Automatic sea turtle nest detection via deep learning

Out of the seven species of sea turtles in the world, six are classified as endangered. Mexico is home to five of these species which are protected by the government laws, however these animals are still subject to many threats, the most crucial is the poaching and illegal commerce of their eggs. Th...

Full description

Bibliographic Details
Main Author: Sanchez Castillo, Ricardo
Format: Dissertation (University of Nottingham only)
Language:English
Published: 2015
Subjects:
Online Access:https://eprints.nottingham.ac.uk/30798/
_version_ 1848794062636711936
author Sanchez Castillo, Ricardo
author_facet Sanchez Castillo, Ricardo
author_sort Sanchez Castillo, Ricardo
building Nottingham Research Data Repository
collection Online Access
description Out of the seven species of sea turtles in the world, six are classified as endangered. Mexico is home to five of these species which are protected by the government laws, however these animals are still subject to many threats, the most crucial is the poaching and illegal commerce of their eggs. There are programs related to the prevention of these illegal activities such as the surveillance of the beaches during nesting season but monitoring the long extension of beaches in the country is exhausting. In order to solve this problem, the current project proposes the use of drones to automatically detect sea turtle nests along the beach making use of machine learning and computer vision algorithms. However, sea turtle nests detection is a complex task due to the similarity between a nest and its surrounding area, therefore this project has explored the subject using the deep learning approach, particularly making use of Convolutional Neural Network architectures which have shown a success in challenges related to image classification and localisation and outperforms classical machine learning methods. In order to find the best architecture for this task, different architectures were trained and tested in similar conditions to classify an image as either nest or not a nest, then the best architecture was used for detecting nests using frames extracted from a video obtained using a drone. Finally, a tracking algorithm is proposed for detecting nests within a video stream in order to obtain a complete system for a real world application in a near future. Results show an encouraging performance in classification and recognition which is also non-dependent of the current task such that by performing the corresponding training, this algorithm could also be used for detecting another kind of objects. There is still research to be done but probably the first steps have been taken for this important task which can be useful for the conservation of this sea species.
first_indexed 2025-11-14T19:10:13Z
format Dissertation (University of Nottingham only)
id nottingham-30798
institution University of Nottingham Malaysia Campus
institution_category Local University
language English
last_indexed 2025-11-14T19:10:13Z
publishDate 2015
recordtype eprints
repository_type Digital Repository
spelling nottingham-307982017-10-19T15:04:56Z https://eprints.nottingham.ac.uk/30798/ Automatic sea turtle nest detection via deep learning Sanchez Castillo, Ricardo Out of the seven species of sea turtles in the world, six are classified as endangered. Mexico is home to five of these species which are protected by the government laws, however these animals are still subject to many threats, the most crucial is the poaching and illegal commerce of their eggs. There are programs related to the prevention of these illegal activities such as the surveillance of the beaches during nesting season but monitoring the long extension of beaches in the country is exhausting. In order to solve this problem, the current project proposes the use of drones to automatically detect sea turtle nests along the beach making use of machine learning and computer vision algorithms. However, sea turtle nests detection is a complex task due to the similarity between a nest and its surrounding area, therefore this project has explored the subject using the deep learning approach, particularly making use of Convolutional Neural Network architectures which have shown a success in challenges related to image classification and localisation and outperforms classical machine learning methods. In order to find the best architecture for this task, different architectures were trained and tested in similar conditions to classify an image as either nest or not a nest, then the best architecture was used for detecting nests using frames extracted from a video obtained using a drone. Finally, a tracking algorithm is proposed for detecting nests within a video stream in order to obtain a complete system for a real world application in a near future. Results show an encouraging performance in classification and recognition which is also non-dependent of the current task such that by performing the corresponding training, this algorithm could also be used for detecting another kind of objects. There is still research to be done but probably the first steps have been taken for this important task which can be useful for the conservation of this sea species. 2015-12-10 Dissertation (University of Nottingham only) NonPeerReviewed application/pdf en https://eprints.nottingham.ac.uk/30798/1/CS-dissert_PRIZE-WINNER_74_SanchezCastillo_Ricardo_2015.pdf Sanchez Castillo, Ricardo (2015) Automatic sea turtle nest detection via deep learning. [Dissertation (University of Nottingham only)] sea turtle nest deep learning convolutional neural network artificial intelligence.
spellingShingle sea turtle
nest
deep learning
convolutional neural network
artificial intelligence.
Sanchez Castillo, Ricardo
Automatic sea turtle nest detection via deep learning
title Automatic sea turtle nest detection via deep learning
title_full Automatic sea turtle nest detection via deep learning
title_fullStr Automatic sea turtle nest detection via deep learning
title_full_unstemmed Automatic sea turtle nest detection via deep learning
title_short Automatic sea turtle nest detection via deep learning
title_sort automatic sea turtle nest detection via deep learning
topic sea turtle
nest
deep learning
convolutional neural network
artificial intelligence.
url https://eprints.nottingham.ac.uk/30798/