Main content

Deep Learning Based Computer Vision for Animal Re-Identification

Show simple item record

dc.contributor.advisor Kremer, Stefan
dc.contributor.author Schneider, Stefan
dc.date.accessioned 2020-06-23T15:51:04Z
dc.date.available 2020-06-23T15:51:04Z
dc.date.copyright 2020-06
dc.date.created 2020-06-17
dc.date.issued 2020-06-23
dc.identifier.uri http://hdl.handle.net/10214/18056
dc.description.abstract Animal re-identification (re-ID) is fundamental to our understanding of community ecology, population dynamics and ethological analyses. Recent advances in the area of deep learning for computer vision offer a promising solution to improve upon the current methodologies for animal re-ID. The success of deep learning methods for human re-ID is well documented when ample training images are available for each individual. Despite this success, little has been done utilizing their capabilities for animal re-ID. In order to implement animal re-ID systems in practice, deep learning systems must be able to accomplish a variety of computer vision objectives. These include: quantifying the number of animals in an image, classifying the animal species within an image, localizing and extracting animal individuals within an image, and lastly re-identifying animal individuals. This work begins with a review of computer vision methods for animal re-ID (Chapter 2). I explore the quantification of animal individuals from images considering fish and dolphin counts in the Amazon River (Chapter 3). I then demonstrate the success of deep learning methods considering species identification, strategies for handling class imbalance, and quantifying performance when testing on background locations that are included/excluded from training (Chapter 4). I demonstrate the ability of deep learning systems to classify and localize animal species from camera trap images considering three global environments (Chapter 5). I then utilize five animal individual data sets to compare the success and generality of similarity comparison deep learning methods for animal re-ID (Chapter 6). Finally, I demonstrate these techniques in combination to successfully implement animal re-ID for an entirely novel study of Octopus tetricus social behaviour (Chapter 7). This work describes the complete animal re-ID pipeline for ecologists to follow in practice, outlining expected accuracies and guidelines for best practices. It imprints results to the machine learning research community considering tasks relative to the under represented task of animal re-ID. This work provides details on the necessary components required to achieve real-time camera trap survey systems. Lastly, this work encourages the progress of interdisciplinary areas of science. en_US
dc.language.iso en en_US
dc.subject Deep Learning en_US
dc.subject Animal Re-Identification en_US
dc.subject Computer Vision en_US
dc.subject Neural Network en_US
dc.subject Ethology en_US
dc.subject Octopus en_US
dc.subject Serengeti en_US
dc.subject Machine Learning en_US
dc.subject AI en_US
dc.subject Population Monitoring en_US
dc.subject Population Dynamics en_US
dc.subject Camera Trap en_US
dc.title Deep Learning Based Computer Vision for Animal Re-Identification en_US
dc.type Thesis en_US
dc.degree.programme Computer Science en_US
dc.degree.name Doctor of Philosophy en_US
dc.degree.department School of Computer Science en_US
dc.rights.license All items in the Atrium are protected by copyright with all rights reserved unless otherwise indicated.


Files in this item

Files Size Format View Description
Schneider_Stefan_202006_PhD.pdf 17.90Mb PDF View/Open Thesis PDF

This item appears in the following Collection(s)

Show simple item record