Developing visual sensing strategies through next best view planning

Enrique Dunn; Jur Van Den Berg; Jan Michael Frahm

doi:10.1109/IROS.2009.5354179

Developing visual sensing strategies through next best view planning

Enrique Dunn, Jur Van Den Berg, Jan Michael Frahm

Department of Computer Science

Stevens Institute of Technology

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

Abstract

We propose an approach for acquiring geometric 3D models using cameras mounted on autonomous vehicles and robots. Our method uses structure from motion techniques from computer vision to obtain the geometric structure of the scene. To achieve an efficient goal-driven resource deployment, we develop an incremental approach, which alternates between an accuracy-driven next best view determination and recursive path planning. The next best view is determined by a novel cost function that quantifies the expected contribution of future viewing configurations. A sensing path for robot motion towards the next best view is then achieved by a cost-driven recursive search of intermediate viewing configurations. We discuss some of the properties of our view cost function in the context of an iterative view planning process and present experimental results on a synthetic environment.

Original language	English
Title of host publication	2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009
Pages	4001-4008
Number of pages	8
DOIs	https://doi.org/10.1109/IROS.2009.5354179
State	Published - Dec 11 2009
Event	2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009 - St. Louis, MO, United States Duration: Oct 11 2009 → Oct 15 2009

Publication series

Name	2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009

Conference

Conference	2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009
Country/Territory	United States
City	St. Louis, MO
Period	10/11/09 → 10/15/09

ASJC Scopus subject areas

Artificial Intelligence
Computer Vision and Pattern Recognition
Human-Computer Interaction
Control and Systems Engineering

Access to Document

10.1109/IROS.2009.5354179

Cite this

@inproceedings{f80c9cd6b8f54b229f2a63db22385e8e,

title = "Developing visual sensing strategies through next best view planning",

abstract = "We propose an approach for acquiring geometric 3D models using cameras mounted on autonomous vehicles and robots. Our method uses structure from motion techniques from computer vision to obtain the geometric structure of the scene. To achieve an efficient goal-driven resource deployment, we develop an incremental approach, which alternates between an accuracy-driven next best view determination and recursive path planning. The next best view is determined by a novel cost function that quantifies the expected contribution of future viewing configurations. A sensing path for robot motion towards the next best view is then achieved by a cost-driven recursive search of intermediate viewing configurations. We discuss some of the properties of our view cost function in the context of an iterative view planning process and present experimental results on a synthetic environment.",

author = "Enrique Dunn and {Van Den Berg}, Jur and Frahm, {Jan Michael}",

year = "2009",

month = dec,

day = "11",

doi = "10.1109/IROS.2009.5354179",

language = "English",

isbn = "9781424438044",

series = "2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009",

pages = "4001--4008",

booktitle = "2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009",

note = "2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009 ; Conference date: 11-10-2009 Through 15-10-2009",

}

Dunn, E, Van Den Berg, J & Frahm, JM 2009, Developing visual sensing strategies through next best view planning. in 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009., 5354179, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009, pp. 4001-4008, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009, St. Louis, MO, United States, 10/11/09. https://doi.org/10.1109/IROS.2009.5354179

Developing visual sensing strategies through next best view planning. / Dunn, Enrique; Van Den Berg, Jur; Frahm, Jan Michael.
2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009. 2009. p. 4001-4008 5354179 (2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009).

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

TY - GEN

T1 - Developing visual sensing strategies through next best view planning

AU - Dunn, Enrique

AU - Van Den Berg, Jur

AU - Frahm, Jan Michael

PY - 2009/12/11

Y1 - 2009/12/11

N2 - We propose an approach for acquiring geometric 3D models using cameras mounted on autonomous vehicles and robots. Our method uses structure from motion techniques from computer vision to obtain the geometric structure of the scene. To achieve an efficient goal-driven resource deployment, we develop an incremental approach, which alternates between an accuracy-driven next best view determination and recursive path planning. The next best view is determined by a novel cost function that quantifies the expected contribution of future viewing configurations. A sensing path for robot motion towards the next best view is then achieved by a cost-driven recursive search of intermediate viewing configurations. We discuss some of the properties of our view cost function in the context of an iterative view planning process and present experimental results on a synthetic environment.

AB - We propose an approach for acquiring geometric 3D models using cameras mounted on autonomous vehicles and robots. Our method uses structure from motion techniques from computer vision to obtain the geometric structure of the scene. To achieve an efficient goal-driven resource deployment, we develop an incremental approach, which alternates between an accuracy-driven next best view determination and recursive path planning. The next best view is determined by a novel cost function that quantifies the expected contribution of future viewing configurations. A sensing path for robot motion towards the next best view is then achieved by a cost-driven recursive search of intermediate viewing configurations. We discuss some of the properties of our view cost function in the context of an iterative view planning process and present experimental results on a synthetic environment.

UR - http://www.scopus.com/inward/record.url?scp=76249113893&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=76249113893&partnerID=8YFLogxK

U2 - 10.1109/IROS.2009.5354179

DO - 10.1109/IROS.2009.5354179

M3 - Conference contribution

SN - 9781424438044

T3 - 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009

SP - 4001

EP - 4008

BT - 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009

T2 - 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009

Y2 - 11 October 2009 through 15 October 2009

ER -

Developing visual sensing strategies through next best view planning

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Cite this