Facial expression recognition(FER) plays an important role in human-machine interaction. An assistant robot having a close interaction with human being should be able to recognize human facial expression. FER is a non...
详细信息
Facial expression recognition(FER) plays an important role in human-machine interaction. An assistant robot having a close interaction with human being should be able to recognize human facial expression. FER is a non-trivial problem because each individual has his own way to reveal his emotion and the facial expressions of two different persons may not be totally identical. Hence,facial expression recognition is still a challenging problem in computer vision. In this work, we propose a simple solution for facial expression recognition that uses a combination of Convolutional Neural Network and specific image pre-processing *** experiments employed to evaluate our technique were carried out using two largely used public databases(CK+, JAFFE).A study of the impact of each image pre-processing operation in the accuracy rate is presented. The proposed method: achieves competitive results when compared with other facial expression recognition methods-97.85% of accuracy in the CK+ database-it is fast to train,and it allows for real time facial expression recognition with standard computers.
With the application of magnetic thin films becoming more and more widespread,people pay more and more attention to the performance *** order to obtain a magnetic film with a specific performance,it is very important ...
详细信息
With the application of magnetic thin films becoming more and more widespread,people pay more and more attention to the performance *** order to obtain a magnetic film with a specific performance,it is very important to judge the quality of the magnetic film and measure the magnetic properties of the ***,with the increase of the film preparation process,the thickness of the prepared film is getting thinner and the magnetic moment signal contained therein is also *** brings a certain degree of difficulty to the traditional measurement *** example,the VSM system that obtains the hysteresis loop by measuring the magnetic moment signal has become somewhat inadequate for the measurement of ultra-thin *** order to solve this issue,a new method based on anomalous Hall effect is introduced in this *** test system of this system adopts the four-probe measuring method,a constant current is applied across the surface of the film sample,and the abnormal Hall voltage is measured at the other two *** R-H curve of the sample can be obtained through *** compared to VSM measurement,this method is simpler and stable,more accurate,which can greatly reduce the anomalous Hall-effect device R-H characteristic measurement cost.
This paper investigates the problem of finite-time H∞ state estimation for discrete-time stochastic switched genetic regulatory networks(GRNs) with time-varying delays and exogenous disturbances. A new discrete tim...
详细信息
This paper investigates the problem of finite-time H∞ state estimation for discrete-time stochastic switched genetic regulatory networks(GRNs) with time-varying delays and exogenous disturbances. A new discrete time-delayed stochastic switched GRN model with uncertain sojourn probabilities is devised, which is more general than the switched GRNs model with completely known sojourn probabilities. The sufficient conditions which guarantee the stochastic finite-time boundedness of the estimation error dynamics with a prescribed H∞ disturbance attenuation level are derived. By solving several matrix inequalities,the state estimator parameters can be obtained. A numerical example is given to illustrate the effectiveness of our results.
This paper investigates the stability of neural networks with a time-varying *** on the good effectiveness of the augmented Lyapunov-Krasovskii functional(LKF),some useful integral vectors are summarized and used to c...
详细信息
This paper investigates the stability of neural networks with a time-varying *** on the good effectiveness of the augmented Lyapunov-Krasovskii functional(LKF),some useful integral vectors are summarized and used to construct single integral terms with augmented quadratic integrand so as to develop a novel augmented LKF *** an extended reciprocally convex matrix inequality and an auxiliary function-based inequality are utilized to estimate the derivative of the *** a result,an improved stability criterion is ***,the advantage of proposed method is demonstrated by a numerical example.
In this paper, a new unscented Kalman filter(Unscented Kalman filter, UKF) for nonlinear system with both one-step randomly delayed measurements and colored measurement noises is proposed. Firstly, the first-order Mar...
详细信息
In this paper, a new unscented Kalman filter(Unscented Kalman filter, UKF) for nonlinear system with both one-step randomly delayed measurements and colored measurement noises is proposed. Firstly, the first-order Markov sequence model is used to whiten colored noise, at the same time, an independent and identically distributed Bernoulli variable is used to model the delay of measurement data transmission, then the model of nonlinear one-step randomly time delay system with colored noise whitening is established. Secondly, filter recursion formula of UKF under the above model is proposed through unscented transformation(Unscented transformation, UT) to calculate the posterior mean and covariance of the nonlinear state based on the Bayesian filter framework. The proposed new UKF method can effectively deal with the issue that traditional UKF is failure under the condition of one-step randomly delayed measurements and colored measurement noises. The efficiency and superiority of the proposed method are illustrated in a numerical example for a target tracking problem.
Considering the difficulties in estimating depth from single image, in this paper, we propose a method to obtain the absolute scale depth map by combining the convolution neural network and depth filter. We compute re...
详细信息
Considering the difficulties in estimating depth from single image, in this paper, we propose a method to obtain the absolute scale depth map by combining the convolution neural network and depth filter. We compute relative transformation between consecutive frames by direct tracking features, which are extracted from RGB images and whose depthes are predicted by deep network, and then optimize relative motion by searching for a better feature alignment in epipolar line, and finally update every pixel depth of the reference frame by depth filter. We evaluate the proposed method on the open dataset comparison against the state of the art in depth estimation to evaluate our method.
A new concept of a synchronous detector for Giant Magneto-Impedance(GMI) sensors is presented. This concept combines a lock-in amplifier, with outstanding capabilities, high speed and a feedback approach that ensure...
详细信息
A new concept of a synchronous detector for Giant Magneto-Impedance(GMI) sensors is presented. This concept combines a lock-in amplifier, with outstanding capabilities, high speed and a feedback approach that ensures the amplitude detection with easily adjustable gain. The synchronous detector is capable of measuring high-frequency and very low amplitude signals without the use of diode-based active rectifiers or analog switches. In comparison with most of the commercially available diode-based peak detectors, the linearity of the synchronous detector is generally better, especially for low level amplitudes. The synchronous detector has been used for the amplitude measurement of single frequency sine signal and for the demodulation of amplitude-modulated signal. It has also been successfully integrated in a GMI sensor prototype. Magnetic field measurements in open-and closed-loop of this sensor have been conducted. The measured sensitivity was about 1.02 V/Oe in open-loop while it was 0.12 V/Oe in close-loop. The above research provides technical accumulation for the design of sensor nodes based on GMI sensor wireless sensor networks.
Aiming at the detection of moving objects in video series, a moving object detection algorithm based on background difference method and inter-frame difference method is proposed. A new background update method is pro...
详细信息
Aiming at the detection of moving objects in video series, a moving object detection algorithm based on background difference method and inter-frame difference method is proposed. A new background update method is proposed to update the unchanged background area into the background frame. Experiments show that this method overcomes the problems of false detection and empty in the previous detection algorithms. The method can meet the need of real-time detection and tracking of moving targets with the advantages of high accuracy and fast calculation speed.
The traditional wired seismograph has disadvantages such as cumbersome cable, complicated wiring, crosstalk and noise between adjacent transmission lines. In addition, the dynamic range of the instrument is small, and...
详细信息
The traditional wired seismograph has disadvantages such as cumbersome cable, complicated wiring, crosstalk and noise between adjacent transmission lines. In addition, the dynamic range of the instrument is small, and the observation of seismic signals is not intuitive, which can not meet the needs of high-precision seismic exploration. In order to solve these problems, the design of distributed three component seismic data acquisition system based on Lo Ra wireless communication technology is proposed. The system uses Lo Ra long-distance wireless communication technology and 24 bit Σ-Δ ADC, which realizes long-distance wireless communication and large dynamic range seismic data acquisition. Besides, the system has manmachine interaction interface, which can observe the parameters of seismic waveform in real time and adjust sampling rate directly. The whole circuit has the advantages of simple design, high precision and good stability. To sum up, the design has certain practical value and application prospect.
This paper presents a two-stage position control strategy based on the differential evolution(DE) algorithm for a planar second-order nonholonomic manipulator,which has one passive joint and this passive joint is not ...
详细信息
This paper presents a two-stage position control strategy based on the differential evolution(DE) algorithm for a planar second-order nonholonomic manipulator,which has one passive joint and this passive joint is not the first joint(planar APA manipulator for short,where m≥1,n≥0).An offline DE algorithm is used to calculate all link target angles corresponding to the target *** to these target angles,a Lyapunov function is constructed to design the controllers A for the control stage 1,which are used to control all active links to their target *** to the constraint equation of the planar APA manipulator,an oscillatory trajectory is planned for the first active link based on the online DE *** the first active link tracks the oscillatory trajectory,it will back to its target angle ***,the passive link will be jointly controlled to its target angle ***,the other Lyapunov function is constructed to design the controllers B for the control stage 2,which are used to control the first active link tracks the target trajectory and control the remaining m+n-1 active links maintain in their target *** results of a planar AAPA manipulator demonstrate the effectiveness of the proposed control strategy.
暂无评论