Nie Mingyu

TL;DR: In this paper, the authors proposed a high spectral image Deming method based on relative abundance, which includes performing wavelet analysis and denouncing on high spectral data, optimizing a target function through iteration, and acquiring end element matrix and relative terminal element abundance matrix.

TL;DR: In this paper, an extracting method of optical spectrum vector cross-correlation features in hyper-spectral image classification is presented, which comprises the steps that pre-treatment, normalization, denoising, dimensionality reduction and the like of hyper-Spectral image data are included; boostrap sampling and weighted average are performed so as to obtain a reference sample set; spectral signal random process theoretical assumption includes first assumption and second assumption, wherein in the first assumption, spectral signals are random experiments of a stable random process at a certain time, and in the second assumption the

TL;DR: In this article, a hyperspectral image feature extraction method based on 3D wavelet transform and a sparse tensor was proposed, which can improve the classification accuracy of a whole classification system.

TL;DR: In this paper, a unified classification method for a hyper-spectral image spectrum domain and a spatial domain was proposed, which consists of the steps as follows: pre-classifying hyperspectral images in a spectrum domain, normalizing the data of the hyperspectral images, randomly generating a training sample set and a testing sample set, calculating class-center of each class in the training sample sets, calculating a vector angle of the class-centre and feature vector of each sample in each class, and pre-classified the test sample according to a Bayesian Decision Theory