TY - GEN
T1 - Seeing is Not Believing
T2 - 2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023
AU - Hsu, Chih Chung
AU - Jhang, Yu An
AU - Ko, Min Tso
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Amid the rapid growth of low-earth orbits (LEOs) and hyperspectral imaging (HSI) techniques, this study addresses the overlooked area of security challenges, specifically hyperspectral content manipulation or inpainting. We present HyperForensics, a novel dataset based on NASA's AVIRIS data, covering diverse scenarios across a wavelength range of 0.4 to 2.5 micrometers. To confront the challenge of detecting small manipulated regions within HSIs, we develop a detection method using a high-resolution network (HRNet) that maintains high resolution and spatial accuracy. Experiments demonstrate this approach outperforms existing methods, highlighting the critical role of spatial-spectral features in HSI forgery detection. This pioneering work in HSI forgery benchmarking and detection invites further research to enhance HSI security.
AB - Amid the rapid growth of low-earth orbits (LEOs) and hyperspectral imaging (HSI) techniques, this study addresses the overlooked area of security challenges, specifically hyperspectral content manipulation or inpainting. We present HyperForensics, a novel dataset based on NASA's AVIRIS data, covering diverse scenarios across a wavelength range of 0.4 to 2.5 micrometers. To confront the challenge of detecting small manipulated regions within HSIs, we develop a detection method using a high-resolution network (HRNet) that maintains high resolution and spatial accuracy. Experiments demonstrate this approach outperforms existing methods, highlighting the critical role of spatial-spectral features in HSI forgery detection. This pioneering work in HSI forgery benchmarking and detection invites further research to enhance HSI security.
UR - http://www.scopus.com/inward/record.url?scp=85178368319&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85178368319&partnerID=8YFLogxK
U2 - 10.1109/IGARSS52108.2023.10282019
DO - 10.1109/IGARSS52108.2023.10282019
M3 - Conference contribution
AN - SCOPUS:85178368319
T3 - International Geoscience and Remote Sensing Symposium (IGARSS)
SP - 5858
EP - 5861
BT - IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 16 July 2023 through 21 July 2023
ER -