Applied Mechanics and Materials Vols. 397-400

Abstract: The definition of cepstrum analysis, diagnostic characteristics and the advantages of the method in gearbox fault diagnosis were introduced in this paper, and what are units and significance of horizontal and vertical coordinates of cepstrum was also analyzed , along with the cited examples of cepstrum analysis in gearbox fault diagnosis application .

Abstract: Moving target abnormity behavior identity technology is the one key base of Intelligent Video Surveillance. Object detection technology, target tracking technology, target classification technology has reached full development at present. About abnormity behavior identity technology, there have three technologies: template matching techniques, state-space techniques, Semantics Description techniques. Research situation of these technologies is introduced in this paper, and orientation of technological development of these technologies is also introduced in this paper.

Abstract: Traffic congestion detection is the basis of dynamic traffic control and real time guidance. This study proposes a fuzzy logic based traffic congestion identification method. The components of a fuzzy logic inference are firstly formulated. According to such information as the speed and occupancy of freeway traffic flow, and the weather conditions on the freeway, a congestion identification method based on fuzzy logic inference is then designed. Gauss curves are assumed for the membership functions of the input and output variables, and 45 fuzzy rules are also established. Finally, the congestion identification method is simulated. Simulation results verify the effectiveness of the above method. Fuzzy logic inference is suitable for estimating the traffic congestion index.

Abstract: Dark surrounds make detection of moving target more difficult based on traditional methods. A real time identification of fast moving object under weak illumination is critical for some special applications. Traditional blob, contour and kernel-based tracking methods either need high computational loads or require normal illumination which limit their application. In this paper, we propose a new method trying to settle such difficulty based on temporal standard deviation. The performance of new method was evaluated with simulation data and real video data recorded by a simple imaging system. Combining hardware acceleration, a real time detection and visualization of fast moving boundary in dark environment can be achieved.

Abstract: In acquisition and transmission procedures, images are often contaminated by noise in spatial and frequency domain. Image denoising is usually the first step in information extraction. At present there are many frequency domain denoising methods like low pass and high pass filtering but have not yet attained a desirable level. In this paper, we proposed a new denoising method based on Analogical Basis Deconstruction (ABD) theory. It uses only uncontaminated or slightly contaminated frequency data to recover the image through Asymptotic Iterative Estimate (AIE) algorithm. The performance of new method was tested on a simulation image and compared with the traditional frequency domain methods.

Abstract: A new approach for speech stream detection based on empirical mode decomposition (EMD) under a noisy environment is proposed. Accurate speech stream detection proves to significantly improve speech recognition performance under noise. The proposed algorithm relies on the Teager energy and spectral entropy characteristics of the signal to determine whether an input frame is speech or non-speech. Firstly, the noise signals can be decomposed into different numbers of sub-signals called intrinsic mode functions (IMFs) with the EMD. Then, spectral entropy is used to extract the desired feature for noisy IMF components and Teager energy is used to non-noisy IMF components. Finally, in order to show the effectiveness of the proposed method, we present examples showing that the new measure is more effective than traditional measures. The experiments show that the proposed algorithm can suppress different noise types with different SNR.

Abstract: With the social development, networking of information products is enhanced. Media asset management system as a resource management platform must evolve in order to better serve users. Combined with today's more widely used solutions to the industry popular media asset management system design for partial revision proposed optimized media asset management system design ideas.

Abstract: A mosaic method of based on rotational scan sequence cylindrical barcode which is suitable for metal parts is put forward, which combined the hardware and the software. Firstly, extract the feature points of each serial image based on scale-interaction of Marr wavelets. Then, get the optimal match of feature points with improved image local entropy. Lastly, complete the natural splice of the defect 2D bar code images through the algorithm of three interpolation and multi-resolution spline. The experimental results show that the algorithm could extract the feature points of consistent relative position and quantity after the processes of rotation, brightness, blur and nose, at the same time, assure the splicing efficiency and measurement precision of image mosaic. The method can also better finish the defect bar code recovery caused by curvature deformation.

Abstract: Image restoration is an important application of the digital image processing. Unlike traditional restoration algorithms that operate on a blurred image to recover the original, we propose a technique that the correction should be applied to the original image before blurring. To accomplish this, we approximate the Point-Spread-Function (PSF) of different defocus blur images by the circular disk. According to the estimated PSF, the original image is pro-processed based on Wiener filtering and High Dynamic Range (HDR) compression. Experiments results show that using this technique can help ameliorate the visual blur and the defocus images finally have a sharp vision.

Abstract: This paper presents a method to detect weak harmonic signal embedded in chaotic noise. Using different correlation characteristic of harmonic and chaotic signal ,we can transform the sample signal to a new data sequence which has new harmonic . The new harmonic frequency is m times of the original harmonic and beyond the center bandwidth of noise. Then use wavelet packet decomposition to analysis the energy distribution of harmonic and chaotic signals and extract the component which the harmonic energy concentrated on, In the end, a multiple signal classification (MUSIC) algorithm is employed to estimate harmonic frequencies . The method suit for the complex background noise (strong chaotic noise and gaussian noise).