自动人脸跟踪方法研究

针对实时视频监控领域中传统的Camshift算法不能自动跟踪人脸和容易受到肤色相近遮挡等问题,首先采用Adaboost算法实现了人脸的自动检测,同时对于跟踪丢失等情形,通过贪心预测和卡尔曼预测对跟踪偏差进行实时改进,并比较两种算法的优缺点。实验表明前者对跟踪的准确性有较大提高,后者具有较好的实时性,在相近肤色遮挡时仍能实现正确跟踪,并对侧脸也有较好的效果,算法具有较好的鲁棒性。     

三轴移动载荷对半刚性路面性能影响分析

为研究多轴车辆移动载荷对半刚性路面性能影响规律,针对半刚性路面的特点,依据弹性层状体系理论,将半刚性路面的沥青层、半刚性基层、半刚性底基层及土基层按线弹性考虑,建立了半刚性路面的三维有限元分析模型,分析了车辆三轴移动载荷对半刚性路面性能影响。结果表明,3轴载荷作用下路面应力变化与车辆轴数有关,当车桥依次驶过路面时,路面应力出现3次突变,沥青层三向压应力、半刚性基层和底基层的垂直压应力、横向拉应力和水平拉应力均增大,最大拉应力出现在半刚性基层和底基层结合处;前轴驶过时轮迹带中心区域各层的横向剪应力最大,后轴驶过时轮迹带边缘区域各层的横向剪应力最大,最大值出现在沥青层底部;中轴驶过时路面各层的水平剪应力最大,最大值也出现在沥青层底部。因此,设计路面结构时,半刚性基层和半刚性底基层应选取抗弯和抗拉强度较高的材料,并应加强沥青面层的抗剪强度。     

一种基于步幅长度及频域特征的步态识别方法

步态识别作为一种较新的生物认证技术有其独特优势,它旨在根据人行进过程中的行走步态模式来识别其身份.提出一种基于步幅长度及频域特征的步态识别方法:首先采用背景减除算法实现运动人体检测,并根据步幅长度变化特征进行周期分割.然后提取步幅长度极值结合关键帧的频幅均值构成五维特征向量,最后用标准模式分类器在中科院自动化所提供的CASIA步态数据库中进行实验,在降低了算法复杂度的同时,获得了令人鼓舞的实验结果.     

HTTP-SoLDiER: An HTTP-flooding attack detection scheme with the large deviation principle

HTTP-flooding attack is a much stealthier distributed denial of service （DDoS） attack, challenging the survivability of the web services seriously. Observing the web access behavior, we find that the surfing preference of normal users is much more consistent with the webpage popularity than that of malicious users. Based on this observation, this paper proposes a novel detection scheme for HTTP-flooding （HTTP-SoLDiER）. Specifically, HTTP-SoLDiER first quantifies the consistency between web users surfing preference and the web- page popularity with large-deviation principle. Then HTTP-SoLDiER distinguishes the malicious users from normal ones according to the large-deviation probability. In practice, the webpage popularity plays a key role in attack detection of HTTP-SoLDiER. Due to the never-ending updating of the webpage content and the disturbance induced by attackers, the webpage popularity often varies over time. Thus, it is critical for HTTP-SoLDiER to dynamically update the webpage popularity. We design a reversible exponentially weighted moving average （EWMA） algorithm to solve the problem. Finally, we evaluate the effectiveness of this scheme in terms of true positive （TF） and false positive （FP） probabilities with NS-3 simulations. The simulation results show that HTTP-SoLDiER can detect all random HTTP-flooding attackers and most of the perfect-knowledge HTTP-flooding attackers at little false positive.     

气固错流移动颗粒床过滤器压降特性研究

研究了错流移动颗粒床过滤器操作压降与过滤介质特性、表现过滤气速、颗粒层移动速度和床层粉尘沉积量之间的关系。结果表明，无粉尘沉积时，床层压降可以用Ergun方程计算。颗粒层移动速度的变化并不会造成床层压降的显著变化。除尘过程中，床层内粉尘沉积量随气体中粉尘浓度的增大、颗粒层移动速度的减小而增加，同时将导致床层压降的显著增大。错流移动床除尘操作压降可以用带修正项的Ergun方程计算，其修正项为比沉积率和颗粒层空欧率的函数。在实验数据范围内，该方程的计算结果与实验数据最大偏差小于15％。     

基于线性多尺度模型的计算机网络数据流量预测

为了解决网络安全监控问题,提出了一种用于预测网络流量的算法.通过多个不同尺度的线性模型进行网络数据的组合预测,每个尺度的线性模型由经过滤波器滤波后的部分原始数据估计得到,最终的预测流量数据由多个尺度线性模型的平均预测值得到.选择的线性模型为自回归滑动平均模型,且尺度较小的线性模型对应自回归滑动平均模型的阶数较高.结果表明,本算法的预测精度高,整体预测误差的均值在10-3量级.     

Second order sliding mode control with backstepping approach for moving mass spinning missiles

An attitude controller using the second order sliding mode control methodology with a backstepping approach (SOSMCB) is designed and implemented for a spinning missile with two internal moving mass blocks. The system consists of a rigid body and two radial internal moving mass blocks and its mathematical model is established based on Newtonian mechanics. The control scheme integrates a second order sliding mode control algorithm into the last step of the backstepping approach, and its stability is proved by means of a Lyapunov function. The performance of the controller is demonstrated by numerical simulations, the results show that the attitude controller is stable and effective.     

一种基于深度信息的人头检测方法

针对目前人头检测方法对光线变化敏感和易受阴影干扰的问题,提出了一种基于深度图像的人头检测方法.首先通过运动目标检测,得到运动人员所在区域;然后对该区域使用改进的立体匹配算法,该匹配算法对传统的WTA匹配算法进行改进,只对强纹理点进行匹配,对弱纹理点只进行视差验证,并根据三角投影原理计算出深度图.由于深度图中人员与周围场景的深度分布不同,根据深度分布将人头区域提取出来,得到候选区域,最后将候选区域经过形态学运算并根据区域轮廓的特征来判断是否为人头.实验结果表明:该方法在不同光线环境条件下的检测正确率为94%以上,误检测率仅为5.77%,检测精度高,对光线和阴影的抗干扰性良好,能够很好地适应复杂环境.     

Micro-motion feature analysis and parameter estimation methods for moving ship

Micro-motion parameter estimation is an important way to improve ability of radar to detect the ship target. Focusing on the difficulty and speed problems existing in the current parameter estimation method of a complex moving ship, based on the analytical result of the echo's time-frequency features, a novel method to estimate the micro-motion period by calculating the backward shift cross-correlation coefficients of the echo's sparse time-frequency matrix is proposed in this paper. Firstly, the backward shift cross-correlation coefficients of the echo's sparse time-frequency matrix are calculated using the FFT (fast Fourier transform) algorithm. The peaks positions of the cross-correlation coefficients matrix are then detected. Finally, the period can be figured out quickly. Compared with the general method, the proposed method can estimate the micro-motion period accurately and quickly. A computer simulation is given to illustrate the effectiveness of the proposed method.     

基于 EWMA 控制图模型的公司财务质量判别

针对以往基于静态数据的两分类判别法的不足,选取沪深A股公司季报数据,将公司的财务质量分为正常、不稳定和困境3种状况,构建了具有时间累积性的EWMA控制图模型进行判别分析。选取了另外的24家沪深A股公司对模型的判别准确率进行了测试。结果表明,通过构建EWMA控制图模型并划分不同的控制限,可以对多个类型的公司财务质量做出有效的判别。