Search

Your search keyword '"Liu, Xinlin"' showing total 551 results
Start Over Author "Liu, Xinlin"
551 results on '"Liu, Xinlin"'

6. Fast Noise Removal in Hyperspectral Images via Representative Coefficient Total Variation

Author

Peng, Jiangjun, Wang, Hailin, Cao, Xiangyong, Liu, Xinlin, Rui, Xiangyu, and Meng, Deyu

Subjects
Computer Science - Computer Vision and Pattern Recognition, Electrical Engineering and Systems Science - Image and Video Processing
Abstract

Mining structural priors in data is a widely recognized technique for hyperspectral image (HSI) denoising tasks, whose typical ways include model-based methods and data-based methods. The model-based methods have good generalization ability, while the runtime cannot meet the fast processing requirements of the practical situations due to the large size of an HSI data $ \mathbf{X} \in \mathbb{R}^{MN\times B}$. For the data-based methods, they perform very fast on new test data once they have been trained. However, their generalization ability is always insufficient. In this paper, we propose a fast model-based HSI denoising approach. Specifically, we propose a novel regularizer named Representative Coefficient Total Variation (RCTV) to simultaneously characterize the low rank and local smooth properties. The RCTV regularizer is proposed based on the observation that the representative coefficient matrix $\mathbf{U}\in\mathbb{R}^{MN\times R} (R\ll B)$ obtained by orthogonally transforming the original HSI $\mathbf{X}$ can inherit the strong local-smooth prior of $\mathbf{X}$. Since $R/B$ is very small, the HSI denoising model based on the RCTV regularizer has lower time complexity. Additionally, we find that the representative coefficient matrix $\mathbf{U}$ is robust to noise, and thus the RCTV regularizer can somewhat promote the robustness of the HSI denoising model. Extensive experiments on mixed noise removal demonstrate the superiority of the proposed method both in denoising performance and denoising speed compared with other state-of-the-art methods. Remarkably, the denoising speed of our proposed method outperforms all the model-based techniques and is comparable with the deep learning-based approaches., Comment: 16 pages, 18 figures, 5 tables, 1 theorem

Published
2022
Full Text
View/download PDF

12. Monocular Depth Estimation with Sharp Boundary

Author

Yang, Xin, Chang, Qingling, Liu, Xinlin, and Cui, Yan

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Monocular depth estimation is the base task in computer vision. It has a tremendous development in the decade with the development of deep learning. But the boundary blur of the depth map is still a serious problem. Research finds the boundary blur problem is mainly caused by two factors, first, the low-level features containing boundary and structure information may loss in deeper networks during the convolution process., second, the model ignores the errors introduced by the boundary area due to the few portions of the boundary in the whole areas during the backpropagation. In order to mitigate the boundary blur problem, we focus on the above two impact factors. Firstly, we design a scene understanding module to learn the global information with low- and high-level features, and then to transform the global information to different scales with our proposed scale transform module according to the different phases in the decoder. Secondly, we propose a boundary-aware depth loss function to pay attention to the effects of the boundary's depth value. The extensive experiments show that our method can predict the depth maps with clearer boundaries, and the performance of the depth accuracy base on NYU-depth v2 and SUN RGB-D is competitive., Comment: 20 pages,9 figures

Published
2021

36. Development and Item Selection of the Inflammatory Bowel Disease Patient-reported Outcomes Scale Based on Theories of Traditional Chinese Medicine

Author

Jianfeng LUO, Jiangtao HOU, Zhengkun HOU, Bin PENG, Huibiao LI, Shiying LIU, Zhenfan HE, Jiamin ZHONG, Shijing ZHANG, Fengbin LIU, Xinlin CHEN

Subjects
inflammatory bowel disease, patient-reported outcomes, tcm theories, quality of life, item selection, construction of scale, Medicine
Abstract

Background The prevalence of inflammatory bowel disease (IBD) increases annually in China. The integrated traditional Chinese and western medicine is helpful to alleviate and control symptoms of IBD. Quality of life (QoL) is an important index to evaluate the clinical efficacy of IBD. However, there are few studies about IBD patient-reported outcomes (PROs) based on TCM theories. Objective To determine the framework and items, and then use them to develop the IBD PROs scale using TCM theories. Methods Under the guidance of the TCM theory of "body and mind harmony, and man's adaptation to his total environment" , literature review, core-group discussion and expert consultation were carried out. The conceptual framework and item pool of the draft of an IBD PROs scale were developed, then the corresponding items were determined, forming the draft of the IBD PROs scale. Then the draft scale was pre-tested in IBD patients treated in Department of Spleen and Stomach Diseases, the First Affiliated Hospital of Guangzhou University of Chinese Medicine from January to June 2021. The dispersion tendency, Cronbach's α and correlation analysis were used for further item selection. Results The final IBD PROs scale is composed of two domains: body and mind harmony (12 body-related items, and 9 mind-related items) and man's adaptation to his total environment (6 items) . Conclusion The IBD PROs scale developed based on theories of TCM could be used to evaluate the QoL of IBD patients. But further clinical research is still needed to verify its reliability and validity.

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results