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

Distortion-Robust Spherical Camera Motion Estimation via Dense Optical Flow

Citation Author(s):
Alessandro Moro, Hiromitsu Fujii, Atsushi Yamashita, Hajime Asama
Submitted by:
Sarthak Pathak
Last updated:
18 October 2018 - 2:08am
Document Type:
Poster
Document Year:
2018
Event:
Presenters Name:
Sarthak Pathak
Paper Code:
WA.P6.6

Abstract 

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:

Dataset Files

Conference Poster

(296)