Autor: |
Ji-Woong Choi, Dayoung Chun, Hyuk-Jae Lee, Hyun Kim |
Rok vydání: |
2019 |
Předmět: |
|
Zdroj: |
2019 34th International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC). |
DOI: |
10.1109/itc-cscc.2019.8793291 |
Popis: |
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. |
Databáze: |
OpenAIRE |
Externí odkaz: |
|