H
He Yang
Researcher at Mississippi State University
Publications - 21
Citations - 1317
He Yang is an academic researcher from Mississippi State University. The author has contributed to research in topics: Hyperspectral imaging & Contextual image classification. The author has an hindex of 11, co-authored 21 publications receiving 1185 citations.
Papers
More filters
Journal ArticleDOI
Similarity-Based Unsupervised Band Selection for Hyperspectral Image Analysis
TL;DR: The experimental result shows that the proposed unsupervised band selection algorithms based on band similarity measurement can yield a better result in terms of information conservation and class separability than other widely used techniques.
Journal ArticleDOI
An Efficient Method for Supervised Hyperspectral Band Selection
TL;DR: A new supervised band-selection algorithm that uses the known class signatures only without examining the original bands or the need of class training samples is proposed, which can complete the task much faster than traditional methods that test bands or band combinations.
Journal ArticleDOI
Optical flow and principal component analysis-based motion detection in outdoor videos
TL;DR: Experimental results demonstrate that this approach outperforms other existing methods by extracting the moving objects more completely with lower false alarms.
Journal ArticleDOI
Particle Swarm Optimization-Based Hyperspectral Dimensionality Reduction for Urban Land Cover Classification
He Yang,Qian Du,Genshe Chen +2 more
TL;DR: In these experiments, SVM classification accuracy using PSO-selected bands is greatly higher than using all of the original bands or dimensionality-reduced data from principal component analysis (PCA) or linear discriminant analysis (LDA), and the improvement on SVM accuracy can bring out even more significant improvement in classifier fusion.
Journal ArticleDOI
Unsupervised Hyperspectral Band Selection Using Graphics Processing Units
He Yang,Qian Du,Genshe Chen +2 more
TL;DR: This paper proposes parallel implementations via emerging general-purpose graphics processing units (GPUs) for band selection without changing band selection result that is comparable to the cluster-based parallel implementation and an approach to using several selected pixels for unsupervised band selection and the number of pixels needed can be equal to thenumber of selected bands minus one.