-
公开(公告)号:US08189925B2
公开(公告)日:2012-05-29
申请号:US12478569
申请日:2009-06-04
申请人: Michael Kroepfl , Eyal Ofek , Yonatan Wexler , Donald Wysocki , Gur Kimchi
发明人: Michael Kroepfl , Eyal Ofek , Yonatan Wexler , Donald Wysocki , Gur Kimchi
CPC分类号: G06K9/4671 , G06K9/00624 , G06K9/6211
摘要: Embodiments of the present invention relate to systems, methods and computer storage media for associating a known geographic location with a known identity. Feature matching, of at least two images, is performed in at least two iterations. The iterations are based on an orientation of feature vectors associated with points of interest in each image. A geometric model is applied to the matched points of interest to improve the matched pairs. Two images are identified as being related. As a result, the known geographic location is associated with the known identity. Additional embodiments include augmenting feature vectors with a coordinate location of a related point of interest based on a geometric model. Further, an exemplary embodiment includes an additional matching iteration based on the augmented feature vectors. In an exemplary embodiment, the feature matching utilizes a Scale-Invariant Feature Transform (SIFT).
摘要翻译: 本发明的实施例涉及用于将已知地理位置与已知身份相关联的系统,方法和计算机存储介质。 至少两个图像的特征匹配在至少两次迭代中执行。 迭代基于与每个图像中的兴趣点相关联的特征向量的方向。 将几何模型应用于匹配的兴趣点以改善匹配的对。 两个图像被识别为相关。 结果,已知的地理位置与已知身份相关联。 附加实施例包括基于几何模型来增加具有相关兴趣点的坐标位置的特征向量。 此外,示例性实施例包括基于增强特征向量的附加匹配迭代。 在示例性实施例中,特征匹配利用尺度不变特征变换(SIFT)。
-
公开(公告)号:US08060302B2
公开(公告)日:2011-11-15
申请号:US12416115
申请日:2009-03-31
申请人: Boris Epshtein , Eyal Ofek
发明人: Boris Epshtein , Eyal Ofek
IPC分类号: G01C21/32
CPC分类号: G01C21/3602 , G01C21/3644
摘要: Visual images may be used to detect, or verify the existence of, landmarks. In one example, the landmarks may be used to provide driving or walking directions. A set of records may be examined to identify the street addresses of businesses or other entities. Additionally, street-level images may be captured with a camera, and the locations at which the images were captured may be recorded. The images may be evaluated with an Optical Character Recognition (OCR) process to determine what words appear in the images. The words in the image are compared with the names of entities whose addresses are near where the image was captured. If the words match the entity name, then a sign identifying the entity is presumed to be visible along a particular route, and the entity may be used as a landmark in a set of walking or driving directions.
摘要翻译: 可以使用视觉图像来检测或验证地标的存在。 在一个示例中,地标可以用于提供驾驶或步行方向。 可以检查一组记录以识别企业或其他实体的街道地址。 此外,可以用相机捕获街道级图像,并且可以记录拍摄图像的位置。 可以用光学字符识别(OCR)处理来评估图像,以确定图像中出现什么字。 将图像中的单词与地址接近图像所在实体的名称进行比较。 如果这些单词与实体名称相匹配,则认为标识该实体的符号被认为是沿特定路线可见,并且该实体可以用作一组步行或行驶方向中的地标。
-
公开(公告)号:US07991283B2
公开(公告)日:2011-08-02
申请号:US12242739
申请日:2008-09-30
申请人: Billy Chen , Eyal Ofek , Pragyana K. Mishra
发明人: Billy Chen , Eyal Ofek , Pragyana K. Mishra
IPC分类号: G03B17/24
CPC分类号: G03B17/24 , G01C11/04 , G03B2217/246 , G03D15/001 , G06F17/30241 , G06F17/30265
摘要: Labels of elements in images may be compared to known elements to determine a region from which an image was created. Using this information, the approximate image position can be found, additional elements may be recognized, labels may be checked for accuracy and additional labels may be added.
摘要翻译: 可以将图像中的元素的标签与已知元素进行比较,以确定创建图像的区域。 使用该信息,可以找到近似图像位置,可以识别附加元件,可以检查标签的精度,并且可以添加附加标签。
-
公开(公告)号:US07941271B2
公开(公告)日:2011-05-10
申请号:US11562143
申请日:2006-11-21
申请人: Eyal Ofek
发明人: Eyal Ofek
CPC分类号: G06F17/30241 , G01C21/00 , G06F17/30017 , G06F17/3087
摘要: A system, method and computer-readable media are disclosed for displaying images corresponding to a path. The method can include downloading a path and one or more images corresponding to positions along the path, wherein the downloaded images are actual images of an environment near the corresponding positions. Additionally, the method can include detecting a position of a mobile device, and providing the downloaded images as the mobile device moves to the corresponding detected positions along the path.
摘要翻译: 公开了一种用于显示对应于路径的图像的系统,方法和计算机可读介质。 该方法可以包括下载路径和对应于沿着路径的位置的一个或多个图像,其中所下载的图像是相应位置附近的环境的实际图像。 此外,该方法可以包括检测移动设备的位置,并且当移动设备移动到沿着路径的对应的检测位置时提供下载的图像。
-
公开(公告)号:US20100313113A1
公开(公告)日:2010-12-09
申请号:US12479673
申请日:2009-06-05
申请人: Billy Chen , Eyal Ofek , Bo Zhang , Ying-Qing Xu
发明人: Billy Chen , Eyal Ofek , Bo Zhang , Ying-Qing Xu
IPC分类号: G06F17/00
CPC分类号: G06F17/30781 , G06F17/30241 , G06T19/006
摘要: Various embodiments provide techniques for calibrating and annotating video content. In one or more embodiments, an instance of video content can be calibrated with one or more geographical models and/or existing calibrated video content to correlate the instance of video content with one or more geographical locations. According to some embodiments, geographical information can be used to annotate the video content. Geographical information can include identification information for one or more structures, natural features, and/or locations included in the video content. Some embodiments enable a particular instance of video content to be correlated with other instances of video content based on common geographical information and/or common annotation information. Thus, a user can access video content from other users with similar travel experiences and/or interests. A user may also access annotations provided by other users that may be relevant to a particular instance of video content.
摘要翻译: 各种实施例提供了用于校准和注释视频内容的技术。 在一个或多个实施例中,视频内容的实例可以用一个或多个地理模型和/或现有校准的视频内容进行校准,以将视频内容的实例与一个或多个地理位置相关联。 根据一些实施例,地理信息可以用于对视频内容进行注释。 地理信息可以包括用于一个或多个结构,包括在视频内容中的自然特征和/或位置的识别信息。 一些实施例使视频内容的特定实例能够基于公共地理信息和/或公共注释信息与视频内容的其他实例相关联。 因此,用户可以从具有相似旅行经历和/或兴趣的其他用户访问视频内容。 用户还可以访问可能与视频内容的特定实例相关的其他用户提供的注释。
-
公开(公告)号:US20100250196A1
公开(公告)日:2010-09-30
申请号:US12415860
申请日:2009-03-31
申请人: Stephen L. Lawler , Eyal Ofek , Gur Kimchi , Leonard Smith , Avi Bar-Zeev
发明人: Stephen L. Lawler , Eyal Ofek , Gur Kimchi , Leonard Smith , Avi Bar-Zeev
CPC分类号: H04L67/10 , G06N3/006 , G06Q10/0637 , G06Q30/0273
摘要: Aspects relate to a cognitive agent that performs functions associated with a desired result. The functions performed by cognitive agent supplement other activities performed at a same time. In such a manner, the cognitive agent can function as a surrogate for a user. A performed activity can trigger implementation of another activity that is an extension of the performed activity. Cognitive agent can perform functions that can be represented as an avatar. Further, cognitive agent can be associated with a diagnostics component that evaluates an operating condition. Based on the operating condition cognitive agent can implement automatic actions associated with mitigating failures and/or prolonging the life of machinery.
摘要翻译: 方面涉及执行与期望结果相关联的功能的认知代理。 认知机构执行的功能补充了同时进行的其他活动。 以这种方式,认知代理可以用作用户的代理。 执行的活动可以触发作为执行活动的扩展的另一个活动的实现。 认知代理可以执行可以表示为头像的功能。 此外,认知代理可以与评估操作条件的诊断部件相关联。 基于操作条件,认知代理可以实现与减轻故障和/或延长机器寿命相关的自动动作。
-
公开(公告)号:US20100246890A1
公开(公告)日:2010-09-30
申请号:US12411398
申请日:2009-03-26
申请人: Eyal Ofek , Ido Omer , Michael Kroepfl , Mark Tabb , Kartik Muktinutalapati
发明人: Eyal Ofek , Ido Omer , Michael Kroepfl , Mark Tabb , Kartik Muktinutalapati
IPC分类号: G06K9/00
CPC分类号: G06K9/3258
摘要: A system described herein includes a detector component that automatically determines location of a license plate in a digital image. The system further includes a blurrer component that automatically blurs the digital image at the determined location of the license plate, wherein blurring undertaken by the blurrer component is based at least in part upon confidence scores assigned to pixels in the digital image that correspond to the determined location of the license plate.
摘要翻译: 本文描述的系统包括自动确定数字图像中车牌位置的检测器部件。 所述系统还包括模糊部件,其自动地模糊所述车牌的确定位置处的数字图像,其中由所述模糊部件进行的模糊至少部分地基于分配给所述数字图像中对应于所确定的数字图像中的像素的置信度分数 车牌位置。
-
公开(公告)号:US20100241514A1
公开(公告)日:2010-09-23
申请号:US12405261
申请日:2009-03-17
申请人: Eyal Ofek , Yonatan Wexler
发明人: Eyal Ofek , Yonatan Wexler
CPC分类号: G06Q30/0261 , G01C21/3679 , G06F16/9537 , G06Q30/00
摘要: A system described herein includes an information provider component that uses at least one information providing algorithm to transmit data for display on a display screen of a user, wherein the data corresponds to a geographic location. The system also includes a receiver component that receives an indication from a mobile device of the user that the user has travelled to the geographic location. The system further includes an updater component that causes the at least one information providing algorithm to be updated upon the receiver component receiving the indication.
摘要翻译: 本文描述的系统包括使用至少一个信息提供算法来发送用于在用户的显示屏幕上显示的数据的信息提供者组件,其中数据对应于地理位置。 该系统还包括一个接收器组件,该接收器组件从用户已经行进到地理位置的用户的移动设备接收指示。 所述系统还包括更新器组件,其在所述接收器组件接收所述指示时使所述至少一个信息提供算法被更新。
-
公开(公告)号:US20090208110A1
公开(公告)日:2009-08-20
申请号:US12031221
申请日:2008-02-14
申请人: Hugues H Hoppe , Yonatan Wexler , Eyal Ofek , Huamin Wang
发明人: Hugues H Hoppe , Yonatan Wexler , Eyal Ofek , Huamin Wang
IPC分类号: G06K9/46
摘要: The claimed subject matter provides systems and/or methods that factor large-scale repeated content within and/or among images. The system can include devices and components that factor received or acquired images into epitomes that include all the content of the received or acquired images and transform maps that encode how to construct a facsimile or a close approximation of the image by selecting transformed regions from the epitomes. Though use of both the epitomes and the transform maps in conjunction, a facsimile or a close approximation of the input image can be reconstructed and displayed.
摘要翻译: 所要求保护的主题提供了在图像内和/或图像内产生大规模重复内容的系统和/或方法。 系统可以包括将接收或获取的图像归因于包含所接收或获取的图像的所有内容的图像的变换图,以及通过从图像中选择变换区域来编码如何构造图像的传真或近似的变换图的设备和组件 。 虽然结合使用了缩影图和变换图,但可以重构和显示输入图像的传真或近似近似。
-
公开(公告)号:US20090110327A1
公开(公告)日:2009-04-30
申请号:US11928083
申请日:2007-10-30
申请人: Billy Chen , Eyal Ofek
发明人: Billy Chen , Eyal Ofek
IPC分类号: G06K9/36
CPC分类号: G06T17/10
摘要: In accordance with one or more aspects, a plane in a 3D coordinate system in which a 3D model is to be generated based on one or more 2D images is identified. A direction of extrusion for the plane is also identified. Additionally, a user identification of a region of interest on a 2D image is received and projected onto the plane. A location in the 3D model of the region of interest is then automatically identified by extruding the plane along the direction of extrusion until the region of interest in the plane matches a corresponding region of at least one of the one or more 2D images.
摘要翻译: 根据一个或多个方面,识别在3D坐标系中的基于一个或多个2D图像要生成3D模型的平面。 还确定了平面的挤出方向。 另外,2D图像上的感兴趣区域的用户识别被接收并投影到平面上。 然后通过沿着挤出方向挤压平面直到该平面中的感兴趣区域与一个或多个2D图像中的至少一个的相应区域相匹配来自动识别感兴趣区域的3D模型中的位置。
-
-
-
-
-
-
-
-
-