Identification and Classification of Wildlife from Camera-Trap Images using Machine Learning and Computer Vision

Sheikh, Nawaz (2020) Identification and Classification of Wildlife from Camera-Trap Images using Machine Learning and Computer Vision. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (2MB) | Preview
Preview	PDF (Configuration manual) Download (4MB) | Preview

Abstract

An active research on flora and fauna is carried out since last few decades. We have focused on analysis of wildlife monitoring acquired from camera-trap networks which provides data from natural scenes. Camera-traps are placed in wildlife sanctuaries, national parks and reserves all over the world. It is the best practice to monitor wildlife from the images captured using camera-traps. Citizen science community consists of many researchers and citizen scientists who work on the data gathered from camera-traps and apply various machine learning and computer vision algorithms so that the results can be used in wildlife conservation. This project focuses on classifying animal species gathered from the Missouri Camera Traps dataset using InceptionV3, MobileNet and VGG-16 architectures of deep convolutional neural networks. Also, the weights from this project can be used in transfer learning to classify similar animal species on another dataset. Our intensive results shows that DCNN provides accuracy of 69.5% for the model of InceptionV3 for six classes of animals from the Missouri Camera Traps dataset.
Keywords: Wildlife, Camera-traps, Machine Learning, Deep convolutional neural networks, Computer Vision, Transfer Learning

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software G Geography. Anthropology. Recreation > GE Environmental Sciences > Environment
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Dan English
Date Deposited:	15 Jun 2020 11:42
Last Modified:	15 Jun 2020 11:42
URI:	https://norma.ncirl.ie/id/eprint/4283

Actions (login required)

View Item