公开(公告)号：US20080107186A1

公开(公告)日：2008-05-08

申请号：US11556092

申请日：2006-11-02

申请人： Mikhail Brusnitsyn ,  Ian Clarke ,  Hui Zhou

发明人： Mikhail Brusnitsyn ,  Ian Clarke ,  Hui Zhou

IPC分类号： H04N7/24

CPC分类号： H04N19/86 ,  H04N19/117 ,  H04N19/139 ,  H04N19/154 ,  H04N19/176 ,  H04N19/527

摘要： A method of estimating and compensating for jitter between two video frames in a digital video sequence comprises comparing a pixel subset in one video frame to candidate matching pixel subsets within a search area in the other video frame to obtain a preliminary matching pixel subset. Based on the location of the preliminary matching pixel subset, an adapted search area is formed and the comparing is continued within the adapted search area to obtain a final matching pixel subset. Motion is calculated between the video frames based on the final match thereby to estimate the jitter. The video frames are then transformed based on the estimated jitter.

摘要翻译： 一种估计和补偿数字视频序列中两个视频帧之间的抖动的方法包括将一个视频帧中的像素子集与另一视频帧中的搜索区域内的候选匹配像素子集进行比较，以获得初步匹配像素子集。 基于初步匹配像素子集的位置，形成适应搜索区域，并且在适应搜索区域内继续进行比较以获得最终匹配像素子集。 基于最终匹配在视频帧之间计算运动，从而估计抖动。 然后基于估计的抖动来变换视频帧。

公开(公告)号：US08130845B2

公开(公告)日：2012-03-06

申请号：US11556092

申请日：2006-11-02

申请人： Mikhail Brusnitsyn ,  Ian Clarke ,  Hui Zhou

发明人： Mikhail Brusnitsyn ,  Ian Clarke ,  Hui Zhou

IPC分类号： H04N7/26

CPC分类号： H04N19/86 ,  H04N19/117 ,  H04N19/139 ,  H04N19/154 ,  H04N19/176 ,  H04N19/527

摘要： A method of estimating and compensating for jitter between two video frames in a digital video sequence comprises comparing a pixel subset in one video frame to candidate matching pixel subsets within a search area in the other video frame to obtain a preliminary matching pixel subset. Based on the location of the preliminary matching pixel subset, an adapted search area is formed and the comparing is continued within the adapted search area to obtain a final matching pixel subset. Motion is calculated between the video frames based on the final match thereby to estimate the jitter. The video frames are then transformed based on the estimated jitter.

摘要翻译： 一种估计和补偿数字视频序列中两个视频帧之间的抖动的方法包括将一个视频帧中的像素子集与另一视频帧中的搜索区域内的候选匹配像素子集进行比较，以获得初步匹配像素子集。 基于初步匹配像素子集的位置，形成适应搜索区域，并且在适应搜索区域内继续进行比较以获得最终匹配像素子集。 基于最终匹配在视频帧之间计算运动，从而估计抖动。 然后基于估计的抖动来变换视频帧。

公开(公告)号：US20060045322A1

公开(公告)日：2006-03-02

申请号：US10926658

申请日：2004-08-26

申请人： Ian Clarke ,  Hui Zhou ,  Jeffrey Achong

发明人： Ian Clarke ,  Hui Zhou ,  Jeffrey Achong

IPC分类号： G06K9/00

CPC分类号： G06K9/186 ,  G06Q20/042

摘要： A system and method of recognizing characters in a captured image, includes selecting a portion of the image encompassing a string of characters in the captured image to be recognized. The selected portion is examined to identify segments that potentially include the characters of the string. During the examining multiple tests on pixels in the selected portion are performed. The identified segments are then examined to recognize the string of characters.

公开(公告)号：US20070031059A1

公开(公告)日：2007-02-08

申请号：US11198055

申请日：2005-08-05

申请人： Jeffrey Achong ,  Hui Zhou ,  Ian Clarke

发明人： Jeffrey Achong ,  Hui Zhou ,  Ian Clarke

IPC分类号： G06K9/40

CPC分类号： G06K9/38 ,  G06K2209/01 ,  G06T5/009 ,  G06T5/40

摘要： A method of enhancing contrast in a digital image comprises isolating pixels of the image having intensities falling within a low intensity range, determining at least one feature of the pixel distribution with the range and adjusting intensities of pixels in the image to make the pixels within the range more visually distinct. An apparatus for enhancing contrast in a digital image is also provided.

摘要翻译： 一种增强数字图像中的对比度的方法包括：分离具有落在低强度范围内的强度的图像的像素，确定具有该范围的像素分布的至少一个特征并调整图像中的像素的强度，以使像素在 范围更加视觉上不同。 还提供了一种用于增强数字图像中的对比度的装置。

公开(公告)号：US20070041656A1

公开(公告)日：2007-02-22

申请号：US11207365

申请日：2005-08-19

申请人： Ian Clarke ,  Hui Zhou ,  Puneet Khanduri

发明人： Ian Clarke ,  Hui Zhou ,  Puneet Khanduri

IPC分类号： G06K9/40

CPC分类号： G06T3/4038

摘要： In one embodiment, a method of reducing brightness variations in a panorama comprises calculating a gamma plane based on the panorama, blurring and normalizing the gamma plane and then applying the blurred and normalized gamma plane to the panorama thereby to reduce brightness variations therein.

摘要翻译： 在一个实施例中，一种降低全景图中的亮度变化的方法包括基于全景图计算伽马平面，模糊和归一化伽马平面，然后将模糊和归一化的伽马平面应用于全景图，从而减少其中的亮度变化。

公开(公告)号：US20070008312A1

公开(公告)日：2007-01-11

申请号：US11177811

申请日：2005-07-08

申请人： Hui Zhou ,  Derek Hang Chun Kwok ,  Ian Clarke

发明人： Hui Zhou ,  Derek Hang Chun Kwok ,  Ian Clarke

IPC分类号： G06T15/00

CPC分类号： G06T7/80 ,  G06T2200/32 ,  G06T2207/10012

摘要： A method of estimating three-dimensional camera position information from a series of two-dimensional images that form a panorama employs common features in adjoining image pairs in the series to estimate a transform between the images in the pairs. The common features are subsequently employed to adjust an estimated rotational component of each transform by reducing error between coordinates corresponding to the common features in three-dimensional space in image pairs, on a pair-by-pair basis. A global optimization of the position estimation, used for long sequences of images such as 360 degree panoramas, refines the estimates of the rotational and focal length components of the transforms by concurrently reducing error between all 3D common feature coordinates for all adjoining pairs.

摘要翻译： 从形成全景的一系列二维图像中估计三维相机位置信息的方法在系列中的相邻图像对中使用公共特征来估计对中的图像之间的变换。 随后采用共同特征，通过在逐对的基础上减少图像对中的三维空间中与公共特征相对应的坐标之间的误差来调整每个变换的估计旋转分量。 用于诸如360度全景的长序列图像的位置估计的全局优化通过同时减少所有相邻对的所有3D共同特征坐标之间的误差来精化变换的旋转和焦距分量的估计。

公开(公告)号：US20060072853A1

公开(公告)日：2006-04-06

申请号：US10958838

申请日：2004-10-05

申请人： Ian Clarke ,  Hui Zhou ,  Jeffrey Achong

发明人： Ian Clarke ,  Hui Zhou ,  Jeffrey Achong

IPC分类号： G06K9/32

CPC分类号： G06T3/0012

摘要： A method of fractionally resizing an image comprises locating areas of sensitivity in the image. Adjustment lines in the image are selected at least partially based on the location of the located areas of sensitivity. The image is then resized along the adjustment lines. An apparatus for fractionally resizing an image is also provided.

公开(公告)号：US07593591B2

公开(公告)日：2009-09-22

申请号：US11198055

申请日：2005-08-05

申请人： Jeffrey Matthew Achong ,  Hui Zhou ,  Ian Clarke

发明人： Jeffrey Matthew Achong ,  Hui Zhou ,  Ian Clarke

IPC分类号： G06K9/40 ,  G06K9/38

CPC分类号： G06K9/38 ,  G06K2209/01 ,  G06T5/009 ,  G06T5/40

摘要： A method of enhancing contrast in a digital image comprises isolating pixels of the image having intensities falling within a low intensity range, determining at least one feature of the pixel distribution with the range and adjusting intensities of pixels in the image to make the pixels within the range more visually distinct. An apparatus for enhancing contrast in a digital image is also provided.

摘要翻译： 一种增强数字图像中的对比度的方法包括：分离具有落在低强度范围内的强度的图像的像素，确定具有该范围的像素分布的至少一个特征并调整图像中的像素的强度，以使像素在 范围更加视觉上不同。 还提供了用于增强数字图像中的对比度的装置。

公开(公告)号：US07574071B2

公开(公告)日：2009-08-11

申请号：US10958838

申请日：2004-10-05

申请人： Ian Clarke ,  Hui Zhou ,  Jeffrey Matthew Achong

发明人： Ian Clarke ,  Hui Zhou ,  Jeffrey Matthew Achong

IPC分类号： G06K9/32

CPC分类号： G06T3/0012

摘要： A method of fractionally resizing an image comprises locating areas of sensitivity in the image. Adjustment lines in the image are selected at least partially based on the location of the located areas of sensitivity. The image is then resized along the adjustment lines. An apparatus for fractionally resizing an image is also provided.

摘要翻译： 一种分数尺寸调整图像的方法包括在图像中定位敏感区域。 至少部分地基于所定位的敏感区域的位置来选择图像中的调整线。 然后，图像沿调整线调整大小。 还提供了用于分数尺寸调整图像的设备。

公开(公告)号：US07565029B2

公开(公告)日：2009-07-21

申请号：US11177811

申请日：2005-07-08

申请人： Hui Zhou ,  Derek Hang Chun Kwok ,  Ian Clarke

发明人： Hui Zhou ,  Derek Hang Chun Kwok ,  Ian Clarke

IPC分类号： G06K9/36 ,  G06K9/00

CPC分类号： G06T7/80 ,  G06T2200/32 ,  G06T2207/10012

摘要： A method of estimating three-dimensional camera position information from a series of two-dimensional images that form a panorama employs common features in adjoining image pairs in the series to estimate a transform between the images in the pairs. The common features are subsequently employed to adjust an estimated rotational component of each transform by reducing error between coordinates corresponding to the common features in three-dimensional space in image pairs, on a pair-by-pair basis. A global optimization of the position estimation, used for long sequences of images such as 360 degree panoramas, refines the estimates of the rotational and focal length components of the transforms by concurrently reducing error between all 3D common feature coordinates for all adjoining pairs.

摘要翻译： 从形成全景的一系列二维图像中估计三维相机位置信息的方法在系列中的相邻图像对中使用公共特征来估计对中的图像之间的变换。 随后采用共同特征，通过在逐对的基础上减少图像对中的三维空间中与公共特征相对应的坐标之间的误差来调整每个变换的估计旋转分量。 用于诸如360度全景的长序列图像的位置估计的全局优化通过同时减少所有相邻对的所有3D共同特征坐标之间的误差来精化变换的旋转和焦距分量的估计。