Tao Du

Research on Hidden Danger and Fault Location Technology of Distribution Network Based on Correlation Analysis

Hongyi Yang, Huo Chao, Tao Du, Zhidong Liu et autres

us, cn (code pays fourni par la source)

Intensified wildfire activity due to volcanism across the Triassic-Jurassic boundary in northwestern China

Wenxin Hu, Qingyong Luo, Jianfa Chen, Linhao Fang et autres

cn, kz (code pays fourni par la source)

Real-time 3D reconstruction and positioning in complex underground pipeline networks based on slam algorithm based on multi-sensor fusion

Tao Du

Underground pipeline networks are the core of urban infrastructure. Their maintenance and inspection rely on accurate real-time positioning and three-dimensional models. However, the underground environment has problems such as insufficient lighting, complex structures, and signal obstruction, which limit the applicability of traditional …

cn (code pays fourni par la source)

LPVIMO-SAM: Tightly-coupled LiDAR/Polarization Vision/Inertial/Magnetometer/Optical Flow Odometry via Smoothing and Mapping

Peng Guo, Wenshuo Li, Tao Du

We propose a tightly-coupled LiDAR/Polarization Vision/Inertial/Magnetometer/Optical Flow Odometry via Smoothing and Mapping (LPVIMO-SAM) framework, which integrates LiDAR, polarization vision, inertial measurement unit, magnetometer, and optical flow in a tightly-coupled fusion. It enables high-precision and robust real-time state estimation and map construction in …

cn (code pays fourni par la source)

Short-term wind power forecasting in complex terrain based on spatiotemporal enhanced deep correction network

Ying Zhang, Dalei Qiao, Shun Wu, Chao Liu et autres

cn, Tunisie, us (code pays fourni par la source)

PFLIO-SAM: Tightly Coupled Polarization Camera/Optical Flow/LiDAR/IMU Odometry via Smoothing and Mapping

Tao Du, Peng Guo

LiDAR inertial odometry (LIO) faces issues such as error accumulation and insufficient feature points in open and low-texture environments, which lead to cumulative heading errors and height drift. To tackle these problems, we introduce a polarization camera to provide absolute heading angle …

cn (code pays fourni par la source)

A Polarization-Aware Adversarial Attack Method for Deceiving Polarized Vision Systems

Junjie Zhang, Yu‐Chen Hu, Weijie Zhang, Tao Du

To address the vulnerability of deep learning-based polarized vision models to adversarial sample attacks, this paper proposes a polarization-aware adversarial attack (PA3) generation method based on polarization parameter space optimization. The method generates adversarial samples that are imperceptible to the human eye …

cn (code pays fourni par la source)

Neural network-based intelligent fusion terminal testing method

Tao Du

Intelligent fusion terminals are the core components of intelligent distribution stations in low-voltage distribution Internet of Things. To enhance the practical application of intelligent fusion terminals in distribution Internet of Things, a neural network-based intelligent fusion terminal testing method is proposed. The …

cn (code pays fourni par la source)

Optimal vector matching fusion method for bionic compound eye polarization compass and inertial sensor integration

Qingfeng Dou, Tao Du, Yan Wang, Xinxin Liu et autres

cn (code pays fourni par la source)

A Novel Tightly Coupled Solution for SINS/Polarized Navigation System/Odometer Integration Using Polarized and Installed Angle Errors Model

Qingfeng Dou, Tao Du, Shanpeng Wang, Zhenbing Qiu et autres

Precise and reliable autonomous navigation in a GPS-denied environment is critical to unmanned systems. The idea of combining SINS, the polarized navigation system (PNS), and the odometer (OD) inspired by desert ants has been proven to be effective for autonomous navigation. However, …

cn (code pays fourni par la source)

Performance Evaluation of Three Parameterizations on Internal Tidal Mixing in the Northern Pacific

Jiao Tan, Jing Meng, Xu Chen, Cun Jia et autres

cn (code pays fourni par la source)

Learning Neural Constitutive Laws From Motion Observations for Generalizable PDE Dynamics

Pingchuan Ma, Peter Yichen Chen, Bolei Deng, Joshua B. Tenenbaum et autres

We propose a hybrid neural network (NN) and PDE approach for learning generalizable PDE dynamics from motion observations. Many NN approaches learn an end-to-end model that implicitly models both the governing PDE and constitutive models (or material models). Without explicit PDE knowledge, …