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. 发明申请

US20100246969A1 COMPUTATIONALLY EFFICIENT LOCAL IMAGE DESCRIPTORS 审中-公开
标题翻译：计算效率高的局部图像描述符
公开(公告)号：US20100246969A1
公开(公告)日：2010-09-30
申请号：US12410469
申请日：2009-03-25
申请人： Simon A. J. Winder , Gang Hua
发明人： Simon A. J. Winder , Gang Hua
IPC分类号： G06K9/46
CPC分类号： G06K9/4671
摘要： Described is a technology in which an image (or image patch) is processed into a highly discriminative and computationally efficient image descriptor that has a low storage footprint. Feature vectors are generated from an image (or image patch), and further processed via a polar Gaussian pooling approach (a DAISY configuration) into a descriptor. The descriptor is normalized, and processed with a dimension reduction component and a quantization component (based upon dynamic range reduction) into a finalized descriptor, which may be further compressed. The resulting descriptors have significantly reduced error rates and significantly smaller sizes than other image descriptors (such as SIFT-based descriptors).
摘要翻译：描述了一种技术，其中图像（或图像贴片）被处理成具有低存储空间的高度辨别性和计算效率的图像描述符。特征向量从图像（或图像块）生成，并且通过极高斯混合方法（DAISY配置）进一步处理成描述符。描述符被归一化，并且将尺寸减小分量和量化分量（基于动态范围缩小）处理成最终描述符，其可被进一步压缩。所得到的描述符与其他图像描述符（例如基于SIFT的描述符）相比，显着降低了错误率和显着更小的大小。

2. 发明授权

US08023742B2 Local image descriptors using linear discriminant embedding 有权
标题翻译：局部图像描述符使用线性判别嵌入
公开(公告)号：US08023742B2
公开(公告)日：2011-09-20
申请号：US11868988
申请日：2007-10-09
申请人： Matthew Alun Brown , Gang Hua , Simon A. J. Winder
发明人： Matthew Alun Brown , Gang Hua , Simon A. J. Winder
IPC分类号： G06K9/46 , G06K9/68
CPC分类号： G06K9/4609 , G06K9/6256
摘要： To render the comparison of image patches more efficient, the data of an image patch can be projected into a smaller-dimensioned subspace, resulting in a descriptor of the image patch. The projection into the descriptor subspace is known as a linear discriminant embedding, and can be performed with reference to a linear discriminant embedding matrix. The linear discriminant embedding matrix can be constructed from projection vectors that maximize those elements that are shared by matching image patches or that are used to distinguish non-matching image patches, while also minimizing those elements that are common to non-matching image patches or that distinguish matching image patches. The determination of such projection vectors can be limited such that only orthogonal vectors comprise the linear discriminant embedding matrix. The determination of the linear discriminant embedding matrix can likewise be constrained to avoid overfitting to training data.
摘要翻译：为了使图像补丁的比较更加有效，图像补丁的数据可以投影到较小尺寸的子空间中，从而导致图像补丁的描述符。将描述符子空间的投影称为线性判别嵌入，并且可以参照线性判别嵌入矩阵来执行。线性判别嵌入矩阵可以由投影向量构成，该矢量最大化匹配图像片段共享的元素，或者用于区分不匹配的图像片段，同时最小化非匹配图像片段常见的那些元素，或者区分匹配的图像补丁。可以限制这种投影向量的确定，使得仅正交向量包括线性判别嵌入矩阵。线性判别嵌入矩阵的确定同样可以被限制，以避免训练数据过度拟合。

3. 发明申请

US20090091802A1 Local Image Descriptors Using Linear Discriminant Embedding 有权
标题翻译：本地图像描述符使用线性判别嵌入
公开(公告)号：US20090091802A1
公开(公告)日：2009-04-09
申请号：US11868988
申请日：2007-10-09
申请人： Matthew Alun Brown , Gang Hua , Simon A. J. Winder
发明人： Matthew Alun Brown , Gang Hua , Simon A. J. Winder
IPC分类号： H04N1/40
CPC分类号： G06K9/4609 , G06K9/6256
摘要： To render the comparison of image patches more efficient, the data of an image patch can be projected into a smaller-dimensioned subspace, resulting in a descriptor of the image patch. The projection into the descriptor subspace is known as a linear discriminant embedding, and can be performed with reference to a linear discriminant embedding matrix. The linear discriminant embedding matrix can be constructed from projection vectors that maximize those elements that are shared by matching image patches or that are used to distinguish non-matching image patches, while also minimizing those elements that are common to non-matching image patches or that distinguish matching image patches. The determination of such projection vectors can be limited such that only orthogonal vectors comprise the linear discriminant embedding matrix. The determination of the linear discriminant embedding matrix can likewise be constrained to avoid overfitting to training data.
摘要翻译：为了使图像补丁的比较更有效率，图像补丁的数据可以投影到更小尺寸的子空间中，导致图像补丁的描述符。将描述符子空间的投影称为线性判别嵌入，并且可以参照线性判别嵌入矩阵来执行。线性判别嵌入矩阵可以由投影向量构成，该投影矢量使由匹配的图像补丁共享的元素最大化，或者用于区分非匹配图像补丁的同时也最小化非匹配图像补丁常见的那些元素，或者区分匹配的图像补丁。可以限制这种投影向量的确定，使得仅正交向量包括线性判别嵌入矩阵。线性判别嵌入矩阵的确定同样可以被限制，以避免训练数据过度拟合。

4. 发明授权

US09043186B2 Surface normal computation on noisy sample of points 有权
标题翻译：表面正常计算噪声样本点
公开(公告)号：US09043186B2
公开(公告)日：2015-05-26
申请号：US13314213
申请日：2011-12-08
申请人： Michael Kallay , Simon A. J. Winder
发明人： Michael Kallay , Simon A. J. Winder
IPC分类号： G06F7/60 , G06T7/00
CPC分类号： G06T7/0051 , G06T7/50 , G06T2200/04 , G06T2207/10028
摘要： Various technologies described herein pertain to computing surface normals for points in a point cloud. The point cloud is representative of a measured surface of a physical object. A point in the point cloud can be set as a point of origin, and points in the point cloud can be modeled as electrostatic point charges. Moreover, a point of least electrostatic potential on a sphere centered at the point of origin can be computed as a function of the electrostatic point charges. Further, unit vector with a direction from the point of origin to the point of least electrostatic potential on the sphere can be assigned as a normal for the point of origin.
摘要翻译：本文描述的各种技术适用于计算点云中的点的表面法线。点云表示物理对象的测量表面。点云中的点可以设置为原点，点云中的点可以建模为静电点电荷。此外，可以以静电点电荷的函数计算以起点原点为中心的球体上的最小静电电位点。此外，具有从起点到球体上最小静电电位的方向的单位向量可以被分配为原点的法线。

5. 发明申请

US20130321393A1 SMOOTHING AND ROBUST NORMAL ESTIMATION FOR 3D POINT CLOUDS 有权
标题翻译：用于3D点云的平滑和稳定的正态估计
公开(公告)号：US20130321393A1
公开(公告)日：2013-12-05
申请号：US13566796
申请日：2012-08-03
申请人： Simon A. J. Winder
发明人： Simon A. J. Winder
IPC分类号： G06T17/00
CPC分类号： G06T15/04 , G06T15/08 , G06T15/205 , G06T17/00 , G06T2210/56 , H04N7/142 , H04N7/15 , H04N13/0014 , H04N13/0239 , H04N13/0257 , H04N13/117 , H04N13/239 , H04N13/257 , H04R2227/005
摘要： A “Point Cloud Smoother” provides various techniques for refining a 3D point cloud or other 3D input model to generate a smoothed and denoised 3D output model. Smoothing and denoising is achieved, in part, by robustly fitting planes to a neighborhood of points around each point of the input model and using those planes to estimate new points and corresponding normals of the 3D output model. These techniques are useful for a number of purposes, including, but not limited to, free viewpoint video (FVV), which, when combined with the smoothing techniques enabled by the Point Cloud Smoother, allows 3D data of videos or images to be denoised and then rendered and viewed from any desired viewpoint that is supported by the input data.
摘要翻译： “点云平滑器”提供了用于精细化3D点云或其他3D输入模型以生成平滑和去噪3D输出模型的各种技术。平滑和去噪部分地通过将平面稳固地拟合到输入模型的每个点附近的点附近，并且使用这些平面来估计3D输出模型的新点和相应的法线。这些技术对于许多目的是有用的，包括但不限于自由视点视频（FVV），当与点云平滑器启用的平滑技术相结合时，视频或图像的3D数据被去噪声，然后从由输入数据支持的任何期望的视点呈现和观看。

6. 发明申请

US20130151210A1 SURFACE NORMAL COMPUTATION ON NOISY SAMPLE OF POINTS 有权
标题翻译：点的噪声样本表面正常计算
公开(公告)号：US20130151210A1
公开(公告)日：2013-06-13
申请号：US13314213
申请日：2011-12-08
申请人： Michael Kallay , Simon A. J. Winder
发明人： Michael Kallay , Simon A. J. Winder
IPC分类号： G06F7/60
CPC分类号： G06T7/0051 , G06T7/50 , G06T2200/04 , G06T2207/10028
摘要： Various technologies described herein pertain to computing surface normals for points in a point cloud. The point cloud is representative of a measured surface of a physical object. A point in the point cloud can be set as a point of origin, and points in the point cloud can be modeled as electrostatic point charges. Moreover, a point of least electrostatic potential on a sphere centered at the point of origin can be computed as a function of the electrostatic point charges. Further, unit vector with a direction from the point of origin to the point of least electrostatic potential on the sphere can be assigned as a normal for the point of origin.
摘要翻译：本文描述的各种技术适用于计算点云中的点的表面法线。点云表示物理对象的测量表面。点云中的点可以设置为原点，点云中的点可以建模为静电点电荷。此外，可以以静电点电荷的函数计算以起点原点为中心的球体上的最小静电电位点。此外，具有从起点到球体上最小静电电位的方向的单位向量可以被分配为原点的法线。

7. 发明申请

US20090154795A1 INTERACTIVE CONCEPT LEARNING IN IMAGE SEARCH 有权
标题翻译：图像搜索中的交互式概念学习
公开(公告)号：US20090154795A1
公开(公告)日：2009-06-18
申请号：US11954246
申请日：2007-12-12
申请人： Desney S. Tan , Ashish Kapoor , Simon A. J. Winder , James A. Fogarty
发明人： Desney S. Tan , Ashish Kapoor , Simon A. J. Winder , James A. Fogarty
IPC分类号： G06K9/62
CPC分类号： G06F17/30247 , G06K9/6215
摘要： An interactive concept learning image search technique that allows end-users to quickly create their own rules for re-ranking images based on the image characteristics of the images. The image characteristics can include visual characteristics as well as semantic features or characteristics, or may include a combination of both. End-users can then rank or re-rank any current or future image search results according to their rule or rules. End-users provide examples of images each rule should match and examples of images the rule should reject. The technique learns the common image characteristics of the examples, and any current or future image search results can then be ranked or re-ranked according to the learned rules.
摘要翻译：一种交互式概念学习图像搜索技术，允许最终用户基于图像的图像特征快速创建自己的重新排序图像的规则。图像特征可以包括视觉特征以及语义特征或特征，或者可以包括两者的组合。然后，最终用户可以根据其规则或规则对当前或将来的图像搜索结果进行排名或重新排序。最终用户提供每个规则应该匹配的图像的示例以及规则应该拒绝的图像的示例。该技术学习示例的常见图像特征，然后可以根据学习的规则对任何当前或将来的图像搜索结果进行排名或重新排序。

8. 发明授权

US09767598B2 Smoothing and robust normal estimation for 3D point clouds 有权
公开(公告)号：US09767598B2
公开(公告)日：2017-09-19
申请号：US13566796
申请日：2012-08-03
申请人： Simon A. J. Winder
发明人： Simon A. J. Winder
IPC分类号： G09G5/00 , G06T19/00 , G06T15/04 , G06T17/00 , H04N7/14 , H04N13/02 , G06T15/08 , G06T15/20 , H04N7/15 , H04N13/00
CPC分类号： G06T15/04 , G06T15/08 , G06T15/205 , G06T17/00 , G06T2210/56 , H04N7/142 , H04N7/15 , H04N13/0014 , H04N13/0239 , H04N13/0257 , H04N13/117 , H04N13/239 , H04N13/257 , H04R2227/005
摘要： A “Point Cloud Smoother” provides various techniques for refining a 3D point cloud or other 3D input model to generate a smoothed and denoised 3D output model. Smoothing and denoising is achieved, in part, by robustly fitting planes to a neighborhood of points around each point of the input model and using those planes to estimate new points and corresponding normals of the 3D output model. These techniques are useful for a number of purposes, including, but not limited to, free viewpoint video (FVV), which, when combined with the smoothing techniques enabled by the Point Cloud Smoother, allows 3D data of videos or images to be denoised and then rendered and viewed from any desired viewpoint that is supported by the input data.

9. 发明授权

US09008446B2 Interactive concept learning in image search 有权
标题翻译：图像搜索中的互动概念学习
公开(公告)号：US09008446B2
公开(公告)日：2015-04-14
申请号：US13429342
申请日：2012-03-24
申请人： Desney S. Tan , Ashish Kapoor , Simon A. J. Winder , James A. Fogarty
发明人： Desney S. Tan , Ashish Kapoor , Simon A. J. Winder , James A. Fogarty
IPC分类号： G06K9/62 , G06F17/30
CPC分类号： G06F17/30247 , G06K9/6215
摘要： An interactive concept learning image search technique that allows end-users to quickly create their own rules for re-ranking images based on the image characteristics of the images. The image characteristics can include visual characteristics as well as semantic features or characteristics, or may include a combination of both. End-users can then rank or re-rank any current or future image search results according to their rule or rules. End-users provide examples of images each rule should match and examples of images the rule should reject. The technique learns the common image characteristics of the examples, and any current or future image search results can then be ranked or re-ranked according to the learned rules.
摘要翻译：一种交互式概念学习图像搜索技术，允许最终用户基于图像的图像特征快速创建自己的重新排序图像的规则。图像特征可以包括视觉特征以及语义特征或特征，或者可以包括两者的组合。然后，最终用户可以根据其规则或规则对当前或将来的图像搜索结果进行排名或重新排序。最终用户提供每个规则应该匹配的图像的示例以及规则应该拒绝的图像的示例。该技术学习示例的常见图像特征，然后可以根据学习的规则对任何当前或将来的图像搜索结果进行排名或重新排序。

10. 发明申请

US20120183206A1 INTERACTIVE CONCEPT LEARNING IN IMAGE SEARCH 有权
标题翻译：图像搜索中的交互式概念学习
公开(公告)号：US20120183206A1
公开(公告)日：2012-07-19
申请号：US13429342
申请日：2012-03-24
申请人： Desney S. Tan , Ashish Kapoor , Simon A. J. Winder , James A. Fogarty
发明人： Desney S. Tan , Ashish Kapoor , Simon A. J. Winder , James A. Fogarty
IPC分类号： G06K9/62
CPC分类号： G06F17/30247 , G06K9/6215
摘要： An interactive concept learning image search technique that allows end-users to quickly create their own rules for re-ranking images based on the image characteristics of the images. The image characteristics can include visual characteristics as well as semantic features or characteristics, or may include a combination of both. End-users can then rank or re-rank any current or future image search results according to their rule or rules. End-users provide examples of images each rule should match and examples of images the rule should reject. The technique learns the common image characteristics of the examples, and any current or future image search results can then be ranked or re-ranked according to the learned rules.
摘要翻译：一种交互式概念学习图像搜索技术，允许最终用户基于图像的图像特征快速创建自己的重新排序图像的规则。图像特征可以包括视觉特征以及语义特征或特征，或者可以包括两者的组合。然后，最终用户可以根据其规则或规则对当前或将来的图像搜索结果进行排名或重新排序。最终用户提供每个规则应该匹配的图像的示例以及规则应该拒绝的图像的示例。该技术学习示例的常见图像特征，然后可以根据学习的规则对任何当前或将来的图像搜索结果进行排名或重新排序。

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