基于黎曼度量结构相似度的图像质量评价方法

图像最主要的是其结构特性,人类的视觉系统是从图像结构上获得图像信息,为了更好的对图像的质量进行评价,本文在SSM模型的基础上提出一种基于黎曼度量的结构相似度评价,把图像置于黎曼流形中进行讨论.实验结果表明本文提出的方法比SSM模型更有区分度,更符合人类视觉系统的特性.     

一种基于结构相似度的多视点码率分配方法

多视点视频编码是当前视频编码领域的研究热点之一。在有限的网络带宽下,合理的码率分配可以提高视频主观视觉质量。本文提出一种基于结构相似度的码率分配方法,首先对视频帧提取基于结构相似度的显著图,然后结合显著图对重要宏块和非重要宏块分配不同的QP值,以达到码率分配的目的。实验结果表明,本文方法在有限的带宽下能有效的提高多视点视频的视觉主观质量。     

VIDEO MOTION CAPTURE IN VBA——VIDEO-BASED ANIMATION

ＩＮＴＲＯＤＵＣＴＩＯＮＭｏｔｉｏｎｃａｐｔｕｒｅｐｌａｙｓａｎｉｍｐｏｒｔａｎｔｒｏｌｅｉｎｔｈｅｃｒｅａｔｉｏｎｏｆｓｐｅｃｉａｌｅｆｆｅｃｔｓｉｎｍａｎｙｆｉｅｌｄｓ.Ａｓｉｄｅｆｒｏｍｕｓｅｉｎｆｉｌｍｓａｎｄａｎｉｍａｔｉｏｎｓ,ｍｏｔｉｏｎｃａｐｔｕｒｅｈａｓｃｏｍｐｒｅｈｅｎｓｉｖｅａｐｐｌｉｃａｔｉｏｎｓｉｎｔｈｅａｎａｌｙｓｉｓｏｆａｔｈｌｅｔｅｐｅｒｆｏｒｍａｎｃｅ ,ｍｅｄｉｃａｌｄｉａｇｎｏｓｔｉｃｓ,ｓｕｒｖｅｉｌｌａｎｃｅ ,ｖｉｄｅｏｒｅｔｒｉｅｖａｌ,ｅｔｃ.Ｃｏｎｖｅｎ…     

VIDEO MOTION CAPTURE IN VBA

Computer vision has very wide application in human motion capture research. This paper proposes a new approach to do motion capture in video. It is composed of image sequence based tracking of human feature points and the reconstruction of the three-dimension(3D) motion skeleton. First, every part of the human body from top to bottom is tracked on the basis of a human model. The image difference and a morph-block similarity algorithm based on subpixels are used. Then camera calibration is done using the line correspondences between the 3D model and the image. Finally the 3D motion skeleton is established by use of the model knowledge. This approach does not aim at a given mode of human motion. Rather, it analyzes large scale motion from frame to frame in complex, variational background, and sets up a 3D motion skeleton in the perspective projection. The experiment results are presented at the end of the paper. Project (69803009) supported by Natural Science Foundation of China (NSFC) and Key Project of National Development Planning Committee.     

A fast block-matching algorithm based on variable shape search

INTRODUCTION Block-matching motion estimation is a key video coding technology that reduces the temporal redundancy between adjacent frames. The 3GPP/ 3GPP2 mandatory video codecs (MPEG-4 Simple Profile or H.263 Baseline) have adopted this tech- nology extensively. However, block-matching motion estimation is quite computationally intensive if the Full Search (FS) algorithm is used which exhaus- tively checks all possible candidate motion vectors within the search window. Therefore…     

A channel distortion model for video over lossy packet networks

Error-resilient video communication over lossy packet networks is often designed and operated based on models for the effect of losses on the reconstructed video quality. This paper analyzes the channel distortion for video over lossy packet networks and proposes a new model that, compared to previous models, more accurately estimates the expected mean-squared error distortion for different packet loss patterns by accounting for inter-frame error propagation and the correlation between error frames. The accuracy of the proposed model is validated with JVT/H.264 encoded standard test sequences and previous frame concealment, where the proposed model provides an obvious accuracy gain over previous models.     

A channel distortion model for video over lossy packet networks

Error-resilient video communication over lossy packet networks is often designed and operated based on models for the effect of losses on the reconstructed video quality. This paper analyzes the channel distortion for video over lossy packet networks and proposes a new model that, compared to previous models, more accurately estimates the expected mean-squared error distortion for different packet loss patterns by accounting for inter-frame error propagation and the correlation between error frames. The accuracy of the proposed model is validated with JVT/H.264 encoded standard test sequences and previous frame concealment, where the proposed model provides an obvious accuracy gain over previous models.     

一种基于二次变换运动预测的有损分割图轮廓编码

1　 Ｉｎｔｒｏｄｕｃｔｉｏｎ　Ｔｈｅｉｎｔｅｒｅｓｔｉｎｖｅｒｙｌｏｗｂｉｔ ｒａｔｅｖｉｄｅｏｃｏｄｉｎｇｈａｓｉｎ ｃｒｅａｓｅｄｃｏｎｓｉｄｅｒａｂｌｙｗｉｔｈｔｈｅｃｒｅａｔｉｏｎｏｆｎｅｗｓｅｒｖｉｃｅｓａｎｄａｐｐｌｉｃａｔｉｏｎｓｒｅｑｕｉｒｉｎｇｔｈｉｓｃｌａｓｓｏｆｂｉｔｒａｔｅｓｉｎｔｈｅｉｒｆｕｎｃｔｉｏｎ .Ｗｉｔｈｔｈｉｓｔｒｅｎｄ ,ｏｂｊｅｃｔ ｏｒｉｅｎｔｅｄｖｉｄｅｏｃｏｄｉｎｇｗａｓｆｉｒｓｔｐｒｏｐｏｓｅｄｂｙＭｕｓｍａｎｎｅｔａｌ.ｉｎ 1989[1 ],ａｎｄｈａｓｂｅｅ…     

视觉注意的数据包优先级排序策略研究

为了提高视频流传输效率,本文提出一种基于视觉注意的数据包优先级排序策略。本文排序策略主要包括三个过程：首先,根据率失真理论计算数据包客观重要性;其次,通过分析视频镜头中视觉转移特性确定视频帧的时空显著图,采用灵活宏块排序技术将显著区域与背景区域分离,并根据数据包所包含区域的时空显著度确定数据包主观重要性;最后综合数据包主客观重要性得出数据包的最终优先级。实验结果表明,本文方法能够有效提高视频流的主观重建图像质量。     

Media-specific rate allocation in heterogeneous wireless networks

INTRODUCTION With the development of novel wireless tech- nologies and increasing available bandwidth, multi- media applications over wireless networks become attractive for both businesses and end users. Fast de- ployment of Wi-Fi HotSpots, increase in wireless coverage of remote habitable areas (Wi-Max, or wireless mesh networks), improved data services over the 2G cellular systems and the long awaited debut of 3G wireless services offer many potential and inter- operable communicatio…     

A network-aware error-resilient method using prioritized intra refresh for wireless video communications

We propose a novel prioritized intra refresh method for the wireless video communication. The proposed method considers the characteristics of the human visual system, the error-sensitivity of the bitstream, and the state of the time-varying wireless channel jointly. An expected perceptual distortion model was used to adjust the intra refresh rate adaptively. This model consists of the perceptual weight map based on an attention model, the bit error probability map based on bitstream size, and the dynamic channel state information （CSI）. Experimental results indicate that, compared with other intra refresh methods that consider only the content of the video or the CSI, the proposed method improves the average peak signal-to-noise ratio （PSNR） of the whole frame by about 0.5 dB, and improves the average PSNR of the attention-area by about 0.8 dB.     

Edge-oriented compression coding on image sequence

１　Ｉｎｔｒｏｄｕｃｔｉｏｎ　Ｉｎｉｍａｇｅｃｏｍｐｒｅｓｓｉｏｎｃｏｄｉｎｇｓｃｈｅｍｅｓ,ｖａｒｉｏｕｓｉｍａｇｅｃｏｄｉｎｇｔｅｃｈｎｉｑｕｅｓｓｕｃｈａｓｔｒａｎｓｆｏｒｍｃｏｄｉｎｇｈａｖｅｂｅｅｎｄｅｖｅｌｏｐｅｄ．Ｗｈｉｌｅｔｈｅｓｅｔｅｃｈｎｉｑｕｅｓｈａｖｅｌｅｄｔｏｒｅｌａｔｉｖｅｌｙｈｉｇｈｑｕａｌｉｔｙｒｅｃｏｎｓｔｒｕｃｔｅｄｉｍａｇｅｓａｔｂｉｔｒａｔｅｓａｒｏｕｎｄ１．０ｂ／ｐｉｘｅｌｏｒｍｏｒｅ,ｔｈｅｙｓｏｍｅｔｉｍｅｓｐｒｏｄｕｃｅｓｐｅｃｉｆｉｃｔｙｐｅｏｆ…     

Distortion identification technique based on Hilbert-Huang transform in video stabilization

A distortion identification technique is presented based on Hilbert-Huang transform to identify distortion model and distortion frequency of distorted real-world image sequences. The distortion model is identified simply based on Hilbert marginal spectral analysis after empirical mode decomposing. And distortion frequency is identified by analyzing the occurrence frequency of instantaneous frequency components of every intrinsic mode functions. Rational digital frequency filter with suitable cutoff frequency is designed to remove undesired fluctuations based on identification results. Experimental results show that this technique can identify distortion model and distortion frequency of displacement sequence accurately and efficiently. Based on identification results, distorted image sequence can be stabilized effectively.     

Adaptive foreground and shadow segmentation using hidden conditional random fields

Video object segmentation is important for video surveillance, object tracking, video object recognition and video editing. An adaptive video segmentation algorithm based on hidden conditional random fields (HCRFs) is proposed, which models spatio-temporal constraints of video sequence. In order to improve the segmentation quality, the weights of spatio-temporal con- straints are adaptively updated by on-line learning for HCRFs. Shadows are the factors affecting segmentation quality. To separate foreground objects from the shadows they cast, linear transform for Gaussian distribution of the background is adopted to model the shadow. The experimental results demonstrated that the error ratio of our algorithm is reduced by 23% and 19% respectively, compared with the Gaussian mixture model (GMM) and spatio-temporal Markov random fields (MRFs).     

面向Adhoc网络的视频多描述编码及其传输方法

为增强无线多跳网络（Ad hoc网络）中视频传输的抗误码性能,提出了一种面向Ad hoc网络的视频多描述编码及其传输方法。首先,通过判断两个相邻帧运动矢量的差值,自适应地在视频序列中插入参考帧以提高帧间编码效率;然后分别抽取出视频序列中的奇数帧和偶数帧形成两个描述;最后,在确保传输路径可靠性的基础上,选取两个质量较高的节点不相交路径分别传输视频序列的两个描述,以提高视频传输的可靠性。OPNET Modeler中的仿真实验结果表明,与目前Ad hoc网络中典型的多描述编码及传输方法MDC_AODV相比,本文提出的方法有效地增强了视频传输的抗误码性,提高了接收端的视频质量。     

基于面部图像的非接触式婴儿心率监测

为实现便捷、可靠的日常婴儿心率实时监测,提出一种基于面部图像的非接触式婴儿心率实时监测方法。首先引入欧拉视频放大技术,对一定时间间隔内视频的每一帧图像进行颜色增强处理,从而改善婴儿面部颜色变化微弱、所含心率信息不明显的问题;然后,通过Adaboost算法从每一视频帧中识别出婴儿面部,并从婴儿面部选取脸颊区域作为敏感区域以提取脉搏波信号,以此为基础提出一种改进的反射光强模型,抑制日间因环境光变化引起的干扰以及运动噪声干扰,提高脉搏波信号信噪比;此外采用摄像头的红外自主光源,通过一种基于相空间重构的单通道独立成分分析法分离夜间脉搏波信号的运动噪声,解决因夜间光照条件差引起的婴儿心率监测困难的问题;最后开发整个系统上位机应用程序,并通过实验验证该方法正确性和有效性。     

基于运动连通性的初始视频对象提取

为了从视频序列中获取初始视频对象,提出了一种改进的基于运动连通性的初始视频对象提取算法.视频中的运动对象高度连通结构化,这就使得运动连通性是适用于视频对象分割的高级特征.据此首先对反映对象的一致性运动的累计帧差图进行尖锐噪声滤除,然后应用自适应阈值算法提取对象运动区域,接着根据运动连通性标记出最大连通区域,通过后处理得到视频对象的分割模版从而有效提取出初始视频对象.对比实验结果表明,该算法能自动、快速、准确地提取出初始视频对象,获得了理想的主客观分割效果.     

基于加权的运动矢量恢复差错掩盖算法

为了解决视频图像在传输过程中产生运动矢量丢失问题,本文提出一种新的后处理差错掩盖算法。我们在DCT域进行边缘检测,把与丢失块相邻的图像块分为边缘块和平滑块,同时把丢失块周围的图像块运动矢量的大小和方向分成九类。结合边缘检测与运动矢量分类,我们提出一种加权运动矢量恢复算法。仿真结果表明对不同视频序列,此算法都能比传统的方法恢复出质量更高的图像。     

一种有效的基于运动矢量场的压缩域运动对象分割算法

In this paper an efficient compressed domain moving object segmentation algorithm is proposed, in which the motion vector (MV) field parsed from the compressed video is the only cue used for moving object segmentation. First the MV field is temporally and spatially normalized, and then accumulated by an iterative backward projection to enhance salient motions and alleviate noisy MVs. The accumulated MV field is then segmented into motion-homogenous regions using a modified statistical region growing approach. Finally, moving object regions are extracted in turn based on minimization of the joint prediction error using the estimated motion models of two region sets containing the candidate object region and other remaining regions, respectively. Experimental results on several H.264 compressed video sequences demonstrate good segmentation performance.     

数字化课堂教学测评技术初探——软信息等级判据评估

课堂教学的多因素综合评估是个复杂问题,是一个软信息的、多判据的决策过程。用模糊数学方法建立的人工智能评估模型可以较为全面地对课堂教学进行评估。使用改进后模型编制的软件对若干数学录像课做分析,结果表明,软信息等级判据评估有望克服简单加权平均的弊端。