Q
Qian Du
Researcher at Mississippi State University
Publications - 621
Citations - 27841
Qian Du is an academic researcher from Mississippi State University. The author has contributed to research in topics: Hyperspectral imaging & Computer science. The author has an hindex of 62, co-authored 555 publications receiving 18872 citations. Previous affiliations of Qian Du include University of Maryland, Baltimore County & Texas A&M University–Kingsville.
Papers
More filters
Journal ArticleDOI
Efficient Deep Learning of Non-local Features for Hyperspectral Image Classification
TL;DR: The benefits of the proposed ENL-FCN are threefold: the long-range contextual information is incorporated effectively; the efficient module can be freely embedded in a deep neural network in a plug-and-play fashion; and it has much fewer learning parameters and requires less computational resources.
Journal ArticleDOI
Reconstruction From Random Projections of Hyperspectral Imagery With Spectral and Spatial Partitioning
TL;DR: CPPCA is extended to incorporate both spectral and spatial partitioning of the hyperspectral dataset with experimental results evaluating reconstruction quality not only in terms of squared-error and spectral-angle fidelity but also via performance of the reconstructed data in classification and unmixing tasks.
Proceedings ArticleDOI
Variants of N-FINDR Algorithm for Endmember Extraction
TL;DR: Based on experimental evaluation and comparison, instructive recommendations in implementation strategy for practical applications are provided and performance discrepancy among these versions of the original N-FINDR algorithm is analyzed.
Journal ArticleDOI
Deep Latent Spectral Representation Learning-Based Hyperspectral Band Selection for Target Detection
TL;DR: An unsupervised band selection method based on deep latent spectral representation learning, called DLSRL, is proposed that imposes spectral consistency onDeep latent space that resolves the issue of insufficient samples and spectral information lost in HSI interpretation.
Journal ArticleDOI
Low-Rank Subspace Representation for Supervised and Unsupervised Classification of Hyperspectral Imagery
Alex Sumarsono,Qian Du +1 more
TL;DR: Experimental results demonstrate that the proposed LRSR method can increase classification accuracy, particularly for complicated image scenes, and outperform the often-used low-rank representation approach.