公开(公告)号：US07742623B1

公开(公告)日：2010-06-22

申请号：US12221552

申请日：2008-08-04

申请人： Hankyu Moon ,  Rajeev Sharma ,  Namsoon Jung

发明人： Hankyu Moon ,  Rajeev Sharma ,  Namsoon Jung

IPC分类号： G06K9/00

CPC分类号： G06K9/00604 ,  G06K9/00228

摘要： The present invention is a method and system to estimate the visual target that people are looking, based on automatic image measurements. The system utilizes image measurements from both face-view cameras and top-down view cameras. The cameras are calibrated with respect to the site and the visual target, so that the gaze target is determined from the estimated position and gaze direction of a person. Face detection and two-dimensional pose estimation locate and normalize the face of the person so that the eyes can be accurately localized and the three-dimensional facial pose can be estimated. The eye gaze is estimated based on either the positions of localized eyes and irises or on the eye image itself, depending on the quality of the image. The gaze direction is estimated from the eye gaze measurement in the context of the three-dimensional facial pose. From the top-down view the body of the person is detected and tracked, so that the position of the head is estimated using a body blob model that depends on the body position in the view. The gaze target is determined based on the estimated gaze direction, estimated head pose, and the camera calibration. The gaze target estimation can provide a gaze trajectory of the person or a collective gaze map from many instances of gaze.

摘要翻译： 本发明是基于自动图像测量来估计人们正在寻找的视觉目标的方法和系统。 该系统利用来自面视摄像机和自顶向下摄像机的图像测量。 摄像机相对于场地和视觉目标进行校准，从而根据人的估计位置和视线方向确定目标目标。 面部检测和二维姿态估计定位和归一化人脸，使眼睛能够被精确定位，并且可以估计三维面部姿势。 根据图像的质量，基于局部眼睛和虹膜的位置或眼睛图像本身来估计眼睛注视。 在三维面部姿势的背景下，从眼睛注视测量估计视线方向。 从自上而下的视角，人体的身体被检测和跟踪，以便使用取决于视图中的身体位置的身体斑点模型来估计头部的位置。 目标目标是根据估计的注视方向，估计头部姿态和相机校准来确定的。 注视目标估计可以从许多注视情况提供人的凝视轨迹或集体凝视图。

公开(公告)号：US07590261B1

公开(公告)日：2009-09-15

申请号：US10912450

申请日：2004-07-30

申请人： Vladimir Y. Mariano ,  Rajeev Sharma

发明人： Vladimir Y. Mariano ,  Rajeev Sharma

IPC分类号： G06K9/00

CPC分类号： G06K9/00785 ,  G06K9/6878

摘要： The invention is a method for detecting events in an imaged scene by analyzing the occlusion of linear features in the background image. Linear features, curved or straight, in specific scene locations are either manually specified or automatically learned from an image or image sequence of the background scene. For each linear feature, an occlusion model determines whether the line or part of it is occluded. The locations of the lines of interest in the scene, together with their occlusion characterizations, collectively form a description of the scene for a particular image. An event, defined as a series of descriptions of the scene over an image sequence, can then be initially defined and subsequently detected automatically by the system. An example application of this is counting cars or people passing in front of a video camera.

摘要翻译： 本发明是通过分析背景图像中的线性特征的遮挡来检测成像场景中的事件的方法。 在特定场景位置的线性特征，弯曲或直线，可以从背景场景的图像或图像序列手动指定或自动学习。 对于每个线性特征，遮挡模型确定线或其一部分是否被遮挡。 感兴趣的场景的位置以及它们的遮挡特性一起形成特定图像的场景的描述。 然后可以首先定义事件，定义为一系列对图像序列的场景的描述，然后由系统自动检测。 这方面的一个例子是计算在摄像机前面通过的汽车或人。

公开(公告)号：US07274803B1

公开(公告)日：2007-09-25

申请号：US10403234

申请日：2003-03-31

申请人： Rajeev Sharma ,  Nils Krahnstoever ,  Emilio Schapira

发明人： Rajeev Sharma ,  Nils Krahnstoever ,  Emilio Schapira

IPC分类号： G06K9/00 ,  G06K9/34 ,  H04N7/14 ,  H04N7/18 ,  H04N9/47

CPC分类号： G06K9/00375

摘要： The present invention is a system and method for detecting and analyzing motion patterns of individuals present at a multimedia computer terminal from a stream of video frames generated by a video camera and the method of providing visual feedback of the extracted information to aid the interaction process between a user and the system. The method allows multiple people to be present in front of the computer terminal and yet allow one active user to make selections on the computer display. Thus the invention can be used as method for contact-free human-computer interaction in a public place, where the computer terminal can be positioned in a variety of configurations including behind a transparent glass window or at a height or location where the user cannot touch the terminal physically.

摘要翻译： 本发明是一种用于从由摄像机产生的视频帧流中检测和分析存在于多媒体计算机终端的个人的运动模式的系统和方法，以及提供所提取的信息的视觉反馈以帮助在 用户和系统。 该方法允许多个人存在于计算机终端之前，并且允许一个主动用户在计算机显示器上进行选择。 因此，本发明可以用作公共场合中的无接触人机交互的方法，其中计算机终端可以以包括透明玻璃窗后面或用户不能接触的高度或位置处的各种配置来定位 物理终端。

公开(公告)号：US07225414B1

公开(公告)日：2007-05-29

申请号：US10634962

申请日：2003-08-05

申请人： Rajeev Sharma ,  Emilio Schapira ,  Namsoon Jung

发明人： Rajeev Sharma ,  Emilio Schapira ,  Namsoon Jung

IPC分类号： G06F3/00 ,  G06F9/00

CPC分类号： G06F3/017 ,  G06F3/012

摘要： The present invention is a method and apparatus for attracting the attention of people in public places and engaging them in a touch-free interaction with a multimedia display using an image-capturing system and a set of Computer Vision algorithms as a means of informing the public as well as collecting data about/from the users. The invention is named, Virtual Touch Entertainment (VTE) Platform. The VTE Platform comprises of a series of interaction states, such as the Wait State, the Attraction State, the User Engagement State, the User Interaction State, and the Interaction Termination State. The modules in these interaction states handle complicated tasks assigned to them, such as attracting the users, training the users, providing the multimedia digital content to the users, and collecting the user data and statistics, in an efficient and intelligent manner. The user is able to experience a whole new way of interaction paradigm while getting information and entertainment through the rich digital multimedia. The system operates automatically and dynamically in real-time throughout the whole interaction process.

摘要翻译： 本发明是一种用于吸引公共场所的人的注意力的方法和装置，并且使用图像捕获系统和一组计算机视觉算法作为通知公众的手段使其与多媒体显示器的无触摸的交互 以及从用户那里收集数据。 该发明被命名为虚拟触摸娱乐（VTE）平台。 VTE平台包括一系列交互状态，例如等待状态，吸引状态，用户参与状态，用户交互状态和交互终止状态。 这些交互状态中的模块处理分配给他们的复杂任务，例如吸引用户，训练用户，向用户提供多媒体数字内容，并以高效智能的方式收集用户数据和统计信息。 用户能够通过丰富的数字多媒体获得信息和娱乐，体验全新的互动模式。 系统在整个交互过程中实时自动动态地运行。