26 0

SweepNet: Wide-baseline Omnidirectional Depth Estimation

Title
SweepNet: Wide-baseline Omnidirectional Depth Estimation
Author
임종우
Keywords
Cameras; Lenses; Calibration; Neural networks; Three-dimensional displays; Robot vision systems
Issue Date
2019-05
Publisher
IEEE
Citation
IEEE International Conference on Robotics and Automation, Page. 6073-6079
Abstract
Omnidirectional depth sensing has its advantage over the conventional stereo systems since it enables us to recognize the objects of interest in all directions without any blind regions. In this paper, we propose a novel wide-baseline omnidirectional stereo algorithm which computes the dense depth estimate from the fisheye images using a deep convolutional neural network. The capture system consists of multiple cameras mounted on a wide-baseline rig with ultra-wide field of view (FOV) lenses, and we present the calibration algorithm for the extrinsic parameters based on the bundle adjustment. Instead of estimating depth maps from multiple sets of rectified images and stitching them, our approach directly generates one dense omnidirectional depth map with full 360° coverage at the rig global coordinate system. To this end, the proposed neural network is designed to output the cost volume from the warped images in the sphere sweeping method, and the final depth map is estimated by taking the minimum cost indices of the aggregated cost volume by SGM. For training the deep neural network and testing the entire system, realistic synthetic urban datasets are rendered using Blender. The experiments using the synthetic and real-world datasets show that our algorithm outperforms the conventional depth estimation methods and generate highly accurate depth maps.
URI
https://ieeexplore.ieee.org/document/8793823http://repository.hanyang.ac.kr/handle/20.500.11754/114931
ISBN
978-153866026-3
ISSN
2577-087X
DOI
10.1109/ICRA.2019.8793823
Appears in Collections:
COLLEGE OF ENGINEERING[S](공과대학) > COMPUTER SCIENCE(컴퓨터소프트웨어학부) > Articles
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE