Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Distortion-Robust Spherical Camera Motion Estimation via Dense Optical Flow

Abstract: 

Conventional techniques for frame-to-frame camera motion estimation rely on tracking a set of sparse feature points. However, images taken from spherical cameras have high distortion which can induce mistakes in feature point tracking, offsetting the advantage of their large fields-of-view. Hence, in this research, we attempt a novel approach of using dense optical flow for distortion-robust spherical camera motion estimation. Dense optical flow incorporates smoothing terms and is free of local outliers. It encodes the camera motion as well as dense 3D information. Our approach decomposes dense optical flow into epipolar geometry and the dense disparity map, and reprojects this disparity map to estimate 6 DoF camera motion. The approach handles spherical image distortion in a natural way. We experimentally demonstrate its accuracy and robustness.

up
0 users have voted:

Paper Details

Authors:
Alessandro Moro, Hiromitsu Fujii, Atsushi Yamashita, Hajime Asama
Submitted On:
18 October 2018 - 2:08am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Sarthak Pathak
Paper Code:
WA.P6.6
Document Year:
2018
Cite

Document Files

Conference Poster

(25 downloads)

Subscribe

[1] Alessandro Moro, Hiromitsu Fujii, Atsushi Yamashita, Hajime Asama, "Distortion-Robust Spherical Camera Motion Estimation via Dense Optical Flow", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3667. Accessed: Nov. 19, 2018.
@article{3667-18,
url = {http://sigport.org/3667},
author = {Alessandro Moro; Hiromitsu Fujii; Atsushi Yamashita; Hajime Asama },
publisher = {IEEE SigPort},
title = {Distortion-Robust Spherical Camera Motion Estimation via Dense Optical Flow},
year = {2018} }
TY - EJOUR
T1 - Distortion-Robust Spherical Camera Motion Estimation via Dense Optical Flow
AU - Alessandro Moro; Hiromitsu Fujii; Atsushi Yamashita; Hajime Asama
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3667
ER -
Alessandro Moro, Hiromitsu Fujii, Atsushi Yamashita, Hajime Asama. (2018). Distortion-Robust Spherical Camera Motion Estimation via Dense Optical Flow. IEEE SigPort. http://sigport.org/3667
Alessandro Moro, Hiromitsu Fujii, Atsushi Yamashita, Hajime Asama, 2018. Distortion-Robust Spherical Camera Motion Estimation via Dense Optical Flow. Available at: http://sigport.org/3667.
Alessandro Moro, Hiromitsu Fujii, Atsushi Yamashita, Hajime Asama. (2018). "Distortion-Robust Spherical Camera Motion Estimation via Dense Optical Flow." Web.
1. Alessandro Moro, Hiromitsu Fujii, Atsushi Yamashita, Hajime Asama. Distortion-Robust Spherical Camera Motion Estimation via Dense Optical Flow [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3667