Following non-stationary distributions by controlling the vector quantization accuracy of a growing neural gas network

In this paper, an original method extended from growing neural gas (GNG-T) [B. Fritzke, A growing neural gas network learns topologies, in: G. Tesauro, D.S. Touretzky, T.K. Leen (Eds.), Advances in Neural Information Processing Systems 7, MIT Press, Cambridge, MA, 1995, pp. 625–632] is presented. The method performs continuously vector quantization over a distribution that changes over time. It deals with both sudden changes and continuous ones, and is thus suited for the video tracking framework, where continuous tracking is required as well as fast adaptation to incoming and outgoing people. The central mechanism relies on the management of the quantization resolution, that copes with stopping condition problems of usual GNG inspired methods. Application to video tracking is presented.     

Automatic composition of broadcast sports video

This study examines an automatic broadcast soccer video composition system. The research is important as the ability to automatically compose broadcast sports video will not only improve broadcast video generation efficiency, but also provides the possibility to customize sports video broadcasting. We present a novel approach to the two major issues required in the system’s implementation, specifically the camera view selection/switching module and the automatic replay generation module. In our implementation, we use multi-modal framework to perform video content analysis, event and event boundary detection from the raw unedited main/sub-camera captures. This framework explores the possible cues using mid-level representations to bridge the gap between low-level features and high-level semantics. The video content analysis results are utilized for camera view selection/switching in the generated video composition, and the event detection results and mid-level representations are used to generate replays which are automatically inserted into the broadcast soccer video. Our experimental results are promising and found to be comparable to those generated by broadcast professionals.     

Retrieval of movie scenes by semantic matrix and automatic feature weight update

A new semantic-based video scene retrieval method is proposed in this paper. Twelve low-level features extracted from a video clip are represented in a genetic chromosome and target videos that user has in mind are retrieved by the interactive genetic algorithm through the feedback iteration. In this procedure, high-level semantic relevance between retrieved videos is accumulated with so-called semantic relevance matrix and semantic frequency matrix for each iteration, and they are combined with an automatic feature weight update scheme to retrieve more target videos at the next iteration. Experiments over 300 movie scene clips extracted from latest well-known movies, showed an user satisfaction of 0.71 at the fourth iteration for eight queries such as “gloominess”, “happiness”, “quietness”, “action”, “conversation”, “explosion”, “war”, and “car chase”.     

A weighted string pattern matching-based passage ranking algorithm for video question answering

Video question answering aims to pinpoint answers in response to user’s specified questions. However, most question answering technologies involve in integrating rich specific external knowledge such as syntactic parsers, which are often unavailable for many languages. In this paper, we present a new string pattern matching-based passage ranking algorithm for extending traditional text Q/A toward videoQ/A. Users interact with our videoQ/A system through natural language questions whereas our system returns three sentence-length passages with corresponding video clips as answers. We collect 45 GB Discovery videos and 253 Chinese questions for evaluation. The experimental results showed that our method outperformed six top-performed ranking models. It is 7.39% better than the second best method (language model-based) in relatively MRR score and 6.12% in precision rate. Besides, we also show that the use of a trained Chinese word segmentation tool did decrease the overall videoQ/A performance where most ranking algorithms dropped at least 10% in relatively MRR, precision, and answer pattern recall rates.     

基于统计的SVC层间编码快速模式决策算法

可分级视频编码提供了较为灵活的编码方式,但层间模式决策算法增加了编码器的计算复杂度。该文分析了基本层和增强层间模式分布的相关性,设计一种层间编码快速模式决策算法。实验结果表明,在PSNR平均仅降低0.04 dB、码率减少0.096%的前提下,该优化算法能使编码时间平均减少50.34%。     

文化遗产视频检索系统的研究与实现

介绍文化遗产视频检索系统的设计与实现方法。描述采用MVC架构的系统的总体结构及其主要功能模块。针对网络带宽窄、视频传输数据量大的特点,提出一种新的支持基于内容的视频检索算法——基于“视频指纹”的检索方法,采用RGB颜色空间平均值作为视频特征。设计了相应的匹配检索算法,实验结果表明该算法具有较高的检索准确度,查全率比原算法提高了33.33%。     

基于MATLAB的AVI视频影像分解与压缩

为了实现对AVI(Audio Video Interleaved)文件中视频影像的分析和处理,提出了一种根据AVI文件的存储结构、利用Matlab中的音视频处理函数aviread等编程的方法,将AVI文件中的视频数据流读出并存储为一系列BMP文件,再进行小波变换压缩后写入AVI文件.利用该方法,实现了AVI视频影像的分解、合成及压缩,编程简单、数据处理可靠、程序运行高效.     

一种适于多媒体流的鲁棒性水印方案

提出一种适用于多媒体流的鲁棒性水印算法,该方案将二值图像分段后经扩频调制作为水印信息分别嵌入视频帧的DCT域和音频的DCT域.实验结果表明:算法中嵌入的水印具有良好的不可觉察性,算法复杂度低,并且能够抵抗帧删除,帧插入和帧替换等攻击.对于针对音频信号的攻击,也具有良好的鲁棒性.此外,可以参照另一信号的相应信息,恢复被破坏的水印.     

基于Single—Sequence布图规划线长约束问题的研究

布图规划是VLSI设计中非常重要的步骤。Single—Sequenc是一种非常有用的表示布图的编码方法。在实际的布图规划中,由于线长对芯片性能有较大的影响,因此为了使芯片的整体性能达到最优,考虑线长因素,使线长尽可能短。该论文提出了在用模拟退火算法寻求最优布图的同时,通过对算法加以改进,考虑线长约束条件,有效地解决了布图规划的线长约束问题。     

基于多镜头的视频行为识别方法

该文提出一种基于多摄像机信息融合的行为识别方法。新方法使用背景融合的方式融合多镜头的信息,使用背景差分提出人体目标,基于运动惯性定律解决了多目标跟踪的问题,并在行为识别中引入了人工智能和多层次分析等先进的手段。