Driving Video Prediction based on Motion Estimation of 3D Objects using a Stereo Camera System

Takuya Umemura, Fumihiko Sakaue, Jun Sato

2020

Abstract

In this paper, we propose a method to synthesize future images in a driving scene using a stereo camera system fitted on vehicles. In this method, three-dimensional (3D) objects in a driving scenario, such as vehicles, buildings, and humans, are reconstructed by a stereo camera system. The reconstructed objects are separated by semantic image segmentation based on 2D image information. Furthermore, motion prediction using a Kalman filter is applied to each object. 3D objects in future scenes are rendered using this motion prediction. However, some regions, which are occluded in the input images, cannot be predicted. Therefore, an image inpainting technique is used for the occluded regions in the input image. Experimental results show that our proposed method can synthesize natural predicted images.

Paper Citation

in Harvard Style

Umemura T., Sakaue F. and Sato J. (2020). Driving Video Prediction based on Motion Estimation of 3D Objects using a Stereo Camera System. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP; ISBN 978-989-758-402-2, SciTePress, pages 859-866. DOI: 10.5220/0009349108590866

in Bibtex Style

@conference{visapp20,
author={Takuya Umemura and Fumihiko Sakaue and Jun Sato},
title={Driving Video Prediction based on Motion Estimation of 3D Objects using a Stereo Camera System},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP},
year={2020},
pages={859-866},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009349108590866},
isbn={978-989-758-402-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP
TI - Driving Video Prediction based on Motion Estimation of 3D Objects using a Stereo Camera System
SN - 978-989-758-402-2
AU - Umemura T.
AU - Sakaue F.
AU - Sato J.
PY - 2020
SP - 859
EP - 866
DO - 10.5220/0009349108590866
PB - SciTePress