TY - GEN
T1 - WEIGHTED SPARSITY CONSTRAINT TENSOR FACTORIZATION FOR HYPERSPECTRAL UNMIXING
AU - Yuan, Yuan
AU - Dong, Le
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - Recently, the unmixing methods based on non-negative tensor factorization (NTF) have received a lot of attention. Many NTF-based methods combine total variation (TV) regularization, aiming at maintaining the smoothness of the abundance maps to improve the performance of unmixing. However, the existing TV regularization ignores the sparsity sharing on the spatial difference images among different bands. To tackle this issue, a weighted total variation regularizer on the spatial difference maps of abundances is proposed in this paper, which uses the L2,1 norm to explore the sparse structure in abundances along the spectral dimension. In addition, the L1/2 norm is used to enhance the spatial sparsity of abundances. The proposed method can not only enhance the sparsity in abundances, but also keep the spatial similarity characteristics of data. Compared with the existing popular methods, the proposed method has superior performance on both synthetic data and real data.
AB - Recently, the unmixing methods based on non-negative tensor factorization (NTF) have received a lot of attention. Many NTF-based methods combine total variation (TV) regularization, aiming at maintaining the smoothness of the abundance maps to improve the performance of unmixing. However, the existing TV regularization ignores the sparsity sharing on the spatial difference images among different bands. To tackle this issue, a weighted total variation regularizer on the spatial difference maps of abundances is proposed in this paper, which uses the L2,1 norm to explore the sparse structure in abundances along the spectral dimension. In addition, the L1/2 norm is used to enhance the spatial sparsity of abundances. The proposed method can not only enhance the sparsity in abundances, but also keep the spatial similarity characteristics of data. Compared with the existing popular methods, the proposed method has superior performance on both synthetic data and real data.
KW - Hyperspectral unmixing
KW - Sparse characteristics
KW - Tensor factorization
KW - Total variation
UR - http://www.scopus.com/inward/record.url?scp=85126040866&partnerID=8YFLogxK
U2 - 10.1109/IGARSS47720.2021.9553154
DO - 10.1109/IGARSS47720.2021.9553154
M3 - 会议稿件
AN - SCOPUS:85126040866
T3 - International Geoscience and Remote Sensing Symposium (IGARSS)
SP - 3333
EP - 3336
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 -