Xuan Zhou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xuan Zhou has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Xinnan Fan
College of Information Science and Engineering, Hohai University, Changzhou 213200, China
3 shared publications - Pengfei Shi
College of Artificial Intelligence and Automation, Hohai University, Changzhou 213200, China
2 shared publications - Hao Jin
College of Information Science and Engineering, Hohai University, Changzhou 213000, China
1 shared publication - Hexiong Yan
College of Artificial Intelligence and Automation, Hohai University, Changzhou 213000, China
1 shared publication - Huanru Sun
College of Information Science and Engineering, Hohai University, Changzhou 213200, China
1 shared publication - Liang Lu
College of IoT Engineering, Hohai University, Changzhou, China
1 shared publication
Latest Publications
- Open Access
New Underwater Image Enhancement Algorithm Based on Improved U-Net
(1) Objective: As light propagates through water, it undergoes significant attenuation and scattering, causing underwater images to experience color distortion and exhibit a bluish or greenish tint. Additionally, suspended particles in the water further degrade image quality. This paper proposes an improved U-Net network model for underwater image enhancement to generate high-quality images. (2) Method: Instead of incorporating additional complex modules into enhancement networks, we opted to simplify the classic U-Net architecture. Specifically, we replaced the standard convolutions in U-Net with our self-designed efficient basic block, which integrates a simplified channel attention mechanism. Moreover, we employed Layer Normalization to enhance the capability of training with a small number of samples and used the GELU activation function to achieve additional benefits in image denoising. Furthermore, we introduced the SK fusion module into the network to aggregate feature information, replacing traditional concatenation operations. In the experimental section, we used the “Underwater ImageNet” dataset from “Enhancing Underwater Visual Perception (EUVP)” for training and testing. EUVP, established by Islam et al., is a large-scale dataset comprising paired images (high-quality clear images and low-quality blurry images) as well as unpaired underwater images. (3) Results: We compared our proposed method with several high-performing traditional algorithms and deep learning-based methods. The traditional algorithms include He, UDCP, ICM, and ULAP, while the deep learning-based methods include CycleGAN, UGAN, UGAN-P, and FUnIEGAN. The results demonstrate that our algorithm exhibits outstanding competitiveness on the underwater imagenet-dataset. Compared to the currently optimal lightweight model, FUnIE-GAN, our method reduces the number of parameters by 0.969 times and decreases Floating-Point Operations Per Second (FLOPS) by more than half. In terms of image quality, our approach achieves a minimal UCIQE reduction of only 0.008 while improving the NIQE by 0.019 compared to state-of-the-art (SOTA) methods. Finally, extensive ablation experiments validate the feasibility of our designed network. (4) Conclusions: The underwater image enhancement algorithm proposed in this paper significantly reduces model size and accelerates inference speed while maintaining high processing performance, demonstrating strong potential for practical applications.
Open AccessNew Underwater Image Enhancement Algorithm Based on Improved U-Net
(1) Objective: As light propagates through water, it undergoes significant attenuation and scattering, causing underwater images to experience color distortion and exhibit a bluish or greenish tint. Additionally, suspended particles in the water further degrade image quality. This paper proposes an improved U-Net network model for underwater image enhancement to generate high-quality images. (2) Method: Instead of incorporating additional complex modules into enhancement networks, we opted to simplify the classic U-Net architecture. Specifically, we replaced the standard convolutions in U-Net with our self-designed efficient basic block, which integrates a simplified channel attention mechanism. Moreover, we employed Layer Normalization to enhance the capability of training with a small number of samples and used the GELU activation function to achieve additional benefits in image denoising. Furthermore, we introduced the SK fusion module into the network to aggregate feature information, replacing traditional concatenation operations. In the experimental section, we used the “Underwater ImageNet” dataset from “Enhancing Underwater Visual Perception (EUVP)” for training and testing. EUVP, established by Islam et al., is a large-scale dataset comprising paired images (high-quality clear images and low-quality blurry images) as well as unpaired underwater images. (3) Results: We compared our proposed method with several high-performing traditional algorithms and deep learning-based methods. The traditional algorithms include He, UDCP, ICM, and ULAP, while the deep learning-based methods include CycleGAN, UGAN, UGAN-P, and FUnIEGAN. The results demonstrate that our algorithm exhibits outstanding competitiveness on the underwater imagenet-dataset. Compared to the currently optimal lightweight model, FUnIE-GAN, our method reduces the number of parameters by 0.969 times and decreases Floating-Point Operations Per Second (FLOPS) by more than half. In terms of image quality, our approach achieves a minimal UCIQE reduction of only 0.008 while improving the NIQE by 0.019 compared to state-of-the-art (SOTA) methods. Finally, extensive ablation experiments validate the feasibility of our designed network. (4) Conclusions: The underwater image enhancement algorithm proposed in this paper significantly reduces model size and accelerates inference speed while maintaining high processing performance, demonstrating strong potential for practical applications.
- 20 June 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (4) , 10233-10246
An effective automatic object detection algorithm for continuous sonar image sequences
- 20 June 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (4) , 10233-10246
An effective automatic object detection algorithm for continuous sonar image sequences
- 11 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 29 (10709908) , 1609-1613
RAFM: Recurrent Atrous Feature Modulation for Accurate Monocular Depth Estimating
Current top-performing coarse-to-fine monocular depth estimation systems mainly depend on deeper backbones, such as a full ResNet50. These systems benefit from the powerful multiscale feature representations but suffer from the high computational costs and memory overheads. Conversely, the recurrent depth refinement systems fulfill the lightweight architecture, while the local multiscale context often limits their accuracies. To handle this problem, we propose an atrous spatial (AS) module by utilizing atrous convolutions with different rates, which efficiently captures the multiscale context. We further assemble our AS module to the current recurrent depth refinement system R-MSFM, constructing a powerful monocular depth estimation system called RAFM. To evaluate its effectiveness, we conduct the comprehensive experiments and show that our RAFM outperforms the previous SOTA methods in all metrics on KITTI while keeping the real-time speed. For accuracy, our RAFM achieves a square relative error (Sq Rel) of 0.702 on KITTI, a 12.6% error reduction from the previous SOTA method (0.802). For model size and inference speed, our RAFM gets a frame rate of 33fps on a GPU with 7.5 M parameters, which is faster and more lightweight than the recent SOTA method (5fps and 128 M). The code is available at https://github.com/jsczzzk/RAFM.
- 11 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 29 (10709908) , 1609-1613
RAFM: Recurrent Atrous Feature Modulation for Accurate Monocular Depth Estimating
Current top-performing coarse-to-fine monocular depth estimation systems mainly depend on deeper backbones, such as a full ResNet50. These systems benefit from the powerful multiscale feature representations but suffer from the high computational costs and memory overheads. Conversely, the recurrent depth refinement systems fulfill the lightweight architecture, while the local multiscale context often limits their accuracies. To handle this problem, we propose an atrous spatial (AS) module by utilizing atrous convolutions with different rates, which efficiently captures the multiscale context. We further assemble our AS module to the current recurrent depth refinement system R-MSFM, constructing a powerful monocular depth estimation system called RAFM. To evaluate its effectiveness, we conduct the comprehensive experiments and show that our RAFM outperforms the previous SOTA methods in all metrics on KITTI while keeping the real-time speed. For accuracy, our RAFM achieves a square relative error (Sq Rel) of 0.702 on KITTI, a 12.6% error reduction from the previous SOTA method (0.802). For model size and inference speed, our RAFM gets a frame rate of 33fps on a GPU with 7.5 M parameters, which is faster and more lightweight than the recent SOTA method (5fps and 128 M). The code is available at https://github.com/jsczzzk/RAFM.