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.
N1 - Publisher Copyright:
© 2021 IEEE.
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 - http://www.scopus.com/inward/record.url?scp=85126038857&partnerID=8YFLogxK
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 -