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

US08724904B2 Anomaly detection in images and videos 失效
标题翻译：图像和视频中的异常检测
公开(公告)号：US08724904B2
公开(公告)日：2014-05-13
申请号：US13280896
申请日：2011-10-25
申请人： Yuichi Fujiki , Norman Haas , Ying Li , Charles A. Otto , Balamanohar Paluri , Sharathchandra Pankanti
发明人： Yuichi Fujiki , Norman Haas , Ying Li , Charles A. Otto , Balamanohar Paluri , Sharathchandra Pankanti
IPC分类号： G06K9/46
CPC分类号： G06K9/6284 , B61L23/044 , B61L23/047 , B61L23/048 , G06K9/6218
摘要： A system, method, and computer program product for detecting anomalies in an image. In an example embodiment the method includes partitioning each image of a set of images into a plurality of image local units. The method further includes clustering all local units in the image set into clusters, and consequently assigning a class label to each local unit based on the clustering results. The local units with identical class labels having at least one substantially related image feature. Further, the method includes assigning a weight to each of the local units based on a variation of the class labels across all images in a set of images. The method further includes performing a clustering over all images in the set by using a distance metric that takes the learned weight of each local unit into account, then determining the images that belong to minorities of the clusters as anomalies.
摘要翻译：一种用于检测图像异常的系统，方法和计算机程序产品。在示例实施例中，该方法包括将一组图像的每个图像划分为多个图像本地单元。该方法还包括将图像集中的所有局部单元聚类成群集，并且因此基于聚类结果将类标签分配给每个本地单元。具有相同类别标签的本地单元具有至少一个基本上相关的图像特征。此外，该方法包括基于一组图像中的所有图像上的类别标签的变化来为每个本地单元分配权重。该方法还包括通过使用考虑每个本地单元的学习权重的距离度量来执行集合中的所有图像的聚类，然后将属于集群的少数群体的图像确定为异常。

2. 发明申请

US20130101221A1 ANOMALY DETECTION IN IMAGES AND VIDEOS 失效
标题翻译：图像和视频中的异常检测
公开(公告)号：US20130101221A1
公开(公告)日：2013-04-25
申请号：US13280896
申请日：2011-10-25
申请人： Yuichi Fujiki , Norman Haas , Ying Li , Charles A. Otto , Balamanohar Paluri , Sharathchandra Pankanti
发明人： Yuichi Fujiki , Norman Haas , Ying Li , Charles A. Otto , Balamanohar Paluri , Sharathchandra Pankanti
IPC分类号： G06K9/62 , G06K9/46
CPC分类号： G06K9/6284 , B61L23/044 , B61L23/047 , B61L23/048 , G06K9/6218
摘要： A system, method, and computer program product for detecting anomalies in an image. In an example embodiment the method includes partitioning each image of a set of images into a plurality of image local units. The method further includes clustering all local units in the image set into clusters, and consequently assigning a class label to each local unit based on the clustering results. The local units with identical class labels having at least one substantially related image feature. Further, the method includes assigning a weight to each of the local units based on a variation of the class labels across all images in a set of images. The method further includes performing a clustering over all images in the set by using a distance metric that takes the learned weight of each local unit into account, then determining the images that belong to minorities of the clusters as anomalies.
摘要翻译：一种用于检测图像异常的系统，方法和计算机程序产品。在示例实施例中，该方法包括将一组图像的每个图像划分为多个图像本地单元。该方法还包括将图像集中的所有局部单元聚类成群集，并且因此基于聚类结果将类标签分配给每个本地单元。具有相同类别标签的本地单元具有至少一个基本上相关的图像特征。此外，该方法包括基于一组图像中的所有图像上的类别标签的变化来为每个本地单元分配权重。该方法还包括通过使用考虑每个本地单元的学习权重的距离度量来执行集合中的所有图像的聚类，然后将属于集群的少数群体的图像确定为异常。

3. 发明申请

US20120237081A1 ANOMALOUS PATTERN DISCOVERY 失效
标题翻译：异常图案发现
公开(公告)号：US20120237081A1
公开(公告)日：2012-09-20
申请号：US13049032
申请日：2011-03-16
申请人： Ankur Datta , Balamanohar Paluri , Sharathchandra U. Pankanti , Yun Zhai
发明人： Ankur Datta , Balamanohar Paluri , Sharathchandra U. Pankanti , Yun Zhai
IPC分类号： G06K9/00
CPC分类号： G06K9/00778 , G06K9/00785 , G06K9/6284
摘要： A trajectory of movement of an object is tracked in a video data image field that is partitioned into a plurality of different grids. Global image features from video data relative to the trajectory are extracted and compared to a learned trajectory model to generate a global anomaly detection confidence decision value as a function of fitting to the learned trajectory model. Local image features are also extracted for each of the image field grids that include object trajectory, which are compared to learned feature models for the grids to generate local anomaly detection confidence decisions for each grid as a function of fitting to the learned feature models for the grids. The global anomaly detection confidence decision value and the local anomaly detection confidence decision values for the grids are into a fused anomaly decision with respect to the tracked object.
摘要翻译：在被划分成多个不同网格的视频数据图像字段中跟踪对象的移动轨迹。提取视频数据相对于轨迹的全局图像特征，并将其与已学习的轨迹模型进行比较，以生成与学习轨迹模型拟合的函数的全局异常检测置信判定值。对于包括对象轨迹的每个图像场网格也提取局部图像特征，其与用于网格的学习特征模型进行比较，以针对每个网格生成局部异常检测置信决定，作为对于学习特征模型的拟合的函数，网格全局异常检测置信度判定值和网格的局部异常检测置信判定值相对于跟踪对象进入融合异常判定。

4. 发明授权

US09158976B2 Efficient retrieval of anomalous events with priority learning 有权
标题翻译：优先学习有效地检索异常事件
公开(公告)号：US09158976B2
公开(公告)日：2015-10-13
申请号：US13110331
申请日：2011-05-18
申请人： Ankur Datta , Balamanohar Paluri , Sharathchandra U. Pankanti , Yun Zhai
发明人： Ankur Datta , Balamanohar Paluri , Sharathchandra U. Pankanti , Yun Zhai
IPC分类号： G08B13/196 , G06K9/00 , G06F19/24 , G06K9/62
CPC分类号： G06K9/00771 , G06F19/24 , G06K9/6284 , G06T7/251 , G08B13/19606
摘要： Local models learned from anomaly detection are used to rank detected anomalies. The local models include image feature values extracted from an image field of video image data with respect to different predefined spatial and temporal local units, wherein anomaly results are determined by failures to fit to applied anomaly detection module local models. Image features values extracted from the image field local units associated with anomaly results are normalized, and image feature values extracted from the image field local units are clustered. Weights for anomaly results are learned as a function of the relations of the normalized extracted image feature values to the clustered image feature values. The normalized values are multiplied by the learned weights to generate ranking values to rank the anomalies.
摘要翻译：从异常检测中获取的局部模型用于对检测到的异常进行排序。本地模型包括从视频图像数据的图像字段提取的关于不同的预定空间和时间局部单位的图像特征值，其中异常结果由适合于应用的异常检测模块本地模型的失败确定。从与异常结果相关联的图像场本地单元提取的图像特征值被归一化，并且从图像场本地单元提取的图像特征值被聚类。根据归一化提取的图像特征值与聚类图像特征值的关系来学习异常结果的权重。归一化值乘以学习权重以产生排序值以排除异常。

5. 发明授权

US08660368B2 Anomalous pattern discovery 失效
标题翻译：异常模式发现
公开(公告)号：US08660368B2
公开(公告)日：2014-02-25
申请号：US13049032
申请日：2011-03-16
申请人： Ankur Datta , Balamanohar Paluri , Sharathchandra U. Pankanti , Yun Zhai
发明人： Ankur Datta , Balamanohar Paluri , Sharathchandra U. Pankanti , Yun Zhai
IPC分类号： G06K9/68
CPC分类号： G06K9/00778 , G06K9/00785 , G06K9/6284
摘要： A trajectory of movement of an object is tracked in a video data image field that is partitioned into a plurality of different grids. Global image features from video data relative to the trajectory are extracted and compared to a learned trajectory model to generate a global anomaly detection confidence decision value as a function of fitting to the learned trajectory model. Local image features are also extracted for each of the image field grids that include object trajectory, which are compared to learned feature models for the grids to generate local anomaly detection confidence decisions for each grid as a function of fitting to the learned feature models for the grids. The global anomaly detection confidence decision value and the local anomaly detection confidence decision values for the grids are into a fused anomaly decision with respect to the tracked object.
摘要翻译：在被划分成多个不同网格的视频数据图像字段中跟踪对象的移动轨迹。提取视频数据相对于轨迹的全局图像特征，并将其与已学习的轨迹模型进行比较，以生成与学习轨迹模型拟合的函数的全局异常检测置信判定值。对于包括对象轨迹的每个图像场网格也提取局部图像特征，其与用于网格的学习特征模型进行比较，以针对每个网格生成局部异常检测置信决定，作为对于学习特征模型的拟合的函数，网格全局异常检测置信度判定值和网格的局部异常检测置信判定值相对于跟踪对象进入融合异常判定。

6. 发明申请

US20120294511A1 EFFICIENT RETRIEVAL OF ANOMALOUS EVENTS WITH PRIORITY LEARNING 有权
标题翻译：高效地检索异常事件
公开(公告)号：US20120294511A1
公开(公告)日：2012-11-22
申请号：US13110331
申请日：2011-05-18
申请人： Ankur Datta , Balamanohar Paluri , Sharathchandra U. Pankanti , Yun Zhai
发明人： Ankur Datta , Balamanohar Paluri , Sharathchandra U. Pankanti , Yun Zhai
IPC分类号： G06K9/62
CPC分类号： G06K9/00771 , G06F19/24 , G06K9/6284 , G06T7/251 , G08B13/19606
摘要： Local models learned from anomaly detection are used to rank detected anomalies. The local models include image feature values extracted from an image field of video image data with respect to different predefined spatial and temporal local units, wherein anomaly results are determined by failures to fit to applied anomaly detection module local models. Image features values extracted from the image field local units associated with anomaly results are normalized, and image feature values extracted from the image field local units are clustered. Weights for anomaly results are learned as a function of the relations of the normalized extracted image feature values to the clustered image feature values. The normalized values are multiplied by the learned weights to generate ranking values to rank the anomalies.
摘要翻译：从异常检测中获取的局部模型用于对检测到的异常进行排序。本地模型包括从视频图像数据的图像字段提取的关于不同的预定空间和时间局部单位的图像特征值，其中异常结果由适合于应用的异常检测模块本地模型的失败确定。从与异常结果相关联的图像场本地单元提取的图像特征值被归一化，并且从图像场本地单元提取的图像特征值被聚类。根据归一化提取的图像特征值与聚类图像特征值的关系来学习异常结果的权重。归一化值乘以学习权重以产生排序值以排除异常。

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