基于联合优化的强耦合孪生区域推荐网络的目标跟踪算法

针对区域推荐网络（RPN）在目标跟踪任务中出现的最大分类分数与最佳边框不匹配的问题，提出一种基于联合优化的强耦合孪生区域推荐跟踪算法（SCSiamRPN）。首先，采用Bounded IoU方法来优化正样本交并比（IoU）值的计算，通过分解公式、固定变量、替换差值和约束近似的操作来简化计算过程。然后，优化损失函数结构，通过在分类损失函数中添加以IoU值为纽带的耦合因子来联合分类任务和边框回归任务，以提升高IoU样本的损失值；通过在边框回归损失函数中添加以IoU为主变量的加权系数来提高目标中心样本的贡献，以提升边框定位精度。仿真结果显示：SCSiamRPN算法在OTB100数据集上的精度和成功率为0.86和0.64；同基于孪生区域推荐候选网络的高性能单目标跟踪（SiamRPN）算法相比，均有3%的提升。实验结果表明：SCSiamRPN算法解决了最大分类分数与最佳边框不匹配的问题，增强了分类和边框回归任务的耦合性，且在不损失跟踪速度的前提下实现了跟踪精度的较大幅度提升。     

基于多层特征增强的实时视觉跟踪

为了解决全卷积孪生视觉跟踪网络（SiamFC）出现相似语义信息干扰物使得跟踪目标发生漂移，导致跟踪失败的问题，设计出一种基于多层特征增强的实时视觉跟踪网络（MFESiam），分别去增强高层和浅层的特征表示能力，从而提升算法的鲁棒性。首先，对于浅层特征，利用一个轻量并且有效的特征融合策略，通过一种数据增强技术模拟一些在复杂场景中的变化，例如遮挡、相似物干扰、快速运动等来增强浅层特征的纹理特性；其次，对于高层特征，提出一个像素感知的全局上下文注意力机制模块（PCAM）来提高目标的长时定位能力；最后，在三个具有挑战性的跟踪基准库OTB2015、GOT-10K和2018年视觉目标跟踪库（VOT2018）上进行大量实验。实验结果表明，所提算法在OTB2015和GOT-10K上的成功率指标比基准SiamFC分别高出6.3个百分点和4.1个百分点，并且以每秒45帧的速度运行达到实时跟踪。在VOT2018实时挑战上，所提算法的平均期望重叠率指标超过2018年的冠军，即高性能的候选区域孪生视觉跟踪器（SiamRPN），验证了所提算法的有效性。     

On controllability and trajectory tracking of a kinematic vehicle model

This paper presents some further results concerning the issues of controllability and trajectory tracking regarding a front-wheel drive vehicle kinematic model. A simple procedure for computing an open-loop control strategy that transfers the system between given initial and final states, is presented. In particular, the input function is computed by means of a set of linear algebraic equations. The resulting motion planning procedure allows us to present a control scheme for solving the trajectory (a time-parameterized reference signal) tracking problem. Various applications of the approach in forward and backward motions are considered, and simulation results are presented.     

Tracking multiple people with recovery from partial and total occlusion

Robust tracking of multiple people in video sequences is a challenging task. In this paper, we present an algorithm for tracking faces of multiple people even in cases of total occlusion. Faces are detected first; then a model for each person is built. The models are handed over to the tracking module which is based on the mean shift algorithm, where each face is represented by the non-parametric distribution of the colors in the face region. The mean shift tracking algorithm is robust to partial occlusion and rotation, and is computationally efficient, but it does not deal with the problem of total occlusion. Our algorithm overcomes this problem by detecting the occlusion using an occlusion grid, and uses a non-parametric distribution of the color of the occluded person's cloth to distinguish that person after the occlusion ends. Our algorithm uses the speed and the trajectory of each occluded person to predict the locations that should be searched after occlusion ends. It integrates multiple features to handle tracking multiple people in cases of partial and total occlusion. Experiments on a large set of video clips demonstrate the robustness of the algorithm, and its capability to correctly track multiple people even when faces are temporarily occluded by other faces or by other objects in the scene.     

Real-time multiple people tracking using competitive condensation

The CONDENSATION (Conditional Density Propagation) algorithm has a robust tracking performance and suitability for real-time implementation. However, the CONDENSATION tracker has some difficulties with real-time implementation for multiple people tracking since it requires very complicated shape modelling and a large number of samples for precise tracking performance. Further, it shows a poor tracking performance in the case of close or partially occluded people. To overcome these difficulties, we present three improvements: First, we construct effective templates of people's shapes using the SOM (Self-Organizing Map). Second, we take the discrete HMM (Hidden Markov Modelling) for an accurate dynamical model of the people's shape transition. Third, we use the competition rule to separate close or partially occluded people effectively. Simulation results shows that the proposed CONDENSATION algorithm can achieve robust and real-time tracking in the image sequences of a crowd of people.     

传感器网络目标恢复算法研究

分析了传感器网络在目标跟踪过程中产生目标丢失故障的原因.在此基础上采用分簇设计思想,通过对跟踪目标移动速度的计算和目标搜寻区域的建立等方法,提出了目标丢失故障恢复新的算法和技术.实验证明,所提出的算法和技术在延长传感器网络生存时间前提下,能够有效地解决跟踪目标发生丢失故障后目标快速恢复问题.     

User Independent Paging Scheme for Mobile IP

Multi-step paging has been widely proposed in personal communications services (PCS) systems to reduce the signaling overheads. Similar ideas can be applied to Mobile IP to provide IP paging services. However, current proposed multi-step paging schemes are user dependent under which the partition of paging areas and the selection of paging sequence are different for each user. The performance of a user dependent paging scheme for individual users may be affected by many factors. It is often difficult to achieve perfect performance for each user. In addition, when multiple users are paged at the same time, user dependent paging schemes may consume significant system resources. This paper introduces a user independent paging scheme where the paging criterion is not based on individual user information. The goal of user independent paging is to provide satisfactory overall performance of the whole system, when personalized optimal performance for each user is hard to obtain. The user independent paging scheme is proposed for IP mobility for its easy implementation and convenient combination with paging request aggregation. The paging criterion adopted is the mobility rate of each subnet determined by the aggregated movements of all mobile users. In order to implement the proposed scheme, a concept of “semi-idle state” is introduced and the detailed solution for obtaining mobility rate is presented. Analytical results show that when paging one user at a time, the performance of the proposed user independent paging scheme is comparable to that of the paging schemes based on perfect knowledge of user movement statistics. When paging multiple users simultaneously and when the knowledge on individual user behavior is not perfectly accurate, the proposed scheme has remarkable advantages in terms of reducing the overall paging cost. Jiang Xie received her B.E. degree from Tsinghua University, Beijing, China, in 1997, M.Phil. degree from Hong Kong University of Science and Technology in 1999, and M.S. and Ph.D. degrees from Georgia Institute of Technology in 2002 and 2004, respectively, all in electrical engineering. She is currently an assistant professor with the Department of Electrical and Computer Engineering at the University of North Carolina-Charlotte. Her current research interests include resource and mobility management of wireless networks,QoS provisioning, and next-generation Internet. She is a member of IEEE and ACM.     

Soft-Decision Decoding of Punctured Convolutional Codes in Asynchronous-CDMA Communications Under Perfect Phase-Tracking Conditions

In this paper, the performance of punctured convolutional codes of short constraint lengths is discussed. The punctured codes are used to provide error protection to a particular user in an asynchronous CDMA system. A perfect phase reference is assumed to be available throughout this paper. A slow fading Rician channel is assumed. Maximum likelihood decoding through a Viterbi algorithm is used to decode the information symbols. Soft-decision decoding of punctured convolutional codes is considered in this paper. The upper bounds with Viterbi decoding are derived and plotted for the various punctured codes considered. The simulated results are found to agree very well with their upper and lower bounds.     

一种同轴跟踪系统的自适应前馈方法

在同轴跟踪雷达系统中，前馈是为了克服伺服系统的二阶动态滞后而采取的一项关键技术。文中结合同轴跟踪系统模型，将前馈引入计算机数据处理部分，提出一种自适应前馈方法，并结合专门开发的同轴跟踪系统仿真软件，对前馈参数的选取进行了讨论。最后与无前馈的传统单脉冲雷达的仿真跟踪试验进行对比，验证了其自适应前馈的效果。     

雷达低角跟踪性能影响分析

基于相控阵雷达的天线波束形成原理和单脉冲体制测角原理，分析了波瓣分裂对雷达角敏函数曲线的影响以及多路径效应对S波段舰载有源相控阵雷达低空跟踪性能的影响，比较了改善跟踪低仰角目标性能的3种方法如偏轴跟踪和复角技术的现实性和可行性。