Xuanlin Min

ORCID: 0000-0003-0196-172X
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Video Surveillance and Tracking Methods
  • Advanced Neural Network Applications
  • Animal Virus Infections Studies
  • Robotics and Sensor-Based Localization
  • Speech Recognition and Synthesis
  • Anomaly Detection Techniques and Applications
  • Infrared Target Detection Methodologies
  • Human Pose and Action Recognition
  • SARS-CoV-2 detection and testing
  • SARS-CoV-2 and COVID-19 Research
  • Speech and Audio Processing
  • 3D Surveying and Cultural Heritage
  • Music and Audio Processing
  • 3D Shape Modeling and Analysis
  • Remote Sensing and LiDAR Applications

Nanjing Municipal Center for Disease Control And Prevention
2024

Nanjing Medical University
2024

Chongqing University of Science and Technology
2021-2024

Georgetown University
2022

Yamaguchi University
2022

Nanjing Tech University
2022

Zhoukou Normal University
2022

Dalian Institute of Chemical Physics
2022

Ca' Foscari University of Venice
2022

A.E. Favorsky Irkutsk Institute of Chemistry
2022

Real-time object detection on unmanned aerial vehicles (UAVs) poses a challenging issue due to the limited computing resources of edge devices. To address this problem, we propose novel lightweight network named LWUAVDet for real-time UAV applications. The detector comprises three core components: E-FPN, PixED Head, and Aux Head. Firstly, develop an extended refined topology in Neck layer, called enhance multi-scale representation each stage alleviate aliasing effect caused by repetitive...

10.1109/jiot.2024.3388045 article EN IEEE Internet of Things Journal 2024-04-12

Violence behavior detection has played an important role in computer vision, its widely used unmanned security monitoring systems, Internet video filtration, etc. However, automatically detecting violence from surveillance cameras long been a challenging issue due to the real-time and accuracy. In this brief, novel multi-scale spatio-temporal network termed as MSTN is proposed detect stream. To begin with, feature extraction module (STM) developed extract key features between foreground...

10.1109/tbiom.2022.3233399 article EN IEEE Transactions on Biometrics Behavior and Identity Science 2023-01-02

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused the disease 2019 (COVID-19) pandemic, which is still a global public health concern. During March 2022, rapid and confined single-source outbreak of SARS-CoV-2 was identified in community Nanjing municipal city. Overall, 95 individuals had laboratory-confirmed infection. The whole genomes 61 viral samples were obtained, all members BA.2.2 lineage clearly demonstrated presence one large clade, infections could be traced...

10.1093/ve/veae085 article EN cc-by-nc Virus Evolution 2024-01-01

Real-time object detection on Unmanned Aerial Vehicles (UAVs) is a challenging issue due to the limited computing resources of edge GPU devices as Internet Things (IoT) nodes. To solve this problem, in paper, we propose novel lightweight deep learning architectures named FasterX based YOLOX model for real-time GPU. First, design an effective and PixSF head replace original better detect small objects, which can be further embedded depthwise separable convolution (DS Conv) achieve lighter...

10.48550/arxiv.2209.03157 preprint EN cc-by arXiv (Cornell University) 2022-01-01

In the process of driving a vehicle, good sound quality experience is essential for driver. However, in real-time audio and video communication, because wireless voice vehicle will inevitably be interfered by various internal external environmental noises during transmission process, this makes original pure become noisy polluted noise, thus, communication seriously affected. And it inevitable that we encounter undesirable sounds, such as current exhaust etc. article, analyze types noise may...

10.1109/icesit53460.2021.9696798 article EN 2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT) 2021-11-22
Coming Soon ...