Applied Mechanics and Materials Vols. 701-702

Abstract: In order to improve the robustness of visual tracking in complex environments, a novel multi-feature fusion tracking method based on mean shift and particle filter is proposed. In the proposed method, the color and shape information are adaptively fused to represent the target observation, and incorporating mean shift method into particle filter method. The method can overcome the degeneracy problem of particle. Experimental results demonstrate that this method can improve stability and accuracy of tracking.

Abstract: Aiming at the problem of common-frequency interference among gun-pointing radars, frequency agility technique was introduced. The reason why existing technique of frequency agility can’t investigate and identify common-frequency interference effectively was analyzed. A new frequency agility technique based on auxiliary channel and full-time reconnaissance and receiving is presented. Auxiliary channel investigates and identifies environmental signals full-time not intermittent, then uses microwave cancellation technique to eliminate local radar’s emission pulses. As a result, when auxiliary channel amplitude is greater than the main channel, it must be common-frequency interference. The above measures guarantee the accurate identification of common-frequency interference.

Abstract: Background subtraction, where the foreground is segmented from the background, is the first step of data analysis and processing in automated visual surveillance. Aiming to solve the problems associated with dynamic, multi-modal background, we explore a new approach which can handle the unconstrained environment. Based on multiclass support vector machines, a new MSVM is proposed for the classification of the background and the foreground. The simulation indicates our proposed algorithm is feasible.

Abstract: This paper propose a hybrid model which combine LBP and Meanshift for unmanned aerial vehicle image segmentation. In order to take full advantage of UAV image,The segmentation start with the over-segmentation regions,where the image divided into many regions by Mean shift. Then the small regions are merge with their neighbors by the hybrid distance with spectral, spatial and LBP histogram.

Abstract: A new recognition method of gait is presented in this paper. In this method, the feature vector of gait is found by multidistinguish analysis of wavelet transform, and gait is recognized by genetic algorithm (GA). This method is different from the traditional method of correlation matching recognition gait. First, the stored space reduces greatly because recognition model is used to replace the store of gait profile image template. Thus this method reduces stored memory greatly. Second real-time is ensured in the process of gait recognition by using GA. The experiments of recognition using the three kinds of gait databases are performed. The experiment results show the feasibility and effectiveness of the proposed method.

Abstract: Sea clutter is interference background in radar target processing. It is difficult to detect long-range weak target in sea clutter. Sea clutter signal changes complex, with high intensity. For close signal, radar receiver will overload and reach saturation point. We are interested in the most dynamic range for displaying target echo and fast changing component of clutter. By analyzing spatial and temporal correlation of sea clutter, slow changing component can be minus from sea clutter. The innovation of this paper is to propose a linear prediction error method for sea clutter to increase dynamic range of radar receiver. It prevents overloading and reaching saturation point at close range.

Abstract: Under existing conditions, the use of optical lens, imaging spectrometer, and the establishment of a rectangular CMOS image sensor spectral imaging system. Wide spectrum of white LED illuminated sample, by ordinary optical imaging lens, then the multi-channel narrowband filter array on the image plane splitting, and finally by the CMOS image acquisition system, converting optical signals into electrical signals, and then converted by the analog-digital converter chip to a digital signal to the computer. Finally, computer-spectral image cube collected for processing. At the same time, the advantages of airborne multispectral imager used in the UAV trials, obtain higher picture quality, and maintain a portable, imaging speed, and further validate the reliability of the experimental system.

Abstract: In the process of imaging, digitalization and transmission, images are generally contaminated by Gaussian noise and salt & pepper noise, which cannot be eliminated completely at the same time only by Mean filter or Median filter. Aiming at solving this problem, an improved hybrid median-mean filter algorithm based on the Improved Median Filtering (IMF) algorithm is proposed in this paper. The experimental results show that the new algorithm shows better performance than either Median filtering algorithm or Mean filtering algorithm, which can not only get rid of Gaussian noise and salt & pepper noise simultaneously, but also minimize the contradictions between noise erasing and image details protecting effectively.

Abstract: Dynamic environments often bring great challenges to moving object detection. Solving this problem will promote expansion of application fields of moving object detection. Unlike those background subtraction methods using local feature-based background models, inspired by integrity of human visual perception, we present a background subtraction method for moving object detection in dynamic environments, building its background models based on global features extracted by pulse coupled neural network. We employ the pulse coupled neural network to take good advantage of their global coupling characters, in order to imitate the human biological visual activity. After sensing images via the pulse coupled neural network, we extract global information of the scenes and then build background models robust to background disturbances based on the global features. Experimental results prove that, our method behaves well in terms of visual and quantitative evaluations for dynamic environments.

Abstract: In order to solve the problem of detecting harmonic and reactive currents of single-phase APF, the paper gives a detection method for real time harmonic current and reactive current. In the paper, it makes use of some characteristics of triangle function, and calculates the amplitude of active and reactive component from load current. Then the DC component can be extracted by using a low-pass filter, namely the required active component and reactive component. This paper analyzes the characteristics of two kinds of low pass filter, and selects the superior performance moving average filter for experiment. The paper introduces the design of the software and hardware process. The circuit configuration of the proposed approach used in the single-phase system is simple, its dynamic response speed is fast and its detection precision is high. The result of the experiment shows that the proposed approach is feasible and valid.