A Multimodal Scheme for Program Segmentation and Representation in Broadcast Video Streams

With the advance of digital video recording and playback systems, the request for efficiently managing recorded TV video programs is evident so that users can readily locate and browse their favorite programs. In this paper, we propose a multimodal scheme to segment and represent TV video streams. The scheme aims to recover the temporal and structural characteristics of TV programs with visual, auditory, and textual information. In terms of visual cues, we develop a novel concept named program-oriented informative images (POIM) to identify the candidate points correlated with the boundaries of individual programs. For audio cues, a multiscale Kullback-Leibler (K-L) distance is proposed to locate audio scene changes (ASC), and accordingly ASC is aligned with video scene changes to represent candidate boundaries of programs. In addition, latent semantic analysis (LSA) is adopted to calculate the textual content similarity (TCS) between shots to model the inter-program similarity and intra-program dissimilarity in terms of speech content. Finally, we fuse the multimodal features of POIM, ASC, and TCS to detect the boundaries of programs including individual commercials (spots). Towards effective program guide and attracting content browsing, we propose a multimodal representation of individual programs by using POIM images, key frames, and textual keywords in a summarization manner. Extensive experiments are carried out over an open benchmarking dataset TRECVID 2005 corpus and promising results have been achieved. Compared with the electronic program guide (EPG), our solution provides a more generic approach to determine the exact boundaries of diverse TV programs even including dramatic spots.     

形象广告片在电视媒体中的定位

和其他的传媒类型相比,影像有着与生俱来的优势,直观而富有冲击力,好的形象广告片应该做到的是有效传播,不仅要让受众被该片吸引,还应该使其产生一定的认可度和归属感,该文想通过对形象广告片的特性包括与功能广告之间的区别来阐述形象广告片在电视媒体中的定位,使形象广告片成为引动我们的认知,产生情感偏好的重要传播载体,使其散发出经典隽永的魅力。     

一种体育视频中广告牌商标的实时识别算法

近期, 体育视频分析中的广告牌商标的探测和识别方法已经广泛应用于许多其他领域, 比如商业电视. 基于此, 提出了一种能在不同体育视频(如足球、篮球和F1赛车等)中进行广告牌商标实时识别的算法, 该算法主要包括两个步骤, 首先, 利用基于模糊决策树的方法进行广告牌图像帧的探测; 其次, 利用颜色特征和局部SIFT (Scale-invariant feature transform)特征来描述不同商标的外观, 并最终通过基于潜在语义分析(Latent semantic analysis, LSA)的SIFT词汇匹配来识别所给定的商标模板. 初步的实验表明了本文算法的有效性, 并且该算法能在实时情况下运行.     

基于镜头的鲁棒视频广告检测

随着多媒体技术的发展，自动检测出数字视频节目里面嵌入的广告是很具挑战性的研究．然而，由于嵌入的广告的制作方式和表现手法的多样性，很多自动检测模型的实验结果往往不甚理想．为了提高检测系统的鲁棒性，提出了3阶段广告检测系统．首先，提出了基于区域特征重要性的镜头检测算法（RBFID，region-based feature importance detection），实现视频播放中突变镜头和消隐镜头的检测，同时从每个镜头提取出一些统计特征用来标识镜头．然后，利用SVM的优异分类特性实现镜头分类．最后为了能得到精确的广告视频段，利用广告视频在内容和时间上的连续性来消除错分的镜头，然后将广告镜头整合成广告视频段．本系统在30个电视节目的片段上进行验证，实验结果表明此广告检测系统具有实用性．     

Shot Partitioning Based Recognition of TV Commercials

Digital video applications exploit the intrinsic structure of video sequences. In order to obtain and represent this structure for video annotation and indexing tasks, the main initial step is automatic shot partitioning. This paper analyzes the problem of automatic TV commercials recognition, and a new algorithm for scene break detection is then introduced. The structure of each commercial is represented by the set of its key-frames, which are automatically extracted from the video stream. The particular characteristics of commercials make commonly used shot boundary detection techniques obtain worse results than with other video content domains. These techniques are based on individual image features or visual cues, which show significant performance lacks when they are applied to complex video content domains like commercials. We present a new scene break detection algorithm based on the combined analysis of edge and color features. Local motion estimation is applied to each edge in a frame, and the continuity of the color around them is then checked in the following frame. By separately considering both sides of each edge, we rely on the continuous presence of the objects and/or the background of the scene during each shot. Experimental results show that this approach outperforms single feature algorithms in terms of precision and recall.     

MiSPOT: dynamic product placement for digital TV through MPEG-4 processing and semantic reasoning

In an increasingly competitive market, stakeholders of the television industry strive to exploit all the possibilities to get revenues from advertising, but their practices are usually at odds with the comfort of the TV viewers. This paper presents the proof of concept of MiSPOT, a system that brings a non-invasive and fully personalized form of advertising to Interactive Digital TV, targeting both domestic and mobile receivers. MiSPOT employs semantic reasoning techniques to select advertisements suited to the preferences, interests and needs of each individual viewer, and then relies on multimedia composition abilities to blend the advertising material with the TV program he/she is viewing at any time. The advertisements can be set to launch interactive commercials, thus enabling means for the provision of t-commerce services. Evaluation experiments are described to show the technical viability of the proposal, and also to gauge the opinions of end users. Questions about the potential impact and exploitation of this new form of advertising are addressed too.     

一种基于音频匹配的广告检测算法

广告检测是指从电视节目中自动地检测出广告序列。传统方法使用基于计算机视觉算法的技术框架对视频内容进行广告检测,无法在性能和效率上满足商业化需求。本算法仅利用广告音频信息完成广告检测工作。首先抽取广告库的原始音频信息,使用短时傅里叶变换将其转化为声谱图,再应用预筛选的滤波器集合进行二值化,得到局部特征描述子,组成广告音频库;其次在广告检测过程中,以同样方法提取其特征描述子,在广告音频库中检索得到检测结果。基于音频匹配的广告检测算法具有存储小、准确度高、实时性强等诸多优点。实验表明该算法可以显著提高广告检测系统的鲁棒性和性能,可应用于现实场景中。     

支持文本识别与取词的DVD播放软件的设计与实现

DVD视频提供丰富的文本资源,但是由于其文本信息是以图片的形式存储的,目前的播放软件不能提供针对文本信息的识别和查询.通过对包含字幕数据的私有流1的分析,总结了字幕数据的存储格式和访问接口,给出了字幕流的提取和解码算法,提出了自动化的文本识别方法,并且以MPEG-2解码器为核心设计了一种支持文本识别和查询的DVD播放软件,最后利用DirectX技术实现了该播放软件.     

基于自适应薄板样条全变分的肺CT/PET图像配准

全变分正则项虽然能够在具有滑移运动的肺等胸腹部器官图像配准时校正边界不连续位移场，但仍然无法保留图像的局部特征，损失配准精度。针对肺图像CT单模配准和CT/PET双模配准，通过像素点空间位置权重将薄板样条能量算子与全变分算子进行空间加权建立自适应薄板样条全变分正则项。然后，将正则项与CRMI相似性测度以及L-BFGS优化方法结合建立非刚性配准算法。通过DIR-Lab 4D-CT公共数据集和CT/PET临床数据集上的实验结果表明，提出的方法能够在保证边界不连续运动的同时保证图像内部的平滑性，具有更高的配准精度。     

用C程序生成中英文字幕对照文件

通过C程序对分别从网上下载的中、英文字幕文件,借助于文件中字幕显示时间信息,对两文件进行排序合并,生成的文件拥有中英文逐句对照效果,对学习英语很有帮助。     

On the trail of the shadow woman: the mystery of motion capture

Motion capture houses throw away the person and keep the shadow-the essence of their motion-and apply that motion to animate all kinds of characters. In the past few years, as the technology has become less expensive and at the same time more accurate, MoCap has helped lessen the rigors of traditional cell animation-especially in highly cost-conscious projects like TV commercials. A MoCap studio can use both magnetic and optical capture systems. Each has certain advantages. The magnetic system handles shoots that don't need really high accuracy, and the director wants to be able to apply the data to his character in real time. Magnetic systems generally are faster at providing data to use in animation, though optical systems are generally more accurate and can track more points. That may be changing, though     

Personalized and mobile digital TV applications

The introduction of mobile and broadband networks in complement to the existing satellite, cable, and terrestrial platforms, opens new opportunities for interactive TV (ITV) applications. In addition, the widespread adoption of multimedia computing has enabled the processing of TV content on personal devices such as mobile phones and PCs. The above developments raise novel issues and require the adoption of new multimedia standards and application frameworks. In particular, the explosion in the amount of available TV channels over digital television platforms (broadcast or internet protocol) makes searching and locating interesting content a cumbersome task. In this context, personalization research is concerned with the adaptation of content (e.g. movies, news, advertisements). Personalization is achieved with the employment of algorithms and data collection schemes that predict and recommend to television viewers content that match their interests. In addition, the distribution of TV content to mobile devices over broadband wireless raises the issue of video quality. Video quality depends on many aspects of the video encoding systems, such as bit rate and algorithms that model human perception of video on small screens. In this article, we examine contemporary research in personalized and mobile digital TV applications. Moreover, we present a critical survey of the most prominent research and provide directions for further research in personalized and mobile digital TV (DTV) applications.     

Minimum-phase criterion on sampling time for sampled-data interval systems using genetic algorithms

In this paper, a genetic algorithm-based approach is proposed to determine a desired sampling-time range which guarantees minimum phase behaviour for the sampled-data system of an interval plant preceded by a zero-order hold (ZOH). Based on a worst-case analysis, the identification problem of the sampling-time range is first formulated as an optimization problem, which is subsequently solved under a GA-based framework incorporating two genetic algorithms. The first genetic algorithm searches both the uncertain plant parameters and sampling time to dynamically reduce the search range for locating the desired sampling-time boundaries based on verification results from the second genetic algorithm. As a result, the desired sampling-time range ensuring minimum phase behaviour of the sampled-data interval system can be evolutionarily obtained. Because of the time-consuming process that genetic algorithms generally exhibit, particularly the problem nature which requires undertaking a large number of evolution cycles, parallel computation for the proposed genetic algorithm is therefore proposed to accelerate the derivation process. Illustrated examples in this paper have demonstrated that the proposed GA-based approach is capable of accurately locating the boundaries of the desired sampling-time range.     

音视频相结合的广告检测算法

利用广告最后一帧的特点,提出了一种新颖的音视频相结合的广告检测的方法。在镜头分割的基础上,运用基于SVM的FMPI（有产品信息的图像帧）检测与静音段检测相结合的方法检测广告区域最后一帧。根据检测出来的结果确定广告的开始位置和结束位置,从而确定广告区域。实验结果表明,该方法不仅具有较高的准确率和查全率,而且解决了以往广告检测边缘定位不准的问题。     

OTT TV的发展阶段和业务模式研究

首先阐明OTT TV的概念、产业链构成,然后结合产业链和监管政策的演进对OTT Tv业务发展阶段进行了划分,并具体分析了每一阶段产业链各方对于OTT业务模式的探索实践,最后提出OTT Tv的5种业务模式,并分析其盈利能力和演进方向,以供业界参考。     

Quality is in the eye of the stakeholders: what do professional subtitlers and viewers think about subtitling?

Quality is a rather slippery concept, and its assessment in subtitling can be a challenging task, as its appreciation can easily vary depending on the different stakeholders involved in the production and reception of subtitles. In this paper, we evaluate quality indicators in subtitling as perceived by professional subtitlers and viewers. After exploring the various subtitle parameters that can have an impact on the quality of the end product (such as line breaks, synchronisation, display rates), we present the results of two qualitative studies conducted with professional subtitlers and subtitle viewers with different audiovisual backgrounds. The results yield some similarities and discrepancies, particularly in the way in which the strategy of condensation is perceived by the two groups, and they also help delineate the subtitle parameters that should be taken into consideration in order to improve the creative process as well as the reception of subtitles.