Applied Mechanics and Materials Vol. 740

Abstract: Transportation vehicle tracking systems need to equip with a tracking algorithm with not only good tracking accuracy, but also fast computation speed to meet the real time changes of vehicles. l₁ tracker has good tracking accuracy, but the high computational complexity limits its application in real-time systems. In order to solve this problem, this paper proposed a novel algorithm that utilize compressive sensing to reduce dimensions and improved Sparsity Adaptive Matching Pursuit (SAMP) algorithm to rebuild the coefficients of templates. The experimental results show that the l₁-FSAMP algorithm not only improves the running speed, but also reduces the average tracking errors by 83% compared to the l₁-OMP algorithm. The results show that the proposed algorithm is suitable for practical real-time tracking of transportation vehicles.

Abstract: Temperature sensing cable was mainly used for simultaneous detection of multi-point temperature of the measured object. It was widely used not only in industrial areas, such as the detection of cable temperature access to facility, but also in the agricultural sector, such as the greenhouse temperature testing. Conventional temperature sensing cable was mainly linear temperature sensing switch cable, and the transmission of data was also wired, so in practical applications, this temperature sensing cable had many disadvantages. In this article, the digital temperature sensor DS18B20 manufacturing temperature sensing cable was studied and researched, ZigBee technology was used for wireless transmission, and a high efficiency, low cost, wide application of the monitoring network was established to develop a new temperature sensing cable.

Abstract: Modified Prandtl-Ishlinskii model is a phenomenological model widely used to characterize and compensate the hysteresis nonlinearity of piezoelectric material or magnetostrictive material. In addition, the identification method is the key section to determine the accuracy of the model. In this paper, mathematical principles of 3 identification methods are appealed and compared, then effects of the model are examined under 10Hz excitation frequency.

Abstract: Video quality impairments mainly caused by noisy transmit channel. No-Reference evaluating method is an important way to predict the video quality due to without any other loader to the transmit channel. Aiming at improve the accuracy and effectiveness of No-Reference video quality evaluating model, a novel variable-weight evaluating model is proposed. Motion intensity is introduced to qualify the variation of video content. And a weight control function is obtained based on the statistic studying method. Then the weight of clearness and smoothness can be adjusted in real time through the weight control function. The variable-weight evaluating model takes into the human perceptual properties. The experimental results show that the variable-weight evaluation model outperforms the existing evaluation models and achieves high correlation with the subjective test results.

Abstract: Aiming at the problem of color image two value segmentation, present an improved two value plant image segmentation method based on fuzzy clustering theory. In the light of the problem that fuzzy clustering algorithm is difficult to segment the low SNR image, improve Membership function; Aiming at the problem that image pixel information is too large, mapping image information to the gray feature space, treat the same gray pixel as a whole, improve operation efficiency. The experimental results show that, the improved algorithm has stronger anti noise ability, higher segmentation accuracy, shorter operation time, has good prospects for engineering applications.

Abstract: A new algorithm of video watermarking based on changed area is studied in this paper. We propose a method to located area which pixels change greatly from three successive frames of uncompressed video by using three-frame differencing. Then we choose the region where changes drastically to embed watermark by using the Quantization Modulation algorithm in DCT coefficients. In order to have a good performance on video quality and embed more information, we divided the binary watermark into two parts which obtain a logistic Arnold transform before being embedded. The experimental results indicates that the proposed scheme has a good performance to frame dropping, frame cropping, frame rating, Gaussian noising, MPEG2 compression, etc. and it has a advantage on little degrading the video quality.

Abstract: In order to achieve fast and accurate face recognition, firstly, this paper extracts face contour lines based on face contour feature to achieve treat a human face shape classification, thereby reducing the measured face search range. Secondly, using the method of Gabor wavelet to extract local texture on face when range was approximately determined, then matching with the face library whose range has been narrowed. Experiments show that this parallel approach not only achieved rapid recognition, but also achieve a high recognition rate due to a combination of the two methods.

Abstract: According to the principle and the method of initial alignment of strapdown inertial navigation system, proposed based on Sage-Husa adaptive kalman filter algorithm. The measured simulation data, compared with those of kalman filtering algorithm, show that the optimized algorithm can optimize the noise estimation, revise accumulated error of strapdown inertial navigation system, and greatly improve the navigation accuracy.

Abstract: The accurate prediction model’s establishing of the blast furnace coke rate is important for optimizing the integrated production indicators of iron and steel enterprise. For the problem of accuracy of the model of coke rate, This paper established blast coke rate modeling with support vector machine algorithm, the model parameters of support vector machine was optimized by genetic algorithm, then a coke rate model based on support vector machine with the best parameters was built. Simulation results showed that: the forecasting model’s outcome, average absolute error and the mean relative error, was small which is based on genetic algorithm optimized SVM. coke rate model based on Genetic algorithm optimized support vector machine has high degree of accuracy and a certain practicality.

Abstract: This article describes the classification of China bank check, green fluorescent reaction under ultraviolet light source illumination of the featured regions—— invisible flower mission and motif pattern, and recognize the accuracy of detecting bank check feature area by signal processing and pattern recognition of UV green fluorescent response signal receiver at particular locations. It described the light filter for bank check, which is different from RMB Banknote