Multiple concurrent object descriptions in support of autonomous navigation

Aaron F. Bobick; Robert C. Bolles

Multiple concurrent object descriptions in support of autonomous navigation

Aaron F. Bobick
, Robert C. Bolles

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

Abstract

A sensor system designed to support autonomous navigation should provide a stable, robust model of the environment. We propose and illustrate an approach in which multiple concurrent descriptions of objects are used to construct such a stable model. The principal idea is that several different representations are used to describe the same object in order to support different visual tasks, and to insure an appropriate match between the data, the model, and the task. The use of multiple representations to describe objects requires that the system be able to decide which descriptions of an object are valid. In our approach we use stability over time to indicate validity. To illustrate the power of this approach we have implemented a system, 'TraX', that constructs and refines models of outdoor objects detected in sequences of range data.

Original language	English
Title of host publication	Proceedings of SPIE - The International Society for Optical Engineering
Publisher	Publ by Int Soc for Optical Engineering
Pages	383-392
Number of pages	10
ISBN (Print)	0819410292
State	Published - 1993
Event	Sensor Fusion V - Boston, MA, USA Duration: Nov 15 1992 → Nov 17 1992

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	1828
ISSN (Print)	0277-786X

Conference

Conference	Sensor Fusion V
City	Boston, MA, USA
Period	11/15/92 → 11/17/92

Cite this

@inproceedings{1fb9e5b06d5d4dea97030965d8832dee,

title = "Multiple concurrent object descriptions in support of autonomous navigation",

abstract = "A sensor system designed to support autonomous navigation should provide a stable, robust model of the environment. We propose and illustrate an approach in which multiple concurrent descriptions of objects are used to construct such a stable model. The principal idea is that several different representations are used to describe the same object in order to support different visual tasks, and to insure an appropriate match between the data, the model, and the task. The use of multiple representations to describe objects requires that the system be able to decide which descriptions of an object are valid. In our approach we use stability over time to indicate validity. To illustrate the power of this approach we have implemented a system, 'TraX', that constructs and refines models of outdoor objects detected in sequences of range data.",

author = "Bobick, \{Aaron F.\} and Bolles, \{Robert C.\}",

year = "1993",

language = "English",

isbn = "0819410292",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "Publ by Int Soc for Optical Engineering",

pages = "383--392",

booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

note = "Sensor Fusion V ; Conference date: 15-11-1992 Through 17-11-1992",

}

Multiple concurrent object descriptions in support of autonomous navigation. / Bobick, Aaron F.; Bolles, Robert C.
Proceedings of SPIE - The International Society for Optical Engineering. Publ by Int Soc for Optical Engineering, 1993. p. 383-392 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 1828).

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

TY - GEN

T1 - Multiple concurrent object descriptions in support of autonomous navigation

AU - Bobick, Aaron F.

AU - Bolles, Robert C.

PY - 1993

Y1 - 1993

N2 - A sensor system designed to support autonomous navigation should provide a stable, robust model of the environment. We propose and illustrate an approach in which multiple concurrent descriptions of objects are used to construct such a stable model. The principal idea is that several different representations are used to describe the same object in order to support different visual tasks, and to insure an appropriate match between the data, the model, and the task. The use of multiple representations to describe objects requires that the system be able to decide which descriptions of an object are valid. In our approach we use stability over time to indicate validity. To illustrate the power of this approach we have implemented a system, 'TraX', that constructs and refines models of outdoor objects detected in sequences of range data.

AB - A sensor system designed to support autonomous navigation should provide a stable, robust model of the environment. We propose and illustrate an approach in which multiple concurrent descriptions of objects are used to construct such a stable model. The principal idea is that several different representations are used to describe the same object in order to support different visual tasks, and to insure an appropriate match between the data, the model, and the task. The use of multiple representations to describe objects requires that the system be able to decide which descriptions of an object are valid. In our approach we use stability over time to indicate validity. To illustrate the power of this approach we have implemented a system, 'TraX', that constructs and refines models of outdoor objects detected in sequences of range data.

UR - https://www.scopus.com/pages/publications/0027311561

M3 - Conference contribution

AN - SCOPUS:0027311561

SN - 0819410292

T3 - Proceedings of SPIE - The International Society for Optical Engineering

SP - 383

EP - 392

BT - Proceedings of SPIE - The International Society for Optical Engineering

PB - Publ by Int Soc for Optical Engineering

T2 - Sensor Fusion V

Y2 - 15 November 1992 through 17 November 1992

ER -

Multiple concurrent object descriptions in support of autonomous navigation

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this