Deyu Qi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Deyu Qi has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Wei-Wei Lin
School of Computer Engineering and Science, South China Univ. of Tech., Guangzhou Guangdong, 510640, China
2 shared publications - Bo Liu
School of Automation, Guangdong University of Technology, Guangzhou 510006, China
1 shared publication - ChangJian Zhang
School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, China
1 shared publication - Fei-Qiao Mao
College of Computer Science & Engineering, South China University of Technology, Guangzhou, China
1 shared publication - JiaJun Yao
School of Software Engineering, South China University of Technology, Guangzhou 510006, China
1 shared publication - Jing Guo
School of Software Engineering, South China University of Technology, Guangzhou 510006, China
1 shared publication
Latest Publications
- Open Access
Video Summarization Based on Mutual Information and Entropy Sliding Window Method
This paper proposes a video summarization algorithm called the Mutual Information and Entropy based adaptive Sliding Window (MIESW) method, which is specifically for the static summary of gesture videos. Considering that gesture videos usually have uncertain transition postures and unclear movement boundaries or inexplicable frames, we propose a three-step method where the first step involves browsing a video, the second step applies the MIESW method to select candidate key frames, and the third step removes most redundant key frames. In detail, the first step is to convert the video into a sequence of frames and adjust the size of the frames. In the second step, a key frame extraction algorithm named MIESW is executed. The inter-frame mutual information value is used as a metric to adaptively adjust the size of the sliding window to group similar content of the video. Then, based on the entropy value of the frame and the average mutual information value of the frame group, the threshold method is applied to optimize the grouping, and the key frames are extracted. In the third step, speeded up robust features (SURF) analysis is performed to eliminate redundant frames in these candidate key frames. The calculation of Precision, Recall, and F are optimized from the perspective of practicality and feasibility. Experiments demonstrate that key frames extracted using our method provide high-quality video summaries and basically cover the main content of the gesture video.Open AccessVideo Summarization Based on Mutual Information and Entropy Sliding Window Method
This paper proposes a video summarization algorithm called the Mutual Information and Entropy based adaptive Sliding Window (MIESW) method, which is specifically for the static summary of gesture videos. Considering that gesture videos usually have uncertain transition postures and unclear movement boundaries or inexplicable frames, we propose a three-step method where the first step involves browsing a video, the second step applies the MIESW method to select candidate key frames, and the third step removes most redundant key frames. In detail, the first step is to convert the video into a sequence of frames and adjust the size of the frames. In the second step, a key frame extraction algorithm named MIESW is executed. The inter-frame mutual information value is used as a metric to adaptively adjust the size of the sliding window to group similar content of the video. Then, based on the entropy value of the frame and the average mutual information value of the frame group, the threshold method is applied to optimize the grouping, and the key frames are extracted. In the third step, speeded up robust features (SURF) analysis is performed to eliminate redundant frames in these candidate key frames. The calculation of Precision, Recall, and F are optimized from the perspective of practicality and feasibility. Experiments demonstrate that key frames extracted using our method provide high-quality video summaries and basically cover the main content of the gesture video. - 31 January 2012
- Published by AICIT in International Journal of Digital Content Technology and its Applications
- Vol. 6 (1) , 471-478
Study and Implementation of Wireless Sensor Networks Collaboration based on Bio-inspired Trust and Reputation Model(BTRM)
- 31 January 2012
- Published by AICIT in International Journal of Digital Content Technology and its Applications
- Vol. 6 (1) , 471-478
Study and Implementation of Wireless Sensor Networks Collaboration based on Bio-inspired Trust and Reputation Model(BTRM)
- 1 May 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 19483449,p. 2282-2287
Adaptive Linkage: an Interface Level Adaptable Component Development Technique
Business requirements change consequentially causes software system business functions change and changing components which participate in performing the business functions, so flexible components can well adapt to the change of business functions. In order to solve component flexibility problem, this paper proposes an adaptable component development technique------adaptive linkage, which at interface level enables component to flexibly support business functions change. The proposed logical structure of adaptive component which owns multiple interfaces and multiple implementations, the introduced adaptive linkage descriptor provide the basis for adaptive linkage development technique, a formal model of adaptive linkage descriptor is addressed as a theory basis for its code autogeneration; then we implement this technique with XML and based on encapsulation and inheritance programming mechanisms in object oriented software development technology. At last, in the example system development process we adopt this technique to develop the components which participate in the performance of computing students required courses average score function to show how to use this technique, at the same time this also illustrates that developing adaptable component with this technique can effectively simplify developers' work when amending a component, and moreover, the amending of a component does not effect the performance of other business functions which don't hope the component to change and in whose performance the component participants.
- 1 May 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 19483449,p. 2282-2287
Adaptive Linkage: an Interface Level Adaptable Component Development Technique
Business requirements change consequentially causes software system business functions change and changing components which participate in performing the business functions, so flexible components can well adapt to the change of business functions. In order to solve component flexibility problem, this paper proposes an adaptable component development technique------adaptive linkage, which at interface level enables component to flexibly support business functions change. The proposed logical structure of adaptive component which owns multiple interfaces and multiple implementations, the introduced adaptive linkage descriptor provide the basis for adaptive linkage development technique, a formal model of adaptive linkage descriptor is addressed as a theory basis for its code autogeneration; then we implement this technique with XML and based on encapsulation and inheritance programming mechanisms in object oriented software development technology. At last, in the example system development process we adopt this technique to develop the components which participate in the performance of computing students required courses average score function to show how to use this technique, at the same time this also illustrates that developing adaptable component with this technique can effectively simplify developers' work when amending a component, and moreover, the amending of a component does not effect the performance of other business functions which don't hope the component to change and in whose performance the component participants.
- 1 January 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1561-1565
Research and Implementation Issues of Fusegrid
After analyzing problems in current grid environments, a new grid architecture (called FuseGrid) based on the tree-shaped fusion of resources is presented in this paper. JVMs act as a base computing resources in the proposed grid architecture, in which all objects that can be accessed by computer systems are regarded as resources and they are aggregated and fused in the form of tree from bottom to top, forming new resources of higher level. After introducing an overview of FuseGrid and discussing its functionality model, the key issues of FuseGrid implementation, the algorithms for tree building, dynamic reconfiguring tree and resource searching are presented in this paper. Then, it focuses on the task allocation algorithm using dynamic load balancing for large-scale applications in FuseGrid. Finally, the experiments show that FuseGrid has excellent performance when it is used as an execution environment of large batch of Java applications
- 1 January 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1561-1565
Research and Implementation Issues of Fusegrid
After analyzing problems in current grid environments, a new grid architecture (called FuseGrid) based on the tree-shaped fusion of resources is presented in this paper. JVMs act as a base computing resources in the proposed grid architecture, in which all objects that can be accessed by computer systems are regarded as resources and they are aggregated and fused in the form of tree from bottom to top, forming new resources of higher level. After introducing an overview of FuseGrid and discussing its functionality model, the key issues of FuseGrid implementation, the algorithms for tree building, dynamic reconfiguring tree and resource searching are presented in this paper. Then, it focuses on the task allocation algorithm using dynamic load balancing for large-scale applications in FuseGrid. Finally, the experiments show that FuseGrid has excellent performance when it is used as an execution environment of large batch of Java applications
- 1 January 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 2160133X,p. 4389-4394
Research and Implementation Issues of Fusegrid
After analyzing problems in current grid environments, a new grid architecture(called FuseGrid) based on the tree-shaped fusion of resources is presented in this paper. JVMs act as a base computing resources in the proposed grid architecture, in which all objects that can be accessed by computer systems are regarded as resources and they are aggregated and fused in the form of tree from bottom to top, forming new resources of higher level. After introducing an overview of FuseGrid and discussing its functionality model, the key issues of FuseGrid implementation, the algorithms for tree building, dynamic reconfiguring tree and resource searching are presented in this paper. Then, it focuses on the task allocation algorithm using dynamic load balancing for large-scale applications in FuseGrid. Finally, the experiments show that FuseGrid has excellent performance when it is used as an execution environment of large batch of Java applications.
- 1 January 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 2160133X,p. 4389-4394
Research and Implementation Issues of Fusegrid
After analyzing problems in current grid environments, a new grid architecture(called FuseGrid) based on the tree-shaped fusion of resources is presented in this paper. JVMs act as a base computing resources in the proposed grid architecture, in which all objects that can be accessed by computer systems are regarded as resources and they are aggregated and fused in the form of tree from bottom to top, forming new resources of higher level. After introducing an overview of FuseGrid and discussing its functionality model, the key issues of FuseGrid implementation, the algorithms for tree building, dynamic reconfiguring tree and resource searching are presented in this paper. Then, it focuses on the task allocation algorithm using dynamic load balancing for large-scale applications in FuseGrid. Finally, the experiments show that FuseGrid has excellent performance when it is used as an execution environment of large batch of Java applications.