Time filter

Source Type

Liu R.,Beijing Jiaotong University | Zhao Y.,Beijing Key Laboratory of Advanced Information Science and Network Technology | Wei S.,Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering | Zhu Z.,China Three Gorges University
Proceedings - IEEE International Conference on Multimedia and Expo | Year: 2015

Cross-media retrieval has received increasing interest in recent years, which aims to addressing the semantic correlation issues within rich media. As two key aspects, cross-media representation and indexing have been studied for dealing with cross-media similarity measure and the scalability issue, respectively. In this paper, we propose a new cross-media hashing scheme, called Centroid Approaching Cross-Media Hashing (CAMH), to handle both cross-media representation and indexing simultaneously. Different from existing indexing methods, the proposed method introduces semantic category information into the learning procedure, leading to more exact hash codes of multiple media type instances. In addition, we present a comparative study of cross-media indexing methods under a unique evaluation framework. Extensive experiments on two commonly used datasets demonstrate the good performance in terms of search accuracy and time complexity. © 2015 IEEE.


Chen P.,Hubei Key Laboratory of Intelligent Vision based Monitoring for Hydroelectric Engineering | Chen P.,China Three Gorges University | Yang L.,China Three Gorges University | Huo J.,China Three Gorges University
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2016

As a kind of stable feature matching algorithm, SIFT has been widely used in many fields. In order to further improve the robustness of the SIFT algorithm, an improved SIFT algorithm with Kernel Discriminant Analysis (KFDA-SIFT) is presented for image registration. The algorithm uses KFDA to SIFT descriptors for feature extraction matrix, and uses the new descriptors to conduct the feature matching, finally chooses RANSAC to deal with the matches for further purification. The experiments show that the presented algorithm is robust to image changes in scale, illumination, perspective, expression and tiny pose with higher matching accuracy. © 2016 SPIE.


Zhou H.,Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering | Zhou H.,China Three Gorges University | Ren D.,Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering | Ren D.,China Three Gorges University | And 6 more authors.
Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology | Year: 2015

In the Delay Tolerant Networks (DTNs), in order to discover the neighbors, the nodes in the network have to probe the surrounding environment continually. This can be an extremely energy-consuming process. If the nodes probe very frequently, they consume a lot of energy, and may be energy inefficient. On the other hand, infrequent contact probing might cause loss of many contacts, and thus missing the opportunities to exchange data. Therefore, there exists a trade-off between the energy efficiency and contact opportunities in the DTNs. In order to investigate this trade-off, this study first proposes a model to quantify the contact detecting probability when the contact probing interval is constant based on the Random Way-Point (RWP) model. Moreover, this study also demonstrates that the strategy which probes at a constant interval performs the best performance, among all contact probing strategies with the same average contact probing interval. Then, based on the proposed model, this study analyzes the trade-off between the energy efficiency and contact detecting probability under different situations. Finally, extensive simulations are conducted to validate the correctness of the proposed model. ©, 2015, Science Press. All right reserved.

Loading Hubei Key Laboratory of Intelligent Vision based Monitoring for Hydroelectric Engineering collaborators
Loading Hubei Key Laboratory of Intelligent Vision based Monitoring for Hydroelectric Engineering collaborators