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. 发明授权

US09008424B2 Method and system for comparing images 有权
标题翻译：用于比较图像的方法和系统
公开(公告)号：US09008424B2
公开(公告)日：2015-04-14
申请号：US13981824
申请日：2011-01-25
申请人： Giovanni Cordara , Gianluca Francini , Skjalg Lepsoy , Pedro Porto Buarque de Gusmao
发明人： Giovanni Cordara , Gianluca Francini , Skjalg Lepsoy , Pedro Porto Buarque de Gusmao
IPC分类号： G06K9/00 , G06K9/46 , G06K9/68 , G06K9/62
CPC分类号： G06K9/68 , G06K9/6211
摘要： A method for comparing a first image with a second image. The method identifies first keypoints in the first image and second keypoints in the second image and associates each first keypoint with a corresponding second keypoint to form a corresponding keypoint match. For each pair of first keypoints, the method further calculates the distance therebetween for obtaining a corresponding first length. Similarly, for each pair of second keypoints, the method calculates the distance therebetween for obtaining a corresponding second length. The method further calculates a plurality of distance ratios; each distance ratio is based on a length ratio between a selected one between a first length and a second length and a corresponding selected one between a second length and a first length, respectively.
摘要翻译：一种用于将第一图像与第二图像进行比较的方法。该方法识别第一图像中的第一关键点和第二图像中的第二关键点，并且将每个第一关键点与相应的第二关键点相关联以形成相应的关键点匹配。对于每对第一关键点，该方法进一步计算它们之间的距离以获得对应的第一长度。类似地，对于每对第二关键点，该方法计算它们之间的距离以获得相应的第二长度。该方法进一步计算多个距离比; 每个距离比基于分别在第一长度和第二长度之间的所选择的长度比和在第二长度和第一长度之间的相应选择的长度比。

2. 发明申请

US20130308861A1 METHOD AND SYSTEM FOR COMPARING IMAGES 有权
标题翻译：用于比较图像的方法和系统
公开(公告)号：US20130308861A1
公开(公告)日：2013-11-21
申请号：US13981824
申请日：2011-01-25
申请人： Giovanni Cordara , Gianluca Francini , Skjalg Lepsoy , Pedro Porto Buarque De Gusmao
发明人： Giovanni Cordara , Gianluca Francini , Skjalg Lepsoy , Pedro Porto Buarque De Gusmao
IPC分类号： G06K9/68
CPC分类号： G06K9/68 , G06K9/6211
摘要： A method for comparing a first image with a second image. The method identifies first keypoints in the first image and second keypoints in the second image and associates each first keypoint with a corresponding second keypoint to form a corresponding keypoint match. For each pair of first keypoints, the method further calculates the distance therebetween for obtaining a corresponding first length. Similarly, for each pair of second keypoints, the method calculates the distance therebetween for obtaining a corresponding second length. The method further calculates a plurality of distance ratios; each distance ratio is based on a length ratio between a selected one between a first length and a second length and a corresponding selected one between a second length and a first length, respectively.
摘要翻译：一种用于将第一图像与第二图像进行比较的方法。该方法识别第一图像中的第一关键点和第二图像中的第二关键点，并且将每个第一关键点与相应的第二关键点相关联以形成相应的关键点匹配。对于每对第一关键点，该方法进一步计算它们之间的距离以获得对应的第一长度。类似地，对于每对第二关键点，该方法计算它们之间的距离以获得相应的第二长度。该方法进一步计算多个距离比; 每个距离比基于分别在第一长度和第二长度之间的所选择的长度比和在第二长度和第一长度之间的相应选择的长度比。

3. 发明授权

US08625678B2 Method for scalable video coding on a plurality of space resolution levels 有权
标题翻译：用于在多个空间分辨率级别上进行可缩放视频编码的方法
公开(公告)号：US08625678B2
公开(公告)日：2014-01-07
申请号：US11992741
申请日：2005-09-29
申请人： Giovanni Cordara , Gianluca Francini , Skjalg Lepsoy
发明人： Giovanni Cordara , Gianluca Francini , Skjalg Lepsoy
IPC分类号： H04N7/12
CPC分类号： H04N19/53 , H04N19/537
摘要： A method for estimating motion for the scalable video coding, includes the step of estimating the motion field of a sequence of photograms which can be represented with a plurality of space resolution levels including computing the motion field for the minimum resolution level and, until the maximum resolution level is reached, repeating the steps of: rising by one resolution level; extracting the photograms for such resolution level; and computing the motion field for such resolution level. The motion field is computed through an optical flow equation which contains, for every higher level than the minimum resolution level, a regularization factor between levels which points out the difference between the solution for the considered level and the solution for the immediately lower resolution level. A more or less high value of the regularization factor implies more or less relevant changes of the component at the considered resolution during the following process iterations.
摘要翻译：用于估计可伸缩视频编码的运动的方法包括估计可以用多个空间分辨率级别表示的摄影图序列的运动场的步骤，包括计算最小分辨率级别的运动场，并且直到最大值达到分辨率水平，重复以上步骤：上升一分辨率水平; 提取这样的分辨率级别的照片; 并计算这种分辨率水平的运动场。运动场是通过一个光学流量方程来计算的，对于每个比最小分辨率级别高的级别，它包含指出所考虑的级别的解决方案与立即降低分辨率级别的解决方案之间的差异的级别之间的正则化因子。正则化因子的或多或少高值意味着在以下过程迭代期间，在考虑的分辨率下组件的或多或少的相关变化。

4. 发明授权

US08160353B2 Method for determining dense disparity fields in stereo vision 有权
标题翻译：用于确定立体视觉中密集视差场的方法
公开(公告)号：US08160353B2
公开(公告)日：2012-04-17
申请号：US12085854
申请日：2005-12-21
申请人： Gianluca Francini , Giovanni Cordara , Skjalg Lepsoy
发明人： Gianluca Francini , Giovanni Cordara , Skjalg Lepsoy
IPC分类号： G06K9/00
CPC分类号： G06T7/97 , G06K9/209 , H04N13/246 , H04N2013/0081
摘要： In a stereo vision system comprising two cameras shooting the same scene from different positions, a method is performed for determining dense disparity fields between digital images shot by the two cameras, including the steps of capturing a first and a second image of the scene, and determining, for each pixel of the second image, the displacement from a point in the first image to such pixel of the second image minimizing an optical flow objective function, wherein the optical flow objective function includes, for each pixel of the second image, a term depending in a monotonously increasing way on the distance between the epipolar line associated with such pixel and the above point in the first image, such term depending on calibration parameters of the two cameras and being weighed depending on the uncertainty of the calibration data.
摘要翻译：在包括从不同位置拍摄相同场景的两个摄像机的立体视觉系统中，执行用于确定由两个摄像机拍摄的数字图像之间的密集视差场的方法，包括捕获场景的第一和第二图像的步骤，以及为所述第二图像的每个像素确定从所述第一图像中的点到所述第二图像的所述像素的位移，使得所述光流目标函数最小化，其中所述光流目标函数对于所述第二图像的每个像素包括这取决于与这种像素相关联的核线与第一图像中的上述点之间的距离的单调增加的方式，该项取决于两个照相机的校准参数，并且根据校准数据的不确定性被称重。

5. 发明申请

US20090304090A1 Method for Scalable Video Coding 有权
标题翻译：可扩展视频编码方法
公开(公告)号：US20090304090A1
公开(公告)日：2009-12-10
申请号：US11992741
申请日：2005-09-29
申请人： Giovanni Cordara , Gianluca Francini , Skjalg Lepsoy
发明人： Giovanni Cordara , Gianluca Francini , Skjalg Lepsoy
IPC分类号： H04N7/12
CPC分类号： H04N19/53 , H04N19/537
摘要： A method for estimating motion for the scalable video coding, includes the step of estimating the motion field of a sequence of photograms which can be represented with a plurality of space resolution levels including computing the motion field for the minimum resolution level and, until the maximum resolution level is reached, repeating the steps of: rising by one resolution level; extracting the photograms for such resolution level; and computing the motion field for such resolution level. The motion field is computed through an optical flow equation which contains, for every higher level than the minimum resolution level, a regularization factor between levels which points out the difference between the solution for the considered level and the solution for the immediately lower resolution level. A more or less high value of the regularization factor implies more or less relevant changes of the component at the considered resolution during the following process iterations.
摘要翻译：用于估计可伸缩视频编码的运动的方法包括估计可以用多个空间分辨率级别表示的摄影图序列的运动场的步骤，包括计算最小分辨率级别的运动场，并且直到最大值达到分辨率水平，重复以上步骤：上升一分辨率水平; 提取这样的分辨率级别的照片; 并计算这种分辨率水平的运动场。运动场是通过一个光学流量方程来计算的，对于每个比最小分辨率级别高的级别，它包含指出所考虑的级别的解决方案与立即降低分辨率级别的解决方案之间的差异的级别之间的正则化因子。正则化因子的或多或少高值意味着在以下过程迭代期间，在考虑的分辨率下组件的或多或少的相关变化。

6. 发明申请

US20100215248A1 Method for Determining Dense Disparity Fields in Stereo Vision 有权
标题翻译：确定立体视觉中密集差距场的方法
公开(公告)号：US20100215248A1
公开(公告)日：2010-08-26
申请号：US12085854
申请日：2005-12-21
申请人： Gianluca Francini , Giovanni Cordara , Skjalg Lepsoy
发明人： Gianluca Francini , Giovanni Cordara , Skjalg Lepsoy
IPC分类号： G06K9/00
CPC分类号： G06T7/97 , G06K9/209 , H04N13/246 , H04N2013/0081
摘要： In a stereo vision system comprising two cameras shooting the same scene from different positions, a method is performed for determining dense disparity fields between digital images shot by the two cameras, including the steps of capturing a first and a second image of the scene, and determining, for each pixel of the second image, the displacement from a point in the first image to such pixel of the second image minimising an optical flow objective function, wherein the optical flow objective function includes, for each pixel of the second image, a term depending in a monotonously increasing way on the distance between the epipolar line associated with such pixel and the above point in the first image, such term depending on calibration parameters of the two cameras and being weighed depending on the uncertainty of the calibration data.
摘要翻译：在包括从不同位置拍摄相同场景的两个摄像机的立体视觉系统中，执行用于确定由两个摄像机拍摄的数字图像之间的密集视差场的方法，包括捕获场景的第一和第二图像的步骤，以及为所述第二图像的每个像素确定从所述第一图像中的点到所述第二图像的所述像素的位移，使得所述光流目标函数最小化，其中所述光流目标函数对于所述第二图像的每个像素包括这取决于与这种像素相关联的核线与第一图像中的上述点之间的距离的单调增加的方式，该项取决于两个照相机的校准参数，并且根据校准数据的不确定性被称重。

7. 发明授权

US09013487B2 Method for the calculation of the bounding box of vectorial graphic shapes 有权
标题翻译：计算矢量图形边界框的方法
公开(公告)号：US09013487B2
公开(公告)日：2015-04-21
申请号：US13520140
申请日：2009-12-30
申请人： Giovanni Cordara , Gianluca Francini , Diego Gibellino , Andrea Varesio
发明人： Giovanni Cordara , Gianluca Francini , Diego Gibellino , Andrea Varesio
IPC分类号： G06T11/20
CPC分类号： G06T11/203
摘要： Method for determining the bounding box of a computerized graphic shape comprising one or more primitives described in vectorial mode, wherein the bounding box is calculated by applying analytical mathematical formulas to the vectorial description of the primitives constituting the shape without preliminarily performing a phase of drawing and displaying of the shape through resolution of the vectorial primitives that compose it.
摘要翻译：一种用于确定包括以矢量模式描述的一个或多个原语的计算机化图形的边界框的方法，其中通过将分析数学公式应用于构成形状的图元的矢量描述而不预先执行绘制阶段来计算边界框，通过构成它的矢量图元的分辨率来显示形状。

8. 发明申请

US20120299932A1 METHOD FOR THE CALCULATION OF THE BOUNDING BOX OF VECTORIAL GRAPHIC SHAPES 有权
标题翻译：计算图形图形边框的方法
公开(公告)号：US20120299932A1
公开(公告)日：2012-11-29
申请号：US13520140
申请日：2009-12-30
申请人： Giovanni Cordara , Gianluca Francini , Diego Gibellino , Andrea Varesio
发明人： Giovanni Cordara , Gianluca Francini , Diego Gibellino , Andrea Varesio
IPC分类号： G06T11/20
CPC分类号： G06T11/203
摘要： Method for determining the bounding box of a computerized graphic shape comprising one or more primitives described in vectorial mode, wherein the bounding box is calculated by applying analytical mathematical formulas to the vectorial description of the primitives constituting the shape without preliminarily performing a phase of drawing and displaying of the shape through resolution of the vectorial primitives that compose it.
摘要翻译：一种用于确定包括以矢量模式描述的一个或多个原语的计算机化图形的边界框的方法，其中通过将分析数学公式应用于构成形状的图元的矢量描述而不预先执行绘制阶段来计算边界框，通过构成它的矢量图元的分辨率来显示形状。

9. 发明申请

US20090268809A1 Method, apparatus and system for robust video transmission 有权
标题翻译：用于强大视频传输的方法，装置和系统
公开(公告)号：US20090268809A1
公开(公告)日：2009-10-29
申请号：US12308882
申请日：2006-06-30
申请人： Giovanni Cordara , Marco Tagliasacchi , Stefano Tubaro
发明人： Giovanni Cordara , Marco Tagliasacchi , Stefano Tubaro
IPC分类号： H04N7/32
CPC分类号： H04N19/395 , H04N19/89
摘要： A method of transmitting video data related to a sequence of video frames, includes: encoding the video frames according to a first predictive encoding to generate encoded video data, the encoded video data including a prediction error based on the difference between a portion of a current video frame in the sequence and a first predictor thereof based on a first preceding video frame in the sequence; generating auxiliary video data related to the portion of the current video frame; and transmitting the encoded video data and the auxiliary video data to a receiver, the encoded video data being transmitted over a first channel, and the auxiliary video data being transmitted over a second channel. The step of generating auxiliary video data includes calculating a correlation between the first predictor and a predetermined second predictor based on a second preceding video frame in the sequence, the second preceding video frame preceding in the sequence the first preceding video frame.
摘要翻译：一种发送与视频帧序列相关的视频数据的方法包括：根据第一预测编码对视频帧进行编码以产生编码视频数据，所述编码视频数据包括基于当前的一部分之间的差的预测误差基于序列中的第一先前视频帧的序列中的视频帧和第一预测器; 产生与当前视频帧的部分有关的辅助视频数据; 以及将经编码的视频数据和辅助视频数据发送到接收机，经由第一信道发送的编码视频数据，以及通过第二信道发送的辅助视频数据。产生辅助视频数据的步骤包括基于序列中的第二先前视频帧计算第一预测器和预定第二预测器之间的相关性，前序视频帧中的第二先前视频帧。

10. 发明申请

US20050021805A1 System and method for transmitting multimedia information streams, for instance for remote teaching 审中-公开
标题翻译：用于传输多媒体信息流的系统和方法，例如用于远程教学
公开(公告)号：US20050021805A1
公开(公告)日：2005-01-27
申请号：US10491398
申请日：2002-09-27
申请人： Gianluca De Petris , Alessandro Costa Laia , Giovanni Cordara
发明人： Gianluca De Petris , Alessandro Costa Laia , Giovanni Cordara
IPC分类号： G09B5/06 , G09B5/08 , H04N7/14 , H04N7/15 , G06F15/16
CPC分类号： H04N7/147 , G09B5/06 , G09B5/08 , H04N7/15
摘要： A system for accomplishing the transmission of a multimedia stream between at least a transmitter (3) and at least a receiver (5). The multimedia stream comprises an audio/video stream with at least an information stream associated thereto. To at least some of the objects included in the multimedia stream is associated a respective description and space-type characterisation, so that each receiver (5) is able to interact with the aforesaid objects changing their space-time position relative to the other stream independently from the transmitter (3) and from the other receivers. Preferential application to remote teaching techniques.
摘要翻译：一种用于在至少发射机（3）和至少一个接收机（5）之间完成多媒体流传输的系统。多媒体流包括至少与其相关联的信息流的音频/视频流。对于包括在多媒体流中的至少一些对象与相应的描述和空间类型表征相关联，使得每个接收器（5）能够与前述对象相互作用，以独立地相对于另一个流改变它们的时空位置从发射机（3）和其他接收机。优先应用于远程教学技术。

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