J
Jinyi Zou
Researcher at Beijing University of Chemical Technology
Publications - 5
Citations - 297
Jinyi Zou is an academic researcher from Beijing University of Chemical Technology. The author has contributed to research in topics: Feature extraction & Contextual image classification. The author has an hindex of 5, co-authored 5 publications receiving 262 citations. Previous affiliations of Jinyi Zou include Peking University.
Papers
More filters
Journal ArticleDOI
Scene classification using local and global features with collaborative representation fusion
TL;DR: Experimental results demonstrate that the proposed method significantly outperforms the state-of-the-art methods on scene classification of local and global spatial features.
Journal ArticleDOI
Hyperspectral Image Classification Using Weighted Joint Collaborative Representation
TL;DR: Experimental results using two real HSIs suggest that the proposed WJCR outperforms the original JCR and some other traditional classifiers, such as the support vector machine (SVM), the SVM with a composite kernel, and simultaneous orthogonal matching pursuit.
Journal ArticleDOI
Sparse Representation-Based Nearest Neighbor Classifiers for Hyperspectral Imagery
Jinyi Zou,Wei Li,Qian Du +2 more
TL;DR: Experimental results demonstrate that the proposed SRNN, LSRNN, and JSRNN classifiers increase the classification accuracy compared with the traditional k-NN, local mean-based NN (LMNN) classifiers, and original sparse representation classifiers using representation residuals.
Journal ArticleDOI
Classification of hyperspectral urban data using adaptive simultaneous orthogonal matching pursuit
TL;DR: In this paper, an adaptive SOMP (ASOMP) was proposed to improve the performance of the original SOMP based on a priori segmentation map, where within-segment pixels are preserved while between segment pixels are excluded, whose weights are recovered by solving a sparsityconstrained optimization problem.
Proceedings ArticleDOI
Using CNN-based high-level features for remote sensing scene classification
TL;DR: From the experimental results, the proposed CNN-based scene classification method does provide more excellent performance and be superior to several state-of-the-art methods.