Background reconstruction plays an important role in many applications like video surveillance, motion analysis. Traditional Adaptive Gaussian Mixture Model will lose target when deal with arbitrary-long stationary ob...
详细信息
Background reconstruction plays an important role in many applications like video surveillance, motion analysis. Traditional Adaptive Gaussian Mixture Model will lose target when deal with arbitrary-long stationary object. In this paper, a novel method for detecting this kind of object is proposed to improve the performance of Adaptive Gaussian Mixture Model. Parameter restoration is designed to deal with arbitrary-long stationary target and solve the short-comings of the latest algorithm. The parameters among the K distribution of each pixel covered by the object will be restored when the object stayed for over threshold frames. Then the target will not be updated as a part of background model. Experimental results show that the proposed algorithm proves to be a more robust method by detecting the stationary target in an arbitrary-long time.
This paper presents a novel method for detection and recognition of glass defects in low resolution images. First, the defect region is located by the method of Canny edge detection, and thus the smallest connected re...
详细信息
This paper presents a novel method for detection and recognition of glass defects in low resolution images. First, the defect region is located by the method of Canny edge detection, and thus the smallest connected region (rectangle) can be found. Then, the binary information of the core region can be obtained based on a specific filter. After noises are removed, a novel Binary Feature Histogram (BFH) is proposed to describe the characteristic of the glass defect. Finally, the AdaBoost method is adopted for classification. The classifiers are designed based on BFH. Experiments with 800 bubble images and 240 non-bubble images prove that the proposed method is effective and efficient for recognition of glass defects, such as bubbles and inclusions.
Hypersonic vehicle has the characteristics of strong nonlinearity, time-varying, strong coupling and large flight envelope, which make the controller design extremely difficult. In this paper, the longitudinal dynamic...
详细信息
Hypersonic vehicle has the characteristics of strong nonlinearity, time-varying, strong coupling and large flight envelope, which make the controller design extremely difficult. In this paper, the longitudinal dynamic model of hypersonic vehicle is studied. Firstly, the linearized model around the equilibrium point is acquired and analyzed. Subsequently, a predictive controller is designed based on the linearized model to track the velocity setpoint under a certain flight condition. In order to extend the controller ability to large flight envelope, a multi-model switching based predictive control method is proposed. Simulation results show that the method could get better performance then single-model based predictive control.
Detecting motion pattern in dynamic crowd scenes is a challenging problem in computer vision field. In this paper, we propose a novel approach to detect the motion patterns from global perspective. To extract the disc...
详细信息
Detecting motion pattern in dynamic crowd scenes is a challenging problem in computer vision field. In this paper, we propose a novel approach to detect the motion patterns from global perspective. To extract the discriminative spatial-temporal features, we introduce the Motion History Image (MHI) into the optical flow algorithm. Motion patterns are then detected by automatic clustering of optical flow vectors through hierarchical clustering. Experiment evaluation on some challenging videos shows reliable detection results and demonstrates the effectiveness of our proposed approach.
This paper mainly deals with the issue of “staircase phenomenon” of delay-independently stable networked controlsystems (NCSs). There already exist works on this topic in continuous-time domain, this paper extends ...
详细信息
This paper mainly deals with the issue of “staircase phenomenon” of delay-independently stable networked controlsystems (NCSs). There already exist works on this topic in continuous-time domain, this paper extends the former result and deals with the more realistic discrete-time case. The definition of “staircase phenomenon” is given at first and the reason is analyzed. Then it is proven that if a NCS with traditional feedback structure is delay-independently stable, then “staircase phenomenon” in its dynamic response cannot be eliminated. This paper proceeds to prove that if a NCS which is delay-independently stable is introduced with scattering transformation, then its steady state error and “staircase phenomenon” in its dynamic response can be eliminated altogether by tuning the parameter of the transformation.
In this paper, a novel data-driven approach is presented to monitor processes influenced by gradual small shifts. The primary idea is to first build multivariate exponentially weighted moving average (MEWMA) model bas...
详细信息
In this paper, a novel data-driven approach is presented to monitor processes influenced by gradual small shifts. The primary idea is to first build multivariate exponentially weighted moving average (MEWMA) model based on the originally measured variables to keep the memory effect of the process trend. Then introduce a unified Mahalanobis distance based monitoring statistic, which makes full use of the feature of the normal distribution of the process variables, to better capture the deviation of the process variables. A case study of the Tennessee Eastman process (TEP) is used to demonstrate the superiority of the proposed method over other conventional ones in performance and workload of the gradual small shifts monitoring.
In this paper, an approach to design on-line robust model predictive control (RMPC) for time-delayed systems with structured uncertainties is proposed, where an uncertain time-varying input delay and multiple fixed st...
详细信息
ISBN:
(纸本)9781612844879
In this paper, an approach to design on-line robust model predictive control (RMPC) for time-delayed systems with structured uncertainties is proposed, where an uncertain time-varying input delay and multiple fixed state delays are included. By invoking the augmented state, a new system description with no input delay is introduced. For the resulting augmented systems with state delays, multi-step feedback control laws are utilized which guarantee both the satisfaction of input and state constraints and closed-loop stability. Finally a numerical example is given to illustrate the effectiveness of the proposed approach.
This paper we propose a multi-objective optimization model to deal with the capacity planning in semiconductor manufacturing system, which is a typical multi-objective problem. Unlike traditional optimization methods,...
详细信息
ISBN:
(纸本)9781424494408
This paper we propose a multi-objective optimization model to deal with the capacity planning in semiconductor manufacturing system, which is a typical multi-objective problem. Unlike traditional optimization methods, our model combines case-based reasoning with adaptive resonance theory and multi-objective genetic algorithm, in which some constraints such as maximizing profits, utilization of capacities, minimizing unmet demands etc are considered. An illustration shows how these techniques work effectively is also presented.
作者：
Ruimin BaoLanjuan ZhuDepartment of Automation
and Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Jiaotong University Shanghai China
In parallel with the quick expansion of embedded devices come the rapid growth of embedded software. The commonly used software developing methods can't meet the fast growing demands of variable software when conc...
详细信息
In parallel with the quick expansion of embedded devices come the rapid growth of embedded software. The commonly used software developing methods can't meet the fast growing demands of variable software when concerning user experience, cross-platforms, upgrade, hardware resources, etc. This paper proposes a new embedded software developing architecture based on the neural network organization and component principles. With the advantages of the network's dynamic weight adjusting and flexible self-learning structure, the approach can not only enable the software better adapt to the users' attributes, but also make the software be easily to extend and upgrade.
In this paper, a modified interval type-2 fuzzy T-S modeling method is applied to a heat exchange process on the equipment CE117 Process Trainer. First, subtractive clustering method combined with least square method ...
详细信息
In this paper, a modified interval type-2 fuzzy T-S modeling method is applied to a heat exchange process on the equipment CE117 Process Trainer. First, subtractive clustering method combined with least square method is employed to build the type-1 fuzzy T-S model. Then the type-2 fuzzy T-S model is obtained from the type-1 model through unconstrained optimization where the Nelder-Mead Simplex method is utilized. Finally, the results of the experiment prove the efficiency of the proposed algorithm.
暂无评论