Object detection and synthetic infrared image generation for UAV-based aerial images
| buir.advisor | Körpeoğlu, İbrahim | |
| dc.contributor.author | Özkanoğlu, Mehmet Akif | |
| dc.date.accessioned | 2023-09-22T10:21:30Z | |
| dc.date.available | 2023-09-22T10:21:30Z | |
| dc.date.copyright | 2023-09 | |
| dc.date.issued | 2023-09 | |
| dc.date.submitted | 2023-09-19 | |
| dc.department | Department of Computer Engineering | |
| dc.description | Cataloged from PDF version of article. | |
| dc.description | Thesis (Master's): Bilkent University, Department of Computer Engineering, İhsan Doğramacı Bilkent University, 2023. | |
| dc.description | Includes bibliographical references (leaves 81-94). | |
| dc.description.abstract | This thesis contains two main works related to aerial image processing. In the first work (in the first main part of this thesis), we present novel approaches to detect objects in aerial images. We introduce a novel object detection algorithm based on CenterNet which yields the state-of-the-art results in many metrics on many aerial benchmark datasets, when this thesis was written. In this part, we study the effect of different loss functions, and architectures for improving the detection performance of objects in aerial images taken by UAVs. We show that our proposed approaches help improving certain aspects of the learning process for detecting objects in aerial images. To train recent deep learning-based supervised object detection algorithms, the availability of annotations is essential. Many algorithms, today, use both infrared (IR) and visible (RGB) image pairs as input. However, large datasets (such as VisDrone [1] or ImageNet [2]) typically are captured in the visible spectrum. Therefore, a domain transfer-based approach to artificially generate in-frared equivalents of the visible images for existing datasets is presented in the second part of this thesis. Such image pairs, then, can be used to train object detection algorithms for either mode in future work. | |
| dc.description.degree | M.S. | |
| dc.description.statementofresponsibility | by Mehmet Akif Özkanoğlu | |
| dc.format.extent | xviii, 94 leaves : color illustrations, charts, tables ; 30 cm. | |
| dc.identifier.itemid | B162521 | |
| dc.identifier.uri | https://hdl.handle.net/11693/113892 | |
| dc.language.iso | English | |
| dc.publisher | Bilkent University | |
| dc.rights | info:eu-repo/semantics/openAccess | |
| dc.subject | Image generation | |
| dc.subject | Object detection | |
| dc.subject | Deep learning | |
| dc.subject | GANs | |
| dc.title | Object detection and synthetic infrared image generation for UAV-based aerial images | |
| dc.title.alternative | İHA tabanlı havadan görüntüler için nesne tespiti ve sentetik kızılötesi | |
| dc.type | Thesis |