Vehicle tracking and speed estimation in aerial footage
| dc.contributor.advisor | Hadachi, Amnir, juhendaja | |
| dc.contributor.author | Juurik, Jorgen | |
| dc.contributor.other | Tartu Ülikool. Loodus- ja täppisteaduste valdkond | et |
| dc.contributor.other | Tartu Ülikool. Arvutiteaduse instituut | et |
| dc.date.accessioned | 2023-11-09T10:12:09Z | |
| dc.date.available | 2023-11-09T10:12:09Z | |
| dc.date.issued | 2020 | |
| dc.description.abstract | The field of object detection and object tracking has seen great improvements over the last few years with the innovation of modern machine learning algorithms and neural network models. Object tracking models can be utilized in many subjects, such as autonomous driving and surveillance. The goal of this thesis is to explore modern object detection and object tracking methods to construct a model which is able to track vehicles in top-down aerial footage. The YOLO method is used for creating the object detection model while a simple object tracking approach with Kalman Filtering is implemented. | et |
| dc.identifier.uri | https://hdl.handle.net/10062/94130 | |
| dc.language.iso | eng | et |
| dc.publisher | Tartu Ülikool | et |
| dc.rights | openAccess | et |
| dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 International | * |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | * |
| dc.subject | Neural Networks | et |
| dc.subject | Object detection | et |
| dc.subject | YOLO | et |
| dc.subject | Object tracking | et |
| dc.subject | Kalman Filtering | et |
| dc.subject.other | bakalaureusetööd | et |
| dc.subject.other | informaatika | et |
| dc.subject.other | infotehnoloogia | et |
| dc.subject.other | informatics | et |
| dc.subject.other | infotechnology | et |
| dc.title | Vehicle tracking and speed estimation in aerial footage | et |
| dc.type | Thesis | et |