A5088989374- Image and Video Quality Assessment
- Advanced Image Processing Techniques
- Video Coding and Compression Technologies
- Advanced Vision and Imaging
- Image Enhancement Techniques
- Teleoperation and Haptic Systems
- Visual Attention and Saliency Detection
- Tactile and Sensory Interactions
- Image and Signal Denoising Methods
- Multimedia Communication and Technology
- Video Surveillance and Tracking Methods
- Advanced Image Fusion Techniques
- Advanced Data Compression Techniques
- Gaze Tracking and Assistive Technology
- Smart Grid Energy Management
- Energy Load and Power Forecasting
- Radiomics and Machine Learning in Medical Imaging
- Advanced Computing and Algorithms
- Telecommunications and Broadcasting Technologies
- Image Processing Techniques and Applications
- Mobile Crowdsensing and Crowdsourcing
- Advanced Sensor and Control Systems
- Virtual Reality Applications and Impacts
- Video Analysis and Summarization
- Advanced Optical Imaging Technologies
Fuzhou University
2016-2025
Harbin Engineering University
2024
South China Agricultural University
2023
University College Dublin
2023
South China University of Technology
2022
Shanghai Urban Construction Design and Research Institute (Group)
2022
University of Toronto
2022
Second Affiliated Hospital of Fujian Medical University
2021
Fujian Medical University
2021
Nanjing University of Aeronautics and Astronautics
2021
Accurate estimation of the traffic state can help to address issue urban congestion, providing guiding advices for people's travel and regulation. In this paper, we propose a novel short-term flow prediction algorithm based on an adaptive multi-kernel support vector machine (AMSVM) with spatial-temporal correlation, which is named as AMSVM-STC. First, explore both nonlinearity randomness flow, hybridize Gaussian kernel polynomial constitute AMSVM. Second, optimize parameters AMSVM particle...
The ever-growing multimedia traffic has underscored the importance of effective codecs. Among them, up-to-date lossy video coding standard, Versatile Video Coding (VVC), been attracting attentions community. However, gain VVC is achieved at cost significant encoding complexity, which brings need to realize fast encoder with comparable Rate Distortion (RD) performance. In this paper, we propose optimize complexity intra-frame prediction, a two-stage framework deep feature fusion and...
Humans cannot perceive the minimal level of difference in pixel variation. To overcome problem, concept just-noticeable (JND) was proposed. JND measures amount that must be changed for variation to detectable by humans. However, characteristics were not considered traditional perceptual measurements. In this paper, we provide a comprehensive survey latest JND-related studies. First, an extensive overview models. models comprise human visual system and masking effects. Next, introduce...
Image Super-Resolution (SR) techniques improve visual quality by enhancing the spatial resolution of images. Quality evaluation metrics play a critical role in comparing and optimizing SR algorithms, but current achieve only limited success, largely due to lack large-scale databases, which are essential for learning accurate robust metrics. In this work, we first build image database using novel semi-automatic labeling approach, allows us label large number images with manageable human...
For multicenter clinical studies, characterizing the robustness of image-derived radiomics features is essential. Features calculated on PET images have been shown to be very sensitive image noise. The purpose this work was investigate efficacy a relatively simple harmonization strategy feature and agreement. A purpose-built texture pattern phantom scanned 10 different scanners in 7 institutions with various acquisition reconstruction protocols. An technique based equalizing...
Accurate prediction of the traffic state can help to solve problem urban congestion, providing guiding advices for people's travel and regulation. In this paper, we propose a novel short-term flow algorithm, which is based on Multi-kernel Support Vector Machine (MSVM) Adaptive Particle Swarm Optimization (APSO). Firstly, explore both nonlinear randomness characteristic flow, hybridize Gaussian kernel polynomial constitute MSVM. Secondly, optimize parameters MSVM with APSO algorithm by...
The emerging 360-degree video has a good practical prospect in broadcasting due to its more immersive experience than traditional videos. To maintain high fidelity with panoramic vision, adopts significantly increased resolution planar videos, which also inevitably leads higher encoding complexity. In this paper, we propose flexible complexity optimization method for coding, the encoder is capable of adapting different constraints diversified scenarios. particular, proposed realized...
A tri-axial magnetometer (TAM) needs to calibrate its instrument parameters, including nonorthogonality, scale factor among three axis, and bias, improve measurement precision. In general, most scalar calibrations require a measure magnetic field intensity as reference for calibration, which will increase the cost of calibration facilities. this article, method total errors TAM, independent intensity, is proposed based on constrained optimization using sequential quadratic programming (SQP)...
End-to-end learning-based video coding has attracted substantial attentions by compressing signals as stacked visual features. This paper proposes an end-to-end deep codec with jointly optimized compression and enhancement modules (JCEVC). First, we propose a dual-path generative adversarial network (DPEG) to reconstruct details after compression. An α-path β-path concurrently the structure information local textures. Second, reuse DPEG in both motion compensation quality modules, which are...
In order to provide haptic transmission with low latency, high transparency, and reliability, tactile internet combines the fifth generation of mobile networks (5G) form 5G internet. Based on internet, communication improves immersion realism interaction by enriching sensory experience in many critical aspects industries. This paper presents an overview recent achievements communication, including signal capture, encoding, delivery. We first introduce concepts applications haptics. Then we...
To date, Versatile Video Coding (VVC) has a more magnificent overall performance than High Efficiency (HEVC). The Quadtree with Nested Multi-Type Tree (QTMT) coding block structure can substantially enhance video quality in VVC. However, the gain also leads to greater complexity. Therefore, this letter proposes Fast Decision Scheme Based on Structural Similarity Index Metric Variation (FDS-SSIMV) solve problem. Firstly, (SSIMV) characteristic among sub units of spit mode is illustrated....
Abstract Oil contaminated sandy soil is considered to be an economical and environmental problem for the oil industry. The level of contamination measured in Total Organic Carbon (TOC), which a sum parameter measure hydrocarbon compounds. TOC main contributor field. disposal process soil, commonly used current fields, attracts huge investment resource. In effort clean from field, experiment program designed remove sand by using ultrasonic technology. experiments with samples field Austria...
In multimedia services, the introduction of haptic signals provides a more immersive user experience besides conventional audio-visual perceptions. To support synchronous streaming and display these information, it is imperative to efficiently compress store signals, which promotes development optimization codecs. this paper, we propose an end-to-end codec for high-efficiency, low-delay perception-lossless compression kinesthetic signal, one two major components signals. The proposed encoder...
High Dynamic Range (HDR) images improve visual quality by representing a wide range of luminance in real world. HDR Image Quality Assessment (IQA) is essential processing technologies. This work focus on the IQA for applications represented compression. Towards designing these tasks, user-end display information should not be considered, given that tasks only media intrinsic features. However, most existing metrics are associated with luminance, hence they can handle during processing. In...
Video quality assessment is critical in optimizing video coding techniques. However, the state-of-the-art methods have limited performance, which largely due to lack of large-scale subjective databases for training. In this work, a semi-automatic labeling method adopted build compressed database, allows us label large number videos with manageable human workload. The resulting Compressed database Semi-Automatic Ratings (CVSAR), so far largest database. We train no-reference model 3D CNN...