This paper presents a novel efficient semantic image classification algorithm for high-level feature indexing of high-dimension image database. Experiments show that the algorithm performs well. The size of the train ...This paper presents a novel efficient semantic image classification algorithm for high-level feature indexing of high-dimension image database. Experiments show that the algorithm performs well. The size of the train set and the test set is 7 537 and 5 000 respectively. Based on this theory, another ground is built with 12,000 images, which are divided into three classes: city, landscape and person, the total result of the classifications is 88.92%, meanwhile, some preliminary results are presented for image understanding based on semantic image classification and low level features. The groundtruth for the experiments is built with the images from Corel database, photos and some famous face databases.展开更多
Synergic movement of finger's joints provides human hand tremendous dexterities,and the detection of kinematics parameters is critical to describe and evaluate the kinesiology functions of the fingers.The present ...Synergic movement of finger's joints provides human hand tremendous dexterities,and the detection of kinematics parameters is critical to describe and evaluate the kinesiology functions of the fingers.The present work is the attempt to investigate how the angular velocity and angular acceleration of the joints of index finger vary with respect to time during conducting a motor task.A high-speed video camera has been employed to visually record the movement of index finger,and miniaturized(5-mm diameter) reflective markers have affixed to the subject's index finger on the side close to thumb and dorsum of thumb at different joint landmarks.Captured images have been reviewed frame by frame to get the coordinate values of each joint,and the angular displacements,angular velocities and angular acceleration can be obtained with triangle function.The experiment results show that the methods here can detect the kinematics parameters of index finger joints during moving,and can be a valid route to study the motor function of index finger.展开更多
提出了一种利用"bag of words"模型对视频内容进行建模和匹配的方法。通过量化视频帧的局部特征构建视觉关键词(visual words)辞典,将视频的子镜头表示成若干视觉关键词的集合。在此基础上构建基于子镜头的视觉关键词词组的...提出了一种利用"bag of words"模型对视频内容进行建模和匹配的方法。通过量化视频帧的局部特征构建视觉关键词(visual words)辞典,将视频的子镜头表示成若干视觉关键词的集合。在此基础上构建基于子镜头的视觉关键词词组的倒排索引,用于视频片段的匹配和检索。这种方法保留了局部特征的显著性及其相对位置关系,而且有效地压缩了视频的表达,加速的视频的匹配和检索过程。实验结果表明,和已有方法相比,基于"bag of words"的视频匹配方法在大视频样本库上获得了更高的检索精度和检索速度。展开更多
对基于HTTP live streaming(简称HLS)协议的流媒体直播系统的工作原理以及结构进行了系统的介绍,利用网络数据分析仪来深入研究客户端与服务器的交互传输过程,剖析了这种技术应用于网络电视直播时所存在的视频流索引文件重复下载的冗余...对基于HTTP live streaming(简称HLS)协议的流媒体直播系统的工作原理以及结构进行了系统的介绍,利用网络数据分析仪来深入研究客户端与服务器的交互传输过程,剖析了这种技术应用于网络电视直播时所存在的视频流索引文件重复下载的冗余问题,在一定程度上造成了网络流量的浪费,降低了传输效率.针对这类问题提出了一种改善的方法——标志法,即在.m3u8文件中添加一个新标签,并通过计算推导和实验验证把改善前后的效果进行了定量分析和对比,实验结果表明该方法可有效降低流量浪费率,提高传输性能,具有较大的可行性.展开更多
根据国家乒乓球队技战术视频分析的具体需求,运用Visual Studio 2015开发环境,采用C++开发语言,MFC框架结合MYSQL数据库和XML,在Windows 10系统环境下,开发了一套"乒乓军师"专项技战术视频分析系统。该系统主要由3个模块组成...根据国家乒乓球队技战术视频分析的具体需求,运用Visual Studio 2015开发环境,采用C++开发语言,MFC框架结合MYSQL数据库和XML,在Windows 10系统环境下,开发了一套"乒乓军师"专项技战术视频分析系统。该系统主要由3个模块组成:1)技战术指标信息采集模块;2)技战术指标信息处理模块;3)报告生成模块。该系统已成功应用于国家乒乓球队,并大幅度提高了技战术采集与分析的工作效率,同时也提高了工作的准确率。除此之外该软件的成本较低,有非常广泛的应用和普及前景。展开更多
文摘This paper presents a novel efficient semantic image classification algorithm for high-level feature indexing of high-dimension image database. Experiments show that the algorithm performs well. The size of the train set and the test set is 7 537 and 5 000 respectively. Based on this theory, another ground is built with 12,000 images, which are divided into three classes: city, landscape and person, the total result of the classifications is 88.92%, meanwhile, some preliminary results are presented for image understanding based on semantic image classification and low level features. The groundtruth for the experiments is built with the images from Corel database, photos and some famous face databases.
基金Supported by the National Natural Science Foundation of China (30770546 )Natural Science Foundation of Chongqing(2006BB2043,2007BB5148)
文摘Synergic movement of finger's joints provides human hand tremendous dexterities,and the detection of kinematics parameters is critical to describe and evaluate the kinesiology functions of the fingers.The present work is the attempt to investigate how the angular velocity and angular acceleration of the joints of index finger vary with respect to time during conducting a motor task.A high-speed video camera has been employed to visually record the movement of index finger,and miniaturized(5-mm diameter) reflective markers have affixed to the subject's index finger on the side close to thumb and dorsum of thumb at different joint landmarks.Captured images have been reviewed frame by frame to get the coordinate values of each joint,and the angular displacements,angular velocities and angular acceleration can be obtained with triangle function.The experiment results show that the methods here can detect the kinematics parameters of index finger joints during moving,and can be a valid route to study the motor function of index finger.
文摘提出了一种利用"bag of words"模型对视频内容进行建模和匹配的方法。通过量化视频帧的局部特征构建视觉关键词(visual words)辞典,将视频的子镜头表示成若干视觉关键词的集合。在此基础上构建基于子镜头的视觉关键词词组的倒排索引,用于视频片段的匹配和检索。这种方法保留了局部特征的显著性及其相对位置关系,而且有效地压缩了视频的表达,加速的视频的匹配和检索过程。实验结果表明,和已有方法相比,基于"bag of words"的视频匹配方法在大视频样本库上获得了更高的检索精度和检索速度。
文摘对基于HTTP live streaming(简称HLS)协议的流媒体直播系统的工作原理以及结构进行了系统的介绍,利用网络数据分析仪来深入研究客户端与服务器的交互传输过程,剖析了这种技术应用于网络电视直播时所存在的视频流索引文件重复下载的冗余问题,在一定程度上造成了网络流量的浪费,降低了传输效率.针对这类问题提出了一种改善的方法——标志法,即在.m3u8文件中添加一个新标签,并通过计算推导和实验验证把改善前后的效果进行了定量分析和对比,实验结果表明该方法可有效降低流量浪费率,提高传输性能,具有较大的可行性.
文摘根据国家乒乓球队技战术视频分析的具体需求,运用Visual Studio 2015开发环境,采用C++开发语言,MFC框架结合MYSQL数据库和XML,在Windows 10系统环境下,开发了一套"乒乓军师"专项技战术视频分析系统。该系统主要由3个模块组成:1)技战术指标信息采集模块;2)技战术指标信息处理模块;3)报告生成模块。该系统已成功应用于国家乒乓球队,并大幅度提高了技战术采集与分析的工作效率,同时也提高了工作的准确率。除此之外该软件的成本较低,有非常广泛的应用和普及前景。
