公开(公告)号：US08700766B2

公开(公告)日：2014-04-15

申请号：US13231805

申请日：2011-09-13

Applicant: Simon Michael Rowe

Inventor： Simon Michael Rowe

IPC: G06F15/173

CPC classification number: G06Q30/0201 ,  G06Q30/0241

Abstract: A server computer receives web request events corresponding to web requests issued by users. Each web request event includes: a cookie that identifies the user computer that originated the corresponding web request; an IP address corresponding to the user computer; and a date/time stamp indicating when the corresponding web request was received at a web server. The server stores the web request events. The server selects a subset of the web request events, all of which are associated with the same cookie. Then the server computes a geographical location corresponding to the user computer, where the computation uses the IP address associated with the web request event. The server determines the local time and day of week corresponding to the web request. The server then classifies the user computer based, at least in part, on a usage pattern corresponding to the web request events in the subset.

Abstract translation: 服务器计算机接收与用户发布的Web请求对应的Web请求事件。 每个Web请求事件包括：识别发起相应web请求的用户计算机的cookie; 与用户计算机对应的IP地址; 以及指示在web服务器上何时接收到相应的web请求的日期/时间戳。 服务器存储Web请求事件。 服务器选择一个Web请求事件的子集，所有这些都与相同的cookie相关联。 然后，服务器计算对应于用户计算机的地理位置，其中计算使用与web请求事件相关联的IP地址。 服务器确定与Web请求对应的本地时间和星期几。 然后，服务器至少部分地基于与子集中的web请求事件相对应的使用模式来对用户计算机进行分类。

公开(公告)号：US20140026158A1

公开(公告)日：2014-01-23

申请号：US13552561

申请日：2012-07-18

Applicant: Simon Michael Rowe ,  Nick Salvatore Arini ,  Owen Charlebois

Inventor： Simon Michael Rowe ,  Nick Salvatore Arini ,  Owen Charlebois

IPC: H04N21/442

CPC classification number: H04N21/252 ,  H04H60/31 ,  H04H60/37 ,  H04H60/45 ,  H04H60/58 ,  H04H60/82 ,  H04H60/94 ,  H04N21/25891 ,  H04N21/4126 ,  H04N21/42201 ,  H04N21/42218 ,  H04N21/4394 ,  H04N21/441 ,  H04N21/44204 ,  H04N21/44218 ,  H04N21/4532 ,  H04N21/4758 ,  H04N21/4882 ,  H04N21/6582

Abstract: A TV audience survey system for determining the TV viewing activities of a plurality of individuals in a household includes a master device and multiple tags, each tag assigned to an individual. After an individual logs into the system and starts watching the TV, the master device communicates with the corresponding tag repeatedly to accumulate data representing the individual's TV viewing activities. Such data can be used to determine when the individual stops watching the TV for an extended period of time without logging out of the system and when the household member remains watching the TV after logging or being logged out of the system. The master device then reports the accumulated data to a remote server, which uses the data to determine whether the individual complies with the logging protocol defined by the TV audience survey system and update the TV viewership data associated with this household.

Abstract translation: 用于确定家庭中多个人的电视观看活动的电视观众调查系统包括主设备和多个标签，每个标签被分配给个人。 在个人登录系统并开始观看电视之后，主设备反复与相应的标签进行通信，以累积表示个人电视观看活动的数据。 这样的数据可用于确定个人何时停止观看电视长时间，而不会退出系统，以及家庭成员在登录或退出系统后仍然观看电视。 主设备然后将累积的数据报告给远程服务器，远程服务器使用数据来确定个人是否符合电视观众调查系统定义的日志记录协议，并更新与该家庭相关的电视观众数据。

公开(公告)号：US07257239B2

公开(公告)日：2007-08-14

申请号：US10241594

申请日：2002-09-12

Applicant: Simon Michael Rowe ,  Alistair William McLean

Inventor： Simon Michael Rowe ,  Alistair William McLean

IPC: G06K9/00

CPC classification number: G06K9/00221

Abstract: A modelling system is provided in which a model generation computer (3) stores within a model database (17) a plurality of principle component analysis models (18-1-18n) for modelling individuals. The principle component analysis models (18-1-18-n) are generated from data sets of individuals sharing identifying characteristics e.g. the same gender/ethnicity/age etc. When a new image is to be modelled using the system, characterising data for the new individual is received together with an image of that individual. The characterising data is used to select from the model database (17) a principle component analysis model (18-1-18-n) where the principle component analysis model selected comprises a model generated utilising images of individuals sharing the identifying characteristics corresponding to the characterisation data for the individual to be modelled.

Abstract translation: 提供了一种建模系统，其中模型生成计算机（3）在模型数据库（17）内存储用于建模个人的多个主成分分析模型（18-1-18n）。 主要成分分析模型（18-1-18-n）是从共享识别特征的个体的数据集生成的。 相同的性别/种族/年龄等。当使用系统对新图像进行建模时，将收到新个体的数据的表征以及该个体的图像。 特征数据用于从模型数据库（17）中选择主成分分析模型（18-1-18n），其中所选择的主成分分析模型包括利用共享与 要被建模的个人的表征数据。

公开(公告)号：US07158097B2

公开(公告)日：2007-01-02

申请号：US10681230

申请日：2003-10-09

Applicant: Richard Ian Taylor ,  Simon Michael Rowe

Inventor： Richard Ian Taylor ,  Simon Michael Rowe

IPC: G09G5/00

CPC classification number: G06F3/013

Abstract: A gaze tracking system (1,3,8) is provided which obtains images of an operator (9) and processes the images to associate the images with coordinates of where the operators gaze is directed towards.In order to identify images where an operator is looking in the same direction, images obtained by a camera (8) are first processed using the retinex algorithm. Image patches from the processed image are then compared with stored feature images and an initial classification based upon the correspondence between areas of the processed image and the stored feature images is determined. This initial classification is then further processed and each image is assigned a single classification. The areas identified by different classifications are then determined so that classifications assigned to adjacent images identify points closer together and classifications never assigned to an adjacent images identify points further apart.

Abstract translation: 提供了一种注视跟踪系统（1,3,8），其获得操作者（9）的图像，并处理图像以将图像与操作者注视指向的坐标相关联。 为了识别操作者在相同方向看的图像，首先使用retinex算法来处理由相机（8）获得的图像。 然后将来自经处理的图像的图像补丁与存储的特征图像进行比较，并且基于处理的图像的区域与存储的特征图像之间的对应关系确定初始分类。 然后进一步处理该初始分类，并为每个图像分配单一分类。 然后确定由不同分类识别的区域，使得分配给相邻图像的分类将点更靠近在一起，并且从未分配给相邻图像的分类更远地识别点。

公开(公告)号：US06421459B1

公开(公告)日：2002-07-16

申请号：US09153041

申请日：1998-09-15

Applicant: Simon Michael Rowe

Inventor： Simon Michael Rowe

IPC: G06K900

CPC classification number: G06T15/205 ,  G06T7/97 ,  G06T2200/08 ,  H04N5/2224

Abstract: In an image processing system, a three-dimensional computer model is created of a real-world static background scene. Video images of objects moving on the background are recorded and processed to identify the portions of the image corresponding to the moving objects and to calculate the corresponding positions in the three-dimensional computer model. Each moving object is represented by at least one vertical plane in the three-dimensional computer model. Images, comprising the simulated background and the moving object planes onto which are rendered the video data of the moving object recorded by the video camera, are displayed to the user from any desired viewing direction(s).

Abstract translation: 在图像处理系统中，创建一个真实世界的静态背景场景的三维计算机模型。 记录和处理在背景上移动的物体的视频图像，以识别对应于移动物体的图像部分，并计算三维计算机模型中的对应位置。 每个运动物体由三维计算机模型中的至少一个垂直平面表示。 包括模拟背景和被呈现为由摄像机记录的运动物体的视频数据的运动物体平面的图像从任何所需的观看方向显示给用户。