Applied Mechanics and Materials Vol. 610

Abstract: Image edge details contains a rich amount of informations, enhancing edge details is the key of image post-processing. Traditional enhancement methods often lead to edge detail information lost. Fortunately, we find the curvelet transform good performance to reflect the detail information in the edge. In this paper, we add Wrap step to USFFT algorithm based on the Fast Discrete Curvelet Transform (FDCT), and adopt cyclic shift method and Er iteration. At the same time, we adopt adaptive threshold method. In order to get the objective evaluation result, comparing the wavelet algorithm and FDCT to the proposed method, we select peak signal-to-noise ratio. Experimental results show that the proposed method is not only superior to wavelet method, but also superior to single FDCT in the edge and detail information preservation.

Abstract: A topic discovery approach of the image has been proposed. First, the training images are segmented into some blocks. After clustering blocks, we obtained class set generated by cluster centers, and extracted all nouns from text annotation of each training image to obtain a keyword set. Secondly, the un-label testing image is also segmented into some blocks as same as training images, we calculated the correlation between the block and keyword, and the keyword set for each block may be obtained. Finally, the number of the same keyword appearing in the each block is calculated, we let the keywords with maximum to appear times be as the topics of the image. The experimental results confirm that proposed approach for the image is effectiveness and has good performance.

Abstract: In reference to telemetry data processing, an improved method is presented, which makes use of telemetry data that the conventional method abandons. Qualitative analysis is made to show the advantage of the improved method. Simulation results indicate that the improved method can obtain 1~3dB gain, better than the conventional method.

Abstract: Due to the characteristic of remote sensing image, we propose a novel method based on K-means algorithm also with the improved multi-phrase level set model. Comparing with the classical multi-phase C-V model, the improved model considers the region area information, gradient information and edge detection .Proper use of gradient information can overcome the inaccurate edge localization defects in image segmentation. The edge detection is used for keeping the boundary information better in the evolution process .For the reason of picking up the contour’s convergent speed and enable the avoidance of trap .Four stages are constructed. Firstly, a median filtering is applied to smooth the original image and reduce parts of noise. Secondly, the usage of K-means algorithm gains more obvious differences of characteristics. Next, the reconstruction of gradient is obtained by using Sobel operator. Finally, segmentation result is achieved by using an improved method of multi-phase level set image segmentation. Experimental results show that the proposed approach has advantages in rapid and efficient application of remote sensing image segmentation.

Abstract: Image segmentation is an important research subject in the area of image processing. Most of the existing image segmentation methods partition the image based on the single cue of the image, the color, which brings a serious limitation when the complex scenes involve in the natural images. In this paper, we introduce a novel unsupervised image segmentation method via affinity propagation which takes into local texture and color features with superpixel map. The new method fuses color and texture information as local feature of each superpixel. The experimental results show that the proposed method performs better and steadier when partitioning various complex nature images, comparing to the existing methods.

Abstract: Directed at the defects of time-consuming feature points extracting and out-of-sync between matching feature points and processing video frames in the original SURF (Speeded Up Robust Features) algorithm in mobile pattern recognition applications. For these shortcomings, this paper proposes an improved SURF algorithm. The algorithm uses buffer mechanism. An adaptation threshold is used when extracting feature points. Experimental results show that using the improved SURF algorithm in mobile applications has achieved the purpose of real-time processing. It has certain values in both theory and practice.

Abstract: In this paper, we researched a vehicle terminal-based Intelligent Travel System. We gave the overall design of the system architecture, and gave the function of each module. The system could provide users with personalized service focus on users’ preferences and user-based personalized intelligent location information service. We proposed recommendation algorithm focus on user-based personalized intelligent location information, built a set of strong association rules, and optimized foundation algorithm. The results showed that the optimized algorithm had better performance and could satisfy the user’s personalized travel needs.

Abstract: Analyzing the attractiveness of point-of-interests (POIs) in a city is very important to business location selection, market analysis, traffic management, and urban planning. Recently Analyzing the attractiveness of POIs based on GPS data calls scholars’ attention. However, the existing methods ignore the variation of POI’s attractiveness owing to its categories and the time-slots. Therefore, we propose a novel approach of analyzing POIs’ attractiveness variation based on taxis’ trajectories. According to the situation of taxis’ stopping nearby the POIs which belongs to certain categories in different time-slots, we can compute the POIs’ attractiveness. Furthermore, the law of citizens activity can be analyzed and provide reference to urban planning.

Abstract: The effective control of high-vibration intensity frequency and its overtime and over-limited is a bottleneck technology of chaotic vibration machine to finish specific operation. A PLC advance control system based on intelligent frequency is developed. Prediction of the possible vibration intensity extreme points and its distribution are processed data mining and prediction by sensor signal amplification, analog-digital conversion, and online monitor. Moreover, advanced control of the overtime and over-limited vibration intensity is achieved by constraint conditions correction and real-time feedback. The advanced control results can be verified by comparing grinding effect of conventional vibration mill with that of advanced control vibration mill. Further, the deaggregation and refinement of super-hard and superfine grinding can be achieved.

Abstract: In order to realize the industrial computer can control automatic adjustment of linear motor, design the linear motor control scheme based on virtual instrument technology. System driven by the control card of GE series, based on the LabVIEW development platform, realizes the intelligent control of linear motor.