E-CNN: Accurate Spherical Camera Rotation Estimation via Uniformization of Distorted Optical Flow Fields
Dabae Kim, Sarthak Pathak, Alessandro Moro, Ren Komatsu, Atsushi Yamashita, Hajime Asama
Abstract
Spherical cameras, which can acquire all-round information, are effective to estimate rotation for robotic applications. Recently, Convolutional Neural Networks have shown great robustness in solving such regression problems. However they are designed for planar images and cannot deal with the non-uniform distortion present in spherical images, when expressed in the planar equirectangular projection. This can lower the accuracy of motion estimation. In this research, we propose an Equirectangular-Convolutional Neural Network (E-CNN) to solve this issue. This novel network regresses 3D spherical camera rotation by uniformizing distorted optical flow patterns in the equirectangular projection. We experimentally show that this results in consistently lower error as opposed to learning from the distorted optical flow.
BibTeX
@inproceedings{icassp2019_ecnnaccuratesphe,
title = {E-CNN: Accurate Spherical Camera Rotation Estimation via Uniformization of Distorted Optical Flow Fields},
author = {Dabae Kim and Sarthak Pathak and Alessandro Moro and Ren Komatsu and Atsushi Yamashita and Hajime Asama},
booktitle = {ICASSP 2019},
year = {2019}
}