Tong Zhai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Tong Zhai has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Zhiguo Zhang
Beijing University of Posts and Telecommunications
3 shared publications - Haojie Zhang
State Key Lab of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications (BUPT), Beijing 100876, China
2 shared publications - Kun Yang
State Key Lab of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications (BUPT), Beijing 100876, China
2 shared publications - Yufei Qiu
State Key Lab of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications (BUPT), Beijing 100876, China
2 shared publications - Shanming Liu
School of Integrated Circuit Science and Engineering, Beihang University, Beijing 100191, China
1 shared publication - Shaolong Chang
State key laboratory of Information photonics and optical communications, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China
1 shared publication
Latest Publications
- Open Access
Optimizing the Reliability of Underground Utility Tunnel Localization via Multi-Source Fusion and DVAE-CNN
This paper proposes a reliability-optimized localization method for underground utility tunnels based on multi-source fusion and a denoising variational autoencoder model. The method acquires a multi-sensor localization dataset aligned with a unified time reference. By employing a convolutional neural network-assisted denoising variational autoencoder (DVAE-CNN), it regulates localization outcomes through three key aspects: a multi-source heterogeneous data quality assessment model, a formulation of the target state transition equation, and an environmental prior-information-aided weight update strategy. This approach overcomes the low-reliability issues caused by information loss and errors in the complex environment of underground utility tunnels. Compared to localization results without reliability regulation mechanisms, the proposed method achieves an average improvement of 73.6% in localization accuracy and 85.2% in localization reliability. Finally, localization experiments conducted in an underground utility tunnel demonstrate that the proposed method can provide highly robust, reliable and continuous positioning services, indicating significant potential for application and broader adoption.
Open AccessOptimizing the Reliability of Underground Utility Tunnel Localization via Multi-Source Fusion and DVAE-CNN
This paper proposes a reliability-optimized localization method for underground utility tunnels based on multi-source fusion and a denoising variational autoencoder model. The method acquires a multi-sensor localization dataset aligned with a unified time reference. By employing a convolutional neural network-assisted denoising variational autoencoder (DVAE-CNN), it regulates localization outcomes through three key aspects: a multi-source heterogeneous data quality assessment model, a formulation of the target state transition equation, and an environmental prior-information-aided weight update strategy. This approach overcomes the low-reliability issues caused by information loss and errors in the complex environment of underground utility tunnels. Compared to localization results without reliability regulation mechanisms, the proposed method achieves an average improvement of 73.6% in localization accuracy and 85.2% in localization reliability. Finally, localization experiments conducted in an underground utility tunnel demonstrate that the proposed method can provide highly robust, reliable and continuous positioning services, indicating significant potential for application and broader adoption.
- Open Access
Self-Supervised Joint Learning for pCLE Image Denoising
Probe-based confocal laser endoscopy (pCLE) has emerged as a powerful tool for disease diagnosis, yet it faces challenges such as the formation of hexagonal patterns in images due to the inherent characteristics of fiber bundles. Recent advancements in deep learning offer promise in image denoising, but the acquisition of clean-noisy image pairs for training networks across all potential scenarios can be prohibitively costly. Few studies have explored training denoising networks on such pairs. Here, we propose an innovative self-supervised denoising method. Our approach integrates noise prediction networks, image quality assessment networks, and denoising networks in a collaborative, jointly trained manner. Compared to prior self-supervised denoising methods, our approach yields superior results on pCLE images and fluorescence microscopy images. In summary, our novel self-supervised denoising technique enhances image quality in pCLE diagnosis by leveraging the synergy of noise prediction, image quality assessment, and denoising networks, surpassing previous methods on both pCLE and fluorescence microscopy images.
Open AccessSelf-Supervised Joint Learning for pCLE Image Denoising
Probe-based confocal laser endoscopy (pCLE) has emerged as a powerful tool for disease diagnosis, yet it faces challenges such as the formation of hexagonal patterns in images due to the inherent characteristics of fiber bundles. Recent advancements in deep learning offer promise in image denoising, but the acquisition of clean-noisy image pairs for training networks across all potential scenarios can be prohibitively costly. Few studies have explored training denoising networks on such pairs. Here, we propose an innovative self-supervised denoising method. Our approach integrates noise prediction networks, image quality assessment networks, and denoising networks in a collaborative, jointly trained manner. Compared to prior self-supervised denoising methods, our approach yields superior results on pCLE images and fluorescence microscopy images. In summary, our novel self-supervised denoising technique enhances image quality in pCLE diagnosis by leveraging the synergy of noise prediction, image quality assessment, and denoising networks, surpassing previous methods on both pCLE and fluorescence microscopy images.
- Open Access
High-Resolution Image Processing of Probe-Based Confocal Laser Endomicroscopy Based on Multistage Neural Networks and Cross-Channel Attention Module
Probe-based confocal laser endomicroscopy (pCLE) is a subcellular in vivo imaging technique that generates diagnostic images revealing malignant structural modifications in epithelial tissues. In the clinical diagnosis of probe confocal laser endomicroscopy (pCLE), the image background generally has the problems of dynamic blur or information loss, which is not conducive to achieving high-resolution and clear pCLE imaging. In recent years, deep learning technology has achieved remarkable results in image deblurring. For the task of recovering high-resolution pCLE images, the current methods still suffer from the following drawbacks: it is difficult to choose a strategy to make CNN converge at a deeper level and mainstream methods cannot handle the complex balance between spatial details and high-level feature information well when reconstructing clear images. In order to solve the problem, we propose a new cross-channel attention, multistage, high-resolution pCLE image deblurring structure. This methodology improves the supervised attention mechanism, enhances the ability of feature extraction and fusion capabilities, and improves the quality of image deblurring by adding cross-channel attention module (CAM) into the multistage neural networks’ architecture. The experimental results show that the average peak signal-to-noise ratio (PSNR) of the proposed model on the dataset is as high as 29.643 dB, and the structural similarity (SSIM) reaches 0.855. This method is superior to the prior algorithms in the visualization of recovered images, and the edge and texture details of the restored pCLE images are clearer.
Open AccessHigh-Resolution Image Processing of Probe-Based Confocal Laser Endomicroscopy Based on Multistage Neural Networks and Cross-Channel Attention Module
Probe-based confocal laser endomicroscopy (pCLE) is a subcellular in vivo imaging technique that generates diagnostic images revealing malignant structural modifications in epithelial tissues. In the clinical diagnosis of probe confocal laser endomicroscopy (pCLE), the image background generally has the problems of dynamic blur or information loss, which is not conducive to achieving high-resolution and clear pCLE imaging. In recent years, deep learning technology has achieved remarkable results in image deblurring. For the task of recovering high-resolution pCLE images, the current methods still suffer from the following drawbacks: it is difficult to choose a strategy to make CNN converge at a deeper level and mainstream methods cannot handle the complex balance between spatial details and high-level feature information well when reconstructing clear images. In order to solve the problem, we propose a new cross-channel attention, multistage, high-resolution pCLE image deblurring structure. This methodology improves the supervised attention mechanism, enhances the ability of feature extraction and fusion capabilities, and improves the quality of image deblurring by adding cross-channel attention module (CAM) into the multistage neural networks’ architecture. The experimental results show that the average peak signal-to-noise ratio (PSNR) of the proposed model on the dataset is as high as 29.643 dB, and the structural similarity (SSIM) reaches 0.855. This method is superior to the prior algorithms in the visualization of recovered images, and the edge and texture details of the restored pCLE images are clearer.