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

US09008356B1 Perceptually-driven representation for object recognition 有权
标题翻译：感知驱动的对象识别表示
公开(公告)号：US09008356B1
公开(公告)日：2015-04-14
申请号：US13301623
申请日：2011-11-21
申请人： Alexander T. Toshev , Jay Yagnik , Vivek Kwatra
发明人： Alexander T. Toshev , Jay Yagnik , Vivek Kwatra
IPC分类号： G06K9/00 , G06K9/48 , G06T7/20
CPC分类号： G06T7/20 , G06K9/468 , G06K9/6211 , G06K9/6878
摘要： Methods and systems for processing an image to facilitate automated object recognition are disclosed. More particularly, an image is processed based on a perceptual grouping for the image (e.g., derived via segmentation, derived via contour detection, etc.) and a geometric-configuration model for the image (e.g., a bounding box model, a constellation, a k-fan, etc.).
摘要翻译：公开了用于处理图像以促进自动对象识别的方法和系统。更具体地，基于用于图像的感知分组（例如，通过经由轮廓检测等得到的分割导出）和图像的几何配置模型（例如，边界框模型，星座图， k风扇等）。

2. 发明授权

US09483701B1 System and method for using segmentation to identify object location in images 有权
标题翻译：使用分割来识别图像中的对象位置的系统和方法
公开(公告)号：US09483701B1
公开(公告)日：2016-11-01
申请号：US13299281
申请日：2011-11-17
申请人： Vivek Kwatra , Jay Yagnik , Alexander T. Toshev
发明人： Vivek Kwatra , Jay Yagnik , Alexander T. Toshev
IPC分类号： G06K9/62 , G06K9/00 , G06K9/32
CPC分类号： G06K9/3241 , G06K9/00771 , G06K9/468 , G06K9/6255 , G06T7/0081 , G06T7/0097 , G06T2207/20081
摘要： A computing device segments an image into a plurality of segments, wherein each segment of the plurality of segments has a segment location and a set of pixels that share visual characteristics. The computing device determines an initial set of bounding boxes for the image based on the plurality of segments. The computing device determines a reduced set of bounding boxes based on combining bounding boxes of the initial set of bounding boxes, the reduced set of bounding boxes corresponding to one or more objects in the image, each of the one or more objects having an object class and an object location.
摘要翻译：计算设备将图像分割成多个段，其中多个段中的每个段具有共享视觉特征的段位置和一组像素。计算设备基于多个段确定图像的初始边界框集合。计算设备基于组合边界框的边界框来确定缩小的边界框集合，所述边界框对应于所述图像中的一个或多个对象，所述一个或多个对象中的每一个具有对象类和对象位置。

3. 发明授权

US08768048B1 System and method for exploiting segment co-occurrence relationships to identify object location in images 有权
标题翻译：利用片段同现关系识别图像中对象位置的系统和方法
公开(公告)号：US08768048B1
公开(公告)日：2014-07-01
申请号：US13299789
申请日：2011-11-18
申请人： Vivek Kwatra , Jay Yagnik , Alexander T. Toshev , Poonam Suryanarayan
发明人： Vivek Kwatra , Jay Yagnik , Alexander T. Toshev , Poonam Suryanarayan
IPC分类号： G06K9/62
CPC分类号： G06K9/6202 , G06K9/72
摘要： A computing device segments an image into a plurality of segments, wherein each segment of the plurality of segments comprises a set of pixels that share visual characteristics. The computing device then determines expected contexts for the segments, wherein an expected context for a segment comprises at least one of additional segments or features expected to occur in the image together with the segment. The computing device then identifies a probable object based on the expected contexts.
摘要翻译：计算设备将图像分割成多个段，其中多个段中的每个段包括共享视觉特征的一组像素。计算设备然后确定段的预期上下文，其中段的预期上下文包括期望与该段一起出现在图像中的附加段或特征中的至少一个。然后，计算设备基于预期上下文识别可能的对象。

4. 发明授权

US08467607B1 Segmentation-based feature pooling for object models 有权
标题翻译：对象模型的基于分段的特征池
公开(公告)号：US08467607B1
公开(公告)日：2013-06-18
申请号：US13301621
申请日：2011-11-21
申请人： Alexander T. Toshev , Jay Yagnik , Vivek Kwatra
发明人： Alexander T. Toshev , Jay Yagnik , Vivek Kwatra
IPC分类号： G06T7/0081
CPC分类号： G06K9/4642
摘要： Methods and systems for processing an image to create an object model are disclosed. In accordance with one embodiment, each segment of the image is assigned to a respective bin of a bounding box. For each bin of the bounding box, the value of a feature for the bin is computed based on the values of that feature for each of the segments assigned to the bin. An object model is then created based on the values of the feature for the bin.
摘要翻译：公开了用于处理图像以创建对象模型的方法和系统。根据一个实施例，图像的每个段被分配给边界框的相应仓。对于边界框的每个仓，根据分配给仓的每个段的该特征的值来计算仓的特征值。然后基于bin的特征值创建对象模型。

5. 发明授权

US08385662B1 Principal component analysis based seed generation for clustering analysis 有权
标题翻译：基于主成分分析的种子生成用于聚类分析
公开(公告)号：US08385662B1
公开(公告)日：2013-02-26
申请号：US12432989
申请日：2009-04-30
申请人： Sangho Yoon , Jay Yagnik , Mei Han , Vivek Kwatra
发明人： Sangho Yoon , Jay Yagnik , Mei Han , Vivek Kwatra
IPC分类号： G06K9/62
CPC分类号： G06K9/6247 , G06K9/6223
摘要： Clustering algorithms such as k-means clustering algorithm are used in applications that process entities with spatial and/or temporal characteristics, for example, media objects representing audio, video, or graphical data. Feature vectors representing characteristics of the entities are partitioned using clustering methods that produce results sensitive to an initial set of cluster seeds. The set of initial cluster seeds is generated using principal component analysis of either the complete feature vector set or a subset thereof. The feature vector set is divided into a desired number of initial clusters and a seed determined from each initial cluster.
摘要翻译：诸如k均值聚类算法的聚类算法被用于处理具有空间和/或时间特征的实体的应用中，例如表示音频，视频或图形数据的媒体对象。使用产生对初始集群种子集合敏感的结果的聚类方法对代表实体特征的特征向量进行分区。使用完整特征向量集或其子集的主成分分析来生成初始簇种子集合。特征向量集合被分为期望数量的初始簇和从每个初始簇确定的种子。

6. 发明授权

US08396325B1 Image enhancement through discrete patch optimization 有权
标题翻译：通过离散补丁优化的图像增强
公开(公告)号：US08396325B1
公开(公告)日：2013-03-12
申请号：US12430812
申请日：2009-04-27
申请人： Vivek Kwatra , Mei Han , Jay Yagnik
发明人： Vivek Kwatra , Mei Han , Jay Yagnik
IPC分类号： G06K9/36
CPC分类号： G06T7/33
摘要： An image processing system enhances the resolution of an original image using higher-resolution image data from other images. The image processing system defines a plurality of overlapping partitions for the original image, each partition defining a set of non-overlapping site patches. During an optimization phase, the system identifies, for site patches of the original images, label patches within related images that are of most relevance. During a rendering phase independent of the optimization phase, an output image with enhanced resolution is synthesized by substituting, for site patches of the original image, the identified relevant label patches from the related images.
摘要翻译：图像处理系统使用来自其他图像的更高分辨率图像数据增强原始图像的分辨率。图像处理系统为原始图像定义多个重叠的分区，每个分区定义一组不重叠的站点块。在优化阶段期间，系统会针对最相关的相关图像中的原始图像的贴片进行标签贴图。在独立于优化阶段的渲染阶段期间，通过从相关图像中替换原始图像的位置贴片来识别识别的相关标签贴图来合成具有增强分辨率的输出图像。

7. 发明授权

US08938119B1 Facade illumination removal 有权
标题翻译：门面照明去除
公开(公告)号：US08938119B1
公开(公告)日：2015-01-20
申请号：US13461482
申请日：2012-05-01
申请人： Mei Han , Vivek Kwatra , Shengyang Dai , Sergey Ioffe
发明人： Mei Han , Vivek Kwatra , Shengyang Dai , Sergey Ioffe
IPC分类号： G06K9/00
CPC分类号： G06K9/4661 , G06T5/008
摘要： An image comprising color pixels with varying illumination is selected. Instances of a repeating pattern in the image are determined. Illumination values for illuminated pixels at locations within instances of the repeating pattern are calculated based on pixel intensities of non-illuminated pixels at corresponding locations in other instances of the repeating pattern. The illumination variation is removed from the illuminated pixels based on the calculated illumination values to produce enhanced pixels. Color from the non-illuminated pixels at the corresponding locations in other instances of the repeating pattern is propagated to the enhanced pixels.
摘要翻译：选择包括具有变化的照明的彩色像素的图像。确定图像中的重复图案的实例。基于重复图案的其他实例中的相应位置处的非照明像素的像素强度来计算在重复图案的实例内的位置处的照明像素的照明值。基于所计算的照明值，从照明像素去除照明变化以产生增强像素。来自重复图案的其他实例中的相应位置处的非照明像素的颜色被传播到增强像素。

8. 发明授权

US08860825B2 Methods and systems for removal of rolling shutter effects 有权
标题翻译：去除滚动快门效果的方法和系统
公开(公告)号：US08860825B2
公开(公告)日：2014-10-14
申请号：US13611023
申请日：2012-09-12
申请人： Matthias Grundmann , Vivek Kwatra , Irfan Essa
发明人： Matthias Grundmann , Vivek Kwatra , Irfan Essa
IPC分类号： H04N5/228 , H04N5/335
CPC分类号： H04N5/23264 , G06T5/003 , G06T7/246 , G06T2207/20201
摘要： Methods and systems for rolling shutter removal are described. A computing device may be configured to determine, in a frame of a video, distinguishable features. The frame may include sets of pixels captured asynchronously. The computing device may be configured to determine for a pixel representing a feature in the frame, a corresponding pixel representing the feature in a consecutive frame; and determine, for a set of pixels including the pixel in the frame, a projective transform that may represent motion of the camera. The computing device may be configured to determine, for the set of pixels in the frame, a mixture transform based on a combination of the projective transform and respective projective transforms determined for other sets of pixels. Accordingly, the computing device may be configured to estimate a motion path of the camera to account for distortion associated with the asynchronous capturing of the sets of pixels.
摘要翻译：描述滚动快门拆卸的方法和系统。计算设备可以被配置为在视频的帧中确定可区分的特征。帧可以包括异步捕获的像素集合。计算设备可以被配置为针对表示帧中的特征的像素来确定代表连续帧中的特征的对应像素; 并且对于包括帧中的像素的一组像素，确定可以表示相机的运动的投影变换。计算设备可以被配置为针对帧中的像素集合，基于针对其他像素集合确定的投影变换和相应的投影变换的组合来确定混合变换。因此，计算设备可以被配置为估计相机的运动路径以考虑与该组像素的异步捕获相关联的失真。

9. 发明申请

US20140205206A1 SYSTEMS AND METHODS FOR RESIZING AN IMAGE 有权
标题翻译：用于校正图像的系统和方法
公开(公告)号：US20140205206A1
公开(公告)日：2014-07-24
申请号：US13749564
申请日：2013-01-24
申请人： MAYUR DATAR , Huei-Hung Christopher Liao , Vivek Kwatra , Allen Huang
发明人： MAYUR DATAR , Huei-Hung Christopher Liao , Vivek Kwatra , Allen Huang
IPC分类号： G06T3/40
CPC分类号： G06K9/18 , G06T3/0012
摘要： In some instances, an image may have dimensions that do not correspond to a slot to display the image. For example, an image content item may have dimensions that do not correspond to a content item slot. The image may be resized using seam carving to add or remove pixels of the image. A saliency map for the image may be used having saliency scores for each pixel of the image. Evaluation metrics may be used before, during, and after, seam carving to determine whether salient content is affected by the seam carving. In some instances, a seam cost threshold value may be used for adaptive step size during the seam carving. The resized image may then be outputted, such as for an image content item to be served with a resource.
摘要翻译：在某些情况下，图像可能具有不对应于显示图像的时隙的尺寸。例如，图像内容项目可以具有与内容项目时隙不对应的维度。可以使用接缝雕刻来调整图像的大小，以添加或删除图像的像素。可以使用图像的显着图，其具有图像的每个像素的显着性分数。评估指标可以在缝合雕刻之前，之中和之后使用，以确定显着含量是否受到缝合雕刻的影响。在一些情况下，在缝合雕刻期间可以使用接缝成本阈值用于自适应步长。然后可以输出调整大小的图像，例如用于要与资源一起服务的图像内容项目。

10. 发明授权

US08737723B1 Fast randomized multi-scale energy minimization for inferring depth from stereo image pairs 有权
标题翻译：快速随机多尺度能量最小化，用于从立体图像对中推断深度
公开(公告)号：US08737723B1
公开(公告)日：2014-05-27
申请号：US13309125
申请日：2011-12-01
申请人： Vivek Kwatra
发明人： Vivek Kwatra
IPC分类号： G06K9/00 , G06T7/00 , G06T15/20
CPC分类号： G06T7/0075 , G06T3/4053 , G06T5/005 , G06T15/205 , G06T2207/20016
摘要： An image processing module infers depth from a stereo image pair according to a multi-scale energy minimization process. A stereo image pair is progressively downsampled to generate a pyramid of downsampled image pairs of varying resolution. Starting with the coarsest downsampled image pair, a disparity map is generated that reflects displacement between corresponding pixels in the stereo image pair. The disparity map is then progressively upsampled. At each upsampling stage, the disparity labels are refined according to an energy function. The disparity labels provide depth information related to surfaces depicted in the stereo image pair.
摘要翻译：图像处理模块根据多尺度能量最小化过程从立体图像对推断深度。立体图像对逐渐下采样以产生具有不同分辨率的下采样图像对的金字塔。从最粗糙的下采样图像对开始，产生反映立体图像对中的相应像素之间的位移的视差图。然后逐渐上升采样视差图。在每个上采样阶段，视差标签根据能量函数进行细化。视差标签提供与立体图像对中描绘的表面有关的深度信息。

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