公开(公告)号：US09524556B2

公开(公告)日：2016-12-20

申请号：US14705348

申请日：2015-05-06

申请人： Nokia Corporation

发明人： Mithun Uliyar ,  Gururaj Gopal Putraya ,  Soumik Ukil ,  Basavaraja S V ,  Krishna Annasagar Govindarao ,  Veldandi Muninder

IPC分类号： G06T7/00 ,  H04N13/02

CPC分类号： G06T7/0055 ,  G06T7/514 ,  G06T7/557 ,  G06T2200/21 ,  G06T2207/10052 ,  G06T2207/20228 ,  H04N13/111 ,  H04N13/214 ,  H04N13/232 ,  H04N13/271 ,  H04N2013/0081

摘要： In an example embodiment, a method, apparatus and computer program product are provided. The method includes computing a first cost volume for a light-field image. A first depth map comprising depth information of the plurality of sub-images of the light-field image is computed based on the first cost volume. A first view image comprising reconstruction information is reconstructed based on the depth information of the plurality of sub-images. A second cost volume corresponding to the first cost volume is computed based on the reconstruction information. The second cost volume is filtered based on the first view image to generate an aggregated cost volume. A second depth map is generated based on the aggregated cost volume. The second depth map facilitates generation of a second view image that is associated with a resolution higher than a resolution of the first view image.

摘要翻译： 在示例实施例中，提供了一种方法，装置和计算机程序产品。 该方法包括计算光场图像的第一成本体积。 基于第一成本体积计算包括光场图像的多个子图像的深度信息的第一深度图。 基于多个子图像的深度信息来重构包括重建信息的第一视图图像。 基于重构信息计算与第一成本量对应的第二成本量。 基于第一视图图像来过滤第二成本量以生成聚合成本量。 基于聚合成本量生成第二个深度图。 第二深度图有助于产生与高于第一视图图像的分辨率的分辨率相关联的第二视图图像。

公开(公告)号：US09390508B2

公开(公告)日：2016-07-12

申请号：US14617348

申请日：2015-02-09

申请人： Nokia Corporation

发明人： Soumik Ukil ,  Veldandi Muninder ,  Krishna Annasagar Govindarao

IPC分类号： G06K9/00 ,  G06T7/00

CPC分类号： G06T7/0075 ,  G06T7/593 ,  G06T2207/10012 ,  G06T2207/10024 ,  G06T2207/20072 ,  G06T2207/20076

摘要： In an example embodiment a method, apparatus and computer program product are provided. The method includes facilitating receipt of a first and a second image. A first and a second aggregated cost volume associated with pixels of the first and the second images are determined for a plurality of disparity values. A first and a second disparity maps are generated based on the first and the second aggregated cost volume. A confidence map for disparity values of the first image is generated based on the first aggregated cost volume. One or more infinity regions in the first image are determined based on a number of confident pixels in color segments of the first image. A third disparity map is generated by determining filtered disparity values for the pixels of the first image where filtered disparity values for pixels of the one or more infinity regions are a pre-defined disparity value.

摘要翻译： 在示例实施例中，提供了一种方法，装置和计算机程序产品。 该方法包括促进第一和第二图像的接收。 针对多个视差值确定与第一和第二图像的像素相关联的第一和第二聚合成本音量。 基于第一和第二聚合成本量产生第一和第二视差图。 基于第一聚合成本体积生成第一图像的差异值的置信度图。 基于第一图像的颜色段中的可信像素的数量来确定第一图像中的一个或多个无穷大区域。 通过确定第一图像的像素的滤波视差值来生成第三视差图，其中一个或多个无限大区域的像素的滤波视差值是预定义的视差值。

公开(公告)号：US09361721B2

公开(公告)日：2016-06-07

申请号：US14359053

申请日：2012-11-07

申请人： Nokia Corporation

发明人： Veldandi Muninder ,  S V Basavaraja

IPC分类号： G06T11/60 ,  G06K9/46 ,  G06T7/00 ,  G06T3/40

CPC分类号： G06T11/60 ,  G06K9/4638 ,  G06T3/4038

摘要： Various methods are provided for processing images. One example method may include computing a starting point and an ending point for an image seam as defined by an intersection of a rectangle bounding a first image and a rectangle bounding a second image. The method may also include determining whether the starting point and the ending point for the image seam are final points based on a determined mask region. The method may also include refining the starting point and the ending point by using an intersection of a mask image of the first image and a mask image of the second image in an instance in which it is determined that the starting point and the ending point are not final points. The method may also include computing a seam direction and one or more seam points using the starting point and the ending point.

摘要翻译： 提供了各种处理图像的方法。 一个示例性方法可以包括计算由界定第一图像和限定第二图像的矩形的矩形的交点确定的图像接缝的起点和终点。 该方法还可以包括基于确定的掩模区域来确定图像接缝的起始点和终点是否是最终点。 该方法还可以包括通过使用第一图像的掩模图像和第二图像的掩模图像的交集来确定起始点和终点，其中确定起点和终点是 不是最终点。 该方法还可以包括使用起点和终点来计算接缝方向和一个或多个接缝点。

公开(公告)号：US09147226B2

公开(公告)日：2015-09-29

申请号：US14012006

申请日：2013-08-28

申请人： Nokia Corporation

发明人： Basavaraja S V ,  Veldandi Muninder

IPC分类号： G06K9/32 ,  G06T3/00 ,  G06T3/40

CPC分类号： G06T3/0012 ,  G06T3/4038

摘要： In accordance with an example embodiment a method, apparatus and computer program product are provided. The method comprises extracting a set of image features from a first image and a corresponding set of image features from a second image. A first transformation matrix and a second transformation matrix are computed between the first image and the second image based on a matching of the set of image features in the first image with the corresponding set of image features in the second image. A first set of feature points is determined based on the first transformation matrix, and a second set of feature points based on the second transformation matrix. A transformation matrix is estimated between the first set of feature points and the second set of feature points. The second image is aligned with the first image based on the transformation matrix.

摘要翻译： 根据示例实施例，提供了一种方法，装置和计算机程序产品。 该方法包括从第二图像中提取一组图像特征和来自第二图像的相应图像特征集合。 基于第一图像中的图像特征集合与第二图像中的相应图像特征集的匹配，在第一图像和第二图像之间计算第一变换矩阵和第二变换矩阵。 基于第一变换矩阵和基于第二变换矩阵的第二组特征点来确定第一组特征点。 在第一组特征点和第二组特征点之间估计变换矩阵。 基于变换矩阵将第二图像与第一图像对准。

公开(公告)号：US20150131909A1

公开(公告)日：2015-05-14

申请号：US14395962

申请日：2013-04-05

申请人： Nokia Corporation

发明人： Veldandi Muninder ,  Basavaraja S V

IPC分类号： G06T3/40 ,  G06T3/00 ,  H04N5/232 ,  G06K9/46

CPC分类号： G06T3/4038 ,  G06K9/4609 ,  G06T3/0068 ,  G06T2200/32 ,  H04N5/23238

摘要： In accordance with an example embodiment a method, apparatus and computer program product are provided. The method comprise assigning weights to at least one first feature and at least one second feature. The at least one first feature may be associated with a first image and the at least one second feature may be associated with a second image. The weights are assigned based on a distance of the at least one first feature and the at least one second feature from a central portion of the corresponding one of the first image and the second image. The method further includes registering the first image and the second image based at least on the assigned weights to determine transforms between the first image and the second image. The first image and the second image may be based on the determined transform.

摘要翻译： 根据示例实施例，提供了一种方法，装置和计算机程序产品。 该方法包括将权重分配给至少一个第一特征和至少一个第二特征。 所述至少一个第一特征可以与第一图像相关联，并且所述至少一个第二特征可以与第二图像相关联。 所述权重基于所述至少一个第一特征的距离和所述至少一个第二特征从所述第一图像和所述第二图像中的对应的一个的中心部分分配。 该方法还包括至少基于分配的权重来登记第一图像和第二图像，以确定第一图像和第二图像之间的变换。 第一图像和第二图像可以基于所确定的变换。

公开(公告)号：US20140314325A1

公开(公告)日：2014-10-23

申请号：US14359053

申请日：2012-11-07

申请人： Nokia Corporation

发明人： Veldandi Muninder ,  S V Basavaraja

IPC分类号： G06T11/60 ,  G06T7/00 ,  G06K9/46

CPC分类号： G06T11/60 ,  G06K9/4638 ,  G06T3/4038

摘要： Various methods are provided for processing images. One example method may include computing a starting point and an ending point for an image seam as defined by an intersection of a rectangle bounding a first image and a rectangle bounding a second image. The method may also include determining whether the starting point and the ending point for the image seam are final points based on a determined mask region. The method may also include refining the starting point and the ending point by using an intersection of a mask image of the first image and a mask image of the second image in an instance in which it is determined that the starting point and the ending point are not final points. The method may also include computing a seam direction and one or more seam points using the starting point and the ending point.

摘要翻译： 提供了各种处理图像的方法。 一个示例性方法可以包括计算由界定第一图像和限定第二图像的矩形的矩形的交点确定的图像接缝的起始点和终点。 该方法还可以包括基于确定的掩模区域来确定图像接缝的起始点和终点是否是最终点。 该方法还可以包括通过使用第一图像的掩模图像和第二图像的掩模图像的交集来确定起始点和终点，其中确定起点和终点是 不是最终点。 该方法还可以包括使用起点和终点来计算接缝方向和一个或多个接缝点。

公开(公告)号：US20140147043A1

公开(公告)日：2014-05-29

申请号：US14078767

申请日：2013-11-13

申请人： NOKIA CORPORATION

发明人： Veldandi Muninder

IPC分类号： G06T7/40

CPC分类号： G06T7/408 ,  G06T5/001 ,  G06T5/50 ,  G06T7/33 ,  G06T2207/10024 ,  H04N5/23229 ,  H04N9/045

摘要： In accordance with an example embodiment a method, apparatus and computer program product are provided. The method comprises receiving colour image frames and panchromatic image frames associated with a scene. The colour image frames correspond to the panchromatic image frames. The method further comprises computing registration information based on a panchromatic image frame and one or more panchromatic image frames from among the panchromatic image frames. A colour image frame corresponding to the panchromatic image frame is modified based on the registration information.

摘要翻译： 根据示例实施例，提供了一种方法，装置和计算机程序产品。 该方法包括接收与场景相关联的彩色图像帧和全色图像帧。 彩色图像帧对应于全色图像帧。 该方法还包括基于全色图像帧和来自全色图像帧中的一个或多个全色图像帧来计算登记信息。 基于注册信息修改与全色图像帧对应的彩色图像帧。

公开(公告)号：US09679220B2

公开(公告)日：2017-06-13

申请号：US14700052

申请日：2015-04-29

申请人： Nokia Corporation

发明人： Krishna Annasagar Govindarao ,  Soumik Ukil ,  Veldandi Muninder

IPC分类号： G06K9/00 ,  G06K9/68 ,  G06K9/46 ,  G06T1/00 ,  G06T9/40 ,  G06K9/32 ,  G06F17/30 ,  G06T7/00 ,  G06T7/11 ,  G06T7/162

CPC分类号： G06K9/469 ,  G06F17/30958 ,  G06K9/3233 ,  G06K2009/3291 ,  G06T1/0007 ,  G06T7/11 ,  G06T7/162 ,  G06T7/97 ,  G06T9/40 ,  G06T2207/10004 ,  G06T2207/10028 ,  G06T2207/20072

摘要： In an example embodiment, a method, apparatus and computer program product are provided. The method includes facilitating receipt of an image of a scene and determining a graph based on connecting nodes of the image. The nodes are either pixels or superpixels of the image. The graph is determined by determining one or more connections of a node to one or more nodes belonging to a pre-defined image region around the node in the image. The connections are associated with edge weights that are determined based on at least one of similarity parameters and spatial distances between the node and the one or more nodes. The method includes determining disparity values at the nodes of the image based at least on performing tree based aggregation of a cost volume on the graph, where the cost volume is associated with the image and at least one view image of the scene.

公开(公告)号：US20150170371A1

公开(公告)日：2015-06-18

申请号：US14561002

申请日：2014-12-04

申请人： Nokia Corporation

发明人： Veldandi Muninder ,  Soumik Ukil ,  Krishna Annasagar Govindarao

IPC分类号： G06T7/00 ,  H04N13/00 ,  G06T7/40

CPC分类号： G06T7/593 ,  G06T2207/10012 ,  G06T2207/10024 ,  H04N13/128 ,  H04N2013/0081

摘要： In an example embodiment, a method, apparatus and computer program product are provided. The method includes facilitating receipt of primary depth map and plurality of color segments, the primary depth map associated with a first image and a second image that are stereoscopic pair of images of a scene, and the color segments associated with the first image. The method includes generating plurality of disparity planes based on the color segments and the primary depth map. The method includes determining aggregated cost volume between pixels of the first and second images for the disparity planes. The method includes assigning plane labels corresponding to the disparity planes to pixels of the first and second images based on the aggregated cost volume, an individual pixel being assigned a plane label. The method includes generating secondary depth map based on the plane labels assigned to the pixels of the first and second images.

摘要翻译： 在示例实施例中，提供了一种方法，装置和计算机程序产品。 该方法包括促进主要深度图和多个颜色段的接收，与第一图像相关联的主要深度图和作为场景的立体对图像的第二图像以及与第一图像相关联的颜色分段。 该方法包括基于颜色段和主深度图生成多个视差平面。 该方法包括确定视差平面的第一和第二图像的像素之间的聚合成本体积。 该方法包括基于聚合成本体积分配对应于视差平面的平面标签到第一和第二图像的像素，分配单个像素的平面标签。 该方法包括基于分配给第一和第二图像的像素的平面标签产生二次深度图。

公开(公告)号：US20150078669A1

公开(公告)日：2015-03-19

申请号：US14333857

申请日：2014-07-17

申请人： Nokia Corporation

发明人： Soumik Ukil ,  Veldandi Muninder ,  Krishna Annasagar Govindarao

IPC分类号： G06K9/46 ,  G06K9/62

CPC分类号： G06K9/00208 ,  G06K9/00234 ,  G06K9/66 ,  G06T7/11 ,  G06T7/593 ,  G06T7/97 ,  G06T2207/10012

摘要： In an example embodiment, a method, apparatus and computer program product are provided. The method includes facilitating receipt of a first image and a second image of a scene comprising one or more objects. The method includes detecting the objects in the first image by detecting object point of the objects in the first image. The method includes detecting the object points of the objects in the second image based on detection of the object points of the objects in the first image. Detection of an object point in the second image that corresponds to an object point of the first image comprises searching for the object point on an epipolar line in the second image corresponding to the object point of the first image. The method includes determining disparity values between the objects points in the first image and the object points in the second image.

摘要翻译： 在示例实施例中，提供了一种方法，装置和计算机程序产品。 该方法包括便利接收包含一个或多个对象的场景的第一图像和第二图像。 该方法包括通过检测第一图像中的对象的对象点来检测第一图像中的对象。 该方法包括：基于第一图像中对象的对象点的检测来检测第二图像中的对象的对象点。 对与第一图像的对象点对应的第二图像中的对象点的检测包括搜索对应于第一图像的对象点的第二图像中的核线上的对象点。 该方法包括确定第一图像中的对象点与第二图像中的对象点之间的视差值。