检索结果-内蒙古大学图书馆

IEEE International Conference on Image processing

作者： Yi Zou Xu Zhao Yuncai Liu Key Laboratory of System Control and Information Processing Department of Automation Shanghai Jiao Tong University

ISBN: (纸本)9781479983407

Coherent motion is a very common motion pattern in crowded scenes. Coherent Filter is a very effective and robust tool to detect coherent motions based on point trajectories, the performance of coherent filter depends on point trajectories' property. In this work, we present a two-stage strategy to extract dense, accurate and long-term point trajectories from crowded scenes. The method includes a tracklets acquisition procedure and a tracklets association procedure. We use LDOF tracker to acquire dense tracklets, and then formulate tracklets association as a linear assignment problem (LAP). Experiments conducted on challenging crowd datasets show that our trajectories are very suitable for detecting coherent motions in crowded scenes.

关键词： Crowded scenes Coherent motions Point tracker Tracklets association trajectory Crowding patterning of movement Association associations Filters indium

来源：评论

学校读者我要写书评

暂无评论

Latent training for convolutional neural networks

Latent training for convolutional neural networks

引用

International Conference on Estimation, Detection and information Fusion (ICEDIF)

作者： Zi Huang Qi Liu Zhiyuan Chen Yuming Zhao Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781479964192

Pedestrian detection and recognition has become the basic research in various social fields. Convolutional neural networks have excellent learning ability and can recognize various patterns with robustness to some extent distortions and transformations. Yet, they need much more intermediate hidden units and cannot learning from unlabeled samples. In this paper, we purpose a latent training model based on the convolutional neural network. The purposed model adopts part detectors to reduce the scale of the intermediate layer. It also follows a latent training method to determine the labels of unlabeled negative parts. Last, a two-stage learning scheme is purposed to overlay the size of the network step by step. Experimental results on the public static pedestrian detection dataset, INRIA Person Dataset [1], show that our model achieves 98% of the detection accuracy and 95% of the average precision.

关键词： Pattern recognition Distortion Bellows Detectors Convolution Robustness

来源：评论

学校读者我要写书评

暂无评论

ADAPTIVE APPEARANCE LEARNING FOR HUMAN POSE ESTIMATION

ADAPTIVE APPEARANCE LEARNING FOR HUMAN POSE ESTIMATION

引用

IEEE International Conference on Image processing

作者： Lei Wang Xu Zhao Yuncai Liu Key Laboratory of System Control and Information Processing Department of Automation Shanghai Jiao Tong University

ISBN: (纸本)9781479983407

We address the problem of pose estimation in videos. The part detectors play important roles, but traditional template-based detectors (e.g. Histogram of Gradient, HoG) fail at pose estimation due to the high variability in appearance. We present an adaptive representation of appearance and shape for articulated human body. The full representation of human body is based on the flexible mixture-of-parts model. We train a Naive Bayes classifier to obtain a confidence score of estimated pose by the basic mixture model, and based on the confidence we learn an instance-specific appearance model. For between-frame consistency, we design a time-efficient energy function for motion cues instead of complex motion models. We incorporate these models into a framework that allows for efficient inference. Quantitative evaluation of pose estimation conducted on two video datasets demonstrates the effectiveness of the proposed method.

关键词： Human Body pose estimation Posing Human histograms confidence Videotapes detector

来源：评论

学校读者我要写书评

暂无评论

H2 Optimal Speed Regulator for Vector controlled Induction Motor Drives

H2 Optimal Speed Regulator for Vector Controlled Induction M...

引用

第27届中国控制与决策会议

作者： Mengxiang Chen Weidong Zhang Key Laboratory of System Control and Information Processing Ministry of Education of ChinaShanghai Jiaotong University

ISBN: (纸本)9781479970186

This paper studies the application of H2 optimal control to speed regulator for vector controlled induction motor drives.A mechanical movement model derived from vector control is employed in the *** analytical optimal speed controller is obtained which has a form of PI *** based on MATLAB/Simulink is carried out to verify the control scheme,and the results show that the designed controller has good speed tracking ability for various speed commands and is robust against load torque variations.

关键词： H2 Optimal control,Induction Motor,Vector control

来源：评论

学校读者我要写书评

暂无评论

A DISCRIMINATIVE TRACKLETS REPRESENTATION FOR CROWD ANALYSIS

A DISCRIMINATIVE TRACKLETS REPRESENTATION FOR CROWD ANALYSIS

引用

IEEE International Conference on Image processing

作者： Chongjing Wang Xu Zhao Zheng Shou Yi Zhou Yuncai Liu Key Laboratory of System Control and Information Processing Department of Automation Shanghai Jiao Tong University

ISBN: (纸本)9781479983407

In this work, we propose a discriminative tracklets representation for motion pattern extraction from crowded scene. The representation incorporates relative position, velocity, and direction information of tracklet into one compact form by shaping it within a rectangle. We adopt deep belief networks to extract low-dimensional features from this representation. It not only reduces the computational complexity for the following clustering, but also achieves more discriminative tracklets representation which is invariant to noises brought by tracking failures. To determine the spatio-temporal distribution of each motion pattern, a robust clustering scheme composed of three clustering procedures is proposed. Comprehensive experiments in multiple datasets validate the effectiveness of our approach.

关键词： Deep networks Tracklets Crowd analysis patterning of movement Bayesian networks Noise complexity classes Invariant Cluster Analysis WWOX gene Rectangle

来源：评论

学校读者我要写书评

暂无评论

An improved reference point sampling method on Pareto optimal front

An improved reference point sampling method on Pareto optima...

引用

Congress on Evolutionary Computation

作者： Cheng He Linqiang Pan Hang Xu Ye Tian Xingyi Zhang Laboratory of Image Information Processing and Intelligent Control Huazhong University of Science and Technology Wuhan Hubei China Huazhong University of Science and Technology Wuhan Hubei CN Department of Computer Science Xiamen University Xiamen Fujian China Key Lab of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei Anhui China

ISBN: (纸本)9781509006243

In this paper, we propose a sampling approach of reference points used for performance metrics of multi-objective evolutionary algorithms. Traditional reference point sampling methods, such as the Das and Dennis method, usually sample the reference points via a set of uniformly distributed weight vectors generated on an ideal hyper-plane in objective space, which however often ignore the geometric shape of a specific Pareto front. Therefore, we propose a novel reference point sampling approach by taking the specific shape of the Pareto optimal front to be tackled into account for measuring the performance of multi-objective evolutionary algorithms. The performance of the proposed reference point sampling method against the other two state-of-the-art sampling methods is tested on six test instances in various conditions, which clearly demonstrate the effectiveness and superiority of the proposed sampling method.

关键词： Sampling methods Shape Convergence Evolutionary computation Optimization Euclidean distance

来源：评论

学校读者我要写书评

暂无评论

Extracting Chinese polarity shifting patterns from massive text corpora

引用

Lingua Sinica 2016年第1期2卷 1-22页

作者： Ge Xu Chu-Ren Huang Department of Computer Science Minjiang University Fuzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou China Internet Innovation Research Center of Humanities and Social Sciences Base of Colleges and Universities in Fujian Fuzhou China Department of Chinese and Bilingual Studies The Hong Kong Polytechnic University Kowloon Hong Kong

In sentiment analysis, polarity shifting means shifting the polarity of a sentiment clue that expresses emotion, evaluation, etc. Compared with other natural language processing (NLP) tasks, extracting polarity shifting patterns from corpora is a challenging one because the methods used to shift polarity are flexible, which often invalidates fully automatic approaches. In this study, which aimed to extract polarity shifting patterns that inverted, attenuated, or canceled polarity, we used a semi-automatic approach based on sequence mining. This approach greatly reduced the cost of human annotating, while covering as many frequent polarity shifting patterns as possible. We tested this approach on different domain corpora and in different settings. Three types of experiments were performed and the experimental results were analyzed, which will be reported in this paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Improved NSGA2 Algorithm with the Adaptive Differential Mutation Operator

An Improved NSGA2 Algorithm with the Adaptive Differential M...

引用

第三十四届中国控制会议

作者： WEI Jing QIAO Junfei Meng Qinchao College of Electronic Information and Control Engineering Beijing University of TechnologyBeijing Key Laboratory of Computational Intelligence and Intelligent System

ISBN: (纸本)9781467374439

This paper proposes an improved non-dominated sorting genetic algorithm(NSGA2)-DNSGA2, with the aim of preserving diversity of obtained optimal solution and avoiding the original NSGA2 algorithm falling into local optimal. The proposed DNSGA2 algorithm which introduces a differential mutation operator to replace the original polynomial mutation because the method of differential local search is helpful to the uniformity of Pareto optimal solution set. The performance of the proposed DNSGA2, NSGA2 and W-LRCD-NSGA2(Based on left-right crowding distance non-dominated sorting genetic algorithm) are compared via four benchmark functions. Simulation results indicate that the diversity and uniformity of Pareto optimal solution obtained by DNSGA2 are better than the other two algorithms.

关键词： Multi-objective,NSGA2,Differential mutation,Pareto optimal solution

来源：评论

学校读者我要写书评

暂无评论

Improved minimum entropy control for two-input and two-output networked control systems

Improved minimum entropy control for two-input and two-outpu...

引用

UKACC International Conference on control (control)

作者： Jianhua Zhang Yamin Kuai Shuqing Zhou Guolian Hou Mifeng Ren State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources Beijing China School of Control and Computer Engineering North China Electric Power University Beijing China College of Information Engineering Taiyuan University of Technology Taiyuan China

In this paper, the problem of control algorithm design for a class of nonlinear two-input and two-output (TITO) networked control systems (NCSs) with non-Gaussian random time delays is investigated, where a general non-linear auto-regressive moving average with exogenous model is used to describe the plant. Due to the non-Gaussian random time delays involved in the systems, it is insufficient to obtain a satisfactory optimal control algorithm by only controlling the expected value of the tracking errors. The Renyi entropies of the tracking errors and control inputs are adopted to characterize the randomness of the closed-loop system. The formulations of the probability density functions (PDFs) of the tracking errors and control inputs are deduced. By minimizing the new performance index, a recursive optimal control algorithm is obtained. Furthermore, the local stability condition of the closed-loop systems is established. Finally, the simulation results are presented to illustrate the effectiveness of the proposed method.

关键词： Entropy Probability density function Performance analysis Delays Delay effects Networked control systems Stochastic processes

来源：评论

学校读者我要写书评

暂无评论

Trajectory-based node selection scheme in vehicular crowdsensing

Trajectory-based node selection scheme in vehicular crowdsen...

引用

IEEE International Conference on Communications in China (ICCC)

作者： Kang Han Cailian Chen Qianli Zhao Xinping Guan Department of Automation Key Laboratory of System Control and Information Processing Shanghai P.R. China

ISBN: (纸本)9781509002443

Vehicular crowdsensing has attracted lots of attentions due to its low cost and timeliness for urban sensing applications such as traffic estimation and environment monitoring. It is of great importance for a vehicular crowdsensing system to recruit a limited number of vehicles to achieve a maximum sensing coverage. It is challenging due to the unpredictable behaviors of vehicles. In this paper, an efficient vehicle recruiting scheme is proposed by minimizing the vehicle's trajectory. To simplify the recruiting scheme design, a heuristic algorithm is firstly proposed. Then considering the dynamics of vehicles in the real world, a dynamic threshold based online algorithm is presented. We evaluate the performance of the proposed algorithms through estimating the Urban Heat Island of Shanghai, China in the real word data. The results demonstrate that the proposed algorithms outperform existing algorithms by reducing more than 50% of vehicles needed and improving the estimation accuracy.

关键词： Vehicles Heuristic algorithms Trajectory Roads Temperature sensors Algorithm design and analysis

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：