基于模式模板的MPEG压缩视频序列的划变转换检测

为了在进行视频分段时，对一些复杂的和奇异的Wipe转换模式进行检测，得出了一种基于模式模板的MPEG压缩视频序列的划变转换检测方法。该方法是在刻画划变转换时，用一种视频帧间图象特征变化信息的模式模板；并用一个基于该模式模板的算法，来检测包括各种奇异转换在内的划变转换，同时为了消除运动干扰，还引入了Hough变换。实验结果显示，该方法能精确检测划变转换区的位置和识别相应的转换模式，另外，无论是已存在的或将来出现的划变转换模式，该算法都同样适用。     

Non-rigid face tracking with enforced convexity and local appearance consistency constraint

Convex quadratic fitting (CQF) has demonstrated great success recently in the task of non-rigidly registering a face in a still image using a constrained local model (CLM). A CLM is a commonly used model for non-rigid object registration and contains two components: (i) local patch-experts that model the appearance of each landmark in the object, and (ii) a global shape prior describing how each of these landmarks can vary non-rigidly. Conventional CLMs can be used in non-rigid facial tracking applications through a track-by-detection strategy. However, the registration performance of such a strategy is susceptible to local appearance ambiguity. Since there is no motion continuity constraint between neighboring frames of the same sequence, the resultant object alignment might not be consistent from frame to frame and the motion field is not temporally smooth. In this paper, we extend the CQF fitting method into the spatio-temporal domain by enforcing the appearance consistency constraint of each local patch between neighboring frames. More importantly, we show, as in the original CQF formulation, that the global warp update can be optimized jointly in an efficient manner. Finally, we demonstrate that our approach receives improved performance for the task of non-rigid facial motion tracking on the videos of clinical patients.     

基于肤色及轮廓信息的人耳实时跟踪

实时人耳跟踪作为人耳识别系统的前提，是一个意义重大且具有挑战性的课题。为了实现对人耳的快速实时跟踪定位，提出了一种融合肤色及灰度轮廓信息检测跟踪序列图像中人耳的新方法。该方法首先采用改进的CAMSHIFT算法在肤色概率分布基础上，初步对侧面人脸这一包含耳朵的大面积肤色区域进行粗定位，进而根据耳朵自身丰富的轮廓信息，应用轮廓提取及拟合来进一步精确定位人耳。实际应用表明，该方法具有速度快、效率高和鲁棒性好的特点，不仅能够满足实时性的要求，并且对于干扰和耳朵自身一定角度的偏转都有较好的容错性。此外，该方法在相对复杂的背景下仍能获得较好的跟踪效果。     

基于角点光流与SVM的增氧机工作状态检测

在水产养殖中,实时检测增氧机的工作状态非常重要。因此,提出了一种基于角点光流与支持向量机SVM模型的增氧机工作状态检测方法。该方法首先通过摄像机采集增氧机停止/运行状态的视频,然后对相继前后两个视频帧,利用Harris算法检测前一帧图像的水花角点,再根据后一帧,用金字塔Lucas-kanade光流法计算角点的光流量,从而得出水花角点在两帧之间的帧间平均位移;然后,利用学习阶段视频的角点帧间平均位移数据训练SVM模型;最后利用训练好的SVM模型对增氧机实时工作状态进行判断。在工作阶段,采用一种过滤异常视频帧的方法,提高检测的准确率。通过实验表明,该方法适应于对不同光照、不同视频获取角度和不同拍摄距离条件下增氧机工作状态的实时监控,检测准确率高于直方图阈值分割方法。同时,该方法具有较好的鲁棒性和实时性。     

基于滤波与曲线拟合的电子稳像算法

针对目前电子稳像算法无法同时去除高频噪声与低频噪声的问题,提出了可同时去除高频噪声和低频噪声的滤波与曲线拟合相结合的方法。该方法首先用位平面匹配算法快速估计出帧间的偏移量;其次对帧间偏移量进行累加,计算出当前帧相对于参考帧的全局运动量,并对全局运动量进行卡尔曼滤波,以去除高频噪声;最后,对卡尔曼滤波的结果进行曲线拟合以去除低频噪声;最终,得到稳定的主运动轨迹。实验证明,该方法可以有效地去除高频和低频噪声,视频稳定效果良好。     

Interactions of excitatory and inhibitory feedback topologies in facilitating pattern separation and retrieval

Within the brain, the interplay between connectivity patterns of neurons and their spatiotemporal dynamics is believed to be intricately linked to the bases of behavior, such as the process of storing, consolidating, and retrieving memory traces. Memory is believed to be stored in the synaptic patterns of anatomical circuitry in the form of increased connectivity densities within subpopulations of neurons. At the same time, memory recall is thought to correspond to activation of discrete areas of the brain corresponding to those memories. Such regional subpopulations can selectively activate during memory recall or retrieval, signifying the process of accessing a single memory or concept. It has been shown previously that recovery of single memory activity patterns is mediated by global neuromodulation signifying transition into different cognitive states such as sleep or awake exploration. We examine how underlying topology can affect memory awake activation and sleep reactivation when such memories share increasing proportions of neurons. The results show that while single memory activation is diminished with increased overlap, pattern separation can be recovered by offsetting excitatory associations between two memories with targeted and heterogeneous inhibitory feedback. Such findings point to the importance of excitatory-to-inhibitory current balance at both the global and local levels in the context of memory retrieval and replay, and highlight the role of network topology in memory management processes.     

重力固体潮IMF的AM-FM模型及其非线性拟合

首先建立AM-FM数学模型,用多个相近载波的调幅信号组合描述它。利用最小二乘法对幅度调制和频率调制两个部分分别进行非线性拟合;拟合以相关系数满足一定条件为精度控制原则,拟合项数以相邻相关系数不再显著变化为判定条件。有效性检验证明该方法切实可行。重力固体潮IMF的拟合结果表明,AM-FM数学模型可以很好地刻画重力固体潮IMF;重力固体潮是多个AM-FM信号合成的复合信号。为后续深入研究重力固体潮的AM-FM信号特征、循环平稳信号特征等性质建立了良好的数学基础。     

基于主色特征识别的新闻视频口播帧

基于主色特征识别的新闻视频口播帧是一种全新的口播帧识别方法，该方法首先提取口播帧的主色模板，然后利用该模板对新闻视频的帧序列进行匹配，并由计算机自动对口 播帧进行检测和标识。该检测方法与现有的检测方法相比，具有设计简单、计算量小、检测速度快的特点，可以完全做到实时检测。     

基于火焰图像动态特征的火灾识别算法

提出了一种基于火焰图像动态特征的火灾识别算法.首先在HSI空间对捕捉的图像进行彩色分割,通过相邻两帧图像判断视频中是否存在可疑火焰.当有可疑火焰存在时,再连续捕捉多帧图像,进行火焰中心定位并提取火焰动态特征,最后判断是否发生火灾.实验结果表明,该算法具有比较好的鲁棒性,能够有效地提高火灾识别的准确率、降低误报漏报率.     

利用时空特征编码的单目标跟踪网络

目的 随着深度神经网络的出现,视觉跟踪快速发展,视觉跟踪任务中的视频时空特性,尤其是时序外观一致性(temporal appearance consistency)具有巨大探索空间。本文提出一种新颖简单实用的跟踪算法——时间感知网络(temporal-aware network, TAN),从视频角度出发,对序列的时间特征和空间特征同时编码。方法 TAN内部嵌入了一个新的时间聚合模块(temporal aggregation module, TAM)用来交换和融合多个历史帧的信息,无需任何模型更新策略也能适应目标的外观变化,如形变、旋转等。为了构建简单实用的跟踪算法框架,设计了一种目标估计策略,通过检测目标的4个角点,由对角构成两组候选框,结合目标框选择策略确定最终目标位置,能够有效应对遮挡等困难。通过离线训练,在没有任何模型更新的情况下,本文提出的跟踪器TAN通过完全前向推理(fully feed-forward)实现跟踪。结果 在OTB(online object tracking:a benchmark)50、OTB100、TrackingNet、LaSOT(a high-qua...     

基于曲线拟合函数和GPU的地形无缝渲染

针对大规模地形实时渲染时不同层次细节过渡产生的画面不连续性问题,以及计算机实时调度大量数据而造成帧速较低的问题,提出了一种基于曲线拟合函数和GPU加速的地形实时绘制方法。根据采样数据点采用最小二乘法构造曲线拟合函数,通过曲线函数控制不同层次网格顶点的布局,从而消除因层次细节变化产生的裂缝。同时根据分辨率不同构建金字塔模型,针对不同层次细节区域数据进行有损或无损压缩,依据视点运动预测实时解压相应数据。实验表明,该方法在地形实时渲染阶段,在保证了较高帧速率的同时,利用视点运动预测保证了帧速率变化小,有效的消除了裂缝,增强了画面效果。     

Spatiotemporal directional coherence-based scrolling-text detection for frame rate up-conversion

This paper proposes a novel scrolling-text detection method that uses spatiotemporal directional coherence for frame rate up-conversion. Spatiotemporal directional coherence is defined as the coherence level of the spatiotemporal gradient distribution in consecutive frames. Existing scrolling-text detection methods usually detect text using the motion vectors of an image or the distributions of gradient components. The number of motion vectors to determine the scrolling-text decreases at the start and end points of the frame boundary. Therefore, they have difficulty accurately detecting the scrolling text from the start or end points of a frame boundary. The distributions of gradient components can be generated by non-scrolling-text components and they cannot consider the temporal information of consecutive frames, so they may erroneously detect non-scrolling-text regions as the scrolling-text. Unlike the previous methods, which are vulnerable to the presence of texture and noise, the core idea of the proposed method is to use the spatiotemporal directional coherence of the gradient components in the consecutive frames to detect the regions with a dominant edge orientation component for generation of the scrolling-text map and use bit codes from the luminance values to analyze the diversity of luminance patterns for refinement process. With these, the proposed method can further improve the detection accuracy compared to the benchmark methods. The experimental results showed that the proposed method enhanced the average F₁ score by up to 0.5195 (a 137.69 % improvement) compared to the benchmark methods. The average computation time per pixel of the proposed method was also reduced by up to 16.205 μs (a 70.57 % reduction) compared to the benchmark methods.     

基于动态功能连接的运动任务大脑状态表达

针对传统静态功能连接分析技术不能准确反映大脑动态功能状态的问题,提出了一种基于全脑动态功能连接(DFC)分析对大脑的状态变化进行表达的方法。首先,利用个体的弥散张量成像(DTI)数据构建高精确度全脑网络,将运动任务下功能磁共振成像(fMRI)数据映射到相应DTI空间后,提取各节点fMRI信号;然后,采用滑动时间窗口方法计算随时间变化的全脑功能连接强度矩阵,并提取动态功能连接向量(DFCV)样本;最后,将所有个体的DFCV样本通过基于Fisher准则的字典学习(FDDL)算法进行稀疏表达和分类。共得到8个该运动任务下全脑功能连接状态模式,各模式的功能连接强度空间分布具有明显差异,模式1、模式2和模式3占据了大部分样本分布(77.6%),且与平均静态功能连接强度矩阵之间的相似度明显高于其他5个模式。此外,大脑在各模式之间的状态迁移遵循一定的规律。实验结果表明,采用全脑DFC和FDDL学习相结合的方法,能够有效地对任务态下大脑的功能状态变化进行表达,为研究脑动态信息处理机制提供基础。     

A method for the automatic analysis of the sleep macrostructure in continuum

Sleep staging is one of the most important tasks within the context of sleep studies. For more than 40 years the gold standard to the characterization of patient’s sleep macrostructure has been based on set of rules proposed by Rechtschaffen and Kales and recently modified by the American Academy of Sleep Medicine. Nevertheless the resulting map of sleep, the so-called hypnogram, has several limitations such as its low temporal resolution and the unnatural characterization of sleep through the assignment of discrete sleep states. This study reports an automatic method for the characterization of the structure of the sleep. The main intention is to overcome limitations of epoch-based sleep staging by obtaining a more continuous evolution of the sleep of the patient. The method is based on the use of fuzzy inference in order to avoid binary decisions, provide soft transitions and enable concurrent characterization of the different states. It is proven, in addition, how the new proposed continuous representation can still be used to generate the classical epoch-based hypnogram.     

基于分段拟合的非线性组合调制雷达信号设计

线性调频与伪随机码组合调制的雷达信号可增加信号复杂度,在降低信号被截获概率方面有突出优势,但该组合具有线性调频高旁瓣,且无法克服加窗处理后主瓣宽度增大的缺点。利用驻留相位产生的非线性调频信号能够抑制旁瓣的特点,提出分段拟合的非线性调频与巴克码调制相结合的方法,将其各自的优点加以结合,不仅可以减小距离与速度模糊度,而且可以抑制旁瓣。对该组合信号的显函数模型仿真曲线和模糊函数图进行分析,仿真结果表明,该方法不仅可以降低距离与速度模糊度、降低信号被低截获概率,而且产生了比传统非线性调频更低的旁瓣,说明了该方法用于雷达信号的可行性与优越性。     

电压型PWM整流器新型相幅控制

在分析其控制原理的基础上,提出了用整流器输入前端电压滞后角作为输入变量控制网侧输入电流的相位幅值控制的新方法,解决了传统相幅控制方法存在的问题。建立了基于三相静止坐标系和两相旋转坐标系的整流器数学模型,并验证了这个新的控制方法的有效性。     

一种有效的GPS周跳探测与修复方法研究

利用GPS载波相位进行姿态测量时,要达到很高的精度必须保证观测数据中没有载波相位周跳的发生,因此,正确探测与修复周跳是GPS姿态测量中的一个关键问题.通过分析比较常用周跳探测方法,采用电离层残差法对周跳进行探测,同时提出一种基于拟合方法的周跳修复方法.该方法能解决电离层残差检测周跳时的多值性问题,能够检测较小周跳和10周以上大的周跳,并且能很好地区分和修复周跳发生历元的载波相位值.利用实测数据验证了该方法的有效性与可行性.     

Video flickering removal using temporal reconstruction optimization

In this paper, we introduce an approach to remove the flickers in the videos, and the flickers are caused by applying image-based processing methods to original videos frame by frame. First, we propose a multi-frame based video flicker removal method. We utilize multiple temporally corresponding frames to reconstruct the flickering frame. Compared with traditional methods, which reconstruct the flickering frame just from an adjacent frame, reconstruction with multiple temporally corresponding frames reduces the warp inaccuracy. Then, we optimize our video flickering method from following aspects. On the one hand, we detect the flickering frames in the video sequence with temporal consistency metrics, and just reconstructing the flickering frames can accelerate the algorithm greatly. On the other hand, we just choose the previous temporally corresponding frames to reconstruct the output frames. We also accelerate our video flicker removal with GPU. Qualitative experimental results demonstrate the efficiency of our proposed video flicker method. With algorithmic optimization and GPU acceleration, the time complexity of our method also outperforms traditional video temporal coherence methods.

     

Effective wipe detection in MPEG compressed video using macro block type information

For video scene analysis, the wipe transition is considered most complex and difficult to detect. In this paper, an effective wipe detection method is proposed using the macroblock (MB) information of the MPEG compressed video. By analyzing the prediction directions of B frames, which are revealed in the MB types, the scene change region of each frame can be found. Once the accumulation of the scene change regions covers most of the area of the frame, the sequence will be considered a motionless wipe transition sequence. Besides, uncommon intracoded MB of the B frame can also be applied as an indicator of the motion wipe transition. A very simple analysis based on small amount of MB type information is sufficient to achieve wipe detection directly on MPEG compressed video. Easy extraction of MB type information, low-complexity analysis algorithm and robustness to arbitrary shape and direction of wipe transitions are the great advantages of the proposed method.     

基于最小二乘的正交距离拟合方法研究

对点云进行拟合以获得信息模型是许多工程应用领域的一个核心问题,其目的是根据设计模型和规范的要求,高精度地对三维部件、工件进行检查、检核。在最小二乘原理的基础上,阐述了一种新的拟合方法--几何正交距离拟合,运用这种方法的算法处理标准几何体测量数据,并与一般代数拟合方法处理结果进行比较,分析了同一几何体运用不同方法对拟合结果的影响。得出在测量点误差较大的情况下和进行曲线曲面拟合时,几何正交距离拟合方法优于一般代数拟合方法。