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

US08903198B2 Image ranking based on attribute correlation 有权
标题翻译：基于属性相关的图像排名
公开(公告)号：US08903198B2
公开(公告)日：2014-12-02
申请号：US13152615
申请日：2011-06-03
申请人： Ankur Datta , Rogerio S. Feris , Sharathchandra U. Pankanti , Behjat Siddiquie
发明人： Ankur Datta , Rogerio S. Feris , Sharathchandra U. Pankanti , Behjat Siddiquie
IPC分类号： G06K9/60 , G06F17/30 , G06K9/62
CPC分类号： G06F17/30256 , G06F17/30277 , G06F17/3028 , G06F17/3053 , G06K9/00268 , G06K9/481 , G06K9/6263 , G06K9/66 , G06N99/005
摘要： Images are retrieved and ranked according to relevance to attributes of a multi-attribute query through training image attribute detectors for different attributes annotated in a training dataset. Pair-wise correlations are learned between pairs of the annotated attributes from the training dataset of images. Image datasets may then be searched via the trained attribute detectors for images comprising attributes in a multi-attribute query, wherein images are retrieved from the searching that each comprise one or more of the query attributes and also in response to information from the trained attribute detectors corresponding to attributes that are not a part of the query but are relevant to the query attributes as a function of the learned plurality of pair-wise correlations. The retrieved images are ranked as a function of respective total numbers of attributes within the query subset attributes.
摘要翻译：根据与训练数据集中注释的不同属性的训练图像属性检测器，根据与多属性查询的属性的相关性来检索和排列图像。在图像训练数据集的注释属性对之间学习成对相关。然后可以经由经训练的属性检测器搜索包括多属性查询中的属性的图像的图像数据集，其中从搜索中检索每个包括一个或多个查询属性的图像，并且还响应于来自经训练的属性检测器的信息对应于不是查询的一部分但与所学习的多个成对相关性的函数的查询属性相关的属性。检索到的图像根据查询子集属性内的各个属性总数的顺序排列。

2. 发明授权

US08620026B2 Video-based detection of multiple object types under varying poses 有权
标题翻译：在不同姿势下的多种对象类型的基于视频的检测
公开(公告)号：US08620026B2
公开(公告)日：2013-12-31
申请号：US13085547
申请日：2011-04-13
申请人： Ankur Datta , Rogerio S. Feris , Sharathchandra U. Pankanti , Behjat Siddiquie , Yun Zhai
发明人： Ankur Datta , Rogerio S. Feris , Sharathchandra U. Pankanti , Behjat Siddiquie , Yun Zhai
IPC分类号： G06K9/00
CPC分类号： G06K9/4604 , G06K9/00751
摘要： Training data object images are clustered as a function of motion direction attributes and resized from respective original into same aspect ratios. Motionlet detectors are learned for each of the sets from features extracted from the resized object blobs. A deformable sliding window is applied to detect an object blob in input by varying window size, shape or aspect ratio to conform to a shape of the detected input video object blob. A motion direction of an underlying image patch of the detected input video object blob is extracted and motionlet detectors selected and applied that have similar motion directions. An object is thus detected within the detected blob and semantic attributes of an underlying image patch extracted if a motionlet detectors fires, the extracted semantic attributes available for use for searching for the detected object.
摘要翻译：训练数据对象图像作为运动方向属性的函数进行聚类，并从相应的原始尺寸变为相同的宽高比。通过从调整大小的对象斑点中提取的特征，为每个集合学习运动检测器。应用可变形滑动窗口通过改变窗口尺寸，形状或宽高比来检测输入中的对象斑点，以符合检测到的输入视频对象斑点的形状。提取检测到的输入视频对象斑点的底层图像块的运动方向，并选择并应用具有相似运动方向的运动检测器。因此，如果移动检测器触发，则所提取的底层图像块的检测到的blob和语义属性中的对象被检测到，所提取的语义属性可用于搜索检测到的对象。

3. 发明申请

US20120308121A1 IMAGE RANKING BASED ON ATTRIBUTE CORRELATION 有权
标题翻译：基于属性关联的图像排序
公开(公告)号：US20120308121A1
公开(公告)日：2012-12-06
申请号：US13152615
申请日：2011-06-03
申请人： Ankur Datta , Rogerio S. Feris , Sharathchandra U. Pankanti , Behjat Siddiquie
发明人： Ankur Datta , Rogerio S. Feris , Sharathchandra U. Pankanti , Behjat Siddiquie
IPC分类号： G06K9/62
CPC分类号： G06F17/30256 , G06F17/30277 , G06F17/3028 , G06F17/3053 , G06K9/00268 , G06K9/481 , G06K9/6263 , G06K9/66 , G06N99/005
摘要： Images are retrieved and ranked according to relevance to attributes of a multi-attribute query through training image attribute detectors for different attributes annotated in a training dataset. Pair-wise correlations are learned between pairs of the annotated attributes from the training dataset of images. Image datasets may then be searched via the trained attribute detectors for images comprising attributes in a multi-attribute query, wherein images are retrieved from the searching that each comprise one or more of the query attributes and also in response to information from the trained attribute detectors corresponding to attributes that are not a part of the query but are relevant to the query attributes as a function of the learned plurality of pair-wise correlations. The retrieved images are ranked as a function of respective total numbers of attributes within the query subset attributes.
摘要翻译：根据与训练数据集中注释的不同属性的训练图像属性检测器，根据与多属性查询的属性的相关性来检索和排列图像。在图像训练数据集的注释属性对之间学习成对相关。然后可以经由经训练的属性检测器搜索包括多属性查询中的属性的图像的图像数据集，其中从搜索中检索每个包括一个或多个查询属性的图像，并且还响应于来自经训练的属性检测器的信息对应于不是查询的一部分但与所学习的多个成对相关性的函数的查询属性相关的属性。检索到的图像根据查询子集属性内的各个属性总数的顺序排列。

4. 发明申请

US20120263346A1 VIDEO-BASED DETECTION OF MULTIPLE OBJECT TYPES UNDER VARYING POSES 有权
标题翻译：基于视频检测的多个对象类型在不同的位置
公开(公告)号：US20120263346A1
公开(公告)日：2012-10-18
申请号：US13085547
申请日：2011-04-13
申请人： Ankur Datta , Rogerio S. Feris , Sharathchandra U. Pankanti , Behjat Siddiquie , Yun Zhai
发明人： Ankur Datta , Rogerio S. Feris , Sharathchandra U. Pankanti , Behjat Siddiquie , Yun Zhai
IPC分类号： G06K9/00
CPC分类号： G06K9/4604 , G06K9/00751
摘要： Training data object images are clustered as a function of motion direction attributes and resized from respective original into same aspect ratios. Motionlet detectors are learned for each of the sets from features extracted from the resized object blobs. A deformable sliding window is applied to detect an object blob in input by varying window size, shape or aspect ratio to conform to a shape of the detected input video object blob. A motion direction of an underlying image patch of the detected input video object blob is extracted and motionlet detectors selected and applied that have similar motion directions. An object is thus detected within the detected blob and semantic attributes of an underlying image patch extracted if a motionlet detectors fires, the extracted semantic attributes available for use for searching for the detected object.
摘要翻译：训练数据对象图像作为运动方向属性的函数进行聚类，并从相应的原始尺寸变为相同的宽高比。通过从调整大小的对象斑点中提取的特征，为每个集合学习运动检测器。应用可变形滑动窗口通过改变窗口尺寸，形状或宽高比来检测输入中的对象斑点，以符合检测到的输入视频对象斑点的形状。提取检测到的输入视频对象斑点的底层图像块的运动方向，并选择并应用具有相似运动方向的运动检测器。因此，如果移动检测器触发，则所提取的底层图像块的检测到的blob和语义属性中的对象被检测到，所提取的语义属性可用于搜索检测到的对象。

5. 发明授权

US08811663B2 Object detection in crowded scenes 有权
标题翻译：拥挤场景中的物体检测
公开(公告)号：US08811663B2
公开(公告)日：2014-08-19
申请号：US13150952
申请日：2011-06-01
申请人： Lisa M. Brown , Rogerio S. Feris , Sharathchandra U. Pankanti , James Petterson , Behjat Siddiquie
发明人： Lisa M. Brown , Rogerio S. Feris , Sharathchandra U. Pankanti , James Petterson , Behjat Siddiquie
IPC分类号： G06K9/00 , G06K9/62
CPC分类号： G06K9/6256 , G06K9/00778 , G06K9/00785 , G06K9/6264
摘要： Methods and systems are provided for object detection. A method includes automatically collecting a set of training data images from a plurality of images. The method further includes generating occluded images. The method also includes storing in a memory the generated occluded images as part of the set of training data images, and training an object detector using the set of training data images stored in the memory. The method additionally includes detecting an object using the object detector, the object detector detecting the object based on the set of training data images stored in the memory.
摘要翻译：为对象检测提供了方法和系统。一种方法包括从多个图像自动收集一组训练数据图像。该方法还包括产生遮挡图像。该方法还包括将生成的遮挡图像作为训练数据图像集合的一部分存储在存储器中，并且使用存储在存储器中的训练数据图像集训练对象检测器。该方法还包括使用对象检测器检测对象，对象检测器基于存储在存储器中的训练数据图像集合来检测对象。

6. 发明授权

US08498448B2 Multi-view object detection using appearance model transfer from similar scenes 有权
公开(公告)号：US08498448B2
公开(公告)日：2013-07-30
申请号：US13183760
申请日：2011-07-15
申请人： Rogerio S. Feris , Sharathchandra U. Pankanti , Behjat Siddiquie
发明人： Rogerio S. Feris , Sharathchandra U. Pankanti , Behjat Siddiquie
IPC分类号： G06K9/00 , H04N5/225
CPC分类号： G06K9/00718 , G06K9/00771 , G06K9/00785 , G06K9/6218 , G06T7/246 , G06T7/73 , G06T2207/10016 , G06T2207/20081
摘要： View-specific object detectors are learned as a function of scene geometry and object motion patterns. Motion directions are determined for object images extracted from a training dataset and collected from different camera scene viewpoints. The object images are categorized into clusters as a function of similarities of their determined motion directions, the object images in each cluster are acquired from the same camera scene viewpoint. Zenith angles are estimated for object image poses in the clusters relative to a position of a horizon in the cluster camera scene viewpoint, and azimuth angles of the poses as a function of a relation of the determined motion directions of the clustered images to the cluster camera scene viewpoint. Detectors are thus built for recognizing objects in input video, one for each of the clusters, and associated with the estimated zenith angles and azimuth angles of the poses of the respective clusters.

7. 发明申请

US20130016877A1 MULTI-VIEW OBJECT DETECTION USING APPEARANCE MODEL TRANSFER FROM SIMILAR SCENES 有权
公开(公告)号：US20130016877A1
公开(公告)日：2013-01-17
申请号：US13183760
申请日：2011-07-15
申请人： Rogerio S. Feris , Sharathchandra U. Pankanti , Behjat Siddiquie
发明人： Rogerio S. Feris , Sharathchandra U. Pankanti , Behjat Siddiquie
IPC分类号： G06K9/62 , G06K9/00
CPC分类号： G06K9/00718 , G06K9/00771 , G06K9/00785 , G06K9/6218 , G06T7/246 , G06T7/73 , G06T2207/10016 , G06T2207/20081
摘要： View-specific object detectors are learned as a function of scene geometry and object motion patterns. Motion directions are determined for object images extracted from a training dataset and collected from different camera scene viewpoints. The object images are categorized into clusters as a function of similarities of their determined motion directions, the object images in each cluster are acquired from the same camera scene viewpoint. Zenith angles are estimated for object image poses in the clusters relative to a position of a horizon in the cluster camera scene viewpoint, and azimuth angles of the poses as a function of a relation of the determined motion directions of the clustered images to the cluster camera scene viewpoint. Detectors are thus built for recognizing objects in input video, one for each of the clusters, and associated with the estimated zenith angles and azimuth angles of the poses of the respective clusters.

8. 发明授权

US08917934B2 Multi-cue object detection and analysis 有权
标题翻译：多提示对象检测和分析
公开(公告)号：US08917934B2
公开(公告)日：2014-12-23
申请号：US13523074
申请日：2012-06-14
申请人： Ankur Datta , Rogerio S. Feris , Sharathchandra U. Pankanti , Xiaoyu Wang
发明人： Ankur Datta , Rogerio S. Feris , Sharathchandra U. Pankanti , Xiaoyu Wang
IPC分类号： G06K9/00 , G06K9/34 , H04N1/40 , H04N1/46
CPC分类号： G06T7/11 , G06K9/00536 , G06K9/00785 , G06K9/3241 , G06K9/38 , G06K9/4642 , G06T7/13 , G06T7/194 , G06T2207/10016 , G06T2207/10024 , G06T2207/20021 , G06T2207/30236
摘要： Foreground objects of interest are distinguished from a background model by dividing a region of interest of a video data image into a grid array of individual cells that are each smaller than that a foreground object of interest. More particularly, image data of the foreground object of interest spans a contiguous plurality of the cells. Each of the cells are labeled as foreground if accumulated edge energy within the cell meets an edge energy threshold, if color intensities for different colors within each cell differ by a color intensity differential threshold, or as a function of combinations of said determinations in view of one or more combination rules.
摘要翻译：将感兴趣的前景物体与背景模型区分开，将视频数据图像的感兴趣区域划分为各自小于感兴趣的前景对象的各个单元格的网格阵列。更具体地，感兴趣的前景对象的图像数据跨越连续的多个单元。如果每个单元内的不同颜色的颜色强度与颜色强度差异阈值相差，或者作为所述确定的组合的函数，则单元格内的累积边缘能量满足边缘能量阈值时，每个单元格被标记为前景一个或多个组合规则。

9. 发明申请

US20130336581A1 MULTI-CUE OBJECT DETECTION AND ANALYSIS 有权
标题翻译：多目标对象检测与分析
公开(公告)号：US20130336581A1
公开(公告)日：2013-12-19
申请号：US13523074
申请日：2012-06-14
申请人： Ankur Datta , Rogerio S. Feris , Sharathchandra U. Pankanti , Xiaoyu Wang
发明人： Ankur Datta , Rogerio S. Feris , Sharathchandra U. Pankanti , Xiaoyu Wang
IPC分类号： G06K9/46 , G06K9/68
CPC分类号： G06T7/11 , G06K9/00536 , G06K9/00785 , G06K9/3241 , G06K9/38 , G06K9/4642 , G06T7/13 , G06T7/194 , G06T2207/10016 , G06T2207/10024 , G06T2207/20021 , G06T2207/30236
摘要： Foreground objects of interest are distinguished from a background model by dividing a region of interest of a video data image into a grid array of individual cells that are each smaller than that a foreground object of interest. More particularly, image data of the foreground object of interest spans a contiguous plurality of the cells. Each of the cells are labeled as foreground if accumulated edge energy within the cell meets an edge energy threshold, if color intensities for different colors within each cell differ by a color intensity differential threshold, or as a function of combinations of said determinations in view of one or more combination rules.
摘要翻译：将感兴趣的前景物体与背景模型区分开，将视频数据图像的感兴趣区域划分为各自小于感兴趣的前景对象的各个单元格的网格阵列。更具体地，感兴趣的前景对象的图像数据跨越连续的多个单元。如果每个单元内的不同颜色的颜色强度与颜色强度差异阈值相差，或者作为所述确定的组合的函数，则单元格内的累积边缘能量满足边缘能量阈值时，每个单元格被标记为前景一个或多个组合规则。

10. 发明申请

US20140098989A1 MULTI-CUE OBJECT ASSOCIATION 有权
标题翻译：多目标对象协会
公开(公告)号：US20140098989A1
公开(公告)日：2014-04-10
申请号：US13645831
申请日：2012-10-05
申请人： Ankur Datta , Rogerio S. Feris , Sharathchandra U. Pankanti , Yun Zhai
发明人： Ankur Datta , Rogerio S. Feris , Sharathchandra U. Pankanti , Yun Zhai
IPC分类号： G06K9/00
CPC分类号： G06K9/00778 , G06K9/38 , G06K2209/23 , G06T7/248 , G06T2207/10016 , G06T2207/30236
摘要： Multiple discrete objects within a scene image captured by a single camera track are distinguished as un-labeled from a background model within a first frame of a video data input. Object position and object appearance and/or object size attributes are determined for each of the blobs, and costs determined to assign to existing blobs of existing object tracks as a function of the determined attributes and combined to generate respective combination costs. The un-labeled object blob that has a lowest combined cost of association with any of the existing object tracks is labeled with the label of that track having the lowest combined cost, said track is removed from consideration for labeling remaining un-labeled object blobs, and the process iteratively repeated until each of the track labels have been used to label one of the un-labeled blobs.
摘要翻译：由单个摄像机轨道拍摄的场景图像内的多个离散对象被区分为视频数据输入的第一帧内的背景模型的未标记。确定每个斑点的对象位置和对象外观和/或对象大小属性，以及确定为根据所确定的属性分配给现有对象轨道的现有块的成本并组合以生成相应的组合成本。与任何现有对象轨道具有最低组合成本的未标记对象斑点用具有最低组合成本的该轨道的标签进行标记，所述轨道被从考虑中去除以标记剩余的未标记对象斑点，并且迭代地重复该过程，直到每个轨道标签已被用于标记未标记的一个斑点。

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