Best Viewpoint Tracking for Camera Mounted on Robotic Arm with Dynamic Obstacles

Christos Maniatis; Marcelo Saval-Calvo; Radim Tylecek; Robert Fisher

doi:10.1109/3DV.2017.00022

Best Viewpoint Tracking for Camera Mounted on Robotic Arm with Dynamic Obstacles

Christos Maniatis, Marcelo Saval-Calvo, Radim Tylecek, Robert Fisher

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The problem of finding a next best viewpoint for 3D modeling or scene mapping has been explored in computer vision over the last decade. This paper tackles a similar problem, but with different characteristics. It proposes a method for dynamic next best viewpoint recovery of a target point while avoiding possible occlusions. Since the environment can change, the method has to iteratively find the next best view with a global understanding of the free and occupied parts.
We model the problem as a set of possible viewpoints which correspond to the centers of the facets of a virtual tessellated hemisphere covering the scene. Taking into account occlusions, distances between current and future viewpoints, quality of the viewpoint and joint constraints (robot arm joint distances or limits), we evaluate the next best viewpoint. The proposal has been evaluated on 8 different scenarios with different occlusions and a short 3D video sequence to validate its dynamic performance.

Original language	English
Title of host publication	Proceedings of the International Conference on 3D Vision 2017
Place of Publication	Qingdao, China
Publisher	Institute of Electrical and Electronics Engineers
Pages	107-115
Number of pages	9
ISBN (Electronic)	978-1-5386-2610-8
ISBN (Print)	978-1-5386-2611-5
DOIs	https://doi.org/10.1109/3DV.2017.00022
Publication status	Published - 7 Jun 2018
Event	International Conference on 3D Vision 2017 - Qingdao, China Duration: 10 Oct 2017 → 12 Oct 2017 http://irc.cs.sdu.edu.cn/3dv/

Publication series

Name
Publisher	IEEE
ISSN (Electronic)	2475-7888

Conference

Conference	International Conference on 3D Vision 2017
Abbreviated title	3DV 2017
Country/Territory	China
City	Qingdao
Period	10/10/17 → 12/10/17
Internet address	http://irc.cs.sdu.edu.cn/3dv/

Access to Document

10.1109/3DV.2017.00022

PID5042309Accepted author manuscript, 910 KB

https://ieeexplore.ieee.org/document/8374563

TrimBot2020-A gardening robot for rose, hedge and topiary trimming (coordinating)
Fisher, B. (Principal Investigator)
EU government bodies
1/01/16 → 31/12/19
Project: Research

Cite this

@inproceedings{d909db8d089640f9adfb63add877cee8,

title = "Best Viewpoint Tracking for Camera Mounted on Robotic Arm with Dynamic Obstacles",

abstract = "The problem of finding a next best viewpoint for 3D modeling or scene mapping has been explored in computer vision over the last decade. This paper tackles a similar problem, but with different characteristics. It proposes a method for dynamic next best viewpoint recovery of a target point while avoiding possible occlusions. Since the environment can change, the method has to iteratively find the next best view with a global understanding of the free and occupied parts.We model the problem as a set of possible viewpoints which correspond to the centers of the facets of a virtual tessellated hemisphere covering the scene. Taking into account occlusions, distances between current and future viewpoints, quality of the viewpoint and joint constraints (robot arm joint distances or limits), we evaluate the next best viewpoint. The proposal has been evaluated on 8 different scenarios with different occlusions and a short 3D video sequence to validate its dynamic performance.",

author = "Christos Maniatis and Marcelo Saval-Calvo and Radim Tylecek and Robert Fisher",

year = "2018",

month = jun,

day = "7",

doi = "10.1109/3DV.2017.00022",

language = "English",

isbn = "978-1-5386-2611-5",

publisher = "Institute of Electrical and Electronics Engineers",

pages = "107--115",

booktitle = "Proceedings of the International Conference on 3D Vision 2017",

address = "United States",

note = "International Conference on 3D Vision 2017, 3DV 2017 ; Conference date: 10-10-2017 Through 12-10-2017",

url = "http://irc.cs.sdu.edu.cn/3dv/",

}

Maniatis, C, Saval-Calvo, M, Tylecek, R & Fisher, R 2018, Best Viewpoint Tracking for Camera Mounted on Robotic Arm with Dynamic Obstacles. in Proceedings of the International Conference on 3D Vision 2017. Institute of Electrical and Electronics Engineers, Qingdao, China, pp. 107-115, International Conference on 3D Vision 2017, Qingdao, China, 10/10/17. https://doi.org/10.1109/3DV.2017.00022

Best Viewpoint Tracking for Camera Mounted on Robotic Arm with Dynamic Obstacles. / Maniatis, Christos; Saval-Calvo, Marcelo; Tylecek, Radim et al.
Proceedings of the International Conference on 3D Vision 2017. Qingdao, China: Institute of Electrical and Electronics Engineers, 2018. p. 107-115.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Best Viewpoint Tracking for Camera Mounted on Robotic Arm with Dynamic Obstacles

AU - Maniatis, Christos

AU - Saval-Calvo, Marcelo

AU - Tylecek, Radim

AU - Fisher, Robert

PY - 2018/6/7

Y1 - 2018/6/7

N2 - The problem of finding a next best viewpoint for 3D modeling or scene mapping has been explored in computer vision over the last decade. This paper tackles a similar problem, but with different characteristics. It proposes a method for dynamic next best viewpoint recovery of a target point while avoiding possible occlusions. Since the environment can change, the method has to iteratively find the next best view with a global understanding of the free and occupied parts.We model the problem as a set of possible viewpoints which correspond to the centers of the facets of a virtual tessellated hemisphere covering the scene. Taking into account occlusions, distances between current and future viewpoints, quality of the viewpoint and joint constraints (robot arm joint distances or limits), we evaluate the next best viewpoint. The proposal has been evaluated on 8 different scenarios with different occlusions and a short 3D video sequence to validate its dynamic performance.

AB - The problem of finding a next best viewpoint for 3D modeling or scene mapping has been explored in computer vision over the last decade. This paper tackles a similar problem, but with different characteristics. It proposes a method for dynamic next best viewpoint recovery of a target point while avoiding possible occlusions. Since the environment can change, the method has to iteratively find the next best view with a global understanding of the free and occupied parts.We model the problem as a set of possible viewpoints which correspond to the centers of the facets of a virtual tessellated hemisphere covering the scene. Taking into account occlusions, distances between current and future viewpoints, quality of the viewpoint and joint constraints (robot arm joint distances or limits), we evaluate the next best viewpoint. The proposal has been evaluated on 8 different scenarios with different occlusions and a short 3D video sequence to validate its dynamic performance.

U2 - 10.1109/3DV.2017.00022

DO - 10.1109/3DV.2017.00022

M3 - Conference contribution

SN - 978-1-5386-2611-5

SP - 107

EP - 115

BT - Proceedings of the International Conference on 3D Vision 2017

PB - Institute of Electrical and Electronics Engineers

CY - Qingdao, China

T2 - International Conference on 3D Vision 2017

Y2 - 10 October 2017 through 12 October 2017

ER -

Best Viewpoint Tracking for Camera Mounted on Robotic Arm with Dynamic Obstacles

Abstract

Publication series

Conference

Access to Document

Fingerprint

Projects

TrimBot2020-A gardening robot for rose, hedge and topiary trimming (coordinating)

Cite this