A novel traffic sign recognition system is presented in this work. Firstly, the color segmentation and shape classifier based on signature feature of region are used to detect traffic signs in input video sequences. S...A novel traffic sign recognition system is presented in this work. Firstly, the color segmentation and shape classifier based on signature feature of region are used to detect traffic signs in input video sequences. Secondly, traffic sign color-image is preprocessed with gray scaling, and normalized to 64×64 size. Then, image features could be obtained by four levels DT-CWT images. Thirdly, 2DICA and nearest neighbor classifier are united to recognize traffic signs. The whole recognition algorithm is implemented for classification of 50 categories of traffic signs and its recognition accuracy reaches 90%. Comparing image representation DT-CWT with the well-established image representation like template, Gabor, and 2DICA with feature selection techniques such as PCA, LPP, 2DPCA at the same time, the results show that combination method of DT-CWT and 2DICA is useful in traffic signs recognition. Experimental results indicate that the proposed algorithm is robust, effective and accurate.展开更多
This paper presents an improved voice morphing algorithm based on Gaussian Mixture Model(GMM) which overcomes the traditional one in the terms of overly smoothed problems of the converted spectral and discontinuities ...This paper presents an improved voice morphing algorithm based on Gaussian Mixture Model(GMM) which overcomes the traditional one in the terms of overly smoothed problems of the converted spectral and discontinuities between frames.Firstly, a maximum likelihood estimation for the model is introduced for the alleviation of the inversion of high dimension matrixes caused by traditional conversion function.Then, in order to resolve the two problems associated with the baseline, a codebook compensation technique and a time domain medial filter are applied.The results of listening evaluations show that the quality of the speech converted by the proposed method is significantly better than that by the traditional GMM method, and the Mean Opinion Score(MOS) of the converted speech is improved from 2.5 to 3.1 and ABX score from 38% to 75%.展开更多
In the present paper, under investigation is a nonisospectral modified Kadomtsev-Petviashvili equation, which is shown to have two Painleve branches through the Painleve analysis. With symbolic computation, two Lax pa...In the present paper, under investigation is a nonisospectral modified Kadomtsev-Petviashvili equation, which is shown to have two Painleve branches through the Painleve analysis. With symbolic computation, two Lax pairs for such an equation are derived by applying the generalized singular manifold method. Furthermore, based on the two obtained Lax pairs, the binary Darboux transformation is constructed and then the N-th-iterated potential transformation formula in the form of Grammian is also presented.展开更多
A minimum mean-squared error （MSE） beamforming algorithm employing the optimum fractional Fourier transform （Opt-FrFT） domain second-order cyclostationarity is proposed. This method can efficiently filter out the ...A minimum mean-squared error （MSE） beamforming algorithm employing the optimum fractional Fourier transform （Opt-FrFT） domain second-order cyclostationarity is proposed. This method can efficiently filter out the compact desired chirp signal, with a consequence that the cyclically uncorrelated interferences and stationary （colored） Gaussian noise are greatly suppressed in the Opt- FrFT domain. This improves the MSE minimization cyclic beamformer by reducing effectively the Opt-FrFY domain signal-noise cross terms in the presence of finite data length de-correlation operation. Simulation results show that the new method works well under a wide range of signal-to-noise ratio （SNR） and signal-to-interference ratio （SIR）.展开更多
In this paper,the rogue waves of the higher-order dispersive nonlinear Schrdinger(HDNLS) equation are investigated,which describes the propagation of ultrashort optical pulse in optical fibers.The rogue wave solutions...In this paper,the rogue waves of the higher-order dispersive nonlinear Schrdinger(HDNLS) equation are investigated,which describes the propagation of ultrashort optical pulse in optical fibers.The rogue wave solutions of HDNLS equation are constructed by using the modified Darboux transformation method.The explicit first and secondorder rogue wave solutions are presented under the plane wave seeding solution background.The nonlinear dynamics and properties of rogue waves are discussed by analyzing the obtained rational solutions.The influence of little perturbation on the rogue waves is discussed with the help of graphical simulation.展开更多
The constructal optimizations of T-shaped fin with two-dimensional heat transfer model are carried out by finite element method and taking the minimization of equivalent thermal resistance based on entransy dissipatio...The constructal optimizations of T-shaped fin with two-dimensional heat transfer model are carried out by finite element method and taking the minimization of equivalent thermal resistance based on entransy dissipation and the minimization of maximum thermal resistance as optimization objectives, respectively. The effects of the global parameter a (integrating the coefficient of convective heat transfer, the overall area occupied by fin and its thermal conductivity) and the volume fraction ? of fin on the minimums of equivalent thermal resistance and maximum thermal resistance as well as their corresponding optimal configurations are analyzed. The comparison of the results based on the above two optimization objectives is conducted. The results show that the optimal structures based on the two optimization objectives are obviously different from each other. Compared with the optimization result by taking the minimization of maximum thermal resistance as the objective, the optimization result by taking the equivalent thermal resistance minimization as the objective can reduce the average temperature difference in the fin obviously. The increases of a and ? can all improve the working status of local hot spot and the global heat transfer performance of the system. But the improvement effects of the increases of a and ? on the minimization of equivalent thermal resistance are different from those on the minimization of maximum thermal resistance. For either objective, the effect of a is different from that of ?. The T-shaped fin with minimum equivalent thermal resistance is much taller than that with minimum maximum thermal resistance; for either optimization objective, the stem of fin is thicker than the branches of fin, and the stem thickness is relatively close to branch thickness when the minimization of equivalent thermal resistance is taken as the optimization objective. The T-shaped fin with flat stem and slender branches can benefit the reduction of the maximum thermal resistance.展开更多
基金Projects(90820302, 60805027) supported by the National Natural Science Foundation of ChinaProject(200805330005) supported by Research Fund for Doctoral Program of Higher Education, ChinaProject(2009FJ4030) supported by Academician Foundation of Hunan Province, China
文摘A novel traffic sign recognition system is presented in this work. Firstly, the color segmentation and shape classifier based on signature feature of region are used to detect traffic signs in input video sequences. Secondly, traffic sign color-image is preprocessed with gray scaling, and normalized to 64×64 size. Then, image features could be obtained by four levels DT-CWT images. Thirdly, 2DICA and nearest neighbor classifier are united to recognize traffic signs. The whole recognition algorithm is implemented for classification of 50 categories of traffic signs and its recognition accuracy reaches 90%. Comparing image representation DT-CWT with the well-established image representation like template, Gabor, and 2DICA with feature selection techniques such as PCA, LPP, 2DPCA at the same time, the results show that combination method of DT-CWT and 2DICA is useful in traffic signs recognition. Experimental results indicate that the proposed algorithm is robust, effective and accurate.
基金Supported by a grant from the National High Technology Research and Development Program of China (863 Program, No.2006AA010102)the National Natural Science Foundation of China (No.60872105).
文摘This paper presents an improved voice morphing algorithm based on Gaussian Mixture Model(GMM) which overcomes the traditional one in the terms of overly smoothed problems of the converted spectral and discontinuities between frames.Firstly, a maximum likelihood estimation for the model is introduced for the alleviation of the inversion of high dimension matrixes caused by traditional conversion function.Then, in order to resolve the two problems associated with the baseline, a codebook compensation technique and a time domain medial filter are applied.The results of listening evaluations show that the quality of the speech converted by the proposed method is significantly better than that by the traditional GMM method, and the Mean Opinion Score(MOS) of the converted speech is improved from 2.5 to 3.1 and ABX score from 38% to 75%.
基金supported by National Natural Science Foundation of China under Grant Nos.60772023 and 60372095the Key Project of the Ministry of Education under Grant No.106033+3 种基金the Open Fund of the State Key Laboratory of Software Development Environment under Grant No.SKLSDE-07-001Beijing University of Aeronautics and Astronautics,the National Basic Research Program of China (973 Program) under Grant No.2005CB321901by the Specialized Research Fund for the Doctoral Program of Higher Education under Grant No.20060006024the Ministry of Education
文摘In the present paper, under investigation is a nonisospectral modified Kadomtsev-Petviashvili equation, which is shown to have two Painleve branches through the Painleve analysis. With symbolic computation, two Lax pairs for such an equation are derived by applying the generalized singular manifold method. Furthermore, based on the two obtained Lax pairs, the binary Darboux transformation is constructed and then the N-th-iterated potential transformation formula in the form of Grammian is also presented.
基金Supported by the National Natural Science Foundation of China （ No. 60672084, 60602037, 60736006）.
文摘A minimum mean-squared error （MSE） beamforming algorithm employing the optimum fractional Fourier transform （Opt-FrFT） domain second-order cyclostationarity is proposed. This method can efficiently filter out the compact desired chirp signal, with a consequence that the cyclically uncorrelated interferences and stationary （colored） Gaussian noise are greatly suppressed in the Opt- FrFT domain. This improves the MSE minimization cyclic beamformer by reducing effectively the Opt-FrFY domain signal-noise cross terms in the presence of finite data length de-correlation operation. Simulation results show that the new method works well under a wide range of signal-to-noise ratio （SNR） and signal-to-interference ratio （SIR）.
基金Supported by the National Natural Science Foundation of China under Grant No.11071164Innovation Program of Shanghai Municipal Education Commission under Grant Nos.12YZ105 and 13ZZ118+1 种基金the Foundation of University Young Teachers Training Program of Shanghai Municipal Education Commission under Grant No.slg11029the National Natural Science Foundation of China under Grant No.11171220
文摘In this paper,the rogue waves of the higher-order dispersive nonlinear Schrdinger(HDNLS) equation are investigated,which describes the propagation of ultrashort optical pulse in optical fibers.The rogue wave solutions of HDNLS equation are constructed by using the modified Darboux transformation method.The explicit first and secondorder rogue wave solutions are presented under the plane wave seeding solution background.The nonlinear dynamics and properties of rogue waves are discussed by analyzing the obtained rational solutions.The influence of little perturbation on the rogue waves is discussed with the help of graphical simulation.
基金supported by the National Natural Science Foundation of China (Grant No. 10905093)the Program for New Century Excellent Talents in University of China (Grant No. NCET-04-1006)+1 种基金the Foundation for the Author of National Excellent Doctoral Dissertation of China (Grant No. 200136)the Natural Science Foundation for Youngsters of Naval University of Engineering (Grant No. HGDQNJJ10017)
文摘The constructal optimizations of T-shaped fin with two-dimensional heat transfer model are carried out by finite element method and taking the minimization of equivalent thermal resistance based on entransy dissipation and the minimization of maximum thermal resistance as optimization objectives, respectively. The effects of the global parameter a (integrating the coefficient of convective heat transfer, the overall area occupied by fin and its thermal conductivity) and the volume fraction ? of fin on the minimums of equivalent thermal resistance and maximum thermal resistance as well as their corresponding optimal configurations are analyzed. The comparison of the results based on the above two optimization objectives is conducted. The results show that the optimal structures based on the two optimization objectives are obviously different from each other. Compared with the optimization result by taking the minimization of maximum thermal resistance as the objective, the optimization result by taking the equivalent thermal resistance minimization as the objective can reduce the average temperature difference in the fin obviously. The increases of a and ? can all improve the working status of local hot spot and the global heat transfer performance of the system. But the improvement effects of the increases of a and ? on the minimization of equivalent thermal resistance are different from those on the minimization of maximum thermal resistance. For either objective, the effect of a is different from that of ?. The T-shaped fin with minimum equivalent thermal resistance is much taller than that with minimum maximum thermal resistance; for either optimization objective, the stem of fin is thicker than the branches of fin, and the stem thickness is relatively close to branch thickness when the minimization of equivalent thermal resistance is taken as the optimization objective. The T-shaped fin with flat stem and slender branches can benefit the reduction of the maximum thermal resistance.
