公开(公告)号：US20110299770A1

公开(公告)日：2011-12-08

申请号：US12959056

申请日：2010-12-02

申请人： Sundeep Vaddadi ,  John H. Hong ,  Onur C. Hamsici ,  Yuriy Reznik ,  Chong U. Lee

发明人： Sundeep Vaddadi ,  John H. Hong ,  Onur C. Hamsici ,  Yuriy Reznik ,  Chong U. Lee

IPC分类号： G06K9/46

CPC分类号： G06K9/6211

摘要： A method for feature matching in image recognition is provided. First, image scaling may be based on a feature distribution across scale spaces for an image to estimate image size/resolution, where peak(s) in the keypoint distribution at different scales is used to track a dominant image scale and roughly track object sizes. Second, instead of using all detected features in an image for feature matching, keypoints may be pruned based on cluster density and/or the scale level in which the keypoints are detected. Keypoints falling within high-density clusters may be preferred over features falling within lower density clusters for purposes of feature matching. Third, inlier-to-outlier keypoint ratios are increased by spatially constraining keypoints into clusters in order to reduce or avoid geometric consistency checking for the image.

摘要翻译： 提供了图像识别中特征匹配的方法。 首先，图像缩放可以基于用于图像的尺度空间上的特征分布来估计图像尺寸/分辨率，其中使用不同尺度的关键点分布中的峰值来跟踪主要图像尺度并粗略跟踪对象尺寸。 其次，代替使用图像中的所有检测到的特征进行特征匹配，可以基于检测到关键点的聚类密度和/或比例级别来修剪关键点。 落入高密度群集中的关键点可能优于落入低密度群集中的特征，用于特征匹配。 第三，通过将关键点空间约束成簇，从而增加关键点比率，以减少或避免图像的几何一致性检查。

公开(公告)号：US08706711B2

公开(公告)日：2014-04-22

申请号：US13340024

申请日：2011-12-29

申请人： Sundeep Vaddadi ,  Onur C. Hamsici ,  John H. Hong ,  Yuriy Reznik ,  Chong U. Lee

发明人： Sundeep Vaddadi ,  Onur C. Hamsici ,  John H. Hong ,  Yuriy Reznik ,  Chong U. Lee

IPC分类号： G06F17/30

CPC分类号： G06K9/6282 ,  G06K9/6228

摘要： Various arrangements for using a k-dimensional tree for a search are presented. A plurality of descriptors may be stored. Each of the plurality of descriptors stored is linked with a first number of stored dimensions. The search may be performed using the k-dimensional tree for one or more query descriptors that at least approximately match one or more of the plurality of descriptors linked with the first number of stored dimensions. The k-dimensional tree may be built using the plurality of descriptors wherein each of the plurality of descriptors is linked with a second number of dimensions when the k-dimensional tree is built. The second number of dimensions may be a greater number of dimensions than the first number of stored dimensions.

摘要翻译： 提出了使用k维树进行搜索的各种布置。 可以存储多个描述符。 所存储的多个描述符中的每一个与存储维度的第一数量相关联。 可以使用k维树进行搜索，所述查询描述符至少近似地匹配与第一数量的存储维度相链接的多个描述符中的一个或多个。 可以使用多个描述符构建k维树，其中当构建k维树时，多个描述符中的每个描述符与第二数量的维度相关联。 第二数量的尺寸可以是比第一数量的存储尺寸更大的尺寸数量。

公开(公告)号：US08705876B2

公开(公告)日：2014-04-22

申请号：US12959056

申请日：2010-12-02

申请人： Sundeep Vaddadi ,  John H. Hong ,  Onur C. Hamsici ,  Yuriy Reznik ,  Chong U. Lee

发明人： Sundeep Vaddadi ,  John H. Hong ,  Onur C. Hamsici ,  Yuriy Reznik ,  Chong U. Lee

IPC分类号： G06K9/62

CPC分类号： G06K9/6211

摘要： A method for feature matching in image recognition is provided. First, image scaling may be based on a feature distribution across scale spaces for an image to estimate image size/resolution, where peak(s) in the keypoint distribution at different scales is used to track a dominant image scale and roughly track object sizes. Second, instead of using all detected features in an image for feature matching, keypoints may be pruned based on cluster density and/or the scale level in which the keypoints are detected. Keypoints falling within high-density clusters may be preferred over features falling within lower density clusters for purposes of feature matching. Third, inlier-to-outlier keypoint ratios are increased by spatially constraining keypoints into clusters in order to reduce or avoid geometric consistency checking for the image.

摘要翻译： 提供了图像识别中特征匹配的方法。 首先，图像缩放可以基于用于图像的尺度空间上的特征分布来估计图像尺寸/分辨率，其中使用不同尺度的关键点分布中的峰值来跟踪主要图像尺度并粗略跟踪对象尺寸。 其次，代替使用图像中的所有检测到的特征进行特征匹配，可以基于检测到关键点的聚类密度和/或比例级别来修剪关键点。 落入高密度群集中的关键点可能优于落入低密度群集中的特征，用于特征匹配。 第三，通过将关键点空间约束成簇，从而增加关键点比率，以减少或避免图像的几何一致性检查。

公开(公告)号：US08582889B2

公开(公告)日：2013-11-12

申请号：US12986607

申请日：2011-01-07

申请人： Sundeep Vaddadi ,  John H. Hong ,  Onur C. Hamsici ,  Chong U. Lee

发明人： Sundeep Vaddadi ,  John H. Hong ,  Onur C. Hamsici ,  Chong U. Lee

IPC分类号： G06K9/00

CPC分类号： G06K9/4671

摘要： A normalization process is implemented at a difference of scale space to completely or substantially reduce the effect that illumination changes has on feature/keypoint detection in an image. An image may be processed by progressively blurring the image using a smoothening function to generate a smoothened scale space for the image. A difference of scale space may be generated by taking the difference between two different smoothened versions of the image. A normalized difference of scale space image may be generated by dividing the difference of scale space image by a third smoothened version of the image, where the third smoothened version of the image that is as smooth or smoother than the smoothest of the two different smoothened versions of the image. The normalized difference of scale space image may then be used to detect one or more features/keypoints for the image.

摘要翻译： 在尺度空间的差异上实现归一化过程以完全或基本上减少照明变化对图像中的特征/关键点检测的影响。 可以通过使用平滑函数逐渐模糊图像来生成图像来生成图像，以生成平滑的图像尺度空间。 可以通过获取图像的两个不同平滑版本之间的差异来产生比例空间的差异。 尺度空间图像的归一化差异可以通过将尺度空间图像的差除以图像的第三平滑版本而生成，其中图像的第三平滑版本比两个不同平滑版本中最平滑的平滑或平滑 的图像。 尺度空间图像的归一化差异可以用于检测图像的一个或多个特征/关键点。

公开(公告)号：US20120330967A1

公开(公告)日：2012-12-27

申请号：US13340024

申请日：2011-12-29

申请人： Sundeep Vaddadi ,  Onur C. Hamsici ,  John H. Hong ,  Yuriy Reznik ,  Chong U. Lee

发明人： Sundeep Vaddadi ,  Onur C. Hamsici ,  John H. Hong ,  Yuriy Reznik ,  Chong U. Lee

IPC分类号： G06F17/30

CPC分类号： G06K9/6282 ,  G06K9/6228

摘要： Various arrangements for using a k-dimensional tree for a search are presented. A plurality of descriptors may be stored. Each of the plurality of descriptors stored is linked with a first number of stored dimensions. The search may be performed using the k-dimensional tree for one or more query descriptors that at least approximately match one or more of the plurality of descriptors linked with the first number of stored dimensions. The k-dimensional tree may be built using the plurality of descriptors wherein each of the plurality of descriptors is linked with a second number of dimensions when the k-dimensional tree is built. The second number of dimensions may be a greater number of dimensions than the first number of stored dimensions.

摘要翻译： 提出了使用k维树进行搜索的各种布置。 可以存储多个描述符。 所存储的多个描述符中的每一个与存储维度的第一数量相关联。 可以使用k维树进行搜索，所述查询描述符至少近似地匹配与第一数量的存储维度相链接的多个描述符中的一个或多个。 可以使用多个描述符构建k维树，其中当构建k维树时，多个描述符中的每个描述符与第二数量的维度相关联。 第二数量的尺寸可以是比第一数量的存储尺寸更大的尺寸数量。

公开(公告)号：US09530073B2

公开(公告)日：2016-12-27

申请号：US13090180

申请日：2011-04-19

申请人： Onur C. Hamsici ,  John H. Hong ,  Yuriy Reznik ,  Sundeep Vaddadi ,  Chong Uk. Lee

发明人： Onur C. Hamsici ,  John H. Hong ,  Yuriy Reznik ,  Sundeep Vaddadi ,  Chong Uk. Lee

IPC分类号： G06K9/00 ,  G06K9/46

CPC分类号： G06K9/4671

摘要： A local feature descriptor for a point in an image is generated over multiple levels of an image scale space. The image is gradually smoothened to obtain a plurality of scale spaces. A point may be identified as the point of interest within a first scale space from the plurality of scale spaces. A plurality of image derivatives is obtained for each of the plurality of scale spaces. A plurality of orientation maps is obtained (from the plurality of image derivatives) for each scale space in the plurality of scale spaces. Each of the plurality of orientation maps is then smoothened (e.g., convolved) to obtain a corresponding plurality of smoothed orientation maps. Therefore, a local feature descriptor for the point may be generated by sparsely sampling a plurality of smoothed orientation maps corresponding to two or more scale spaces from the plurality of scale spaces.

摘要翻译： 图像中的一个点的局部特征描述符是通过图像比例空间的多个级别生成的。 图像逐渐平滑以获得多个刻度空间。 点可以被识别为来自多个刻度空间的第一刻度空间内的兴趣点。 为多个刻度空间中的每一个获得多个图像导数。 对于多个刻度空间中的每个刻度空间，获得多个取向图（来自多个图像衍生）。 然后对多个取向图中的每一个进行平滑（例如，卷积）以获得相应的多个平滑取向图。 因此，可以通过从多个比例空间中稀疏采样对应于两个或更多比例空间的多个平滑取向图来生成该点的局部特征描述符。

公开(公告)号：US09036925B2

公开(公告)日：2015-05-19

申请号：US13312335

申请日：2011-12-06

申请人： Sundeep Vaddadi ,  Onur C. Hamsici ,  Yuriy Reznik ,  John H. Hong ,  Chong U. Lee

发明人： Sundeep Vaddadi ,  Onur C. Hamsici ,  Yuriy Reznik ,  John H. Hong ,  Chong U. Lee

IPC分类号： G06K9/62 ,  G06K9/54 ,  G06K9/60 ,  G06F17/30

CPC分类号： G06F17/30247 ,  G06K9/62 ,  G06K9/627

摘要： Techniques are disclosed for performing robust feature matching for visual search. An apparatus comprising an interface and a feature matching unit may implement these techniques. The interface receives a query feature descriptor. The feature matching unit then computes a distance between a query feature descriptor and reference feature descriptors and determines a first group of the computed distances and a second group of the computed distances in accordance with a clustering algorithm, where this second group of computed distances comprises two or more of the computed distances. The feature matching unit then determines whether the query feature descriptor matches one of the reference feature descriptors associated with a smallest one of the computed distances based on the determined first group and second group of the computed distances.

摘要翻译： 公开了用于执行用于视觉搜索的鲁棒特征匹配的技术。 包括接口和特征匹配单元的装置可以实现这些技术。 接口接收查询特征描述符。 特征匹配单元然后计算查询特征描述符和参考特征描述符之间的距离，并且根据聚类算法确定计算出的距离的第一组和所计算的距离的第二组，其中该第二组计算距离包括两个 或更多的计算距离。 特征匹配单元然后基于所确定的计算出的距离的第一组和第二组来确定查询特征描述符是否与与计算出的距离中的最小一个相关联的参考特征描述符之一匹配。

公开(公告)号：US20130293532A1

公开(公告)日：2013-11-07

申请号：US13619234

申请日：2012-09-14

申请人： Sundeep Vaddadi ,  Andrew Moore Ziegler ,  Onur C. Hamsici

发明人： Sundeep Vaddadi ,  Andrew Moore Ziegler ,  Onur C. Hamsici

IPC分类号： G06T15/00

CPC分类号： G06T15/005 ,  G06T7/11 ,  G06T2207/10028 ,  G06T2207/20101

摘要： Techniques for segmentation of three-dimensional (3D) point clouds are described herein. An example of a method for user-assisted segmentation of a 3D point cloud described herein includes obtaining a 3D point cloud of a scene containing a target object; receiving a seed input indicative of a location of the target object within the scene; and generating a segmented point cloud corresponding to the target object by pruning the 3D point cloud based on the seed input.

摘要翻译： 本文描述了三维（3D）点云的分割技术。 本文描述的用于用户辅助分割3D点云的方法的示例包括获得包含目标对象的场景的3D点云; 接收指示所述目标物体在所述场景内的位置的种子输入; 以及通过基于种子输入修剪3D点云来生成与目标对象相对应的分割点云。

公开(公告)号：US08571306B2

公开(公告)日：2013-10-29

申请号：US13229654

申请日：2011-09-09

申请人： Yuriy Reznik ,  Onur C Hamsici ,  Sundeep Vaddadi ,  John H Hong ,  Chong U Lee

发明人： Yuriy Reznik ,  Onur C Hamsici ,  Sundeep Vaddadi ,  John H Hong ,  Chong U Lee

IPC分类号： G06K9/00

CPC分类号： G06T9/00 ,  G06F17/18 ,  G06F17/30247 ,  G06K9/4671 ,  G06K2009/226 ,  G06T9/005

摘要： Methods and devices for coding of feature locations are disclosed. In one embodiment, a method of coding feature location information of an image includes generating a hexagonal grid, where the hexagonal grid includes a plurality of hexagonal cells, quantizing feature locations of an image using the hexagonal grid, generating a histogram to record occurrences of feature locations in each hexagonal cell, and encoding the histogram in accordance with the occurrences of feature locations in each hexagonal cell. The method of encoding the histogram includes applying context information of neighboring hexagonal cells to encode information of a subsequent hexagonal cell to be encoded in the histogram, where the context information includes context information from first order neighbors and context information from second order neighbors of the subsequent hexagonal cell to be encoded.

摘要翻译： 公开了用于编码特征位置的方法和装置。 在一个实施例中，一种编码图像的特征位置信息的方法包括生成六边形网格，其中六边形网格包括多个六边形单元格，使用六边形网格量化图像的特征位置，生成直方图以记录特征的出现 每个六边形单元格中的位置，并根据每个六边形单元格中特征位置的出现来对直方图进行编码。 对直方图进行编码的方法包括应用相邻六边形单元格的上下文信息来编码在直方图中要编码的随后的六边形单元格的信息，其中上下文信息包括来自一阶邻居的上下文信息和来自第二阶邻居的上下文信息 六角形单元格进行编码。

公开(公告)号：US20120027290A1

公开(公告)日：2012-02-02

申请号：US13193294

申请日：2011-07-28

申请人： Pawan Kumar Baheti ,  Sundeep Vaddadi ,  Ashwin Swaminathan ,  Yuriy Reznik ,  Onur C. Hamsici ,  Murali Ramaswamy Chari ,  John H. Hong ,  Chong Uk Lee

发明人： Pawan Kumar Baheti ,  Sundeep Vaddadi ,  Ashwin Swaminathan ,  Yuriy Reznik ,  Onur C. Hamsici ,  Murali Ramaswamy Chari ,  John H. Hong ,  Chong Uk Lee

IPC分类号： G06K9/62

CPC分类号： G06K9/6857 ,  G06K9/4671

摘要： In one example, an apparatus includes a processor configured to extract a first set of one or more keypoints from a first set of blurred images of a first octave of a received image, calculate a first set of one or more descriptors for the first set of keypoints, receive a confidence value for a result produced by querying a feature descriptor database with the first set of descriptors, wherein the result comprises information describing an identity of an object in the received image, and extract a second set of one or more keypoints from a second set of blurred images of a second octave of the received image when the confidence value does not exceed a confidence threshold. In this manner, the processor may perform incremental feature descriptor extraction, which may improve computational efficiency of object recognition in digital images.

摘要翻译： 在一个示例中，设备包括处理器，其被配置为从接收到的图像的第一个八度音阶的第一组模糊图像中提取一个或多个关键点的第一组，计算第一组的一个或多个描述符 关键点，通过用第一组描述符查询特征描述符数据库而产生的结果的置信度值，其中结果包括描述接收到的图像中的对象的身份的信息，并且从一个或多个关键点中提取一个或多个关键点的第二组 当置信度值不超过置信度阈值时，接收图像的第二倍频程的第二组模糊图像。 以这种方式，处理器可以执行增量特征描述符提取，这可以提高数字图像中对象识别的计算效率。