检索结果-内蒙古大学图书馆

Dynamic View Synthesis from Small Camera Motion Videos

IEEE Transactions on Visualization and Computer Graphics 2025年 PP卷 PP页

作者： Sun, Huiqiang Li, Xingyi Peng, Juewen Shen, Liao Cao, Zhiguo Xian, Ke Lin, Guosheng Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Wuhan 430074 China Nanyang Technological University (NTU) S-Lab 639798 Singapore Huazhong University of Science and Technology School of Electronic Information and Communications Wuhan 430074 China

Novel view synthesis for dynamic 3D scenes poses a significant challenge. Many notable efforts use NeRF-based approaches to address this task and yield impressive results. However, these methods rely heavily on sufficient motion parallax in the input images or videos. When the camera motion range becomes limited or even stationary (i.e., small camera motion), existing methods encounter two primary challenges: incorrect representation of scene geometry and inaccurate estimation of camera parameters. These challenges make prior methods struggle to produce satisfactory results or even become invalid. To address the first challenge, we propose a novel Distribution-based Depth Regularization (DDR) that ensures the rendering weight distribution to align with the true distribution. Specifically, unlike previous methods that use depth loss to calculate the error of the expectation, we calculate the expectation of the error by using Gumbel-softmax to differentiably sample points from discrete rendering weight distribution. Additionally, we introduce constraints that enforce the volume density of spatial points before the object boundary along the ray to be near zero, ensuring that our model learns the correct geometry of the scene. To demystify the DDR, we further propose a visualization tool that enables observing the scene geometry representation at the rendering weight level. For the second challenge, we incorporate camera parameter learning during training to enhance the robustness of our model to camera parameters. We conduct extensive experiments to demonstrate the effectiveness of our approach in representing scenes with small camera motion input, and our results compare favorably to state-of-the-art methods. © 1995-2012 IEEE.

关键词： Dynamic NeRF Neural radiance field Novel view synthesis Small camera motion

来源：评论

学校读者我要写书评

暂无评论

Fast alignment of marks in COG bonding based on multi-resolution

Fast alignment of marks in COG bonding based on multi-resolu...

引用

MIPPR 2007: Automatic Target Recognition and image Analysis;and Multispectral image Acquisition

作者： Geng, Hui Hong, Hanyu Zhang, Yan Lin, Zhimin Lab. for Image Processing and Intelligence Control Wuhan Institute of Technology Hubei 430074 China

ISBN: (纸本)9780819469502

COG (chip on glass) bonding is widely used in LCD industry. The alignment of marks in COG bonding needs high precision and reliability. It is of utmost importance to find two marks in COG fast and exactly. Its key technique is to use the advanced optical system to get the two-marked positions of chip on the glass, and to use the PLC procedure control to complete the automatic alignment. A series of experiments are performed to test the algorithms proposed, which show that the fast alignment of marks in COG bonding based on multi-resolution is both rational and highly effective.

关键词： Liquid crystal displays

来源：评论

学校读者我要写书评

暂无评论

The depth information estimation of microscope defocus image based-on Markov random field

The depth information estimation of microscope defocus image...

引用

2008 IEEE International Conference on Robotics, Automation and Mechatronics, RAM 2008

作者： Zeng, Xiangjin Huang, Xinhan Wang, Min Peng Li Department of Control Science and Engineering Key Lab. of Image Processing and Intelligence Control HUST Wuhan China

ISBN: (纸本)9781424416769

For depth information estimation of microscope defocus image, a blur parameter model of defocus image based on Markov random field has been present. It converts problem of depth estimation into optimization problem. An improved Iterated Conditional Modes Algorithm has been applied to complete optimization problem, which the select of initial point employed Least squares estimate algorithm prevents that the result gets into local optimization. The experiments and simulations prove that the model and algorithm is efficiency. © 2008 IEEE.

关键词： Microscopes

来源：评论

学校读者我要写书评

暂无评论

3-D reconstruction of blood vessels skeleton based on Neural network

3-D reconstruction of blood vessels skeleton based on Neural...

引用

13th International Conference on Neural Information processing, ICONIP 2006

作者： Zhiguo, Cao Bo, Peng Institute of Image Processing and Artificial Intelligence Huazhong University of Sci. and Tec. State Key Lab. for Image Processing and Intelligent Control Wuhan 430074 Hubei China

ISBN: (纸本)3540464840

For the 3-D reconstruction of blood vessels skeleton from biplane angiography system, an efficient 3-D reconstruction method based on neural network(NN) is proposed in this paper. First, we find a set of 2-D corresponding points on the vessels' skeleton in the matched image pair. Secondly, NN is utilized to build the relationships between the 3-D points and their projective 2-D points. Thirdly, by feeding the corresponding points we found into the NN, the 3D coordinates of the points on vessels can be obtained. At last we employ B-spline interpolation to improve reconstruction performance. Experiment results demonstrate the efficiency of the new method. © Springer-Verlag Berlin Heidelberg 2006.

关键词： Blood vessels

来源：评论

学校读者我要写书评

暂无评论

A comparative study of radial basis function neural networks in dynamic clustering algorithm

A comparative study of radial basis function neural networks...

引用

MIPPR 2009 - Pattern Recognition and Computer Vision: 6th International Symposium on Multispectral image processing and Pattern Recognition

作者： Zhou, Peng Li, Dehua Wu, Hong Zeng, Jun Chen, Feng State Key Lab. for Image Processing and Intelligent Control Institute for Pattern Recognition and Intelligence Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9780819478078

This paper developed two learning procedure, respectively, based on the orthogonal least squares (OLS) method and the "Innovation- Contribution" criterion (ICc) proposed newly. The orthogonal use of the stepwise-regression algorithm of the ICc mages the model structure independent of the selected term sequence and reduces the cluster region further as compared with orthogonal least squares (OLS). as the Bayesian information criteria (BIC) method is incorporate into the clustering process of the ICc, except for the widths of Gaussian functions, it has no other parameter that need tuning ,but the user is required to specify the tolerance ρ, which is relevant to noises and will be difficult to implement in the real system, for the OLS algorithm. The two algorithms are employed to the Radial Basis Function Neural Networks (RBFNN) to compare its performance for different noise nonlinear dynamic systems. Experimental results show that they provide an efficient approximation to the required results for fitting models, but the clustering procedures of the ICc is substantially better solutions than does the OLS. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： Radial basis function networks

来源：评论

学校读者我要写书评

暂无评论

Integer Haar wavelet for romote sensing image compression 6

Integer Haar wavelet for romote sensing image compression

引用

6th International Conference on Signal processing, ICSP 2002

作者： Zhenhua, Wang Hongbo, Xu Yan, Tian Jinwen, Tian Jian, Liu State Key Lab. for Image Processing and Intelligent Control Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)0780374886

With the development of remote sensing technique, onboard data compression has become an urgent need and a lot of study has been directed toward the development of efficient techniques. In this paper, the construction approach of integer Haar is discussed briefly, and a'simple image compression scheme based on integer Haar Wavelet Transform and block DPCM is proposed. The scheme can be easily designed for data processing in real-time system of remote sensing with parellel algorithm. Simulation experimental results demonstrate that the proposed approach is a efficient image compression method. © 2002 IEEE.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

Modeling of cortical signals using echo state networks

Modeling of cortical signals using echo state networks

引用

MIPPR 2009 - Pattern Recognition and Computer Vision: 6th International Symposium on Multispectral image processing and Pattern Recognition

作者： Zhou, Hanying Wang, Yongji Huang, Jiangshuai Key Lab. for Image Processing and Intelligent Control Department of Control Science and Engineering Huazhong University of Science and Technology China

ISBN: (纸本)9780819478078

Diverse modeling frameworks have been utilized with the ultimate goal of translating brain cortical signals into prediction of visible behavior. The inputs to these models are usually multidimensional neural recordings collected from relevant regions of a monkey's brain while the outputs are the associated behavior which is typically the 2-D or 3-D hand position of a primate. Here our task is to set up a proper model in order to figure out the move trajectories by input the neural signals which are simultaneously collected in the experiment. In this paper, we propose to use Echo State Networks (ESN) to map the neural firing activities into hand positions. ESN is a newly developed recurrent neural network(RNN) model. Besides its dynamic property and short term memory just as other recurrent neural networks have, it has a special echo state property which endows it with the ability to model nonlinear dynamic systems powerfully. What distinguished it from transitional recurrent neural networks most significantly is its special learning method. In this paper we train this net with a refined version of its typical training method and get a better model. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Design of a wearable rehabilitation robotic hand actuated by pneumatic artificial muscles

Design of a wearable rehabilitation robotic hand actuated by...

引用

2009 7th Asian control Conference, ASCC 2009

作者： Kexin, Xing Jian, Huang Qi, Xu Yongji, Wang Key Lab. of Image Processing and Intelligent Control Department of Control Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9788995605691

Intensive task-oriented repetitive physical therapies provided by individualized interaction between the patient and the rehabilitation specialist can improve the hand motor performance of the patient survived from stroke or traumatic brain injury. However, the therapy is time-consuming and expensive. Furthermore, it is difficult to evaluate the result of therapy quantitatively and objectively. The goal of this research is to develop a novel wearable device for robotic assistive hand repetitive therapy. We designed a pneumatic artificial muscle (PAM) driven rehabilitation robotic hand that is wearable and provides assistive forces required for grasping and release movements. The robot has two distinct degrees of freedom at the thumb and the fingers. The embedded sensors are employed to obtain the feedback position and force information for robot control and quantitative evaluation of task performance. To encourage the patients' self-regulation and improve the performance of the task, a PC based Virtual Reality game was developed. In order to realize a compliant and smooth motion, cubic spline functions are adopted in the trajectory planning of metacarpophalangeal joints. To realize the trajectory tracking control, a conventional PID controller was implemented and evaluated. Experiments were performed to confirm the effectiveness of the proposed device and methods. The robot has the potential of providing supplemental at-home therapy in addition to in the clinic treatment. ©2009 ACA.

关键词： Degrees of freedom (mechanics)

来源：评论

学校读者我要写书评

暂无评论

A Security and Trust Protection Framework for Open CNC Production Line

A Security and Trust Protection Framework for Open CNC Produ...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Dong, Zeyang Qin, Yuanqing Li, Zewei Wang, Hanwen Huazhong University of Science and Technology School of Artificial Intelligence and Automation MOE Lab of Image Processing and Intelligent Control Wuhan China

ISBN: (纸本)9781665465335

With the further integration of information technology and industry, the computer numerical control (CNC) production line has gradually changed from the original isolated and closed mode to an open one. It faces not only internal threats, but also threats from the Internet. Starting from the characteristics and cybersecurity problem analysis of open CNC production lines, this paper proposes a security and trust protection framework based on trusted computing 3.0 and the concept of defense in depth, where a tri-element peer architecture is introduced to realize two-way authentication between the access device and the platform and an active immunity scheme for open CNC system is designed to ensure the trust from the source, and the trusted NC-Link agent/adaper are utilized to connect the heterogeneous equipments trustedly in the production line. The proposed framework can improve the information security level of the open CNC production line while maintaining its openness. © 2022 IEEE.

关键词： Trusted computing

来源：评论

学校读者我要写书评

暂无评论

A new fuzzy ART neural network based on dual competition and resonance technique

A new fuzzy ART neural network based on dual competition and...

引用

3rd International Symposium on Neural Networks, ISNN 2006 - Advances in Neural Networks

作者： Zhang, Lei Wang, Guoyou Wang, Wentao Lab. for Biometric and Medical Image Processing Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)354034439X

A new Fuzzy ART neural network model based on dual competition and resonance technique is proposed. This new model takes the competition and resonance method of the input nodes into the output nodes, putting the input nodes and output nodes competition and resonance together, solves the over-segmentation of the FART algorithm due to the vigilance's increase in the application of the image segmentation. Experimental results have shown that compared with the original FART, this algorithm has a better segmentation and antinoise performance. © Springer-Verlag Berlin Heidelberg 2006.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：