APPLICATION OF COMPOSITIONAL NEURAL NETWORKS FOR ROBUST CLASSIFICATION OF INFRARED IMAGERY

Gregory P. Spell; Leslie M. Collins; Jordan M. Malof

doi:10.1109/IGARSS47720.2021.9553370

APPLICATION OF COMPOSITIONAL NEURAL NETWORKS FOR ROBUST CLASSIFICATION OF INFRARED IMAGERY

Gregory P. Spell, Leslie M. Collins, Jordan M. Malof

Computer Science

Duke University

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

1 Scopus citations

Abstract

Thermal infrared (IR) imaging has increasingly been used for remote sensing applications, which has required the adaptation of processing techniques for “natural images” (e.g., RGB images) to this unique domain in order to accommodate such differences as texture and resolution. While Convolutional Neural Networks (CNNs) have recently been shown to perform well for classification of IR images, we consider the common scenario in which the target object is partially occluded. Recent work demonstrates that deep CNNs struggle to generalize under occlusion, and Compositional CNNs (CompNets) have been proposed as deep models to mitigate this shortcoming. In this work, we apply CompNets to IR imagery, discuss the considerations in moving from natural images to IR, and analyze performance on a dataset that has been artificially occluded. Our results indicate that CompNets do, indeed, bolster robustness to occlusion in the IR domain.

Original language	English
Title of host publication	IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2799-2802
Number of pages	4
ISBN (Electronic)	9781665403696
DOIs	https://doi.org/10.1109/IGARSS47720.2021.9553370
State	Published - 2021
Event	2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021 - Brussels, Belgium Duration: Jul 12 2021 → Jul 16 2021

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)
Volume	2021-July

Conference

Conference	2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021
Country/Territory	Belgium
City	Brussels
Period	07/12/21 → 07/16/21

Funding

Work performed under: Prime Contract W15P7T-19-D-0082 for C5ISR Center NVESD.

Keywords

Compositional model
Convolutional neural network
Deep learning
Infrared imagery

Access to Document

10.1109/IGARSS47720.2021.9553370

Cite this

Spell, G. P., Collins, L. M., & Malof, J. M. (2021). APPLICATION OF COMPOSITIONAL NEURAL NETWORKS FOR ROBUST CLASSIFICATION OF INFRARED IMAGERY. In IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings (pp. 2799-2802). (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2021-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS47720.2021.9553370

Spell, Gregory P. ; Collins, Leslie M. ; Malof, Jordan M. / APPLICATION OF COMPOSITIONAL NEURAL NETWORKS FOR ROBUST CLASSIFICATION OF INFRARED IMAGERY. IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 2799-2802 (International Geoscience and Remote Sensing Symposium (IGARSS)).

@inproceedings{449765e31af24e4c840471eab9a7ea0e,

title = "APPLICATION OF COMPOSITIONAL NEURAL NETWORKS FOR ROBUST CLASSIFICATION OF INFRARED IMAGERY",

abstract = "Thermal infrared (IR) imaging has increasingly been used for remote sensing applications, which has required the adaptation of processing techniques for “natural images” (e.g., RGB images) to this unique domain in order to accommodate such differences as texture and resolution. While Convolutional Neural Networks (CNNs) have recently been shown to perform well for classification of IR images, we consider the common scenario in which the target object is partially occluded. Recent work demonstrates that deep CNNs struggle to generalize under occlusion, and Compositional CNNs (CompNets) have been proposed as deep models to mitigate this shortcoming. In this work, we apply CompNets to IR imagery, discuss the considerations in moving from natural images to IR, and analyze performance on a dataset that has been artificially occluded. Our results indicate that CompNets do, indeed, bolster robustness to occlusion in the IR domain.",

keywords = "Compositional model, Convolutional neural network, Deep learning, Infrared imagery",

author = "Spell, \{Gregory P.\} and Collins, \{Leslie M.\} and Malof, \{Jordan M.\}",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021 ; Conference date: 12-07-2021 Through 16-07-2021",

year = "2021",

doi = "10.1109/IGARSS47720.2021.9553370",

language = "English",

series = "International Geoscience and Remote Sensing Symposium (IGARSS)",

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

pages = "2799--2802",

booktitle = "IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings",

}

Spell, GP, Collins, LM & Malof, JM 2021, APPLICATION OF COMPOSITIONAL NEURAL NETWORKS FOR ROBUST CLASSIFICATION OF INFRARED IMAGERY. in IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2021-July, Institute of Electrical and Electronics Engineers Inc., pp. 2799-2802, 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021, Brussels, Belgium, 07/12/21. https://doi.org/10.1109/IGARSS47720.2021.9553370

APPLICATION OF COMPOSITIONAL NEURAL NETWORKS FOR ROBUST CLASSIFICATION OF INFRARED IMAGERY. / Spell, Gregory P.; Collins, Leslie M.; Malof, Jordan M.
IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2021. p. 2799-2802 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2021-July).

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

TY - GEN

T1 - APPLICATION OF COMPOSITIONAL NEURAL NETWORKS FOR ROBUST CLASSIFICATION OF INFRARED IMAGERY

AU - Spell, Gregory P.

AU - Collins, Leslie M.

AU - Malof, Jordan M.

PY - 2021

Y1 - 2021

N2 - Thermal infrared (IR) imaging has increasingly been used for remote sensing applications, which has required the adaptation of processing techniques for “natural images” (e.g., RGB images) to this unique domain in order to accommodate such differences as texture and resolution. While Convolutional Neural Networks (CNNs) have recently been shown to perform well for classification of IR images, we consider the common scenario in which the target object is partially occluded. Recent work demonstrates that deep CNNs struggle to generalize under occlusion, and Compositional CNNs (CompNets) have been proposed as deep models to mitigate this shortcoming. In this work, we apply CompNets to IR imagery, discuss the considerations in moving from natural images to IR, and analyze performance on a dataset that has been artificially occluded. Our results indicate that CompNets do, indeed, bolster robustness to occlusion in the IR domain.

AB - Thermal infrared (IR) imaging has increasingly been used for remote sensing applications, which has required the adaptation of processing techniques for “natural images” (e.g., RGB images) to this unique domain in order to accommodate such differences as texture and resolution. While Convolutional Neural Networks (CNNs) have recently been shown to perform well for classification of IR images, we consider the common scenario in which the target object is partially occluded. Recent work demonstrates that deep CNNs struggle to generalize under occlusion, and Compositional CNNs (CompNets) have been proposed as deep models to mitigate this shortcoming. In this work, we apply CompNets to IR imagery, discuss the considerations in moving from natural images to IR, and analyze performance on a dataset that has been artificially occluded. Our results indicate that CompNets do, indeed, bolster robustness to occlusion in the IR domain.

KW - Compositional model

KW - Convolutional neural network

KW - Deep learning

KW - Infrared imagery

UR - https://www.scopus.com/pages/publications/85126038857

U2 - 10.1109/IGARSS47720.2021.9553370

DO - 10.1109/IGARSS47720.2021.9553370

M3 - Conference contribution

AN - SCOPUS:85126038857

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 2799

EP - 2802

BT - IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021

Y2 - 12 July 2021 through 16 July 2021

ER -

Spell GP, Collins LM, Malof JM. APPLICATION OF COMPOSITIONAL NEURAL NETWORKS FOR ROBUST CLASSIFICATION OF INFRARED IMAGERY. In IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2021. p. 2799-2802. (International Geoscience and Remote Sensing Symposium (IGARSS)). doi: 10.1109/IGARSS47720.2021.9553370

APPLICATION OF COMPOSITIONAL NEURAL NETWORKS FOR ROBUST CLASSIFICATION OF INFRARED IMAGERY

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this