检索结果-内蒙古大学图书馆

Surface reconstruction from unorganized point clouds based on edge growing

Advances in Manufacturing 2019年第3期7卷 343-352页

作者： Xu-Jia Qin Zhong-Tian Hu Hong-Bo Zheng Mei-Yu Zhang College of Computer Science and Technology Zhejiang University of TechnologyHangzhou 310023People's Republic of China Key Laboratory of Visual Media Intelligent Processing Technology of Zhejiang Province Hangzhou 310023People's Republic of China

Owing to unorganized point cloud data,unexpected triangles,such as holes and slits,may be generated during mesh surface *** solve this problem,a mesh surface reconstruction method based on edge growing from unorganized point clouds is *** method first constructs an octree structure for unorganized point cloud data,and determines the k-nearest neighbor for each ***,the method searches for flat areas in the point clouds to be used as the initial mesh edge growth regions,to avoid incorrect reconstruction of the mesh surface owing to the growth of initial sharp ***,the optimal mesh surface is obtained by controlling the mesh edge growing based on compulsive restriction and comprehensive optimization *** experimental results of mesh surface reconstruction show that the method is feasible and shows high reconstruction performance without introducing holes or slits in the reconstructed mesh surface.

关键词： Mesh surface reconstruction Point clouds Edge growing Octree

来源：评论

学校读者我要写书评

暂无评论

Exploring Optimal Adaptive Activation Functions for Various Tasks

Exploring Optimal Adaptive Activation Functions for Various ...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Aizhu Liu Haigen Hu Tian Qiu Qianwei Zhou Qiu Guan Xiaoxin Li College of Computer Science and Technology Zhejiang University of Technology Hangzhou P.R. China Key Laboratory of Visual Media Intelligent Processing Technology of Zhejiang Province Hangzhou P.R. China

ISBN: (数字)9781728162157

ISBN: (纸本)9781728162164

An activation function is a key component of artificial neural networks (ANNs). It has a great impact on the performance and convergence of neural networks. In this work, a self-adapting methodology is proposed to explore the optimal adaptive activation functions for various tasks based on S-shaped or ReLu-shaped activation functions, which are regulated only by introducing several parameters. To verify the effectiveness of the proposed methodology, a series of comparison experiments are performed with MLP, CNN and RNN network structure on the benchmark datasets of image, text and audio. The experimental results are encouraging, and show that the proposed methodology can locate the optimal activation functions for various tasks. Nevertheless, the obtained functions are competitive and the improvements on network performance are significant compared with other popular activation functions, such as ELU, PReLU, ReLU, and Sigmoid.

关键词： Adaptive systems Task analysis Biological neural networks Convergence Neurons Shape Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

SC3EF: A Joint Self-Correlation and Cross-Correspondence Estimation Framework for Visible and Thermal Image Registration

arXiv

引用

arXiv 2025年

作者： Tong, Xi Luo, Xing Yang, Jiangxin Cao, Yanpeng Li, Xin State Key Laboratory of Fluid Power and Mechatronic Systems Laboratory of Advanced Manufacturing Technology of Zhejiang Province School of Mechanical Engineering Zhejiang University Hangzhou310027 China Section of Visual Computing and Creative Media School of Performance Visualization and Fine Arts Texas A&M University College StationTX77843 United States

Multispectral imaging plays a critical role in a range of intelligent transportation applications, including advanced driver assistance systems (ADAS), traffic monitoring, and night vision. However, accurate visible and thermal (RGB-T) image registration poses a significant challenge due to the considerable modality differences. In this paper, we present a novel joint Self-Correlation and Cross-Correspondence Estimation Framework (SC3EF), leveraging both local representative features and global contextual cues to effectively generate RGB-T correspondences. For this purpose, we design a convolution-transformer-based pipeline to extract local representative features and encode global correlations of intra-modality for inter-modality correspondence estimation between unaligned visible and thermal images. After merging the local and global correspondence estimation results, we further employ a hierarchical optical flow estimation decoder to progressively refine the estimated dense correspondence maps. Extensive experiments demonstrate the effectiveness of our proposed method, outperforming the current state-of-the-art (SOTA) methods on representative RGB-T datasets. Furthermore, it also shows competitive generalization capabilities across challenging scenarios, including large parallax, severe occlusions, adverse weather, and other cross-modal datasets (e.g., RGB-N and RGB-D). Copyright © 2025, The Authors. All rights reserved.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

Enhanced Entropy-Based Resource Searching in Unstructured P2P Networks

引用

Chinese Journal of Electronics 2015年第2期24卷 229-235页

作者： GONG Weihua JIN Rong YANG Lianghuai HUANG Decai School of Computer Science and Technology Zhejiang University of Technology Key Laboratory of Visual Media Intelligent Process Technology of Zhejiang Province School of Informatics and Electronics Zhejiang Sci-Tech University

How to find desired resources efficiently and accurately is one fundamental challenge of any unstructured P2 P networks, which is mainly involved some difficulties in the P2 P overlay topology, data representation in peers and routing mechanism. In this paper, we address the issue of resilient routing in unstructured P2 P networks. An efficient algorithm called Query routing tree(QRT) based on maximum mutual information is proposed to improve the performance of resource searching, which has tightly associated the resource contents of peers with the logical links in P2 P network that makes the query messages forwarded more effectively in similar peers and can hit more target resources faster. Additionally, we present an optimized routing scheme with the query conditions taken into account, to obtain the optimal routing tree with the minimal information gain from the candidate tree set so as to adapt to different query types more flexibly. The simulation results show the proposed QRT can reduce the search cost more effectively and maintain higher targets hit rate than existing typical algorithms such as Flooding, k-RW and APS. Finally, our optimized scheme is also proved to conduct high searching performance with nicer self-adaptability and scalability in unstructured P2 P networks.

关键词： Peer-to-peer(P2P) Resource searching Entropy Query routing tree Information gain

来源：评论

学校读者我要写书评

暂无评论

Multi-style video stylization based on texture advection

引用

Science China(Information Sciences) 2015年第11期58卷 90-102页

作者： TANG Ying ZHANG Yan SHI XiaoYing FAN Jing School of Computer Science and Technology Zhejiang University of Technology Key Laboratory of Visual Media Intelligent Process Technology of Zhejiang Province School of Software Engineering Hangzhou Dianzi University

Artistic video stylization, which is widely used in multimedia entertainment, transforms a given video into different artistic styles. Most of the existing video stylization algorithms can simulate single or limited video artistic styles. Although some algorithms can achieve multi-style video processing, these algorithms are complex and difficult to implement. To solve this problem, we propose a multi-styled video stylization algorithm based on texture advection, where different artistic styles are synthesized and transferred from user-specified texture samples of desired styles. We use the direction field-guided texture synthesis to compute the texture layer that represents the artistic style. Painterly directional video styles are simulated competently by the orientation changes in the synthesized anisotropic textures. There appeared local distorted region of the texture layer during texture advection under the optical flow field. To address this issue, we propose the texture inpaint to synthesize the limited distorted region and make the stylized video temporally coherent. We also accelerate the video stylization by using the CUDA parallel computing framework that parallelly computes the morphological operations used for video abstraction. Finally, we produce stylized videos of multiple artistic styles with satisfactory experimental results, including the styles of oil painting, watercolor painting and stylized lines drawing.

关键词： non-photorealistic rendering video stylization texture synthesis direction field CUDA

来源：评论

学校读者我要写书评

暂无评论

An optimized texture-by-numbers synthesis method and its visual applications

引用

Science China(Information Sciences) 2013年第5期56卷 50-63页

作者： FAN Jing SHI XiaoYing ZHOU Zhan TANG Ying School of Computer Science and Technology Zhejiang University of Technology Key Laboratory of Visual Media Intelligent Processing Technology of Zhejiang Province School of Information Engineering Zhejiang University of Technology

The framework of texture-by-numbers(TBN) synthesizes images of global-varying patterns with intuitive user *** TBN synthesis methods have difficulties in achieving high-quality synthesis results and efficiency *** paper proposes a fast TBN synthesis method based on texture optimization,which uses global optimization to solve the controllable non-homogeneous texture synthesis *** algorithm produces high quality synthesis results by combining texture optimization into TBN framework with two *** initialization process is adopted to generate the initial output of the global optimization algorithm,which speeds up the algorithm’s convergence rate and enhances synthesis *** distance metrics to measure image similarities are specifically designed for different images to better match human visual perception for structural patterns and a user study is conducted to verify the effectiveness of the *** further improve the synthesis speed,the algorithm is entirely implemented on GPU based on CUDA *** optimized TBN method is applied to various visual applications including not only traditional TBN applications,but also image in-painting and texture-based flow *** experimental results show that our method synthesizes images of higher or comparable qualities with higher efficiency than other state-of-art synthesis methods.

关键词： texture-by-number texture optimization feature synthesis CUDA

来源：评论

学校读者我要写书评

暂无评论

An efficient routing algorithm based on mutual information in unstructured P2P networks

引用

Journal of Computational Information Systems 2013年第17期9卷 7011-7019页

作者： Gong, Weihua Yang, Lianghuai Chen, Jiujun Pei, Xiaobing School of Computer Science and Technology Zhejiang University of Technology Hangzhou 310023 China Key Laboratory of Visual Media Intelligent Process Technology of Zhejiang Province Hangzhou 310023 China School of Software Engineering Huazhong University of Science and Technology Wuhan 430074 China

Resource searching is the first and foremost challenge in unstructured P2P networks. Although having received a lot of attentions during past few years, many proposed search methods still can't avoid some serious drawbacks such as high cost and low effciency in dynamic P2P environment. To resolve these weaknesses, this paper proposes an e?cient Query Routing Tree (QRT) algorithm based on maximum mutual information to improve the performance of resource searching, which has tightly associated the resource contents of peers with the logical links of P2P network. The primary benefits are that our proposed QRT algorithm can make the query messages forwarded more effectively in similar peers and hit more target resources faster. The experimental results show that our proposed QRT algorithm can decrease the search cost more effectively and maintain higher targets hit rate compared to Flooding, k-RW and APS algorithms, and the QRT algorithm is also proved to conduct high searching performance with better scalability in unstructured P2P networks. © 2013 Binary Information Press.

关键词： Forestry

来源：评论

学校读者我要写书评

暂无评论

Public transit vehicle arrival information system based on mobile internet

Public transit vehicle arrival information system based on m...

引用

2013 International Conference on Vehicle and Mechanical Engineering and Information technology, VMEIT 2013

作者： Pan, Jian Dai, Xiu Ting Xu, Xiao Qi Lou, Yi Chao College of Computer of Science and Technology Zhejiang University of Technology Hangzhou 310023 China Key Laboratory of Visual Media Intelligent Process Technology of Zhejiang Province Hangzhou 310023 China College of Information and Electronic Engineering Zhejiang Gongshang University Hangzhou 310018 China

ISBN: (纸本)9783037858202

At present, arrival time information service and security supervision of public transit vehicles have become a hot issue of society and government departments. In this paper, a system for notifying passengers waiting for buses of the status of the vehicles, including the arrival times of vehicles at stops, is proposed. The system includes GPS devices located in the vehicles for determining the location of the vehicles along their routes. A server is coupled to the GPS devices for receiving the locations of vehicles, computing the arrival times of vehicles based on history data model, and publishing the information on website using RESTful API. Experiments on real datasets show that the system is a powerful tool for arrival time prediction of public transit vehicles. © (2013) Trans Tech Publications, Switzerland.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Ontology-based knowledge management for forest channel

Ontology-based knowledge management for forest channel

引用

2012 9th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2012

作者： Fan, Jing Liu, Xiuying Shen, Ying Dong, Tianyang Key Laboratory of Visual Media Intelligent Processing Technology of Zhejiang Province School of Computer Science and Technology Zhejiang University of Technology Hangzhou 310023 China

ISBN: (纸本)9781467300223

Forest channel is an important part of land greening. In order to scientifically configure the species of the forest channel, this paper proposed an ontology-based method for forest channel knowledge management. The forest channel knowledge can be described as three parts: green regions, species characteristics, species configure modes. Combined with self-defined rules and knowledge, greening scheme can be reasoned based on customer's requirement. Several typical technologies are used in this system, such as OWL to represent the forest channel ontology and Jena to reason on the rules. This method can help make strategic decisions in forest channel knowledge management. © 2012 IEEE.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Ontology-based knowledge management for forest channel

Ontology-based knowledge management for forest channel

引用

International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)

作者： Jing Fan Xiuying Liu Ying Shen Tianyang Dong School of Computer Science and Technology Key Laboratory of Visual Media Intelligent Processing Technology of Zhejiang Province Zhejiang University of Technology Hangzhou China

关键词： Vegetation Green products Ontologies Cognition OWL Roads Knowledge management

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：