The rapid growth of multimedia content necessitates powerful technologies to filter, classify, index and retrieve video documents more efficiently. However, the essential bottleneck of image and video analysis is the ...The rapid growth of multimedia content necessitates powerful technologies to filter, classify, index and retrieve video documents more efficiently. However, the essential bottleneck of image and video analysis is the problem of semantic gap that low level features extracted by computers always fail to coincide with high-level concepts interpreted by humans. In this paper, we present a generic scheme for the detection video semantic concepts based on multiple visual features machine learning. Various global and local low-level visual features are systelrtically investigated, and kernelbased learning method equips the concept detection system to explore the potential of these features. Then we combine the different features and sub-systen on both classifier-level and kernel-level fusion that contribute to a more robust system Our proposed system is tested on the TRECVID dataset. The resulted Mean Average Precision （MAP） score is rmch better than the benchmark perforrmnce, which proves that our concepts detection engine develops a generic model and perforrrs well on both object and scene type concepts.展开更多
To study the problem of obstacle detection based on multi-sensors data fusion,the multi-target tracking theory and techniques are introduced into obstacle detection systems,and the exact position of obstacle can be de...To study the problem of obstacle detection based on multi-sensors data fusion,the multi-target tracking theory and techniques are introduced into obstacle detection systems,and the exact position of obstacle can be determined.Data fusion problems are discussed directly based on achievable data from some sensors without considering the specific structure of each individual sensor.With respect to normal linear systems and nonlinear systems,the corresponding algorithms are proposed.The validity of the method is confirmed by simulation results.展开更多
Collaboration in wireless sensor systems must be fault-tolerant due to the harsh environmental conditions at which such systems can be deployed. This paper focuses on finding the signal processing algorithms for colla...Collaboration in wireless sensor systems must be fault-tolerant due to the harsh environmental conditions at which such systems can be deployed. This paper focuses on finding the signal processing algorithms for collaborative target detection based on the generalized approach to signal processing （GASP） in the presence of noise. The signal processing algorithms are efficient in terms of communication cost, precision, accuracy, and number of faulty sensors tolerable in the wireless sensor systems. Two types of generalized signal processing algorithms, namely, value fusion and decision fusion constructed according to GASP in the presence of noise, are identified first. When comparing their performance and communication overhead, the decision fusion algorithm is found to become superior to the value fusion algorithm as the ratio of faulty sensors to fault free sensors increases. The use of GASP under designing the value and decision fusion algorithms in wireless sensor systems allows us to obtain the same performance, but at low values of signal energy, as well as under employment of the universally adopted signal processing algorithms widely used in practice.展开更多
基金Acknowledgements This paper was supported by the coUabomtive Research Project SEV under Cant No. 01100474 between Beijing University of Posts and Telecorrrcnications and France Telecom R＆D Beijing the National Natural Science Foundation of China under Cant No. 90920001 the Caduate Innovation Fund of SICE, BUPT, 2011.
文摘The rapid growth of multimedia content necessitates powerful technologies to filter, classify, index and retrieve video documents more efficiently. However, the essential bottleneck of image and video analysis is the problem of semantic gap that low level features extracted by computers always fail to coincide with high-level concepts interpreted by humans. In this paper, we present a generic scheme for the detection video semantic concepts based on multiple visual features machine learning. Various global and local low-level visual features are systelrtically investigated, and kernelbased learning method equips the concept detection system to explore the potential of these features. Then we combine the different features and sub-systen on both classifier-level and kernel-level fusion that contribute to a more robust system Our proposed system is tested on the TRECVID dataset. The resulted Mean Average Precision （MAP） score is rmch better than the benchmark perforrmnce, which proves that our concepts detection engine develops a generic model and perforrrs well on both object and scene type concepts.
基金Sponsored by the Science Foundation for Youths of Heilongjiang Province(Grant No.QC08C05)
文摘To study the problem of obstacle detection based on multi-sensors data fusion,the multi-target tracking theory and techniques are introduced into obstacle detection systems,and the exact position of obstacle can be determined.Data fusion problems are discussed directly based on achievable data from some sensors without considering the specific structure of each individual sensor.With respect to normal linear systems and nonlinear systems,the corresponding algorithms are proposed.The validity of the method is confirmed by simulation results.
文摘Collaboration in wireless sensor systems must be fault-tolerant due to the harsh environmental conditions at which such systems can be deployed. This paper focuses on finding the signal processing algorithms for collaborative target detection based on the generalized approach to signal processing （GASP） in the presence of noise. The signal processing algorithms are efficient in terms of communication cost, precision, accuracy, and number of faulty sensors tolerable in the wireless sensor systems. Two types of generalized signal processing algorithms, namely, value fusion and decision fusion constructed according to GASP in the presence of noise, are identified first. When comparing their performance and communication overhead, the decision fusion algorithm is found to become superior to the value fusion algorithm as the ratio of faulty sensors to fault free sensors increases. The use of GASP under designing the value and decision fusion algorithms in wireless sensor systems allows us to obtain the same performance, but at low values of signal energy, as well as under employment of the universally adopted signal processing algorithms widely used in practice.
