Du Junping
Beijing University of Posts and Telecommunications
Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Du Junping.
chinese control conference | 2006
Lin Peng; Jia Yingmin; Du Junping; Yuan Shiying
In this paper, distributed consensus control is investigated for networks of agents with double integrator dynamics. Two kinds of networks are analyzed, i.e., directed networks with fixed topology and undirected networks with fixed topology and time-delay. For each of the networks, a sufficient and necessary condition is given to guarantee the consensus. It is proved that the largest tolerable time-delay is only related to the largest eigenvalue of the graph Laplacian. Finally, two numerical examples are provided to illustrate the obtained results.
The Journal of China Universities of Posts and Telecommunications | 2016
Li Linghui; Du Junping; Liang Meiyu; Ren Nan; Fan Dan
Abstract Existing learning-based super-resolution (SR) reconstruction algorithms are mainly designed for single image, which ignore the spatio-temporal relationship between video frames. Aiming at applying the advantages of learning-based algorithms to video SR field, a novel video SR reconstruction algorithm based on deep convolutional neural network (CNN) and spatio-temporal similarity (STCNN-SR) was proposed in this paper. It is a deep learning method for video SR reconstruction, which considers not only the mapping relationship among associated low-resolution (LR) and high-resolution (HR) image blocks, but also the spatio-temporal non-local complementary and redundant information between adjacent low-resolution video frames. The reconstruction speed can be improved obviously with the pre-trained end-to-end reconstructed coefficients. Moreover, the performance of video SR will be further improved by the optimization process with spatio-temporal similarity. Experimental results demonstrated that the proposed algorithm achieves a competitive SR quality on both subjective and objective evaluations, when compared to other state-of-the-art algorithms.
international conference on networking sensing and control | 2010
Gao Tian; Du Junping; Sun Zengqi; Jia Yingmin
In this paper, digital tourism integrated service system has been studied and implemented. Integrated service support platform is built based on broadband networks, on the basis of achieving the management information subsystem and application service subsystem. Management information subsystem provides the main function of information management and video surveillance in scenic area for the tourism authority departments and tourism enterprises; applications service subsystem provides tourists with tourism information service from the tourism public service navigation, tourism travel planning, tourism smart navigation based on PDA and scenic video active service system.
international conference on control, automation and systems | 2010
Liang Meiyu; Du Junping; Jia Yingmin; Sun Zengqi
Making the semantic description and automatic semantic annotation of the image which contains rich contents and intuitive expression is a research subject that is challenging. It is a key technology of realizing fast and effective image retrieval and a research focusing on cross media mining. Also it has great application value in various kinds of fields. This paper studies and discusses image media semantic description and automatic semantic annotation. By extracting SIFT visual features, we make the description of the image semantic, then establish the association between local image visual features and semantic keywords, and finally realize the image to the text feature mapping and the automatic semantic annotation. The simulation experiment result shows that this method can accomplish the image automatic semantic annotation efficiently, and also it can reach a higher accuracy.
international conference on control, automation and systems | 2010
Yang Yuehua; Du Junping; Jia Yingmin; Sun Zengqi
As the users of social network sites increases, the types of applications service social network sites provide are becoming more and more. This paper establishes an SNS graph generation model based on social services provided by kaixin.com, which describes the intrinsic relationship of entities (users, groups, applications, posts, and albums) in the site; extracts some rules according to the relationship of entities and applies these rules to the SNS graph generation, so the SNS graph can be updated dynamically with the selected social network site;Finally proposes an algorithm used to predict which applications may obtain more users in the future roughly based on SNS graph and according to the prediction results the social network site can adjust its website structure thereby absorbing more users.
international conference on networking sensing and control | 2010
Wang Su; Du Junping; Zhou Yipeng; Sun Zengqi; Jia yingming
A data based intelligent decision support system is proposed to solve problems of decision making of tourism management in complex environments. Firstly, the architecture of the decision support system integrated with several intelligence technologies is proposed, and some key technologies of implementation, such as 3S and decomposition of large decision table are also introduced. Then, some data analysis methods used in this decision support system are presented, which include tourism information categories, space time pattern of tourism status, tourism planning and navigation, early warning of tourism status and safety incidents. Finally, several applications of this system are also given.
chinese control conference | 2008
Li Juntao; Jia Yingmin; Du Junping; Li Wenlin
Laplacian support vector machine (LapSVM) is an attracting tool for semi-supervised classification with manifold regularization. In this paper, we devote to selecting the extrinsic and intrinsic regularization parameters. To this end, a fusion of training and validation levels is first proposed, based on which, the optimal regularization parameters selection problem can be cast as a standard semidefinite programming. Then, a hybrid manifold regularization algorithm is also developed, thus eliminating the difficulty of balancing between the ambient space and the intrinsic geometric of the data distribution. Finally, experiments are performed that verify the research results.
world congress on intelligent control and automation | 2016
Yuan Yifan; Du Junping; Fan Dan; Jang-Myung Lee
With the rapid development of technologies, such as cloud computing, big Data and so forth, tourism Big Data has drawn the attention of many scholars. How to make full use of a large amount of raw data from tourism activity, and how to recognize and discover tourism activity quickly, accurately and conveniently from information which is accumulated over a long period have become a new direction of tourism data application. In this paper, text analysis, text classification and other relevant technologies are combined based on text mining. Furthermore, a tourism activity recognition and discovery system is designed and implemented, which has achieved the recognition and discovery of tourism activity from a large amount of information. The research results could contribute to recommending and predicting tourism activity in China.
international symposium on industrial electronics | 2009
Zheng Jinxin; Du Junping
In automatic image mosaic, the problem of solving and optimizing the modeled image parameters is usually a least square problem. In this paper an approach to solve the image parameterization based on the Levenberg-Marquardt algorithm is introduced. An appropriate camera parameterization model is firstly established, and the problem of optimization against the parameters is turned into a least square problem of the projection error between images, which solves registering all the images. Finally the images are rendered with their parameters to a spherical surface, where the linear blending and bi-linear interpolation are employed to render the images. The spherical surface is unfolded into a planar surface which gives the final mosaic result.
world congress on intelligent control and automation | 2016
Wen Yaomin; Du Junping; Liang Meiyu; Fan Dan; Jang-Myung Lee
In recent years, accidents occur frequently because the people number of scenic spots is lack of control. In this paper, a novel real-time people number detection algorithm of scenic spot based on density center clustering (DPBC) is proposed. Taking account of the complexity of the scenic environment, we use the Gauss mixture model (GMM) to suppress the background interference, extract the feature points from the crowd and cluster these feature points by applying a clustering algorithm based on density center. Then we establish a training set and estimate the people number by using the support vector regression model (SVR). We implement the proposed algorithm based on Opencv and use PETS dataset to validate the effectiveness of our proposed algorithm. Experimental results demonstrate that compared with Aibiol algorithm and Conte algorithm, our proposed algorithm improved the accuracy for estimating the people number in a scenic spot.