scientific journals. Under this open access license, as an author you agree that anyone may reuse your article in whole or in part for any purpose, free of charge, including commercial purposes. Anyone can copy, distribute or reuse the content as long as the author and original source are correctly cited. This facilitates freedom of reuse and also ensures that content can be extracted without barriers for research needs.

 

This work is licensed under a Creative Commons Attribution 3.0 International (CC BY 3.0).

 

The Enfoque UTE journal guarantees and declares that authors always retain all copyrights and full publishing rights without restrictions [© The Author(s)]. Acknowledgment (BY): Any exploitation of the work is allowed, including a commercial purpose, as well as the creation of derivative works, the distribution of which is also allowed without any restriction.