检索结果-内蒙古大学图书馆

3rd IAPR Asian Conference on pattern recognition, ACPR 2015

作者： Du, Yong Fu, Yun Wang, Liang Center for Research on Intelligent Perception and Computing CRIPAC China Center for Excellence in Brain Science and Intelligence Technology CEBSIT China Nat'l Lab of Pattern Recognition Institute of Automation Chinese Academy of Sciences China College of Engineering College of Computer and Information Science Northeastern University United States

ISBN: (纸本)9781479961009

Temporal dynamics of postures over time is crucial for sequence-based action recognition. Human actions can be represented by the corresponding motions of articulated skeleton. Most of the existing approaches for skeleton based action recognition model the spatial-temporal evolution of actions based on hand-crafted features. As a kind of hierarchically adaptive filter banks, Convolutional Neural Network (CNN) performs well in representation learning. In this paper, we propose an end-to-end hierarchical architecture for skeleton based action recognition with CNN. Firstly, we represent a skeleton sequence as a matrix by concatenating the joint coordinates in each instant and arranging those vector representations in a chronological order. Then the matrix is quantified into an image and normalized to handle the variable-length problem. The final image is fed into a CNN model for feature extraction and recognition. For the specific structure of such images, the simple max-pooling plays an important role on spatial feature selection as well as temporal frequency adjustment, which can obtain more discriminative joint information for different actions and meanwhile address the variable-frequency problem. Experimental results demonstrate that our method achieves the state-of-art performance with high computational efficiency, especially surpassing the existing result by more than 15 percentage on the challenging ChaLearn gesture recognition dataset. © 2015 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Theory of ϕ-Jensen variance and its applications in higher education

引用

Journal of Inequalities and Applications 2015年第1期2015卷 1-40页

作者： Wen, JiaJin Huang, Yi Cheng, Sui Sun Institute of Mathematical Inequalities and Applications College of Mathematics and Computer Science Chengdu University Chengdu 610106 China Key Laboratory of Pattern Recognition and Intelligent Information Processing of Higher Education Institutions of Sichuan Province College of Mathematics and Computer Science Chengdu University Chengdu 610106 China Department of Mathematics Tsing Hua University Hsinchu 30043 Taiwan

This paper introduces the theory of ϕ-Jensen variance. Our main motivation is to extend the connotation of the analysis of variance and facilitate its applications in probability, statistics and higher education. To this end, we first introduce the relevant concepts and properties of the interval function. Next, we study several characteristics of the log-concave function and prove an interesting quasi-log concavity conjecture. Next, we introduce the theory of ϕ-Jensen variance and study the monotonicity of the interval function JVar_ϕ φ(X_[a,b]) by means of the log concavity. Finally, we demonstrate the applications of our results in higher education, show that the hierarchical teaching model is ‘normally’ better than the traditional teaching model under the appropriate hypotheses, and study the monotonicity of the interval function Var A (X_[a,b]). © 2015, Wen et al.

关键词： hierarchical teaching model interval function k-normal distribution truncated random variable ϕ-Jensen variance

来源：评论

学校读者我要写书评

暂无评论

Iterative data adaptive anisotropic image filtering

Iterative data adaptive anisotropic image filtering

引用

2012 International Conference on Machine Learning and Cybernetics, ICMLC 2012

作者： Yang, Chang-Cai Zheng, Xin-Yi Tian, Jin-Wen Shang, Ke Tian, Xin Hao, Wei Institute for Pattern Recognition and Artificial Intelligence Science and Technology on Multi-Spectral Information Processing Laboratory Huazhong University of Science and Technology Wuhan 430074 China Electrical Engineering and Renewable Energy School China Three Gorges University Yichang 443002 China Institute of Intelligent Vision and Image Information College of Computer and Information Technology China Three Gorges University Yichang 443002 China

ISBN: (纸本)9781467314855

This paper presents a novel data-adaptive anisotropic filtering technique built on top of an iterative scheme. This new technique can preserve the original significant structures while suppressing noises to the largest extent. To achieve this goal, dominant orientation information of all gradients is used to control the local kernel adaptively. This results in elongated and elliptical contours spread along the directions of the local edge structure. With these locally adapted kernels, the smoothing is mostly effective along the edges, rather than across them. Therefore details in the original input can be preserved. The performance of the proposed data-adaptive anisotropic filter together with its iterative scheme are compared with the conventional Gaussian filter, anisotropic diffusion filter, the structure-adaptive anisotropic filter, and the iterative kernel regression scheme. The experimental results on both simulated Gaussian and Poission noisy images indicate that the proposed method performs the best, and the iterative scheme can significantly improve the performance of the noise suppressing while delivering high computation efficiency. © 2012 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Camera Abnormal Movement and Foreign Object Invasion Detection Based on Cumulative Edge Distribution Probability Model

Camera Abnormal Movement and Foreign Object Invasion Detecti...

引用

2018 International Conference on Security, pattern Analysis, and Cybernetics, SPAC 2018

作者： Yu, Xiangru Cai, Fudong Dou, Yimin Li, Jinping Institute of Pattern Recognition and Intelligent System School of Information Science and Engineering University of Jinan Jinan China Shandong Provincial Key Laboratory of Network Based Intelligent Computing Jinan China Shandong College University Key Laboratory of Information Processing and Cognitive Computing in 13th Five-year University of Jinan Jinan China Shandong Senter Electronic Co. Ltd Zibo China

ISBN: (纸本)9781728105512

In practice, there often exist some occasions where video surveillance can only be realized by using rechargeable batteries due to the high cost of power supply. In order to extend the battery life, images can only be taken at a certain interval. Obviously, image difference is an important method to obtain various changes in this case. Among these changes, foreign invasion is one of the focuses. However, due to bolt shedding, abnormal weather and other factors, the camera may have abnormal movement which may seriously affect the detection effect of image difference method. Therefore, it is an urgent issue to find an effective way to detect the abnormal movement of camera and improve the detection accuracy of foreign invasion. Considering the characteristics of this kind of image sequences, we propose an effective algorithm to detect the camera abnormal movement and foreign object invasion based on a cumulative edge distribution probability model. Since sky region is relatively simple, we only discuss changes in sky region to detect camera abnormal movement. Our algorithm has 6 basic steps: firstly, segment the sky region;secondly, extract the edge information of the current image and the preceding adjacent image in the image sequence;thirdly, determine if the edge information of two adjacent images coincide. If consistent, then go to the next step, otherwise, it indicates that the camera has abnormal movement, then alarm;fourthly, calculate the cumulative edge probability distribution model in the sky region by using the historical image sequence;fifthly, by using adaptive Parzen window, determine if foreign object invasion exists by comparing the probability model of cumulative edge distribution with edge distribution of the current image;sixthly, update the cumulative edge distribution probability model in sky region. The algorithm achieves good results in practical applications. Through the test of thousands of images taken in the wild, the detection accuracy of

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

An Improved algorithm of priority scheduling for μc/OS-II

Boletin Tecnico/Technical Bulletin

引用

Boletin Tecnico/Technical Bulletin 2017年第2期55卷 73-78页

作者： Zhang, Chunhong Ren, Jianqiang College of Mathematics and Information Langfang Teachers University Langfang Hebei065000 China Institute of Pattern Recognition and Intelligent System Langfang Teachers University Langfang Hebei065000 China

In the classical priority bitmap scheduling algorithm, lookup table method will lead to the problem that the memory space is too large due to the increase of the number of tasks. In this regard, this paper proposes a low complexity priority scheduling algorithm based on the mathematical model mapping, which can efficiently calculate the bit number of the highest priority task in the ready task, and then determine the highest priority task. Compared with the classical algorithm, this algorithm can effectively avoid the serious time and space cost caused by the mapping table. Under the premise of ensuring the scheduling performance and real-time scheduling, the maximum number of tasks supported is extended from 64 to more than 256 or more. The improved algorithm breaks through the limitation of μC/OS-II on the number of tasks, and effectively extends the application of the system kernel in more complex real-time systems.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Improved robust watermarking based on rational dither modulation

Communications in Computer and Information Science

引用

Communications in Computer and information Science 2014年 437卷 305-314页

作者： Wang, Zairan Dong, Jing Wang, Wei Tan, Tieniu Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China College of Engineering and Information Technology University of Chinese Academy of Sciences China

ISBN: (纸本)9783662454978

Rational dither modulation (RDM) watermarking was presented to resist amplitude scaling attack. This property is achieved by quantizing the ratio of consecutive samples instead of samples themselves. In this paper, we improve the performance of basic RDM watermarking to resist more types of watermarking attacks. We improve the robustness of our modified RDM watermarking by the following three aspects: 1) The quantization step size is increased by modifying two coefficients instead of only one coefficient in the basic RDM method, 2) Several modification rules are defined to reduce embedding distortion, and 3) The coefficients with larger magnitudes in the lowest sub-band in DWT domain are selected to embed watermark. A variety of attacks are implemented to evaluate the performance of our method. Experimental results demonstrate that our method outperforms the basic RDM method and two state-of-the-art watermarking methods over a wide range of attacks and it also has good imperceptibility. © Springer-Verlag Berlin Heidelberg 2014.

关键词： Modulation

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

SSERBC 2017: Sclera segmentation and eye recognition benchmarking competition

SSERBC 2017: Sclera segmentation and eye recognition benchma...

引用

2017 IEEE International Joint Conference on Biometrics, IJCB 2017

作者： Das, Abhijit Pal, Umapada Ferrer, Miguel A. Blumenstein, Michael Štepec, Dejan Rot, Peter Emeršič, Žiga Peer, Peter Štruc, Vitomir Kumar, S.V. Aruna Harish, B.S. Institute for Integrated and Intelligent Systems Griffith University QLD Australia Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India IDeTIC University of Las Palmas de Gran Canaria Las Palmas Spain School of Software University of Technology Sydney Australia Faculty of Computer and Information Science University of Ljubljana Ljubljana Slovenia Department of Information Science and Engineering Sri Jayachamrajendra College of Engineering Mysusru Karnataka India

ISBN: (纸本)9781538611241

This paper summarises the results of the Sclera Segmentation and Eye recognition Benchmarking Competition (SSERBC 2017). It was organised in the context of the International Joint Conference on Biometrics (IJCB 2017). The aim of this competition was to record the recent developments in sclera segmentation and eye recognition in the visible spectrum (using iris, sclera and peri-ocular, and their fusion), and also to gain the attention of researchers on this subject. In this regard, we have used the Multi-Angle Sclera Dataset (MASD version 1). It is comprised of2624 images taken from both the eyes of 82 identities. Therefore, it consists of images of 164 (82×2) eyes. A manual segmentation mask of these images was created to baseline both tasks. Precision and recall based statistical measures were employed to evaluate the effectiveness of the segmentation and the ranks of the segmentation task. recognition accuracy measure has been employed to measure the recognition task. Manually segmented sclera, iris and peri-ocular regions were used in the recognition task. Sixteen teams registered for the competition, and among them, six teams submitted their algorithms or systems for the segmentation task and two of them submitted their recognition algorithm or systems. The results produced by these algorithms or systems reflect current developments in the literature of sclera segmentation and eye recognition, employing cutting edge techniques. The MASD version 1 dataset with some of the ground truth will be freely available for research purposes. The success of the competition also demonstrates the recent interests of researchers from academia as well as industry on this subject. © 2017 IEEE.

关键词： Competition

来源：评论

学校读者我要写书评

暂无评论

Learning human actions with an adaptive codebook

Learning human actions with an adaptive codebook

引用

International Conference on Virtual Systems and MultiMedia

作者： Yu Kong Xiaoqin Zhang Weiming Hu Yunde Jia Beijing Laboratory of Intelligent Information Technology School of Computer Science Beijing Institute of Technology Beijing China College of Mathematics & Information Science Wenzhou University Zhejiang China National Laboratory of Pattern Recognition China

Learning a compact and yet discriminative codebook for classifying human actions is a challenging problem. One difficulty lies in that the learning procedure is split into two independent phases (dimension reduction and clustering) and thus results in the loss of discriminative information which clustering requires. Besides, traditional used principal component analysis is not optimized for class separability and may not help to improve data separation. In this paper, we propose a novel optimization framework which unifies dimension reduction and clustering. In contrast to previous methods, our method enables to dynamically select indispensable and crucial dimensions for building a discriminative codebook. We add metric learning before clustering to provide the clustering method with an optimized distance metric. Experimental results show that our approach constructs a highly discriminative codebook and achieves comparable results to other state-of-the-art approaches.

关键词： Humans Principal component analysis Measurement Accuracy Optimization Covariance matrix Kernel

来源：评论

学校读者我要写书评

暂无评论

Dynamic round robin scheduling algorithm for μc/OS-III

Boletin Tecnico/Technical Bulletin

引用

Boletin Tecnico/Technical Bulletin 2017年第7期55卷 8-15页

作者： Zhang, Chunhong Ren, Jianqiang Luo, Ping College of Mathematics and Information Langfang Teachers University Langfang Hebei065000 China Institute of Pattern Recognition and Intelligent System Langfang Teachers University Langfang Hebei065000 China Langfang Key Laboratory of Intelligent Transportation System Langfang Hebei065000 China

In μC/OS-III, the traditional round robin algorithm is inefficient for tasks with the same priority. To solve this problem, this paper proposes a dynamic round robin scheduling algorithm based on the shortest remaining time first, called SRTFDRR. The algorithm determines the scheduling order according to the submission time and the remaining execution time of each task;For tasks with the same priority, set up multiple ready queues, each queue calculates the time slice independently based on the average value of the remaining execution time of the task;The ready task is inserted into the ready queue RQ1 of the corresponding priority in the order of burst time increments;If the priority of the queue task is the current highest priority, the SRTFDRR algorithm runs the task in the queue RQ1;If the time slice expires, there is a task in RQ1 that has not yet finished, and the remaining execution part moves into queue RQ2 waiting for scheduling again, and so on until all tasks are finished. A multi-level queue is formed during the scheduling process. Simulation results show that, compared with the traditional RR algorithm, the SRTFDRR algorithm reduces the average turnaround time, average waiting time, average response time and switching times. It performs well in performance, overhead, and fairness of scheduling.

关键词： Scheduling

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：