公开(公告)号：US09330297B2

公开(公告)日：2016-05-03

申请号：US13742658

申请日：2013-01-16

Applicant: Xerox Corporation

Inventor： Beilei Xu ,  Robert P. Loce ,  Graham Pennington

IPC: G06K9/00

CPC classification number: G06K9/00261

Abstract: A system and method of video-based chew counting by receiving image frames from a video camera, determining feature points within the image frames from the video camera, generating a motion signal based on movement of the feature points across the image frames from the video camera, and determining a chew count based on the motion signal.

Abstract translation: 一种通过从摄像机接收图像帧的基于视频的咀嚼计数的系统和方法，确定来自摄像机的图像帧内的特征点，基于来自摄像机的图像帧上的特征点的移动产生运动信号 ，并且基于运动信号确定咀嚼计数。

公开(公告)号：US20150043771A1

公开(公告)日：2015-02-12

申请号：US13963200

申请日：2013-08-09

Applicant: Xerox Corporation

Inventor： Wencheng Wu ,  Yao Rong Wang ,  Graham Pennington

IPC: G06K9/32 ,  G06K9/00 ,  G06K9/62 ,  G08G1/14 ,  G06T7/20

CPC classification number: G06K9/3233 ,  G06K9/00711 ,  G06K9/00771 ,  G06K9/00785 ,  G06K9/6256 ,  G06K9/6262 ,  G06K9/6267 ,  G06T7/20 ,  G06T2207/10016 ,  G06T2207/20081 ,  G08G1/14

Abstract: Hybrid methods, systems and processor-readable media for video and vision based access control for parking occupancy determination. One or more image frames of a parking area of interest can be acquired from among two or more regions of interest defined with respect to the parking area of interest. The regions of interest can be analyzed for motion detection or image content change detection. An image content classification operation can be performed with respect to a first region of interest among the regions of interest based on the result of the image content change detection. An object tracking operation can then be performed with respect to a second region of interest among the regions of interest if the result of the image content classification operation indicates a presence of one or more objects of interest within the parking area of interest.

Abstract translation: 用于基于视频和视觉的访问控制的混合方法，系统和处理器可读介质，用于停车占用确定。 可以从相关于感兴趣的停车区域定义的两个或更多个关注区域中获取感兴趣的停车区域的一个或多个图像帧。 可以分析感兴趣区域的运动检测或图像内容变化检测。 可以基于图像内容变化检测的结果，针对感兴趣区域中的第一感兴趣区域执行图像内容分类操作。 如果图像内容分类操作的结果表示感兴趣的停车区域内的一个或多个感兴趣对象的存在，则可以针对感兴趣区域中的第二感兴趣区域执行对象跟踪操作。