专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20120027248A1 Foreground Analysis Based on Tracking Information 失效
标题翻译：基于跟踪信息的前景分析
公开(公告)号：US20120027248A1
公开(公告)日：2012-02-02
申请号：US12844330
申请日：2010-07-27
申请人： Rogerio S. Feris , Arun Hampapur , Frederik C. Kjeldsen , Hao-Wei Liu
发明人： Rogerio S. Feris , Arun Hampapur , Frederik C. Kjeldsen , Hao-Wei Liu
IPC分类号： G06K9/00
CPC分类号： G06K9/46 , G06K9/00711 , G06K9/00744 , G06K9/00771 , G06K2009/4666 , G06T11/20 , H04N7/18
摘要： Techniques for performing foreground analysis are provided. The techniques include identifying a region of interest in a video scene, applying a background subtraction algorithm to the region of interest to detect a static foreground object in the region of interest, and determining whether the static foreground object is abandoned or removed, wherein determining whether the static foreground object is abandoned or removed comprises performing a foreground analysis based on edge energy and region growing, and pruning one or more false alarms using one or more track statistics.
摘要翻译：提供了执行前景分析的技术。这些技术包括识别视频场景中的感兴趣区域，将感兴趣的区域应用背景减法算法来检测感兴趣区域中的静态前景对象，以及确定是否放弃或去除静态前景对象，其中确定是否静态前景对象被放弃或移除包括基于边缘能量和区域增长执行前景分析，以及使用一个或多个轨道统计修剪一个或多个虚假报警。

2. 发明授权

US08483481B2 Foreground analysis based on tracking information 失效
标题翻译：基于跟踪信息的前景分析
公开(公告)号：US08483481B2
公开(公告)日：2013-07-09
申请号：US12844330
申请日：2010-07-27
申请人： Rogerio S. Feris , Arun Hampapur , Frederik C. Kjeldsen , Hao-Wei Liu
发明人： Rogerio S. Feris , Arun Hampapur , Frederik C. Kjeldsen , Hao-Wei Liu
IPC分类号： G06T7/0081
CPC分类号： G06K9/46 , G06K9/00711 , G06K9/00744 , G06K9/00771 , G06K2009/4666 , G06T11/20 , H04N7/18
摘要： Techniques are provided. The techniques include identifying a region of interest in a video scene, applying a background subtraction algorithm to the region of interest to detect a static foreground object in the region of interest, and determining whether the static foreground object is abandoned or removed, wherein determining whether the static foreground object is abandoned or removed comprises performing a foreground analysis based on edge energy and region growing, and pruning one or more false alarms using one or more track statistics.
摘要翻译：提供技术。这些技术包括识别视频场景中的感兴趣区域，将感兴趣的区域应用背景减法算法来检测感兴趣区域中的静态前景对象，以及确定是否放弃或去除静态前景对象，其中确定是否静态前景对象被放弃或移除包括基于边缘能量和区域增长执行前景分析，以及使用一个或多个轨道统计修剪一个或多个虚假报警。

3. 发明授权

US08675917B2 Abandoned object recognition using pedestrian detection 有权
标题翻译：放弃对象识别使用行人检测
公开(公告)号：US08675917B2
公开(公告)日：2014-03-18
申请号：US13285354
申请日：2011-10-31
申请人： Lisa M. Brown , Rogerio S. Feris , Frederik C. Kjeldsen , Kristina Scherbaum
发明人： Lisa M. Brown , Rogerio S. Feris , Frederik C. Kjeldsen , Kristina Scherbaum
IPC分类号： G06K9/00 , H04N5/225
CPC分类号： G06K9/00369 , G06K9/626 , G06K9/6857
摘要： Methods and apparatus are provided for improved abandoned object recognition using pedestrian detection. An abandoned object is detected in one or more images by determining if one or more detected objects in a foreground of the images comprises a potential abandoned object; applying a trained pedestrian detector to the potential abandoned object to determine if the potential abandoned object comprises at least a portion of a pedestrian; and classifying the potential abandoned object as an abandoned object based on whether the potential abandoned object is not at least a portion of a pedestrian. The trained pedestrian detector is trained using positive training samples comprised of at least portions of human bodies in one or more poses and/or negative training samples comprised of at least portions of abandoned objects.
摘要翻译：提供了使用行人检测改进废弃物识别的方法和装置。通过确定图像的前景中的一个或多个检测到的对象是否包括潜在废弃对象，在一个或多个图像中检测到废弃物体; 将经过训练的行人检测器应用于潜在废弃物体以确定潜在废弃物体是否包括行人的至少一部分; 并且基于潜在废弃物体是否不是行人的至少一部分，将潜在废弃物体分类为废弃物体。训练有素的行人检测器使用由至少部分被遗弃物体组成的一个或多个姿势和/或负训练样本中的人体的至少部分组成的训练有素的训练样本进行训练。

4. 发明申请

US20130108102A1 Abandoned Object Recognition Using Pedestrian Detection 有权
标题翻译：放弃对象识别使用行人检测
公开(公告)号：US20130108102A1
公开(公告)日：2013-05-02
申请号：US13285354
申请日：2011-10-31
申请人： Lisa M. Brown , Rogerio S. Feris , Frederik C. Kjeldsen , Kristina Scherbaum
发明人： Lisa M. Brown , Rogerio S. Feris , Frederik C. Kjeldsen , Kristina Scherbaum
IPC分类号： G06K9/62
CPC分类号： G06K9/00369 , G06K9/626 , G06K9/6857
摘要： Methods and apparatus are provided for improved abandoned object recognition using pedestrian detection. An abandoned object is detected in one or more images by determining if one or more detected objects in a foreground of the images comprises a potential abandoned object; applying a trained pedestrian detector to the potential abandoned object to determine if the potential abandoned object comprises at least a portion of a pedestrian; and classifying the potential abandoned object as an abandoned object based on whether the potential abandoned object is not at least a portion of a pedestrian. The trained pedestrian detector is trained using positive training samples comprised of at least portions of human bodies in one or more poses and/or negative training samples comprised of at least portions of abandoned objects.
摘要翻译：提供了使用行人检测改进废弃物识别的方法和装置。通过确定图像的前景中的一个或多个检测到的对象是否包括潜在废弃对象，在一个或多个图像中检测到废弃物体; 将经过训练的行人检测器应用于潜在废弃物体以确定潜在废弃物体是否包括行人的至少一部分; 并且基于潜在废弃物体是否不是行人的至少一部分，将潜在废弃物体分类为废弃物体。训练有素的行人检测器使用由至少部分被遗弃物体组成的一个或多个姿势和/或负训练样本中的人体的至少部分组成的训练有素的训练样本进行训练。

5. 发明授权

US08155872B2 Method and apparatus for indoor navigation 有权
标题翻译：室内导航方法和装置
公开(公告)号：US08155872B2
公开(公告)日：2012-04-10
申请号：US11668540
申请日：2007-01-30
申请人： Frederik C. Kjeldsen , Anthony Levas , Gopal S. Pingali , Claudio S. Pinhanez , Mark E. Podlaseck , Piyawadee Sukavitiya
发明人： Frederik C. Kjeldsen , Anthony Levas , Gopal S. Pingali , Claudio S. Pinhanez , Mark E. Podlaseck , Piyawadee Sukavitiya
IPC分类号： G01C21/30 , G01C21/32
CPC分类号： G01C21/206 , G03B21/006
摘要： Techniques are provided for providing physical routes to target locations. The techniques include obtaining at least one target location from at least one user; determining at least one physical route to said at least one target location; and displaying said at least one determined physical route through a sequence of at least one sign display, wherein each sign display are configured to display a plurality of physical routes.
摘要翻译：提供了提供物理路线到目标位置的技术。所述技术包括从至少一个用户获得至少一个目标位置; 确定至少一个到所述至少一个目标位置的物理路线; 以及通过至少一个符号显示的序列显示所述至少一个确定的物理路由，其中每个符号显示被配置为显示多个物理路由。

6. 发明授权

US06864912B1 Computer system providing hands free user input via optical means for navigation or zooming 有权
标题翻译：计算机系统通过用于导航或缩放的光学装置提供免提用户输入
公开(公告)号：US06864912B1
公开(公告)日：2005-03-08
申请号：US09464841
申请日：1999-12-16
申请人： Robert B. Mahaffey , Lawrence F. Weiss , Richard S. Schwerdtfeger , Frederik C. Kjeldsen
发明人： Robert B. Mahaffey , Lawrence F. Weiss , Richard S. Schwerdtfeger , Frederik C. Kjeldsen
IPC分类号： G06T5/20 , H04N7/18
CPC分类号： G06F3/012
摘要： A system and method are described for selectively providing display data to a display device dependent upon an optically detected proximity of a user's face to a camera. One embodiment of a computer system includes the camera, the display device, and a processing system. The camera produces image signals representing a first image and a second image of the user's face, wherein the first image precedes the second image in time. The processing system receives the image signals and analyzes the first and second images to determine the proximity of the user's face to the camera. More specifically, the processing system compares the first and second images to determine the proximity of the user's face to the camera in the second image relative to the proximity of the user's face in the first image. The processing system provides the display data to the display device dependent upon the proximity of the user's face to the camera. In order to determine the proximity of the user's face to the camera, the processing system may compare: (i) a size of the user's face in the first and second images, and/or (ii) a distance between selected facial features of the user in the first and second images. The processing system may provide more of the display data to the display device when the user's face is closer to the camera, and may provide less of the display data to the display device when the user's face is farther from the camera.
摘要翻译：描述了一种系统和方法，用于根据光学检测到的用户面部与相机的接近度来选择性地向显示设备提供显示数据。计算机系统的一个实施例包括相机，显示装置和处理系统。相机产生表示用户脸部的第一图像和第二图像的图像信号，其中第一图像在时间上在第二图像之前。处理系统接收图像信号并分析第一和第二图像以确定用户脸部与相机的接近度。更具体地，处理系统比较第一和第二图像，以相对于第一图像中的用户面部的接近度来确定第二图像中的用户面部与相机的接近度。处理系统根据用户面部与相机的接近度，将显示数据提供给显示装置。为了确定用户面部与相机的接近度，处理系统可以比较：（i）第一和第二图像中的用户面部的尺寸，和/或（ii）所选择的面部特征之间的距离用户在第一和第二图像中。当用户的脸部更接近照相机时，处理系统可以向显示设备提供更多的显示数据，并且当用户的脸部远离相机时可以向显示设备提供较少的显示数据。

7. 发明申请

US20080180637A1 Method And Apparatus For Indoor Navigation 有权
标题翻译：室内导航方法与装置
公开(公告)号：US20080180637A1
公开(公告)日：2008-07-31
申请号：US11668540
申请日：2007-01-30
申请人： Frederik C. Kjeldsen , Anthony Levas , Gopal S. Pingali , Claudio S. Pinhanez , Mark E. Podlaseck , Piyawadee Sukavitiya
发明人： Frederik C. Kjeldsen , Anthony Levas , Gopal S. Pingali , Claudio S. Pinhanez , Mark E. Podlaseck , Piyawadee Sukavitiya
IPC分类号： G03B21/00
CPC分类号： G01C21/206 , G03B21/006
摘要： Techniques are provided for providing physical routes to target locations. The techniques include obtaining at least one target location from at least one user; determining at least one physical route to said at least one target location; and displaying said at least one determined physical route through a sequence of at least one sign display, wherein each sign display are configured to display a plurality of physical routes.
摘要翻译：提供了提供物理路线到目标位置的技术。所述技术包括从至少一个用户获得至少一个目标位置; 确定至少一个到所述至少一个目标位置的物理路线; 以及通过至少一个符号显示的序列显示所述至少一个确定的物理路由，其中每个符号显示被配置为显示多个物理路由。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式