Pregled bibliografske jedinice broj: 1112435
L0-Motivated Low-Rank Sparse Subspace Clustering for Hyperspectral Imagery
L0-Motivated Low-Rank Sparse Subspace Clustering for Hyperspectral Imagery // IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium
Waikoloa (HI), Sjedinjene Američke Države: Institute of Electrical and Electronics Engineers (IEEE), 2020. str. 1038-1041 doi:10.1109/IGARSS39084.2020.9324155 (poster, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 1112435 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
L0-Motivated Low-Rank Sparse Subspace Clustering
for Hyperspectral Imagery
Autori
Tian, Long ; Du, Qian ; Kopriva, Ivica
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium
/ - : Institute of Electrical and Electronics Engineers (IEEE), 2020, 1038-1041
Skup
IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
Mjesto i datum
Waikoloa (HI), Sjedinjene Američke Države, 26.09.2020. - 02.10.2020
Vrsta sudjelovanja
Poster
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
Hyperspectral image (HSI) ; low-rank recovery ; sparse representation ; subspace clustering ; S0/L0 quasi-norms
Sažetak
Hyperspectral image (HSI) Clustering is an unsupervised task, which segments pixels into different groups without using labeled samples. Low-rank sparse subspace clustering (LRSSC) is often applied to achieve the clustering of high-dimensional data such as HSI. The LRSSC combines low-rank recovery and sparse representation to capture both global and local structures of the data. Nuclear and L1-norm are often used to measure rank and sparsity in LRSSC since minimization of these two norms results in a convex optimization problem. However, the use of Nuclear and L1-norm can only approximate the original problem, and may lead to over-penalization. Thus, the direct solution of a Schatten-0 (S0) and L0 quasi-norm regularized objective function has been proposed in the LRSSC for more accurate representation. This paper proposes to use the S0/L0-regulared LRSSC (S0/L0-LRSSC) for hyperspectral image clustering. To accommodate the large data size, an original HSI is pre- partitioned, and the S0/L0-LRSSC is implemented in a distributed way. Our experiments show that the performance of the S0/L0-LRSSC in hyperspectral image clustering is better than the original LRSSC and its variants based on Nuclear and L1-norm minimization.
Izvorni jezik
Engleski
Znanstvena područja
Matematika, Računarstvo
POVEZANOST RADA
Projekti:
HRZZ-IP-2016-06-5235 - Strukturne dekompozicije empirijskih podataka za računalno potpomognutu dijagnostiku bolesti (DEDAD) (Kopriva, Ivica, HRZZ - 2016-06) ( CroRIS)
Ustanove:
Institut "Ruđer Bošković", Zagreb
Profili:
Ivica Kopriva
(autor)
