Sensor Placement for Active Modeling of Unknown Objects

S. Y. Chen; Y. F. Li; R. S. Lu

Sensor Placement for Active Modeling of Unknown Objects

S. Y. Chen
, Y. F. Li
, R. S. Lu

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

2 Citations (Scopus)

Abstract

This paper presents a novel method to solve the next viewpoint problem in active vision systems for modeling of unknown objects or environments. It is based on the surface trend method, that is, the unknown part of surface is proposed to have the same trend as the known part of the object and the surface curvature is smoothly changing. A mathematical model is established to predict the unknown part of object surface and then the next viewpoint can be determined. The new viewpoint is planned with great efficiency and satisfying lots of sensor placement constraints such as resolution, in focus, and field of view. In addition, some experiments are also provided for demonstrating that the method can work very well in modeling freeform objects.

Original language	English
Title of host publication	Proceedings of the Joint Conference on Information Sciences
Pages	749-752
Volume	6
Publication status	Published - 2002
Event	Proceedings of the 6th Joint Conference on Information Sciences, JCIS 2002 - Research Triange Park, NC, United States Duration: 8 Mar 2002 → 13 Mar 2002

Publication series

Name
Volume	6

Conference

Conference	Proceedings of the 6th Joint Conference on Information Sciences, JCIS 2002
Place	United States
City	Research Triange Park, NC
Period	8/03/02 → 13/03/02

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{bc90c4e582734627afbffac73bdb954a,

title = "Sensor Placement for Active Modeling of Unknown Objects",

abstract = "This paper presents a novel method to solve the next viewpoint problem in active vision systems for modeling of unknown objects or environments. It is based on the surface trend method, that is, the unknown part of surface is proposed to have the same trend as the known part of the object and the surface curvature is smoothly changing. A mathematical model is established to predict the unknown part of object surface and then the next viewpoint can be determined. The new viewpoint is planned with great efficiency and satisfying lots of sensor placement constraints such as resolution, in focus, and field of view. In addition, some experiments are also provided for demonstrating that the method can work very well in modeling freeform objects.",

author = "Chen, \{S. Y.\} and Li, \{Y. F.\} and Lu, \{R. S.\}",

year = "2002",

language = "English",

isbn = "970789017",

volume = "6",

pages = "749--752",

booktitle = "Proceedings of the Joint Conference on Information Sciences",

note = "Proceedings of the 6th Joint Conference on Information Sciences, JCIS 2002 ; Conference date: 08-03-2002 Through 13-03-2002",

}

TY - GEN

T1 - Sensor Placement for Active Modeling of Unknown Objects

AU - Chen, S. Y.

AU - Li, Y. F.

AU - Lu, R. S.

PY - 2002

Y1 - 2002

N2 - This paper presents a novel method to solve the next viewpoint problem in active vision systems for modeling of unknown objects or environments. It is based on the surface trend method, that is, the unknown part of surface is proposed to have the same trend as the known part of the object and the surface curvature is smoothly changing. A mathematical model is established to predict the unknown part of object surface and then the next viewpoint can be determined. The new viewpoint is planned with great efficiency and satisfying lots of sensor placement constraints such as resolution, in focus, and field of view. In addition, some experiments are also provided for demonstrating that the method can work very well in modeling freeform objects.

AB - This paper presents a novel method to solve the next viewpoint problem in active vision systems for modeling of unknown objects or environments. It is based on the surface trend method, that is, the unknown part of surface is proposed to have the same trend as the known part of the object and the surface curvature is smoothly changing. A mathematical model is established to predict the unknown part of object surface and then the next viewpoint can be determined. The new viewpoint is planned with great efficiency and satisfying lots of sensor placement constraints such as resolution, in focus, and field of view. In addition, some experiments are also provided for demonstrating that the method can work very well in modeling freeform objects.

UR - https://www.scopus.com/pages/publications/1642271380

UR - https://www.scopus.com/pages/publications/1642271380#tab=impact

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 970789017

VL - 6

SP - 749

EP - 752

BT - Proceedings of the Joint Conference on Information Sciences

T2 - Proceedings of the 6th Joint Conference on Information Sciences, JCIS 2002

Y2 - 8 March 2002 through 13 March 2002

ER -

Sensor Placement for Active Modeling of Unknown Objects

Abstract

Publication series

Conference

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this