Improving the performance of YOLO-based detection algorithms for small object detection in UAV-taken images

Simple item page
buir.advisorKörpeoğlu, İbrahim
dc.contributor.authorŞahin, Öykü
dc.date.accessioned2023-02-08T06:38:51Z
dc.date.available2023-02-08T06:38:51Z
dc.date.copyright2023-01
dc.date.issued2023-01
dc.date.submitted2023-01-19
dc.descriptionCataloged from PDF version of article.en_US
dc.descriptionThesis (Master's): Bilkent University, Department of Computer Engineering, İhsan Doğramacı Bilkent University, 2023.en_US
dc.descriptionIncludes bibliographical references (leaves 89-102).en_US
dc.description.abstractRecent advances in computer vision yield emerging novel applications for cameraequipped unmanned aerial vehicles such as object detection. The accuracy of the existing object detection solutions running on images acquired by Unmanned Aerial Vehicles (UAVs) is limited when compared to the performance of the object detection solutions designed for ground-taken images. Existing object detection solutions demonstrate lower performance on aerial datasets because of the reasons originating from the nature of the UAVs. These reasons can be summarized as: (i) the lack of large drone datasets with different types of objects, (ii) the larger variance in both scale and orientation of objects in drone images, and (iii) the difference in shape and texture of the features between the ground and the aerial images. Due to these reasons, YOLO-based models, a popular family of one-stage object detectors, perform insufficiently in UAV-based applications. In this thesis, two improved YOLO models: YOLODrone and YOLODrone+ are introduced for detecting objects in drone images. The performance of the models are tested on VisDrone2019 and SkyDataV1 datasets and improved results are reported when compared to the original YOLOv3 and YOLOv5 models.en_US
dc.description.provenanceSubmitted by Betül Özen (ozen@bilkent.edu.tr) on 2023-02-08T06:38:51Z No. of bitstreams: 1 B161702.pdf: 90361123 bytes, checksum: fb843ec858766bffad70cedf8c597788 (MD5)en
dc.description.provenanceMade available in DSpace on 2023-02-08T06:38:51Z (GMT). No. of bitstreams: 1 B161702.pdf: 90361123 bytes, checksum: fb843ec858766bffad70cedf8c597788 (MD5) Previous issue date: 2023-01en
dc.description.statementofresponsibilityby Öykü Şahinen_US
dc.format.extentxviii, 102 leaves : color illustrations, charts, tables ; 30 cm.en_US
dc.identifier.itemidB161702
dc.identifier.urihttp://hdl.handle.net/11693/111198
dc.language.isoEnglishen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectObject detectionen_US
dc.subjectDrone visionen_US
dc.subjectDeep neural networken_US
dc.subjectYOLOsen_US
dc.titleImproving the performance of YOLO-based detection algorithms for small object detection in UAV-taken imagesen_US
dc.title.alternativeKüçük nesne tanıma üzerine kullanılan YOLO tabanlı nesne tanıma algoritmalarının iyileştirilmesien_US
dc.typeThesisen_US
thesis.degree.disciplineComputer Engineering
thesis.degree.grantorBilkent University
thesis.degree.levelMaster's
thesis.degree.nameMS (Master of Science)

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
B161702.pdf
Size:
86.18 MB
Format:
Adobe Portable Document Format
Description:
Full printable version
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.69 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Graduate School of Engineering and Science