-
1.发明授权Methods and systems for matching keypoints and tracking regions between frames of video data 有权用于匹配视频数据帧之间的关键点和跟踪区域的方法和系统公开(公告)号：US09002055B2
公开(公告)日：2015-04-07
申请号：US12682425
申请日：2008-10-13
CPC分类号： G06T7/0081 , G06T7/11 , G06T7/174 , G06T7/251 , G06T2207/10016 , G06T2207/30232
摘要： A method (100) and system (300) is described for processing video data comprising a plurality of images. The method (100) comprising obtaining (104, 106), for each of the plurality of images, a segmentation in a plurality of regions and a set of keypoints, and tracking (108) at least one region between a first image and a subsequent image resulting in a matched region in the subsequent image taking into account a matching between keypoints in the first image and the subsequent image. The latter results in accurate tracking of regions. Furthermore the method may optionally also perform label propagation taking into account keypoint tracking.
摘要翻译： 描述了用于处理包括多个图像的视频数据的方法（100）和系统（300）。 所述方法（100）包括为多个图像中的每一个获得（104,106）多个区域中的分割和一组关键点，以及跟踪（108）第一图像和随后的至少一个区域 考虑到第一图像和后续图像中的关键点之间的匹配，导致后续图像中的匹配区域的图像。 后者导致区域的准确跟踪。 此外，该方法还可以可选地还考虑关键点跟踪来执行标签传播。
-
公开(公告)号：US20100239123A1
公开(公告)日：2010-09-23
申请号：US12682425
申请日：2008-10-13
CPC分类号： G06T7/0081 , G06T7/11 , G06T7/174 , G06T7/251 , G06T2207/10016 , G06T2207/30232
摘要： A method (100) and system (300) is described for processing video data comprising a plurality of images. The method (100) comprising obtaining (104, 106), for each of the plurality of images, a segmentation in a plurality of regions and a set of keypoints, and tracking (108) at least one region between a first image and a subsequent image resulting in a matched region in the subsequent image taking into account a matching between keypoints in the first image and the subsequent image. The latter results in accurate tracking of regions. Furthermore the method may optionally also perform label propagation taking into account keypoint tracking.
摘要翻译： 描述了用于处理包括多个图像的视频数据的方法（100）和系统（300）。 所述方法（100）包括为多个图像中的每一个获得（104,106）多个区域中的分割和一组关键点，以及跟踪（108）第一图像和随后的至少一个区域 考虑到第一图像和后续图像中的关键点之间的匹配，导致后续图像中的匹配区域的图像。 后者导致区域的准确跟踪。 此外，该方法还可以可选地还考虑关键点跟踪来执行标签传播。
-
公开(公告)号：US20090169096A1
公开(公告)日：2009-07-02
申请号：US12089140
申请日：2006-10-12
CPC分类号： G06T7/579 , G06T7/557 , G06T7/586 , G06T2207/10021 , G06T2207/30264
摘要： We describe methods of characterising a set of images to determine their respective illumination, for example for recovering the 3D shape of an illuminated object. The method comprises: inputting a first set of images of the object captured from different positions; determining frontier point data from the images, this defining a plurality of frontier points on the object and for each said frontier point a direction of a normal to the surface of the object at the frontier point, and determining data defining the image capture positions; inputting a second set of images of said object, having substantially the same viewpoint and different illumination conditions; and characterising the second set of images said frontier point data to determine data comprising object reflectance parameter data (β) and, for each image of said second set, illumination data (L) comprising data defining an illumination direction and illumination intensity for the image.
摘要翻译： 我们描述表征一组图像的方法以确定它们各自的照明，例如用于恢复被照亮物体的3D形状。 该方法包括：输入从不同位置捕获的对象的第一组图像; 确定来自图像的边界点数据，其定义对象上的多个边界点，并为每个所述前沿点定义在边界点处的对象的表面的法线方向，以及确定定义图像捕获位置的数据; 输入所述对象的第二组图像，具有基本上相同的视点和不同的照明条件; 并且表征第二组图像，所述边界点数据以确定包括对象反射参数数据（β）的数据，并且对于所述第二组的每个图像，包括限定图像的照明方向和照明强度的数据的照明数据（L）。
-
公开(公告)号：US08417021B2
公开(公告)日：2013-04-09
申请号：US12089140
申请日：2006-10-12
IPC分类号： G06K9/00
CPC分类号： G06T7/579 , G06T7/557 , G06T7/586 , G06T2207/10021 , G06T2207/30264
摘要： We describe methods of characterizing a set of images to determine their respective illumination, for example for recovering the 3D shape of an illuminated object. The method comprises: inputting a first set of images of the object captured from different positions; determining frontier point data from the images, this defining a plurality of frontier points on the object and for each said frontier point a direction of a normal to the surface of the object at the frontier point, and determining data defining the image capture positions; inputting a second set of images of said object, having substantially the same viewpoint and different illumination conditions; and characterizing the second set of images said frontier point data to determine data comprising object reflectance parameter data (β) and, for each image of said second set, illumination data (L) comprising data defining an illumination direction and illumination intensity for the image.
摘要翻译： 我们描述表征一组图像的方法以确定它们各自的照明，例如用于恢复被照亮物体的3D形状。 该方法包括：输入从不同位置捕获的对象的第一组图像; 确定来自图像的边界点数据，其定义对象上的多个边界点，并为每个所述前沿点定义在边界点处的对象的表面的法线方向，以及确定定义图像捕获位置的数据; 输入所述对象的第二组图像，具有基本上相同的视点和不同的照明条件; 并且表征所述第二组图像，所述边界点数据以确定包括对象反射参数数据（＆bgr）的数据，并且对于所述第二组的每个图像，包括限定图像的照明方向和照明强度的数据的照明数据（L） 。
-
公开(公告)号：US08670619B2
公开(公告)日：2014-03-11
申请号：US13448562
申请日：2012-04-17
CPC分类号： G06K9/4671 , G06K9/4614 , G06K9/56
摘要： A method for operating on images is described for interest point detection and/or description working under different scales and with different rotations, e.g. for scale-invariant and rotation-invariant interest point detection and/or description.
摘要翻译： 描述了用于在图像上操作的方法，用于在不同尺度和不同旋转下的感兴趣点检测和/或描述工作，例如， 用于尺度不变和旋转不变的兴趣点检测和/或描述。
-
公开(公告)号：US20100066216A1
公开(公告)日：2010-03-18
申请号：US12448790
申请日：2007-01-11
申请人： Hidetoshi Kusumi , Tomasz Blachowicz , Hiromichi Yanagihara , Marleen De Weser , Jonas Ambeck-Madsen , Gabriel Othmezouri , Igor Stankovic , Ryuji Funayama , Katsuhiro Sakai
发明人： Hidetoshi Kusumi , Tomasz Blachowicz , Hiromichi Yanagihara , Marleen De Weser , Jonas Ambeck-Madsen , Gabriel Othmezouri , Igor Stankovic , Ryuji Funayama , Katsuhiro Sakai
CPC分类号： H02K31/00 , H02K11/0094 , H02N11/006
摘要： To provide a quantum motor capable of reliably carrying out rotation. A quantum motor includes a rotor containing a functional material of which quantum characteristic is externally controllable, an N pole permanent magnet and an S pole permanent magnet applying magnetic field to the rotor, and a light source varying the quantum characteristic of the rotor. The light source varies the quantum characteristic of the rotor, so that rotation force is generated in the rotor and the rotor rotates.
摘要翻译： 提供能够可靠地进行旋转的量子电动机。 量子电动机包括含有量子特性可外部控制的功能材料的转子，向转子施加磁场的N极永磁体和S极永磁体，以及改变转子的量子特性的光源。 光源改变转子的量子特性，从而在转子中产生旋转力，转子旋转。
-
公开(公告)号：US20090238460A1
公开(公告)日：2009-09-24
申请号：US12298879
申请日：2007-04-30
IPC分类号： G06K9/00
CPC分类号： G06K9/4671 , G06K9/4614 , G06K9/56
摘要： Methods and apparatus for operating on images are described, in particular methods and apparatus for interest point detection and/or description working under different scales and with different rotations, e.g. for scale-invariant and rotation-invariant interest point detection and/or description. The present invention can provide improved or alternative apparatus and methods for matching interest points either in the same image or in a different image. The present invention can provide alternative or improved software for implementing any of the methods of the invention. The present invention can provide alternative or improved data structures created by multiple filtering operations to generate a plurality of filtered images as well as data structures for storing the filtered images themselves, e.g. as stored in memory or transmitted through a network. The present invention can provide alternative or improved data structures including descriptors of interest points in images, e.g. as stored in memory or transmitted through a network as well as datastructures associating such descriptors with an original copy of the image or an image derived therefrom, e.g. a thumbnail image.
摘要翻译： 描述了用于在图像上操作的方法和装置，特别是用于在不同尺度和不同旋转下进行兴趣点检测和/或描述的方法和装置，例如， 用于尺度不变和旋转不变的兴趣点检测和/或描述。 本发明可以提供用于在相同图像或不同图像中匹配兴趣点的改进的或替代的装置和方法。 本发明可以提供用于实现本发明的任何方法的替代或改进的软件。 本发明可以提供通过多次滤波操作产生的替代或改进的数据结构，以产生多个滤波图像，以及用于存储滤波图像本身的数据结构，例如， 存储在存储器中或通过网络传输。 本发明可以提供替代或改进的数据结构，包括图像中的兴趣点的描述符，例如。 如存储在存储器中或通过网络传输的数据结构以及将这样的描述符与图像的原始副本或从其导出的图像相关联的数据结构。 缩略图。
-
公开(公告)号：US08165401B2
公开(公告)日：2012-04-24
申请号：US12298879
申请日：2007-04-30
IPC分类号： G06K9/46
CPC分类号： G06K9/4671 , G06K9/4614 , G06K9/56
摘要： Methods and apparatus for operating on images are described, in particular methods and apparatus for interest point detection and/or description working under different scales and with different rotations, e.g. for scale-invariant and rotation-invariant interest point detection and/or description. The present invention can provide improved or alternative apparatus and methods for matching interest points either in the same image or in a different image. The present invention can provide alternative or improved software for implementing any of the methods of the invention. The present invention can provide alternative or improved data structures created by multiple filtering operations to generate a plurality of filtered images as well as data structures for storing the filtered images themselves, e.g. as stored in memory or transmitted through a network. The present invention can provide alternative or improved data structures including descriptors of interest points in images, e.g. as stored in memory or transmitted through a network as well as data structures associating such descriptors with an original copy of the image or an image derived therefrom, e.g. a thumbnail image.
摘要翻译： 描述了用于在图像上操作的方法和装置，特别是用于在不同尺度和不同旋转下进行兴趣点检测和/或描述的方法和装置，例如， 用于尺度不变和旋转不变的兴趣点检测和/或描述。 本发明可以提供用于在相同图像或不同图像中匹配兴趣点的改进的或替代的装置和方法。 本发明可以提供用于实现本发明的任何方法的替代或改进的软件。 本发明可以提供通过多次滤波操作产生的替代或改进的数据结构，以产生多个滤波图像，以及用于存储滤波图像本身的数据结构，例如， 存储在存储器中或通过网络传输。 本发明可以提供替代或改进的数据结构，包括图像中的兴趣点的描述符，例如。 如存储在存储器中或通过网络传输的数据结构，以及将这样的描述符与图像的原始副本或从其导出的图像相关联的数据结构。 缩略图。
-
公开(公告)号：US09904846B2
公开(公告)日：2018-02-27
申请号：US14346015
申请日：2011-09-20
申请人： Toshiki Kindo , Masahiro Ogawa , Ryuji Funayama
发明人： Toshiki Kindo , Masahiro Ogawa , Ryuji Funayama
CPC分类号： G06K9/00369 , B60W2420/40 , B60W2550/10 , G06K9/00342 , G06K9/00348 , G06K9/00805 , G08G1/08 , G08G1/166
摘要： According to the present invention, a pedestrian is detected from an imaged image and a partial image including the pedestrian is extracted, shape information of the pedestrian acquired from the extracted partial image is accumulated and the shape information of a predetermined time before and the current shape information are compared using the accumulated shape information to detect change in the movement of the pedestrian, discontinuous movement estimating information indicating a discontinuous movement of the pedestrian that occurs following the change in the movement of the pedestrian is acquired from a storage means at the time the change in the movement of the pedestrian is detected, and a behavior of the pedestrian is predicted using the acquired discontinuous movement estimating information.
-
公开(公告)号：US09632191B2
公开(公告)日：2017-04-25
申请号：US13637858
申请日：2011-09-20
申请人： Jun Sato , Ryuji Funayama
发明人： Jun Sato , Ryuji Funayama
CPC分类号： G01V1/001 , G01S3/808 , G01S3/86 , G08G1/166 , H04R3/005 , H04R2201/401 , H04R2430/21 , H04R2499/13
摘要： Disclosed is a sound source detection device 1 which compares information of sound collected by sound collectors 13, 14, 15, and 16 to detect a predetermined sound source. The sound source detection device 1 includes a target determination unit 22 which arranges sound collectors at the same distance from a noise source inside a mobile object to determine a detection-target region of a sound source, and a sound source detection unit 25 which detects the direction of the predetermined sound source using information of sound of the detection-target region determined by the target determination unit 22. Accordingly, the sound source detection unit 25 does not determine sound input to the sound collectors 13, 14, 15, and 16 at the same timing as a detection target, making it possible to eliminate the influence of a noise source other than a sound source inside the mobile object in advance.
-
-
-
-
-
-
-
-
-
搜索结果
58 条记录 (耗时 0.028 秒)
