A Study for Selecting the Best One-Stage Detector for Autonomous Driving

Dayoung Chun, Jiwoong Choi, Hyun Kim, Hyuk Jae Lee

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

6 Scopus citations

Abstract

A development of deep learning has accelerated research into autonomous driving. Especially, deep-learning based object detection has been actively studied and has become an essential technology for autonomous driving. In this paper, the representative one-stage detectors are evaluated and compared using the autonomous driving dataset, and the best algorithm is proposed in terms of trade-off between detection accuracy and processing speed. In addition, the effect of input size in utilizing this algorithm for autonomous driving application is analyzed through various experiments, and finally the most suitable input size for autonomous driving is proposed.

Original languageEnglish
Title of host publication34th International Technical Conference on Circuits/Systems, Computers and Communications, ITC-CSCC 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728132716
DOIs
StatePublished - Jun 2019
Event34th International Technical Conference on Circuits/Systems, Computers and Communications, ITC-CSCC 2019 - JeJu, Korea, Republic of
Duration: 23 Jun 201926 Jun 2019

Publication series

Name34th International Technical Conference on Circuits/Systems, Computers and Communications, ITC-CSCC 2019

Conference

Conference34th International Technical Conference on Circuits/Systems, Computers and Communications, ITC-CSCC 2019
Country/TerritoryKorea, Republic of
CityJeJu
Period23/06/1926/06/19

Keywords

  • Autonomous driving
  • Object detection
  • One-stage detector
  • YOLOv3

Fingerprint

Dive into the research topics of 'A Study for Selecting the Best One-Stage Detector for Autonomous Driving'. Together they form a unique fingerprint.

Cite this