• Türkçe
    • English
  • English 
    • Türkçe
    • English
  • Login
View Item 
  •   DSpace@Medipol
  • Fakülteler
  • Mühendislik ve Doğa Bilimleri Fakültesi
  • Electrical and Electronics Engineering
  • Bildiri Koleksiyonu
  • View Item
  •   DSpace@Medipol
  • Fakülteler
  • Mühendislik ve Doğa Bilimleri Fakültesi
  • Electrical and Electronics Engineering
  • Bildiri Koleksiyonu
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Improved YOLOv4 for aerial object detection

Thumbnail

View/Open

Tam Metin / Full Text (956.6Kb)

Access

info:eu-repo/semantics/embargoedAccess

Date

2021

Author

Ali, Sharoze
Siddique, Arslan
Ateş, Hasan Fehmi
Güntürk, Bahadır Kürşat

Metadata

Show full item record

Citation

Ali, S., Siddique, A., Ateş, H. F. ve Güntürk, B. K. (2021). Improved YOLOv4 for aerial object detection. 29th IEEE Conference on Signal Processing and Communications Applications, SIU. Virtual, Istanbul, 9-11 June 2021. https://dx.doi.org/10.1109/SIU53274.2021.9478027

Abstract

Drones equipped with cameras are being used for surveillance purposes. These surveillance systems need vision-based object detection of ground objects which look very small because of the altitude of drones. We propose an improved YOLOv4 model targeted for vision-based small object detection. We investigated the performance of state of the art YOLOv4 object detector on the VisDrone dataset. We enhanced the features of small objects by connecting Upsampling layers and concatenating the upsampled features with the original features to obtain more refined and grained features for small objects. Experiments showed that the modified YOLOv4 achieved 2 percent better mAP results as compared to the original YOLOv4 at different image resolutions on the VisDrone dataset while running at the same speed as the original YOLOv4.

Source

29th IEEE Conference on Signal Processing and Communications Applications, SIU

URI

https://dx.doi.org/10.1109/SIU53274.2021.9478027
https://hdl.handle.net/20.500.12511/7811

Collections

  • Bildiri Koleksiyonu [192]
  • Bildiri Koleksiyonu [43]
  • Scopus İndeksli Yayınlar Koleksiyonu [5815]
  • WoS İndeksli Yayınlar Koleksiyonu [5982]



DSpace software copyright © 2002-2015  DuraSpace
Contact Us | Send Feedback
Theme by 
@mire NV
 

 




| Guide | Contact |

DSpace@Medipol

by OpenAIRE
Advanced Search

sherpa/romeo

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsInstitution AuthorORCIDTitlesSubjectsTypeLanguageDepartmentCategoryWoS Q ValueScopus Q ValuePublisherAccess TypeThis CollectionBy Issue DateAuthorsInstitution AuthorORCIDTitlesSubjectsTypeLanguageDepartmentCategoryWoS Q ValueScopus Q ValuePublisherAccess Type

My Account

LoginRegister

Statistics

View Google Analytics Statistics

DSpace software copyright © 2002-2015  DuraSpace
Contact Us | Send Feedback
Theme by 
@mire NV
 

 


|| Guide || Library || İstanbul Medipol University || OAI-PMH ||

Kütüphane ve Dokümantasyon Daire Başkanlığı, İstabul, Turkey
If you find any errors in content, please contact: [email protected]

Creative Commons License
DSpace@Medipol by İstanbul Medipol University Institutional Repository is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 4.0 Unported License..

DSpace@Medipol:


DSpace 6.2

tarafından İdeal DSpace hizmetleri çerçevesinde özelleştirilerek kurulmuştur.