公开(公告)号：US08903132B2

公开(公告)日：2014-12-02

申请号：US13610225

申请日：2012-09-11

申请人： Oliver (“Lake”) Watkins, Jr. ,  Yousuf Chowdhary, Jr. ,  Jeffrey Brunet ,  Ravinder (“Ray”) Sharma ,  Ling Guan ,  Yun Tie ,  Rui Zhang

发明人： Oliver (“Lake”) Watkins, Jr. ,  Yousuf Chowdhary, Jr. ,  Jeffrey Brunet ,  Ravinder (“Ray”) Sharma ,  Ling Guan ,  Yun Tie ,  Rui Zhang

IPC分类号： G06K9/00

CPC分类号： G06K9/00362 ,  G06K9/00261

摘要： A method is provided for detecting a body part in a video stream from a mobile device. A video stream of a human subject is received from a camera connected to the mobile device. The video stream has frames. A first frame of the video stream is identified for processing. This first frame is then partitioned into observation windows, each observation window having pixels. In each observation window, non-skin-toned pixels are eliminated; and the remaining pixels are compared to determine a degree of entropy of the pixels in the observation window. In any observation window having a degree of entropy above a predetermined threshold, a bounded area is made around the region of high entropy pixels. The consistency of the entropy is analyzed in the bounded area. If the bounded area has inconsistently high entropy, a body part is determined to be detected at that bounded area.

摘要翻译： 提供一种用于检测来自移动设备的视频流中的身体部位的方法。 从连接到移动设备的相机接收人类对象的视频流。 视频流具有帧。 视频流的第一帧被识别用于处理。 然后将该第一帧分割成观察窗，每个观察窗具有像素。 在每个观察窗口中，消除非皮肤色调像素; 并且比较剩余像素以确定观察窗中像素的熵程度。 在具有高于预定阈值的熵程度的任何观察窗中，围绕高熵像素的区域进行有界区域。 在有界区域分析熵的一致性。 如果有界区域具有不一致的高熵，则确定在该有界区域处检测到身体部位。

公开(公告)号：US20130064426A1

公开(公告)日：2013-03-14

申请号：US13610225

申请日：2012-09-11

申请人： Oliver (Lake) Watkins, JR. ,  Yousuf Chowdhary ,  Jeffrey Brunet ,  Ravinder (Ray) Sharma ,  Ling Guan ,  Yun Tie ,  Rui Zhang

发明人： Oliver (Lake) Watkins, JR. ,  Yousuf Chowdhary ,  Jeffrey Brunet ,  Ravinder (Ray) Sharma ,  Ling Guan ,  Yun Tie ,  Rui Zhang

IPC分类号： G06K9/62

CPC分类号： G06K9/00362 ,  G06K9/00261

摘要： A method is provided for detecting a body part in a video stream from a mobile device. A video stream of a human subject is received from a camera connected to the mobile device. The video stream has frames. A first frame of the video stream is identified for processing. This first frame is then partitioned into observation windows, each observation window having pixels. In each observation window, non-skin-toned pixels are eliminated; and the remaining pixels are compared to determine a degree of entropy of the pixels in the observation window. In any observation window having a degree of entropy above a predetermined threshold, a bounded area is made around the region of high entropy pixels. The consistency of the entropy is analyzed in the bounded area. If the bounded area has inconsistently high entropy, a body part is determined to be detected at that bounded area.

摘要翻译： 提供一种用于检测来自移动设备的视频流中的身体部位的方法。 从连接到移动设备的相机接收人类对象的视频流。 视频流具有帧。 视频流的第一帧被识别用于处理。 然后将该第一帧分割成观察窗，每个观察窗具有像素。 在每个观察窗口中，消除非皮肤色调像素; 并且比较剩余像素以确定观察窗中像素的熵程度。 在具有高于预定阈值的熵程度的任何观察窗中，围绕高熵像素的区域进行有界区域。 在有界区域中分析熵的一致性。 如果有界区域具有不一致的高熵，则确定在该有界区域处检测到身体部位。