双目系统全视域采样的SVM标定模型分析

目的 为改善摄像机间接标定采样不全、模型表达模糊问题,实现小视场下检测视域完备采样,提出一种基于双目系统全视域采样的支持向量机（SVM）标定方法。方法 该方法利用六角晶格标定板靶点序号可读特点为基础,采集整个双目系统有效视域中检测点的视差坐标、世界坐标并建立完备的样本集。选取SVM对该样本集进行训练,将SVM算法得到的模型参数代入其决策函数中进行求解,获得公式化的标定模型。由于六角晶格标定板的四角和中心分布了5个互为非中心对称的多边形,可在标定板部分区域被采集的情况下获取标定板位姿信息,进而读取采集的各靶点序号。通过上下移动标定板,利用HALCON算子获取图像中各靶点的序号,建立双目视觉系统检测区域的完备样本集。最后,利用SVM算法训练样本获得标定模型,可以明确表达出标定模型的数学形式。结果 与传统采样建立的模型进行对比分析,实验结果表明该方法建立模型的标定误差减小了24.51%,降低了标定模型在传统方法未采样区域的标定误差,证明了该方法的可行性。结论 提出一种基于双目系统全视域采样的支持向量机标定方法,通过非中心对称的多边形确定标定板上靶点的序号,实现双目视觉系统检测视域的完备采样。实验结果表明该方法提高了摄像机间接标定的精度,具有良好的适用性和鲁棒性,适用于小视域内双目视觉系统的间接标定。     

基于加权支持向量机的凸轮升程误差拟合方法

针对凸轮磨削加工过程中存在局部升程误差严重超差的问题,提出了加权支持向量机的凸轮升程误差补偿方法。首先根据圆率的符号判断凸轮升程误差值是否连续,然后建立了不连续点与相邻点之间夹角与加权值的关系。通过加权支持向量机对凸轮升程误差值进行拟合。然后将原始凸轮升程值减去经拟合后的凸轮升程误差值,获得新的凸轮升程值。再根据圆率自动调整加权值的系数,使凸轮升程值光滑点数最大,即获得最优的凸轮升程值。对上述算法进行仿真和编程,经YTM8336-16数控凸轮轴磨床进行磨削验证。实验表明,凸轮升程误差由原来的±0.059 mm降至±0.011 mm,表面粗糙度由Ra0.32μm降至Ra0.25μm,获得良好的效果。     

一种基于Matrix的QR分解向量化方法

提出一种基于Matrix的Givens旋转的QR分解向量化方法。针对Matrix的体系结构特点,对向量数据访存和计算进行优化,使计算均衡分布到各个向量处理单元;设计双缓冲DMA的数据传输策略,使得内核的计算与DMA数据搬移的时间完全重迭,内核始终处于峰值计算,从而取得最佳的计算效率。实验结果表明,该方法能够取得较高的计算效率和性能加速比。     

移植Libsvm软件实现TMS320F28335的支持向量机

化简了支持向量机算法在实际应用中的步骤,提出了利用分解和提取代码的方法在TMS320F28335芯片中移植Libsvm软件,并实现了支持向量机.该方法解决了在C2000系列DSP芯片中实现支持向量机的问题,同时适用于其他型号的芯片.实验结果表明,在保证较高的预测正确率、较快的运行速度和较大的数据量读取的前提下,Libsvm能够正确运行于芯片中.     

A wide view auto‐stereoscopic 3D display with an eye‐tracking system for enhanced horizontal viewing position and viewing distance

This paper describes the development of auto‐stereoscopic three‐dimensional (3D) display with an eye‐tracking system for not only the X‐axis (right–left) and Y‐axis (up–down) plane directions but also the Z‐axis (forward–backward) direction. In the past, the eye‐tracking 3D system for the XY‐axes plane directions that we had developed had a narrow 3D viewing space in the Z‐axis direction because of occurrence of 3D crosstalk variation on screen. The 3D crosstalk variation on screen was occurred when the viewer's eye position moved back and forth along the Z‐axis direction. The reason was that the liquid crystal (LC) barrier pitch was fixed and the LC barrier was able to control the only barrier aperture position. To solve this problem, we developed the LC barrier that is able to control the barrier pitch as well as the barrier aperture position in real time, corresponding to the viewer's eye position. As a result, the 3D viewing space has achieved to expand up to 320–1016 mm from the display surface in the Z‐axis direction and within a range of ±267 mm in the X‐axis direction. In terms of the Y‐axis direction, the viewing space is not necessary to be considered, because of a stripe‐shaped parallax barrier.     

Adaptive actuator failure compensation for multivariable feedback linearizable systems

A feedback linearization‐based adaptive control scheme is developed for multivariable nonlinear systems with redundant actuators subject to uncertain failures. Such an adaptive controller contains a direct adaptive actuator failure compensator to compensate the uncertain actuator failure, a nonlinear feedback to linearize the nonlinear dynamics, and a linear feedback to stabilize the linearized system. The key new design feature is the estimation of both the failure patterns and the failure values, for direct adaptive actuator failure compensation, newly developed for multivariable feedback linearizable nonlinear systems. With direct control signal adaptation, the adaptive failure compensation design ensures closed‐loop stability and asymptotic output tracking in the presence of actuator failure uncertainties. Simulation results from an application to attitude control of a near‐space vehicle dynamic model are presented to verify the desired system performance with adaptive actuator failure compensation. Copyright © 2015 John Wiley & Sons, Ltd.     

Joint underwater target detection and tracking with the Bernoulli filter using an acoustic vector sensor

In this paper, we study the problem of joint underwater target detection and tracking using an acoustic vector sensor (AVS). For this challenging problem, first a realistic frequency domain simulation is set up. The outputs of this simulation generate the two dimensional FRequency–AZimuth (FRAZ) image. On this image, the random finite set (RFS) framework is employed to characterize the target state and sensor measurements. We propose to use the Bernoulli filter, which is the optimal Bayes filter emerged from the RFS framework for randomly on/off switching single dynamic systems. Moreover, to increase the performance of detection and azimuth tracking in low signal-to-noise ratio (SNR) scenarios, a track-before-detect (TBD) measurement model for AVS is proposed to be used with the Bernoulli filter. Sequential Monte Carlo (SMC) implementation is preferred for the Bernoulli filter recursions. Extensive simulation results prove the performance gain obtained by the proposed approach both in estimation accuracy and detection range of the system.     

Tuning space mapping with tuning exponent of T‐matrix

Tuning space mapping (TSM) with tuning exponent parameter of T‐matrix is proposed. A section of design interest in the electromagnetic (EM) model is replaced by “n” pieces cascaded T‐matrixes, and each T‐matrix is the EM‐simulated T‐parameter of preassigned unit cell circuit (PUCC). Finally the optimal exponent parameter of T‐matrix is transferred to original design variables. The proposed TSM not only inherits the advantages of circuit tuning element‐less (CTEL) TSM in prior art but also overcome the number range limitation that the tuning parameter must be positive for tuning in CTEL TSM. The proposed method has the minimal specification error and lowest simulation time comparing with other TSM methods. Verification examples, comparisons and discussions are also implemented. © 2015 Wiley Periodicals, Inc. Int J RF and Microwave CAE 26:232–239, 2016.