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. 发明申请

US20070273696A1 Automated Video-To-Text System 有权
标题翻译：自动视频到文本系统
公开(公告)号：US20070273696A1
公开(公告)日：2007-11-29
申请号：US11695755
申请日：2007-04-03
申请人： Hui Cheng , Darren Butler
发明人： Hui Cheng , Darren Butler
IPC分类号： G06T11/00
CPC分类号： G06T7/00 , G06K9/00771 , G06K9/469 , G06T2207/10016 , G06T2207/20072
摘要： A method for transforming Video-To-Text is disclosed that automatically generates text descriptions of the content of a video. The present invention first segments an input video sequence according to predefined semantic classes using a Mixture-of-Experts blob segmentation algorithm. The resulting segmentation is coerced into a semantic concept graph and based on domain knowledge and a semantic concept hierarchy. Then, the initial semantic concept graph is summarized and pruned. Finally, according to the summarized semantic concept graph and its changes over time, text and/or speech descriptions are automatically generated using one of the three description schemes: key-frame, key-object and key-change descriptions.
摘要翻译：公开了一种用于转换视频到文本的方法，其自动生成视频内容的文本描述。本发明首先使用专家混合分组分割算法根据预定义的语义类别划分输入视频序列。所得到的分割被强制转化为语义概念图，并且基于领域知识和语义概念层次。然后，总结和修剪初始语义概念图。最后，根据总结的语义概念图及其随时间的变化，使用三个描述方案之一自动生成文本和/或语音描述：关键帧，关键对象和键改变描述。

2. 发明授权

US07835578B2 Automated video-to-text system 有权
标题翻译：自动视频到文本系统
公开(公告)号：US07835578B2
公开(公告)日：2010-11-16
申请号：US11695755
申请日：2007-04-03
申请人： Hui Cheng , Darren Butler
发明人： Hui Cheng , Darren Butler
IPC分类号： G06K9/34
CPC分类号： G06T7/00 , G06K9/00771 , G06K9/469 , G06T2207/10016 , G06T2207/20072
摘要： A method for transforming Video-To-Text is disclosed that automatically generates text descriptions of the content of a video. The present invention first segments an input video sequence according to predefined semantic classes using a Mixture-of-Experts blob segmentation algorithm. The resulting segmentation is coerced into a semantic concept graph and based on domain knowledge and a semantic concept hierarchy. Then, the initial semantic concept graph is summarized and pruned. Finally, according to the summarized semantic concept graph and its changes over time, text and/or speech descriptions are automatically generated using one of the three description schemes: key-frame, key-object and key-change descriptions.
摘要翻译：公开了一种用于转换视频到文本的方法，其自动生成视频内容的文本描述。本发明首先使用专家混合分组分割算法根据预定义的语义类别划分输入视频序列。所得到的分割被强制转化为语义概念图，并且基于领域知识和语义概念层次。然后，总结和修剪初始语义概念图。最后，根据总结的语义概念图及其随时间的变化，使用三个描述方案之一自动生成文本和/或语音描述：关键帧，关键对象和键改变描述。

3. 发明授权

US06933985B2 Apparatus and method for compensation of temperature drift of SAW filters 有权
标题翻译：用于补偿SAW滤波器温度漂移的装置和方法
公开(公告)号：US06933985B2
公开(公告)日：2005-08-23
申请号：US10217978
申请日：2002-08-13
申请人： Stephen Beales , Darren Butler
发明人： Stephen Beales , Darren Butler
IPC分类号： H03D3/24 , H04N5/50 , H04N5/44
CPC分类号： H03L1/02
摘要： The invention relates to a method of controlling the operation of a voltage controlled oscillator (VCO) with respect to a SAW filter (6) within a broadcast data receiver (BDR) (104). Over time, it is found that during normal operation of the BDR (104), the SAW filter (6) is susceptible to frequency drift which can affect the operation of the BDR. In accordance with the invention, temperature readings are taken at various time intervals from within the BDR (104) to provide an indication of changes in temperature over time and, if the temperature does change in the BDR with time then the operating frequency of the VCO can be adjusted to a predefined frequency value which is appropriate for the temperature values measured. By adjusting the operating frequency of the VCO with changes in temperature, the drift of the SAW filter (6) can be compensated for, thereby ensuring the continued operation of the BDR (104) in the required manner.
摘要翻译：本发明涉及一种控制广播数据接收机（BDR）（104）内的SAW滤波器（6）的压控振荡器（VCO）的操作的方法。随着时间的推移，发现在BDR（104）的正常操作期间，SAW滤波器（6）易受频率漂移的影响，这可能影响BDR的操作。根据本发明，从BDR（104）内的各种时间间隔获取温度读数，以提供温度随时间变化的指示，并且如果温度随时间而在BDR中变化，则VCO的工作频率可以调整到适合于测量的温度值的预定频率值。通过随温度变化调节VCO的工作频率，可以补偿SAW滤波器（6）的漂移，从而确保BDR（104）以所需方式继续运行。

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