TY - JOUR
T1 - Thermal Image Reconstruction Using Deep Learning
AU - Batchuluun, Ganbayar
AU - Lee, Young Won
AU - Nguyen, Dat Tien
AU - Pham, Tuyen Danh
AU - Park, Kang Ryoung
N1 - Publisher Copyright:
© 2013 IEEE.
PY - 2020
Y1 - 2020
N2 - A high-resolution thermal camera is very expensive and is thus difficult to be used. Furthermore, thermal images become blurred in various cases of object motion, camera shaking, and camera defocusing. To solve these problems, a previous super-resolution restoration (SRR) technique converting a thermal image acquired by a low-resolution camera into a high-resolution one, and a thermal image deblurring method have been researched. However, existing studies were performed based on 1-channel (grayscale) images. In addition, a large-sized and whole image has been used in the existing thermal image deblurring methods, which causes lower deblurring performance. In this study, we propose novel SRR and deblurring methods. The proposed deblurring method is conducted based on small region images. The proposed methods are also conducted using 3-channel (color) thermal images and generative adversarial networks. In addition, the performances of this method are compared in various color spaces (RGB, Gray, HLS, HSV, Lab, Luv, XYZ, YCrCb), image sizes, and thermal databases. Through experiments using self-collected databases and open databases, it was confirmed that the proposed methods show better performance than the state-of-the-art methods.
AB - A high-resolution thermal camera is very expensive and is thus difficult to be used. Furthermore, thermal images become blurred in various cases of object motion, camera shaking, and camera defocusing. To solve these problems, a previous super-resolution restoration (SRR) technique converting a thermal image acquired by a low-resolution camera into a high-resolution one, and a thermal image deblurring method have been researched. However, existing studies were performed based on 1-channel (grayscale) images. In addition, a large-sized and whole image has been used in the existing thermal image deblurring methods, which causes lower deblurring performance. In this study, we propose novel SRR and deblurring methods. The proposed deblurring method is conducted based on small region images. The proposed methods are also conducted using 3-channel (color) thermal images and generative adversarial networks. In addition, the performances of this method are compared in various color spaces (RGB, Gray, HLS, HSV, Lab, Luv, XYZ, YCrCb), image sizes, and thermal databases. Through experiments using self-collected databases and open databases, it was confirmed that the proposed methods show better performance than the state-of-the-art methods.
KW - deep learning
KW - generative adversarial network
KW - image deblurring
KW - super-resolution reconstruction
KW - Thermal image
UR - http://www.scopus.com/inward/record.url?scp=85089475791&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2020.3007896
DO - 10.1109/ACCESS.2020.3007896
M3 - Article
AN - SCOPUS:85089475791
SN - 2169-3536
VL - 8
SP - 126839
EP - 126858
JO - IEEE Access
JF - IEEE Access
M1 - 9136691
ER -