Advanced Materials Research Vols. 271-273

Abstract: BCI systems can use additional intelligence such as machine vision or obstacle avoidance routines to provide a goal-oriented approach. This paper describes a P300-based BCI system to control a small robotic arm. On the robot arm's gripper a small camera was mounted continuously capturing images from the environment. The software waits for a character from the P300-based BCI speller to turn either clockwise or counterclockwise. Once turning the image detection software automatically searches for the colored object and delivers it to a preset target location. Results showed that the BCI system performed fast and accurate.

Abstract: This paper produced for the distortion caused by the edge bluring in the image inpainted, proposing a novel no-reference quality assessment based on the human visual property. Using visual sensitivity function CFS which descripes the properties for human visual to weight noise image detected, acquiring the value for the no-reference assessment that is consistent with the subjective evaluation, the experiment has proved no reference, flexibility and consistent with the human appraisal.

Abstract: In a disaster field, to obtain the optimal path in unknown environment,a rescue robot needs to build an environment map. Sensors mounted on the robots cooperate to monitor the environment, the information of the disaster field is collected by the sonsors of different robots, all signal from sensors (mounted on all robots and signal form GPS) are sent to the bakeside parllel processors with wireless network. A grid computing environment serves as the backside parallel processors with Globus Toolkit, the grid computing processor process all the signals and construct the global map to help robot for navigation path planning.The rescue robot get control signal from the grid computing processor with wireless network,thus, the robot is not necessary to be sophisticated. New computing methods are given for parallel algorithm on grid environment.The experiments show that the method is more practical and helps the path planning problem to be solved more efficiently, the advantages of large seale computing on grid are shown.

Abstract: A method for license plate location based on Twin SVM is proposed in this paper. Firstly, the mathematical models of Twin SVM are introduced, and then the feature extractions of license plate image are discussed, finally it is proved that this location method is very precise and efficient by experiments in VC development environment.

Abstract: With emergence of online virtual reality applications, the 3D data of virtual scenes are available to heterogeneous end user devices with relatively limited computing power, resolution and transmission rate. Still, many virtual scenes created by expert developers are composed of complex 3D data models with huge number of geometry primitives and appearence elements. This complexity can cause a lot of problems when the scenes are deployed on the limited access devices. To address this issue, we propose a virtual scene adaptation framework which is able to perform the transformation of given complex 3D model into new forms with less geometric and appearance data. Through the framework, complex virtual scenes are connected with real-world semantics and are preprocessed with selected optimization strategies based on the semantic features matching client devices’ capabilities before deployment.

Abstract: Traditional ASM (Active Shape Model) methods usually depend heavily on the initial facial landmark positions located by the face detector. During the fitting process the ASM model may be trapped into local optima instead of the global optima due to the inaccurate initial position selection. In this paper we present that this problem can be solved by incorporating pupil and chin localizations in adjusting the initial landmark positions, together with adaptive step length selection based on two-dimensional gradient characteristic in a multi-scale ASM model. Experiments on a face database consisting of 1000 individuals show that this method is practically effective.

Abstract: Based on the sliding mode variable structure control theory, the sliding mode control algorithm is proposed for a nonholonomic mobile robot system. The Lyapunov function and exponential approximation law are used for designing the control law of the mobile robot. And the binocular stereo vision method is proposed for the four wheeled AGV to implement the obstacle detection and the depth calculation. Finally, the control law is designed and simulated by the proposed algorithm for the wheeled mobile robot, and the simulation results show that the proposed algorithm is efficient, and also can reduce the chattering of the system, and in the experiment the four wheeled mobile robot can also successfully detect obstacles.

Abstract: This paper describes an eye naked 3D display cube, which can track a viewer’s position and render the stereo perspective scene in each display surface. The viewers can look the details of 3D models and scenes from any viewpoints. It seems as the real 3D objects lay in the display cube. It supports multi-viewer interactive in one scene. The viewers also can see the position of each other in own screen. They can co-operate in the same scene, although their field of view is independent of each other. The technologies of 3D perspective rendering, marker tracking and image processing are used for the 3D display cube.

Abstract: A number of different classifiers have been used to improve the precision and accuracy and give better classification results. Machine learning classifiers have proven to be the most successful techniques in majority of the fields. This paper presents a comparison of the three most successful machine learning classification techniques SVM, boosting and Local SVM applied to a cancer dataset. The comparison is made on the basis of precision and accuracy along with the training time analysis. Finally, the efficacy of the classifiers is found.

Abstract: This paper proposes a special Chinese automatic summarization method based on Concept-Obtained and Improved K-means Algorithm. The idea of our approach is to obtain concepts of words based on HowNet, and use concept as feature, instead of word. We use conceptual vector space model and Improved K-means Algorithm to form a summarization. Experimental results indicate a clear superiority of the proposed method over the traditional method under the proposed evaluation scheme.