Advanced Materials Research Vols. 774-776

Abstract: The nonsubsampled contourlet transform (NSCT) is not only with multi-scale and localization, but also with multi-direction, anisotropy and shift-invariance. A novel image fusion algorithm based on the NSCT is proposed in this paper, aiming at solving the fusion problem of images. Experimental results demonstrate that the proposed algorithm cannot only extract more important visual information from source images, but also effectively avoid the introduction of artificial information. It outperforms the traditional discrete wavelet transform-based and the Contourlet-based image fusion methods in terms of both visual performance and objective evaluation.

Abstract: This paper presents a genetic-based feature selection algorithm for object recognition. Firstly, the proposed algorithm encodes a solution with a binary chromosome. Secondly, the initial population was generated randomly. Thirdly, a crossover operator and a mutation operator are employed to operate on these chromosomes to generate more competency chromosomes. The probability of the crossover and mutation are adjusted dynamically according to the generation number and the fitness value. The proposed algorithm is tested using the features extracted from cotton foreign fiber objects. The results indicate that the proposed algorithm can obtain the optimal feature subset, and can reduce the classification time while keeping the classification accuracy constant.

Abstract: On-line measurement of fiber temperature based on monochromatic infrared thermometer has been introduced. Due to the probe field of view of monochromatic infrared thermometer being much larger than the fiber diameter, the measurement results is an average between the fiber and backgrounds, which can't be used to indicate the temperature of fibers directly. In this paper, a temperature calibration method has been introduced to decompose the measurement result of monochromatic infrared thermometer, and the calibrated results are compared to the measurement results of infrared thermography. It has been found that the on-line measurement with infrared thermometer could promise high-speed and highly reliable temperature testing for the fibers.

Abstract: The intelligent ultrasonic testing system possessing capabilities of defect tracking and defect simulated analyzing has been developed in this paper according to the characteristic of defects existing in weld connections in turbine runners. The passage then introduces the testing system from angles of structure, function and operation, respectively. Finally, the testing system is applied to an in-service turbine runner and the results indicate that desired efficiency and accuracy of detection in the testing system can be achieved and the mean error of the length for defects can be held within 5mm.

Abstract: Deployment and coverage, studied how to effectively place and control of sensor nodes and to make WSN covered the monitoring area with the purpose of minimum the energy consumption and prolonging the network life cycle under the premise of guarantee the quality of service (QOS),are the primary problems for construction wireless sensor network. This paper analyzes important factors for resolve the coverage problem such as sensing models and deployment way, followed survey the state-of-the art coverage contro1 techniques and presents an overview and analysis of the solution proposed in recent research literature, Further research directions are pointed out in the end.

Abstract: A faster algorithm for calculating the shortest distance between two spatial bodies based on existing algorithms was presented. A simulation analysis of missile models separation process was built by using this algorithm. The simulation proved that this algorithm has the same precision and faster speed compared with other existing algorithms.

Abstract: Support vector machine is a kind of machine learning algorithm which is based on statistical learning theory and VC dimension theory and structural risk minimization principle, it can solve data classification and regression problems. With the in-depth research of support vector machine, in the field of remote sensing image processing applications are also obtained the very big development. This paper first gives a brief introduction of the theory of support vector machine, and then summarized the progress in remote sensing image compression, geometric correction of remote sensing images, processing of remote sensing image data classification research, finally proposed the trend of the support vector machine in application and development in the field of remote sensing image processing problems.

Abstract: The paper mainly introduces the method of obstacle detection of autonomous land vehicle for geological prospecting. According to the categories and characteristic of obstacles, choosing the applicable sensor is the fundamental of accurately detecting obstacles. Data processing, including information collection, information processing and collecting characteristic parameter obstacle, is the difficulty for accurately detecting obstacles.

Abstract: In this paper, the diaphragms Mechanical property of Hot-film air flow sensor is studied on the base of proposition of double-sided convection heat air flow sensor. This diaphragm consists of barrier layer, support layer and passivation layer. For Hot-film air flow sensor, the Diaphragms Mechanical property is mainly up to the support layer, and the support layer is composed of Si₃N₄. In this research, four types of air flow sensors with different thickness of the support layer is prepared and tested at different air flow velocity. On the same time, the stress analysis of the sensor diaphragm is simulated at the flow rate of 5m/s by the finite element software. A conclusion can be drawn that the thickness of support layer can not be less than 1000nm, when the air flow velocity is more than 5m/s.

Abstract: According to the characteristics of the fringe patterns noise, came up with a small area spin filtering noise cancellation algorithm based on parallel marker technology. It means that preprocess the fringe pattern before spin filtering, then did a median filter and calculated the stripe direction, finally used the extract the fringe direction to spin filtering of the original image. The algorithm can marked several targets in scanning process at the same time. So it has a high efficiency. The algorithm can be used in the multi-frequency heterodyne phase shift technology .And we can use the technology to complete the measurement of complex surfaces. Experimental results show that the method has a distinct advantage in measurement accuracy, measurement speed, and noise immunity.