|
View: |
Part 1: Document Description
|
|
Citation |
|
|---|---|
|
Title: |
Thermal Image Guided Upsampling |
|
Identification Number: |
doi:10.21979/N9/9JG8D3 |
|
Distributor: |
DR-NTU (Data) |
|
Date of Distribution: |
2020-04-06 |
|
Version: |
1 |
|
Bibliographic Citation: |
Piriyatharawet, Teerawat, 2020, "Thermal Image Guided Upsampling", https://doi.org/10.21979/N9/9JG8D3, DR-NTU (Data), V1, UNF:6:IuGM51Q8N4QLGePoc6I4EA== [fileUNF] |
|
Citation |
|
|
Title: |
Thermal Image Guided Upsampling |
|
Identification Number: |
doi:10.21979/N9/9JG8D3 |
|
Authoring Entity: |
Piriyatharawet, Teerawat (Nanyang Technological University) |
|
Software used in Production: |
python |
|
Distributor: |
DR-NTU (Data) |
|
Access Authority: |
Piriyatharawet, Teerawat |
|
Depositor: |
Piriyatharawet, Teerawat |
|
Date of Deposit: |
2020-04-06 |
|
Holdings Information: |
https://doi.org/10.21979/N9/9JG8D3 |
|
Study Scope |
|
|
Keywords: |
Computer and Information Science, Computer and Information Science, guided upsamping, deep learning |
|
Abstract: |
A low-resolution thermal imaging sensor becomes more affordable and is widely used in home applications. However, in order to understand detailed activities, a high-resolution thermal image is required. In this paper, we present an unsupervised deep learning framework for joint up-sampling which aims to generate higher resolution thermal image from given corresponding low-resolution thermal image and high-resolution RGB image. The proposed joint up-sampling framework is designed to learn linear transformation between high-resolution guided image and low-resolution thermal image. The new loss function is designed to minimize the error of the linear transformation and to preserve the edge information in the output high-resolution thermal image. Experimental results demonstrate that the proposed method produces a high-resolution thermal image which is comparable to expensive high-resolution thermal cameras. |
|
Kind of Data: |
source code |
|
Methodology and Processing |
|
|
Sources Statement |
|
|
Data Access |
|
|
Other Study Description Materials |
|
|
File Description--f22532 |
|
|
File: seg_images_traing.tab |
|
|
|
|
Notes: |
UNF:6:IuGM51Q8N4QLGePoc6I4EA== |
|
List of Variables: |
|
|
Variables |
|
|
f22532 Location: |
Variable Format: character Notes: UNF:6:gl7wFsrQK/MgWD5y237dPw== |
|
f22532 Location: |
Variable Format: character Notes: UNF:6:E+dvDNsXFW1Oy3Yur3RT0A== |
|
Label: |
arch.py |
|
Notes: |
text/x-python |
|
Label: |
arch_v1.py |
|
Notes: |
text/x-python |
|
Label: |
box_filter.py |
|
Notes: |
text/x-python |
|
Label: |
dataset.py |
|
Notes: |
text/x-python |
|
Label: |
predict.py |
|
Notes: |
text/x-python |
|
Label: |
resize_img.py |
|
Notes: |
text/x-python |
|
Label: |
sobel_operator.py |
|
Notes: |
text/x-python |
|
Label: |
ssim.py |
|
Notes: |
text/x-python |
|
Label: |
training.py |
|
Notes: |
text/x-python |
|
Label: |
training_v1.py |
|
Notes: |
text/x-python |
|
Label: |
upsampling_without_interpolation.py |
|
Notes: |
text/x-python |
|
Label: |
utils_general.py |
|
Notes: |
text/x-python |
|
Label: |
utils.py |
|
Notes: |
text/x-python |
|
Label: |
vis_utils.py |
|
Notes: |
text/x-python |
