Decision-Based Fusion for Vehicle Matching

Sally Ghanem; Ryan A. Kerekes; Ryan Tokola

doi:10.3390/s22072803

Decision-Based Fusion for Vehicle Matching

Sally Ghanem, Ryan A. Kerekes, Ryan Tokola

Research output: Contribution to journal › Article › peer-review

2 Scopus citations

Abstract

In this work, a framework is proposed for decision fusion utilizing features extracted from vehicle images and their detected wheels. Siamese networks are exploited to extract key signatures from pairs of vehicle images. Our approach then examines the extent of reliance between signatures generated from vehicle images to robustly integrate different similarity scores and provide a more informed decision for vehicle matching. To that end, a dataset was collected that contains hundreds of thousands of side-view vehicle images under different illumination conditions and elevation angles. Experiments show that our approach could achieve better matching accuracy by taking into account the decisions made by a whole-vehicle or wheels-only matching network.

Original language	English
Article number	2803
Journal	Sensors (Switzerland)
Volume	22
Issue number	7
DOIs	https://doi.org/10.3390/s22072803
State	Published - Apr 1 2022

Funding

This manuscript has been authored by UT-Battelle, LLC, under contract DE-AC05-00OR22725 with the US Department of Energy (DOE). By accepting the article for publication, the publisher acknowledges that the US government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for US government purposes. DOE will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (https://www.energy.gov/downloads/doe-public-access-plan accessed on 1 June 2021). Funding: This manuscript has been authored by UT-Battelle, LLC, under contract DE-AC05-00OR22725 with the US Department of Energy (DOE). By accepting the article for publication, the publisher acknowledges that the US government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for US government purposes. DOE will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (https://www.energy.gov/downloads/doe-public-access-plan accessed on 1 June 2021).

Keywords

decision fusion
deep networks
vehicle matching

Access to Document

10.3390/s22072803

Cite this

@article{484cb72e55574885b4bf7312d3e72b5b,

title = "Decision-Based Fusion for Vehicle Matching",

abstract = "In this work, a framework is proposed for decision fusion utilizing features extracted from vehicle images and their detected wheels. Siamese networks are exploited to extract key signatures from pairs of vehicle images. Our approach then examines the extent of reliance between signatures generated from vehicle images to robustly integrate different similarity scores and provide a more informed decision for vehicle matching. To that end, a dataset was collected that contains hundreds of thousands of side-view vehicle images under different illumination conditions and elevation angles. Experiments show that our approach could achieve better matching accuracy by taking into account the decisions made by a whole-vehicle or wheels-only matching network.",

keywords = "decision fusion, deep networks, vehicle matching",

author = "Sally Ghanem and Kerekes, {Ryan A.} and Ryan Tokola",

note = "Publisher Copyright: {\textcopyright} 2022 by the authors. Licensee MDPI, Basel, Switzerland.",

year = "2022",

month = apr,

day = "1",

doi = "10.3390/s22072803",

language = "English",

volume = "22",

journal = "Sensors (Switzerland)",

issn = "1424-8220",

publisher = "MDPI",

number = "7",

}

TY - JOUR

T1 - Decision-Based Fusion for Vehicle Matching

AU - Ghanem, Sally

AU - Kerekes, Ryan A.

AU - Tokola, Ryan

PY - 2022/4/1

Y1 - 2022/4/1

N2 - In this work, a framework is proposed for decision fusion utilizing features extracted from vehicle images and their detected wheels. Siamese networks are exploited to extract key signatures from pairs of vehicle images. Our approach then examines the extent of reliance between signatures generated from vehicle images to robustly integrate different similarity scores and provide a more informed decision for vehicle matching. To that end, a dataset was collected that contains hundreds of thousands of side-view vehicle images under different illumination conditions and elevation angles. Experiments show that our approach could achieve better matching accuracy by taking into account the decisions made by a whole-vehicle or wheels-only matching network.

AB - In this work, a framework is proposed for decision fusion utilizing features extracted from vehicle images and their detected wheels. Siamese networks are exploited to extract key signatures from pairs of vehicle images. Our approach then examines the extent of reliance between signatures generated from vehicle images to robustly integrate different similarity scores and provide a more informed decision for vehicle matching. To that end, a dataset was collected that contains hundreds of thousands of side-view vehicle images under different illumination conditions and elevation angles. Experiments show that our approach could achieve better matching accuracy by taking into account the decisions made by a whole-vehicle or wheels-only matching network.

KW - decision fusion

KW - deep networks

KW - vehicle matching

UR - http://www.scopus.com/inward/record.url?scp=85127571690&partnerID=8YFLogxK

U2 - 10.3390/s22072803

DO - 10.3390/s22072803

M3 - Article

C2 - 35408417

AN - SCOPUS:85127571690

SN - 1424-8220

VL - 22

JO - Sensors (Switzerland)

JF - Sensors (Switzerland)

IS - 7

M1 - 2803

ER -

Decision-Based Fusion for Vehicle Matching

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this