A5100448677- Image Enhancement Techniques
- Advanced Image Processing Techniques
- Advanced Image Fusion Techniques
- Opportunistic and Delay-Tolerant Networks
- Advanced Vision and Imaging
- Caching and Content Delivery
- Antenna Design and Optimization
- Laser and Thermal Forming Techniques
- Flow Measurement and Analysis
- Image and Signal Denoising Methods
- Power Line Inspection Robots
- Safety Warnings and Signage
- Fire Detection and Safety Systems
- Microwave Engineering and Waveguides
- Color Science and Applications
- IoT and GPS-based Vehicle Safety Systems
- Service-Oriented Architecture and Web Services
- Face recognition and analysis
- Photoacoustic and Ultrasonic Imaging
Beijing University of Posts and Telecommunications
2014-2025
Anhui Provincial Center for Disease Control and Prevention
2023
Huawei Technologies (Sweden)
2022
University of Würzburg
2022
University of Southern Denmark
2022
Energy Research Institute
2020
Tianjin University of Technology and Education
2010-2012
This paper reviews the challenge on constrained high dynamic range (HDR) imaging that was part of New Trends in Image Restoration and Enhancement (NTIRE) workshop, held conjunction with CVPR 2022. manuscript focuses competition set-up, datasets, proposed methods their results. The aims at estimating an HDR image from multiple respective low (LDR) observations, which might suffer under-or over-exposed regions different sources noise. is composed two tracks emphasis fidelity complexity...
A training method based on transfer learning is proposed in this article, which completes the beamforming task of a deep neural network ResNet through two stages: "data approximation" and "pattern approximation". It shown numerical simulations that achieves better performance tasks, compared to Dolph-Chebyshev Genetic Algorithm. The model can generate complex excitation for arbitrary beam directions within 0∼45° off-axis angle range control sidelobe levels 20dB∼40dB range. Furthermore, with...
If we use the image haze removal of dark channel prior, we're prone to color distortion phenomenon for some large white bright area in image. Aimed at these problems, this paper presents an wiener filtering based on prior. The algorithm is mainly estimate median function media method channel, make more accurate and combine with closer. So that fog restoration problem transformed into optimization problem, by minimizing mean-square error a clearer, fogless finally obtained. Experimental...
Mobile social network service (MSNS) provides daily services for the user and can also be used in emergencies, such as natural disasters. How to conduct composition recovery among mobile devices quickly efficiently is one of important research areas MSNS. This paper puts forward a comprehensive strategy applied MSNS during When communication facilities are limited, several work cooperatively provide users with reliable composite service, known process. In addition, when some fail interrupts,...
This paper constructs a fuzzy contrast enhancement algorithm and then combination with mathematical morphology to improve the fog blurred images which captured in bad weather. In this algorithm, we membership function of domain its inverse operation. Meanwhile, define new more effective can calculate pixel gray after enhanced. Experimental results show that clarity are much improved they processed by proposed paper, it effectively improves blocking effect arises sky region visual quality...
Fire detection is an important technology to reliably guarantee the safety of power transmission scenarios. An effective fire model can help fire-fighting robots be deployed in a timely and accurate manner. However, under hazy conditions, information image will appear blurred, resulting decrease accuracy model. In response this problem, paper designs enhancement based on two-stage attention fusion loss. First, visual multi-head self-attention used extract features first stage, then through...
If the histogram equalization on basis of Retinex theory is used to an image, excessive enhancement or darkening brightness may arise. Aimed at these problems, this paper presents a parabolic adjustment image clearness algorithm, which mainly based theory, equalizing with aid transfer function, while stretching contrast image. Experimental results show that proposed algorithm can make more detailed, contour smoother, whole clearer and visual effects optimized.
Construction plant needs to mobilize personnel for safety inspection and supervision. However, due the large number of plant, conducting one-by-one supervision investigations consumes a lot human resources. Therefore, this article collects construction site inform action through helmet recognition, face external sensors. While monitoring irregularities, risk index each can be obtained assessment system provide judgment information local managers. It supervise manage with higher index.
This paper reviews the challenge on constrained high dynamic range (HDR) imaging that was part of New Trends in Image Restoration and Enhancement (NTIRE) workshop, held conjunction with CVPR 2022. manuscript focuses competition set-up, datasets, proposed methods their results. The aims at estimating an HDR image from multiple respective low (LDR) observations, which might suffer under- or over-exposed regions different sources noise. is composed two tracks emphasis fidelity complexity...