A novel method for fingerprint singular points extraction including location and orientation is proposed based on some properties of the orientation field models. Singular points are located by clustering the results of corner detection. Then, through examining the sub-block orientation fields at a number of selected positions on concentric circles centered about the located singular point, an iterative method based on the orientation differences is proposed to compute the orientation of the core point. Experimental results on NIST4 and FVC2002 four databases demonstrate the proposed method can consistently locate singular points with the high accuracy. The location and orientation of the detected singular points can be used for alignment （translation and rotation） parameters in fingerprint matching.
This article presents a novel people-tracking approach to cope with partial occlusions caused by scene objects. Instead of predicting when and where the occlusions will occur, a part-based model is used to model the pixel distribution of the target body under occlusion. The subdivided patches corresponding to a template image will be tracked independently using Markov chain Monte Carlo （MCMC） method. A set of voting-based rules is established for the patch-tracking result to verify if the target is indeed located at the estimated position. Experiments show the effectiveness of the proposed method.
针对环境中障碍物对被跟踪目标构成不可预知的遮挡问题,提出了一种新的基于局部区域特征匹配的跟踪算法。首先采用一组基本观察片图模拟目标的外观;其次提出了一种将运动轨迹特性与动态模型结合的采样结构,采用马尔可夫链蒙特卡洛(MCMC,Markov chain Monte Carlo)方法独立估计每个基本片图的状态,并使用运动区域一致性规则选择构成目标的有效的特征片图,遮挡状态则被定义为对应片图的消失;最后由有效片图的组合确定目标的可见概率。实验结果表明,与基于单一区域的方法和基于空间互连的多区域方法相比,本文提出的方法在部分或全部遮挡情况下能够更有效预测被跟踪目标的状态。
In a hybrid wired-cum-wireless network environment, packet loss may happen because of congestion or wireless link errors. Therefore, differentiating the cause is important for helping transport protocols take actions to control congestion only when the loss is caused by congestion. In this article, an end-to-end loss differentiation mechanism is proposed to improve the transmission performance of transmission control protocol （TCP）-friendly rate control （TFRC） protocol. Its key design is the introduction of the outstanding machine learning algorithm - the support vector machine （SVM） into the network domain to perform multi-metric joint loss differentiation. The SVM is characterized by using end-to-end indicators for input, such as the relative one-way trip time and the inter-arrival time of packets fore-and-aft the loss, while requiring no support from intermediate network apparatus. Simulations are carried out to evaluate the loss differentiation algorithm with various network configurations, such as with different competing flows, wireless loss rate and queue size. The results show that the proposed classifier is effective under most scenarios, and that its performance is superior to the ZigZag, mBiaz and spike （ZBS） scheme.
DENG Qian-hua ,CAI An-ni School of Telecommunication Engineering,Beijing University of Posts and Telecommunications,Beijing 100876,China
