Automatic detection of endangered species in video and satellite images using deep learning
Document typeBachelor thesis
Rights accessRestricted access - author's decision
All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder
A work on processing techniques using Deep Learning (Convolutional Neural Networks) to detect and classify marine mammals in aerial photographs. The computational capacity offered by these new tools will allow the scientific community to better study endangered species and to give an adequate and rapid response to face the current biodiversity crisis. For this project there isn’t much of a problem to solve but an opportunity to improve. Improve upon the project that was left which tried to choose the appropriate architecture, build a completely new dataset and figure out what are the best parameters in order to achieve certain goals.
SubjectsNeural networks (Computer science), Machine learning, Video recording, Xarxes neuronals (Informàtica), Aprenentatge automàtic, Vídeo
DegreeGRAU EN ENGINYERIA INFORMÀTICA (Pla 2010)