Applied Mechanics and Materials Vols. 347-350

Abstract: Autonomous overtaking maneuver is one of the toughest challenges in the field of autonomous vehicles. A key issue of autonomous overtaking maneuver is to find a dynamically feasible trajectory to avoid collision with the overtaken vehicle and surrounding hazards. Traditional trajectory planning algorithms assume that the initial and final vehicle states are given before and generate a trajectory for the whole overtaking process. However, overtaking maneuver is generally a time consuming process. Those assumptions may be invalid in highly dynamic environment. This paper tries to present a dynamic trajectory planning algorithm for autonomous overtaking maneuvers. The whole overtaking maneuver trajectory is made up of several short-time trajectories. Each short-time trajectory is generated by a kinematic vehicle model and taken into account of the surrounding environment and traffic rules. The concept presented in this paper is demonstrated through simulation and the results are discussed.

Abstract: This article presents a novel approach to extract robust local feature points of video sequence in digital image stabilization system. Robust Harris-SIFT detector is proposed to select the most stable SIFT key points in the video sequence where image motion is happened due to vehicle or platform vibration. Experimental results show that the proposed scheme is robust to various transformations of video sequences, such as translation, rotation and scaling, as well as blurring. Compared with the current state-of-the-art schemes, the proposed scheme yields better performances.

Abstract: In order to reduce the difficulty of adjusting parameters for the codebook model and the computational complexity of probability distribution for the Gaussian mixture model in intelligent visual surveillance, a moving objects detection algorithm based on three-dimensional Gaussian mixture codebook model using XYZ color model is proposed. In this algorithm, a codebook model based on XYZ color model is built, and then the Gaussian model based on X, Y and Z components in codewords is established respectively. In this way, the characteristic of the three-dimensional Gaussian mixture model for the codebook model is obtained. The experimental results show that the proposed algorithm can attain higher real-time capability and its average frame rate is about 16.7 frames per second, while it is about 8.3 frames per second for the iGMM (improved Gaussian mixture model) algorithm, about 6.1 frames per second for the BM (Bayes model) algorithm, about 12.5 frames per second for the GCBM (Gaussian-based codebook model) algorithm, and about 8.5 frames per second for the CBM (codebook model) algorithm in the comparative experiments. Furthermore the proposed algorithm can obtain better detection quantity.

Abstract: Function P-sets is a new mathematical model and structure, which is a new theory and method of studying the laws of dynamic information system. P-information law is the dynamic information law generated by function P-sets, which is information law pair composed of internal P-information and outer P-information law . Using the dynamic and law character-istics of P-information law, the study of attribute control and attribute control theorems of P-information are presented. Finally, the application of attribute control in image border information stabilization is given.

Abstract: Function P-sets (function packet sets) is a novel mathematics structure and model. P-information law is generated by function P-sets, which is an information law pair composed of internal P-information law and outer P-information law . Using the generation and structure of P-information law, the attribute dependence, attribute dependence measurement and attribute dependence theorem of P-information law are presented. Based on the results, the application of P-information attribute dependence is given.

Abstract: In the practical application of the Intelligent Transportation System (ITS), the collected and stored data through Nearest Neighbor Query can easily be contaminated by noise data. The reason is that the sensitivity of Nearest Neighbor Rules (NN Rules) to the noise data leads to the limits of Nearest Neighbor Query's practical application. To solve this problem, by using the insensitivity of Hypothesis Interval to noise data, this thesis improves NN Rules and proposes a classification mode of traffic data collection nearest neighbor rules. When the model predicts the samples, not only the distance from the test samples to the nearest neighbor is considered, but also the degree of the class to which this nearest neighbor belongs is taken into account.

Abstract: The cannon can not driving in line when tire blow out, the distance of sideslip affects the safety of cannon. To solve this problem we design a safe explosion-proof tire internal supporter tire. The simulation model of cannon established by RecurDyn, compared the ordinary pneumatic tire and inner support when cannon equip different tire, we get the cannon in the process of driving dynamics characteristic, it provides theory for the internal support tire equipping.

Abstract: In this paper a signal detection technique based on pilots which are transmitted for channel estimation in OFDM system is proposed in AWGN channel. We analyse the algorithm based on pilots and derive an improved signal detection technique. The performance is compared in terms of detection probability and ROC curves are given. The simulation results show that the improved detection technique whose computational complexity is not high can increase the precision of the detection probability at low SNR.

Abstract: An retrieval algorithm based on dimensionality reduction is proposed to effectively extract the features to improve the performance of image retrieval. Firstly, the most important properties of the subspaces with respect to image retrieval is captured by intelligently utilizing the similarity and dissimilarity information of semantic and geometric structure in image database. Secondly, We propose Semi-supervised Orthogonal Discriminant Embedding Label Propagation method (SODELP) for image retrieval. The experimental results show that our method has the discrimination power against colour, texture and shape features and has good retrieval performance.

Abstract: In respect of the classification of current image retrieval technology and the existing issues, the paper put forward a method designed for image semantic feature extraction based on artificial intelligence. The new method has solved the tough problem of image semantic feature extraction, by fusing fuzzy logic, genetic algorithm and artificial neural network altogether, which greatly improved the efficiency and accuracy of image retrieval.