检索结果-内蒙古大学图书馆

Masked Generative Light Field Prompting for Pixel-Level Structure Segmentations

Research 2024年第4期2024卷 533-544页

作者： Mianzhao Wang Fan Shi Xu Cheng Shengyong Chen The Engineering Research Center of Learning-Based Intelligent System(Ministry of Education) Tianjin University of TechnologyTianjin 300384China Key Laboratory of Computer Vision and System(Ministry of Education) Tianjin University of TechnologyTianjin 300384China School of Computer Science and Engineering Tianjin University of TechnologyTianjin 300384China

Pixel-level structure segmentations have attracted considerable attention,playing a crucial role in autonomous driving within the metaverse and enhancing comprehension in light field-based machine ***,current light field modeling methods fail to integrate appearance and geometric structural information into a coherent semantic space,thereby limiting the capability of light field transmission for visual *** this paper,we propose a general light field modeling method for pixel-level structure segmentation,comprising a generative light field prompting encoder(LF-GPE)and a prompt-based masked light field pretraining(LF-PMP)*** LF-GPE,serving as a light field backbone,can extract both appearance and geometric structural cues *** aligns these features into a unified visual space,facilitating semantic ***,our LF-PMP,during the pretraining phase,integrates a mixed light field and a multi-view light field *** prioritizes considering the geometric structural properties of the light field,enabling the light field backbone to accumulate a wealth of prior *** evaluate our pretrained LF-GPE on two downstream tasks:light field salient object detection and semantic *** results demonstrate that LF-GPE can effectively learn high-quality light field features and achieve highly competitive performance in pixel-level segmentation tasks.

关键词： prompt backbone integrate

来源：评论

学校读者我要写书评

暂无评论

Network Security Situation Evaluation Based on Modified D-S Evidence Theory

引用

Wuhan University Journal of Natural Sciences 2014年第5期19卷 409-416页

作者： WANG Chundong ZHANG YuKey Laboratory of Computer Vision and System Ministry of Education/Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology

With the rapid development of global information and the increasing dependence on network for people, network security problems are becoming more and more serious. By analyzing the existing security assessment methods, we propose a network security situation evaluation system based on modified D-S evidence theory is proposed. Firstly, we give a modified D-S evidence theory to improve the reliability and rationality of the fusion result and apply the theory to correlation analysis. Secondly, the attack successful support is accurately calculated by matching internal factors with external threats. Multi-module evaluation is established to comprehensively evaluate the situation of network security. Finally we use an example of actual network datasets to validate the network security situation evaluation system. The simulation result shows that the system can not only reduce the rate of false positives and false alarms, but also effectively help analysts comprehensively to understand the situation of network security.

关键词： network security situation evaluation informationfusion D-S evidence theory Bayes network theory

来源：评论

学校读者我要写书评

暂无评论

Reasearch on comparison and analysis of the projector calibration 3

Reasearch on comparison and analysis of the projector calibr...

引用

3rd IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference, IMCEC 2019

作者： Han, Bingbing Yang, Shourui Chen, Shengyong Tianjin University of Technology Key Laboratory of Computer Vision and System Ministry of Education Tianjin China

ISBN: (纸本)9781728105130

Projectors are widely used in high-precision industrial fields, and the accuracy of projector calibration is the key to achieve system accuracy. Therefore, it is necessary to perform high-precision calibration for the projector. This paper analyzes the pinhole mathematical model and classifies the calibration method of the projector: projector calibration method based on virtual mark points and projector calibration method based on phase-shifting technique. Then the principle and methods of each calibration method are summarized, the experiment is carried out and the calibration results are compared. Finally, the advantages and disadvantages of two calibration methods are analyzed, which has the certain guiding significance in the choice of projector calibration method. © 2019 IEEE.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

A CNN-LSTM Network for Classification of Attention Deficit Hyperactivity Disorder from EEG Data 41

A CNN-LSTM Network for Classification of Attention Deficit H...

引用

第41届中国控制会议

作者： Yaru Zhang Xiangxin Tan Yue Gu Key Laboratory of Computer Vision and System (Ministry of Education) School of Computer Science and EngineeringTianjin University of Technology Engineering Research Center of Learning-Based Intelligent system Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Attention deficit hyperactivity disorder(ADHD) is one of the most common neuropsychiatric disorders in children,with core symptoms of inattention,impulsivity,and *** a result,early detection and treatment are *** this point,ADHD can be diagnosed using an electroencephalogram(EEG).This study proposes a model for identifying the EEG of children with *** proposed model is made up of three parts:temporal convolutional blocks,spatial convolutional blocks,and Long Short Term Memory(LSTM),and because EEG contains more temporal information than other data,we build a model that can extract more temporal *** study included 24 subjects,including 12 children with ADHD and12 normal *** experimental results show that our proposed model outperforms Support Vector Machine(SVM) and EEGNet,with our model achieving correct classification rates of 92.29%,92.76%,and 90.91% on the three backs,respectively,and 94.25% on the full data,demonstrating the model's feasibility and applicability to the ADHD recognition problem.

关键词： Attention Deficit Hyperactivity Disorder Electroencephalogram Deep learning Classification

来源：评论

学校读者我要写书评

暂无评论

GCA-Net: Global Cross Aware Network for salient object detection 23

GCA-Net: Global Cross Aware Network for salient object detec...

引用

8th International Conference on Multimedia and Image Processing, ICMIP 2023

作者： Zhang, Zixuan Shi, Fan Geng, Xinbo Tao, Yi He, Jing Key Laboratory of Computer Vision and System Ministry of Education School of Computer Science and Engineering Tianjin University of Technology China

ISBN: (纸本)9781450399586

In recent years, significant progress has been made in salient object detection. Nevertheless, there remains a need for further improvements in the effective combination of local and global perspectives. Combining global perception with the local focus can enhance the ability to capture the integrity of protruding objects while achieving accurate segmentation. In this paper, we introduce a newly proposed salient object detection network named GCA-Net, which is built upon three essential components. Firstly, we utilize atrous convolution to effectively aggregate contextual information and refine high-level semantic information via spatial pooling. Secondly, we employ 1-dim crossover operations to achieve global perception while minimizing computational effort. Lastly, We have innovatively integrated a contour-aware loss into our salient object detection task to constrain our model's predictions, leading to more accurate segmentation. After evaluating our model on the established salient object detection benchmark dataset, we conducted extensive experiments to demonstrate the exceptional performance of our method. As a result, our method achieved 1st in both Sm and MAE. © 2023 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An Improved Fitness Evaluation Mechanism with Memory in Spatial Prisoner's Dilemma Game on Regular Lattices

引用

Communications in Theoretical Physics 2013年第3期59卷 257-262页

作者：王娟刘丽娜董恩增王莉 Tianjin Key Laboratory for Control Theory and Complicated Industry Systems Tianjin University of Technology School of Electrical and Electronic Engineering Tianjin University of Technology Key Laboratory of Computer Vision and System(Ministry of Education) Tianjin University of Technology

To deeply understand the emergence of cooperation in natural,social and economical systems,we present an improved fitness evaluation mechanism with memory in spatial prisoner's dilemma game on regular *** our model,the individual fitness is not only determined by the payoff in the current game round,but also by the payoffs in previous round bins.A tunable parameter,termed as the memory strength(μ),which lies between 0 and 1,is introduced into the model to regulate the ratio of payoffs of current and previous game rounds in the individual fitness *** μ = 0,our model is reduced to the standard prisoner's dilemma game;while μ = 1 represents the case in which the payoff is totally determined by the initial strategies and thus it is far from the realistic *** numerical simulations indicate that the memory effect can substantially promote the evolution of *** μ < 1,the stronger the memory effect,the higher the cooperation level,but μ = 1 leads to a pathological state of cooperation,but can partially enhance the cooperation in the very large temptation *** current results are of great significance for us to account for the role of memory effect during the evolution of cooperation among selfish players.

关键词： Prisoner＇s dilemma game fitness evaluation memory effect regular lattice

来源：评论

学校读者我要写书评

暂无评论

Data Secure Transmission Model Based on Compressed Sensing and Digital Watermarking Technology

引用

Wuhan University Journal of Natural Sciences 2014年第6期19卷 505-511页

作者： WANG Chundong BAI Yi MO Xiuliang Key Laboratory of Computer Vision and System Ministry of Education/Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology

Since the Internet of Things（IoT） secret information is easy to leak in data transfer,a data secure transmission model based on compressed sensing（CS） and digital watermarking technology is proposed here. Firstly, for node coding end, the digital watermarking technology is used to embed secret information in the conventional data carrier. Secondly, these data are reused to build the target transfer data by the CS algorithm which are called observed signals. Thirdly, these signals are transmitted to the base station through the wireless channel. After obtaining these observed signals, the decoder reconstructs the data carrier containing privacy information. Finally, the privacy information is obtained by digital watermark extraction algorithm to achieve the secret transmission of signals. By adopting the watermarking and compression sensing to hide secret information in the end of node code, the algorithm complexity and energy consumption are reduced. Meanwhile, the security of secret information is *** simulation results show that the method is able to accurately reconstruct the original signal and the energy consumption of the sensor node is also reduced significantly in consideration of the packet loss.

关键词： the Internet of Things（IoT） data security com pressed sensing（CS） digital watermarking information privacy

来源：评论

学校读者我要写书评

暂无评论

The research of intrusion detection system in cloud computing environment

The research of intrusion detection system in cloud computin...

引用

作者： Wang, Huaibin Zhou, Haiyun Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin 300191 China

ISBN: (纸本)9783642259883

A variety of convenient services have been provided by cloud computing to end users. So providing safe and reliable service assurance is quiet important. Many Network-based intrusion detection systems (NIDS) are used to obtain the packets from the cloud. It has lower detection rate, higher false-positive rate and is unable to resist the single point attack of failure. In this paper, multiple intrusion detection systems (IDSs) are deployed in each layer of cloud infrastructure for protecting each Virtual Machine (VM) against threats. We also propose the cloud alliance concept by the communication agents exchanging the mutual alerts to resist the single point attack of failure. The simulation results indicate that the proposed system have a higher detection rate, lower false-positive rate and can resist the single point attack of failure. © Springer-Verlag Berlin Heidelberg 2011.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

A robust auto-focus measure based on inner energy

引用

Optoelectronics Letters 2017年第4期13卷 309-313页

作者： LI Yang TANG Ting-long HUANG Wei Key Laboratory of Computer Vision and System Ministry of Education School of Computer Science and Engineering Tianjin University of Technology Tianjin 300384 China China Three Gorges University Yichang 443002 China

This paper proposes a robust auto-focus(AF) measure based on inner energy. In general, the inner energy of noise pixels is close to zero because the magnitude of gradient and the direction of the noise pixels are random. Therefore, the inner energy can effectively eliminate the influence of noise on image quality assessment. But the gradients of near edge points are consistent with those of edge points, so the inner energy of edge pixels is relatively large, and the detail information of the image can be highlighted. Experimental results indicate that compared with traditional methods, the proposed method has higher accuracy, fewer local peaks, stronger robustness and better practicability. In particular, the evaluation results are close to the subjective evaluation of the human eyes. These results illustrate that the proposed method can be applied in automatic focusing.

关键词： Magnetic materials Optoelectronic devices

来源：评论

学校读者我要写书评

暂无评论

A pyramid image matching algorithm for chang'E-2 CCD images of the moon 4

A pyramid image matching algorithm for chang'E-2 CCD images ...

引用

4th IEEE International Conference on computer and Communications, ICCC 2018

作者： Zhou, Zhezhe Zhao, Meng Han, Ying Chen, Shengyong Key Laboratory of Computer Vision and System of Ministry of Education School of Computer Science and Engineering Tianjin University of Technology Tianjin China

ISBN: (纸本)9781538683392

The Chang'e-2(CE-2) satellite is equipped with a three-line Charge-coupled Device (CCD) stereo camera with a resolution of 7 meters. Through the camera's linear array scanning images, the stereoscopic images transmitted by CE-2 are processed. The results obtained from the processing can theoretically build a digital elevation model (DEM) with a resolution better than 10 meters. In this paper, an image matching algorithm is proposed as a code link of the built DEM, which can obtain homonymy image points with high accuracy. In view of the acquired CCD image data, the essay introduces the Wavelet Pyramid stratified matching algorithm to process the modified data. In the whole matching process, the feature points of the image are extracted with the Forstner, Moravec, and Harris operators based on gray features, which are then processed by the hierarchical matching algorithm of the wavelet pyramid. The proposed algorithm reduces the error rate of image matching and shortens the matching time and searching time of the non-homonymous image points. CCD image data simulation experiments show that the algorithm can reduce the error rate to 10.38%. © 2018 IEEE.

关键词： Charge coupled devices

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：