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

Park, Jongkuk; Yoon, Yookhyun; Park, Jahnghyon

doi:10.1109/IISA.2019.8900756

상세 보기

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

Park, Jongkuk;
Yoon, Yookhyun;
Park, Jahnghyon

Citations

WEB OF SCIENCE

0

Citations

SCOPUS

0

초록

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.

키워드

ADAS; Computer Vision; Deep Learning; Synthetic data; Vehicle Orientation Estimation; VISION; Cameras; Computer vision; Deep learning; Deep neural networks; Optical radar; Vehicles; Virtual reality; ADAS; Localization performance; Monocular cameras; Orientation estimation; Synthetic data; Training model; Vehicle orientation; Virtual worlds; E-learning

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

저자: Park, Jongkuk; Yoon, Yookhyun; Park, Jahnghyon

DOI: 10.1109/IISA.2019.8900756

발행일: 2019-07

유형: Conference Paper

저널명: 2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA)

페이지: 1 ~ 7