Deep learning based event recognition in aerial imagery
dc.contributor.author | Şahin, A. H. | |
dc.contributor.author | Ateş, Hasan Fehmi | |
dc.date.accessioned | 2024-02-16T08:16:57Z | |
dc.date.available | 2024-02-16T08:16:57Z | |
dc.date.issued | 2023 | |
dc.identifier.isbn | 979-835034081-5 | |
dc.identifier.uri | http://hdl.handle.net/10679/9156 | |
dc.identifier.uri | https://ieeexplore.ieee.org/document/10286774 | |
dc.description.abstract | In this paper, we investigate event recognition for aerial surveillance. This is a significant task especially when we consider the growing popularity of UAVs. The main purpose of the paper is to detect events both at the clip level in aerial videos and also at the frame level in aerial images. To achieve this goal, novel deep learning models and training techniques are used. In this work, we propose new model architectures to detect events in both image and video domains. The developed models are tested on the ERA dataset. Results show that the proposed models achieve state-of-the-art performance on both single images and aerial video clips of the ERA dataset. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | IEEE | en_US |
dc.relation.ispartof | 2023 8th International Conference on Computer Science and Engineering (UBMK) | |
dc.rights | restrictedAccess | |
dc.title | Deep learning based event recognition in aerial imagery | en_US |
dc.type | Conference paper | en_US |
dc.publicationstatus | Published | en_US |
dc.contributor.department | Özyeğin University | |
dc.contributor.authorID | (ORCID 0000-0002-6842-1528 & YÖK ID 17416) Ateş, Hasan Fehmi | |
dc.contributor.ozuauthor | Ateş, Hasan Fehmi | |
dc.identifier.startpage | 426 | en_US |
dc.identifier.endpage | 431 | en_US |
dc.identifier.doi | 10.1109/UBMK59864.2023.10286774 | en_US |
dc.subject.keywords | Aerial event recognition | en_US |
dc.subject.keywords | Computer vision | en_US |
dc.subject.keywords | Deep learning | en_US |
dc.subject.keywords | Hierarchical dense layers | en_US |
dc.subject.keywords | Wide area imagery | en_US |
dc.identifier.scopus | SCOPUS:2-s2.0-85177554022 | |
dc.relation.publicationcategory | Conference Paper - International - Institutional Academic Staff |
Files in this item
Files | Size | Format | View |
---|---|---|---|
There are no files associated with this item. |
This item appears in the following Collection(s)
Share this page