语谱图共振峰的自动跟踪算法

本文介绍一个共振峰轨迹的自动跟踪算法，其特点是不借助于其它的信息来源，仅仅是基于语谱图信息，来确定语谱图上前四个共振峰频率的位置和它们关于时间轴的轨迹。算法由三个层面构成；第一层面是进行频率分布的分析，以决定一个最佳的共振峰搜索起始位置；第二层面是采用双搜索算法，来跟踪随时间变化的共振峰轨迹；第三层面是解决某些冲突现象，在共振峰跟踪问题上的难点之一是处理多个共振峰的合并现象和冗余峰值现象。     

Deep transfer reinforcement learning for resource allocation in hybrid multiple access systems

This paper proposes a resource allocation scheme for hybrid multiple access involving both orthogonal multiple access and non-orthogonal multiple access (NOMA) techniques. The proposed resource allocation scheme employs multi-agent deep reinforcement learning (MA-DRL) to maximize the sum-rate for all users. More specifically, the MA-DRL-based scheme jointly allocates subcarrier and power resources for users by utilizing deep Q networks and multi-agent deep deterministic policy gradient networks. Meanwhile, an adaptive learning determiner mechanism is introduced into our allocation scheme to achieve better sum-rate performance. However, the above deep reinforcement learning adopted by our scheme cannot optimize parameters quickly in the new communication model. In order to better adapt to the new environment and make the resource allocation strategy more robust, we propose a transfer learning scheme based on deep reinforcement learning (T-DRL). The T-DRL-based scheme allows us to transfer the subcarrier allocation network and the power allocation network collectively or independently. Simulation results show that the proposed MA-DRL-based resource allocation scheme can achieve better sum-rate performance. Furthermore, the T-DRL-based scheme can effectively improve the convergence speed of the deep resource allocation network.     

目标跟踪与定位中的视觉标定算法研究

目标跟踪与定位中的一个重要步骤就是摄像机标定,其目的是估计摄像机的外部和内部参数。在严格的几何约束关系之上建立准确的数学模型,提出一种快速得到摄像机中心的方法,然后通过合理的求解次序获得其他摄像机参数,保证了标定参数的精度。利用计算出来的标定参数校正失真图像中的各个像素位置以重新得到像素间原来的空间关系,从而产生精确的不失真图像,并且利用摄像机标定参数对标定模板上的点进行位置计算后,再和实际位置比较进行检验。图像的校正效果实验以及精度验算的结果表明：提出的算法得到了准确可靠的标定参数,和其他算法相比有效提高了精度,能够满足运动跟踪时目标特征位置估计的精度要求。     

A two-beam laser triangulation for measuring the position of a moving object

A two-beam laser triangulation method has been proposed to measure the position of a moving object. The method uses two parallel laser beams to judge the moving direction of an object, allowing us to track it and measure its positions. An uncertainty of 0.2 mm for a measurement range of 50 mm has been obtained. This tracking measurement capability is useful in the calibration of the position of a moving robot arm.     

成像目标跟踪目标建模技术综述

由目标跟踪的数学模型得出,影响目标跟踪性能的三个主要因素为目标状态转移模型、滤波算法和目标建模技术.对目标建模技术进行了综述和分析,分别从特征选择、特征的统计建模和相似性度量三个方面进行了阐述.以畸变不变性、目标/背景分辨能力作为性能评价手段定性地比较了国内外文献中提出的多种目标表征模型.指出了目标跟踪中目标表征模型自...     

一种自适应视频跟踪算法及其ARM DSP实现

视觉跟踪作为图像处理和计算机视觉学科的重要分支,广泛应用与军事和民事的各个领域。对于相对运动速度较快的对象,传统的光流法计算精度不高,本文提出了一种视频跟踪算法,首先通过差分法检测图像差异,然后通过光流法实现视频自适应跟踪功能。设计了基于ARM和DSP的视频跟踪装置,详细讨论了硬件平台和接口设计,以S3C2410作为主控模块、TM320芯片作为图像处理模块。实验结果证明,该算法具有实时性、精度高、灵活性强的优点。     

基于Mean-shift的灰度目标跟踪新算法

Mean-shift算法是一种非参数密度估计算法,可以实现快速的最优匹配,在目标的实时跟踪领域起着非常重要的作用。为了有效的将Mean-shift算法应用到灰度图像中,采用了以方向直方图建立目标模型的策略,提出了在灰度图像中以Mean-shift为核心的目标跟踪算法。实验结果表明,该算法具有不受光照条件影响的优点,在低对比度的情况下仍能实现稳定、实时的跟踪目标。     

水声JANUS信号的分数低阶时频谱迁移学习识别方法

非合作第三方水下标准协议信号识别在水声通信信号识别中具有重要研究意义。针对浅海水声JANUS信号的特征提取因易受脉冲噪声和多径效应等复杂水声环境影响而导致识别率低下的问题,提出一种分数低阶时频谱和ResNet18 （Residual Network 18）相结合的迁移学习识别方法。首先,选取JANUS固定前导作为识别对象,设计分数低阶傅里叶同步压缩变换（FLOFSST）,以分数低阶操作抑制脉冲噪声,以时频重排特性增强时频集中性。其次,将基于ImageNet的ResNet18预训练模型微调,迁移至JANUS信号和常见水声信号时频图集。仿真表明所提算法在信噪比为-10 dB时JANUS信号的识别率为96.15%,能够有效抑制脉冲噪声并减小多径效应影响,比传统算法识别性能好。海试中JANUS信号识别率达90.00%,证明算法识别准确率和网络的泛化性较高。     

观测站非机动情况下的渐进无偏目标跟踪算法

针对无源目标跟踪中将非线性测量方程伪线性化带来有偏估计的缺点,提出了一种基于方位和径向速度联合估计的渐进无偏目标跟踪算法。该算法通过对方位-径向速度组成的伪线性测量方程的噪声协方差矩阵进行约束,使其均方误差达到最小,得到目标状态向量的最小二乘无偏解。仿真和实验结果表明,在观测站非机动情况下,算法能够渐进无偏地收敛到真值,收敛后的距离跟踪误差在5%以内。     

Implementation of opto-digital stereo object tracking system

In this paper, a new opto-digital stereo object tracking system using the variable window mask and the optical binary phase extraction joint transform correlator (BPEJTC) is proposed. At the first step, with the distance information from the stereo camera to the tracking object easily acquired by the structural elements of a stereo vision system, the area of the tracking object can be digitally extracted by using the variable window mask. And, at the second step, by carrying out the optical BPEJTC between this reference image obtained from the variable window mask and the stereo input image, the coordinates of the tracking object's location can be acquired, and then with these values, the convergence angle and the pan/tilt of the stereo tracking camera can be finally controlled. From some experimental results, the proposed system is found to be able to effectively extract the area of the target object from the input image having the background noises by using the variable window mask. And, with the location values of the tracking object obtained by using the optical BPEJTC, the convergence angle and the pan/tilt of the stereo cameras can be controlled. Finally, a feasibility of real-time implementation of the adaptive stereo object tracking system using the proposed algorithm is also suggested.     

一种自动分割跟踪视频运动对象的方法

针对视频图像中单个运动对象的分割和跟踪问题,提出了一种基于时空离散度的视频对象分割跟踪算法。该算法首先采用时空离散度进行运动对象区域的粗定位;然后通过形态学算子来进行细定位,并获取运动物体的二值模型;再然后使用部分Hausdorff距离实现后续帧中运动对象模型的匹配;最后为了容纳运动对象在视场中形状的变化,在图像距离空间中引入了欧几里德范数作为约束条件来完成运动物体模型的更新。实验表明,在运动对象跟踪过程中相邻位置差未超过2个像素点,从而验证了算法的有效性。     

一种多基阵机动目标被动跟踪算法

由多部声纳基阵获取的方位信息对水中机动目标的跟踪实质上是一个非线性状态估计问题,文中首先依据各基阵的方位信息,采用最小二乘法得到目标位置在各采样时刻的初步估计,然后将其作为测量值用于交互多模型算法(IMM)并结合线性卡尔曼滤波(KF)得到目标运动速度和轨迹,避免了应用非线性估计算法直接进行多个方位数据融合过程中存在的各种问题。仿真结果表明这一算法简便,与双基阵纯方位机动目标被动跟踪相比具有较快的收敛速度和较高的跟踪精度。     

Heteronuclear decoupling by optimal tracking

The problem to design efficient heteronuclear decoupling sequences is studied using optimal control methods. A generalized version of the gradient ascent engineering (GRAPE) algorithm is presented that makes it possible to design complex non-periodic decoupling sequences which are characterized by tens of thousands of pulse sequence parameters. In contrast to conventional approaches based on average Hamiltonian theory, the concept of optimal tracking is used: a pulse sequence is designed that steers the evolution of an ensemble of spin systems such that at a series of time points, a specified trajectory of the density operator is tracked as closely as possible. The approach is demonstrated for the case of low-power heteronuclear decoupling in the liquid state for in vivo applications. Compared to conventional sequences, significant gains in decoupling efficiency and robustness with respect to offset and inhomogeneity of the radio-frequency field were found in simulations and experiments.     

动态背景下运动目标检测与跟踪研究

主要研究动态背景下的运动目标检测和跟踪问题。背景补偿差分法是一种常用的动态背景下运动目标检测算法,但检测到的目标轮廓要比其真实轮廓大,检测结果不准确且算法复杂度较高。主动轮廓模型在图像分割和目标提取过程中具有拓扑结构变化灵活性,对数值计算方案的设计更加方便、有效,据此提出一种基于改进C-V模型和卡尔曼滤波的算法,用来检测和跟踪动态背景下的运动目标。提出的算法利用C-V模型曲线演化检测和跟踪目标,使C-V模型在目标的边缘处收敛。结合卡尔曼滤波预测运动目标下一帧位置,从而实现对运动目标轮廓的跟踪。实验结果表明,该方法可以对动态背景下运动目标进行精确的检测与跟踪。     

Research of object tracking based on soft feature

To solve the problem that traditional object tracking method had disadvantage of too much time consumed by data process and object lost under complex background, a novel approach to object tracking based on the space spectrum and edge spectrum is proposed and verified experimentally. Analyzing precursor features and study the unity and complementary of space spectrum and edge spectrum, research the extraction technology of moving object based on space spectrum and edge spectrum in order to track and forecast information of the moving object in real time. Experiments show that the proposed approach overcomes the problems of data dependence and object occlusion and achieves good tracking results.     

基于变分辨率的自适应窗口目标跟踪方法研究

针对视觉跟踪中运动目标的大小也随之改变这一问题,提出一种基于变分辨率的自适应窗口目标跟踪方法。在最大后验概率视觉跟踪算法基础上,分析了运动目标窗口内外框上的后验概率贡献指标,建立了自适应窗口调整目标尺度的数学模型。当运动目标尺寸变化时,其分辨率也相应变化,为了保证跟踪的实时性和效率,采用变分辨率的特征统计采样方法。在对运动目标实现自适应窗口的跟踪时,特征统计的分辨率也随之改变,对尺寸越大的运动目标尺度赋予更低的分辨率,从而实现基于变分辨率的自适应窗口目标跟踪。     

An object tracking method based on guided filter for night fusion image

Online object tracking is a challenging problem as it entails learning an effective model to account for appearance change caused by intrinsic and extrinsic factors. In this paper, we propose a novel online object tracking with guided image filter for accurate and robust night fusion image tracking. Firstly, frame difference is applied to produce the coarse target, which helps to generate observation models. Under the restriction of these models and local source image, guided filter generates sufficient and accurate foreground target. Then accurate boundaries of the target can be extracted from detection results. Finally timely updating for observation models help to avoid tracking shift. Both qualitative and quantitative evaluations on challenging image sequences demonstrate that the proposed tracking algorithm performs favorably against several state-of-art methods.     

基于颜色和空间信息的多特征融合目标跟踪算法

为解决单一特征目标跟踪鲁棒性较差的问题,提出一种基于颜色和空间信息的多特征融合目标跟踪算法。采用一种自适应划分颜色区间的方法提取目标颜色特征,利用空间直方图提取目标颜色的空间分布信息。在粒子滤波框架下将自适应颜色直方图和空间直方图相结合,在特征融合中引入特征不确定性度量方法,自适应调整不同特征对跟踪结果的贡献,提高算法的鲁棒性。仿真实验结果表明,该跟踪算法平均位置最小误差值仅6.967 像素,而单一特征跟踪算法以及传统融合算法的跟踪误差达192.576 像素和199.464像素。说明本文算法在跟踪准确性上优于单一特征跟踪算法及传统融合算法,具有更好的跟踪精度和更高的鲁棒性。     

New type charge transfer states in ferroelectric oxides: Actual problems

Brief review of recent theoretical and experimental studies of Charge Transfer Vibronic Excitons and induced by defects, charge transfer - lattice ground states in ferroelectric oxides and analysis of actual problems is presented. Predictions of new effects related to such charge transfer states are made.