Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Yuhan Zhang has a total of 16 co-authors. Here are the top co-authors by number of shared publications:

  • Zhanchuan Cai

    School of Computer Science and Engineering, Macau University of Science and Technology, Macau, China

    5 shared publications
  • Jieyu Yuan

    VCIP, College of Computer Science, Nankai University, Tianjin, China

    2 shared publications
  • Ben Ye

    School of Computer Science and Engineering, Macau University of Science and Technology, Macau, China

    1 shared publication
  • Cai Shiyuan

    Tianjin University of Technology,School of Electrical and Electronic Engineering,BinShuiXiDao Road,Tianjin,China

    1 shared publication
  • Guo Zhiling

    Tianjin University of Technology,School of Electrical and Electronic Engineering,BinShuiXiDao Road,Tianjin,China

    1 shared publication
  • Jiang Kuncheng

    Tianjin University of Technology,School of Electrical and Electronic Engineering,BinShuiXiDao Road,Tianjin,China

    1 shared publication

Latest Publications

  • Underwater Scene Enhancement via Adaptive Color Analysis and Multispace Fusion

    by Jieyu Yuan, Yuhan Zhang, Zhanchuan Cai

    Marine observation faces significant challenges due to the complex optical characteristics of underwater environments. The combined effects of light attenuation and scattering lead to severe image degradation, while the dynamic nature of underwater conditions introduces additional variability that traditional enhancement methods struggle to address. This work introduces a novel framework for underwater image enhancement that leverages multidomain analysis to achieve robust performance across diverse marine environments. The proposed method incorporates an adaptive scene analysis mechanism that determines optimal enhancement strategies based on environmental characteristics. The enhancement pipeline consists of two key components: First, a comprehensive degradation analysis module that addresses both illumination irregularities and wavelength-dependent attenuation through domain-specific compensation. Second, an advanced fusion scheme that combines multiple enhanced representations using an optimized pyramid model, enabling effective preservation of both global contrast and local details. The framework excels in challenging scenarios such as turbid waters and nonuniform lighting conditions, where conventional methods often fail. Extensive experiments conducted on multiple benchmark data sets demonstrate that our approach achieves superior performance in terms of both objective metrics and subjective visual quality. The results show consistent improvement in visibility, color fidelity, and detail preservation across varying underwater conditions, making it particularly suitable for marine observation and analysis tasks.


  • Open Access

    UWMambaNet: Dual-Branch Underwater Image Reconstruction Based on W-Shaped Mamba

    by Yuhan Zhang, Xinyang Yu, Zhanchuan Cai

    Underwater image enhancement is a challenging task due to the unique optical properties of water, which often lead to color distortion, low contrast, and detail loss. At the present stage, the methods based on the CNN have the problem of insufficient global attention, and the methods based on Transformer generally have the problem of quadratic complexity. To address this challenge, we propose a dual-branch network architecture based on the W-shaped Mamba: UWMambaNet. Our method integrates the color contrast enhancement branch and the detail enhancement branch, and each branch is dedicated to improving specific aspects of underwater images. The color contrast enhancement branch utilizes the RGB and Lab color spaces and uses the Mamba block for advanced feature fusion to enhance color fidelity and contrast. The detail enhancement branch adopts a multi-scale feature extraction strategy to capture fine and contextual details through parallel convolutional paths. The Mamba module is added to the dual branches, and state-space modeling is used to capture the long-range dependencies and spatial relationships in the image data. This enables effective modeling of the complex interactions and light propagation effects inherent in the underwater environment. Experimental results show that our method significantly improves the visual quality of underwater images and is superior to existing technologies in terms of quantitative indicators and visualization effects; compared to the best candidate models on the UIEB and EUVP datasets, UWMambaNet improves UCIQE by 3.7% and 2.4%, respectively.


  • High-Resolution Lunar Brightness Temperature Model Based on Chang’e-2 MRM Data and Spatially Weighted Neural Network

    by Mingwen Zhu, Zhanchuan Cai, Sensen Wu, Yuhan Zhang, Jiayang Li

    Brightness temperature (TB) derived from microwave radiometers (MRM) onboard China’s Chang’e (CE) satellites has provided significant insights into the Moon’s subsurface thermal conditions and evolution. However, conventional TB mapping techniques emphasize spatial correlations among observational data points while largely neglecting the influence of inherent lunar surface factors. In this study, we propose a novel TB estimation approach utilizing Geographically Neural Network Weighted Regression (GNNWR) combined with multi-source lunar remote sensing data to generate TB maps at a higher spatial resolution of 0.0625° × 0.0625°. This method integrates crucial lunar surface parameters in heat conduction and radiation transfer models in a new framework, thereby reducing the risk of overestimation associated with high-resolution targets in sparsely distributed samples. Additionally, by replacing the traditional Geographically Weighted Regression (GWR) kernel with a Spatially Weighted Neural Network (SWNN), the model effectively addresses spatial non-stationarity and heterogeneity present in TB data and microwave radiative transfer. Comparative analyses demonstrate that the GNNWR approach achieves superior performance, as evidenced by the highest R² and the lowest mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE). Furthermore, the generated TB maps demonstrate strong alignment with observed spatial trends. These maps also reveal fine-scale thermal features typically obscured by conventional interpolation methods, enhancing their utility for microwave thermal emission analysis and geological studies.

  • DCGF: Diffusion-Color-Guided Framework for Underwater Image Enhancement

    by Yuhan Zhang, Jieyu Yuan, Zhanchuan Cai

    Underwater exploration is crucial for geoscience and remote sensing, but the capture of underwater images is compromised by the degradation of light absorption and scattering. This paper proposes a Diffusion-Color Guided Framework (DCGF) to enhance the quality of underwater images and address color deviations caused by randomness in general diffusion models during underwater image restoration. In DCGF, the diffusion model reconstructs the image distribution, while a color correction module ensures accurate color representation. A conditional image guides the denoising procedure, aligning the diffusion trajectory closely with the target domain. This approach reduces the impact of diffusion variability and minimizes deviations. Once a predetermined denoising threshold is reached, the color correction module extracts salient characteristics of color distribution from Luminance and RGB channels, enhancing overall efficacy. The experimental results demonstrate that the DCGF algorithm effectively restores degraded underwater images with robustness and effectiveness. The method successfully corrects color degradation and recovers details in low-light conditions, significantly improving underwater image quality.


  • A Novel Feature Fusion Framework for Industrial Automation Single-Multiple Object Detection

    by Peilun Lyu, Jiazheng Liu, Yuhan Zhang, Ben Ye, Ting Lan, Li-Ping Bai, Zhanchuan Cai, Zhi-Hong Jiang

    Traditional Chinese medicines (TCMs) play an important role in the treatment of many diseases. For industrial production, classical TCMs identification methods suffer from high labor cost and low efficiency. Moreover the complex multi-object combinations of TCMs lead to serious feature confusion problem. In this article, we propose a novel detection network for TCMs called TCMnet. It focuses on the performance degradation caused by the images in different datasets containing different number of objects. First, an innovative multilevel feature fusion framework is proposed, which improves the generalization of the model. Then, a receptive field controlling architecture is established to limit the receptive field for reducing the confusion among multiple objects. Finally, a trainable feature resolution enhancement algorithm is proposed to increase the precision of classifier by enhancing local detail information. In the experiments, we choose 18 classes with 1800 images from our TCMs dataset. The experimental results show that TCMnet proposed in this article is able to mitigate the feature confusion problem in single-multiple object detection. In addition, TCMnet achieves a good accuracy compared with other detectors on single-object and multi-object detection tasks.


  • Detection of Road Surface Crack Based on PYNQ

    by Zhang Yuhan, Qin Juan, Guo Zhiling, Jiang Kuncheng, Cai Shiyuan

    This project aims at the problem of road surface image denoising and crack recognition by using embedded camera. Using Gaussian filter to blur the image, over the threshold zero processing and the morphology on and off operation are binarization and further denoising. And the crack contour is marked by FAST feature point recognition, which reach for different road crack damage can be identified. After the simulation, the algorithm is transplanted to the Python on Zynq (PYNQ) system to achieve the purpose of crack identification. There are two parts to the innovation: First, using a lower-cost embedded camera to capture photos, and second, using the characteristics of large difference in gray value between crack region and other regions, the crack profile is marked by the way of FAST feature point recognition and use PYNQ to process. It makes the identification system more integrated and portable, and can judge the crack more accurately and reduce the cost.