Shareability-Exclusivity Representation on Product Grassmann Manifolds for Multi-camera video clustering

With the rapid popularity of multi-camera networks, one human action is usually captured by multiple cameras located at different angles simultaneously. Multi-camera videos contain the distinct perspectives of one action, therefore multiple views can overcome the impacts of illumination and occlusion. In this paper, we propose a novel multi-camera video clustering model, named Shareability-Exclusivity Representation on Product Grassmann Manifolds (PGM-SER), to address two key issues in traditional multi-view clustering methods (MVC): (1) Most MVC methods directly construct a shared similarity matrix by fusing multi-view data or their corresponding similarity matrices, which ignores the exclusive information in each view; (2) Most MVC methods are designed for multi-view vectorial data, which cannot handle the nonlinear manifold structure hidden in multi-camera videos. The proposed PGM-SER firstly adopts Product Grassmann Manifolds to represent multi-camera videos, then simultaneously learn their shared and exclusive information in global structures to achieve multi-camera video clustering. We provide an effective optimization algorithm to solve PGM-SER and present the corresponding convergence analysis. Finally, PGM-SER is tested on three multi-camera human action video datasets and obtain satisfied experimental results.     

基于单目双焦及SIFT特征匹配的深度估计方法

提出一种基于单目双焦及SIFT特征匹配的深度估计方法.根据空间景物的深度在不同焦距下其成像的矢量位置和对应的焦距形成几何关系的原理,通过单相机获取两幅不同焦距下的图像后,运用SIFT算法对两幅图像进行特征提取和特征匹配,得出同一景物像素点距中心点的偏移位置比,从而通过几何关系公式计算出像素点的深度值,以此获取深度图.经实验验证了该方法的可行性,实验结果表明,使用该方法获取深度值仅需单台相机这一设备,方法简单易行,且成本低,具有广阔的应用范围.     

基于TMS320DM368的高清视频采集系统设计与实现

实现了基于TMS320DM368嵌入式处理器的高清视频采集系统,详细介绍了系统的总体架构及主要的软硬件模块。首先,分析了核心处理模块性能及硬件采集模块功能;其次,描述了高清视频采集、处理及传输等模块的软件实现流程,给出了在嵌入式Linux平台下基于Web服务器移植的实现过程;最后,对系统进行测试,结果表明本系统达到了预期的高清视频采集及传输功能,图像清晰度高,实时性好,可以很方便地应用在需要高清视频监视的场合。     

视频处理在智能交通中的应用现状及发展趋势

视频处理作为智能交通中的关键技术,对智能交通系统的性能起着至关重要的作用.对视频处理在智能交通中的应用现状进行了介绍,指出视频处理在智能交通中应用面临的主要问题并对智能交通中视频处理的发展趋势做出了展望.     

基于运动矢量统计的同步视频水印算法

通过分析运动矢量的数据统计特性,提出一种基于统计的抗同步攻击视频水印算法.该算法水印信息表示空间与数据特性紧密联系,具有物理空间、时间不可划分性,克服了传统水印算法的检测器对水印同步的依赖性.实验表明,该算法具有很好的鲁棒性和不可感知性,能够抵抗帧删除等同步攻击以及基于视频内容的攻击;在帧删除率小于18%时,水印正确率大于80%.     

基于GPRS的远程视频监控系统设计

介绍基于GPRS的远程视频监控系统的整体框架及其各组成部件的功能,论述了该系统的设计思路和关键技术,并给出系统主要部件的硬软件实现.     

基于小波变换的视频编码算法分类研究

在视频通信中,视频编码技术不但要有高的编码效率而且其生成的码流要有多种可伸缩性.在此研究领域.涌现出许多新的编码思想和技术,其中基于小波变换的视频编码算法就是很有发晨前景的技术之一.本文对小波变换视频编码算法进行分类研究.对比分析算法各自的优缺点,指出小波视频编码算法的研究方向.     

一种基于DSP和FPGA的图像处理系统

设计了一种以FPGA为数据采集逻辑控制单元,以DSP为高端图像处理单元的数字图像处理系统。介绍了该系统的硬件组成、工作原理。从视频编码单元、图像处理单元和视频输出单元对整个系统的构成和设计进行了描述,分析了系统设计时的各个关键技术环节。     

Comparing the streaming of FGS encoded video at different aggregation levels: frame,GoP, and scene

Fine granularity scalability (FGS), a new coding technique that has recently been added to the MPEG‐4 video coding standard, allows for the flexible scaling of each individual video frame at very fine granularity. This flexibility makes FGS video very well suited for rate‐distortion optimized streaming mechanisms, which minimize the distortion (i.e. maximize the quality) of the streamed video by transmitting the optimal number of bits for each individual frame. The per‐frame optimization of the transmission schedule, however, puts a significant computational burden on video servers and intermediate streaming gateways. In this paper we investigate the rate‐distortion optimized streaming at different video frame aggregation levels. We find that compared to the optimization for each individual video frame, optimization at the level of video scenes reduces the computational effort dramatically, while reducing the video quality only very slightly. Copyright © 2005 John Wiley & Sons, Ltd.     

多功能教堂音视频系统设计与实现

依据智能建筑弱电工程的系统组成原理,结合某基督教堂的具体结构及业主对弱电工程的具体要求,对教堂的综合布线、视频音频的广播、录音录像、闭路电视监控等系统进行了设计与实施,结果表明,各个系统性能指标基本达到设计要求。