检索结果-内蒙古大学图书馆

Point cloud coarse registration based on 3DSIFT keypoint detection

Journal of Computational Information systems 2014年第23期10卷 10121-10128页

作者： Gu, Xiaoying Liu, Yongshan Department of Information Science and Engineering Yanshan University Qinhuangdao China The Key Laboratory for Computer Virtual Technology and System Integration of HeBei Province Yanshan University Qinhuangdao China Data Industry Research Lab Qinhuangdao China

Since the SIFT feature point extraction algorithm with scale changes, rotation transformation invariance, is widely used in image registration. In this paper, the SIFT algorithm is applied to three-dimensional point cloud coarse registration, the proposed 3DSIFT extraction algorithm is suitable for three-dimensional point cloud data, then point coordinates, curvature, the nearest neighbor distance mean and other information compose fourteen-dimensional vector to conduct correspondence match, use the interior point rate of Ransac to obtain optimal transformation, and finally transform the coordinates for source point clouds using the optimal transform, complete the point cloud data coarse registration. Experimental results show that our coarse registration algorithm can effectively extract feature points, and it is robust for the point cloud with noisy point, it can provide accurate and effective initial value for the precise registration such as ICP.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Research on a denoising smoothing algorithm for 3D scattered point cloud

引用

ICIC Express Letters 2014年第9期8卷 2403-2409页

作者： Gu, Xiaoying Liu, Yongshan Wu, Qiong Department of Information Science and Engineering China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University No. 438 Hebei Ave. Qinhuangdao 066004 China Data Industry Research Lab Qinhuangdao 066004 China

In order to effectively eliminate outliers and noise points in 3D scattered point cloud, a denoising smoothing algorithm which is the combination of removing outliers algorithm and trilateral filter is proposed. This is accomplished by rejecting outliers, correcting the normal direction and moving noise points along the modified normal direction within local adaptive neighborhoods. First, the outliers are removed by the method of mathematical statistics, on this basis, estimating normal direction and curvature of point cloud by covariance analysis method. Then, correct the normal direction by combining trilateral filter weighting factor with adaptive optimal neighborhood function. Finally, calculate position offset of data points in the direction of normal amendment by trilateral filter weighting factor in order to smooth the point cloud. Experimental results show that the proposed method is simple and effective, successfully removing noise from point cloud while preserving inherent geometric features. © 2014 ISSN 1881-803X.

关键词： Bandpass filters

来源：评论

学校读者我要写书评

暂无评论

Reinforced Heterogeneous Graphlet Design for Knowledge Graph Representation Learning

SSRN

引用

SSRN 2023年

作者： Gong, Jibing Lin, Yuting Zhao, Yi Lin, Tianyu Fang, Xiaohan Feng, Xinchao Peng, Jiquan School of Information Science and Engineering Yanshan University Qinhuangdao066004 China The Key Laboratory for Computer Virtual Technology System Integration of Hebei Province Yanshan University Qinhuangdao066004 China

Knowledge Graphs have been practical tools to represent and integrate plentiful structural and semantic information in mainstream industrial scenarios. While promising, the heterogeneity and complexity of KGs pose a formidable obstacle, especially for graph representation learning. Most existing KG embedding models omit the dynamic high-order connectivity patterns, and heavily rely on the handcrafted patterns to handle the complex semantic relationships, thereby limiting their ability to adaptively capture nuanced and intricate relationships of knowledge graphs in different tasks. To fill this gap, we present ReHGD — a model designed for KGs that focuses on adaptively designing typed graphlets through a cooperative Multi-agent Reinforcement Learning algorithm. This approach can learn more discriminative graph representations tailored to specific downstream tasks. Specifically, ReHGD engages in the creation of typed graphlets through a two-stage process: it (1) establishes a reinforced chain design module to generate chains without predefined rules, and (2) employs a buffer-aware sampling technique to derive episodic chains from prior experiences. Subsequently, motifs are deduced by applying commute count and Hadamard product operations to the episodic chain-based subgraphs. Finally, ReHGD utilize chain and motif aggregations to learn graph representations. Experimental results on three real-world KGs show that ReHGD outperforms baselines on entity classification. © 2023, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

SYVR virtual Equipment Manufacturing Simulation

SYVR Virtual Equipment Manufacturing Simulation

引用

International Conference on virtual Reality and Visualization (ICVRV)

作者： Yuhan Liu Yong Tang Qian Sun Shiny VR Yanshan University College of Information Science and Engineering Qinhuangdao China Yanshan University The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao China

ISBN: (纸本)9781538684986;9781538684979

SYVR is a real-time simulation graphic engine focusing on equipment manufacturing. It is based on decades of research works of physics simulations, is able to provide services like real-time simulation for key parts of devices, large-scale com-plicated situation simulation, virtual experiment, operational training, visualization of concept design and etc., which con-sist of the whole process of virtual manufacturing and simulation. SYVR can provide comprehensive technology support for industrial 3-dimensional data, accelerate applications of VR to all aspects of industry, cut down development costs of equipment manufacturing significantly, highly increase effi-ciency of equipment design, and promote development of equipment manufacturing.

关键词： Conferences virtual reality Visualization

来源：评论

学校读者我要写书评

暂无评论

Occlusion avoidance approach based on depth image of visual object

引用

ICIC Express Letters, Part B: Applications 2015年第11期6卷 3103-3108页

作者： Zhang, Shihui Sang, Yu Zhang, Xiaojun School of Information Science and Engineering Yanshan University No. 438 Hebei Avenue Qinhuangdao China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province No. 438 Hebei Avenue Qinhuangdao China E and A College Hebei Normal University of Science and Technology No. 360 West Hebei Street Qinhuangdao China

Occlusion avoidance is a more challenging problem in visual field. An occlusion avoidance approach based on depth image of visual object is proposed in this paper. Firstly, the occlusion detection is implemented for the depth image of visual object in current view, and then the occlusion boundary and nether adjacent boundary are obtained to construct occlusion region. Secondly, the occlusion region is segmented into several sub-regions by connecting the corner of occlusion boundary with its nether adjacent boundary point, and the triangular mesh model of each sub-region is established. Thirdly, the candidate observation direction set is determined by utilizing the normal vector of each triangle in triangular mesh model. Finally, the next best view is confirmed based on the candidate observation direction set to realize the occlusion avoidance function. Compared with the existing methods, the proposed approach does not need the priori knowledge of visual object or limit the camera position on a fixed surface. Experimental results demonstrate its feasibility and effectiveness. © 2015 ICIC International.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Real-time simulation of large-scale water environments with interacting objects

引用

Journal of Computational Information systems 2015年第9期11卷 3257-3264页

作者： Li, Ying Peng, Jingxuan Fan, Fuding Lv, Mengya Zhang, Lihui Zhao, Jing Tang, Yong The College of Information Science and Engineering Yanshan University Qinhuangdao China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao China Department of Information Engineering Environmental Management College of China Qinhuangdao China

We present a new GPU scheme for real-time simulation in large-scale water environments with physics-based object interaction. To improve the simulation efficiency, we divide surface waves into ambient waves and interactive waves. A fast and stable Verlet integration method is applied to solve the wave equation to simulate the propagation of interactive waves. To solve the problem that the interactive area caused by the moving object is uncertain, we propose a moving grid suited to LOD (Levels of Detail) surface with multiple resolutions, which reduces the computation cost. The extension of multiple moving grids makes the interaction of water and various objects possible. We propose a volume conservation based method to generate interactive waves and apply rigid body dynamics to demonstrate the effect of water reaction against the object. Experimental results show that our approach achieves higher visual realism and performance. ©, 2015, Binary Information Press. All right reserved.

关键词： Wave equations

来源：评论

学校读者我要写书评

暂无评论

Real-time simulation of foam and sprays based on the Weber number

引用

Journal of Computational Information systems 2014年第7期10卷 2829-2836页

作者： Zhang, Lihui Zhang, Chao Li, Ying Lv, Mengya Tang, Yong The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province The College of Information Science and Engineering Yanshan University Qinhuangdao 066004 China Department of Information Engineering Environmental Management College of China Qinhuangdao 066004 China

In this paper, we propose a method based on the Weber number to uniformly model and simulate the foam and sprays generated by the fluid motion. We use the SPH to construct the fluid and calculate the Weber number of each particle. The fluid particles are divided into foam particles, transition particles and water particles by comparing their Weber number with a given critical value. These particles are rendered independently. For the solid-liquid interaction in fluid, we use SPH particles to mark the solid shape, and correct the changed solid particle position using a rotating equation. Finally, a more precise fluid surface illumination model is proposed, and the Fresnel reflection coefficient of this model can be gotten by the Snell law. Experiment results show that our method achieve real-time performance and the visual effect is desirable. © 2014 Binary Information Press.

关键词： Hydrodynamics

来源：评论

学校读者我要写书评

暂无评论

Frequent closed itemsets mining using ITBitree

引用

International Journal of Advancements in Computing technology 2012年第17期4卷 271-279页

作者： Ren, Jiadong Song, Wei Yu, Shiying College of Information Science and Engineering Yanshan University Qinhuangdao Hebei 066004 China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao City 066004 China Hebei Provincial S and T Management Information Center 159 Dongfeng Road Shijiazhuang Hebei 050021 China

The set of frequent closed itemsets is much smaller than the one of all frequent itemsets. Meanwhile it retains the completeness. In this paper, we propose an ITBitree-based algorithm, called ITBitreeFCIM (ITBitree Frequent Closed Itemsets Miner), for mining the frequent closed itemsets directly. A novel structure termed ITBitree (Itemset Tidset Binary Tree) is defined to store the transaction and itemset information. Frequent closed itemsets are generated directly by searching the right nodes in each layer and the right nodes in their respective search space deeply from this tree using top-down strategy. For the items with same support in the adjacent layers or the items with the same Tids, we use item merging technique to prune the search space. The searched space is used to avoid the generation of duplicates and enormous closure checks. In the process we do not need to check whether a candidate itemset is closed, so we save a lot of time. The experiment proofs the efficiency of the proposed approach.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Improved BP classifier via distance for sample reduction

引用

Journal of computers (Taiwan) 2019年第2期30卷 1-13页

作者： Wen, Jia Deng, Jia Liu, Peng-Fei Wang, Hong-Jun Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University Qinhuangdao China School of Information Science and Engineering Yanshan University Qinhuangdao China State Key Laboratory of Software Engineering of Hebei Province Yanshan University Qinhuangdao China

The BP neural network algorithm is a commonly used technique in the classification field of pattern recognition, which iterates training samples continuously to obtain the decision boundary, until the error reaches the convergence precision. However, due to the extensive redundancy of training samples, this carpet-like training method can easily lead to slow network convergence and low classification performance. In this paper, from the view of sample, a novel BP training method called improved BP Classifier algorithm using Distance for Sample Reduction (DRBP) is proposed. Through the sample weight to get the new training sample, which are the near of the classification interface like support vector, and then iterative training BP classifier to solve the classification issue. The main function of this method is to keep the original sample information, realize the sample reduction, and improve the generalization ability of the BP neural network. First, point sets is used to visualize the training process. And then use 10 sets of the University of California Irvine (UCI) to verify the effectiveness and superiority of our experiments. Finally through Cross-validation, the classification error rate of 10 sets of UCI datasets tested by DRBP training method is lower than that of standard BP neural network (STBP). So the result of the experiment showed that the method of the combined distance sample reduce with BP network can significantly enhance the generalization ability of BP network. © 2019 computer Society of the Republic of China. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

VT-SGN:Spiking Graph Neural Network for Neuromorphic Visual-Tactile Fusion

引用

IEEE Transactions on Haptics 2024年 PP卷 PP-PP页

作者： Wu, Peiliang Zhang, Haozhe Li, Yao Chen, Wenbai Gao, Guowei Yanshan University School of Information Science and Engineering Qinhuangdao066004 China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao066004 China Beijing Information Science and Technology University School of Automation Beijing100192 China

Current issues with neuromorphic visual-tactile perception include limited training network representation and inadequate cross-modal fusion. To address these two issues, we proposed a dual network called visual-tactile spiking graph neural network (VT-SGN) that combines graph neural networks and spiking neural networks to jointly utilize the neuromorphic visual and tactile source data. First, the neuromorphic visual-tactile data were expanded spatiotemporally to create a taxel-based tactile graph in the spatial domain, enabling the complete exploitation of the irregular spatial structure properties of tactile information. Subsequently, a method for converting images into graph structures was proposed, allowing the vision to be trained alongside graph neural networks and extracting graph-level features from the vision for fusion with tactile data. Finally, the data were expanded into the time domain using a spiking neural network to train the model and propagate it backwards. This framework effectively utilizes the structural differences between sample instances in the spatial dimension to improve the representational power of spiking neurons, while preserving the biodynamic mechanism of the spiking neural network. Additionally, it effectively solves the morphological variance between the two perceptions and further uses complementary data between visual and tactile. To demonstrate that our approach can improve the learning of neuromorphic perceptual information, we conducted comprehensive comparative experiments on three datasets to validate the benefits of the proposed VT-SGN framework by comparing it with state-of-the-art studies. © 2008-2011 IEEE.

关键词： Graph 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：