Harbin Institute of Technology

About: Harbin Institute of Technology is a education organization based out in Harbin, China. It is known for research contribution in the topics: Microstructure & Control theory. The organization has 88259 authors who have published 109297 publications receiving 1603393 citations. The organization is also known as: HIT.

Deep Learning for Hyperspectral Image Classification: An Overview

Abstract: Hyperspectral image (HSI) classification has become a hot topic in the field of remote sensing. In general, the complex characteristics of hyperspectral data make the accurate classification of such data challenging for traditional machine learning methods. In addition, hyperspectral imaging often deals with an inherently nonlinear relation between the captured spectral information and the corresponding materials. In recent years, deep learning has been recognized as a powerful feature-extraction tool to effectively address nonlinear problems and widely used in a number of image processing tasks. Motivated by those successful applications, deep learning has also been introduced to classify HSIs and demonstrated good performance. This survey paper presents a systematic review of deep learning-based HSI classification literatures and compares several strategies for this topic. Specifically, we first summarize the main challenges of HSI classification which cannot be effectively overcome by traditional machine learning methods, and also introduce the advantages of deep learning to handle these problems. Then, we build a framework that divides the corresponding works into spectral-feature networks, spatial-feature networks, and spectral–spatial-feature networks to systematically review the recent achievements in deep learning-based HSI classification. In addition, considering the fact that available training samples in the remote sensing field are usually very limited and training deep networks require a large number of samples, we include some strategies to improve classification performance, which can provide some guidelines for future studies on this topic. Finally, several representative deep learning-based classification methods are conducted on real HSIs in our experiments.

Switching Stabilization for a Class of Slowly Switched Systems

Abstract: In this technical note, the problem of switching stabilization for slowly switched linear systems is investigated. In particular, the considered systems can be composed of all unstable subsystems. Based on the invariant subspace theory, the switching signal with mode-dependent average dwell time (MDADT) property is designed to exponentially stabilize the underlying system. Furthermore, sufficient condition of stabilization for switched systems with all stable subsystems under MDADT switching is also given. The correctness and effectiveness of the proposed approaches are illustrated by a numerical example.

Energy-Cascaded Upconversion in an Organic Dye-Sensitized Core/Shell Fluoride Nanocrystal

Abstract: Lanthanide-doped upconversion nanoparticles hold promises for bioimaging, solar cells, and volumetric displays. However, their emission brightness and excitation wavelength range are limited by the weak and narrowband absorption of lanthanide ions. Here, we introduce a concept of multistep cascade energy transfer, from broadly infrared-harvesting organic dyes to sensitizer ions in the shell of an epitaxially designed core/shell inorganic nanostructure, with a sequential nonradiative energy transfer to upconverting ion pairs in the core. We show that this concept, when implemented in a core–shell architecture with suppressed surface-related luminescence quenching, yields multiphoton (three-, four-, and five-photon) upconversion quantum efficiency as high as 19% (upconversion energy conversion efficiency of 9.3%, upconversion quantum yield of 4.8%), which is about ∼100 times higher than typically reported efficiency of upconversion at 800 nm in lanthanide-based nanostructures, along with a broad spectral ra...