A5100323420- Robotics and Sensor-Based Localization
- Robotic Path Planning Algorithms
- Advanced Image and Video Retrieval Techniques
- Advanced Vision and Imaging
- Advanced Neural Network Applications
- Industrial Vision Systems and Defect Detection
- Video Surveillance and Tracking Methods
- Anomaly Detection Techniques and Applications
- Sparse and Compressive Sensing Techniques
- Image Retrieval and Classification Techniques
- 3D Surveying and Cultural Heritage
- Image Processing Techniques and Applications
- Image and Object Detection Techniques
- Adaptive Control of Nonlinear Systems
- Medical Image Segmentation Techniques
- Infrastructure Maintenance and Monitoring
- Robot Manipulation and Learning
- Remote-Sensing Image Classification
- Manufacturing Process and Optimization
- Distributed Control Multi-Agent Systems
- Target Tracking and Data Fusion in Sensor Networks
- 3D Shape Modeling and Analysis
- COVID-19 diagnosis using AI
- Domain Adaptation and Few-Shot Learning
- Generative Adversarial Networks and Image Synthesis
Hunan University
2015-2025
First Affiliated Hospital Zhejiang University
2025
Shanghai Jiao Tong University
2025
Fudan University
2023-2025
Shanghai Normal University
2024
North China Electric Power University
2024
China Electric Power Research Institute
2022-2024
Shanghai Electric (China)
2024
Beihang University
2017-2024
Inner Mongolia University
2015-2024
Fuzzy c-means (FCM) has been considered as an effective algorithm for image segmentation. However, it still suffers from two problems: one is insufficient robustness to noise, and the other Euclidean distance in FCM, which sensitive t
In this article, an adaptive sliding-mode disturbance observer (ASMDO)-based finite-time control scheme with prescribed performance is proposed for unmanned aerial manipulator (UAM) under uncertainties and external disturbances. First, to take into account the dynamic characteristics of UAM, a model UAM state-dependent disturbances introduced. Then, note that priori bounded uncertainty may impose constraint on system state before obtaining closed-loop stability. To remove assumption, ASMDO...
Rails are among the most important components of railway transportation, and real-time defects detection is an challenging task because intensity inhomogeneity, low contrast, noise. This paper presents automatic visual system (RVDS) for surface focuses on several key issues RVDS. First, in view challenges such as complex condition orbital reflectance inequality, we put forward a region-of-interest region extraction algorithm by vertical projection gray contrast algorithm. In addition,...
Significance Previous studies have demonstrated that p21 occupies a central position in cell-cycle regulation and DNA damage responses. As an unstable protein, the of stability has been extensively investigated over past 20 years. Although degradation by ubiquitin-proteasome pathway well characterized, it is unclear whether ubiquitylated can be recycled. Here, we identify USP11 as deubiquitylase directly removes polyubiquitylation stabilizes revealing cellular protein finely regulated...
Glass bottles must be thoroughly inspected before they are used for packaging. However, the vision inspection of bottle bottoms defects remains a challenging task in quality control due to inaccurate localization, difficulty detecting texture region, and intrinsically nonuniform brightness across central panel. To overcome these problems, we propose surface defect detection framework, which is composed three main parts. First, new localization method named entropy rate superpixel circle...
Object detection in traffic scenes has attracted considerable attention from both academia and industry recently. Modern detectors achieve excellent performance under a simple constrained environment while performing poorly the actual complex open environment. Therefore, capability of adapting to new unseen domains is key factor for large-scale application proliferation autonomous driving. To this end, paper proposes novel category-induced coarse-to-fine domain adaptation approach (C2FDA)...
Glass bottles are widely used as containers in the food and beverage industry, especially for beer carbonated beverages. As key part of a glass bottle, bottle bottom its quality closely related to product safety. Therefore, must be inspected before is packaging. In this paper, an apparatus based on machine vision designed real-time inspection, framework defect detection mainly using saliency template matching presented. Following brief description apparatus, our emphasis image analysis....
In cement-based materials, alkalis mainly exist in the form of different alkali sulfates. this study, impacts sulfates on shrinkage, hydration, pore structure, fractal dimension and microstructure low-heat Portland cement (LHPC), medium-heat (MHPC) ordinary (OPC) are investigated. The results indicate that magnify autogenous shrinkage drying materials with mineral compositions, which related to structures hydration processes. LHPC has lowest shrinkage. Otherwise, effect is more profound than...
Radiant heating, as a significant thermal management technique, is best known for its high effect, media-free operation, good penetration, and compatibility different heated shapes. To promote sustainable development in this area, developing advanced infrared radiation material demand. In work, lightweight, flexible dual-emitter electrothermal material, graphene glass fiber (GGF), developed by chemical vapor deposition (CVD) method, with both the elements. Large-area GGF fabric (GGFF)...
In order to better promote the healthy and long-term development of enterprise procurement management process, under background e-commerce environment, Suppliers-Inputs-Process-Outputs-Customers (SIPOC) model, deep learning related theories are expounded proposed. Then, D electric power is studied as samples. After understanding current situation enterprise, there a series problems in such complex no correlation between process overall strategic planning. Finally, through analysis early...
Anomaly detection and localization are widely used in industrial manufacturing for its efficiency effectiveness. Anomalies rare hard to collect supervised models easily over-fit these seen anomalies with a handful of abnormal samples, producing unsatisfactory performance. On the other hand, typically subtle, discern, various appearance, making it difficult detect let alone locate anomalous regions. To address issues, we propose framework called Prototypical Residual Network (PRN), which...
A UAV infrared target detection model ITD-YOLOv8 based on YOLOv8 is proposed to address the issues of missed and false detections caused by complex ground background uneven scale in aerial image detection, as well high computational complexity. Firstly, an improved backbone feature extraction network designed lightweight GhostHGNetV2. It can effectively capture information at different scales, improving accuracy environments while remaining lightweight. Secondly, VoVGSCSP improves perceptual...
Hyperspectral images (HSIs) are composed of hundreds contiguous waveband images, offering a wealth spatial and spectral information. However, the practical use HSIs is often hindered by presence complicated noise caused various factors such as non-uniform sensor response dark current. Traditional methods for denoising rely on constrained optimization approaches, where selecting appropriate prior knowledge critical achieving satisfactory results. Nevertheless, these traditional algorithms...
The sequence of mating operations that can be carried out to assemble a group parts is constrained by the geometric and mechanical properties parts, their assembled configuration, stability resulting subassemblies. An approach representation reasoning about these sequences described here leads several alternative explicit implicit plan representations. Pleiades system will provide an interactive software environment for designers evaluate systems product designs through impact on feasibility...
Rail inspection system (RIS) remains an emergent instrumentation for railway transportation, with its capacity of measuring surface defect on steel rail. However, detecting technique and interpretation RIS constitute a challenging problem since traditional technologies are expensive prone to errors. In this paper, deep multimodel (DM-RIS) is established where fast robust spatially constrained Gaussian mixture model presented segmentation proposal Faster RCNN utilized objective location in...
Defects on rail surfaces, which have become critical problems, need to be detected and removed as quickly possible ensure the fast, safe, stable operation of trains. At present, although many solutions been proposed address these comprehensiveness, rapidity, accuracy defect detection remain unsatisfactory. This study aims resolve existing problems accordingly proposes a multi-model surface system based convolutional neural networks (MRSDI-CNN) from standpoint studying squat surface. The...
Nowadays most of the communication technologies used in manufacturing industry are still wired, including various fieldbuses and dedicated industrial Ethernet technologies, though wireless WiFi ZigBee recently being adopted. This study is to investigate integration 5G with collaborative intelligent (CIM) processes systems. typical scenarios enhanced mobile broadband, massive machine type communications, ultra-reliable low latency introduced. Various possible applications or business slices...