Representing and updating objects' identities in semantic SLAM

Or Tslil; Amit Elbaz; Tal Feiner; Avishy Carmi

doi:10.23919/FUSION45008.2020.9190524

Representing and updating objects' identities in semantic SLAM

Or Tslil, Amit Elbaz, Tal Feiner, Avishy Carmi

Department of Mechanical Engineering

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

3 Scopus citations

Abstract

Simultaneous localization and mapping (SLAM) deals with localizing and mapping in unknown environment. Semantic SLAM incorporates an additional layer of objects identities and their relationships. Here we suggest representing the identity of an object in semantic SLAM as a probability distribution over the object's traits, such as labels, colors, shapes, materials, etc. Objects' identities are estimated by integrating measurements from different sensors and are distinguished based on the discrepancy between the underlying probability distributions as quantified by the Bhattacharyya distance. The semantic mapping scheme is tested both in simulation and experiment using a ground robot.

Original language	English
Title of host publication	Proceedings of 2020 23rd International Conference on Information Fusion, FUSION 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9780578647098
DOIs	https://doi.org/10.23919/FUSION45008.2020.9190524
State	Published - 1 Jul 2020
Event	23rd International Conference on Information Fusion, FUSION 2020 - Virtual, Pretoria, South Africa Duration: 6 Jul 2020 → 9 Jul 2020

Publication series

Name	Proceedings of 2020 23rd International Conference on Information Fusion, FUSION 2020

Conference

Conference	23rd International Conference on Information Fusion, FUSION 2020
Country/Territory	South Africa
City	Virtual, Pretoria
Period	6/07/20 → 9/07/20

Keywords

Bhattacharyya distance
Objects detection
Semantic SLAM

ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Information Systems
Information Systems and Management
Instrumentation

Access to Document

10.23919/FUSION45008.2020.9190524

Cite this

Tslil, O., Elbaz, A., Feiner, T., & Carmi, A. (2020). Representing and updating objects' identities in semantic SLAM. In Proceedings of 2020 23rd International Conference on Information Fusion, FUSION 2020 [9190524] (Proceedings of 2020 23rd International Conference on Information Fusion, FUSION 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/FUSION45008.2020.9190524

@inproceedings{6a2adf1f67e34a2aaef7a9767fe55e64,

title = "Representing and updating objects' identities in semantic SLAM",

abstract = "Simultaneous localization and mapping (SLAM) deals with localizing and mapping in unknown environment. Semantic SLAM incorporates an additional layer of objects identities and their relationships. Here we suggest representing the identity of an object in semantic SLAM as a probability distribution over the object's traits, such as labels, colors, shapes, materials, etc. Objects' identities are estimated by integrating measurements from different sensors and are distinguished based on the discrepancy between the underlying probability distributions as quantified by the Bhattacharyya distance. The semantic mapping scheme is tested both in simulation and experiment using a ground robot.",

keywords = "Bhattacharyya distance, Objects detection, Semantic SLAM",

author = "Or Tslil and Amit Elbaz and Tal Feiner and Avishy Carmi",

note = "Funding Information: This work is supported by the Israel Science Foundation, Grant No. 1723/16. Publisher Copyright: {\textcopyright} 2020 International Society of Information Fusion (ISIF).; 23rd International Conference on Information Fusion, FUSION 2020 ; Conference date: 06-07-2020 Through 09-07-2020",

year = "2020",

month = jul,

day = "1",

doi = "10.23919/FUSION45008.2020.9190524",

language = "English",

series = "Proceedings of 2020 23rd International Conference on Information Fusion, FUSION 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "Proceedings of 2020 23rd International Conference on Information Fusion, FUSION 2020",

address = "United States",

}

Tslil, O, Elbaz, A, Feiner, T & Carmi, A 2020, Representing and updating objects' identities in semantic SLAM. in Proceedings of 2020 23rd International Conference on Information Fusion, FUSION 2020., 9190524, Proceedings of 2020 23rd International Conference on Information Fusion, FUSION 2020, Institute of Electrical and Electronics Engineers Inc., 23rd International Conference on Information Fusion, FUSION 2020, Virtual, Pretoria, South Africa, 6/07/20. https://doi.org/10.23919/FUSION45008.2020.9190524

Representing and updating objects' identities in semantic SLAM. / Tslil, Or; Elbaz, Amit; Feiner, Tal et al.

Proceedings of 2020 23rd International Conference on Information Fusion, FUSION 2020. Institute of Electrical and Electronics Engineers Inc., 2020. 9190524 (Proceedings of 2020 23rd International Conference on Information Fusion, FUSION 2020).

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

TY - GEN

T1 - Representing and updating objects' identities in semantic SLAM

AU - Tslil, Or

AU - Elbaz, Amit

AU - Feiner, Tal

AU - Carmi, Avishy

PY - 2020/7/1

Y1 - 2020/7/1

N2 - Simultaneous localization and mapping (SLAM) deals with localizing and mapping in unknown environment. Semantic SLAM incorporates an additional layer of objects identities and their relationships. Here we suggest representing the identity of an object in semantic SLAM as a probability distribution over the object's traits, such as labels, colors, shapes, materials, etc. Objects' identities are estimated by integrating measurements from different sensors and are distinguished based on the discrepancy between the underlying probability distributions as quantified by the Bhattacharyya distance. The semantic mapping scheme is tested both in simulation and experiment using a ground robot.

AB - Simultaneous localization and mapping (SLAM) deals with localizing and mapping in unknown environment. Semantic SLAM incorporates an additional layer of objects identities and their relationships. Here we suggest representing the identity of an object in semantic SLAM as a probability distribution over the object's traits, such as labels, colors, shapes, materials, etc. Objects' identities are estimated by integrating measurements from different sensors and are distinguished based on the discrepancy between the underlying probability distributions as quantified by the Bhattacharyya distance. The semantic mapping scheme is tested both in simulation and experiment using a ground robot.

KW - Bhattacharyya distance

KW - Objects detection

KW - Semantic SLAM

UR - http://www.scopus.com/inward/record.url?scp=85092697033&partnerID=8YFLogxK

U2 - 10.23919/FUSION45008.2020.9190524

DO - 10.23919/FUSION45008.2020.9190524

M3 - Conference contribution

AN - SCOPUS:85092697033

T3 - Proceedings of 2020 23rd International Conference on Information Fusion, FUSION 2020

BT - Proceedings of 2020 23rd International Conference on Information Fusion, FUSION 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 23rd International Conference on Information Fusion, FUSION 2020

Y2 - 6 July 2020 through 9 July 2020

ER -

Tslil O, Elbaz A, Feiner T, Carmi A. Representing and updating objects' identities in semantic SLAM. In Proceedings of 2020 23rd International Conference on Information Fusion, FUSION 2020. Institute of Electrical and Electronics Engineers Inc. 2020. 9190524. (Proceedings of 2020 23rd International Conference on Information Fusion, FUSION 2020). doi: 10.23919/FUSION45008.2020.9190524

Representing and updating objects' identities in semantic SLAM

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this