专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US08938393B2 Extended videolens media engine for audio recognition 有权
标题翻译：用于音频识别的扩展视频媒体引擎
公开(公告)号：US08938393B2
公开(公告)日：2015-01-20
申请号：US13171246
申请日：2011-06-28
申请人： Priyan Gunatilake , Djung Nguyen , Abhishek Patil , Dipendu Saha
发明人： Priyan Gunatilake , Djung Nguyen , Abhishek Patil , Dipendu Saha
IPC分类号： G10L21/00 , G10L15/00 , G10L17/00 , H04N7/18 , G06F17/30 , G06F3/00 , G10L17/08 , G10L15/26 , H04N21/439 , H04N21/84 , G10L25/81
CPC分类号： G10L17/08 , G10L15/26 , G10L25/81 , H04N21/4394 , H04N21/84
摘要： A system, method, and computer program product for automatically analyzing multimedia data audio content are disclosed. Embodiments receive multimedia data, detect portions having specified audio features, and output a corresponding subset of the multimedia data and generated metadata. Audio content features including voices, non-voice sounds, and closed captioning, from downloaded or streaming movies or video clips are identified as a human probably would do, but in essentially real time. Particular speakers and the most meaningful content sounds and words and corresponding time-stamps are recognized via database comparison, and may be presented in order of match probability. Embodiments responsively pre-fetch related data, recognize locations, and provide related advertisements. The content features may be also sent to search engines so that further related content may be identified. User feedback and verification may improve the embodiments over time.
摘要翻译：公开了一种用于自动分析多媒体数据音频内容的系统，方法和计算机程序产品。实施例接收多媒体数据，检测具有指定音频特征的部分，并输出多媒体数据和生成的元数据的相应子集。来自下载或流式电影或视频剪辑的包括语音，非语音和隐藏字幕的音频内容特征被识别为人可能会做，但基本上是实时的。通过数据库比较来识别特定的扬声器和最有意义的内容声音和单词和相应的时间戳，并且可以按照匹配概率的顺序呈现。实施例响应式预取相关数据，识别位置并提供相关广告。内容特征也可以被发送到搜索引擎，使得可以识别进一步的相关内容。用户反馈和验证可以随时间改进实施例。

2. 发明授权

US08891370B2 Method and apparatus for transmitting a coded video signal 有权
标题翻译：用于发送编码视频信号的方法和装置
公开(公告)号：US08891370B2
公开(公告)日：2014-11-18
申请号：US13717554
申请日：2012-12-17
申请人： Priyan Gunatilake
发明人： Priyan Gunatilake
IPC分类号： H04L12/26 , H04N21/44 , H04N21/658 , H04N21/234 , H04N19/149 , H04N21/6377
CPC分类号： H04N19/503 , H04N19/149 , H04N21/23406 , H04N21/44004 , H04N21/6377 , H04N21/658
摘要： A method and apparatus for transmitting a digitally encoded video image in real time wherein the video image is digitally encoded using a compression algorithm having a variable bit rate, e.g., JPEG2K, to provide an encoded data stream, the encoded data stream is fed into a buffer of known size, and the data is read from the buffer via a streamer with a controllable bit rate to provide a bit stream at a desired stream bit rate for transmission. The bit rate of the encoded data stream from the encoder is monitored by a predictor and predicts a future bit rate of the encoded data stream; and, the bit rate of at least one of the encoder and the streamer is adjusted to provide the desired streaming bit rate wherein the predicting of the future bit rate is carried out using a prediction model based on a smoothed bit rate vs. time curve of the encoded data stream.
摘要翻译：一种用于实时传输数字编码视频图像的方法和装置，其中使用具有可变比特率的压缩算法（例如，JPEG2K）对视频图像进行数字编码，以提供编码数据流，编码数据流被馈送到具有已知尺寸的缓冲器，并且通过具有可控比特率的流分配器从缓冲器读取数据，以提供所需流比特率以便传输。来自编码器的编码数据流的比特率由预测器监视并预测编码数据流的未来比特率; 并且，调整编码器和流送器中的至少一个的比特率以提供期望的流比特率，其中使用基于平滑比特率对时间曲线的预测模型来执行未来比特率的预测编码数据流。

3. 发明授权

US07983160B2 Method and apparatus for transmitting a coded video signal 失效
标题翻译：用于发送编码视频信号的方法和装置
公开(公告)号：US07983160B2
公开(公告)日：2011-07-19
申请号：US10935163
申请日：2004-09-08
申请人： Priyan Gunatilake
发明人： Priyan Gunatilake
IPC分类号： H04L12/26
CPC分类号： H04N19/503 , H04N19/149 , H04N21/23406 , H04N21/44004 , H04N21/6377 , H04N21/658
摘要： A method and apparatus for transmitting a digitally encoded video image in real time via a data network wherein the video image is digitally encoded using a compression algorithm having a variable bit rate, e.g., JPEG2K, to provide an encoded data stream, the encoded data stream is fed into a buffer of known size, and the data is read from the buffer via a streamer with a controllable bit rate to provide a bit stream at a desired stream bit rate for transmission via the network. The bit rate of the encoded data stream from the encoder is monitored by a predictor and predicts a future bit rate of the encoded data stream; and, the bit rate of at least one of the encoder and the streamer is adjusted to provide the desired streaming bit rate.
摘要翻译：一种用于经由数据网络实时地发送数字编码视频图像的方法和装置，其中使用具有可变比特率的压缩算法（例如JPEG2K）对视频图像进行数字编码，以提供编码数据流，编码数据流被馈送到已知尺寸的缓冲器中，并且经由具有可控比特率的流分配器从缓冲器读取数据，以便以期望的流比特率提供用于经由网络传输的比特流。来自编码器的编码数据流的比特率由预测器监视并预测编码数据流的未来比特率; 并且，调整编码器和流送器中的至少一个的比特率以提供期望的流比特率。

4. 发明授权

US08959071B2 Videolens media system for feature selection 有权
标题翻译：视频媒体系统进行功能选择
公开(公告)号：US08959071B2
公开(公告)日：2015-02-17
申请号：US13171223
申请日：2011-06-28
申请人： Priyan Gunatilake
发明人： Priyan Gunatilake
IPC分类号： G06F17/30 , G06K9/00
CPC分类号： G06K9/00744 , G06F17/30784 , G06T7/20 , G06T2207/20021 , G10L15/26 , G10L2025/783 , H04N5/91 , Y10S707/914
摘要： A system, method, and computer program product for automatically analyzing multimedia data are disclosed. Embodiments receive multimedia data, detect portions having specified features, and output a corresponding subset of the multimedia data. Content features from downloaded or streaming movies or video clips are identified as a human probably would do, but in essentially real time. Embodiments then generate an index or menu based on individual consumer preferences. Consumers can peruse the index, or produce customized trailers, or edit and tag content with metadata as desired. The tool can categorize and cluster content by feature, to assemble a library of scenes or scene clusters according to user-selected criteria. The results may be sent to visual search engines so that further related content may be identified for use as a customized trailer, replacement content for advertisements, or as material to be shared with others.
摘要翻译：公开了一种用于自动分析多媒体数据的系统，方法和计算机程序产品。实施例接收多媒体数据，检测具有指定特征的部分，并输出多媒体数据的相应子集。来自下载或流式电影或视频剪辑的内容功能被识别为人类可能会做的，但基本上是实时的。然后，实施例基于个体消费者喜好生成索引或菜单。消费者可以根据需要细读索引或生成自定义预告片，或者使用元数据编辑和标记内容。该工具可以按功能对内容进行分类和集群，根据用户选择的标准组装场景或场景集群。结果可以被发送到视觉搜索引擎，使得可以识别进一步的相关内容以用作定制预告片，用于广告的替换内容，或作为与他人共享的材料。

5. 发明申请

US20120117046A1 VIDEOLENS MEDIA SYSTEM FOR FEATURE SELECTION 有权
标题翻译：用于特征选择的视频媒体系统
公开(公告)号：US20120117046A1
公开(公告)日：2012-05-10
申请号：US13171223
申请日：2011-06-28
申请人： Priyan Gunatilake
发明人： Priyan Gunatilake
IPC分类号： G06F17/30
CPC分类号： G06K9/00744 , G06F17/30784 , G06T7/20 , G06T2207/20021 , G10L15/26 , G10L2025/783 , H04N5/91 , Y10S707/914
摘要： A system, method, and computer program product for automatically analyzing multimedia data are disclosed. Embodiments receive multimedia data, detect portions having specified features, and output a corresponding subset of the multimedia data. Content features from downloaded or streaming movies or video clips are identified as a human probably would do, but in essentially real time. Embodiments then generate an index or menu based on individual consumer preferences. Consumers can peruse the index, or produce customized trailers, or edit and tag content with metadata as desired. The tool can categorize and cluster content by feature, to assemble a library of scenes or scene clusters according to user-selected criteria. The results may be sent to visual search engines so that further related content may be identified for use as a customized trailer, replacement content for advertisements, or as material to be shared with others.
摘要翻译：公开了一种用于自动分析多媒体数据的系统，方法和计算机程序产品。实施例接收多媒体数据，检测具有指定特征的部分，并输出多媒体数据的相应子集。来自下载或流式电影或视频剪辑的内容功能被识别为人类可能会做的，但基本上是实时的。然后，实施例基于个体消费者喜好生成索引或菜单。消费者可以根据需要细读索引或生成自定义预告片，或者使用元数据编辑和标记内容。该工具可以按功能对内容进行分类和集群，根据用户选择的标准组装场景或场景集群。结果可以被发送到视觉搜索引擎，使得可以识别进一步的相关内容以用作定制预告片，用于广告的替换内容，或作为与他人共享的材料。

6. 发明申请

US20120114233A1 VIDEOLENS MEDIA ENGINE 有权
标题翻译：视频媒体引擎
公开(公告)号：US20120114233A1
公开(公告)日：2012-05-10
申请号：US13171176
申请日：2011-06-28
申请人： Priyan Gunatilake
发明人： Priyan Gunatilake
IPC分类号： G06K9/46 , G06K9/36 , G06K9/00 , G10L15/26
CPC分类号： G06K9/00744 , G06F17/30784 , G06T7/20 , G06T2207/20021 , G10L15/26 , G10L2025/783 , H04N5/91 , Y10S707/914
摘要： A system, method, and computer program product for automatically analyzing multimedia data are disclosed. Embodiments receive multimedia data, detect portions having specified features, and output a corresponding subset of the multimedia data. Content features from downloaded or streaming movies or video clips are identified as a human probably would do, but in essentially real time. Embodiments then generate an index or menu based on individual consumer preferences. Consumers can peruse the index, or produce customized trailers, or edit and tag content with metadata as desired. The tool can categorize and cluster content by feature, to assemble a library of scenes or scene clusters according to user-selected criteria.
摘要翻译：公开了一种用于自动分析多媒体数据的系统，方法和计算机程序产品。实施例接收多媒体数据，检测具有指定特征的部分，并输出多媒体数据的相应子集。来自下载或流式电影或视频剪辑的内容功能被识别为人类可能会做的，但基本上是实时的。然后，实施例基于个体消费者喜好生成索引或菜单。消费者可以根据需要细读索引或生成自定义预告片，或者使用元数据编辑和标记内容。该工具可以按功能对内容进行分类和集群，根据用户选择的标准组装场景或场景集群。

7. 发明申请

US20070081592A1 Systems and methods for enhanced coding gain 有权
标题翻译：增强编码增益的系统和方法
公开(公告)号：US20070081592A1
公开(公告)日：2007-04-12
申请号：US11245922
申请日：2005-10-06
申请人： Priyan Gunatilake
发明人： Priyan Gunatilake
IPC分类号： H04N11/04 , H04N7/12
CPC分类号： H04N19/88 , H04N19/12 , H04N19/186 , H04N19/57 , H04N19/61 , H04N19/85
摘要： Additional data compression is achieved by enhancing the spatial and temporal correlation of the data in a pre-processing module prior to sending the data to an encoding algorithm, such as for example, the MPEG algorithm. An input frame of data is decomposed into a luminance frame and two chrominance frames. The luminance frame is transformed on the basis of each of a plurality of luminance pixels within the frame to produce a transformed luminance frame having a plurality of transformed luminance pixels. A map describing a relationship between the plurality of luminance pixels of the luminance frame and the plurality of transformed luminance pixels of the transformed luminance frame is created. The two chrominance frames are transformed according to the map to produce two transformed chrominance frames. The transformed luminance frame and the two transformed chrominance frames are integrated to produce a transformed output frame.
摘要翻译：在将数据发送到诸如MPEG算法的编码算法之前，通过增强预处理模块中的数据的空间和时间相关来实现附加数据压缩。数据的输入帧被分解为亮度帧和两个色度帧。基于帧内的多个亮度像素中的每一个来变换亮度帧，以产生具有多个变换的亮度像素的变换的亮度帧。创建描述亮度帧的多个亮度像素与变换的亮度帧的多个变换的亮度像素之间的关系的映射。根据地图对两个色度帧进行变换以产生两个变换的色度帧。经变换的亮度帧和两个经变换的色度帧被积分以产生经变换的输出帧。

8. 发明申请

US20060050970A1 Method and apparatus for transmitting a coded video signal 失效
公开(公告)号：US20060050970A1
公开(公告)日：2006-03-09
申请号：US10935163
申请日：2004-09-08
申请人： Priyan Gunatilake
发明人： Priyan Gunatilake
IPC分类号： G06K9/36
CPC分类号： H04N19/503 , H04N19/149 , H04N21/23406 , H04N21/44004 , H04N21/6377 , H04N21/658
摘要： A method and apparatus for transmitting a digitally encoded video image in real time via a data network wherein the video image is digitally encoded using a compression algorithm having a variable bit rate, e.g., JPEG2K, to provide an encoded data stream, the encoded data stream is fed into a buffer of known size, and the data is read from the buffer via a streamer with a controllable bit rate to provide a bit stream at a desired stream bit rate for transmission via the network. The bit rate of the encoded data stream from the encoder is monitored by a predictor and predicts a future bit rate of the encoded data stream; and, the bit rate of at least one of the encoder and the streamer is adjusted to provide the desired streaming bit rate.

9. 发明授权

US08971651B2 Videolens media engine 有权
标题翻译：视频媒体引擎
公开(公告)号：US08971651B2
公开(公告)日：2015-03-03
申请号：US13171176
申请日：2011-06-28
申请人： Priyan Gunatilake
发明人： Priyan Gunatilake
IPC分类号： G06K9/36 , G06K9/00 , G06F17/30 , G10L15/26 , G10L25/78
CPC分类号： G06K9/00744 , G06F17/30784 , G06T7/20 , G06T2207/20021 , G10L15/26 , G10L2025/783 , H04N5/91 , Y10S707/914
摘要： A system, method, and computer program product for automatically analyzing multimedia data are disclosed. Embodiments receive multimedia data, detect portions having specified features, and output a corresponding subset of the multimedia data. Content features from downloaded or streaming movies or video clips are identified as a human probably would do, but in essentially real time. Embodiments then generate an index or menu based on individual consumer preferences. Consumers can peruse the index, or produce customized trailers, or edit and tag content with metadata as desired. The tool can categorize and cluster content by feature, to assemble a library of scenes or scene clusters according to user-selected criteria.
摘要翻译：公开了一种用于自动分析多媒体数据的系统，方法和计算机程序产品。实施例接收多媒体数据，检测具有指定特征的部分，并输出多媒体数据的相应子集。来自下载或流式电影或视频剪辑的内容功能被识别为人类可能会做的，但基本上是实时的。然后，实施例基于个体消费者喜好生成索引或菜单。消费者可以根据需要细读索引或生成自定义预告片，或者使用元数据编辑和标记内容。该工具可以按功能对内容进行分类和集群，根据用户选择的标准组装场景或场景集群。

10. 发明授权

US08966515B2 Adaptable videolens media engine 有权
标题翻译：适应性视频媒体引擎
公开(公告)号：US08966515B2
公开(公告)日：2015-02-24
申请号：US13171207
申请日：2011-06-28
申请人： Priyan Gunatilake
发明人： Priyan Gunatilake
IPC分类号： H04N7/16 , H04N5/91 , G06K9/00 , G06F17/30 , G10L15/26 , G06T7/00 , G06T7/20 , G10L25/78
CPC分类号： G06K9/00744 , G06F17/30784 , G06T7/20 , G06T2207/20021 , G10L15/26 , G10L2025/783 , H04N5/91 , Y10S707/914
摘要： A system, method, and computer program product for automatically analyzing multimedia data are disclosed. Embodiments receive multimedia data, detect portions having specified features, and output a corresponding subset of the multimedia data. Content features from downloaded or streaming movies or video clips are identified as a human probably would do, but in essentially real time. Embodiments then generate an index or menu based on individual consumer preferences. Consumers can peruse the index, or produce customized trailers, or edit and tag content with metadata as desired. The tool can categorize and cluster content by feature, to assemble a library of scenes or scene clusters according to user-selected criteria. The results may be sent to visual search engines so that further related content may be identified for use as a customized trailer, replacement content for advertisements, or as material to be shared with others.
摘要翻译：公开了一种用于自动分析多媒体数据的系统，方法和计算机程序产品。实施例接收多媒体数据，检测具有指定特征的部分，并输出多媒体数据的相应子集。来自下载或流式电影或视频剪辑的内容功能被识别为人类可能会做的，但基本上是实时的。然后，实施例基于个体消费者喜好生成索引或菜单。消费者可以根据需要细读索引或生成自定义预告片，或者使用元数据编辑和标记内容。该工具可以按功能对内容进行分类和集群，根据用户选择的标准组装场景或场景集群。结果可以被发送到视觉搜索引擎，使得可以识别进一步的相关内容以用作定制预告片，用于广告的替换内容，或作为与他人共享的材料。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式