-
1.
公开(公告)号:US09013401B2
公开(公告)日:2015-04-21
申请号:US14246383
申请日:2014-04-07
申请人: Intel Corporation
发明人: Shahzad Malik , Abhishek Ranjan , Phillipp J. Hubert , Umeshbhai Patel , William J. Colson , Haroon F. Mirza , Faizal N. Javer
CPC分类号: G06F3/005 , G06F3/012 , G06K9/00778 , G06Q30/0242
摘要: Measuring audience size for a digital sign comprises generating a plurality of paths, one for each face detected in a first sequence of video frames captured by a camera proximate the digital sign, and generating a zone in the sequence of video frames through which passes a threshold number of the paths. Motion and direction of motion within the zone is then measured in a second sequence of video frames to calculate the audience size that passes through the zone in the second sequence of video frames.
摘要翻译: 测量数字符号的听众大小包括产生多个路径,一个针对由接近数字符号的摄像机所捕获的第一序列的视频帧中检测到的每个脸部,并且产生通过阈值的视频帧序列中的区域 路径数。 然后在视频帧的第二序列中测量区域内的运动和运动方向,以计算通过视频帧的第二序列中的区域的观众大小。
-
公开(公告)号:US09292753B2
公开(公告)日:2016-03-22
申请号:US13682930
申请日:2012-11-21
申请人: Intel Corporation
发明人: Abhishek Ranjan , Shahzad A. Malik , Phillipp J. Hubert , Umeshbhai Patel , Faizal N. Javer , Haroon F. Mirza , William J. Colson
IPC分类号: G06K9/00
CPC分类号: G06K9/00993 , G06K9/00261
摘要: The present disclosure is directed to a parallel face detection and tracking system. In general, embodiments consistent with the present disclosure may be configured to distribute the processing load associated with the detection and tracking of different faces in an image between multiple data processors. If needed, processing load balancing and/or protective features may be implemented to prevent the data processors from becoming overwhelmed. In one embodiment, a device may comprise, for example, a communication module and at least one processing module. The communication module may be configured to receive at least image information that may be processed by a plurality of data processors in the data processing module. For example, each of the data processors may be configured to detect faces in the image information and/or track detected faces in the image information based on at least one criterion.
摘要翻译: 本公开涉及一种平行人脸检测和跟踪系统。 通常,与本公开内容一致的实施例可以被配置为将与多个数据处理器之间的图像中的不同面部的检测和跟踪相关联的处理负载分配。 如果需要,可以实现处理负载平衡和/或保护特征以防止数据处理器被淹没。 在一个实施例中,设备可以包括例如通信模块和至少一个处理模块。 通信模块可以被配置为至少接收可以由数据处理模块中的多个数据处理器处理的图像信息。 例如,每个数据处理器可以被配置为基于至少一个标准来检测图像信息中的面部和/或跟踪图像信息中的检测到的面部。
-
3.
公开(公告)号:US20140218285A1
公开(公告)日:2014-08-07
申请号:US14246383
申请日:2014-04-07
申请人: Intel Corporation
发明人: Shahzad Malik , Abhishek Ranjan , Phillipp J. Hubert , Umeshbhai Patel , William J. Colson , Haroon F. Mirza , Faizal N. Javer
IPC分类号: G06F3/00
CPC分类号: G06F3/005 , G06F3/012 , G06K9/00778 , G06Q30/0242
摘要: Measuring audience size for a digital sign comprises generating a plurality of paths, one for each face detected in a first sequence of video frames captured by a camera proximate the digital sign, and generating a zone in the sequence of video frames through which passes a threshold number of the paths. Motion and direction of motion within the zone is then measured in a second sequence of video frames to calculate the audience size that passes through the zone in the second sequence of video frames.
摘要翻译: 测量数字符号的听众大小包括产生多个路径,一个针对由接近数字符号的摄像机所捕获的第一序列的视频帧中检测到的每个脸部,并且产生通过阈值的视频帧序列中的区域 路径数。 然后在视频帧的第二序列中测量区域内的运动和运动方向,以计算通过视频帧的第二序列中的区域的观众大小。
-
-