检索结果-内蒙古大学图书馆

Object measurement system based on Surveillance video-images 1

6th International Conference on Frontier computing, FC 2017

作者： Duan, Hui-Xian Wang, Jun Song, Lei Liu, Na Cyber Physical System R&D Center The Third Research Institute of Ministry of Public Security Shanghai201204 China The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai200092 China Shanghai International Technology and Trade United Co. Ltd Shanghai200031 China

ISBN: (数字)9789811073984

ISBN: (纸本)9789811073977

Object measurement based on surveillance video-images is a critical task in the field of intelligent video surveillance. In this paper, we proposed an object measurement system based on surveillance video-images. Firstly, considering the scene of the urban video surveillance, a novel calibration tool is designed for such scene, which is portable, collapsible and operational. Next, based on the portable calibration tool, the intrinsic and extrinsic parameters of the surveillance camera can be estimated. Then, an object measurement system based on surveillance video-images is developed, which include the acquisition module of calibration data, the computation module of camera parameters, the selection module of measurement endpoint and the computation module of object. Finally, in the traffic checkpoint, experiments are carried out to verify the effectiveness of the object measurement system. The results show that as long as the surveillance camera is one-time calibrated based on the portable calibration tool, this system can measure the object on the surveillance video-images captured by the calibrated camera. What’s more, experimental results have shown that the object measurement system can be used to estimate the vehicle speed and measure the body height within the acceptable error range, and then have demonstrated the effectiveness of the object measurement system. © 2018, Springer Nature Singapore Pte Ltd.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

A New One-Class Classification Method with Multiple Encoder-Decoder Pairs for Images

A New One-Class Classification Method with Multiple Encoder-...

引用

International Conference on Intelligent Human-Machine systems and Cybernetics, IHMSC

作者： Dongxiang Chen Chungang Yan Mimi Wang Department of Electronics and Information Engineering Tongji University The Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai China

One of the main destinations of image classification methods is to screen out the images belonging to the target class (positive) and identify the images of other classes (negative). Although most classifiers are trained on both positive samples and negative samples, in reality, negative samples are often unavailable. One-class classifiers trained only on positive samples, are proposed to solve this problem. However, how to train effectively a classifier remains a daunting challenge. Considering the success of deep learning in the field of computer vision in recent years, we propose a one-class classification model for images based on convolutional neural network (CNN). The model consists of two parts of networks with different responsibilities. The network of the first part works as the discriminator, used to identify whether the images are positive. The networks of the second part, each of which consists of an encoder-decoder pair work as the guiders of the discriminator. They guide the discriminator to learn what images it should identify to be negative. Different encoder-decoder pairs can restore images to different degrees. Images restored to different degrees can be used to train the discriminator. The discriminator learns that images under a specific restored degree don't belong to the target class. The experiment results on CIFAR-10 show that our method can achieve good performance, with less difficulty in training than the GAN-based counterparts'.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SelectCast: Scalable data aggregation scheme in wireless sensor networks

SelectCast: Scalable data aggregation scheme in wireless sen...

引用

IEEE INFOCOM 2011

作者： Wang, Cheng Tang, Shaojie Li, Xiang-Yang Jiang, Changjun Department of Computer Science Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai China Department of Computer Science Illinois Institute of Technology Chicago IL 60616 United States TNLIST School of Software Tsinghua University China

ISBN: (纸本)9781424499212

In this work, for a wireless sensor network (WSN) of n randomly placed sensors with node density λ ∈ [1, n], we study the tradeoffs between the aggregation throughput and gathering efficiency. The gathering efficiency refers to the ratio of the number of the sensors whose data have been gathered to the total number of sensors. Specifically, we design two efficient aggregation schemes, called single-hop-length (SLH) scheme and multiple-hop-length (MLH) scheme. By novelly integrating these two schemes, we theoretically prove that our protocol achieves the optimal tradeoffs, and derive the optimal aggregation throughput depending on a given threshold value (lower bound) on gathering efficiency. Particularly, we show that under the MLH scheme, for a practically important set of symmetric functions called perfectly compressible functions, including the mean, max, or various kinds of indicator functions, etc., the data from Θ(n) sensors can be aggregated to the sink at the throughput of a constant order Θ(1), implying that our MLH scheme is indeed scalable. © 2011 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

A study on the optimum state for classroom learning from brain cognition perspective-research on relaxed alertness

引用

Journal of Convergence Information Technology 2012年第23期7卷 564-571页

作者： Gu, Rong Li, Jie Department of Electronic Science and Technology Tongji University Shanghai China The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

Booming development in brain science injects new vitality into the reform of teaching methods. Based on the perspective of brain cognition, this article addresses the optimum state for classroom learning- the relaxed alertness. This is a good state of mind combined low threats with high challenges. Specially, the vigilance is estimated by extracting useful electroencephalogram (EEG) information in time-domain, frequency-domain and spatial distribution. It is used as an indicator to judge whether a student is in the optimum state. Focusing on how to achieve that ideal state, this article discusses some new teaching methods, including the use of Baroque music to stimulate alpha brainwave, the design of effective pattern of guiding class to arouse positive emotions of students and the conversion of teaching forms as novel stimuli to heip them improve vigilance and tide over thinking trough. The effectiveness of these methods is verified by the relevant experimental results.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Evaluating feedback systems for residential building energy monitoring

Evaluating feedback systems for residential building energy ...

引用

2013 IEEE International Conference on Automation Science and Engineering, CASE 2013

作者： Guo, Wenqi Wendy Ullah, Tania Zhou, Mengchu National Institute of Standards and Technology Gaithersburg MD 20899 United States ECE Dept. New Jersey Institute of Technology Newark NJ 07102 United States Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 201804 China

ISBN: (纸本)9781479915156

Rising global energy demand, increasing electricity prices, and the limitation of natural resources have led to increased interest in energy monitoring of residential buildings. Much research has been done to examine the effect of energy use feedback to building occupants. An important step towards energy awareness is to provide timely and finegrained consumption information of major household energy expenditures through feedback systems, known as residential energy monitoring systems (REMS). To accomplish this, researchers and product designers are intent on improving the residential whole-building energy consumption estimates gained through sensor networks at homes. Additionally, profiling the usage of appliances and devices within a home can be used to determine an occupant's daily activities and to optimize energy consumption. In this work, we take a step toward creating an evaluation procedure for REMS by determining factors that affect their ability to accurately convey energy usage to occupants. Two feedback sensor systems are assessed in a testbed in which electrical loads typical to a home are operated. Preliminary tests show that the accuracy of the REMS measurement is dependent on an electrical load's power factor. Together with other findings, the results will assist researchers in forming a comprehensive test procedure that will characterize feedback systems in the future. © 2013 IEEE.

关键词： Sensor networks

来源：评论

学校读者我要写书评

暂无评论

Research on the Matthews correlation coefficients metrics of personalized recommendation algorithm evaluation

引用

International Journal of Hybrid Information Technology 2015年第1期8卷 163-172页

作者： Liu, Yingbo Cheng, Jiujun Yan, Chendan Wu, Xiao Chen, Fuzhen Key Laboratory of Embedded System and Service Computing of Ministry of Education Tongji University Shanghai China Department of Computer Science and Technology Tongji University Shanghai China

The personalized recommendation systems could better improve the personalized service for network user and alleviate the problem of information overload in the Internet. As we all know, the key point of being a successful recommendation system is the performance of recommendation algorithm. When scholars put forward some new recommendation algorithms, they claim that the new algorithms have been improved in some respects, better than previous algorithm. So we need some evaluation metrics to evaluate the algorithm performance. Due to the scholar didn’t fully understand the evaluation mechanism of recommendation algorithms. They mainly emphasized some specific evaluation metrics like Accuracy, Diversity. What’s more, the academia did not establish a complete and unified assessment of recommendation algorithms evaluation system which is credibility to do the work of recommendation evaluation. So how to do this work objective and reasonable is still a challengeable task. In this article, we discussed the present evaluation metrics with its respective advantages and disadvantages. Then, we put forward to use the Matthews Correlation Coefficient to evaluate the recommendation algorithm’s performance. All this based on an open source projects called mahout which provides a rich set of components to construct the classic recommendation algorithm. The results of the experiments show that the applicability of Matthews correlation coefficient in the relative evaluation work of recommendation algorithm. © 2015 SERSC.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Rotational invariant LBP-SURF for fast and robust image matching

Rotational invariant LBP-SURF for fast and robust image matc...

引用

International Conference on Signal Processing and Communication systems, ICSPCS

作者： Penghui Jiang Shengjie Zhao Samuel Cheng School of Electronic and Information Engineering Tongji University Shanghai China Key Lab of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

Speeded Up Robust Features (SURF) is one of the most robust and widely used image matching algorithms based on local features. However, the performance for rotation image is poor when one image is a rotated version of the other. To improve the matching accuracy of rotation image, we present an modified image matching algorithm combining Haar wavelet and the rotation invariant Local Binary Patterns (LBP). Firstly, keypoints are extracted from the images for matching by applying the Hessian matrix and integral images. Secondly, each keypoint is described by the Rotation Invariant LBP patterns and Haar wavelet, which are computed from the image patch centered at the keypoint. Finally, the matching pairs between the two sets of keypoints are determined by using the nearest neighbor distance based on matching strategy. The experimented results show that in comparison with prior works the proposed algorithm is efficient when tested on the images of scaling, rotation, blurring and brightening.

关键词： Robustness Feature extraction Image matching Brightness Lighting Euclidean distance embedded systems

来源：评论

学校读者我要写书评

暂无评论

An immune approach for detecting the user's behavior of electronic transaction process

引用

Journal of Computational Information systems 2015年第2期11卷 683-692页

作者： Jiang, Shaoping Yan, Chungang Zhao, Peihai Wang, Mimi Department of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

In the process of electronic transaction, there are many abnormal conditions such as user's own mistakes, account theft and so on. Inspired by mechanisms of immune homeostasis, immune surveillance and immune update from the biological immune system, an immune approach for detecting the user's behavior of electronic transaction process is proposed to solve these problems and make the user's behaviors credible. By computing age of each log and cleaning up the aging logs, logs which can reflect the user's habit could be gotten and the mechanism of immune homeostasis is realized. With the newly-generated transaction sequence detected to be abnormal or not, the mechanisms of immune surveillance is achieved. Updating related sets is the realization of immune update, and the goal of detecting the user's behavior can be reached. The experimental results show that the true positive rate can reach 92% when the false positive rate is 10.8%. 1553-9105/Copyright © 2015 Binary Information Press

关键词： Physiology

来源：评论

学校读者我要写书评

暂无评论

An algorithm for generating home states of Petri nets

引用

Journal of Computational Information systems 2011年第12期7卷 4225-4232页

作者： Wang, Pengwei Ding, Zhijun Chai, Hua Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai 200092 China Department of Computer Science and Technology Tongji University Shanghai 201804 China

Home states are ground markings which can be reached from any other reachable markings of a Petri net. The existence of home states is a strong property, and it is not only of important theoretical research meaning, but also of great practical value. This paper presents an algorithm for generating home states. For any bounded Petri net, the algorithm can judge whether it contains home states or not, and obtain the set of all its home states. The correctness of the algorithm is proved, and its complexity is analyzed, the result shows that it is a polynomial-time algorithm, so it is effective. Meanwhile, we implemented the algorithm in the popular Petri net tool PIPE2, which can be used for experimental purposes. Then a number of conclusions about the relationships between home state and deadlock are given, which bring great convenience to judge deadlock and exert control pointedly. Copyright © 2011 Binary Information Press.

关键词： Petri nets

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of DSP Cache 21

Design and Implementation of DSP Cache

引用

21st IEEE International Conference on Communication Technology, ICCT 2021

作者： Liang, Kunkun Wu, Jun Ren, Haoqi Zhang, Zhifeng Tan, Bin Tongji University Electronics and Information Engineering College Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai201804 China School of Computer Science Fudan University Shanghai200438 China College of Electronics and Information Engineering Jinggangshan University Ji'an343009 China

ISBN: (纸本)9781665432061

The cache can improve the DSP processor's access speed to external memory and solve the 'Storage Wall' problem. Designing an efficient and flexible cache module plays an vital role in improving the memory access efficiency and overall performance of the DSP. Based on the analysis of DSP storage level design requirements, combined with the actual pipeline structure of the DSP processor SWIFT independently developed by our laboratory, in this paper, we design and implement first- level instruction and data cache. For L1 D-Cache, the relevant conflict detection and processing module is designed to support four parallel Load/Store access requests. The size of the cache can be flexibly configured according to actual application requirements to achieve a balance between power consumption and latency. To write back the modified data left in the cache before the cache size is changed, the Cacheclean instruction is designed. Finally, module-level functional verification and logic synthesis are carried out. The results show that the cache function meets expectations, and the critical path after logic synthesis optimization meets the requirement of 1GHz frenuency. © 2021 IEEE.

关键词： Pipelines

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：