Pedestrian Detection from Thermal Images Incorporating Saliency Features

Fatih Altay; Senem Velipasalar

doi:10.1109/IEEECONF51394.2020.9443411

Pedestrian Detection from Thermal Images Incorporating Saliency Features

Fatih Altay, Senem Velipasalar

Research output: Chapter in Book/Entry/Poem › Conference contribution

4 Scopus citations

Abstract

Methods relying entirely on visible-range/color images start to have problems in detection tasks when there is not enough light to illuminate the scene. Thermal cameras, which operate based on the infrared radiation emitted by objects, can provide detectable information in low- or no-light conditions. In this paper, we propose a method to improve the performance of a pedestrian detection algorithm on thermal images by incorporating features from saliency maps to enrich the thermal image features. We employ a modified version of a state-of-the-art object detection network, and feed the thermal images and their saliency maps to two parallel networks. Experimental results on five different datasets show that our proposed approach performs better at detecting pedestrians in thermal images compared to its vanilla version and a baseline model.

Original language	English (US)
Title of host publication	Conference Record of the 54th Asilomar Conference on Signals, Systems and Computers, ACSSC 2020
Editors	Michael B. Matthews
Publisher	IEEE Computer Society
Pages	1548-1552
Number of pages	5
ISBN (Electronic)	9780738131269
DOIs	https://doi.org/10.1109/IEEECONF51394.2020.9443411
State	Published - Nov 1 2020
Event	54th Asilomar Conference on Signals, Systems and Computers, ACSSC 2020 - Pacific Grove, United States Duration: Nov 1 2020 → Nov 5 2020

Publication series

Name	Conference Record - Asilomar Conference on Signals, Systems and Computers
Volume	2020-November
ISSN (Print)	1058-6393

Conference

Conference	54th Asilomar Conference on Signals, Systems and Computers, ACSSC 2020
Country/Territory	United States
City	Pacific Grove
Period	11/1/20 → 11/5/20

Keywords

Pedestrian Detection
Saliency Maps
Thermal Images

ASJC Scopus subject areas

Signal Processing
Computer Networks and Communications

Access to Document

10.1109/IEEECONF51394.2020.9443411

Cite this

Altay, F., & Velipasalar, S. (2020). Pedestrian Detection from Thermal Images Incorporating Saliency Features. In M. B. Matthews (Ed.), Conference Record of the 54th Asilomar Conference on Signals, Systems and Computers, ACSSC 2020 (pp. 1548-1552). [9443411] (Conference Record - Asilomar Conference on Signals, Systems and Computers; Vol. 2020-November). IEEE Computer Society. https://doi.org/10.1109/IEEECONF51394.2020.9443411

Pedestrian Detection from Thermal Images Incorporating Saliency Features. / Altay, Fatih; Velipasalar, Senem.
Conference Record of the 54th Asilomar Conference on Signals, Systems and Computers, ACSSC 2020. ed. / Michael B. Matthews. IEEE Computer Society, 2020. p. 1548-1552 9443411 (Conference Record - Asilomar Conference on Signals, Systems and Computers; Vol. 2020-November).

Research output: Chapter in Book/Entry/Poem › Conference contribution

Altay, F & Velipasalar, S 2020, Pedestrian Detection from Thermal Images Incorporating Saliency Features. in MB Matthews (ed.), Conference Record of the 54th Asilomar Conference on Signals, Systems and Computers, ACSSC 2020., 9443411, Conference Record - Asilomar Conference on Signals, Systems and Computers, vol. 2020-November, IEEE Computer Society, pp. 1548-1552, 54th Asilomar Conference on Signals, Systems and Computers, ACSSC 2020, Pacific Grove, United States, 11/1/20. https://doi.org/10.1109/IEEECONF51394.2020.9443411

Altay F, Velipasalar S. Pedestrian Detection from Thermal Images Incorporating Saliency Features. In Matthews MB, editor, Conference Record of the 54th Asilomar Conference on Signals, Systems and Computers, ACSSC 2020. IEEE Computer Society. 2020. p. 1548-1552. 9443411. (Conference Record - Asilomar Conference on Signals, Systems and Computers). doi: 10.1109/IEEECONF51394.2020.9443411

@inproceedings{01e1cf74140046c99ca1f07da1420585,

title = "Pedestrian Detection from Thermal Images Incorporating Saliency Features",

abstract = "Methods relying entirely on visible-range/color images start to have problems in detection tasks when there is not enough light to illuminate the scene. Thermal cameras, which operate based on the infrared radiation emitted by objects, can provide detectable information in low- or no-light conditions. In this paper, we propose a method to improve the performance of a pedestrian detection algorithm on thermal images by incorporating features from saliency maps to enrich the thermal image features. We employ a modified version of a state-of-the-art object detection network, and feed the thermal images and their saliency maps to two parallel networks. Experimental results on five different datasets show that our proposed approach performs better at detecting pedestrians in thermal images compared to its vanilla version and a baseline model.",

keywords = "Pedestrian Detection, Saliency Maps, Thermal Images",

author = "Fatih Altay and Senem Velipasalar",

note = "Funding Information: The information, data, or work presented herein was funded in part by National Science Foundation (NSF) under Grant 1739748, Grant 1816732 and by the Advanced Research Projects Agency-Energy (ARPA-E), U.S. Department of Energy, under Award Number DE-AR0000940. The views and opinions of authors expressed herein do not necessarily state or reflect those of the United States Government or any agency thereof. Publisher Copyright: {\textcopyright} 2020 IEEE.; 54th Asilomar Conference on Signals, Systems and Computers, ACSSC 2020 ; Conference date: 01-11-2020 Through 05-11-2020",

year = "2020",

month = nov,

day = "1",

doi = "10.1109/IEEECONF51394.2020.9443411",

language = "English (US)",

series = "Conference Record - Asilomar Conference on Signals, Systems and Computers",

publisher = "IEEE Computer Society",

pages = "1548--1552",

editor = "Matthews, {Michael B.}",

booktitle = "Conference Record of the 54th Asilomar Conference on Signals, Systems and Computers, ACSSC 2020",

address = "United States",

}

TY - GEN

T1 - Pedestrian Detection from Thermal Images Incorporating Saliency Features

AU - Altay, Fatih

AU - Velipasalar, Senem

N1 - Funding Information: The information, data, or work presented herein was funded in part by National Science Foundation (NSF) under Grant 1739748, Grant 1816732 and by the Advanced Research Projects Agency-Energy (ARPA-E), U.S. Department of Energy, under Award Number DE-AR0000940. The views and opinions of authors expressed herein do not necessarily state or reflect those of the United States Government or any agency thereof. Publisher Copyright: © 2020 IEEE.

PY - 2020/11/1

Y1 - 2020/11/1

N2 - Methods relying entirely on visible-range/color images start to have problems in detection tasks when there is not enough light to illuminate the scene. Thermal cameras, which operate based on the infrared radiation emitted by objects, can provide detectable information in low- or no-light conditions. In this paper, we propose a method to improve the performance of a pedestrian detection algorithm on thermal images by incorporating features from saliency maps to enrich the thermal image features. We employ a modified version of a state-of-the-art object detection network, and feed the thermal images and their saliency maps to two parallel networks. Experimental results on five different datasets show that our proposed approach performs better at detecting pedestrians in thermal images compared to its vanilla version and a baseline model.

AB - Methods relying entirely on visible-range/color images start to have problems in detection tasks when there is not enough light to illuminate the scene. Thermal cameras, which operate based on the infrared radiation emitted by objects, can provide detectable information in low- or no-light conditions. In this paper, we propose a method to improve the performance of a pedestrian detection algorithm on thermal images by incorporating features from saliency maps to enrich the thermal image features. We employ a modified version of a state-of-the-art object detection network, and feed the thermal images and their saliency maps to two parallel networks. Experimental results on five different datasets show that our proposed approach performs better at detecting pedestrians in thermal images compared to its vanilla version and a baseline model.

KW - Pedestrian Detection

KW - Saliency Maps

KW - Thermal Images

UR - http://www.scopus.com/inward/record.url?scp=85107738445&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85107738445&partnerID=8YFLogxK

U2 - 10.1109/IEEECONF51394.2020.9443411

DO - 10.1109/IEEECONF51394.2020.9443411

M3 - Conference contribution

AN - SCOPUS:85107738445

T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers

SP - 1548

EP - 1552

BT - Conference Record of the 54th Asilomar Conference on Signals, Systems and Computers, ACSSC 2020

A2 - Matthews, Michael B.

PB - IEEE Computer Society

T2 - 54th Asilomar Conference on Signals, Systems and Computers, ACSSC 2020

Y2 - 1 November 2020 through 5 November 2020

ER -

Pedestrian Detection from Thermal Images Incorporating Saliency Features

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this