Advanced Materials Research Vols. 846-847

Abstract: This paper focuses on the data processing modeling for reference materials preparation. By analyzing the data of reference materials (RMs), the process of repeatability and stability verification, uncertainty estimation, traceability of the value of a quantity and the characterization of RMs are detailed in the paper.

Abstract: Face contains the very rich information, which is a typical biological feature .It has a wide application prospect in personal identification, intelligent video surveillance and human-computer interaction. Face detection is to determine the number, the location, size and other information of all the faces among the color images that have been input. Firstly, skin color model is established, and then we use the skin color model to convert color image to gray image, and then we can denoise gray image, at last use the Fisher criterion to obtain the dynamic threshold segmentation of the face image, so as to lay a good foundation for the location of the face region. Through the experiment we can see, the selection of dynamic threshold, for different detecting images, obtained better color segmentation.

Abstract: Identification and amendment dangerous driving behavior timely and accurately is a necessary means to reduce traffic accidents. This paper proposed a dangerous driving behavior identification method based on neural network and Bayesian filter. By using vehicle-mounted radars and cameras obtain movement state information of the vehicles around the host vehicle and lane line distance data, on the basis of which, the identification model is established. Then evaluate model performance by the real data. The test results show that after the correction of neural network output by Bayesian filter, the model accuracy has a sharp rise.

Abstract: According to the problem that the whole data and information is always necessary, using rough set theory as a guide, making some analyses on reduction in knowledge base and information system, this paper propose a general mode structure of reduction. It shows that there are three terms in process of reduction and the most important term is definition and measure of ability.

Abstract: Classification of lettuce growth peroid is the premise of records of lettuce growth information. In this study, lettuce images in every growth period are collected. And visible images are preprocessed to extract features to establish initial feature library of lettuce images. Through R cluster analysis on many features, good image eigenvector are obtained. Classification of the lettuce samples are obtained by modeling and analysis of the neural networks. The experimental classification results compared with practical classification results, the recognition accuracy is up to 88.4%.

Abstract: The principles of using computer parallel calculation method carries out in-depth analysis and research for computer art photography virtual imaging technology, and carries out image processing experiments for the artistic image rendering, we can get better art photography image processing effect. Combined with photography image virtual image mathematical model, this paper designs a computer program of photography image art rendering, and carries out art rendering for a landscape painting, we can get ideal art modification effect. Finally, this paper begins to calculated results for the parallel computing of art photography rendering, the calculation is found that the parallel computing is less time-consuming than general algorithm and with the increase of pixel time-consuming increased gently, it doesnt appear large fluctuations. For an image of the same resolution to carry on data processing, the general algorithm takes 55 seconds to complete the task. For parallel computing, it needs to3 seconds to complete, greatly saving time and computer resources, and providing the theory reference for the development of artistic photographys virtual image technology

Abstract: With the rapid development of multimedia communications and the computer network technology, video information has a rising proportion in multimedia information. It owns the great amount of data so that it can obtain accurate information for needed video retrieval research, which has become one of the hot topics of research in this field. By taking soccer video for example, this paper firstly analyzes structure of the soccer video and framework structure. Based on this, this paper makes a specific analysis on the extraction of soccer video feature by combining with the literature to apply SSD apparent characteristic. And then, assisted by the improvement of Hidden Markov Model (HMM), this paper constructs the second frame differential method to detect the shot of soccer video. The test results show that the precision of this method is higher in close-up and misjudgment slow motion. However, it has certain leak detection in slow motion replay of high speed movement.

Abstract: There are plenty of intelligence algorithms and heuristic algorithms for TSP (Traveling Salesman Problem). In this paper, local optimization algorithm which is a good representative of heuristic algorithms was analyzed. The performance of 2-opt (optimization), 3-opt and 4-opt were analyzed and compared through experiments. To reduce running time and improve their feasibility, a modification was made on 3-opt and 4-opt. Ant colony optimization as a good representative of intelligence algorithm was combined with k-opt to analyze. The results provide reference to application of k-opt and designing optimization algorithms for TSP in future.

Abstract: The traditional Tactical Internet (TI) simulative training didnt consider the terrain environment and maneuver simulation, so its fidelity was low. The paper aimed to resolve it. Firstly, the paper gave the modeling process of TI terrain environment, and put forward the corresponding ways to some parts of the modeling process. Secondly, the paper gave the optimization steps of TI terrain model, it improved the simulation running efficiency; and then the paper utilized the large area database management technique to solve dynamic loading and rendering problem of large terrain model. Lastly, the paper gave the maneuver simulation way to the communication vehicles of TI, it solved the problems of maneuver collision and precise maneuvering along the road. The paper presented the realization results in each part, and it proved the effectiveness of the given ways.

Abstract: An optimized collision detection algorithm based on dynamic bounding volume tree is proposed in this paper. First this algorithm adopts spatial division to exclude objects which cant intersect to define the potential intersection areas. Then use a new dynamic OBB bounding volume tree to test whether the intersection happened between the objects in the same grid. At last, this algorithm improves the traditional overlapping test between the primitives for accurate collision detection to accelerate the detection between objects. Compared to the traditional collision detection algorithm based on OBB bounding volume. This algorithm can effectively improve the real-time of the collision detection without affecting the accuracy of original collision detection.