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

facebooktwittermailshare

360-degree Video Stitching for Dual-fisheye Lens Cameras Based On Rigid Moving Least Squares

Abstract: 

Dual-fisheye lens cameras are becoming popular for 360-degree video capture, especially for User-generated content (UGC), since they are affordable and portable. Images generated by the dual-fisheye cameras have limited overlap and hence require non-conventional stitching techniques to produce high-quality 360x180-degree panoramas. This paper introduces a novel method to align these images using interpolation grids based on rigid moving least squares. Furthermore, jitter is the critical issue arising when one applies the image-based stitching algorithms to video. It stems from the unconstrained movement of stitching boundary from one
frame to another. Therefore, we also propose a new algorithm to maintain the temporal coherence of stitching boundary to provide jitter-free 360-degree videos. Results show that the
method proposed in this paper can produce higher quality stitched images and videos than prior work.

up
0 users have voted:

Paper Details

Authors:
Tuan Ho, Ioannis Schizas, K. R. Rao, Madhukar Budagavi
Submitted On:
16 September 2017 - 5:42pm
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Tuan Ho
Paper Code:
2811
Document Year:
2017
Cite

Document Files

Tuan_ICIP17_Slides.pdf

(14 downloads)

ICIP_Supplement_Materials_paperID_2811.zip

(14 downloads)

Subscribe

[1] Tuan Ho, Ioannis Schizas, K. R. Rao, Madhukar Budagavi, "360-degree Video Stitching for Dual-fisheye Lens Cameras Based On Rigid Moving Least Squares", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1984. Accessed: Sep. 24, 2017.
@article{1984-17,
url = {http://sigport.org/1984},
author = {Tuan Ho; Ioannis Schizas; K. R. Rao; Madhukar Budagavi },
publisher = {IEEE SigPort},
title = {360-degree Video Stitching for Dual-fisheye Lens Cameras Based On Rigid Moving Least Squares},
year = {2017} }
TY - EJOUR
T1 - 360-degree Video Stitching for Dual-fisheye Lens Cameras Based On Rigid Moving Least Squares
AU - Tuan Ho; Ioannis Schizas; K. R. Rao; Madhukar Budagavi
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1984
ER -
Tuan Ho, Ioannis Schizas, K. R. Rao, Madhukar Budagavi. (2017). 360-degree Video Stitching for Dual-fisheye Lens Cameras Based On Rigid Moving Least Squares. IEEE SigPort. http://sigport.org/1984
Tuan Ho, Ioannis Schizas, K. R. Rao, Madhukar Budagavi, 2017. 360-degree Video Stitching for Dual-fisheye Lens Cameras Based On Rigid Moving Least Squares. Available at: http://sigport.org/1984.
Tuan Ho, Ioannis Schizas, K. R. Rao, Madhukar Budagavi. (2017). "360-degree Video Stitching for Dual-fisheye Lens Cameras Based On Rigid Moving Least Squares." Web.
1. Tuan Ho, Ioannis Schizas, K. R. Rao, Madhukar Budagavi. 360-degree Video Stitching for Dual-fisheye Lens Cameras Based On Rigid Moving Least Squares [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1984