公开(公告)号：US06925410B2

公开(公告)日：2005-08-02

申请号：US10010104

申请日：2001-11-08

Applicant: Ajith Kumar Narayanan

Inventor： Ajith Kumar Narayanan

IPC: H04L12/28 ,  G06F3/033 ,  G08C17/00 ,  H04B7/26 ,  H04Q7/34 ,  H04Q7/38 ,  G01C19/00 ,  G06F3/00 ,  G06F19/00

CPC classification number: G06F3/0346 ,  G08C17/00 ,  G08C2201/41 ,  G08C2201/91

Abstract: A device network to process signals has target devices, selecting devices that are movable relative to the target devices, and controllers. The controllers are in communication with the target devices and the selecting devices. Each of the selecting devices has a position sensor and an orientation sensor to provide spatial and angular co-ordinates of position and orientation when pointing to a target device and upon receiving a user input. Each of the selecting devices also has a signal processor to generate a control signal having the position and orientation data. This control signal is then transmitted by a transmitter, via a radio frequency channel, to a controller. Upon receiving the control signal, the controller determines whether, for example, a target device has been selected by a selecting device by comparison of the orientation data with a derived orientation based on the position data and the known position of the target devices.

Abstract translation: 用于处理信号的设备网络具有目标设备，选择相对于目标设备可移动的设备以及控制器。 控制器与目标设备和选择设备通信。 每个选择装置具有位置传感器和定向传感器，以在指向目标装置时以及在接收到用户输入时提供位置和方位的空间和角度坐标。 每个选择装置还具有信号处理器以产生具有位置和方向数据的控制信号。 然后，该控制信号由发射机通过射频信道发射到控制器。 在接收到控制信号时，控制器基于位置数据和目标设备的已知位置，通过将取向数据与导出方向进行比较来确定例如目标设备是否已被选择。

公开(公告)号：US07492944B2

公开(公告)日：2009-02-17

申请号：US11457829

申请日：2006-07-17

Applicant: Ajith Kumar Narayanan ,  Alberto Tomita, Jr. ,  Takaaki Murao ,  Tomio Echigo

Inventor： Ajith Kumar Narayanan ,  Alberto Tomita, Jr. ,  Takaaki Murao ,  Tomio Echigo

IPC: G06K9/34 ,  G06K9/46

CPC classification number: H04N19/20 ,  G06T7/246 ,  G06T7/251 ,  G06T2207/10016 ,  G06T2207/30221 ,  G06T2207/30236 ,  G06T2207/30241 ,  H04N19/503 ,  H04N19/553

Abstract: Methods and apparatus for effectively identifying the occlusion of objects, such as persons, having a high degree of freedom. In an example embodiment, after initialization, an image is input, and an image region is extracted from image data. The distance is employed that is obtained when the shape of a two-dimensional histogram in the color space is transformed into the feature space. A graph is formed by using the regions between the frames. A confidence factor is provided and image features are provided as weights to the edges that connect the nodes. Processing is performed and the confidence factor is examined. A connection judged less possible to be a path is removed. When there is only one available connection for the occlusion point, this connection is selected.

Abstract translation: 用于有效地识别具有高度自由度的物体（例如人）的遮挡的方法和装置。 在示例实施例中，在初始化之后，输入图像，并且从图像数据中提取图像区域。 当将颜色空间中的二维直方图的形状变换为特征空间时，采用距离。 通过使用帧之间的区域形成图形。 提供置信因子，并且图像特征被提供为连接节点的边缘的权重。 执行处理并检查置信因子。 取消不太可能成为路径的连接。 当遮挡点只有一个可用连接时，选择此连接。