检索结果-内蒙古大学图书馆

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Peng, Juewen Pan, Zhiyu Liu, Chengxin Luo, Xianrui Sun, Huiqiang Shen, Liao Xian, Ke Cao, Zhiguo Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control China Nanyang Technological University S-Lab Singapore

ISBN: (纸本)9798350302493

Bokeh effect transformation is a novel task in computer vision and computational photography. It aims to convert bokeh effects from one camera lens to another. To this end, we introduce a new concept of blur ratio, which represents the ratio of the blur amount of a target image to that of a source image, and propose a novel framework SBTNet based on this concept. For cat-eye simulation and lens type transformation, a two-channel coordinate map and a two-channel one-hot map are added as extra inputs. The core of the framework is a sequence of parallel FeaNets, along with a feature selection and integration strategy, which aims to transform the blur amount with arbitrary blur ratio. The effectiveness of the proposed framework is demonstrated through extensive experiments, and our solution has achieved the top LPIPS metric in NTIRE 2023 Bokeh Effect Transformation Challenge. © 2023 IEEE.

关键词： Color photography

来源：评论

学校读者我要写书评

暂无评论

An adaptive nonparametric discriminant analysis method and its application to face recognition

An adaptive nonparametric discriminant analysis method and i...

引用

8th Asian Conference on Computer Vision, ACCV 2007

作者： Huang, Liang Yong, Ma. Ijiri, Yoshihisa Lao, Shihong Kawade, Masato Zhao, Yuming Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai 200240 China Sensing and Control Technology Lab. Omron Corporation Kyoto 619-0283 Japan

ISBN: (纸本)9783540763895

Linear Discriminant Analysis (LDA) is frequently used for dimension reduction and has been successfully utilized in many applications, especially face recognition. In classical LDA, however, the definition of the between-class scatter matrix can cause large overlaps between neighboring classes, because LDA assumes that all classes obey a Gaussian distribution with the same covariance. We therefore, propose an adaptive nonparametric discriminant analysis (ANDA) algorithm that maximizes the distance between neighboring samples belonging to different classes, thus improving the discriminating power of the samples near the classification borders. To evaluate its performance thoroughly, we have compared our ANDA algorithm with traditional PCA+LDA, Orthogonal LDA (OLDA) and nonparametric discriminant analysis (NDA) on the FERET and ORL face databases. Experimental results show that the proposed algorithm outperforms the others. © Springer-Verlag Berlin Heidelberg 2007.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Hierarchical Optimizing Energy Management Strategy for Alleviating Degradation in Fuel Cell Hybrid System

引用

IEEE ACCESS 2024年 12卷 57117-57127页

作者： Fu, Jun Xiang, Qian Zeng, Linghong Zu, Yanmin You, Hang Shan, Xinkai Xin, Jie Li, Xi Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Processing & Intelligent Control Minist Educ Wuhan 430074 Peoples R China State Grid Corp China Beijing 102200 Peoples R China Hangzhou ArcSoft Software Co Ltd Hangzhou 310051 Peoples R China

This study designs an energy management strategy for fuel cell hybrid vehicles aimed to alleviating the performance degradation of Proton Exchange Membrane Fuel Cells (PEMFC), fuel consumption, and battery State of Charge (SOC) fluctuations during vehicle operation. The research focuses on the decrease in Electrochemical Surface Area (ECSA) due to Platinum (Pt) catalyst degradation, which is a key factor influencing PEMFC durability. An ECSA model based on the Pt dissolution mechanism is established, and a dynamic condition accelerated stress test (DC-AST) is designed to specifically investigate the impacts of key parameters, such as cycle period, amplitude, and duty cycle on the degradation of ECSA. This reveals the association between ECSA degradation and irregular potential fluctuations. A hierarchical power allocation strategy is then proposed, combining the global search capabilities of optimization algorithms with heuristic strategies in light of these features. The upper level employs Pontryagin's Minimum Principle (PMP) strategy for global power allocation optimization, while the lower level uses a satisfaction-based heuristic strategy that is tailored to the ECSA degradation characteristics, to dynamically adjust power output. Simulation results demonstrate that, compared to traditional rule-based strategies and classical PMP-based strategies, the proposed energy management strategy more effectively mitigates ECSA degradation of PEMFC under typical vehicle conditions.

关键词： Degradation Fuel cells Platinum Batteries Electric potential State of charge Resource management Hybrid power systems Energy management PEMFC hybrid power degradation ECSA energy management

来源：评论

学校读者我要写书评

暂无评论

A probability-based object tracking method

A probability-based object tracking method

引用

4th International Conference on intelligence Science and Big Data Engineering, IScIDE 2013

作者： Song, Xu Li, Guoqiang Li, Ying Zhang, Yanning Shaanxi Province Key Lab. of Speech and Image Information Processing Northwestern Polytechnical University Xi'an 710129 China Science and Technology on Electro-optic Control Laboratory Louyang 471009 China

ISBN: (纸本)9783642420566

Here we take advantage of the signal recovery power of Compressive Sensing (CS) to significantly reduce the computational complexity brought by the high-dimension image data, then an effective and efficient low-dimensional subspace representation of the object is computing by applying Principal Component Analysis (PCA) to a collection of object observations which are low-dimensional vectors derived from CS. An incremental PCA algorithm is used to update this subspace model for characterizing the object appearance changes. Meanwhile, two distances derived from Probabilistic Principal Component Analysis (PPCA): distance from feature space (DFFS) and distance in feature space (DIFS), are used to describe visual similarity between the learned subspace representation model and candidate targets. Comparing with the traditional used reconstruction error, the sum of two distances: DFFS + DIFS, is more accurate and more robust to noises and partial occlusions. Numerous experiment demonstrate that subspace representation model can handle the situation that target objects experience pose changes, scale changes, significant illumination variation, partial occlusions and so on. © 2013 Springer-Verlag Berlin Heidelberg.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Data model driven architecture (DMDA)

Data model driven architecture (DMDA)

引用

4th International Workshop on Advanced Computational intelligence, IWACI 2011

作者： Chen, Chen Chen, Xueguang Liu, Hong Institute of Systems Engineering Huazhong University of Science and Technology Wuhan 430074 China Key Lab. for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9781612843735

Based on the current development of Model Driven Architecture (MDA) in Enterprise Information System (EIS), the paper proposes a DMDA, a new development architecture to improve EIS development speed and quality. The basic idea of the DMDA is to take advantage of formal description, decomposition and re-use on EIS development process to let computer understand development demands of developers and then consequently generate some business models having nothing to do with specific technical realization, combine with specific technical basic platform to finally generate the EIS meeting actual demands based on data model. The practice proves the architecture is capable of simplifying EIS development difficulty, expediting application and development speed, improve development quality and achieve the rapid development purpose. © 2011 IEEE.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Interdependency analysis of infrastructures

引用

6th International Symposium on Neural Networks, ISNN 2009

作者： Mao, Zijun Hong, Liu Fei, Qi Ouyang, Ming Institute of System Engineering Huazhong University of Science and Technology Wuhan 430074 China Key Lab. for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)3642015123

Electric power, potable water, telecommunications, natural gas, and transportation are examples of critical infrastructures, the intrinsic feature of which are suitable for network analysis. This paper proposes a method framework based on the complex network to explore the interdependency of these infrastructures. We describe the topological characterization of two interdependent small-sized real networks, based on which the interdependent model is devised. We define the interdependent factor to characterize the direct interdependency of two infrastructures, and also its fluctuation in the situations of random removal and targeted removal on the electric and water infrastructures is studied. Furthermore we propose a matrix M to reflect all direct and indirect interactions among infrastructures, which also makes contributions to the understanding of infrastructures catastrophes. © 2009 Springer Berlin Heidelberg.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

A video tracking system for limb motion measurement in small animals

A video tracking system for limb motion measurement in small...

引用

2010 International Conference on Optoelectronics and image processing, ICOIP 2010

作者： Xu, Qi Cai, Cong Zhou, Houlun Ren, Hangkong KEY Lab. of Image Processing and Intelligent Control Department of Control Science and Engineering Huazhong University of Science and Technology Wuhan China Department of Anatomy Tongji Medical College Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9780769542522

Motion analysis can provide useful information for biomedical researches. In this paper, we have presented a video tracking system for limb motion measurement in small animals. The system employs a consumer-grade video camera to record the locomotion of a rat, which can reduce the cost of the system. Three matching methods are availab.e for different application. Moreover, a new algorithm to forecast the joint positions based on the polynomial fitting and improved Kalman filtering algorithms has been proposed, not only for limiting the region of matching, but also for marker occlusion and various maneuverability of the limb. Two methods are also applied to detect mismatch for ensuring a reliable tracking. Once 2D markers positions are collected, kinematic characteristics of the motion can be derived. Finally, the experimental results of the tracking system are presented. © 2010 IEEE.

关键词： Motion analysis

来源：评论

学校读者我要写书评

暂无评论

A new roadmap constitution method based on dividing grid and level-set

A new roadmap constitution method based on dividing grid and...

引用

International Symposium on intelligence Information processing and Trusted Computing

作者： Li, Shidong Ding, Mingyue Cai, Chao Institute for Information Engineering of Hubei University for Nationalities Enshi Hubei China Institute for Pattern Recognition and Artificial Intelligence National Lab. for Multi-spectral Information Processing Technologies HUST Wuhan China College of Life Science and Technology Image Processing and Intelligent Control Key Laboratory of Education Ministry of China HUST Wuhan China

ISBN: (纸本)9780769541969

Roadmap methods were widely used in route planning fields, both for robots and unmanned aircrafts. Traditional roadmap is constituted by connecting the vertexes of convex obstacle, which is related to the locations of start and goal of route, so the roadmap can not be reused when anyone of start and goal changed. Absence of reusability reduces the efficiency of route planning by using roadmap. A new roadmap constitution method was proposed in this paper, which is build on dividing the 2D configuration space into multi-scale grids and setting nodes of roadmap on grid boundary using Level-Set method, same method was used to construct the map cells of roadmap between any two nodes lays on same grid . The roadmap constituted with new method can be reused when the start or goal was changed;it is efficient for replanning problem. © 2010 IEEE.

关键词： Reusability

来源：评论

学校读者我要写书评

暂无评论

Epidemic spreading with variant infection rates on scale-free network

引用

6th International Symposium on Neural Networks, ISNN 2009

作者： Hong, Liu Ouyang, Min Mao, Zijun Chen, Xueguang Institute of System Engineering Huazhong University of Science and Technology Wuhan 430074 China Key Lab. for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)3642015123

In this paper, we proposed a susceptible-infected model with variant infection rates because different individuals have different resistance to diseases in different periods of real epidemic events. We consider two cases: Case 1, we know every individual's infection rate to a kind of epidemic, satisfy a type of distribution. Case 2, assume all individuals have same initial infection rates, a susceptible individual's infection rate will be less than the initial rate if he is not infected after limited number of contacts with infected ones. For both two cases, at the time tD, preventive and control measures bring into effects, every individual's infection rate would decrease. We implemented this models on scale-free networks, and found that the epidemic process before the time tD in Case 1 is almost the same as that in Standard SI model if the infection rate in Standard SI model equals the mean infection rate in Case 1. Furthermore, using numerical simulation, we analysis the effects of the parameter tD, and find the bimodal distribution of final infection rates. Finally, we conclude what we get in this paper and give our future direction. © 2009 Springer Berlin Heidelberg.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Skeleton-based fast path planning for UAV

Skeleton-based fast path planning for UAV

引用

MIPPR 2009 - Remote Sensing and GIS Data processing and Other Applications: 6th International Symposium on Multispectral image processing and Pattern Recognition

作者： Liu, Xin Zhou, Chengping Ding, Mingyue Cai, Chao Institute for Pattern Recognition and Artificial Intelligence National Lab. for Multi-spectral Information Processing Technologies Huazhong University of Science and Technology Wuhan 430074 China College of Life Science and Technology Image Processing and Intelligent Control Key Laboratory of Education Ministry of China Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9780819478092

A new path planning method for UAV in static workspace is presented. The method can find a nearly optimal path in short time which satisfies the UAV kinematic constraints. The method makes use of the skeletons to construct the graph of the planning space considering the configuration of the obstacles and utilizes the graph to find a shortest collision-free path, and a novel technique is utilized to convert the free path into a feasible path. The method can be applied to different applications and easy to be implemented. Experimental results showed that the path planning can be done in a fraction of second on a contemporary workstation (2-3 seconds) under the condition of satisfying the kinematic constraints. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： Motion planning

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：