KLI

Improved YOLOv3 with duplex FPN for object detection based on deep learning

Metadata Downloads
Abstract
YOLOv3 is a deep learning-based real-time object detector and is mainly used in applications such as video surveillance and autonomous vehicles. In this paper, we proposed an improved YOLOv3 (You Only Look Once version 3) applied Duplex FPN, which enhanced large object detection by utilizing low-level feature information. The conventional YOLOv3 improved the small object detection performance by applying FPN (Feature Pyramid Networks) structure to YOLOv2. However, YOLOv3 with an FPN structure specialized in detecting small objects, so it is difficult to detect large objects. Therefore, this paper proposed an improved YOLOv3 applied Duplex FPN, which can utilize low-level location information in high-level feature maps instead of the existing FPN structure of YOLOv3. This improved the detection accuracy of large objects. Also, an extra detection layer was added to the top-level feature map to prevent failure of detection of parts of large objects. Further, dimension clusters of each detection layer were reassigned to learn quickly how to accurately detect objects. The proposed method was compared and analyzed in the PASCAL VOC dataset. The experimental results showed that the bounding box accuracy of large objects improved owing to the Duplex FPN and extra detection layer, and the proposed method succeeded in detecting large objects that the existing YOLOv3 did not.
Author(s)
신석용한현호이상훈
Issued Date
2021
Type
Article
Keyword
YOLOv3FPNDarknetobject detectiondeep learning
DOI
10.1177/0020720920983524
URI
https://oak.ulsan.ac.kr/handle/2021.oak/9173
https://ulsan-primo.hosted.exlibrisgroup.com/primo-explore/fulldisplay?docid=TN_cdi_gale_infotrac_658872557&context=PC&vid=ULSAN&lang=ko_KR&search_scope=default_scope&adaptor=primo_central_multiple_fe&tab=default_tab&query=any,contains,Improved%20YOLOv3%20with%20duplex%20FPN%20for%20object%20detection%20based%20on%20deep%20learning&offset=0&pcAvailability=true
Publisher
INTERNATIONAL JOURNAL OF ELECTRICAL ENGINEERING EDUCATION
Location
영국
Language
영어
ISSN
0020-7209
Citation Number
0
Citation Start Page
0
Citation End Page
0
Appears in Collections:
Engineering > IT Convergence
Authorize & License
  • Authorize공개
Files in This Item:
  • There are no files associated with this item.

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.