All-Around 3D Reconstruction from Spherical Images with Semantic Segmentation

被引：0

作者：

Pennanen, Tuulia ^{[1
]}

Ariram, Siva ^{[1
]}

Tikanmaki, Antti ^{[1
]}

Roning, Juha ^{[1
]}

机构：

[1] Univ Oulu, Biomimet & Intelligent Syst Grp, Oulu, Finland

来源：

2021 IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS AND AUTOMATION (IEEE ICMA 2021) | 2021年

关键词：

3D reconstruction; semantic segmentation; spherical images; mobile robotics; ROBUST;

D O I：

10.1109/ICMA52036.2021.9512619

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Lightweight, affordable spherical cameras can be utilized in mobile robotics to build a 3D map of the working environment of a robot. This paper demonstrates how to use the optical flow between two spherical images to quickly construct a semantically meaningful 3D model spanning all directions. The main contribution of the paper is the use of semantic segmentation to increase the robustness of the reconstruction method in both indoor and outdoor applications.

引用

页码：193 / 199

页数：7

共 14 条

[11] Robust and Efficient Indoor Localization Using Sparse Semantic Information from a Spherical Camera [J].

Uygur, Irem ;

Miyagusuku, Renato ;

Pathak, Sarthak ;

Moro, Alessandro ;

Yamashita, Atsushi ;

Asama, Hajime .

SENSORS, 2020, 20 (15) :1-21

[12]

Wada K., 2016, Labelme: Image Polygonal Annotation With Python

[13]

Yang Gengshan, 2019, Advances in neural information processing systems, V5, P12

[14] OmniDepth: Dense Depth Estimation for Indoors Spherical Panoramas [J].

Zioulis, Nikolaos ;

Karakottas, Antonis ;

Zarpalas, Dimitrios ;

Daras, Petros .

COMPUTER VISION - ECCV 2018, PT VI, 2018, 11210 :453-471

← 1 2 →