A5056774030- Power Transformer Diagnostics and Insulation
- Face and Expression Recognition
- Image Enhancement Techniques
- High voltage insulation and dielectric phenomena
- Biometric Identification and Security
- Lignin and Wood Chemistry
- Advanced Image Processing Techniques
- Advanced Vision and Imaging
- Advanced Image Fusion Techniques
- Forensic Fingerprint Detection Methods
- Advanced Image and Video Retrieval Techniques
- Image Retrieval and Classification Techniques
- Image and Video Quality Assessment
- Remote Sensing and Land Use
- Face recognition and analysis
- Oil, Gas, and Environmental Issues
- Power Systems Fault Detection
- Oil and Gas Production Techniques
- Non-Destructive Testing Techniques
- User Authentication and Security Systems
- Impact of Light on Environment and Health
- Robotics and Sensor-Based Localization
- Currency Recognition and Detection
- Computer Graphics and Visualization Techniques
- Electrohydrodynamics and Fluid Dynamics
Guangxi University
2019-2021
ORCID
2020
Samsung (South Korea)
2016
Samsung (China)
2015
University of Chinese Academy of Sciences
2012-2013
This paper reviews the NTIRE 2023 challenge on image denoising (σ = 50) with a focus proposed solutions and results. The aim is to obtain network design capable produce high-quality results best performance measured by PSNR for denoising. Independent additive white Gaussian noise (AWGN) assumed level 50. had 225 registered participants, 16 teams made valid submissions. They gauge state-of-the-art
This paper reviews the video colorization challenge on New Trends in Image Restoration and Enhancement (NTIRE) workshop, held conjunction with CVPR 2023. The target of this is converting grayscale videos into color better performance temporal consistency. consists two tracks. For Track 1, goal achieving best FID (Fréchet Inception Distance) while being constrained to maintain or improve over baseline method terms temporal-consistency metric. Color Distribution Consistency (CDC) index used as...
This paper presents a review of the NTIRE 2023 challenge on night photography rendering.The goal was to find solutions that process raw camera images taken in nighttime conditions conditions, and thereby produce photo-quality output standard RGB (sRGB) space.Unlike previous year's competition, participants were not provided with large training dataset for target sensor.Instead, this time they given color checker illuminated by known light source.To evaluate results, sufficient number viewers...
A new fingerprint compression algorithm based on sparse representation is introduced. Obtaining an overcomplete dictionary from a set of patches allows us to represent them as linear combination atoms. In the algorithm, we first construct for predefined image patches. For given images, its according by computing l(0)-minimization and then quantize encode representation. this paper, consider effect various factors results. Three groups images are tested. The experiments demonstrate that our...
Similarity measuring plays as an import role in stereo matching, whether for visual data from standard cameras or those novel sensors such Dynamic Vision Sensors (DVS). Generally speaking, robust feature descriptors contribute to designing a powerful similarity measurement, demonstrated by classic matching methods. However, the kind and representative ability of DVS are so limited that achieving accurate on becomes very challenging. In this paper, descriptor is proposed improve accuracy...
Developing and integrating advanced image sensors with novel algorithms in camera systems are prevalent the increasing demand for computational photography imaging on mobile platforms. However, lack of high-quality data research rare opportunity in-depth exchange views from industry academia constrain development intelligent (MIPI). With success 1st MIPI Workshop@ECCV 2022, we introduce second challenge including four tracks focusing algorithms. In this paper, summarize review Nighttime...
The grounding grid is the cornerstone for maintaining safe operation of power system. network acts as a concealed project, and its invisible characteristics make defects difficult to be detected, which causes major safety hazards in Thus accurate diagnosis corrosion vital electrical engineering. A method based on branch voltage disturbance proposed this paper, can judge location degree through before after corrosion. Firstly, sensitivity resistance analyzed. Secondly, diagnostic model...
The method using ethanol to evaluate the cellulose insulation aging condition of oil-immersed transformers has been proposed. At present, dominating for detecting in insulating oil is use headspace–gas-chromatography–mass-spectrometry (HS-GC-MS). However, problem quantitative inaccuracy will be sometimes encountered actual detection process due improper instrument parameter setting and manual operation. In this study, as an marker, transformer was separated by VF-624 ms capillary column....
A growing body of evidence suggests that the ethanol dissolved in oil can be used as an indicator to effectively monitor aging behavior insulating paper. In this study, thermal experiments are performed on oil-paper systems with different initial moisture contents and temperatures, then a gas chromatography-mass spectrometer equipped automatic headspace sampler is test samples. The variations correlations temperature, degree analyzed. experimental results show had strong correlation also...
The increasing demand for computational photography and imaging on mobile platforms has led to the widespread development integration of advanced image sensors with novel algorithms in camera systems. However, scarcity high-quality data research rare opportunity in-depth exchange views from industry academia constrain intelligent (MIPI). Building achievements previous MIPI Workshops held at ECCV 2022 CVPR 2023, we introduce our third challenge including three tracks focusing algorithms. In...
This paper presents a review of the NTIRE 2024 challenge on night photography rendering. The goal was to find solutions that process raw camera images taken in nighttime conditions, and thereby produce photo-quality output standard RGB (sRGB) space. Unlike previous year's competition, were collected with mobile phone speed algorithms also measured alongside quality their output. To evaluate results, sufficient number viewers asked assess visual proposed solutions, considering subjective...
Due to the shortcomings of electrical properties and furfural in characterizing aging characteristics paper insulation limitations field application, this focuses on feasibility evaluating polymerization degree insulating by ethanol (EtOH) content transformer oil. The accelerated thermal test is conducted, during which produced degradation paper. For each oil-paper samples, with different concentrations are prepared controlling time. In paper, a gas chromatograph equipped mass spectrometer...
Dynamic vision sensor (DVS) as a novel type of visual sensors can detect moving object in fast and cost effective way by outputting events on edges the object. This paper proposes body part localization method using structured output Deep Belief Network (s-DBN) to label parts block pixels very fashion. Experiments show that our proposed algorithm achieves pixel accuracy 90.13% compared (87.01%) Random Forests (84.15%) under same computational cost. For head/hand detection s-DBN has...
A new method for fingerprint subclassification is proposed. First, a rotation-invariant feature generated by distance between orientation features. Then, fuzzy methods are adopted in both clustering step and classification step. With an introduced parameter, the balance accuracy average comparison times made. The results show that clustered subclasses reasonable outperforms combinations of crisp methods.
In this paper, we proposed a novel method called Nonnegative Matrix Factorization based on Locally Linear Embedding (LLE-NMF). This idea is to factorize the nonnegative matrix considering intrinsic geometric structure of high dimensional data. Instead need estimate pairwise distances between widely separated data points, LLE-NMF able find compact representation recovering global nonlinear from locally linear fits. We updating rules and simulation results. experiments, show encouraging...
Abstract Oil chromatographic analysis is widely used in transformer fault diagnosis However, the problem of excessive total hydrocarbons oil chromatogram caused by failure submersible pump different from body. Technicians need to be able accurately identify these two types failure. For this problem, article proposes a method judging manually starting and stopping monitoring change law data. This first finds out suspicious pumps through current Subsequently, operator starts stops monitors...