arXiv subjects

Xiao Gong

Publications and source records attributed to Xiao Gong.

21 records · Page 2Linked to original sources

arXiv2021

Monolithic Infrared Silicon Photonics: The Rise of (Si)GeSn Semiconductors

(Si)GeSn semiconductors are finally coming of age after a long gestation period. The demonstration of device quality epi-layers and quantum-engineered heterostructures has meant that tunable all-group IV Si-integrated infrared photonics is now a real possibility. Notwithstanding the recent exciting developments in (Si)GeSn materials and devices, this family of semiconductors is still facing serious limitations that need to be addressed to enable reliable and scalable applications. The main outstanding challenges include the difficulty to grow high crystalline quality layers and heterostructures at the desired Sn content and lattice strain, preserve the material integrity during growth and throughout device processing steps, and control doping and defect density. Other challenges are related to the lack of optimized device designs and predictive theoretical models to evaluate and simulate the fundamental properties and performance of (Si)GeSn layers and heterostructures. This Perspective highlights key strategies to circumvent these hurdles and bring this material system to maturity to create far-reaching new opportunities for Si-compatible infrared photodetectors, sensors, and emitters for applications in free-space communication, infrared harvesting, biological and chemical sensing, and thermal imaging.

physics.app-ph↗

arXiv2020

Enhanced Few-shot Learning for Intrusion Detection in Railway Video Surveillance

Video surveillance is gaining increasing popularity to assist in railway intrusion detection in recent years. However, efficient and accurate intrusion detection remains a challenging issue due to: (a) limited sample number: only small sample size (or portion) of intrusive video frames is available; (b) low inter-scene dissimilarity: various railway track area scenes are captured by cameras installed in different landforms; (c) high intra-scene similarity: the video frames captured by an individual camera share a same backgound. In this paper, an efficient few-shot learning solution is developed to address the above issues. In particular, an enhanced model-agnostic meta-learner is trained using both the original video frames and segmented masks of track area extracted from the video. Moreover, theoretical analysis and engineering solutions are provided to cope with the highly similar video frames in the meta-model training phase. The proposed method is tested on realistic railway video dataset. Numerical results show that the enhanced meta-learner successfully adapts unseen scene with only few newly collected video frame samples, and its intrusion detection accuracy outperforms that of the standard randomly initialized supervised learning.

cs.LG↗

arXiv2018

A Low-rank Tensor Dictionary Learning Method for Multi-spectral Images Denoising

As a 3-order tensor, a multi-spectral image (MSI) has dozens of spectral bands, which can deliver more information for real scenes. However, real MSIs are often corrupted by noises in the sensing process, which will further deteriorate the performance of higher-level classification and recognition tasks. In this paper, we propose a Low-rank Tensor Dictionary Learning (LTDL) method for MSI denoising. Firstly, we extract blocks from the MSI and cluster them into groups. Then instead of using the exactly low-rank model, we consider a nearly low-rank approximation, which is closer to the latent low-rank structure of the clean groups of real MSIs. In addition, we propose to learn an spatial dictionary and an spectral dictionary, which contain the spatial features and spectral features respectively of the whole MSI and are shared among different groups. Hence the LTDL method utilizes both the latent low-rank prior of each group and the correlation of different groups via the shared dictionaries. Experiments on synthetic data validate the effectiveness of dictionary learning by the LTDL. Experiments on real MSIs demonstrate the superior denoising performance of the proposed method in comparison to state-of-the-art methods.

eess.IV↗