Advanced Materials Research Vols. 694-697

Abstract: Proposed an approach to identify vehicles considering the variation in image size, illumination, and view angles under different cameras using Support Vector Machine with weighted random trees (WRT-SVM). With quantizing the scale-invariant features of image pairs by the weighted random trees, the identification problem is formulated as a same-different classification problem. Results show the efficiency of building the randomized tree due to the weights of the samples and the control of the false-positive rate of the identify system.

Abstract: Based on the research of PCNN algorithm,details the basic idea of the genetic algorithm, introduction of genetic algorithm for optimal family.In order to verify the effectiveness of the algorithm,implements the algorithm and comparison algorithm on the PC with the VS2008, CUDA, OpenCV 2.2.The experimental results showed that:Improved PCNN algorithm to better deal with the multi-modal regional background,improve the accuracy of moving object segmentation.Effectively filter interference prospects at the same time,complete retention of the shape, the edge information of the moving object.In this paper, the improved genetic algorithm can guarantee the quality of motion detection, and provide a guarantee for the the subsequent image recognition accuracy.

Abstract: A method was presented which was based on Wavelet Transform and Embedded Hidden Markov Mode (EHMM). The proposed algorithm can reduce the affections such as illuminations which affects the recognition rate using the method of Principal Components Analysis (PCA).Analyzed the critical problems that affect recognition rates in Wavelet Transform. Experimental results show that the presented method can get better results.

Abstract: The paper introduces Laplace pyramid, Ridgelet and Curvelet principle, structure and methods, and their denoising experimental studies. It also introduces the traditional direction filter of principle, structure and methodology, and the simulation experiments show that its image denoising PSNR is slightly lower than wavelet but denoising image visual quality is better than former. To that end, proposed a new direction filters that uniform direction filter banks and non-uniform direction filters, proved filter passband condition and related design and implementation issues were discussed. nonlinear experiment shows that the new direction filter bank was better than the wavelet.

Abstract: This paper proposes a novel algorithm of 3D temperature field reconstruction for flame. Shape of the flame is determined by visual hull technology first, and then the flame is divided into voxels, 3D temperature field is achieved after computing temperature for each voxel. Extended dynamic range irradiance images are generated in order to minimize the error of temperature field caused by overexposure or underexposure. To further improve the accuracy of the temperature field, integral operation for radiant existence of flame on camera response band is performed. The computational complexity is efficiently reduced with the lookup table between temperature and radiant existence. Calculation of flame temperature field is transformed into a convex optimization problem. Experimental results show that our algorithm is simple and flexible, and easy to implement, the results accord with physical facts

Abstract: A new image encryption algorithm based on chaotic sequence is proposed, and the over sampled techniques is used in the Chebyshev mapping and Logistic chaotic mapping to generate multi-parameter chaotic key.A chaotic image encryption transmission system is build to achieve the encryption and decryption of the image signal,and the security and the encryption properties of the algorithm are analyzed. Simulation results show that the method ia simple and easy to achieve, and with larger key space ang good encryption effect.

Abstract: According to the detection of moving objects in video sequences, the paper puts forward background subtraction based on Gauss mixture model. It analyzes the usual pixel-level approach, and to develop an efficient adaptive algorithm using Gaussian mixture probability density. Recursive equations are used to constantly update the parameters and but also to simultaneously select the appropriate number of components for each pixel.

Abstract: In this study is relevant to cell area extraction for cytological diagnosis of liquid-based cell examination being used for early diagnosis of uterine cervical cancer by utilizing image processing. As existing cytological diagnosis process has been performed manually by cytotechnologist, the amount of cell image that could be processed was limited. Therefore, in this study, cellular domain extraction through which automatic processing of cytological diagnosis process is enabled was performed and its condition was established depending on the size of cell nucleus based on cytological diagnosis standard of uterine cervical cancer cell. Obtained cell image was processed by hough transform matching with cell image by using matlab through preprocessing phase. As a result, 28 sample images among total 30 sample images were succeeded in finding out target cell and two sample images failed to find it. In the future, modification and verification for such failure case may be required to be performed. It is expected that the result of this study could be utilized for diagnosis process automation of liquid-based cell examination.

Abstract: Based on two-degrees-of-freedom (2-DOFs) quarter-car semi-active suspension model, a method for semi-active suspension control is proposed based on immune algorithm. According to this algorithm, an immune controller is designed to research and simulation for semi-active suspension control. Simulation results show that the proposed algorithm is effective，and compared with the passive suspension and fuzzy logic control (FLC) algorithm, its control capability is the best. Using immune controller, the RMS of body vertical acceleration, tire loads and suspension distortion are significantly reduced, so vehicle ride performance, handling stability are effectively improved.

Abstract: Based on the test scheme and principle of armoured vehicle fire control system, proposes electrical measurement method unite gyros method to test armoured vehicle fire control system; Established the processing model of gun drifting, stability accuracy, gun transfer speed, intergrade quality; according to the gyros drifting problem, proposes drift trend arithmetic to enhancing the accuracy of measuring system.