Advanced Materials Research Vols. 850-851

Abstract: Moving object detection which is an important part of the digital image processing technology is research focus and difficulty in computer vision, pattern recognition, object recognition and tracking, moving image coding, security monitoring and other fields. It also has a wide application prospect in the military, national defense and industry fields. However, when there are large amount of moving targets and exercise conditions, the amount of data generated is also inestimable and target detection is a bottleneck in the data processing at the same time. The work of this paper is to simplify motion detection in optical flow constraint equation solving process and all the solving processes were constructed on GPU for fast speed, then it forms a fast moving target detection.

Abstract: Tracking moving objects in dual-view stereo system is becoming a hot research area in computer vision. To capture the moving objects pixels more accurately, we proposed a new object tracking algorithm which first compute moving objects feature points and then match these points, finally connect the matching feature points and get objects motion trajectories. The algorithm was tested in the video sequences with resolution 640×480 and 768×576 individually. The results show that the algorithm is more robust and the trajectories of the moving objects tracked with our method are more accurate compared with current method of L-K optical flow.

Abstract: The lip behavior detection is work foundation by utilizing video control software behavior, which including the lip positioning, feature extraction and behavior recognition. It is proposed that we utilize LBP operator to conduct lip feature extraction in this article, and adopt SVM to conduct classification and recognition of behavior. Experimental results show that the algorithm can effectively achieve detection and identification of lip behavior in the article, which meet the real-time and robustness in video processing.

Abstract: BP neural network is a hot research field for its powerful simulation calculation ability in various disciplines in recent years, but the algorithm has some shortages such as low convergence which limit the usage of the algorithm. The paper improves BP model with genetic algorithm and applies it to evaluate competitive advantages of logistics enterprises. First the paper designs an evaluation indicator system of competitive advantage of logistics enterprises through analyzing the characteristics of the evaluation indicator; Second, genetic algorithm is used to speed up the convergence of BP algorithm and based on this the paper advances a new competitive advantage evaluation model for logistics enterprises. Finally, the improved model is realized with the data from four Chinese logistics enterprises and the realization of the experimental results show that the model can improve algorithm efficiency and evaluation accuracy and can be used for evaluating the competitive advantages of logistics enterprises practically.

Abstract: Slicing reduction of a system is a technique, which advantage is that the detection can be performed on the part of the global state space which is of interest. In this paper, we present an algorithm which applies the slicing reduction technique to an algebraic verification method for SEREs properties. Due to slicing reduction, the algebraic verification algorithm only requires a part of state variables relevant to the SEREs properties, which can significantly improve the efficiency of the verification algorithm.

Abstract: In this paper, synchronization of a fractional-order system with unknown parameters is studied. The chaotic attractor of the system is got by means of numerical simulation. Then based on the stability theory of fractional-order systems, suitable synchronization controllers and parameter identification rules for the unknown parameters are designed. Numerical simulations are used to demonstrate the effectiveness of the controllers.

Abstract: Newton-Raphson method is used in global equilibrium for the numerical solution of elasto-plastic problems. It is necessary to determine the fourth-rank constitutive parameters of consistent tangent modulus in each integration point. Euler backward method and implicit stress integration is applied while constitutive model is implemented into ANSYS software. Take Chen, Jiao, and Kim model (2005) as an example, comparison of fourth-rank constitutive parameters and without fourth-rank constitutive parameters of consistent tangent modulus indicates that the convergence is obviously influenced by fourth-rank constitutive parameters of consistent tangent modulus for the larger load case, whereas the influence of plastic modulus is almost neglected.

Abstract: Current approaches for opening door usually focus on the recognition of door handle in a fixed position, but in the process of door opening, a manipulator with a mobile platform is very important under real-world scenarios, which brings significance to the location and distance measurement of a door handle when the mobile platform is moving. In this paper, a method for location of a door handle in HSI color space is presented. The image of the door handle is captured by the kinect for Xbox360, and is processed in HSI color space, resulting in a rectangle frame fitted to the door handle to be displayed in real time. The distance value of the door handle is obtained from the depth image. Experiment results show the efficiency of the proposed method.

Abstract: Niche is an important technique for multi-peak function optimization. When the particle swarm optimization (PSO) algorithm is used in multi-peak function optimization, there exist some problems, such as easily falling into prematurely, having slow convergence rate and so on. To solve above problems, an improved PSO algorithm based on niche technique is brought forward. PSO algorithm utilizes properties of swarm behavior to solve optimization problems rapidly. Niche techniques have the ability to locate multiple solutions in multimodal domains. The improved PSO algorithm not only has the efficient parallelism but also increases the diversity of population because of the niche technique. The simulation result shows that the new algorithm is prior to traditional PSO algorithm, having stronger adaptability and convergence, solving better the question on multi-peak function optimization.

Abstract: Core-drilling is the traditional pavement thickness detection method. However, this way is low efficient and destructive. The Ground Penetrating Radar (GPR) is a continuous, high efficient, non-destructive pavement quality testing tool. The dielectric constant, thickness and other information of pavement structure layer are obtained by inverse analysis of GPR echo signal. In this paper, the improved Particle Swarm Optimization (IPSO) is developed to analyze the dielectric constant and thickness of the pavement structure. Compared with inverse analysis results of theoretical model, the inverse precision of IPSO is higher than that of PSO. In addition, the measured echo signal of GPR is analyzed by the IPSO. The errors between inverse results and the actual core-drilling measurements are less than 3%.