142 0

Deep Learning-Based Vehicle Orientation Estimation with Analysis of Training Models on Virtual-Worlds

Title
Deep Learning-Based Vehicle Orientation Estimation with Analysis of Training Models on Virtual-Worlds
Author
박장현
Keywords
ADAS; Computer Vision; Vehicle Orientation Estimation; Deep Learning; Synthetic data
Issue Date
2019-07
Publisher
IEEE
Citation
2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA), Page. 1-7
Abstract
This paper clarifies an issue that the most commonly used ADAS sensors, monocular camera and radar, do not provide abundant information about dynamically changing road scenes. In order to make the sensor more useful for a wide range of ADAS functions, we present an approach to estimate the orientation of surrounding vehicles using deep neural network. We show the possibility that camera-based method can get more competitive, evaluating it on the KITTI Orientation Estimation Benchmark, and also verifying it on our test-driving scenarios. Although its localization performance is not perfect, our model is able to reliably predict the orientation when fine conditions are given. In addition, we further study on training models using synthetic dataset, and share the weakness of this method when comparing to LiDAR-based approach on several conditions such as fully-visible, lightly/heavily-occluded and shading/lighting circumstances.
URI
https://ieeexplore.ieee.org/document/8900756https://repository.hanyang.ac.kr/handle/20.500.11754/152163
ISBN
978-1-7281-4959-2
DOI
10.1109/IISA.2019.8900756
Appears in Collections:
COLLEGE OF ENGINEERING[S](공과대학) > AUTOMOTIVE ENGINEERING(미래자동차공학과) > Articles
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

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

BROWSE