A transfer learning approach to wildlife identification and classification

Simple item page
dc.contributor.authorNaran, Jagruthi
dc.date.accessioned2022-09-29T08:14:29Z
dc.date.available2022-09-29T08:14:29Z
dc.date.issued2021
dc.descriptionA dissertation submitted to the Faculty of Engineering and the Built Environment, University of the Witwatersrand, Johannesburg, in fulfilment of the requirements for the degree of Master of Science in Engineering, 2021en_ZA
dc.description.abstractGlobal climate change is having a significant effect on ecosystems, causing species to vary their behaviour and migrate to more suitable regions. This will require more sustainable management of wildlife populations. Despite research conducted on the identification of wildlife through traditional and deep learning techniques, the challenge of large, labelled datasets required to perform these tasks still exists. In this study, a transfer learning approach is presented for wildlife classification applications. Four pretrained models were trained to identify wildlife in 48 species from the Snapshot Serengeti, Greenpeace and African Wildlife Foundation image datasets. This was done by using two transfer learning techniques, namely freeze-layer and fine-tuning, varying the learning rate and using different pretrained models, namely AlexNet, GoogLeNet, ResNet-101 and VGG-19. Results show that deeper, fine-tuned networks with lower learning rates result in higher classification accuracies. In addition, a comparison of the training times confirmed that the run times for the freeze-layer models were shorter than those of the fine-tuned models. The best result achieved a top-1 and top-5 accuracy of 100% for the ResNet-101 modelen_ZA
dc.description.librarianCK2022en_ZA
dc.facultyFaculty of Engineering and the Built Environmenten_ZA
dc.identifier.urihttps://hdl.handle.net/10539/33366
dc.language.isoenen_ZA
dc.schoolSchool of Mechanical, Industrial and Aeronautical Engineeringen_ZA
dc.titleA transfer learning approach to wildlife identification and classificationen_ZA
dc.typeThesisen_ZA
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
Cover Page & Abstract.pdf
Size:
132.16 KB
Format:
Adobe Portable Document Format
Description:
Download
Thumbnail Image
Name:
MScFull.pdf
Size:
13.98 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
ETD Collection