-
公开(公告)号：US09002060B2
公开(公告)日：2015-04-07
申请号：US13535409
申请日：2012-06-28
CPC分类号： G06K9/00771 , G06K9/00718 , G06K9/00758 , G06K9/6215 , G06K9/6218 , G06K9/6256 , G06K9/6262 , G06K2009/00738
摘要： Automatic object retrieval from input video is based on learned, complementary detectors created for each of a plurality of different motionlet clusters. The motionlet clusters are partitioned from a dataset of training vehicle images as a function of determining that vehicles within each of the scenes of the images in each cluster share similar two-dimensional motion direction attributes within their scenes. To train the complementary detectors, a first detector is trained on motion blobs of vehicle objects detected and collected within each of the training dataset vehicle images within the motionlet cluster via a background modeling process; a second detector is trained on each of the training dataset vehicle images within the motionlet cluster that have motion blobs of the vehicle objects but are misclassified by the first detector; and the training repeats until all of the training dataset vehicle images have been eliminated as false positives or correctly classified.
摘要翻译： 从输入视频自动对象检索是基于为多个不同的运动集群中的每一个创建的学习的互补检测器。 作为确定每个群集中的图像的每个场景内的车辆在其场景内共享类似的二维运动方向属性的函数的函数，将运动群集从训练车辆图像的数据集分割。 训练互补检测器，对第一检测器进行训练，以通过背景建模过程在运动组内的每个训练数据集车辆图像内检测和收集的车辆物体的运动斑点进行训练; 对具有车辆对象的运动斑点但由第一检测器错误分类的运动集群内的训练数据集车辆图像上的每一个训练第二检测器; 并且训练重复，直到所有训练数据集车辆图像已被消除为假阳性或正确分类为止。
-
公开(公告)号：US20140003708A1
公开(公告)日：2014-01-02
申请号：US13535409
申请日：2012-06-28
IPC分类号： G06K9/62
CPC分类号： G06K9/00771 , G06K9/00718 , G06K9/00758 , G06K9/6215 , G06K9/6218 , G06K9/6256 , G06K9/6262 , G06K2009/00738
摘要： Automatic object retrieval from input video is based on learned, complementary detectors created for each of a plurality of different motionlet clusters. The motionlet clusters are partitioned from a dataset of training vehicle images as a function of determining that vehicles within each of the scenes of the images in each cluster share similar two-dimensional motion direction attributes within their scenes. To train the complementary detectors, a first detector is trained on motion blobs of vehicle objects detected and collected within each of the training dataset vehicle images within the motionlet cluster via a background modeling process; a second detector is trained on each of the training dataset vehicle images within the motionlet cluster that have motion blobs of the vehicle objects but are misclassified by the first detector; and the training repeats until all of the training dataset vehicle images have been eliminated as false positives or correctly classified.
摘要翻译： 从输入视频自动对象检索是基于为多个不同的运动集群中的每一个创建的学习的互补检测器。 作为确定每个群集中的图像的每个场景内的车辆在其场景内共享类似的二维运动方向属性的函数的函数，将运动群集从训练车辆图像的数据集分割。 训练互补检测器，对第一检测器进行训练，以通过背景建模过程在运动组内的每个训练数据集车辆图像内检测和收集的车辆物体的运动斑点进行训练; 对具有车辆对象的运动斑点但由第一检测器错误分类的运动集群内的训练数据集车辆图像上的每一个训练第二检测器; 并且训练重复，直到所有训练数据集车辆图像已被消除为假阳性或正确分类为止。
-
公开(公告)号：US20120281873A1
公开(公告)日：2012-11-08
申请号：US13101401
申请日：2011-05-05
IPC分类号： G06K9/00
CPC分类号： G06T7/20 , G06K9/00208 , G06T7/251 , G06T13/20 , G06T17/00 , G06T19/006
摘要： A moving object detected and tracked within a field of view environment of a 2D data feed of a calibrated video camera is represented by a 3D model through localizing a centroid of the object and determining an intersection with a ground-plane within the field of view environment. An appropriate 3D mesh-based volumetric model for the object is initialized by using a back-projection of a corresponding 2D image as a function of the centroid and the determined ground-plane intersection. Nonlinear dynamics of a tracked motion path of the object are represented as a collection of different local linear models. A texture of the object is projected onto the 3D model, and 2D tracks of the object are upgraded to 3D motion to drive the 3D model by learning a weighted combination of the different local linear models that minimizes an image re-projection error of model movement.
摘要翻译： 在校准摄像机的2D数据馈送的视野环境内检测和跟踪的移动物体由3D模型表示，其通过定位对象的质心并确定视场环境内的接地平面的交点 。 通过使用对应的2D图像的反投影作为质心和确定的地面交点的函数来初始化用于对象的适当的基于3D网格的体积模型。 对象的跟踪运动路径的非线性动力学被表示为不同局部线性模型的集合。 将对象的纹理投影到3D模型上，并且将对象的2D轨迹升级到3D运动，以通过学习不同局部线性模型的加权组合来驱动3D模型，从而最小化模型运动的图像重新投影误差 。
-
公开(公告)号：US08498448B2
公开(公告)日：2013-07-30
申请号：US13183760
申请日：2011-07-15
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.
-
公开(公告)号：US20120274805A1
公开(公告)日：2012-11-01
申请号：US13097435
申请日：2011-04-29
IPC分类号： H04N9/73
摘要： Methods and apparatus are provided for color correction of images. One or more colors in an image obtained from a static video camera are corrected by obtaining one or more historical background models from one or more prior images obtained from the static video camera; obtaining a live background model and a live foreground model from one or more current images obtained from the static video camera; generating a reference image from the one or more historical background models; and processing the reference image, the live background model, and the live foreground model to generate a set of color corrected foreground objects in the image. The set of color corrected foreground objects is optionally processed to classify a color of at least one of the foreground objects.
摘要翻译： 为图像的颜色校正提供了方法和装置。 通过从从静态摄像机获得的一个或多个先前图像获得一个或多个历史背景模型来校正从静态摄像机获得的图像中的一种或多种颜色; 从静态摄像机获得的一个或多个当前图像获得实况背景模型和实况前景模型; 从所述一个或多个历史背景模型生成参考图像; 以及处理参考图像，实况背景模型和实况前景模型以生成图像中的一组颜色校正的前景对象。 可选地处理该组色彩校正的前景对象以对至少一个前景对象的颜色进行分类。
-
公开(公告)号：US20130016877A1
公开(公告)日：2013-01-17
申请号：US13183760
申请日：2011-07-15
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.
-
公开(公告)号：US08824791B2
公开(公告)日：2014-09-02
申请号：US13097435
申请日：2011-04-29
摘要： Methods and apparatus are provided for color correction of images. One or more colors in an image obtained from a static video camera are corrected by obtaining one or more historical background models from one or more prior images obtained from the static video camera; obtaining a live background model and a live foreground model from one or more current images obtained from the static video camera; generating a reference image from the one or more historical background models; and processing the reference image, the live background model, and the live foreground model to generate a set of color corrected foreground objects in the image. The set of color corrected foreground objects is optionally processed to classify a color of at least one of the foreground objects.
摘要翻译： 为图像的颜色校正提供了方法和装置。 通过从从静态摄像机获得的一个或多个先前图像获得一个或多个历史背景模型来校正从静态摄像机获得的图像中的一种或多种颜色; 从静态摄像机获得的一个或多个当前图像获得实况背景模型和实况前景模型; 从所述一个或多个历史背景模型生成参考图像; 以及处理参考图像，实况背景模型和实况前景模型以生成图像中的一组颜色校正的前景对象。 可选地处理该组色彩校正的前景对象以对至少一个前景对象的颜色进行分类。
-
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
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。
-
公开(公告)号：US09158976B2
公开(公告)日：2015-10-13
申请号：US13110331
申请日：2011-05-18
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。
-
公开(公告)号：US08751414B2
公开(公告)日：2014-06-10
申请号：US13100868
申请日：2011-05-04
CPC分类号： G06F11/0751 , G06F11/3058 , G06F11/3082
摘要： A method, data processing system, and computer program product for identifying abnormalities in data. A model representing a plurality of modes for an activity generated from training data is retrieved. The training data includes a first plurality of measurements of a first performance of the activity over a period of time. Each of the plurality of modes is identified as one of normal and abnormal. Activity data including a second plurality of measurements of a second performance of the activity is received. A portion of the activity data is compared with the plurality of modes in the model. A notification of an abnormality in the second performance of the activity is generated in response to an identification that the portion of the activity data matches a mode in the plurality of modes identified as abnormal. Confirmation of the abnormality is requested via a user interface.
摘要翻译： 一种用于识别数据异常的方法，数据处理系统和计算机程序产品。 检索表示从训练数据生成的活动的多个模式的模型。 训练数据包括在一段时间内第一次执行活动的测量。 多个模式中的每一个被标识为正常和异常之一。 接收包括活动的第二次执行的第二多个测量的活动数据。 将活动数据的一部分与模型中的多个模式进行比较。 响应于识别出活动数据的一部分与被识别为异常的多个模式中的模式相匹配的标识来生成第二次活动的异常的通知。 通过用户界面要求确认异常。
-
-
-
-
-
-
-
-
-
搜索结果
98 条记录 (耗时 0.028 秒)
