Acoustic semantic labeling and fusion of human-vehicle interactions

Amir Shirkhodaie, Vinayak Elangovan, Aaron Rababaah

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Situational awareness in a Persistent Surveillance System (PSS) can be significantly improved by fusion of Data from physical (Hard) sensors and information provided by human observers (as Soft/biological sensors) from the field. One of the major limitations that this trend brings about is, however, the integration and fusion of the sensory data collected from hard sensors along with soft data gathered from human agents in a consistent and cohesive way. This paper presents a proposed approach for semantic labeling of vehicular non-stationary acoustic events in the context of PSS. Two techniques for feature extraction based on discrete wavelet and short-time Fourier transforms are described. A correlation-based classifier is proposed for classifying and semantic labeling of vehicular acoustic events. The presented result demonstrates the proposed solution is both reliable and effective, and can be extended to future PSS applications.

Original languageEnglish (US)
Title of host publicationSignal Processing, Sensor Fusion, and Target Recognition XX
DOIs
StatePublished - Jun 29 2011
EventSignal Processing, Sensor Fusion, and Target Recognition XX - Orlando, FL, United States
Duration: Apr 25 2011Apr 27 2011

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume8050
ISSN (Print)0277-786X

Other

OtherSignal Processing, Sensor Fusion, and Target Recognition XX
CountryUnited States
CityOrlando, FL
Period4/25/114/27/11

Fingerprint

semantics
surveillance
Surveillance
Labeling
marking
Fusion
Acoustics
vehicles
Fusion reactions
fusion
Semantics
Sensor
acoustics
sensors
Sensors
Interaction
Short-time Fourier Transform
situational awareness
Situational Awareness
interactions

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Shirkhodaie, A., Elangovan, V., & Rababaah, A. (2011). Acoustic semantic labeling and fusion of human-vehicle interactions. In Signal Processing, Sensor Fusion, and Target Recognition XX [80500Q] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 8050). https://doi.org/10.1117/12.883544
Shirkhodaie, Amir ; Elangovan, Vinayak ; Rababaah, Aaron. / Acoustic semantic labeling and fusion of human-vehicle interactions. Signal Processing, Sensor Fusion, and Target Recognition XX. 2011. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{52baec347ae9438eb3e3e63c216ad3cd,
title = "Acoustic semantic labeling and fusion of human-vehicle interactions",
abstract = "Situational awareness in a Persistent Surveillance System (PSS) can be significantly improved by fusion of Data from physical (Hard) sensors and information provided by human observers (as Soft/biological sensors) from the field. One of the major limitations that this trend brings about is, however, the integration and fusion of the sensory data collected from hard sensors along with soft data gathered from human agents in a consistent and cohesive way. This paper presents a proposed approach for semantic labeling of vehicular non-stationary acoustic events in the context of PSS. Two techniques for feature extraction based on discrete wavelet and short-time Fourier transforms are described. A correlation-based classifier is proposed for classifying and semantic labeling of vehicular acoustic events. The presented result demonstrates the proposed solution is both reliable and effective, and can be extended to future PSS applications.",
author = "Amir Shirkhodaie and Vinayak Elangovan and Aaron Rababaah",
year = "2011",
month = "6",
day = "29",
doi = "10.1117/12.883544",
language = "English (US)",
isbn = "9780819486240",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
booktitle = "Signal Processing, Sensor Fusion, and Target Recognition XX",

}

Shirkhodaie, A, Elangovan, V & Rababaah, A 2011, Acoustic semantic labeling and fusion of human-vehicle interactions. in Signal Processing, Sensor Fusion, and Target Recognition XX., 80500Q, Proceedings of SPIE - The International Society for Optical Engineering, vol. 8050, Signal Processing, Sensor Fusion, and Target Recognition XX, Orlando, FL, United States, 4/25/11. https://doi.org/10.1117/12.883544

Acoustic semantic labeling and fusion of human-vehicle interactions. / Shirkhodaie, Amir; Elangovan, Vinayak; Rababaah, Aaron.

Signal Processing, Sensor Fusion, and Target Recognition XX. 2011. 80500Q (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 8050).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Acoustic semantic labeling and fusion of human-vehicle interactions

AU - Shirkhodaie, Amir

AU - Elangovan, Vinayak

AU - Rababaah, Aaron

PY - 2011/6/29

Y1 - 2011/6/29

N2 - Situational awareness in a Persistent Surveillance System (PSS) can be significantly improved by fusion of Data from physical (Hard) sensors and information provided by human observers (as Soft/biological sensors) from the field. One of the major limitations that this trend brings about is, however, the integration and fusion of the sensory data collected from hard sensors along with soft data gathered from human agents in a consistent and cohesive way. This paper presents a proposed approach for semantic labeling of vehicular non-stationary acoustic events in the context of PSS. Two techniques for feature extraction based on discrete wavelet and short-time Fourier transforms are described. A correlation-based classifier is proposed for classifying and semantic labeling of vehicular acoustic events. The presented result demonstrates the proposed solution is both reliable and effective, and can be extended to future PSS applications.

AB - Situational awareness in a Persistent Surveillance System (PSS) can be significantly improved by fusion of Data from physical (Hard) sensors and information provided by human observers (as Soft/biological sensors) from the field. One of the major limitations that this trend brings about is, however, the integration and fusion of the sensory data collected from hard sensors along with soft data gathered from human agents in a consistent and cohesive way. This paper presents a proposed approach for semantic labeling of vehicular non-stationary acoustic events in the context of PSS. Two techniques for feature extraction based on discrete wavelet and short-time Fourier transforms are described. A correlation-based classifier is proposed for classifying and semantic labeling of vehicular acoustic events. The presented result demonstrates the proposed solution is both reliable and effective, and can be extended to future PSS applications.

UR - http://www.scopus.com/inward/record.url?scp=79959551376&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959551376&partnerID=8YFLogxK

U2 - 10.1117/12.883544

DO - 10.1117/12.883544

M3 - Conference contribution

AN - SCOPUS:79959551376

SN - 9780819486240

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

BT - Signal Processing, Sensor Fusion, and Target Recognition XX

ER -

Shirkhodaie A, Elangovan V, Rababaah A. Acoustic semantic labeling and fusion of human-vehicle interactions. In Signal Processing, Sensor Fusion, and Target Recognition XX. 2011. 80500Q. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.883544