A5007822099- Soft Robotics and Applications
- Human Pose and Action Recognition
- Smart Grid Security and Resilience
- Advanced Vision and Imaging
- Teleoperation and Haptic Systems
- Video Surveillance and Tracking Methods
- Image and Object Detection Techniques
- Industrial Vision Systems and Defect Detection
- 3D Shape Modeling and Analysis
- Software-Defined Networks and 5G
- Formal Methods in Verification
- Tracheal and airway disorders
- Pleural and Pulmonary Diseases
- Remote Sensing and Land Use
- Robot Manipulation and Learning
- Safety Systems Engineering in Autonomy
- Magnetic Bearings and Levitation Dynamics
- Robotic Mechanisms and Dynamics
- Image and Video Stabilization
- Distributed Control Multi-Agent Systems
- Advanced Neural Network Applications
- UAV Applications and Optimization
- Robotic Path Planning Algorithms
- Magnetic properties of thin films
- Image Processing Techniques and Applications
Donghua University
2022-2024
Shanghai Jiao Tong University
2023
Anhui Polytechnic University
2023
Ministry of Education of the People's Republic of China
2023
Dalian University of Technology
2022
3D Gaussian Splatting (3DGS) techniques have achieved satisfactory scene representation. Despite their impressive performance, they confront challenges due to the limitation of structure-from-motion (SfM) methods on acquiring accurate initialization, or inefficiency densification strategy. In this paper, we introduce a novel framework EasySplat achieve high-quality 3DGS modeling. Instead using SfM for employ method release power large-scale pointmap approaches. Specifically, propose an...
Intrinsic density-based particle separation is fundamental to biomedical research and materials science. Magnetic levitation offers an accessible label-free approach; however, current platforms are limited by throughput, complex fabrication requirements, manual analysis methods. Here, we demonstrate a high-throughput magnetic levitation-based microfluidic device fabricated using commercial 3D printing, integrated with dual automated systems. The features optimized magnet configurations wide...
At present, deep learning objective detection method based on features suffer from low rates and poor accuracy in metal surface defect detection. This is primarily due to the fact that detected images are mostly gray with small resolution, which makes model inefficient train slow converge. paper proposes a BiSPD-YOLO YOLOv5 solve these problems. Firstly, this uses SDP-Conv module replace traditional strided convolution pooling enhance training of network for low-resolution images; BiFPN then...
Aiming at the problems of actuator saturation, trajectory tracking, formation and obstacle avoidance planning in multi-UAVs control, an anti-saturation UAV control strategy is proposed. First, for tracking problem a single UAV, backstepping used to reduce second-order nonlinear system two first-order subsystems complexity. At same time, saturation function designed eliminate impact on system; On this basis, consistency protocol ensure effectiveness corresponding enable effectively avoid...
Recently, implicit function-based approaches have advanced 3D human reconstruction from a single-view image. However, previous methods suffer issues such as noisy artifacts, loss of geometric details, and broken limbs under the scenarios challenging poses. To address these problems, novel end-to-end deep neural network named ReGIR is proposed, which multi-level architecture combining parametric model with function. The consists coarse level fine level, for each normal maps signed distance...
Summary With the improvement of industrial informatization, various control system network protocols have also been widely used. The reliability these will directly affect safety systems. As an effective method that can automatically analyze reliability, model checking has used in verification safety‐critical In this paper, we propose a modeling design for protocol based on time semantic reconstruction state transition matrix (TSTM). addition, provide TSTM linear temporal logic (LTL). order...